CSI compression model indication method and communication apparatus

Abstract

Provided in the present application are a CSI compression model indication method and a communication apparatus, which help to reduce the overhead of CSI feedback. The method comprises: a terminal device downloading, on the basis of model capability information thereof, M CSI compression models from a model management platform, wherein M is a positive integer greater than or equal to 1; when the M CSI compression models have passed digital signature verification, reporting, to a network device and by means of the capability information, model identifiers of the M CSI compression models supported by the terminal device; and the network device determining a first CSI compression model from among the M CSI compression models on the basis of the current communication scenario of the terminal device, and indicating the model identifier of the first CSI compression model to the terminal device, such that the terminal device can feed CSI back to the network device on the basis of the first CSI compression model.

Description

CSI compression model indication method and communication device

[0001] This application claims priority to the Chinese patent application filed with the China Patent Office on February 21, 2024, with application number 202410192430.1 and application name “CSI Compression Model Indication Method and Communication Device”, the entire contents of which are incorporated by reference into this application. Technical Field

[0002] The present application relates to the field of communication technology, and in particular to a CSI compression model indication method and a communication device. Background Art

[0003] In the fifth generation (5 th In 5G-generation (5G) communication systems, terminal devices can provide feedback on downlink channel quality to network devices, for example, through channel state information (CSI). Upon receiving CSI, network devices can perform beam management, mobility management, rate matching, and other processes based on the CSI to improve communication quality.

[0004] Massive multiple-input, multiple-output (MIMO) technology further improves the reliability and capacity of 5G communication systems by deploying large-scale antenna arrays at base stations. As the number of antenna arrays increases, the overhead of CSI feedback also increases. Therefore, reducing the overhead of CSI feedback is a pressing technical challenge. Summary of the Invention

[0005] The present application provides a CSI compression model indication method and a communication device, which indicate the CSI compression model to a terminal device through a network device, so that the terminal device can feedback CSI based on the indicated CSI compression model, thereby reducing the overhead of CSI feedback.

[0006] In a first aspect, the present application provides a communication method, which can be executed by a terminal device or by a device matched with the terminal device, such as a processor or chip. The method may include: downloading M CSI compression models from a model management platform based on model capability information of the terminal device, where M is a positive integer greater than or equal to 1; in response to the M CSI compression models passing digital signature verification, sending capability information to a network device, the capability information including model identifiers of the M CSI compression models, the M CSI compression models being CSI compression models supported by the terminal device; and receiving model indication information from the network device, the model indication information being used to indicate a first CSI compression model, the M CSI compression models including the first CSI compression model, and the first CSI compression model matching the current communication scenario of the terminal device.

[0007] It can be seen that the terminal device downloads the M CSI compression models it supports, and reports the model identifiers of these M CSI compression models to the network device, so that the network device indicates to the terminal device the first CSI compression model that matches the current communication scenario of the terminal device, so that the terminal device can feedback CSI based on the first CSI compression model, which can reduce the overhead of CSI feedback. The first CSI compression model matches the current communication scenario of the terminal device, so that the CSI fed back based on the first CSI compression model can more realistically reflect the channel state of the current communication scenario, which is beneficial to improving the performance of the network device in beam management, mobility management, rate matching, etc., and is beneficial to improving the communication quality of the current communication scenario. The network device indicates the CSI compression model that matches the current communication scenario of the terminal device, which can realize the dynamic indication of the CSI compression model by the network device. The network device indicates the first CSI compression model and uses the CSI compression recovery model corresponding to the first CSI compression model to process the CSI, which can improve the decoding efficiency of the network device and ensure communication performance.

[0008] In one possible implementation, for any CSI compression model among the M compression models described above, the model includes model information, where the model information includes one or more of a model identifier, model overhead information, model applicability speed information, and model deployment information. In other words, the model information is used to distinguish CSI compression models. Different CSI compression models have different model information, which helps network devices determine the appropriate CSI compression model based on the current communication scenario of a terminal device, thereby reducing CSI feedback overhead.

[0009] Among them, the model identifier is equivalent to the model identity identifier (ID), which is used to identify the CSI compression model. The model overhead information indicates the number of CSI reporting bits, that is, the number of CSI reporting bits corresponding to the CSI compression model. In other words, for a CSI compression model, the number of bits occupied by the CSI when reporting CSI based on it. The model applicable speed information indicates the applicable speed range, that is, the applicable speed range corresponding to the CSI compression model. In other words, for a CSI compression model, in which speed range can it work more accurately and reflect the channel status more accurately. The model deployment information indicates whether it is deployed on the terminal device or the network device. For a CSI compression model, its model deployment information indicates that the CSI compression model is deployed on the terminal device side. If the model deployment information of a CSI compression model indicates that it is deployed on the terminal device side, then the network device side needs to deploy the CSI compression recovery model corresponding to the CSI compression model so that the CSI fed back by the terminal device based on the CSI compression model can be correctly decoded.

[0010] In one possible implementation, when downloading M CSI compression models from a model management platform based on the model capability information of a terminal device, the M CSI compression models can be downloaded from the model management platform based on the model capability information of the terminal device and the model identifiers of K CSI compression recovery models, where K is a positive integer greater than or equal to 1. The K CSI compression recovery models are CSI compression recovery models supported by the network device. In other words, the terminal device downloads M CSI compression models from the model management platform based on its model capability information and the CSI compression recovery models supported by the network device, and the M CSI compression model information is the CSI compression model supported by the terminal device, and is also the CSI compression model corresponding to the CSI compression recovery model supported by the network device. This enables the network device to quickly and accurately decode the CSI fed back by the terminal device using the corresponding CSI compression recovery model.

[0011] In one possible implementation, before downloading M CSI compression models from the model management platform based on the model capability information of the terminal device and the model identifiers of the K CSI compression recovery models, the terminal device receives the model identifiers of the K CSI compression recovery models from the network device, and the model identifier of one CSI compression model corresponds to the model identifier of one CSI compression recovery model. In other words, one CSI compression model on the terminal device side corresponds to one CSI compression recovery model on the network device side, the terminal device feeds back CSI based on the CSI compression model, and the network device decodes the CSI based on the CSI compression recovery model. The network device informs the terminal device of the model identifiers of the CSI compression recovery models it supports, so that when the terminal device downloads the CSI compression model, it downloads the CSI compression model supported by both the terminal device and the network device, so that the network device can quickly and accurately use the corresponding CSI compression recovery model to decode the CSI fed back by the terminal device.

[0012] In one possible implementation, the model capability information of the terminal device includes the model identifier of the CSI compression model supported by the terminal device and / or the model processing capability of the terminal device. That is, the terminal device can download the CSI compression model from the model management platform based on the model identifier of the CSI compression model it supports, and / or can download the CSI compression model from the model management platform based on its model processing capability. The model processing capability may include but is not limited to computing, storage, co-processing and other capabilities. This enables the terminal device to use the downloaded CSI compression model to feedback CSI, which can reduce the feedback overhead of CSI.

[0013] In one possible implementation, the model indication information is carried in downlink control information (DCI) or a media access control-control element (MAC-CE). That is, the network device indicates the model identifier of the first CSI compression model to the terminal device through the DCI or MAC-CE.

[0014] In a second aspect, the present application provides a communication method, which can be executed by a network device or by a device compatible with the network device, such as a processor or chip. The method may include: receiving capability information from a terminal device, the capability information including model identifiers of M CSI compression models, where the M CSI compression models are CSI compression models supported by the terminal device, and M is an integer greater than or equal to 1; determining a first CSI compression model from the M CSI compression models based on a current communication scenario of the terminal device; and sending model indication information to the terminal device, where the model indication information is used to indicate the model identifier of the first CSI compression model.

[0015] It can be seen that the terminal device reports the model identifier of the CSI compression model it supports through the capability information, so that the network device indicates to the terminal device the first CSI compression model that matches the current communication scenario of the terminal device, so that the terminal device can feedback CSI based on the first CSI compression model, which can reduce the overhead of CSI feedback. The first CSI compression model matches the current communication scenario of the terminal device, so that the CSI fed back based on the first CSI compression model can more realistically reflect the channel state of the current communication scenario, which is beneficial to improving the performance of the network device in beam management, mobility management, rate matching, etc., and is beneficial to improving the communication quality of the current communication scenario. The network device indicates the CSI compression model that matches the current communication scenario of the terminal device, which can realize the dynamic indication of the CSI compression model by the network device. The network device indicates the first CSI compression model and uses the CSI compression recovery model corresponding to the first CSI compression model to process the CSI, which can improve the decoding efficiency of the network device and ensure communication performance.

[0016] In one possible implementation, after receiving capability information, the network device may download M CSI compression and recovery models from the model management platform based on the model identifiers of the M CSI compression models included in the capability information. Each CSI compression model identifier corresponds to a CSI compression and recovery model identifier. In other words, the network device downloads the CSI compression and recovery models corresponding to the CSI compression models supported by the terminal device from the model management platform. This facilitates the network device to decode the CSI reported by the terminal device.

[0017] In one possible implementation, after the network device downloads M CSI compression and recovery models from the model management platform, it performs digital signature verification on the M CSI compression and recovery models. After the M CSI compression and recovery models pass the digital signature verification, it performs the step of determining a first CSI compression model or the step of sending model indication information to the terminal device. By performing digital signature verification on the M CSI compression and recovery models, the security of the M CSI compression and recovery models is ensured.

[0018] In one possible implementation, a storage device (i.e., a local storage device) of a network device includes a series of CSI compression and recovery models. Upon receiving capability information, the network device retrieves CSI compression and recovery models corresponding to M CSI compression models from the storage device, where a model identifier of a CSI compression model corresponds to a model identifier of a CSI compression and recovery model. In other words, the network device itself has a series of CSI compression and recovery models that have been contracted with the model management platform. Upon receiving capability information, the network device can retrieve the M CSI compression and recovery models to determine a first CSI compression model based on the current communication scenario of the terminal device.

[0019] In one possible implementation, in response to the current communication scenario of the terminal device being a high mobility scenario, a first CSI compression model supporting a high mobility scenario is determined from M CSI compression models; or, in response to the current communication scenario of the terminal device being a low mobility scenario, a first CSI compression model supporting a low mobility scenario is determined from M CSI compression models; or, in response to the current communication scenario of the terminal device being an indoor communication mobility scenario, a first CSI compression model supporting an indoor communication scenario is determined from M CSI compression models. In other words, the network device can determine and indicate different CSI compression models based on different communication scenarios, and the network device can dynamically indicate the CSI compression model. The indicated CSI compression model matches the communication scenario, so that the CSI fed back based on the indicated CSI compression model can more realistically reflect the channel state of the communication scenario, thereby facilitating improving the performance of the network device in beam management, mobility management, rate matching, etc., and improving the communication quality of the communication scenario.

[0020] In one possible implementation, before receiving capability information from a terminal device, the network device may send model identifiers of K CSI compression recovery models to the terminal device, where the K CSI compression recovery models are CSI compression recovery models supported by the network device, and K is a positive integer greater than or equal to 1. The network device sends the model identifiers of the CSI compression recovery models it supports to the terminal device, so that the terminal device downloads the CSI compression model from the model management platform based on its model capability information and the model identifiers of the CSI compression recovery models supported by the network device. In this way, the CSI compression model downloaded by the terminal device is both a CSI compression model supported by the terminal device and a CSI compression model corresponding to the CSI compression recovery model supported by the network device.

[0021] In a possible implementation, the model indication information is carried in DCI or MAC-CE. That is, the network device indicates the model identifier of the first CSI compression model to the terminal device via DCI or MAC-CE.

[0022] In a possible implementation, for any CSI compression model, it includes model information, and the model information includes one or more of a model identifier, model overhead information, model applicability speed information, and model deployment information.

[0023] The model identifier is equivalent to the model identity (ID) and is used to identify the CSI compression model. The model overhead information indicates the number of CSI reporting bits, i.e., the number of CSI reporting bits corresponding to the CSI compression model. The model applicable speed information indicates the applicable speed range, i.e., the applicable speed range corresponding to the CSI compression model. The model deployment information indicates deployment on the network device.

[0024] In a possible implementation, any CSI compression recovery model also includes model information, where the model information includes one or more of a model identifier, model applicability speed information, and model deployment information.

[0025] The model identifier is equivalent to a model identity (ID) and is used to identify the CSI compression recovery model. The model applicable speed information indicates the applicable speed range, that is, the applicable speed range of the CSI compression model corresponding to the CSI compression recovery model. The model deployment information indicates whether it is deployed on a terminal device or a network device. If a CSI compression model is deployed on a terminal device, the CSI compression recovery model corresponding to the CSI compression model is deployed on a network device.

[0026] In a third aspect, the present application provides a communication device, which includes a module / unit for executing any method described in the first aspect and its possible implementations, or a module / unit for executing any method described in the second aspect and its possible implementations.

[0027] In a fourth aspect, the present application provides a communication device, which may be a terminal device, or a chip, chip system, or processor that supports the terminal device to implement the above-mentioned method, or a logical node, logic module, or software that can implement all or part of the terminal functions. Among them, the communication device may also be a chip system. The communication device can execute the method described in the first aspect. The functions of the communication device can be implemented by hardware, or by hardware executing corresponding software. The hardware or software includes one or more units corresponding to the above-mentioned functions. The unit may be software and / or hardware. The operations and beneficial effects performed by the communication device can refer to the methods and beneficial effects described in the first aspect above, and the repeated parts will not be repeated.

[0028] In a fifth aspect, the present application provides a communication device, which may be a network device, or a chip, chip system, or processor that supports the network device to implement the above-mentioned method, or a logical node, logic module, or software that can implement all or part of the network device functions. Among them, the communication device may also be a chip system. The communication device can execute the method described in the second aspect. The functions of the communication device can be implemented by hardware, or by hardware executing corresponding software. The hardware or software includes one or more units corresponding to the above-mentioned functions. The unit may be software and / or hardware. The operations and beneficial effects performed by the communication device can refer to the method and beneficial effects described in the second aspect above, and the repeated parts will not be repeated.

[0029] In a sixth aspect, the present application provides a communication device, which includes a processor, the processor is coupled to a memory, and the memory is used to store programs or instructions. When the program or instruction is executed by the processor, the communication device executes the method described in any one of the first to second aspects.

[0030] In the seventh aspect, the present application provides a communication device, which includes a processor and an interface circuit, wherein the interface circuit is used to receive signals from other communication devices outside the communication device and transmit them to the processor or send signals from the processor to other communication devices outside the communication device, and the processor is used to implement the method described in any one of the first to second aspects through logic circuits or execution code instructions.

[0031] In an eighth aspect, the present application provides a computer-readable storage medium, which is used to store computer execution instructions. When the computer execution instructions are executed, the method executed by the terminal in the method described in the first aspect is implemented; or, the method executed by the network device in the method described in the second aspect is implemented.

[0032] In the ninth aspect, the present application provides a computer program product comprising a computer program, which, when executed, enables the method executed by the terminal in the method described in the first aspect to be implemented; or, enables the method executed by the network device in the method described in the second aspect to be implemented.

[0033] In a tenth aspect, the present application provides a communication system, which includes a communication device (such as a terminal) for executing the method described in the first aspect and a communication device (such as a network device) for executing the method described in the second aspect.

[0034] It can be understood that the beneficial effects that can be achieved by the communication method, communication device, computer-readable storage medium, and computer program product provided above can be referred to the beneficial effects in the first aspect or the second aspect and any possible implementation thereof, and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] FIG1 is an exemplary diagram of a system architecture using an embodiment of the present application;

[0036] FIG2 is a flowchart illustrating a codebook-based CSI feedback method;

[0037] FIG3 is a schematic diagram of a flow chart of a CSI compression model indication method provided in an embodiment of the present application;

[0038] FIG4 is a schematic flow chart of another CSI compression model indication method provided in an embodiment of the present application;

[0039] FIG5 is a schematic structural diagram of a communication device provided in an embodiment of the present application;

[0040] FIG6 is a schematic structural diagram of another communication device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0041] The specific embodiments of the present application are further described in detail below with reference to the accompanying drawings.

[0042] The terms "first" and "second" and the like in the specification, claims, and drawings of this application are used to distinguish between different objects, not to describe a particular order. Furthermore, the terms "including" and "having," and any variations thereof, are intended to cover non-exclusive inclusions. For example, a process, method, system, product, or apparatus comprising a series of steps or elements is not limited to the listed steps or elements, but may optionally include steps or elements not listed, or may optionally include other steps or elements inherent to the process, method, product, or apparatus.

[0043] References herein to "embodiments" mean that a particular feature, structure, or characteristic described in connection with the embodiments may be included in at least one embodiment of the present application. The appearance of this phrase in various places in the specification does not necessarily refer to the same embodiment, nor does it constitute an independent or alternative embodiment that is mutually exclusive of other embodiments. It is understood, both explicitly and implicitly, by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0044] In this application, "at least one (item)" refers to one or more, "more than one" refers to two or more, "at least two (items)" refers to two or three and more than three, and "and / or" is used to describe the association relationship of associated objects, indicating that there can be three relationships. For example, "A and / or B" can mean: only A exists, only B exists, and A and B exist at the same time, where A and B can be singular or plural. The character " / " generally indicates that the previous and next associated objects are in an "or" relationship. "At least one of the following items" or similar expressions refers to any combination of these items, including any combination of single items or plural items. For example, at least one of a, b or c can mean: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, c can be single or multiple.

[0045] In this application, "sending information to... (e.g., a terminal device)" can be understood as the destination of the information being the terminal device. This can include sending information to the terminal device directly or indirectly. "Receiving information from... (e.g., a terminal device)" or "receiving information from... (e.g., a terminal device)" can be understood as the source of the information being the terminal device, which can include receiving information from the terminal device directly or indirectly. The information may be processed as necessary between the source and destination of the information, such as format changes, but the destination can understand the valid information from the source. Similar expressions in this application can be understood similarly and will not be elaborated on here.

[0046] In the description of this application, "indication" may include direct indication and indirect indication, and may also include explicit indication and implicit indication. The information indicated by a certain information (such as the indication information described below) is called information to be indicated. In the specific implementation process, there are many ways to indicate the information to be indicated. For example, the information to be indicated can be directly indicated, such as indicating the information to be indicated itself or the index of the information to be indicated. For another example, the information to be indicated can also be indirectly indicated by indicating other information, and there is an association between the other indicated information and the information to be indicated. For another example, only a part of the information to be indicated can be indicated, while the other parts of the information to be indicated are known or agreed in advance. In addition, the indication of specific information can be achieved by means of the pre-agreed (such as specified in the protocol) order of arrangement of each information, thereby reducing the indication overhead to a certain extent.

[0047] To better understand the embodiments of the present application, the following first introduces the system architecture involved in the embodiments of the present application:

[0048] The embodiments of the present application can be applied to communication systems evolved after 5G, such as long term evolution (LTE) systems, fifth generation mobile communication (5G) systems, sixth generation mobile communication (6G) systems, satellite communication and short-range wireless communication systems. Among them, the wireless communication systems mentioned in the embodiments of the present application include but are not limited to: three major application scenarios of 5G / 6G mobile communication systems: enhanced mobile broadband (eMBB), ultra reliable low latency communication (URLLC) and massive machine type communication (mMTC), long range Internet of Things (LoRa) systems or vehicle networking systems. A wireless communication system may include one or more network devices, and one or more terminal devices.

[0049] The embodiments of the present application can be applied to the system architecture shown in Figure 1. The communication system 10 shown in Figure 1 may include, but is not limited to, a network device 110, a terminal device 120, and a model management platform 130. The number and form of the devices in Figure 1 are for illustrative purposes only and do not constitute a limitation on the embodiments of the present application. For example, in actual applications, multiple terminal devices may be included.

[0050] Terminal devices, also known as user equipment (UE), mobile stations (MS), and mobile terminals (MT), are devices that provide voice and / or data connectivity to users. Examples include handheld devices and in-vehicle devices with wireless connectivity. Currently, some examples of terminal devices include mobile phones, tablets, laptops, PDAs, mobile internet devices (MIDs), wearable devices, virtual reality (VR) devices, augmented reality (AR) devices, wireless terminals used in industrial control, wireless terminals used in self-driving vehicles, wireless terminals used in remote medical surgery, wireless terminals used in smart grids, wireless terminals used in transportation safety, wireless terminals used in smart cities, and wireless terminals used in smart homes.

[0051] The embodiments of this application do not limit the form factor of the terminal device. The device used to implement the functions of the terminal device can be the terminal device; it can also be a device that supports the terminal device to implement the functions, such as a chip system. The device can be installed in the terminal device or used in conjunction with the terminal device. In the embodiments of this application, the chip system can be composed of a chip or include a chip and other discrete components.

[0052] A network device, also known as an access network device, refers to a radio access network (RAN) node (or device) that connects a terminal device to a wireless network. It can also be called a base station. Examples of RAN nodes include: gNB, transmission reception point (TRP), evolved Node B (eNB), radio network controller (RNC), Node B (NB), base station controller (BSC), base transceiver station (BTS), home base station (e.g., home evolved NodeB, or HNB), baseband unit (BBU), or wireless fidelity (Wi-Fi) access point (AP). Furthermore, in a network architecture, a network device can include a centralized unit (CU) node, a distributed unit (DU) node, or a RAN device that includes both a CU and a DU node. It should be noted that the centralized unit node and the distributed unit node may also use other names, which are not limited in this application.

[0053] The embodiments of this application do not limit the form of network devices. The device used to implement the functions of the network device can be a network device; it can also be a device that supports the network device to implement the function, such as a chip system. The device can be installed in the network device or used in conjunction with the network device. In the embodiments of this application, the chip system can be composed of chips or include chips and other discrete components.

[0054] The model management platform can also be called a CSI model management platform, an artificial intelligence (AI) model management platform, a model management server, a model server, a model cloud server, etc. The model management platform is used to store and manage various types of AI models and can provide downloads of AI models to terminal devices or network devices. The AI ​​model refers to the AI ​​model in the communication system. Such AI models may include a CSI compression model and a CSI compression recovery model. The CSI compression model is deployed on the terminal device side, and the CSI compression recovery model is deployed on the network device side. The model management platform can be, for example, a server, a cloud server, a personal computer (PC), a laptop, etc.

[0055] In an embodiment of the present application, a terminal device may support the deployment of an AI model, such as a CSI compression model. A network device may also support the deployment of an AI model, such as a CSI compression recovery model.

[0056] In order to facilitate understanding of the contents of this solution, some of the terms involved in the embodiments of this application are explained below to facilitate understanding by those skilled in the art. This part is only for ease of understanding and cannot be regarded as a specific limitation of this application.

[0057] 1. Digital Signature

[0058] Digital signature is a security verification method that includes the signing process and the verification process.

[0059] Signature process: The sender generates a signed electronic file, uses a hash algorithm to generate a digital summary of the electronic file, and then asymmetrically encrypts the summary using the signature private key to create a digital signature. The digital signature is then packaged together with the original electronic file and the public key of the signature certificate to form a signature result that is sent to the recipient for verification.

[0060] Verification process: The recipient receives the signature result, which includes the digital signature, the original electronic document, and the sender's public key; uses the public key to decrypt the digital signature to obtain a summary, and then uses a hash algorithm to make a digital summary of the original electronic document to obtain another summary. The hash values ​​of the two summaries are compared. If they are the same, the verification passes; otherwise, the verification fails.

[0061] For example, taking sender A and receiver B as an example, the specific process of digital signature may include:

[0062] (1) A performs a hash operation on the original text to obtain a hash value, which is the digest;

[0063] (2) A uses his own private key and an asymmetric encryption algorithm to encrypt the digest and obtain a digital signature;

[0064] (3) A uses the symmetric key of the symmetric encryption algorithm to encrypt the original text, digital signature, and A's public key to obtain encrypted information;

[0065] (4) A uses B's public key to encrypt the symmetric key using an asymmetric encryption algorithm to form a digital envelope;

[0066] (5) A sends the encrypted message and digital envelope to B;

[0067] (6) After receiving the digital envelope, B decrypts it with his own private key to obtain the symmetric key;

[0068] (7) B uses the symmetric key and the symmetric encryption algorithm to decrypt the encrypted information and restore the original text, digital signature and A's public key;

[0069] (8) B decrypts the digital signature using A's public key to obtain digest 1;

[0070] (9) B performs a hash operation on the original text to obtain another digest, which is assumed to be digest 2;

[0071] (10) Determine whether digest 1 and digest 2 are the same. If they are the same, the digital signature verification passes; otherwise, the verification fails.

[0072] 2. CSI

[0073] CSI can be used to describe information related to channel quality. For example, CSI describes the propagation process of a wireless signal between a transmitter and a receiver, including the effects of distance, scattering, fading, etc. on the signal. For downlink transmission, CSI can be used by the terminal device to feedback the downlink channel quality to the network device so that the network device can perform beam management, mobility management, etc. based on the CSI. The CSI sent by the terminal device to the network device can be carried in the CSI report. For example, CSI can also include at least one of the following: CSI reference signal resource indicator index (CSI-RS Resource Indicator, CRI), rank indicator index (Rank Indicator, RI), channel quality indicator index (Channel quality indicator, CQI), precoding matrix indicator index (Precoding Matrix Indicator, PMI), layer indicator index (Layer Indicator, LI), layer 1 reference signal received power (layer 1 reference signal received power, L1-RSRP), layer 1 signal-to-noise and interference ratio (layer 1 signal-to-noise and interference ratio, L1-SINR).

[0074] The terminal device performs channel measurement through the downlink reference signal to obtain channel information. Measurement can also be described as evaluation, detection or estimation, etc. Among them, the downlink reference signal may include but is not limited to the channel state information reference signal (CSI-RS), the synchronization signal and physical downlink broadcast channel block (SSB) or the physical downlink broadcast channel (PBCH) demodulation reference signal (DMRS), etc. For example, the terminal device can perform downlink channel measurement based on the CSI-RS to obtain channel matrix information, and thus can obtain CSI based on the channel matrix information.

[0075] The CSI report (CSI-Report) is used to report CSI. For example, the CSI report may include at least one of L1-RSRP, L1-SINR, CSI-related information, etc. Specifically, in some embodiments, the CSI report may be configured by the higher-layer parameter CSI report configuration information (CSI-ReportConfig). CSI-ReportConfig may be configured by the higher-layer parameter CSI-MeasConfig. CSI-MeasConfig may indicate or include the following two higher-layer parameters: CSI report configuration information (CSI-ReportConfig) and CSI resource configuration information (CSI-ResourceConfig).

[0076] CSI-ReportConfig may indicate or include CSI-ResourceConfigId. Through CSI-ResourceConfigId, CSI-ReportConfig may be associated with CSI-ResourceConfig, or CSI-ResourceConfig may be associated with CSI-ReportConfig. Association may also be described as mapping or correspondence, etc. For example, if CSI-ReportConfig indicates or includes CSI-ResourceConfigId, it can be understood that the CSI report configuration information is associated with CSI resource configuration information; if CSI-ReportConfig does not indicate or include CSI-ResourceConfigId, it can be understood that the CSI report configuration information is not associated with CSI resource configuration information.

[0077] CSI-ResourceConfig can be used to configure CSI-RS resources for CSI measurement. CSI-ResourceConfig can configure a resource set (e.g., ResourceSet), which can include one or more CSI-RS resources (e.g., CSI-RS-Resource).

[0078] CSI-ResourceConfig may indicate or include: an NZP-CSI-RS resource set (NZP-CSI-RS-ResourceSet), or a CSI interference measurement (CSI Interference Measurement, CSI-IM) resource set (CSI-IM-ResourceSet), or a synchronization signal block (SSB) resource set (SSB-ResourceSet).

[0079] NZP-CSI-RS-ResourceSet can be used for channel measurement and / or interference measurement; CSI-IM-ResourceSet can be used for interference measurement; SSB-ResourceSet can be used for channel measurement.

[0080] The type of CSI-RS resources can be periodic, semi-persistent, or aperiodic.

[0081] The report configuration type (reportConfigType) in CSI-ReportConfig can be used to indicate the report type of the CSI report, which can be a periodic CSI report, an aperiodic CSI report, or a semi-persistent CSI report. The CSI report can be transmitted via the physical uplink control channel (PUCCH) or the physical uplink shared channel (PUSCH).

[0082] 3. CSI Compression Model and CSI Compression Recovery Model

[0083] The CSI compression model is used by the terminal device to compress the CSI. For example, the number of CSI feedback bits before compression is 30 bits, and the number of CSI feedback bits after compression is 20 bits. This helps reduce the CSI feedback overhead.

[0084] The CSI compression recovery model is used by network devices to recover CSI. Since the CSI fed back by the terminal device is processed based on the CSI compression model, the network device can use the CSI compression recovery model to recover the pre-compression CSI upon receiving the CSI. The CSI compression recovery model can also be described as a CSI reconstruction model or a CSI compression reconstruction model.

[0085] A CSI compression model on the terminal device side has a corresponding CSI compression recovery model on the network device side to recover the CSI feedback based on the CSI compression model. In other words, the CSI compression model and the CSI compression recovery model are paired and have a one-to-one correspondence.

[0086] As AI model technology evolves, different vendors may offer different CSI compression and recovery models. Regardless of the AI ​​model used, the AI ​​decoder on the network device and the AI ​​encoder on the terminal device must match to ensure performance. In other words, the prerequisite for the embodiments of this application is that the AI ​​decoder on the network device matches the AI ​​encoder on the terminal device.

[0087] Currently, in 5G communication systems, terminal devices feed back CSI based on a codebook indicated by a network device. For example, taking CSI including PMI as an example, the codebook-based CSI feedback method can be seen in Figure 2. In Figure 2, the terminal device receives the CSI-RS, performs channel estimation and equalization based on the received CSI-RS, determines the precoding matrix based on the results of the channel estimation and equalization and the codebook (indicated by the network device), and then outputs the PMI based on the precoding matrix and feeds back the PMI to the network device; the network device receives the PMI, performs a table lookup based on the PMI to obtain the precoding matrix, and then sends downlink data to the terminal device based on the precoding matrix. However, with the increase in large-scale antenna arrays, the overhead of CSI feedback also increases. The CSI feedback method shown in Figure 2 is difficult to meet the communication scenarios with complex and changing channels.

[0088] In view of this, an embodiment of the present application provides a CSI compression model indication method and a communication device, which indicates the CSI compression model to the terminal device through the network device, so that the terminal device can feedback CSI based on the indicated CSI compression model, which can reduce the overhead of CSI feedback. In an embodiment of the present application, the terminal device does not need to generate a CSI compression model, and the network device does not need to generate a CSI compression recovery model. The CSI compression model and the CSI compression recovery model are provided by the model management platform, and the model management platform can provide the CSI compression model and the CSI compression recovery model of each manufacturer. The terminal device only needs to support the deployment of the CSI compression model and the operation of the CSI compression model. Compared with the terminal device generating the CSI compression model, the power consumption and computing power of the terminal device can be saved to a certain extent. Similarly, the network device only needs to support the deployment of the CSI compression recovery model and the operation of the CSI compression recovery model.

[0089] In an embodiment of the present application, a terminal device may download a CSI compression model from a model management platform. Optionally, the terminal device performs digital signature verification on the downloaded CSI compression model. For a CSI compression model that passes the verification, the terminal device may use it; for a CSI compression model that fails the verification, the terminal device may uninstall or discard it. Similarly, a network device may download a CSI compression recovery model from a model management platform. Optionally, the network device performs digital signature verification on the downloaded CSI compression recovery model. For a CSI compression recovery model that passes the verification, the network device may use it; for a CSI compression recovery model that fails the verification, the network device may uninstall or discard it. The models provided by the model management platform are more diverse than the models generated by the terminal device and the network device. The terminal device and the network device may select a model according to actual needs to adapt to changes in communication scenarios. The terminal device and the network device perform digital signature verification on the downloaded model to ensure the security of the downloaded model.

[0090] The following describes in detail the CSI compression model indication method provided in the embodiment of the present application based on the system architecture shown in FIG1 .

[0091] Please refer to FIG3 , which is a flowchart of a CSI compression model indication method provided in an embodiment of the present application. The method may include but is not limited to the following steps:

[0092] 301. The terminal device downloads M CSI compression models from the model management platform based on the model capability information of the terminal device, where M is a positive integer greater than or equal to 1.

[0093] Among them, the model capability information is used to describe the terminal device's support capability and / or processing capability for the CSI compression model. The support capability indicates which CSI compression model(s) the terminal device supports, and the processing capability indicates which CSI compression model(s) the terminal device can process or run. The model capability information may include the model identifiers of the CSI compression models supported by the terminal device, and / or the model processing capability of the terminal device. The model identifiers of the supported CSI compression models indicate which CSI compression models are supported. The model processing capability indicates which CSI compression model(s) can be processed or run, and may include but is not limited to computing, storage, co-processing and other capabilities.

[0094] Based on its model capability information, the terminal device downloads M CSI compression models from the model management platform. The M CSI compression models can be understood as CSI compression models supported and / or processable by the terminal device, or as CSI compression models that match the model capability information. The value of M depends on the model capability information of the terminal device. For example, if the terminal device supports CSI compression model a and CSI compression model b, the terminal device can download CSI compression model a and CSI compression model b from the model management platform. a and b can be understood as model identifiers of the CSI compression models.

[0095] The terminal device downloads M CSI compression models from the model management platform, which can be: the terminal device sends a CSI compression model download request to the model management platform, and the CSI compression model download request may include the model identifier of each CSI compression model in the M CSI compression models; the model management platform receives the CSI compression model download request, extracts the M CSI compression models, and sends a CSI compression model download response to the terminal device, and the CSI compression model download response may include the M CSI compression models.

[0096] For any of the M CSI compression models, each CSI compression model includes model information. That is, each CSI compression model includes model information, and the model information for different CSI compression models may vary. The model information may include one or more of a model identifier, model overhead information, model applicability speed information, and model deployment information.

[0097] Among them, the model identifier is the model ID, which is used to identify the CSI compression model. The model overhead information indicates the number of CSI reporting bits, that is, the number of CSI reporting bits corresponding to the CSI compression model. That is to say, for a CSI compression model, based on the number of bits occupied by the CSI when reporting CSI. The model applicable speed information indicates the applicable speed range, that is, the applicable speed range corresponding to the CSI compression model. That is to say, for a CSI compression model, in which speed range can it work more accurately and reflect the channel status more accurately. The model deployment information indicates deployment on the terminal device. For a CSI compression model, its model deployment information indicates that the CSI compression model is deployed on the terminal device side. When the model deployment information indicates deployment on the terminal device side or the network device side, 1 bit indication can be used. For example, when the value of this bit is 1, it indicates deployment on the terminal device side.

[0098] For example, the model information of a CSI compression model can be expressed as {ID: a, c: 30 bits, v: 101-200 km / h, i: 1}, where ID a indicates that the model identifier of the CSI compression model is a; c indicates model overhead information, whose value is 30 bits, indicating that the feedback CSI can be represented by 30 bits; v indicates model applicable speed information, whose value is 101-200 km / h, indicating that the CSI compression model is applicable to terminal equipment with a speed range of 101-200 km / h; i indicates model deployment information, whose value is 1, indicating that the CSI compression model is deployed on the terminal equipment.

[0099] The CSI compression model downloaded by the terminal device from the model management platform includes model information. Different CSI compression models have different model information. Model information can also be described as a model tag, which is used to uniquely identify the CSI compression model.

[0100] The CSI-related AI model downloaded by the terminal device from the model management platform is called a CSI compression model. For a CSI compression model, there is a CSI compression recovery model corresponding to the CSI compression model, which is used to recover and decode the CSI. The CSI compression recovery model can be deployed on the network device. In other words, there is a one-to-one correspondence between the CSI compression model on the terminal device side and the CSI compression recovery model on the network device side, and the correspondence is unique. In other words, a CSI compression recovery model is used to recover and process the CSI based on the feedback of its corresponding CSI compression model. For example, CSI compression model a corresponds to CSI compression recovery model I, the terminal device feeds back CSI based on CSI compression model a, and the network device recovers the CSI based on CSI compression recovery model I.

[0101] For any CSI compression recovery model, it also includes model information, which includes one or more of a model identifier, model applicable speed information, and model deployment information. The model identifier, i.e., the model ID, is used to identify the CSI compression recovery model. The model applicable speed information indicates the applicable speed range, i.e., the applicable speed range of the CSI compression model corresponding to the CSI compression recovery model. The model deployment information indicates deployment on a network device.

[0102] For example, the model information of a CSI compression model can be represented as {ID:a, c:30 bits, v:101-200 km / h, i:1}, and its corresponding CSI compression recovery model can be represented as {ID:I, v:101-200 km / h, i:0}. ID I indicates that the model identifier of the CSI compression recovery model is I; v indicates the model applicable speed information, and its value is 101-200 km / h, indicating that the CSI compression recovery model corresponding to the CSI compression recovery model is applicable to terminal device speeds within the range of 101-200 km / h; i indicates model deployment information, and its value is 0, indicating that the CSI compression recovery model is deployed on a network device.

[0103] 302. The terminal device performs digital signature verification on the M CSI compression models.

[0104] The CSI compression model downloaded by the terminal device may also include a digital signature, and then the digital signature is verified. When the digital signatures of the M CSI compression models are verified, the capability information is sent to the network device. For CSI compression models whose digital signatures are not verified, the terminal device can uninstall or discard them. The embodiment shown in Figure 3 takes the example of M CSI compression models passing the digital signature verification. The process of the terminal device verifying the digital signature of the CSI compression model can refer to the specific description of the digital signature mentioned above, which will not be repeated here.

[0105] 303. In response to the M CSI compression models passing the digital signature verification, the capability information is sent to the network device. Correspondingly, the network device receives the capability information from the terminal device.

[0106] The capability information includes model identifiers of M CSI compression models.

[0107] When all M CSI compression models pass digital signature verification, capability information is sent to the network device, including the model identifiers of the M CSI compression models. The M CSI compression models are supported and downloaded by the terminal device. In other words, the terminal device reports the model identifiers of the supported and downloaded CSI compression models to the network device through capability information.

[0108] 304. The network device determines a first CSI compression model from the M CSI compression models based on the current communication scenario of the terminal device.

[0109] Upon receiving the capability information, the network device may determine a first CSI compression model from among the M CSI compression models based on the current communication scenario of the terminal device. Alternatively, the network device may determine the first CSI compression model based on the current communication scenario of the terminal device and the supported CSI compression models reported by the terminal device. The first CSI compression model is used by the terminal device to feedback CSI based on the first CSI compression model in the current communication scenario.

[0110] The current communication scenario of the terminal device may be a communication scenario determined by the network device through communication sensing technology when or after receiving the capability information. The network device determines the current communication scenario through communication sensing technology. For example, the network device measures the current operating speed of the terminal device by sending a positioning reference signal to the terminal device, and then determines the current communication scenario of the terminal device based on the current operating speed. For another example, the network device measures the current operating speed of the terminal device by sending a sensing signal to the terminal device and / or by measuring the sensing signal sent by the terminal device, and then determines the current communication scenario of the terminal device based on the current operating speed. For another example, the network device determines the current communication scenario of the terminal device by comparing the CSI fed back by the terminal device for the previous few times. The previous few times refer to the times before receiving the capability information. If the difference in the CSI fed back for the previous few times is within a certain range (i.e., the channel state does not change much), then it can be determined that the current communication scenario is an indoor communication scenario. The indoor communication scenario has lower requirements for the frequency and accuracy of CSI feedback and the feedback overhead requirement is relatively small. The embodiments of the present application do not limit the specific method by which the network device determines the current communication scenario through communication sensing technology.

[0111] When the current communication scenario of the terminal device is determined, a first CSI compression model that matches the current communication scenario is determined from the M CSI compression models supported and downloaded by the terminal device. Optionally, the network device determines the first CSI compression recovery model based on the current communication scenario of the terminal device and the model information of the M CSI compression recovery models, and then determines the first CSI compression model. The first CSI compression model corresponds to the first CSI compression recovery model. These M CSI compression recovery models are CSI compression recovery models corresponding to the M CSI compression models, and one CSI compression model corresponds to one CSI compression recovery model. The model applicability speed information in the CSI compression model is the same as the model applicability speed information in the CSI compression recovery model to which it corresponds, and then the first CSI compression recovery model can be determined from the M CSI compression recovery models based on the current communication scenario, and then the first CSI compression model is determined.

[0112] In one implementation, upon receiving capability information, the network device may download M CSI compression recovery models from the model management platform based on the model identifiers of the M CSI compression models included in the capability information. For example, the network device sends a CSI compression recovery model download request to the model management platform, and the CSI compression recovery model download request may include the model identifiers of the M CSI compression models or the model identifiers of the M CSI compression recovery models; the model management platform sends a CSI compression recovery model download response to the network device based on the CSI compression recovery model download request, and the CSI compression recovery model download response includes the M CSI compression recovery models. Furthermore, the network device may perform digital signature verification on the M CSI compression recovery models, and if all of them pass the verification, the step of determining the first CSI compression model may be executed, or the step of sending model indication information to the terminal device may be executed. The network device may discard the CSI compression recovery model that fails the verification.

[0113] In another implementation, the network device itself has a series of CSI compression and recovery models that have been contracted with the model management platform. Upon receiving capability information, the network device can extract M CSI compression and recovery models corresponding to the M CSI compression models to determine a first CSI compression model based on the current communication scenario of the terminal device. In other words, the network device's storage device (i.e., local storage device) includes a series of CSI compression and recovery models. Upon receiving capability information, the network device retrieves the CSI compression and recovery models corresponding to the M CSI compression models from the storage device, with the model identifier of each CSI compression model corresponding to the model identifier of each CSI compression and recovery model.

[0114] Exemplarily, the terminal device downloads three CSI compression models, which can be represented as CSI compression model a{ID:a, c:20bits, v:0-100km / h, i:1}, CSI compression model b{ID:b, c:30bits, v:101-200km / h, i:1}, and CSI compression model c{ID:c, c:40bits, v:>201km / h, i:1}, and the terminal device reports the model identifiers of these three CSI compression models through capability information. For example, the network device determines that the current communication scenario is a high-mobility scenario (>300km / h) through communication perception technology. Combined with the capability information of the terminal device, it can determine that the first CSI compression model is CSI compression model c. For another example, the network device determines that the current communication scenario is a low-mobility scenario (<50km / h) through communication perception technology. Combined with the capability information of the terminal device, it can determine that the first CSI compression model is CSI compression model a. For example, the network device uses communication sensing technology to determine that the current communication scenario is an indoor communication scenario where channel state changes infrequently. Combined with the terminal device's capability information, the network device can determine that the first CSI compression model is CSI compression model a. Indoor communication scenarios require lower frequency and accuracy of CSI feedback, and lower feedback overhead.

[0115] 305. The network device sends model indication information to the terminal device. Correspondingly, the terminal device receives the model indication information from the network device.

[0116] The model indication information is used to indicate the model identifier of the first CSI compression model.

[0117] When the network device determines the first CSI compression model, it sends model indication information to the terminal device, indicating the model identifier of the first CSI compression model. The terminal device can then feed back CSI to the network device based on the first CSI compression model.

[0118] The model indication information may be carried in DCI or MAC-CE. That is, the network device indicates the model identifier of the first CSI compression model to the terminal device via DCI or MAC-CE. If the model indication information is carried in DCI, the DCI may include a field whose value is used to indicate the model identifier of the first CSI compression model. If the model indication information is carried in MAC-CE, the MAC-CE may indicate the model identifier of the first CSI compression model via the value of an 8-bit string.

[0119] Optionally, the network device may configure a series of CSI compression model indexes for the terminal device through radio resource control (RRC) signaling. This series of CSI compression models corresponds to the CSI compression recovery models supported by the network device. Furthermore, upon determining the first CSI compression model, the network device may indicate the index of the first CSI compression model to the terminal device through DCI or MAC-CE. This can save the model indication overhead of DCI or MAC-CE.

[0120] In the embodiment shown in Figure 3, the terminal device reports the model identifier of the CSI compression model it supports through capability information, so that the network device indicates to the terminal device the first CSI compression model that matches the current communication scenario of the terminal device, so that the terminal device can feedback CSI based on the first CSI compression model, which can reduce the overhead of CSI feedback.

[0121] Please refer to FIG4 , which is a flowchart of another CSI compression model indication method provided in an embodiment of the present application. The method may include but is not limited to the following steps:

[0122] 401. The network device sends model identifiers of K CSI compression and recovery models to the terminal device. Correspondingly, the terminal device receives the model identifiers of the K CSI compression and recovery models from the network device. K is a positive integer greater than or equal to 1.

[0123] The K CSI compression and recovery models may be understood as CSI compression and recovery models supported by the network device.

[0124] In one implementation, before executing step 401, the network device may download K CSI compression recovery models from the model management platform. For example, the network device sends a CSI compression recovery model download request to the model management platform, and the CSI compression recovery model download request may include the model identifiers of the K CSI compression recovery models. Based on the CSI compression recovery model download request, the model management platform sends a CSI compression recovery model download response to the network device, and the CSI compression recovery model download response includes the K CSI compression recovery models. Furthermore, the network device may perform digital signature verification on the K CSI compression recovery models, and if all are verified successfully, step 401 may be executed. The network device may discard CSI compression recovery models that fail verification.

[0125] In another implementation, the model management platform may push multiple CSI compression and recovery models to the network device. The network device may support all or some of the pushed CSI compression and recovery models. The K CSI compression and recovery models may be all or some of the multiple CSI compression and recovery models pushed by the model management platform. Furthermore, the network device may perform digital signature verification on the pushed CSI compression and recovery models, indicate the CSI compression and recovery models that pass the verification to the terminal device, and discard CSI compression and recovery models that fail the verification.

[0126] 402. The terminal device downloads M CSI compression models from the model management platform based on the model capability information of the terminal device and the model identifiers of the K CSI compression recovery models, where M is a positive integer greater than or equal to 1.

[0127] The model capability information can be found in the detailed description in step 301 and will not be repeated here.

[0128] The M CSI compression models in step 402 can be understood as CSI compression models supported and / or processable by the terminal device, and corresponding to the CSI compression recovery model supported by the network device. In other words, the M CSI compression models are CSI compression models supported by both the terminal device and the network device. The value of M depends on the support capabilities of the terminal device and the network device for the CSI compression model. For example, the terminal device supports CSI compression model a (corresponding to CSI compression recovery model I) and CSI compression model b (corresponding to CSI compression recovery model II), and step 401 indicates CSI compression recovery model I, then the terminal device can download CSI compression model a from the model management platform. The process of the terminal device downloading the CSI compression model from the model management platform can refer to the specific description thereof in step 301, which will not be repeated here.

[0129] 403. The terminal device performs digital signature verification on the M CSI compression models.

[0130] The CSI compression model downloaded by the terminal device may also include a digital signature, and then the digital signature is verified. When the digital signatures of the M CSI compression models are verified, the capability information is sent to the network device. For CSI compression models whose digital signatures are not verified, the terminal device can uninstall or discard them. The embodiment shown in Figure 4 takes the example of M CSI compression models passing the digital signature verification. The process of the terminal device performing digital signature verification on the CSI compression model can refer to the specific description of the digital signature mentioned above, which will not be repeated here.

[0131] 404. In response to the M CSI compression models passing the digital signature verification, the capability information is sent to the network device. Correspondingly, the network device receives the capability information from the terminal device.

[0132] The capability information includes model identifiers of M CSI compression models, which are supported by both the terminal device and the network device and have been downloaded.

[0133] 405. The network device determines a first CSI compression model from M CSI compression models based on the current communication scenario of the terminal device.

[0134] 406. The network device sends model indication information to the terminal device. Correspondingly, the terminal device receives the model indication information from the network device. The model indication information is used to indicate the model identifier of the first CSI compression model.

[0135] The implementation process of step 405 and step 406 can refer to the specific description of step 304 and step 305, which will not be repeated here.

[0136] In the embodiment shown in Figure 4, the terminal device reports the model identifier of the CSI compression model supported by both it and the network device through capability information, so that the network device indicates to the terminal device the first CSI compression model that matches the current communication scenario of the terminal device, so that the terminal device can feedback CSI based on the first CSI compression model, which can reduce the overhead of CSI feedback.

[0137] The present application provides a communication device that can be used to implement the functions of the above-mentioned terminal equipment or network equipment. The communication device can be a terminal device or a network device. The communication device includes a unit that corresponds one-to-one to the method / operation / step / action performed by the terminal device or network device in the above-mentioned method embodiment. The unit can be a hardware circuit, or software, or a combination of a hardware circuit and software. Please refer to Figure 5, which shows a structural diagram of a communication device 500 of an embodiment of the present application. The communication device 500 may include an interface unit 501 and a processing unit 502. Specifically, the processing unit 502 is used to process signaling and / or data, and the signaling and / or data may be data received by the interface unit 501, and the processed signaling and / or data may also be sent by the interface unit 501;

[0138] In one embodiment, when the communication device 500 is a terminal device, wherein:

[0139] Interface unit 501 is used to download M CSI compression models from a model management platform based on the model capability information of the terminal device, where M is a positive integer greater than or equal to 1; in response to the M CSI compression models passing digital signature verification, send capability information to the network device, the capability information including model identifiers of the M CSI compression models, and these M CSI compression models are CSI compression models supported by the terminal device; receive model indication information from the network device, the model indication information is used to indicate a first CSI compression model, the M CSI compression models including the first CSI compression model, and the first CSI compression model matches the current communication scenario of the terminal device.

[0140] In this embodiment, for the specific implementation of the above-mentioned interface unit 501 and processing unit 502, reference may be made to the specific implementation steps of the terminal device in FIG3 or FIG4 , which will not be repeated here.

[0141] In another embodiment, when the communication device shown in FIG5 is a network device, wherein:

[0142] An interface unit 501 is configured to receive capability information from a terminal device, where the capability information includes model identifiers of M CSI compression models, where the M CSI compression models are CSI compression models supported by the terminal device;

[0143] The processing unit 502 is configured to determine a first CSI compression model from the M CSI compression models based on a current communication scenario of the terminal device;

[0144] The interface unit 501 is further used to send model indication information to the terminal device, where the model indication information is used to indicate the model identifier of the first CSI compression model.

[0145] In this embodiment, for the specific implementation of the above-mentioned interface unit 501 and processing unit 502, reference may be made to the specific implementation steps of the network device in FIG3 or FIG4 , which will not be repeated here.

[0146] FIG6 shows a communication device 600 provided in an embodiment of the present application, which is used to implement the functions of the aforementioned terminal device or network device. The device can be a communication device or a device used in a communication device, and the communication device can be a terminal device or a network device. The device used in the communication device can be a chip system or chip within the communication device. The chip system can be composed of a chip or can include a chip and other discrete components.

[0147] The communication device 600 includes at least one processor 610 for implementing the processing function of the device (such as a terminal device or a network device) in the method provided in the embodiment of the present application. The communication device 600 may also include a communication interface 620 for implementing the transceiver operation of the device (such as a terminal device or a network device) in the method provided in the embodiment of the present application. In the embodiment of the present application, the communication interface can be a transceiver, a circuit, a bus, a module or other type of communication interface for communicating with other devices via a transmission medium. For example, the communication interface 620 is used for the device in the communication device 600 to communicate with other devices. The processor 610 uses the communication interface 620 to send and receive data and is used to implement the method described in the above method embodiment.

[0148] The communication device 600 may also include at least one memory 630 for storing program instructions and / or data. The memory 630 is coupled to the processor 610. Coupling in the embodiments of the present application refers to an indirect coupling or communication connection between devices, units, or modules, which may be electrical, mechanical, or other forms, and is used for information exchange between the devices, units, or modules. The processor 610 may operate in conjunction with the memory 630. The processor 610 may execute program instructions stored in the memory 630. One or more memories may be included in the processor.

[0149] The specific connection medium between the communication interface 620, processor 610, and memory 630 is not limited in the embodiments of the present application. In Figure 6, the memory 630, processor 610, and communication interface 620 are connected via a bus. The bus is represented by a bold line in Figure 6. The connection between other components is only for schematic illustration and is not intended to be limiting. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, only one bold line is used in Figure 6, but this does not mean that there is only one bus or one type of bus.

[0150] When the communication device 600 is specifically a device for a device (such as a terminal device or a network device), for example, when the communication device 600 is specifically a chip or a chip system, the communication interface 620 may output or receive a baseband signal. When the communication device 600 is specifically a device (such as a terminal device or a network device), the communication interface 620 may output or receive a radio frequency signal. In an embodiment of the present application, the processor may be a general-purpose processor, a digital signal processor, an application-specific integrated circuit, a field programmable gate array or other programmable logic device, a discrete gate or transistor logic device, or a discrete hardware component, and may implement or execute the various methods, steps, and logic block diagrams disclosed in the embodiments of the present application. A general-purpose processor may be a microprocessor or any conventional processor, etc. The steps of the method disclosed in conjunction with the embodiments of the present application may be directly embodied as being executed by a hardware processor, or may be executed by a combination of hardware and software modules in the processor.

[0151] When the above-mentioned communication device 600 is a module applied to a base station, the base station module implements the functions of the base station in the above-mentioned method embodiment. The base station module receives information from other modules in the base station (such as a radio frequency module or an antenna), and the information is sent by the terminal to the base station; or, the base station module sends information to other modules in the base station (such as a radio frequency module or an antenna), and the information is sent by the base station to the terminal. The base station module here can be a baseband chip of a base station, or a centralized unit (CU), a distributed unit (DU) or other modules, or a device under an open access network (open RAN, O-RAN or ORAN) architecture, such as an open CU, an open DU or other devices.

[0152] It should be noted that the communication interface 620 may be used to execute the functions of the interface unit 501 , and the processor 610 may be used to execute the functions of the processing unit 502 , which will not be described in detail here.

[0153] When the above-mentioned communication device is a chip applied to a terminal device, the chip implements the functions of the terminal device in the above-mentioned method embodiment, and the chip receives information from other devices; or, the chip sends information to other devices.

[0154] When the communication device is a chip used in a network device, the chip implements the functions of the network device in the above method embodiment. The chip receives information from other devices; or the chip sends information to other devices.

[0155] It is understood that the processor in the embodiments of the present application may be a central processing unit (CPU), or may be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field programmable gate arrays (FPGA), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. The general-purpose processor may be a microprocessor or any conventional processor.

[0156] The method steps in the embodiments of the present application can be implemented by hardware or by a processor executing software instructions. The software instructions can be composed of corresponding software modules, which can be stored in random access memory (RAM), flash memory, read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), registers, hard disks, mobile hard disks, compact discs (CD-ROMs), or any other form of storage medium known in the art. An exemplary storage medium is coupled to the processor so that the processor can read information from the storage medium and write information to the storage medium. Of course, the storage medium can also be an integral part of the processor. The processor and storage medium can be located in an ASIC. In addition, the ASIC can be located in an access network device or a terminal. Of course, the processor and storage medium can also exist as discrete components in a terminal or access network device.

[0157] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer programs or instructions. When the computer program or instruction is loaded and executed on a computer, the process or function described in the embodiment of the present application is executed in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer program or instruction can be stored in a computer-readable storage medium or transmitted via the computer-readable storage medium. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server that integrates one or more available media. The available medium can be a magnetic medium, such as a floppy disk, a hard disk, or a magnetic tape; it can also be an optical medium, such as a digital video disk (DVD); it can also be a semiconductor medium, such as a solid state drive (SSD).

[0158] In the various embodiments of the present application, unless otherwise specified or there is a logical conflict, the terms and / or descriptions between different embodiments are consistent and can be referenced by each other. The technical features in different embodiments can be combined to form new embodiments according to their inherent logical relationships.

[0159] It is understood that the various numbers used in the embodiments of this application are merely for ease of description and are not intended to limit the scope of the embodiments of this application. The order of the sequence numbers of the above-mentioned processes does not necessarily imply a specific order of execution; the order of execution of the processes should be determined by their functions and inherent logic.

[0160] An embodiment of the present application further provides a computer-readable storage medium, in which computer-executable instructions are stored. When the computer-executable instructions are executed, the method executed by the terminal device or network device in the above method embodiment is implemented.

[0161] An embodiment of the present application further provides a computer program product, which includes a computer program. When the computer program is executed, the method executed by the terminal device or network device in the above method embodiment is implemented.

[0162] The present application also provides a communication system including a terminal device and a network device. Optionally, the system also includes a model management platform. Each device is configured to execute the method executed by each device in the above method embodiment.

[0163] It should be noted that for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that this application is not limited by the order of the actions described, because according to this application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by this application.

[0164] The descriptions of the various embodiments provided in this application can refer to each other. The descriptions of each embodiment have their own focus. For parts not described in detail in a particular embodiment, please refer to the relevant descriptions of other embodiments. For the convenience and brevity of description, for example, the functions and execution steps of the various devices and equipment provided in the embodiments of this application can refer to the relevant descriptions of the method embodiments of this application. The various method embodiments and the various device embodiments can also refer to, be combined with, or quote each other.

[0165] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some or all of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the scope of the technical solutions of the embodiments of the present application.

Claims

1. A CSI compression model indication method, characterized in that: include: Based on the model capability information of the terminal device, M CSI compression models are downloaded from the model management platform; M is a positive integer greater than or equal to 1; In response to the M CSI compression models passing the digital signature verification, sending capability information to the network device, the capability information including model identifiers of the M CSI compression models; Receive model indication information from the network device, where the model indication information is used to indicate a model identifier of a first CSI compression model, the M CSI compression models include the first CSI compression model, and the first CSI compression model matches a current communication scenario of the terminal device.

2. The method according to claim 1, wherein Any CSI compression model among the M CSI compression models includes model information, where the model information includes one or more of a model identifier, model overhead information, model applicability speed information, and model deployment information.

3. The method according to claim 2, wherein The model overhead information indicates the number of CSI reporting bits, the model applicable speed information indicates the applicable speed range, and the model deployment information indicates deployment on the terminal device.

4. The method according to any one of claims 1 to 3, wherein The downloading of M CSI compression models from the model management platform based on the model capability information of the terminal device includes: Based on the model capability information of the terminal device and the model identifiers of the K CSI compression recovery models, M CSI compression models are downloaded from the model management platform, where K is a positive integer greater than or equal to 1.

5. The method according to claim 4, wherein The method further comprises: The model identifiers of the K CSI compression and recovery models are received from the network device, where one model identifier of a CSI compression model corresponds to one model identifier of a CSI compression and recovery model.

6. The method according to any one of claims 1 to 3, wherein: The model capability information of the terminal device includes the model identifier of the CSI compression model supported by the terminal device and / or the model processing capability of the terminal device.

7. The method according to any one of claims 1 to 3, wherein: The model indication information is carried in downlink control information or a media access control-control element.

8. A CSI compression model indication method, characterized in that: include: receiving capability information from a terminal device, the capability information including model identifiers of M CSI compression models; the M CSI compression models are CSI compression models supported by the terminal device; M is a positive integer greater than or equal to 1; Determining a first CSI compression model from the M CSI compression models based on a current communication scenario of the terminal device; Send model indication information to the terminal device, where the model indication information is used to indicate a model identifier of the first CSI compression model.

9. The method according to claim 8, wherein The method further comprises: Based on the model identifiers of the M CSI compression models, M CSI compression recovery models are downloaded from the model management platform, where the model identifier of one CSI compression model corresponds to the model identifier of one CSI compression recovery model.

10. The method according to claim 9, wherein The method further comprises: Perform digital signature verification on the M CSI compression and recovery models.

11. The method according to claim 8, wherein The method further comprises: M CSI compression recovery models corresponding to the M CSI compression models are acquired from a storage device, where a model identifier of a CSI compression model corresponds to a model identifier of a CSI compression recovery model.

12. The method according to any one of claims 8 to 11, characterized in that The determining, based on a current communication scenario of the terminal device, a first CSI compression model from the M CSI compression models includes: In response to a current communication scenario of the terminal device being a high mobility scenario, determining a first CSI compression model that supports the high mobility scenario from the M CSI compression models; or, In response to a current communication scenario of the terminal device being a low mobility scenario, determining a first CSI compression model that supports the low mobility scenario from the M CSI compression models; or, In response to the current communication scenario of the terminal device being an indoor communication scenario, a first CSI compression model that supports the indoor communication scenario is determined from the M CSI compression models.

13. The method according to any one of claims 8 to 11, wherein: The method further comprises: Send model identifiers of K CSI compression recovery models to the terminal device, where the K CSI compression recovery models are CSI compression recovery models supported by the network device, and K is a positive integer greater than or equal to 1.

14. The method according to any one of claims 8 to 11, wherein: The model indication information is carried in downlink control information or a media access control-control element.

15. A communication device, characterized in that: The method comprises a module for executing the method according to any one of claims 1 to 7 or a module for executing the method according to any one of claims 8 to 14.

16. A communication device, characterized in that: The device comprises a processor, wherein the processor is configured to implement the method according to any one of claims 1 to 7 or the method according to any one of claims 8 to 14 through logic circuits and / or through executing computer programs or instructions.

17. The communication device according to claim 16, wherein: Also includes: A memory is used to store the computer program or instructions.

18. A communication device, characterized in that: The method comprises a processor and an interface circuit, wherein the interface circuit is used to receive signals from other communication devices outside the communication device and transmit them to the processor or send signals from the processor to other communication devices outside the communication device, and the processor is used to implement the method according to any one of claims 1 to 7 or the method according to any one of claims 8 to 14 through a logic circuit or executing code instructions.

19. A computer-readable storage medium, characterized in that The storage medium stores a computer program or instruction. When the computer program or instruction is executed by the communication device, the method according to any one of claims 1 to 7 or the method according to any one of claims 8 to 14 is implemented.

Images