Method and equipment for determining channel state information acquisition scheme

Abstract

The present application relates to a method for determining a channel state information (CSI) acquisition scheme, a terminal device and a network device, the method comprising: a network device determining a channel state information (CSI) acquisition scheme corresponding to communication scenario information, the communication scenario information comprising a scenario to which a wireless communication environment between the network device and the terminal device belongs. According to the embodiment of the invention, the corresponding CSI acquisition scheme can be obtained based on the communication scene information, and the CSI acquisition scheme can be better adapted to the wireless communication environment, so that the CSI acquisition scheme achieves better performance.

Description

Method and device for determining channel state information acquisition scheme Technical Field

[0001] The present application relates to the field of communications, and more specifically, to a method and device for determining a channel state information acquisition scheme. Background Art

[0002] Multiple-Input Multiple-Output (MIMO) technology plays a vital role in Long Term Evolution (LTE) and New Radio (NR) systems, and will continue to be a key enabling technology in future next-generation wireless communication systems. The signal transmission performance of MIMO depends heavily on the accuracy of the channel-state information (CSI) acquired by the transmitter.

[0003] Summary of the Invention

[0004] The embodiments of the present application provide a method and device for determining a channel state information acquisition scheme, which can make the channel state information acquisition scheme more adaptable to the wireless communication environment.

[0005] An embodiment of the present application provides a method for determining a channel state information acquisition scheme, including: a network device determines a CSI acquisition scheme corresponding to communication scenario information, and the communication scenario information includes the scenario to which the wireless communication environment between the network device and the terminal device belongs.

[0006] The present invention provides a method for determining a channel state information acquisition solution, including:

[0007] The terminal device determines the CSI acquisition scheme corresponding to the communication scenario information, where the communication scenario information includes the scenario to which the wireless communication environment between the terminal device and the network device belongs.

[0008] An embodiment of the present application provides a network device, including:

[0009] The first processing unit is used to determine a CSI acquisition scheme corresponding to the communication scenario information, where the communication scenario information includes the scenario to which the wireless communication environment between the network device and the terminal device belongs.

[0010] An embodiment of the present application provides a terminal device, including:

[0011] The first processing unit is used to determine the CSI acquisition scheme corresponding to the communication scenario information, where the communication scenario information includes the scenario to which the wireless communication environment between the terminal device and the network device belongs.

[0012] An embodiment of the present application provides a network device, comprising a processor and a memory, wherein the memory is used to store a computer program, and the processor is used to call and execute the computer program stored in the memory, so that the network device executes the above-mentioned method for determining a channel state information acquisition scheme.

[0013] An embodiment of the present application provides a terminal device, comprising a processor and a memory, wherein the memory is used to store a computer program, and the processor is used to call and execute the computer program stored in the memory, so that the terminal device executes the above-mentioned method for determining the channel state information acquisition scheme.

[0014] The present invention provides a chip for implementing the above-mentioned method for determining a channel state information acquisition scheme. Specifically, the chip includes a processor for calling and executing a computer program from a memory, so that a device equipped with the chip executes the above-mentioned method for determining a channel state information acquisition scheme.

[0015] An embodiment of the present application provides a computer-readable storage medium for storing a computer program. When the computer program is executed by a device, the device executes the above-mentioned method for determining the channel state information acquisition scheme.

[0016] An embodiment of the present application provides a computer program product, including computer program instructions, which enable a computer to execute the above-mentioned method for determining a channel state information acquisition scheme.

[0017] An embodiment of the present application provides a computer program, which, when executed on a computer, enables the computer to execute the above-mentioned method for determining the channel state information acquisition scheme.

[0018] In the embodiment of the present application, a corresponding CSI acquisition scheme can be obtained based on the communication scenario information, and the CSI acquisition scheme can be better adapted to the wireless communication environment, so that the CSI acquisition scheme can achieve better performance. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] FIG1 is a schematic diagram of an application scenario according to an embodiment of the present application.

[0020] FIG2 is a schematic diagram of the basic process of CSI acquisition.

[0021] FIG3 is a schematic diagram of the basic architecture of CSI feedback.

[0022] FIG4 is a schematic diagram of an AI-based CSI feedback solution.

[0023] FIG5 is a schematic flowchart of a method for determining a channel state information acquisition solution according to an embodiment of the present application.

[0024] FIG6 is a schematic flowchart of a method for determining a channel state information acquisition solution according to another embodiment of the present application.

[0025] FIG7 is a schematic flowchart of a method for determining a channel state information acquisition solution according to another embodiment of the present application.

[0026] FIG8 is a schematic flowchart of a method for determining a channel state information acquisition solution according to another embodiment of the present application.

[0027] FIG9 is a schematic flowchart of a method for determining a channel state information acquisition solution according to another embodiment of the present application.

[0028] FIG10 is a schematic flowchart of a method for determining a channel state information acquisition solution according to another embodiment of the present application.

[0029] FIG11 is a schematic flowchart of a method for determining a channel state information acquisition solution according to another embodiment of the present application.

[0030] FIG12 is a schematic flowchart of a method for determining a channel state information acquisition solution according to another embodiment of the present application.

[0031] FIG13 is a schematic flowchart of a method for determining a channel state information acquisition solution according to another embodiment of the present application.

[0032] FIG14 is a schematic diagram of a base station performing scene recognition based on uplink channel information.

[0033] FIG15 is a schematic diagram of a base station performing scene recognition based on CSI information fed back by a UE.

[0034] FIG16 is a schematic diagram of an exemplary model adaptation process.

[0035] FIG17a and FIG17b are schematic diagrams of the processing method after the UE performs scene recognition.

[0036] FIG18 is a schematic diagram of a UE performing scene recognition based on downlink channel measurement results.

[0037] FIG19 is a schematic diagram of channel estimation and CSI feedback based on the AI ​​model.

[0038] FIG20 is a schematic block diagram of a network device according to an embodiment of the present application.

[0039] FIG21 is a schematic block diagram of a network device according to another embodiment of the present application.

[0040] Figure 22 is a schematic block diagram of a terminal device according to an embodiment of the present application.

[0041] Figure 23 is a schematic block diagram of a terminal device according to another embodiment of the present application.

[0042] Figure 24 is a schematic block diagram of a communication device according to an embodiment of the present application.

[0043] Figure 25 is a schematic block diagram of a chip according to an embodiment of the present application.

[0044] Figure 26 is a schematic block diagram of a communication system according to an embodiment of the present application. DETAILED DESCRIPTION

[0045] The technical solutions in the embodiments of the present application will be described below in conjunction with the drawings in the embodiments of the present application.

[0046] 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.

[0047] 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.

[0048] In one embodiment, the communication system in the embodiment of the present application can be applied to a carrier aggregation (CA) scenario, a dual connectivity (DC) scenario, and a standalone (SA) networking scenario.

[0049] In one embodiment, the communication system in the embodiment of the present application can be applied to an unlicensed spectrum, wherein 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, wherein the authorized spectrum can also be considered as an unshared spectrum.

[0050] 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.

[0051] The terminal device can be a station (STAION, 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.

[0052] 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.).

[0053] 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.

[0054] 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.

[0055] 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.

[0056] 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.

[0057] 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.

[0058] FIG1 exemplarily illustrates a communication system 100. The communication system includes a network device 110 and two terminal devices 120. In one embodiment, the communication system 100 may include multiple network devices 110, and each network device 110 may include a different number of terminal devices 120 within its coverage area, which is not limited in this embodiment of the present application.

[0059] In one embodiment, the communication system 100 may further include other network entities such as a Mobility Management Entity (MME) and an Access and Mobility Management Function (AMF), which is not limited in this embodiment of the present application.

[0060] Among them, the network equipment may include access network equipment and core network equipment. That is, the wireless communication system also includes multiple core networks for communicating with the access network equipment. The access network equipment can be an evolutionary base station (evolutional node B, abbreviated as eNB or e-NodeB) macro base station, micro base station (also called "small base station"), pico base station, access point (AP), transmission point (TP) or new generation base station (new generation Node B, gNodeB), etc. in a long-term evolution (LTE) system, a next-generation (mobile communication system) (next radio, NR) system or an authorized auxiliary access long-term evolution (LAA-LTE) system.

[0061] It should be understood that in the embodiments of the present application, a device having a communication function in a network / system may be referred to as a communication device. Taking the communication system shown in Figure 1 as an example, the communication device may include a network device and a terminal device having a communication function. The network device and the terminal device may be specific devices in the embodiments of the present application and will not be described in detail here. The communication device may also include other devices in the communication system, such as a network controller, a mobility management entity, and other network entities, which are not limited in the embodiments of the present application.

[0062] 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.

[0063] 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.

[0064] 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.

[0065] To facilitate understanding of the technical solutions of the embodiments of the present application, the relevant technologies of the embodiments of the present application are described below. The following relevant technologies can be arbitrarily combined with the technical solutions of the embodiments of the present application as optional solutions, and they all fall within the protection scope of the embodiments of the present application.

[0066] 1. CSI acquisition mechanism in cellular communication system.

[0067] In cellular communication systems, the specific method by which a base station acquires CSI varies depending on the duplex communication mode used. Specifically, in time-division duplex (TDD) mode, since both the uplink and downlink operate on the same frequency, the base station can leverage channel reciprocity between the uplink and downlink channels to acquire CSI. This means that the base station can directly estimate CSI, which can be used to guide downlink data transmission, based on the uplink reference signal (RS) (such as the sounding reference signal (SRS)) transmitted by the user equipment (UE). In contrast, in frequency-division duplex (FDD) mode, since the uplink and downlink operate on different frequencies, the base station cannot leverage channel reciprocity to directly estimate downlink CSI based on the uplink RS, making CSI acquisition much more complex. First, the base station configures and transmits reference signals for the UE to perform CSI measurements, such as the synchronization signal and physical broadcast channel (PBCH) block (SSB) or the CSI-RS. The UE then completes channel estimation by measuring the reference signal and feeds back CSI information to the base station, allowing the base station to configure a reasonable and efficient data transmission method based on the current channel conditions.

[0068] In the NR standard, multiple codebooks are standardized to enable the UE to feedback CSI to the base station. The UE will find the codeword with the highest match for the CSI to be fed back from the codebook and feed back the corresponding index to the base station via the uplink. The base station can restore the CSI through the index based on the same codebook. The basic process of CSI acquisition under FDD is shown in Figure 2: The base station UE sends configuration information to configure the reference signal required for CSI acquisition, parameters to be fed back, etc. The base station sends a reference signal to the UE for CSI measurement. After the UE performs channel estimation based on the received reference signal, it obtains the CSI feedback amount based on the estimated channel information. The UE sends feedback information to the base station. The base station restores the CSI based on the feedback information and configures the data transmission method based on the CSI.

[0069] 2. CSI feedback method based on artificial intelligence (AI).

[0070] Figure 3 shows the basic architecture for implementing high-precision CSI feedback in FDD mode using AI technology. The UE can use a pre-trained neural network encoder to convert the acquired CSI information into indication information (bitstream) that can be fed back via the uplink channel. After receiving this indication information, the base station can use the corresponding pre-trained neural network decoder to restore it 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.

[0071] For traditional CSI feedback schemes in FDD mode, current wireless communication systems primarily rely on theoretical modeling of actual communication environments to construct sufficiently sophisticated codebooks. However, as requirements 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. New approaches and methods are necessary, such as combining data-driven AI technology with traditional theories and system design methods, to overcome existing bottlenecks and further enhance wireless system performance.

[0072] For example, the AI-based CSI feedback 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.

[0073] Most current AI-based CSI feedback solutions consider directly using models trained offline for online CSI compression feedback and recovery. However, because AI-based CSI feedback solutions are data-driven, they typically achieve excellent performance in familiar scenarios (e.g., scenarios the AI ​​model encountered during training or similar scenarios), but cannot guarantee performance in unfamiliar scenarios, resulting in poor generalization. Good generalization is essential for AI-based CSI feedback solutions, as the characteristics of the wireless scenarios in cellular systems can change significantly as UEs continue to move. To address this issue, the following approaches can be adopted. The first approach is to design and train a powerful AI model that can be applied to a variety of potential wireless scenarios. However, such a powerful AI model would have high training costs and high operational complexity. Given that UEs often have very limited computing resources and strict energy consumption constraints, this feasibility is questionable. The second approach is to design and train multiple lightweight AI models, with different AI models suitable for different application scenarios, such as urban streets, rural areas, and indoor locations. As shown in Figure 4, scenario 1 has encoder #1 and decoder #1, scenario 2 has encoder #2 and decoder #2, and scenario 3 has encoder #3 and decoder #3. However, a major challenge in implementing this approach is how the base station and UE synchronize and accurately switch models based on different scenarios. Related scene recognition technologies are often applied in computer vision but are not suitable for wireless communication systems.

[0074] FIG5 is a schematic flow chart of a method 500 for determining a channel state information acquisition solution according to an embodiment of the present application. The method can optionally be applied to the system shown in FIG1 , but is not limited thereto. The method includes at least part of the following contents.

[0075] S510: The network device determines a channel state information (CSI) acquisition scheme corresponding to communication scenario information, wherein the communication scenario information may include a scenario to which the wireless communication environment between the network device and the terminal device belongs.

[0076] In an embodiment of the present application, the scenarios to which the wireless communication environment between the network device and the terminal device belongs may include but are not limited to streets, indoors, suburbs, urban areas, rural areas, etc. The communication scenario information may include the names, identifiers, and other information of scenarios such as streets, indoors, suburbs, urban areas, and rural areas. For example, the name of the street scene is "street" and the identifier is "1"; the name of the indoor scene is "indoor" and the identifier is "2". Different scenarios may correspond to different CSI acquisition schemes. For example, the street corresponds to CSI acquisition scheme A, the indoor corresponds to CSI acquisition scheme B, and the suburbs corresponds to CSI acquisition scheme C. The network device can determine whether CSI acquisition scheme A is currently needed to be used or needs to be switched to based on the name of the street scene "street" or the identifier "1". In an embodiment of the present application, the corresponding CSI acquisition scheme can be obtained based on the communication scenario information, and the CSI acquisition scheme can be better adapted to the wireless communication environment, so that the CSI acquisition scheme achieves better performance.

[0077] In one embodiment, the CSI acquisition solution includes an AI model for CSI acquisition and / or a non-AI feedback solution for CSI acquisition, wherein the AI ​​model for CSI acquisition includes at least one of the following:

[0078] CSI feedback model;

[0079] Channel estimation model.

[0080] In the embodiment of the present application, the CSI acquisition process may include stages such as channel measurement, channel estimation, and CSI feedback.

[0081] In an embodiment of the present application, if the AI ​​model used for CSI acquisition is a CSI feedback model, the specific contents of the CSI feedback model on the terminal device and the network device may be different or the same. For example, the terminal device may include an encoder for the CSI feedback model, and the network device may include a decoder for the CSI feedback model. For another example, the terminal device may include an encoder and decoder for the CSI feedback model, and the network device may include a decoder for the CSI feedback model.

[0082] In an embodiment of the present application, if the AI ​​model used for CSI acquisition is a channel estimation model, the same channel estimation model may be included on the terminal device and the network device.

[0083] In the embodiments of the present application, non-AI feedback schemes for CSI acquisition may include multiple, such as codebook-based feedback schemes. Configurable codebook types may include Type 1, Type 2, and enhanced Type 2.

[0084] In the embodiment of the present application, the network device may independently select a CSI acquisition scheme, or may determine the CSI acquisition scheme of the network device based on the CSI acquisition scheme selected by the terminal device.

[0085] In one embodiment, as shown in FIG6 , in method 600 , if the network device autonomously selects a CSI acquisition scheme, S510 may include:

[0086] S610: The network device selects a CSI acquisition scheme based on communication scenario information.

[0087] In one embodiment, as shown in FIG6 , the method 600 further includes:

[0088] S620: The network device sends relevant information of the selected CSI acquisition solution.

[0089] In one embodiment, the relevant information of the CSI acquisition scheme is used to indicate at least one of the following:

[0090] Identification of the CSI feedback model (IDentity, ID);

[0091] The ID of the encoder of the CSI feedback model;

[0092] The ID of the decoder of the CSI feedback model;

[0093] ID of the channel estimation model.

[0094] In an embodiment of the present application, after the network device autonomously selects a CSI acquisition scheme, relevant information of the selected CSI acquisition scheme may be sent to the terminal device. For example, if the network device selects a CSI feedback model based on communication scenario information, the ID of the CSI feedback model may be sent to the terminal device. If the network device selects a decoder for the CSI feedback model based on communication scenario information, the ID of the decoder for the CSI feedback model and / or the ID of the encoder corresponding to the decoder may be sent to the terminal device. If the network device selects a channel estimation model based on communication scenario information, the ID of the channel estimation model may be sent to the terminal device. If the network device selects codebook information based on communication scenario information, a bitmap or the like may be sent to the terminal device to indicate the codebook type.

[0095] In embodiments of the present application, the CSI acquisition scheme information may explicitly or implicitly indicate the name or ID of the model. For example, the CSI acquisition scheme information may include the model ID, encoder ID, or decoder ID, which is an explicit indication. For another example, a bit in the string included in the CSI acquisition scheme information being 0 may implicitly indicate the default model.

[0096] In one embodiment, the relevant information of the CSI acquisition solution is carried by at least one of the following:

[0097] Radio Resource Control (RRC) message, Media Access Control Control Element (MAC CE), Downlink Control Information (DCI).

[0098] For example, the RRC message, MAC CE or DCI sent by the network device to the terminal device carries relevant information of the CSI acquisition scheme.

[0099] In one implementation, as shown in FIG7 , based on any of the methods in the above embodiments, in method 700 , if the terminal device selects a CSI acquisition solution, S510 may include:

[0100] S710. The network device receives relevant information of the CSI acquisition solution;

[0101] S720: The network device determines the CSI acquisition scheme according to the relevant information of the CSI acquisition scheme.

[0102] In an embodiment of the present application, after the terminal device selects the CSI acquisition scheme, relevant information of the selected CSI acquisition scheme can be sent to the network device. If the network device receives the ID of the CSI feedback model selected by the terminal device, the CSI feedback model of the network device can be determined based on the ID of the CSI feedback model. If the network device receives the ID of the decoder of the CSI feedback model selected by the terminal device, the decoder of the CSI feedback model of the network device and / or the encoder corresponding to the decoder can be determined based on the ID of the CSI feedback model. If the network device receives the ID of the encoder of the CSI feedback model selected by the terminal device, the encoder of the CSI feedback model of the network device and / or the decoder corresponding to the encoder can be determined based on the ID of the CSI feedback model. If the network device receives the ID of the channel estimation model selected by the terminal device, the channel estimation model of the network device can be determined based on the ID of the channel estimation model. If the network device receives the codebook type selected by the terminal device, the codebook type of the network device can be determined based on the codebook type.

[0103] In one embodiment, the relevant information of the CSI acquisition solution is carried by at least one of the following:

[0104] RRC message, uplink control information (UCI), physical uplink shared channel (PUSCH).

[0105] For example, the RRC message, UCI or PUSCH sent by the terminal device to the network device can carry relevant information of the CSI acquisition scheme.

[0106] In one embodiment, before S510, the method may include: the network device obtaining an identifier of an allowed CSI acquisition scheme. For example, the network device obtains at least one of an encoder of a CSI feedback model, a decoder of a CSI feedback model, and a channel estimation model; wherein the CSI feedback model and / or the channel estimation model have corresponding communication scenario information.

[0107] In the embodiments of the present application, the network device may obtain multiple permitted CSI acquisition schemes, such as CSI acquisition scheme A, CSI acquisition scheme B, and CSI acquisition scheme C. CSI acquisition scheme A corresponds to scenario 1, CSI acquisition scheme B corresponds to scenario 2, and CSI acquisition scheme C corresponds to scenario 3. The network device may pre-acquire the specific contents of CSI acquisition schemes A, B, and CSI acquisition schemes C. Subsequently, the network device may determine the CSI acquisition scheme to be used or switched based on the communication scenario information. For example, the network device may initially select CSI acquisition scheme A and then switch from CSI acquisition scheme A to CSI acquisition scheme B based on scenario 2.

[0108] In one embodiment, the CSI feedback model and / or the channel estimation model are provided by the terminal device, predefined by the manufacturer, or provided by a third-party device. For example, the third-party device may include a cloud-based model library. The terminal device may obtain at least one of the CSI feedback model, the CSI feedback model encoder, the CSI feedback model decoder, and the channel estimation model from the cloud-based model library.

[0109] In one embodiment, the method also includes: the network device interacts with the terminal device to exchange basic information of the CSI feedback model and / or the channel estimation model, and the basic information of the CSI feedback model and / or the channel estimation model includes at least one of the ID of the CSI feedback model, the ID of the encoder and the ID of the decoder, and the ID of the channel estimation model.

[0110] In an embodiment of the present application, the network device may send the basic information of the CSI feedback model and / or the channel estimation model currently applicable to the network device to the terminal device. The network device may receive the basic information of the CSI feedback model and / or the channel estimation model currently applicable to the terminal device. In this way, the network device and the terminal device may inform each other of the basic information of the CSI acquisition schemes that they are allowed to use. For example, the CSI acquisition schemes allowed to be used by the network device include A, B, C, D and E, the CSI acquisition schemes allowed to be used by the terminal device UE1 include A and B, and the CSI acquisition schemes allowed to be used by the terminal device UE2 include C and D. The network device may send at least one of the IDs of the CSI feedback models, the IDs of the encoders and the IDs of the decoders, and the IDs of the channel estimation models included in the CSI acquisition schemes A, B, C, D and E to the terminal devices UE1 and UE2 respectively. The terminal device UE1 may send at least one of the IDs of the CSI feedback models, the IDs of the encoders and the IDs of the decoders, and the IDs of the channel estimation models included in the CSI acquisition schemes A and B to the network device. The terminal device UE1 may send at least one of the ID of the CSI feedback model, the ID of the encoder and the ID of the decoder, and the ID of the channel estimation model included in the CSI acquisition schemes C and D to the network device.

[0111] In one embodiment, basic information of the CSI feedback model and / or the channel estimation model is configured by at least one of the following:

[0112] RRC message;

[0113] Broadcast messages;

[0114] MAC CE;

[0115] DCI;

[0116] UCI.

[0117] For example, the RRC message, broadcast message, MAC CE, or DCI sent by the network device to the terminal device may carry the basic information of the CSI feedback model and / or the channel estimation model. For another example, the RRC message, MAC CE, or UCI sent by the terminal device to the network device may carry the basic information of the CSI feedback model and / or the channel estimation model.

[0118] In one embodiment, the method further includes: the network device triggering re-adaptation of the CSI acquisition solution based on the first monitoring indicator.

[0119] For example, the network device may determine whether the scenario needs to be changed based on whether some monitoring indicators meet threshold values. If the scenario needs to be changed, the network device may trigger itself to re-adapt the CSI acquisition solution.

[0120] In one embodiment, the method further includes: the network device sending trigger information based on the first monitoring indicator, where the trigger information is used to trigger the terminal device to re-adapt the CSI acquisition solution.

[0121] For example, the network device can determine whether the scene needs to be changed based on whether some monitoring indicators meet the threshold value. If the scene needs to be changed, the network device can trigger the terminal device to re-adapt the CSI acquisition solution.

[0122] In one embodiment, the first monitoring indicator includes at least one of the following:

[0123] Data transmission effect;

[0124] Location information of the terminal device;

[0125] Hybrid Automatic Repeat Request (HARQ) state;

[0126] Channel quality status.

[0127] For example, if the network device detects that the location information of the UE has changed significantly, it may determine that the scenario needs to be changed.

[0128] In one embodiment, the data transmission effect includes the data throughput rate and / or spectrum efficiency of the terminal device.

[0129] For example, the data transmission performance monitored by the network equipment can be reflected in the UE's data throughput rate or spectrum efficiency. If the data transmission performance is good, it can be determined that no scenario change is necessary. If the data transmission performance is poor, then a scenario change may be necessary. Furthermore, the network equipment can trigger a re-adaptation of the CSI acquisition scheme.

[0130] In one embodiment, the HARQ state includes the number of HARQ retransmissions and / or the HARQ retransmission frequency of the terminal device.

[0131] For example, if the network device detects that the number and / or frequency of HARQ retransmissions initiated by the UE exceeds a certain threshold, it may determine that a scenario change is required and trigger re-adaptation of the CSI acquisition scheme.

[0132] In one embodiment, the channel quality status includes at least one of the following: signal to noise ratio (SNR), signal interference noise ratio (SINR), reference signal receiving power (RSRP), reference signal received quality (RSRQ), and received signal strength indication (RSSI).

[0133] For example, if a network device detects that at least one of the channel quality indicators (SNR, SINR, RSRP, RSRQ, and RSSI) in the current communication environment meets a certain threshold, it can determine that a scenario change is necessary. Furthermore, the network device can trigger a re-adaptation of the CSI acquisition scheme.

[0134] In the embodiment of the present application, scene recognition can be performed on a network device or on a terminal device.

[0135] In one embodiment, the method further includes: the network device performs scene recognition on the wireless communication environment between the network device and the terminal device based on the second monitoring indicator to obtain the communication scene information.

[0136] In an embodiment of the present application, after the network device performs scenario recognition to obtain communication scenario information, S610 may be executed, where the network device selects a CSI acquisition scheme corresponding to the communication scenario information.

[0137] In one embodiment, the method further includes: the network device sending the communication scenario information.

[0138] In this embodiment of the present application, after the network device performs scenario identification to obtain communication scenario information, it may also send the communication scenario information to the terminal device, which then selects the CSI acquisition scheme corresponding to the communication scenario information. The network device may then wait for execution of S710 and S720, and after receiving relevant information about the CSI acquisition scheme, determine its own CSI acquisition scheme.

[0139] In one embodiment, the second monitoring indicator includes at least one of the following:

[0140] Uplink channel information;

[0141] Location information of the terminal device;

[0142] CSI fed back by the terminal device.

[0143] In an embodiment of the present application, a network device may use a scene recognition model to process uplink channel information, terminal device location information, CSI fed back by the terminal device, and the like to obtain the scene to which the wireless communication environment between the network device and the terminal device belongs. For example, the network device performs scene recognition based on the UE's previous location information or triggers the UE to report new location information. Alternatively, the network device initiates positioning of the UE and then performs scene recognition based on the UE's new location information.

[0144] In one embodiment, as shown in FIG8 , based on any of the methods in the above embodiments, method 800 may further include:

[0145] S810: The network device requests the terminal device to send a reference signal for scene recognition;

[0146] S820. The network device receives the reference signal.

[0147] S830: The network device performs uplink channel measurement based on the reference signal to obtain an uplink channel measurement result, where the uplink channel measurement result is used to perform scene recognition on the network device.

[0148] In an embodiment of the present application, a network device, such as a base station, can perform scene recognition based on uplink channel information. For example, the network device can request the UE to send an uplink RS through an RRC message, MAC CE, or DCI. The uplink RS can be an RS dedicated to scene recognition. The uplink RS can have a higher density than a common RS and occupy a wider frequency band. After the UE sends the RS to the base station based on the request, the base station can perform uplink channel measurement based on the received RS to obtain uplink channel information. Furthermore, the base station can perform scene recognition based on this uplink channel information.

[0149] In one embodiment, as shown in FIG9 , based on any of the methods in the above embodiments, method 900 may further include:

[0150] S910. The network device sends a CSI feedback configuration for scene recognition to the terminal device;

[0151] S920. The network device receives the CSI fed back by the terminal device based on the CSI feedback configuration, where the CSI is used for scene identification in the network device.

[0152] In an embodiment of the present application, a network device such as a base station can perform scene recognition based on the CSI fed back by the UE. The CSI is a quantized downlink channel information. The base station can perform scene recognition based on the CSI previously fed back by the UE, or it can configure new CSI feedback for the UE model for the purpose of achieving scene recognition. For example, the base station sends a CSI feedback configuration dedicated to scene recognition to the UE through RRC messages, MAC CE, DCI, etc. to trigger the UE to feedback CSI. After receiving the CSI fed back by the UE, the base station can perform scene recognition based on the CSI.

[0153] In one embodiment, scene recognition may not be performed on the network device. In this case, the method further includes: the network device receiving the communication scene information. For example, the terminal device performs scene recognition on the wireless communication environment between the network device and the terminal device to obtain the communication scene information. The network device receives the communication scene information sent by the terminal device.

[0154] Figure 10 is a schematic flow chart of a method 1000 for determining a channel state information acquisition scheme according to an embodiment of the present application. This method can optionally be applied to the system shown in Figure 1, but is not limited thereto. The method includes at least part of the following content. For content in the method executed by the terminal device that is identical or corresponding to that in the network device method embodiment, please refer to the relevant description of the network device.

[0155] S1010. The terminal device determines a channel state information (CSI) acquisition scheme corresponding to the communication scenario information, where the communication scenario information includes a scenario to which the wireless communication environment between the terminal device and the network device belongs.

[0156] In an embodiment of the present application, if it is uplink or downlink communication, the communication scenario information may include the scenario to which the wireless communication environment between the terminal device and the network device belongs. If it is sideline communication, the communication scenario information may include the scenario to which the wireless communication environment between the terminal device and other terminal devices belongs.

[0157] In one embodiment, the CSI acquisition solution includes an AI model for CSI acquisition and / or a non-AI feedback solution for CSI acquisition, wherein the AI ​​model for CSI acquisition includes at least one of the following:

[0158] CSI feedback model;

[0159] Channel estimation model.

[0160] In the embodiment of the present application, the terminal device can independently select a CSI acquisition scheme, or the CSI acquisition scheme of the terminal device can be determined based on the CSI acquisition scheme selected by the network device.

[0161] In one implementation, as shown in FIG11 , based on any of the methods in the above embodiments, in method 1100 , if the terminal device selects a CSI acquisition solution, S1010 may include:

[0162] S1110. The terminal device selects a CSI acquisition scheme based on the communication scenario information.

[0163] In one embodiment, as shown in FIG11 , the method further includes:

[0164] S1120. The terminal device sends relevant information of the selected CSI acquisition scheme.

[0165] In one embodiment, the relevant information of the CSI acquisition solution is carried by at least one of the following:

[0166] RRC message, UCI, PUSCH.

[0167] For example, the RRC message, UCI or PUSCH sent by the terminal device to the network device can carry relevant information of the CSI acquisition scheme.

[0168] In one implementation, as shown in FIG12 , based on any of the methods in the above embodiments, in method 1200 , if the network device autonomously selects a CSI acquisition scheme, S1010 may further include:

[0169] S1210. The terminal device receives relevant information of the CSI acquisition solution;

[0170] S1220. The terminal device determines the CSI acquisition scheme according to relevant information of the CSI acquisition scheme.

[0171] In one embodiment, the relevant information of the CSI acquisition solution is carried by at least one of the following:

[0172] RRC message, MAC CE, DCI.

[0173] For example, the RRC message, MAC CE or DCI sent by the network device to the terminal device carries relevant information of the CSI acquisition scheme.

[0174] In one embodiment, the relevant information of the CSI acquisition scheme is used to indicate at least one of the following:

[0175] ID of the CSI feedback model;

[0176] The ID of the encoder of the CSI feedback model;

[0177] The ID of the decoder of the CSI feedback model;

[0178] ID of the channel estimation model.

[0179] In one embodiment, the method further includes: the terminal device obtains at least one of an encoder of a CSI feedback model, a decoder of a CSI feedback model, and a channel estimation model that is allowed to be used; wherein the CSI feedback model and / or the channel estimation model has corresponding communication scenario information.

[0180] In one implementation, the CSI feedback model and / or the channel estimation model is provided by a network device, predefined by a manufacturer, or provided by a third-party device.

[0181] In one embodiment, the method also includes: the terminal device interacts with the network device to exchange basic information of the CSI feedback model and / or the channel estimation model, and the basic information of the CSI feedback model and / or the channel estimation model includes at least one of the ID of the CSI feedback model, the ID of the encoder and the ID of the decoder, and the ID of the channel estimation model.

[0182] In one embodiment, basic information of the CSI feedback model and / or the channel estimation model is configured by at least one of the following:

[0183] RRC message;

[0184] Broadcast messages;

[0185] MAC CE;

[0186] DCI;

[0187] UCI.

[0188] In one embodiment, the method further includes: the terminal device triggering re-adaptation of the CSI acquisition scheme based on a third monitoring indicator.

[0189] For example, the terminal device may determine whether the scene needs to be changed based on whether some monitoring indicators meet threshold values. If the scene needs to be changed, the terminal device may trigger itself to re-adapt the CSI acquisition solution.

[0190] In one embodiment, the method further includes: the terminal device sending trigger information based on the third monitoring indicator, where the trigger information is used to trigger the network device to re-adapt the CSI acquisition scheme.

[0191] For example, the terminal device can determine whether the scene needs to be changed based on whether some monitoring indicators meet the threshold value. If the scene needs to be changed, the terminal device can trigger the network device to re-adapt the CSI acquisition solution.

[0192] In one embodiment, the third monitoring indicator includes at least one of the following:

[0193] Data transmission effect;

[0194] Location information of the terminal device;

[0195] CSI model performance of the terminal device;

[0196] HARQ status;

[0197] Channel quality status.

[0198] For example, if the UE detects a significant change in its location information, it may determine that a scenario change is necessary. For another example, if the UE has an encoder and decoder for a CSI feedback model, the UE can determine the CSI model performance based on the degree of similarity between the encoder input and the decoder output. If the CSI model performance is good, it may be determined that a scenario change is not necessary; if the CSI model performance is poor, it may be determined that a scenario change is necessary. Furthermore, the UE can trigger a re-adaptation of the CSI acquisition scheme.

[0199] In one embodiment, the data transmission effect includes at least one of a data throughput rate, a spectrum efficiency, a block error rate (BLER), and a bit error rate (BER) of the terminal device.

[0200] For example, the data transmission performance monitored by the terminal device can be reflected by the UE's data throughput, spectral efficiency, BLER, and BER. If the data transmission performance is good, it can be determined that no scenario change is necessary. If the data transmission performance is poor, a scenario change may be necessary. The UE can then trigger a re-adaptation of the CSI acquisition scheme.

[0201] In one embodiment, the HARQ state includes the number of HARQ retransmissions and / or the HARQ retransmission frequency of the terminal device.

[0202] For example, if the UE detects that the number and / or frequency of HARQ retransmissions initiated by itself exceeds a certain threshold, it may determine that a scenario change is required and trigger re-adaptation of the CSI acquisition scheme.

[0203] In one embodiment, the channel quality status includes at least one of the following: SNR, SINR, RSRP, RSRQ, and RSSI.

[0204] For example, if the UE detects that at least one of the channel quality indicators (SNR, SINR, RSRP, RSRQ, and RSSI) in the current communication environment meets a certain threshold, it can determine that a scenario change is necessary. Furthermore, the UE can trigger re-adaptation of the CSI acquisition scheme.

[0205] In one embodiment, the method further includes: the terminal device performing scene recognition on the wireless communication environment between the terminal device and the network device based on the fourth monitoring indicator to obtain the communication scene information.

[0206] In one embodiment, the method further includes: the terminal device sending the communication scenario information.

[0207] In one embodiment, the fourth monitoring indicator includes at least one of the following:

[0208] Downlink channel information;

[0209] Location information of the terminal device;

[0210] CSI model performance of terminal devices.

[0211] For example, if a UE has an encoder and decoder for a CSI feedback model, the UE can determine the CSI model performance based on the similarity between the encoder input and the decoder output. If the CSI model performance is good, the UE can determine that the scenario does not need to be changed. If the CSI model performance is poor, the UE can determine that the scenario needs to be changed. The UE can then trigger a re-adaptation of the CSI acquisition solution.

[0212] In one embodiment, as shown in FIG13 , based on any of the methods in the above embodiments, the method 1300 further includes:

[0213] S1310: The terminal device requests the network device to send a reference signal for scene recognition;

[0214] S1320. The terminal device receives the reference signal;

[0215] S1330. The terminal device performs downlink channel measurement based on the reference signal to obtain a downlink channel measurement result, and the downlink channel measurement result is used to perform scene recognition on the terminal device.

[0216] In an embodiment of the present application, a terminal device, such as a UE, can perform scene recognition based on uplink channel information. For example, the UE can request the terminal to send a downlink RS through an RRC message or UCI, and the downlink RS can be an RS dedicated to scene recognition. The downlink RS can have a higher density than a common RS and occupy a wider frequency band. After the base station sends the RS to the UE based on the request, the UE can perform downlink channel measurement based on the received RS to obtain downlink channel information. Furthermore, the UE can perform scene recognition based on the downlink channel information.

[0217] In one embodiment, scene recognition may not be performed on the terminal device. In this case, the method further includes: the terminal device receiving the communication scene information. For example, the network device performs scene recognition on the wireless communication environment between the network device and the terminal device to obtain the communication scene information. The terminal device receives the communication scene information sent by the network device.

[0218] For specific examples of the terminal device execution method of this embodiment, please refer to the relevant description of the terminal device such as UE in the above-mentioned terminal device execution method embodiment. For the sake of brevity, it will not be repeated here.

[0219] The method for determining a channel state information acquisition scheme provided in an embodiment of the present application is an adaptation method for implementing a channel state information feedback scheme based on scenario recognition in a wireless communication system, so that a base station and a UE can dynamically switch and use the most suitable and effective CSI acquisition scheme, such as a CSI feedback scheme, according to the characteristics of the wireless scenario in which they are located, thereby improving system performance. Specifically, the method includes: (1) acquisition of multiple scenario models and interaction of necessary information; (2) triggering model adaptation; (3) model selection based on scenario recognition; (4) implementation of model adaptation, as well as the triggering conditions and implementation mechanisms involved in each process.

[0220] Example 1: The base station acts as a decision-making entity to implement a CSI acquisition solution such as CSI model adaptation.

[0221] In this example, multiple CSI models suitable for different wireless communication scenarios are configured on both the base station and the UE. The base station, as the decision-maker, completes wireless scenario identification and selects the most appropriate model to adapt to the current scenario. In this embodiment of the application, the CSI model can be referred to as a CSI feedback model, a CSI feedback AI model, etc.

[0222] The overall process of this example includes: multi-scenario model acquisition and necessary information interaction, triggering model adaptation, model selection based on base station scenario recognition, and implementing model adaptation.

[0223] 1. Acquisition of multi-scenario models and necessary information interaction.

[0224] Since the AI-based CSI feedback solution requires the base station and UE to each maintain a matching encoder model and / or decoder model (as shown in Figure 3), multiple sets of models adapted to different scenarios actually correspond to multiple sets of encoder and decoder models. In the embodiments of this application, there are no specific constraints on the definition or division of scenes. The degree of detail depends on the specific implementation. For example, potential scenes may include: Line of Sight (LOS) scenes, Non-Line of Sight (NLOS) scenes, city streets, suburbs, indoors, etc.

[0225] To achieve CSI model adaptation, the UE and base station must first maintain matching encoder and decoder models corresponding to multiple scenarios. Different models should have corresponding identification information (such as model identifiers (IDs)) to facilitate indication when switching models. There are several possible ways to obtain models and corresponding IDs:

[0226] a. Base station provision: The base station maintains multiple models and configures the models and their corresponding IDs to the UE (e.g., via RRC messages, broadcast configuration, MAC CE, or DCI indication). The model configured by the base station to the UE may include only the encoder part or both the encoder and decoder.

[0227] b. Manufacturer predefined: The base station and UE manufacturers have each predefined several matching models. In this case, the UE needs to report the retained model information and corresponding ID to the base station (for example, through RRC messages, UCI indications, etc.) to achieve alignment of the model information between the base station and the UE.

[0228] c. Obtained through third-party channels or agreements.

[0229] When multiple models are maintained, the base station and UE need to reach a consensus on which model to use by default. The default model can be indicated by the base station (e.g., via RRC messages, broadcast configuration, MAC CE, or DCI), by the UE (e.g., via RRC messages, UCI, etc.), or implicitly indicated by the model ID based on predefined rules (e.g., a bit in the ID set to 0 indicates the default model, etc.).

[0230] 2. Trigger model adaptation.

[0231] As the UE moves, the wireless communication environment may change significantly, affecting the adaptability and performance of the CSI model. This requires triggering the re-adaptation of the CSI model to the current scenario. This triggering can be categorized as either UE-triggered or base station-triggered.

[0232] a.UE triggers.

[0233] The UE can determine whether the currently used CSI model is still suitable for the current wireless scenario by monitoring whether one or more indicators meet the threshold. The specific monitoring indicators, corresponding threshold values, and monitoring periods or times can be predefined by the protocol or configured to the UE by the base station. For example, the base station configures the UE through broadcast messages, RRC messages, MAC CE messages, DCI, etc. Examples of potential monitoring indicator candidates are as follows:

[0234] (1) UE-based performance: Since the quality of CSI acquisition ultimately affects the data transmission performance of the communication system, the current data transmission status can be used to determine whether CSI acquisition performance needs to be optimized. Indicators reflecting data communication performance can include the success rate of current data packet reception, such as BLER and BER.

[0235] (2) UE based on current location information: When the UE location changes significantly, the wireless scenario in which it is located is likely to change.

[0236] (3) UE performance based on the current CSI model: When the UE maintains a complete CSI model (including the encoder and decoder), the UE can determine whether to trigger model scenario adaptation by judging the similarity between the encoder input and decoder output of the CSI feedback model. Here, indicators for judging the performance of the CSI feedback model can include similarity between the model input and output, cosine similarity, cosine similarity squared, mean square error, normalized mean square error, etc.

[0237] (4) UE channel quality status based on the current communication environment: The channel quality status can indirectly reflect the distance between the base station and the UE, whether the communication link is blocked, etc. Indicators reflecting the current channel quality status here may include SNR, SINR, RSRP, RSRQ, RSSI, etc.

[0238] When the UE determines that the scenario adaptation needs to be triggered, the UE will transmit a trigger message to the base station. The trigger message can be transmitted through, for example, an RRC message, UCI, PUSCH, etc.

[0239] b. Base station trigger.

[0240] Similarly, the base station can also decide whether to trigger CSI model adaptation by monitoring whether one or several indicators meet the threshold. The specific monitoring indicators and corresponding threshold values ​​can be agreed upon by the protocol, implemented by the base station, or reported by the UE to the base station, such as through RRC messages, UCI, PUSCH, etc. Potential monitoring indicator candidate examples are as follows:

[0241] (1) Base station based on current data transmission performance: Since the quality of CSI acquisition ultimately reflects the data transmission performance of the communication system, the current data transmission status can be used to determine whether CSI acquisition performance needs to be optimized. The base station can monitor the current UE data throughput or spectrum efficiency.

[0242] (2) The base station is based on the current UE's location information: When the UE's location changes significantly, the wireless scenario in which it is located is likely to change.

[0243] (3) The base station is based on the current Hybrid Automatic Repeat-reQuest (HARQ) status: The number and frequency of HARQ retransmissions initiated by the UE reflect the success rate of data reception at the UE to a certain extent. Therefore, the base station can decide whether to trigger scenario adaptation by monitoring the number or frequency of HARQ retransmissions of the UE.

[0244] (4) Channel quality of the base station based on the current communication environment: The channel quality can indirectly reflect the distance between the base station and the UE, whether the communication link is blocked, etc. The base station can monitor the current channel quality between the base station and the UE by monitoring the uplink reference signal sent by the UE. Indicators reflecting the current channel quality can include SNR, SINR, RSRP, RSRQ, RSSI, etc.

[0245] 3. Model selection based on base station scene recognition

[0246] After the CSI model scenario adaptation is triggered, the base station needs to first determine which scenario the wireless communication environment between the base station and the UE belongs to, and then select the model based on the judgment result. There are several possible methods for the base station to implement scenario recognition. Here we only describe the identification basis with potential air interface impact, and do not limit the specific identification method running inside the base station (such as using traditional algorithms, AI models, etc.).

[0247] a. The base station performs scene recognition based on uplink channel information: In FDD mode, although there is no explicit reciprocity between the uplink and downlink channels, and the downlink CSI cannot be directly estimated based on the uplink CSI, there is still a correlation between the two. Based on wireless signal propagation theory, the characteristics of the wireless channel are determined by the wireless transmission environment, such as the distance between the base station and the UE, the presence of a line of sight, the distribution of surrounding buildings, and so on. In essence, the uplink and downlink wireless channels are specific reflections of the same wireless transmission environment in different frequency bands. Therefore, while uplink channel information cannot be directly used to estimate downlink CSI, it can be used for scene recognition and provide guidance for downlink CSI feedback. Specifically, the base station can measure and obtain uplink channel information based on the uplink RS transmitted by the UE in the past, or it can trigger the UE to transmit an uplink RS (such as an SRS) to achieve scene recognition. Triggering the UE to transmit the RS for scene recognition can be achieved through methods such as RRC messages, MAC CE messages, and DCI. Because conventional uplink RS signals may not adequately meet the requirements of scene recognition, the RS signals triggered by the base station to be sent by the UE can be specially configured or defined for this purpose, such as having a higher density or occupying a wider frequency band. An example process is shown in Figure 14: the base station requests the UE to send RS signals for scene recognition. After the UE sends the RS signals, the base station performs uplink channel measurements based on the received RS signals and then performs scene recognition based on the uplink channel information.

[0248] b. Base stations perform scene recognition based on UE location information: The wireless communication scenario is closely linked to the UE's location. The base station can perform scene recognition based on the UE's past positioning results, trigger the UE to report new positioning information, or initiate positioning of the UE.

[0249] c. The base station performs scene recognition based on the CSI information fed back by the UE: The CSI information fed back by the UE is essentially a quantized downlink channel information. Although there will be a certain error between it and the ideal channel information, it still contains rich information. The base station can perform scene recognition based on the CSI results fed back by the UE in the past, or it can configure the UE for new CSI feedback for the purpose of achieving scene recognition (which can be triggered by, for example, RRC messages, MAC CE, DCI, etc.). Since conventional CSI feedback may not meet the needs of scene recognition well, the base station triggers the UE to perform CSI feedback with special configurations or definitions for the purpose of scene recognition, such as configuring a larger feedback overhead, configuring feedback with finer frequency domain granularity, etc. As shown in Figure 15, the process example shows that the base station configures the UE to use more bits for CSI feedback. The UE feeds back high-precision CSI to the base station based on the configuration of the base station. The base station performs scene recognition based on the received high-precision CSI.

[0250] 4. Implement model adaptation

[0251] Since the CSI model needs to work jointly with both the base station and the UE, once the base station completes the model selection, it needs to notify the UE of the selection result. Specifically, the base station needs to configure the ID corresponding to the selected model to the UE (for example, through RRC messages, MAC CE, DCI, etc.). After successfully receiving the configuration ID, the UE needs to feedback to inform the base station (for example, through RRC messages, UCI, PUSCH, etc.). After completing the above steps, the base station and UE will switch to the new CSI model, and the adaptation process is complete.

[0252] Figure 16 shows an example of the model adaptation process. After the base station performs scene recognition, it selects a model based on the recognized scene. The base station sends the selected model ID to the UE. After receiving the model ID from the base station, the UE confirms model adaptation. For example, if the base station sends the decoder ID of the CSI feedback model to the UE, the UE can determine its own encoder ID based on this decoder ID. The UE then sends its own model ID back to the base station. The base station uses the switched model for CSI reception and recovery. The UE uses the switched model for CSI compression and feedback.

[0253] Example 2: UE as the decision-making entity implements CSI acquisition solutions such as CSI model adaptation

[0254] In this example, multiple CSI models suitable for different wireless communication scenarios are configured at both the base station and the UE, and the UE is allowed to perform wireless scenario recognition and select the most appropriate model to adapt to the current scenario. In this embodiment of the application, the CSI model can be referred to as a CSI feedback model, a CSI feedback AI model, etc.

[0255] The overall process of this example includes: multi-scenario model acquisition and necessary information interaction, triggering model adaptation, model selection based on scenario recognition based on UE as the decision-making subject, and implementation of model adaptation.

[0256] 1. Multi-scenario model acquisition and necessary information interaction

[0257] Since the AI-based CSI feedback solution requires the base station and UE to each maintain a matching encoder model and / or decoder model (as shown in Figure 3), multiple sets of models adapted to different scenarios actually correspond to multiple sets of encoder and decoder models. In the embodiments of this application, there are no specific constraints on the definition or division of scenarios. The degree of detail depends on the specific implementation. For example, potential scenarios may include: LOS scenarios, NLOS scenarios, urban streets, suburbs, indoors, etc.

[0258] To achieve CSI model adaptation, the UE and base station need to maintain matching encoder and decoder models corresponding to multiple scenarios. Different models should have corresponding identification information (such as model ID) to facilitate indication when switching models. There are several possible ways to obtain the model and the corresponding ID.

[0259] a. Base station provision: The base station maintains multiple models and configures the models and their corresponding IDs to the UE. For example, the base station configures the models to the UE via RRC messages, broadcast configuration, MAC CE, or DCI. The model configured by the base station to the UE can include only the encoder or both the encoder and decoder.

[0260] b. Manufacturer predefined: The base station and UE manufacturers have each predefined several matching models. In this case, the UE needs to report the retained model information and corresponding ID to the base station (for example, the UE reports to the base station through RRC messages, UCI indications, etc.) to achieve alignment of the model information between the base station and the UE.

[0261] c. Obtained through third-party channels or agreements.

[0262] In the case of multiple models, the base station and the UE need to reach a consensus on which model to use by default. The default model can be indicated by the base station (for example, through RRC messages, broadcast configuration, MAC CE or DCI indication, etc.), by the UE (for example, through RRC messages, UCI indication, etc.), or implicitly indicated by the model ID based on predefined rules (for example, a bit in the ID is set to 0 for the default model, etc.)

[0263] 2. Trigger model adaptation

[0264] As the UE moves, the wireless communication environment may change significantly, affecting the adaptability and performance of the CSI model. This requires triggering the re-adaptation of the CSI model to the current scenario. This triggering can be categorized as either UE-triggered or base station-triggered.

[0265] a.UE triggers.

[0266] The UE can determine whether the currently used CSI model is still suitable for the current wireless scenario by monitoring whether one or more indicators meet the threshold. The specific monitoring indicators, corresponding threshold values, and monitoring periods or times can be predefined by the protocol or configured to the UE by the base station. For example, the base station configures the UE through broadcast messages, RRC messages, MAC CE messages, DCI, etc. Examples of potential monitoring indicator candidates are as follows:

[0267] (1) The UE decides whether to trigger CSI model adaptation based on the current data transmission performance: Since the quality of CSI acquisition ultimately reflects the data transmission performance of the communication system, the current data transmission status can be used to determine whether CSI acquisition performance needs to be optimized. Indicators reflecting data communication performance can include the success rate of current data packet reception, such as BLER and BER.

[0268] (2) The UE decides whether to trigger CSI model adaptation based on its current location information: When the UE location changes significantly, the wireless scenario in which it is located is likely to change.

[0269] (3) The UE decides whether to trigger CSI model adaptation based on the current CSI model performance: When the UE maintains a complete CSI model (including the encoder and decoder), the UE can determine whether to trigger model scenario adaptation by judging the similarity between the encoder input and decoder output of the CSI feedback model. Indicators for judging CSI feedback model performance may include similarity between model input and output, cosine similarity, cosine similarity squared, mean square error, normalized mean square error, etc.

[0270] (4) The UE decides whether to trigger CSI model adaptation based on the channel quality in the current communication environment. The channel quality can indirectly reflect the distance between the base station and the UE, whether the communication link is blocked, etc. Indicators reflecting the current channel quality may include SNR, SINR, RSRP, RSRQ, RSSI, etc.

[0271] When the UE determines that the scenario adaptation needs to be triggered, the UE will transmit a trigger message to the base station. The trigger message can be transmitted through, for example, an RRC message, UCI, PUSCH, etc.

[0272] b. Base station trigger.

[0273] Similarly, the base station can also decide whether to trigger CSI model adaptation by monitoring whether one or several indicators meet the threshold value. Among them, the specific monitoring indicators and the corresponding threshold values ​​can be agreed upon by the protocol, implemented based on the base station, or reported by the UE to the base station, such as through RRC messages, UCI, PUSCH, etc. Potential monitoring indicator candidates are summarized as follows:

[0274] (1) The base station decides whether to trigger CSI model adaptation based on the current data transmission performance: Since the quality of CSI acquisition ultimately reflects the data transmission performance of the communication system, the current data transmission status can be used to determine whether CSI acquisition performance needs to be optimized. The base station can monitor the current UE data throughput or spectrum efficiency.

[0275] (2) The base station decides whether to trigger CSI model adaptation based on the current UE location information: When the UE location changes significantly, the wireless scenario in which it is located is likely to change.

[0276] (3) The base station decides whether to trigger CSI model adaptation based on the current HARQ state: The number and frequency of HARQ retransmissions initiated by the UE reflect the success rate of data reception at the UE to a certain extent. Therefore, the base station can decide whether to trigger scenario adaptation by monitoring the number or frequency of HARQ retransmissions of the UE.

[0277] (4) The base station decides whether to trigger CSI model adaptation based on the channel quality status in the current communication environment: The channel quality status can indirectly reflect the distance between the base station and the UE, whether there is any obstruction in the communication link, etc. The base station can monitor the current channel quality status between the base station and the UE by monitoring the uplink reference signal sent by the UE. Indicators reflecting the current channel quality status here may include SNR, SINR, RSRP, RSRQ, RSSI, etc.

[0278] 3. Model selection based on UE scene recognition

[0279] After CSI model scenario adaptation is triggered, the UE must first determine the scenario type of the wireless communication environment between the base station and the UE. The UE can then report the determination result, such as scenario information or a number, to the base station for model selection based on the UE's feedback scenario. The base station then sends the selection result, such as a model ID, to the UE, as shown in Figure 17a. Alternatively, the UE can select a model based on the scenario identification result and report the selection result, such as a model ID, as shown in Figure 17b.

[0280] There are several possible methods for UE to implement scene recognition. Here, only the recognition basis with potential air interface impact is described. The specific recognition method running inside the UE (such as using traditional algorithms, AI models, etc.) is not limited.

[0281] a. UE scene recognition based on location information: The wireless communication scene is closely related to the UE's location. The UE can perform scene recognition based on its location information. This can effectively protect privacy information.

[0282] b.UE performs scene recognition based on downlink channel measurement results: The wireless environment (such as building density, whether there is a line of sight LOS, etc.) will directly affect the transmission of electromagnetic signals and will be reflected in the wireless channel characteristics. Therefore, the UE can perform scene recognition based on the measured downlink channel information. The UE can directly use the existing downlink RS for channel measurement. On the other hand, since the conventional downlink RS may not meet the needs of scene recognition well, the UE can also trigger the base station to send an RS with a special configuration or definition for the purpose of scene recognition, such as a higher density, occupying a wider frequency band, etc. Triggering the base station to send an RS for scene recognition can be achieved through methods such as RRC messages and UCI. The example process is shown in Figure 18, where the UE requests the base station to send an RS for scene recognition. After receiving the RS sent by the base station, the UE performs downlink channel measurement based on the received RS, and then performs scene recognition based on the downlink channel information.

[0283] c.UE performs scene recognition based on the performance of different CSI models: When the UE maintains multiple complete CSI models (including encoder and decoder models) locally, the UE can run and test the performance of different CSI models locally and make a choice based on the results. Specifically, the UE can input the current CSI to be fed back into different models, and determine which model is most suitable for the current scene by judging the degree of similarity between the encoder input and decoder output of different models. Here, the indicators for judging the performance of the CSI feedback model may include the similarity between the model input and output, cosine similarity, cosine similarity squared, mean square error, normalized mean square error, etc.

[0284] 4. Implement model adaptation

[0285] Since the CSI model needs to work jointly on both the base station and the UE, after the UE or the base station completes the model selection, it needs to notify the other party of the selection result.

[0286] When the base station completes model selection, it needs to configure the ID corresponding to the selected model to the UE (for example, through RRC messages, MAC CE, DCI, etc.). After successfully receiving the configuration ID, the UE needs to feedback to inform the base station (for example, through RRC messages, UCI, PUSCH, etc.).

[0287] When the UE completes model selection, it also needs to send the ID corresponding to the selected model to the base station (e.g., via RRC message, UCI, PUSCH, etc.). After successfully receiving the configuration ID, the base station needs to inform the UE (e.g., via RRC message, MAC CE, DCI, etc.). After completing the above steps, the base station and UE will switch to the new CSI model, and the adaptation process is complete.

[0288] The solution of the embodiment of the present application can achieve adaptation between the CSI feedback model and the wireless scenario in which the UE is located by introducing a scene recognition mechanism in the wireless communication system, thereby achieving better CSI feedback performance. Specifically, under certain complexity constraints, the AI ​​model often performs better in familiar scenarios (that is, scenarios that the AI ​​model has been exposed to or similar scenarios during the training phase), but it is difficult to guarantee performance for unfamiliar scenarios. The process introduced by this solution enables the base station and UE to dynamically select and switch appropriate models according to the actual wireless communication scenario in which they are located, thereby achieving an improvement in overall performance.

[0289] The above example mainly describes how to adapt the communication scenario to the CSI feedback scheme by switching the AI ​​model based on the scene recognition results. In specific application scenarios, the CSI feedback scheme based on the AI ​​model is just an example. In fact, based on the scene recognition results, switching between traditional feedback schemes can also be considered. For example, the switching object is no longer the AI ​​model, but a different codebook type, such as Type I codebook, Type II codebook, etc., or switching between the AI ​​scheme and the traditional codebook scheme.

[0290] The CSI model in the above example can also be replaced by other models. For example, before the CSI compression feedback, the UE needs to perform channel estimation in advance based on the received RS to obtain the CSI. As shown in Figure 19, the channel estimation process can also be implemented by an AI model, and therefore also has the adaptation problem with the communication scenario. For example, after the reference signal is input into the channel estimation model, such as the channel estimation neural network model, the UE-estimated CSI is obtained. The UE-estimated CSI is then input into the encoder (UE side) of the CSI model, such as the CSI feedback neural network model, and the feedback information is sent to the base station. The CSI recovered by the base station is obtained after processing by the decoder at the base station. The adaptation process of the channel estimation model can refer to the adaptation process of the CSI model. The model adaptation process of the embodiment of the present application can be extended to include a channel estimation AI model or other non-AI channel estimation methods.

[0291] FIG20 is a schematic block diagram of a network device 2000 according to an embodiment of the present application. The network device 2000 may include:

[0292] The first processing unit 2001 is used to determine a channel state information CSI acquisition scheme corresponding to communication scenario information, where the communication scenario information includes a scenario to which the wireless communication environment between the network device and the terminal device belongs.

[0293] In one embodiment, the CSI acquisition solution includes an AI model for CSI acquisition and / or a non-AI feedback solution for CSI acquisition, wherein the AI ​​model for CSI acquisition includes at least one of the following:

[0294] CSI feedback model;

[0295] Channel estimation model.

[0296] In one embodiment, the first processing unit 2001 is further configured to select a CSI acquisition scheme based on communication scenario information.

[0297] In one embodiment, based on the network device in the above embodiment, as shown in FIG21 , the network device 2100 further includes:

[0298] The first sending unit 2101 is configured to send relevant information of the selected CSI acquisition scheme.

[0299] In one embodiment, the relevant information of the CSI acquisition solution is carried by at least one of the following:

[0300] Radio resource control RRC message, medium access control MAC control element CE, downlink control information DCI.

[0301] In one embodiment, as shown in FIG21 , the network device 2100 further includes:

[0302] A first receiving unit 2102 is configured to receive relevant information of the CSI acquisition solution;

[0303] The first processing unit is further configured to determine the CSI acquisition scheme according to relevant information of the CSI acquisition scheme.

[0304] In one embodiment, the relevant information of the CSI acquisition solution is carried by at least one of the following:

[0305] RRC message, uplink control information UCI, physical uplink shared channel PUSCH.

[0306] In one embodiment, the relevant information of the CSI acquisition scheme is used to indicate at least one of the following:

[0307] ID of the CSI feedback model;

[0308] The ID of the encoder of the CSI feedback model;

[0309] The ID of the decoder of the CSI feedback model;

[0310] ID of the channel estimation model.

[0311] In one embodiment, as shown in FIG21 , the network device 2100 further includes:

[0312] The acquisition unit 2103 is used to acquire at least one of an encoder of a CSI feedback model, a decoder of a CSI feedback model, and a channel estimation model that are allowed to be used; wherein the CSI feedback model and / or the channel estimation model has corresponding communication scenario information.

[0313] In one implementation, the CSI feedback model and / or the channel estimation model is provided by the terminal device, predefined by the manufacturer, or provided by a third-party device.

[0314] In one embodiment, as shown in FIG21 , the network device 2100 further includes:

[0315] The interaction unit 2104 is configured to interact with the terminal device to exchange basic information of the CSI feedback model and / or the channel estimation model, where the basic information of the CSI feedback model and / or the channel estimation model includes at least one of the ID of the CSI feedback model, the ID of the encoder and the ID of the decoder, and the ID of the channel estimation model. The interaction unit may include a receiving unit and / or a sending unit. The sending unit may send the basic information of the CSI feedback model and / or the channel estimation model currently applicable to the network device to the terminal device. The receiving unit may receive the basic information of the CSI feedback model and / or the channel estimation model currently applicable to the terminal device.

[0316] In one embodiment, basic information of the CSI feedback model and / or the channel estimation model is configured by at least one of the following:

[0317] RRC message;

[0318] Broadcast messages;

[0319] MAC CE;

[0320] DCI;

[0321] UCI.

[0322] In one embodiment, the first processing unit is further configured to trigger re-adaptation of the CSI acquisition solution based on the first monitoring indicator.

[0323] In one embodiment, as shown in FIG21 , the network device 2100 further includes:

[0324] The second sending unit 2105 is used to send trigger information based on the first monitoring indicator, and the trigger information is used to trigger the terminal device to re-adapt the CSI acquisition solution.

[0325] In one embodiment, the first monitoring indicator includes at least one of the following:

[0326] Data transmission effect;

[0327] Location information of the terminal device;

[0328] Hybrid automatic repeat request HARQ state;

[0329] Channel quality status.

[0330] In one embodiment, the data transmission effect includes the data throughput rate and / or spectrum efficiency of the terminal device.

[0331] In one embodiment, the HARQ state includes the number of HARQ retransmissions and / or the HARQ retransmission frequency of the terminal device.

[0332] In one embodiment, the channel quality status includes at least one of the following: signal-to-noise ratio (SNR), signal-to-interference-plus-noise ratio (SINR), reference signal received power (RSRP), reference signal received quality (RSRQ), and received signal strength indicator (RSSI).

[0333] In one embodiment, the first processing unit is further configured to perform scene recognition on the wireless communication environment between the network device and the terminal device based on the second monitoring indicator to obtain the communication scene information.

[0334] In one embodiment, as shown in FIG21 , the network device 2100 further includes:

[0335] The third sending unit 2106 is configured to send the communication scenario information.

[0336] In one embodiment, the second monitoring indicator includes at least one of the following:

[0337] Uplink channel information;

[0338] Location information of the terminal device;

[0339] CSI fed back by the terminal device.

[0340] In one embodiment, as shown in FIG21 , the network device 2100 further includes:

[0341] The second processing unit 2107 is configured to request the terminal device to send a reference signal for scene recognition;

[0342] A second receiving unit 2108 is configured to receive the reference signal;

[0343] The third processing unit 2109 is configured to perform uplink channel measurement based on the reference signal to obtain an uplink channel measurement result, which is used to perform scene recognition on the network device.

[0344] In one embodiment, as shown in FIG21 , the network device 2100 further includes:

[0345] The fourth sending unit 2110 is configured to send a CSI feedback configuration for scene recognition to the terminal device;

[0346] The third receiving unit 2111 is configured to receive the CSI fed back by the terminal device based on the CSI feedback configuration, where the CSI is used to perform scene identification on the network device.

[0347] In one embodiment, as shown in FIG21 , the network device 2100 further includes:

[0348] The fourth receiving unit 2112 is configured to receive the communication scenario information.

[0349] The network devices 2000 and 2100 of the embodiments of the present application can implement the corresponding functions of the network devices in the aforementioned method embodiments. The processes, functions, implementation methods, and beneficial effects corresponding to the various modules (sub-modules, units, or components, etc.) in the network devices 2000 and 2100 can be found in the corresponding descriptions in the aforementioned method embodiments and will not be repeated here. It should be noted that the functions described in the various modules (sub-modules, units, or components, etc.) in the network devices 2000 and 2100 of the application embodiments can be implemented by different modules (sub-modules, units, or components, etc.) or by the same module (sub-module, unit, or component, etc.).

[0350] FIG22 is a schematic block diagram of a terminal device 2200 according to an embodiment of the present application. The terminal device 2200 may include:

[0351] The first processing unit 2201 is used to determine a channel state information CSI acquisition scheme corresponding to the communication scenario information, where the communication scenario information includes the scenario to which the wireless communication environment between the terminal device and the network device belongs.

[0352] In one embodiment, the CSI acquisition solution includes an AI model for CSI acquisition and / or a non-AI feedback solution for CSI acquisition, wherein the AI ​​model for CSI acquisition includes at least one of the following:

[0353] CSI feedback model;

[0354] Channel estimation model.

[0355] In one embodiment, the first processing unit 2201 is further configured to select a CSI acquisition scheme based on communication scenario information.

[0356] In one embodiment, as shown in FIG23 , the terminal device 2300 further includes:

[0357] The first sending unit 2301 is configured to send relevant information of the selected CSI acquisition scheme.

[0358] In one embodiment, the relevant information of the CSI acquisition solution is carried by at least one of the following:

[0359] RRC message, UCI, PUSCH.

[0360] In one embodiment, as shown in FIG23 , the terminal device 2300 further includes:

[0361] A first receiving unit 2302 is configured to receive relevant information of the CSI acquisition solution;

[0362] The first processing unit 2303 is further configured to determine the CSI acquisition scheme according to relevant information of the CSI acquisition scheme.

[0363] In one embodiment, the relevant information of the CSI acquisition solution is carried by at least one of the following:

[0364] RRC message, MAC CE, DCI.

[0365] In one embodiment, the relevant information of the CSI acquisition scheme is used to indicate at least one of the following:

[0366] ID of the CSI feedback model;

[0367] The ID of the encoder of the CSI feedback model;

[0368] The ID of the decoder of the CSI feedback model;

[0369] ID of the channel estimation model.

[0370] In one embodiment, as shown in FIG23 , the terminal device 2300 further includes:

[0371] The acquisition unit 2303 is used to acquire at least one of an encoder of a CSI feedback model, a decoder of a CSI feedback model, and a channel estimation model that are allowed to be used; wherein the CSI feedback model and / or the channel estimation model has corresponding communication scenario information.

[0372] In one implementation, the CSI feedback model and / or the channel estimation model is provided by a network device, predefined by a manufacturer, or provided by a third-party device.

[0373] In one embodiment, as shown in FIG23 , the terminal device 2300 further includes:

[0374] The interaction unit 2304 is configured to interact with the network device to exchange basic information of the CSI feedback model and / or the channel estimation model, where the basic information of the CSI feedback model and / or the channel estimation model includes at least one of the ID of the CSI feedback model, the ID of the encoder and the ID of the decoder, and the ID of the channel estimation model. The interaction unit may include a receiving unit and / or a sending unit. The sending unit may send the basic information of the CSI feedback model and / or the channel estimation model currently applicable to the terminal device to the network device. The receiving unit may receive the basic information of the CSI feedback model and / or the channel estimation model currently applicable to the network device.

[0375] In one embodiment, basic information of the CSI feedback model and / or the channel estimation model is configured by at least one of the following:

[0376] RRC message;

[0377] Broadcast messages;

[0378] MAC CE;

[0379] DCI;

[0380] UCI.

[0381] In one embodiment, as shown in FIG23 , the first processing unit is further configured to trigger re-adaptation of the CSI acquisition solution based on a third monitoring indicator.

[0382] In one embodiment, as shown in FIG23 , the terminal device 2300 further includes:

[0383] The second sending unit 2305 is configured to send trigger information based on the third monitoring indicator, where the trigger information is used to trigger the network device to re-adapt the CSI acquisition solution.

[0384] In one embodiment, the third monitoring indicator includes at least one of the following:

[0385] Data transmission effect;

[0386] Location information of the terminal device;

[0387] CSI model performance of the terminal device;

[0388] HARQ status;

[0389] Channel quality status.

[0390] In one embodiment, the data transmission effect includes at least one of a data throughput rate, a spectrum efficiency, a BLER, and a BER of the terminal device.

[0391] In one embodiment, the HARQ state includes the number of HARQ retransmissions and / or the HARQ retransmission frequency of the terminal device.

[0392] In one embodiment, the channel quality status includes at least one of the following: SNR, SINR, RSRP, RSRQ, and RSSI.

[0393] In one embodiment, the first processing unit is further configured to perform scene recognition on the wireless communication environment between the terminal device and the network device based on the fourth monitoring indicator to obtain the communication scene information.

[0394] In one embodiment, as shown in FIG23 , the terminal device 2300 further includes:

[0395] The third sending unit 2306 is configured to send the communication scenario information.

[0396] In one embodiment, the fourth monitoring indicator includes at least one of the following:

[0397] Downlink channel information;

[0398] Location information of the terminal device;

[0399] CSI model performance of terminal devices.

[0400] In one embodiment, as shown in FIG23 , the terminal device 2300 further includes:

[0401] The second processing unit 2307 is configured to request the network device to send a reference signal for scene recognition;

[0402] A second receiving unit 2308 is configured to receive the reference signal;

[0403] The third processing unit 2309 is configured to perform downlink channel measurement based on the reference signal to obtain a downlink channel measurement result, which is used to perform scene recognition on the terminal device.

[0404] In one embodiment, as shown in FIG23 , the terminal device 2300 further includes:

[0405] The third receiving unit 2310 is configured to receive the communication scenario information.

[0406] The terminal devices 2200 and 2300 of the embodiments of the present application can implement the corresponding functions of the terminal devices in the aforementioned method embodiments. The processes, functions, implementation methods and beneficial effects corresponding to the various modules (sub-modules, units or components, etc.) in the terminal devices 2200 and 2300 can be found in the corresponding descriptions in the aforementioned method embodiments and will not be repeated here. It should be noted that the functions described in the various modules (sub-modules, units or components, etc.) in the terminal devices 2200 and 2300 of the embodiment of the application can be implemented by different modules (sub-modules, units or components, etc.) or by the same module (sub-module, unit or component, etc.).

[0407] Figure 24 is a schematic structural diagram of a communication device 2400 according to an embodiment of the present application. The communication device 2400 includes a processor 2410, which can call and execute a computer program from a memory to enable the communication device 2400 to implement the method in the embodiment of the present application.

[0408] In one embodiment, the communication device 2400 may further include a memory 2420. The processor 2410 may call and execute a computer program from the memory 2420 to enable the communication device 2400 to implement the method in the embodiment of the present application.

[0409] The memory 2420 may be a separate device independent of the processor 2410 , or may be integrated into the processor 2410 .

[0410] In one embodiment, the communication device 2400 may further include a transceiver 2430 , and the processor 2410 may control the transceiver 2430 to communicate with other devices. Specifically, the transceiver 2430 may send information or data to other devices, or receive information or data sent by other devices.

[0411] The transceiver 2430 may include a transmitter and a receiver. The transceiver 2430 may further include an antenna, and the number of antennas may be one or more.

[0412] In one embodiment, the communication device 2400 may be a network device of an embodiment of the present application, and the communication device 2400 may implement the corresponding processes implemented by the network device in each method of the embodiment of the present application. For the sake of brevity, they will not be repeated here.

[0413] In one embodiment, the communication device 2400 may be a terminal device of an embodiment of the present application, and the communication device 2400 may implement the corresponding processes implemented by the terminal device in each method of the embodiment of the present application. For the sake of brevity, they will not be repeated here.

[0414] 25 is a schematic structural diagram of a chip 2500 according to an embodiment of the present application. The chip 2500 includes a processor 2510, which can call and execute a computer program from a memory to implement the method according to the embodiment of the present application.

[0415] In one embodiment, the chip 2500 may further include a memory 2520. The processor 2510 may call and execute a computer program from the memory 2520 to implement the method executed by the terminal device or the network device in the embodiment of the present application.

[0416] The memory 2520 may be a separate device independent of the processor 2510 or may be integrated into the processor 2510 .

[0417] In one embodiment, the chip 2500 may further include an input interface 2530. The processor 2510 may control the input interface 2530 to communicate with other devices or chips, and specifically, may obtain information or data sent by other devices or chips.

[0418] In one embodiment, the chip 2500 may further include an output interface 2540. The processor 2510 may control the output interface 2540 to communicate with other devices or chips, and specifically, may output information or data to other devices or chips.

[0419] In one embodiment, 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.

[0420] In one embodiment, the chip can be applied to the terminal device in the embodiments of the present application, and the chip can implement the corresponding processes implemented by the terminal device in each method of the embodiments of the present application. For the sake of brevity, they will not be repeated here.

[0421] The chips used in the network device and the terminal device may be the same chip or different chips.

[0422] 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.

[0423] The processor mentioned above may be a general-purpose processor, a digital signal processor (DSP), a field programmable gate array (FPGA), an application specific integrated circuit (ASIC), or other programmable logic devices, transistor logic devices, discrete hardware components, etc. The general-purpose processor mentioned above may be a microprocessor or any conventional processor, etc.

[0424] The memory mentioned above may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memories. 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).

[0425] 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.

[0426] FIG26 is a schematic block diagram of a communication system 2600 according to an embodiment of the present application. The communication system 2600 includes a terminal device 2610 and a network device 2620 .

[0427] The terminal device 2610 can be used to implement the corresponding functions implemented by the terminal device in the above method, and the network device 2620 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 described here in detail.

[0428] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When software is used for implementation, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function in accordance with the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from a website, computer, server or data center by wired (such as coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (such as infrared, wireless, microwave, etc.) mode to another website, computer, server or data center. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more available media integrations. The available medium may be a magnetic medium (eg, a floppy disk, a hard disk, a magnetic tape), an optical medium (eg, a DVD), or a semiconductor medium (eg, a solid state disk (SSD)).

[0429] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0430] 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.

[0431] 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 modifications 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 within 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 method for determining a channel state information acquisition scheme, comprising: The network device determines a channel state information (CSI) acquisition scheme corresponding to the communication scenario information, where the communication scenario information includes the scenario to which the wireless communication environment between the network device and the terminal device belongs.

2. The method according to claim 1, wherein The CSI acquisition solution includes an AI model for CSI acquisition and / or a non-AI feedback solution for CSI acquisition, wherein the AI ​​model for CSI acquisition includes at least one of the following: CSI feedback model; Channel estimation model.

3. The method according to claim 1 or 2, wherein The network device determines the CSI acquisition scheme corresponding to the communication scenario information, including: The network device selects a CSI acquisition scheme based on the communication scenario information.

4. The method according to claim 3, wherein: The method further comprises: The network device sends relevant information of the selected CSI acquisition solution.

5. The method according to claim 4, wherein The relevant information of the CSI acquisition scheme is carried by at least one of the following: Radio resource control RRC message, medium access control MAC control element CE, downlink control information DCI.

6. The method according to claim 1 or 2, wherein: The network device determines the CSI acquisition scheme corresponding to the communication scenario information, including: The network device receives relevant information of the CSI acquisition solution; The network device determines the CSI acquisition scheme according to relevant information of the CSI acquisition scheme.

7. The method according to claim 6, wherein: The relevant information of the CSI acquisition scheme is carried by at least one of the following: RRC message, uplink control information UCI, physical uplink shared channel PUSCH.

8. The method according to any one of claims 4 to 7, wherein The relevant information of the CSI acquisition scheme is used to indicate at least one of the following: The ID of the CSI feedback model; The ID of the encoder of the CSI feedback model; The ID of the decoder of the CSI feedback model; ID of the channel estimation model.

9. The method according to any one of claims 1 to 8, wherein The method further comprises: The network device obtains at least one of an encoder of a CSI feedback model, a decoder of a CSI feedback model, and a channel estimation model that is allowed to be used; wherein the CSI feedback model and / or the channel estimation model has corresponding communication scenario information.

10. The method according to claim 9, wherein: The CSI feedback model and / or the channel estimation model is provided by the terminal device, predefined by the manufacturer, or provided by a third-party device.

11. The method according to claim 9 or 10, wherein: The method further comprises: The network device interacts with the terminal device about the basic information of the CSI feedback model and / or the channel estimation model, and the basic information of the CSI feedback model and / or the channel estimation model includes at least one of the ID of the CSI feedback model, the ID of the encoder and the ID of the decoder, and the ID of the channel estimation model.

12. The method according to claim 11, wherein Basic information of the CSI feedback model and / or the channel estimation model is configured by at least one of the following: RRC message; Broadcast messages; MAC CE; DCI; UCI.

13. The method according to any one of claims 1 to 12, wherein The method further comprises: The network device triggers re-adaptation of the CSI acquisition solution based on the first monitoring indicator.

14. The method according to any one of claims 1 to 12, wherein The method further comprises: The network device sends trigger information based on the first monitoring indicator, and the trigger information is used to trigger the terminal device to re-adapt the CSI acquisition scheme.

15. The method according to claim 13 or 14, wherein: The first monitoring indicator includes at least one of the following: Data transmission effect; location information of the terminal device; Hybrid automatic repeat request HARQ state; Channel quality status.

16. The method according to claim 15, wherein The data transmission effect includes the data throughput rate and / or spectrum efficiency of the terminal device.

17. The method according to claim 15 or 16, wherein The HARQ state includes the number of HARQ retransmissions and / or the HARQ retransmission frequency of the terminal device.

18. The method according to any one of claims 15 to 17, wherein The channel quality status includes at least one of the following: signal-to-noise ratio (SNR), signal-to-interference-plus-noise ratio (SINR), reference signal received power (RSRP), reference signal received quality (RSRQ), and received signal strength indicator (RSSI).

19. The method according to any one of claims 1 to 18, wherein The method further comprises: The network device performs scene recognition on the wireless communication environment between the network device and the terminal device based on the second monitoring indicator to obtain the communication scene information.

20. The method according to claim 19, wherein The method further comprises: The network device sends the communication scenario information.

21. The method according to claim 19 or 20, wherein The second monitoring indicator includes at least one of the following: Uplink channel information; Location information of the terminal device; CSI fed back by the terminal device.

22. The method according to any one of claims 19 to 21, wherein The method further comprises: The network device requests the terminal device to send a reference signal for scene recognition; The network device receives the reference signal; The network device performs uplink channel measurement based on the reference signal to obtain an uplink channel measurement result, and the uplink channel measurement result is used to perform scene recognition on the network device.

23. The method according to any one of claims 19 to 21, wherein The method further comprises: The network device sends a CSI feedback configuration for scene recognition to the terminal device; The network device receives the CSI fed back by the terminal device based on the CSI feedback configuration, where the CSI is used to perform scene identification on the network device.

24. The method according to any one of claims 1 to 18, wherein The method further comprises: The network device receives the communication scenario information.

25. A method for determining a channel state information acquisition scheme, comprising: The terminal device determines a channel state information CSI acquisition scheme corresponding to the communication scenario information, where the communication scenario information includes the scenario to which the wireless communication environment between the terminal device and the network device belongs.

26. The method according to claim 25, wherein The CSI acquisition solution includes an AI model for CSI acquisition and / or a non-AI feedback solution for CSI acquisition, wherein the AI ​​model for CSI acquisition includes at least one of the following: CSI feedback model; Channel estimation model.

27. The method according to claim 25 or 26, wherein The terminal device determines the CSI acquisition scheme corresponding to the communication scenario information, including: The terminal device selects a CSI acquisition scheme based on the communication scenario information.

28. The method according to claim 27, wherein The method further comprises: The terminal device sends relevant information of the selected CSI acquisition scheme.

29. The method according to claim 28, wherein The relevant information of the CSI acquisition scheme is carried by at least one of the following: RRC message, UCI, PUSCH.

30. The method of claim 25, wherein: The terminal device determines the CSI acquisition scheme corresponding to the communication scenario information, including: The terminal device receives relevant information of the CSI acquisition solution; The terminal device determines the CSI acquisition scheme based on relevant information of the CSI acquisition scheme.

31. The method according to claim 30, wherein The relevant information of the CSI acquisition scheme is carried by at least one of the following: RRC message, MAC CE, DCI.

32. The method according to any one of claims 28 to 31, wherein The relevant information of the CSI acquisition scheme is used to indicate at least one of the following: ID of the CSI feedback model; The ID of the encoder of the CSI feedback model; The ID of the decoder of the CSI feedback model; ID of the channel estimation model.

33. The method according to any one of claims 25 to 32, wherein The method further comprises: The terminal device obtains at least one of an encoder of a CSI feedback model, a decoder of a CSI feedback model, and a channel estimation model that are allowed to be used; wherein the CSI feedback model and / or the channel estimation model has corresponding communication scenario information.

34. The method according to claim 33, wherein The CSI feedback model and / or the channel estimation model is provided by a network device, predefined by a manufacturer, or provided by a third-party device.

35. The method according to claim 33 or 34, wherein The method further comprises: The terminal device interacts with the network device about the basic information of the CSI feedback model and / or the channel estimation model, and the basic information of the CSI feedback model and / or the channel estimation model includes at least one of the ID of the CSI feedback model, the ID of the encoder and the ID of the decoder, and the ID of the channel estimation model.

36. The method of claim 35, wherein: Basic information of the CSI feedback model and / or the channel estimation model is configured by at least one of the following: RRC message; Broadcast messages; MAC CE; DCI; UCI.

37. The method according to any one of claims 25 to 36, wherein The method further comprises: The terminal device triggers re-adaptation of the CSI acquisition scheme based on a third monitoring indicator.

38. The method according to any one of claims 25 to 36, wherein The method further comprises: The terminal device sends trigger information based on the third monitoring indicator, and the trigger information is used to trigger the network device to re-adapt the CSI acquisition scheme.

39. The method according to claim 37 or 38, wherein The third monitoring indicator includes at least one of the following: Data transmission effect; location information of the terminal device; CSI model performance of the terminal device; HARQ status; Channel quality status.

40. The method of claim 39, wherein The data transmission effect includes at least one of the data throughput rate, spectrum efficiency, BLER and BER of the terminal device.

41. The method according to claim 39 or 40, wherein The HARQ state includes the number of HARQ retransmissions and / or the HARQ retransmission frequency of the terminal device.

42. The method according to any one of claims 39 to 41, wherein The channel quality status includes at least one of the following: SNR, SINR, RSRP, RSRQ, and RSSI.

43. The method according to any one of claims 25 to 42, wherein The method further comprises: The terminal device performs scene recognition on the wireless communication environment between the terminal device and the network device based on the fourth monitoring indicator to obtain the communication scene information.

44. The method according to claim 43, wherein The method further comprises: The terminal device sends the communication scenario information.

45. The method according to claim 43 or 44, wherein The fourth monitoring indicator includes at least one of the following: Downlink channel information; Location information of the terminal device; CSI model performance of terminal devices.

46. ​​A method according to any one of claims 43 to 45, wherein The method further comprises: The terminal device requests the network device to send a reference signal for scene recognition; The terminal device receives the reference signal; The terminal device performs downlink channel measurement based on the reference signal to obtain a downlink channel measurement result, and the downlink channel measurement result is used to perform scene recognition on the terminal device.

47. The method according to any one of claims 25 to 42, wherein The method further comprises: The terminal device receives the communication scenario information.

48. A network device comprising: The first processing unit is used to determine a channel state information CSI acquisition scheme corresponding to the communication scenario information, where the communication scenario information includes the scenario to which the wireless communication environment between the network device and the terminal device belongs.

49. The network device according to claim 48, wherein The CSI acquisition solution includes an AI model for CSI acquisition and / or a non-AI feedback solution for CSI acquisition, wherein the AI ​​model for CSI acquisition includes at least one of the following: CSI feedback model; Channel estimation model.

50. The network device according to claim 48 or 49, wherein: The first processing unit is further configured to select a CSI acquisition scheme based on communication scenario information.

51. The network device according to claim 50, wherein: The network device further includes: The first sending unit is configured to send relevant information of the selected CSI acquisition scheme.

52. The network device according to claim 51, wherein The relevant information of the CSI acquisition scheme is carried by at least one of the following: Radio resource control RRC message, medium access control MAC control element CE, downlink control information DCI.

53. The network device according to claim 48 or 49, wherein: The network device further includes: A first receiving unit, configured to receive relevant information of the CSI acquisition scheme; The first processing unit is further configured to determine the CSI acquisition scheme according to relevant information of the CSI acquisition scheme.

54. The network device according to claim 53, wherein: The relevant information of the CSI acquisition scheme is carried by at least one of the following: RRC message, uplink control information UCI, physical uplink shared channel PUSCH.

55. The network device according to any one of claims 51 to 54, wherein: The relevant information of the CSI acquisition scheme is used to indicate at least one of the following: ID of the CSI feedback model; The ID of the encoder of the CSI feedback model; The ID of the decoder of the CSI feedback model; ID of the channel estimation model.

56. The network device according to any one of claims 48 to 55, wherein: The network device further includes: An acquisition unit is used to acquire at least one of an encoder of a CSI feedback model, a decoder of a CSI feedback model, and a channel estimation model that are allowed to be used; wherein the CSI feedback model and / or the channel estimation model have corresponding communication scenario information.

57. The network device according to claim 56, wherein: The CSI feedback model and / or the channel estimation model is provided by the terminal device, predefined by the manufacturer, or provided by a third-party device.

58. The network device according to claim 56 or 57, wherein: The network device further includes: An interaction unit is used to interact with the terminal device to exchange basic information of the CSI feedback model and / or the channel estimation model, wherein the basic information of the CSI feedback model and / or the channel estimation model includes at least one of the ID of the CSI feedback model, the ID of the encoder and the ID of the decoder, and the ID of the channel estimation model.

59. The network device according to claim 58, wherein Basic information of the CSI feedback model and / or the channel estimation model is configured by at least one of the following: RRC message; Broadcast messages; MAC CE; DCI; UCI.

60. The network device according to any one of claims 48 to 59, wherein: The first processing unit is further configured to trigger re-adaptation of the CSI acquisition solution based on a first monitoring indicator.

61. The network device according to any one of claims 48 to 59, wherein: The network device further includes: The second sending unit is used to send trigger information based on the first monitoring indicator, and the trigger information is used to trigger the terminal device to re-adapt the CSI acquisition scheme.

62. The network device according to claim 60 or 61, wherein: The first monitoring indicator includes at least one of the following: Data transmission effect; location information of the terminal device; Hybrid automatic repeat request HARQ state; Channel quality status.

63. The network device according to claim 62, wherein: The data transmission effect includes the data throughput rate and / or spectrum efficiency of the terminal device.

64. The network device according to claim 62 or 63, wherein: The HARQ state includes the number of HARQ retransmissions and / or the HARQ retransmission frequency of the terminal device.

65. The network device according to any one of claims 62 to 64, wherein: The channel quality status includes at least one of the following: signal-to-noise ratio (SNR), signal-to-interference-plus-noise ratio (SINR), reference signal received power (RSRP), reference signal received quality (RSRQ), and received signal strength indicator (RSSI).

66. The network device according to any one of claims 48 to 65, wherein: The first processing unit is further configured to perform scene recognition on the wireless communication environment between the network device and the terminal device based on the second monitoring indicator to obtain the communication scene information.

67. The network device according to claim 66, wherein: The network device further includes: The third sending unit is used to send the communication scenario information.

68. The network device according to claim 66 or 67, wherein: The second monitoring indicator includes at least one of the following: Uplink channel information; Location information of the terminal device; CSI fed back by the terminal device.

69. The network device according to any one of claims 66 to 68, wherein: The network device further includes: a second processing unit, configured to request the terminal device to send a reference signal for scene recognition; a second receiving unit, configured to receive the reference signal; The third processing unit is configured to perform uplink channel measurement based on the reference signal to obtain an uplink channel measurement result, where the uplink channel measurement result is used to perform scene recognition on the network device.

70. The network device according to any one of claims 66 to 68, wherein: The network device further includes: a fourth sending unit, configured to send a CSI feedback configuration for scene recognition to the terminal device; The third receiving unit is used to receive the CSI fed back by the terminal device based on the CSI feedback configuration, where the CSI is used to perform scene identification in the network device.

71. The network device according to any one of claims 48 to 65, wherein: The network device further includes: The fourth receiving unit is used to receive the communication scenario information.

72. A terminal device comprising: The first processing unit is used to determine a channel state information CSI acquisition scheme corresponding to the communication scenario information, where the communication scenario information includes the scenario to which the wireless communication environment between the terminal device and the network device belongs.

73. The terminal device according to claim 72, wherein: The CSI acquisition solution includes an AI model for CSI acquisition and / or a non-AI feedback solution for CSI acquisition, wherein the AI ​​model for CSI acquisition includes at least one of the following: CSI feedback model; Channel estimation model.

74. The terminal device according to claim 72 or 73, wherein: The first processing unit is further configured to select a CSI acquisition scheme based on communication scenario information.

75. The terminal device according to claim 74, wherein: The terminal device further includes: The first sending unit is configured to send relevant information of the selected CSI acquisition scheme.

76. The terminal device according to claim 75, wherein: The relevant information of the CSI acquisition scheme is carried by at least one of the following: RRC message, UCI, PUSCH.

77. The terminal device according to claim 72, wherein: The terminal device further includes: A first receiving unit, configured to receive relevant information of the CSI acquisition scheme; The first processing unit is further configured to determine the CSI acquisition scheme according to relevant information of the CSI acquisition scheme.

78. The terminal device according to claim 77, wherein: The relevant information of the CSI acquisition scheme is carried by at least one of the following: RRC message, MAC CE, DCI.

79. The terminal device according to any one of claims 75 to 78, wherein: The relevant information of the CSI acquisition scheme is used to indicate at least one of the following: ID of the CSI feedback model; The ID of the encoder of the CSI feedback model; The ID of the decoder of the CSI feedback model; ID of the channel estimation model.

80. The terminal device according to any one of claims 72 to 79, wherein: The terminal device further includes: An acquisition unit is used to acquire at least one of an encoder of a CSI feedback model, a decoder of a CSI feedback model, and a channel estimation model that are allowed to be used; wherein the CSI feedback model and / or the channel estimation model have corresponding communication scenario information.

81. The terminal device according to claim 80, wherein: The CSI feedback model and / or the channel estimation model is provided by a network device, predefined by a manufacturer, or provided by a third-party device.

82. The terminal device according to claim 80 or 81, wherein: The terminal device further includes: An interaction unit is used to interact with the network device to exchange basic information of the CSI feedback model and / or the channel estimation model, where the basic information of the CSI feedback model and / or the channel estimation model includes at least one of the ID of the CSI feedback model, the ID of the encoder and the ID of the decoder, and the ID of the channel estimation model.

83. The terminal device according to claim 82, wherein: The basic information of the CSI feedback model and / or the channel estimation model is configured through at least one of the following: RRC message; broadcast message; MAC CE; DCI; UCI.

84. The terminal device according to any one of claims 72 to 83, wherein: The first processing unit is further configured to trigger re-adaptation of the CSI acquisition solution based on a third monitoring indicator.

85. The terminal device according to any one of claims 72 to 83, wherein: The terminal device further includes: The second sending unit is used to send trigger information based on the third monitoring indicator, where the trigger information is used to trigger the network device to re-adapt the CSI acquisition solution.

86. The terminal device according to claim 84 or 85, wherein: The third monitoring indicator includes at least one of the following: Data transmission effect; location information of the terminal device; CSI model performance of the terminal device; HARQ status; Channel quality status.

87. The terminal device according to claim 86, wherein: The data transmission effect includes at least one of the data throughput rate, spectrum efficiency, BLER and BER of the terminal device.

88. The terminal device according to claim 86 or 87, wherein: The HARQ state includes the number of HARQ retransmissions and / or the HARQ retransmission frequency of the terminal device.

89. The terminal device according to any one of claims 86 to 88, wherein: The channel quality status includes at least one of the following: SNR, SINR, RSRP, RSRQ, and RSSI.

90. The terminal device according to any one of claims 72 to 89, wherein: The first processing unit is further configured to perform scene recognition on the wireless communication environment between the terminal device and the network device based on a fourth monitoring indicator to obtain the communication scene information.

91. The terminal device according to claim 90, wherein: The terminal device further includes: The third sending unit is used to send the communication scenario information.

92. The terminal device according to claim 90 or 91, wherein: The fourth monitoring indicator includes at least one of the following: Downlink channel information; Location information of the terminal device; CSI model performance of terminal devices.

93. The terminal device according to any one of claims 90 to 92, wherein: The terminal device further includes: a second processing unit, configured to request the network device to send a reference signal for scene recognition; a second receiving unit, configured to receive the reference signal; The third processing unit is used to perform downlink channel measurement based on the reference signal to obtain a downlink channel measurement result, and the downlink channel measurement result is used to perform scene recognition on the terminal device.

94. The terminal device according to any one of claims 72 to 89, wherein: The terminal device further includes: The third receiving unit is configured to receive the communication scenario information.

95. A network device comprising: 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, so that the network device executes the method according to any one of claims 1 to 24.

96. A terminal device comprising: 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 so that the terminal device executes the method according to any one of claims 25 to 47.

97. A chip comprising: A processor, configured to call and execute a computer program from a memory, so that a device equipped with the chip executes the method according to any one of claims 1 to 24 or 25 to 47.

98. A computer-readable storage medium for storing a computer program, which, when executed by a device, causes the device to perform the method according to any one of claims 1 to 24 or 25 to 47.

99. A computer program product comprising computer program instructions for causing a computer to perform the method of any one of claims 1 to 24 or 25 to 47.

100. A computer program causing a computer to perform the method of any one of claims 1 to 24 or 25 to 47.

Images