Channel state indication feedback information transmission method, communication device, and storage medium

Abstract

Embodiments of the present disclosure relate to a channel state indication (CSI) feedback information transmission method, a communication device and a storage medium. A user equipment (UE) determines CSI feedback corresponding to each basic unit according to a basic unit of a CSI processing granularity, wherein the basic unit is smaller than a CSI measurement resource indicated by a network side; and transmits CSI feedback information containing the CSI feedback to a base station.

Description

Technical Field

[0001] This application relates to, but is not limited to, the field of wireless communication technology, and particularly to a method for transmitting Channel Status Indicator (CSI) feedback information, a communication device, and a storage medium. Background Technology

[0002] In 5G mobile communication systems, the Channel Status Indicator (CSI) is used to indicate the number of data streams a channel can carry, channel quality or signal-to-noise ratio, and channel matrix. As the number of antennas increases, the overhead of CSI feedback also increases. In particular, the Precoding Matrix Indicator (PMI), which represents the channel matrix within the CSI, further increases the overhead of CSI feedback.

[0003] The 3GPP (3rd Generation Partnership Project) uses Type I / II codebooks for channel matrix feedback. Both Type I and Type II codebooks are based on DFT vectors, but this requires that the antenna array be divided into horizontal and vertical dimensions, with the antennas uniformly arranged in each dimension. This imposes significant limitations on subsequent antenna hardware design, preventing the creation of customized antennas for different scenarios.

[0004] Type I / II codebook designs are based on the assumption of a uniform distribution of signal incident and departure angles. However, in real-world environments, the statistical patterns of signal arrival and departure angles are not uniformly distributed, and the statistical patterns differ for each base station device, leaving room for optimization. 3) Type I / II codebooks have their own application scope. Type I codebooks are relatively simple but have limited accuracy and are designed for single-user transmission. Type II codebooks, on the other hand, have high accuracy and can be used for multi-user transmission. Utilizing precise channel feedback, they can effectively eliminate inter-user interference, but the overhead is too high, leaving significant room for optimization. Summary of the Invention

[0005] In view of this, embodiments of the present disclosure provide a CSI feedback information transmission method, apparatus, communication device, and storage medium.

[0006] According to a first aspect of the present disclosure, a CSI feedback information transmission method is provided, wherein the method is executed by a user equipment (UE), comprising:

[0007] Based on the basic unit of CSI processing granularity, determine the CSI feedback corresponding to each basic unit; wherein, the basic unit is smaller than the CSI measurement resources indicated by the network side;

[0008] Send CSI feedback information, including the CSI feedback, to the base station.

[0009] According to a second aspect of the present disclosure, a CSI feedback information transmission method is provided, wherein the method is executed by a base station and includes:

[0010] The system receives CSI feedback information for multiple basic units sent by a user equipment (UE), wherein the CSI feedback information includes CSI feedback corresponding to each basic unit; wherein the CSI feedback is determined by the UE according to the basic unit corresponding to the CSI processing granularity, and wherein the basic unit is smaller than the CSI measurement resources indicated by the network side.

[0011] According to a third aspect of the present disclosure, a CSI feedback information transmission apparatus is provided, wherein it is applied to a user equipment (UE) and includes:

[0012] The first processing module is configured to determine the CSI feedback corresponding to each basic unit based on the basic unit of CSI processing granularity, wherein the basic unit is smaller than the CSI measurement resources indicated by the network side;

[0013] The first transceiver module is configured to send CSI feedback information, including the CSI feedback, to the base station.

[0014] According to a fourth aspect of the present disclosure, a CSI feedback information transmission apparatus is provided, wherein it is applied to a base station and includes:

[0015] The second transceiver module is configured to receive CSI feedback information for multiple basic units sent by a user equipment (UE), wherein the CSI feedback information includes CSI feedback corresponding to each basic unit; wherein the CSI feedback is determined by the UE according to the basic unit corresponding to the CSI processing granularity, and wherein the basic unit is smaller than the CSI measurement resources indicated by the network side.

[0016] According to a fifth aspect of the present disclosure, a communication device is provided, including a processor, a memory, and an executable program stored in the memory and executable by the processor, wherein when the processor executes the executable program, it performs the steps of the CSI feedback information transmission method as described in the first or second aspect.

[0017] According to a sixth aspect of the present disclosure, a storage medium is provided that stores an executable program thereon, wherein the executable program, when executed by a processor, implements the steps of the CSI feedback information transmission method as described in the first or second aspect.

[0018] According to the CSI feedback information transmission method, apparatus, communication device, and storage medium provided in this disclosure, the UE determines the CSI feedback corresponding to each basic unit based on the basic unit of CSI processing granularity, wherein the basic unit is smaller than the CSI measurement resources indicated by the network side; and sends CSI feedback information containing the CSI feedback to the base station. Thus, by using a basic unit smaller than the CSI measurement resources as the granularity for CSI processing, UEs that do not have the capability to perform CSI processing at the CSI measurement resource granularity can perform CSI processing, increasing the types of UEs that can perform CSI processing, reducing the resource overhead of UEs with weak compression capabilities, and improving the efficiency of CSI feedback.

[0019] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit the embodiments of this disclosure. Attached Figure Description

[0020] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments of the invention and, together with the description, serve to explain the principles of the embodiments of the invention.

[0021] Figure 1 This is a schematic diagram illustrating the structure of a wireless communication system according to an exemplary embodiment;

[0022] Figure 2 This is a flowchart illustrating a CSI feedback information transmission method according to an exemplary embodiment;

[0023] Figure 3 This is a schematic diagram of CSI feedback according to an exemplary embodiment;

[0024] Figure 4 This is a flowchart illustrating another CSI feedback information transmission method according to an exemplary embodiment;

[0025] Figure 5 This is a flowchart illustrating yet another CSI feedback information transmission method according to an exemplary embodiment;

[0026] Figure 6 This is a block diagram illustrating a CSI feedback information transmission device according to an exemplary embodiment;

[0027] Figure 7 This is a block diagram illustrating another CSI feedback information transmission device according to an exemplary embodiment;

[0028] Figure 8 This is a block diagram illustrating an apparatus for transmitting CSI feedback information according to an exemplary embodiment. Detailed Implementation

[0029] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with those of the present invention. Rather, they are merely examples of apparatuses and methods consistent with some aspects of the embodiments of the present invention.

[0030] The terminology used in this disclosure is for the purpose of describing particular embodiments only and is not intended to be limiting of the embodiments of this disclosure. The singular forms “a,” “the,” and “the” as used in this disclosure are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term “and / or” as used herein refers to and includes any and all possible combinations of one or more of the associated listed items.

[0031] It should be understood that although the terms first, second, third, etc., may be used to describe various information in embodiments of this disclosure, such information should not be limited to these terms. These terms are only used to distinguish information of the same type from one another. For example, first information may also be referred to as second information without departing from the scope of embodiments of this disclosure, and similarly, second information may also be referred to as first information. Depending on the context, the word "if" as used herein may be interpreted as "when," "when," or "in response to a determination."

[0032] Please refer to Figure 1 This illustration shows a schematic diagram of the structure of a wireless communication system provided in an embodiment of this disclosure. Figure 1 As shown, the wireless communication system is a communication system based on cellular mobile communication technology. The wireless communication system may include: a number of terminals 11 and a number of base stations 12.

[0033] Terminal 11 can be a device that provides voice and / or data connectivity to a user. Terminal 11 can communicate with one or more core networks via a Radio Access Network (RAN). Terminal 11 can be an Internet of Things (IoT) terminal, such as a sensor device, a mobile phone (or "cellular" phone), and a computer with an IoT terminal. For example, it can be a fixed, portable, pocket-sized, handheld, computer-embedded, or vehicle-mounted device. Examples include a station (STA), subscriber unit, subscriber station, mobile station, mobile station, remote station, access point, remote terminal, access terminal, user terminal, user agent, user device, or user equipment (UE). Alternatively, terminal 11 can also be a device in an unmanned aerial vehicle (UAV). Alternatively, terminal 11 can also be a vehicle-mounted device, such as a vehicle computer with wireless communication capabilities, or a wireless communication device connected to an external vehicle computer. Alternatively, terminal 11 can also be a roadside device, such as a street light, traffic light, or other roadside device with wireless communication capabilities.

[0034] Base station 12 can be a network-side device in a wireless communication system. This wireless communication system can be a fourth-generation mobile communication (4G) system, also known as a Long Term Evolution (LTE) system; or it can be a 5G system, also known as a New Radio (NR) system or a 5G NR system. Alternatively, it can be a next-generation system after 5G. In this case, the access network in the 5G system can be called NG-RAN (New Generation-Radio Access Network). Alternatively, it can be an MTC system.

[0035] In this embodiment, base station 12 can be an evolved NB (eNB) used in a 4G system. Alternatively, base station 12 can also be a gNB (gNB) using a centralized-distributed architecture in a 5G system. When base station 12 adopts a centralized-distributed architecture, it typically includes a central unit (CU) and at least two distributed units (DU). The central unit is equipped with a protocol stack of Packet Data Convergence Protocol (PDCP), Radio Link Control (RLC), and Media Access Control (MAC) layers; the distributed units are equipped with a physical (PHY) layer protocol stack. This disclosure does not limit the specific implementation of base station 12.

[0036] Base station 12 and terminal 11 can establish a wireless connection via a wireless air interface. In different implementations, the wireless air interface is a wireless air interface based on the fourth-generation mobile communication network technology (4G) standard; or, the wireless air interface is a wireless air interface based on the fifth-generation mobile communication network technology (5G) standard, such as a new air interface; or, the wireless air interface can also be a wireless air interface based on a next-generation mobile communication network technology standard based on 5G.

[0037] In some embodiments, terminals 11 can also establish E2E (End to End) connections. Examples include V2V (vehicle to vehicle), V2I (vehicle to Infrastructure), and V2P (vehicle to pedestrian) communication scenarios in vehicle-to-everything (V2X) communication.

[0038] In some embodiments, the wireless communication system described above may further include a network management device 13.

[0039] Several base stations 12 are respectively connected to a network management device 13. The network management device 13 can be a core network device in a wireless communication system, such as an Access and Mobility Management Function (AMF), Session Management Function (SMF), User Plane Function (UPF), Policy Control Function (PCF), or Network Repository Function (NRF). The implementation of the network management device 13 is not limited in this embodiment.

[0040] The execution entities involved in the embodiments disclosed herein include, but are not limited to: UEs such as mobile phone terminals in cellular mobile communication systems, network-side equipment such as access network equipment such as base stations, and core networks.

[0041] The relevant technology uses an artificial intelligence (AI) learning model for AI compression.

[0042] Introducing AI technology can effectively solve the problems existing in Type I / II codebooks:

[0043] 1) For base station antenna arrays that are not neatly arranged, channel data is obtained through simulation modeling, field data acquisition, etc., and specialized AI network training is performed to obtain a matching AI network.

[0044] 2) For complex real-world scenarios, field data collection can also be used to perform specific optimizations for a particular base station.

[0045] 3) For different scenarios and needs, different feedback bits can be used to train the AI ​​network to achieve channel matrix feedback with arbitrary feedback bits and arbitrary precision requirements.

[0046] The AI-based CSI compression scheme considers utilizing the image compression performance of AI, processing the full channel information or feature vector as the image to be compressed, and performing image restoration at the receiving end so that the base station can adjust the corresponding parameters.

[0047] Different numbers of input parameters in CSI compression require different AI models.

[0048] In related technologies, AI models are based on CSI compression across the entire bandwidth (such as BWP). Such compression can fully utilize channel correlation in the frequency domain, but it also has the following problems in actual deployment:

[0049] In actual deployments, terminals may be configured with different BWPs or different CSI measurement resources. If full bandwidth compression is performed in this case, different configurations require corresponding AI models for matching. This poses significant challenges to air interface overhead, terminal storage, and model management.

[0050] In addition, different terminals have different processing capabilities. Some terminals can perform high-bandwidth, multi-input AI compression inference, while others can only perform low-bandwidth AI processing and do not support high-bandwidth AI processing.

[0051] Therefore, how to reduce the management complexity of AI models, improve the flexibility of AI model applications, and enable AI models to adapt to terminals with different capabilities are urgent problems to be solved.

[0052] like Figure 2 As shown, this exemplary embodiment provides a CSI (Channel Status Indicator) feedback information transmission method, which can be executed by a UE in a cellular mobile communication system, including:

[0053] Step 201: Determine the CSI feedback corresponding to each basic unit based on the basic unit of CSI processing granularity; wherein, the basic unit is smaller than the CSI measurement resources indicated by the network side;

[0054] Step 202: Send CSI feedback information containing the CSI feedback to the base station.

[0055] UE can be a terminal such as a mobile phone in a communication system.

[0056] In this embodiment, the basic unit is smaller than the CSI measurement resource indicated by the network side. CSI can be used by the UE to feed back downlink channel quality to the base station. The CSI measurement resource can be the time-domain and / or frequency-domain resources of the downlink channel that CSI can feed back; in one implementation, the CSI measurement resource can be the UE's active BWP. In one implementation, the basic unit is smaller than the active BWP; that is, the UE's active BWP is divided into at least two basic units so that the UE determines CSI feedback for each basic unit.

[0057] In this embodiment of the disclosure, CSI measurement resources can be divided into I basic units, and I CSI feedbacks can be concatenated into a complete CSI feedback message and sent to the base station. Alternatively, all I CSI feedbacks can be sent to the base station, which can then concatenate them into a complete CSI feedback message.

[0058] In this embodiment of the disclosure, the UE can perform CSI processing on all or some basic units and generate CSI feedback information to send to the base station.

[0059] CSI measurement resources can be indicated by the network side. The UE can measure the channel quality within the CSI measurement resource range and provide feedback via CSI.

[0060] For example, CSI measurement resources can be the full bandwidth used by the UE for current data communication with the base station, the bandwidth occupied by the CSI-RS configured on the network side, or a bandwidth range configured on the network side. The bandwidth occupied by the CSI-RS can be the bandwidth occupied by the CSI-RS at the same time domain location, or the bandwidth occupied by the CSI-RS at different time domain locations.

[0061] For example, the UE can use an AI model to process data at the basic unit level within the CSI measurement resource range, thereby obtaining the CSI feedback corresponding to each basic unit within the CSI measurement resource range.

[0062] The UE can divide CSI measurement resources into multiple basic units as the processing granularity, perform CSI processing on each basic unit, and obtain the corresponding CSI feedback for each basic unit. The processing can include any of the following: measurement, prediction, or compression.

[0063] A basic unit can be the smallest resource unit of the downlink channel corresponding to the CSI that the UE can feed back. The basic unit can be the time-domain and / or frequency-domain resources of the downlink channel. The basic unit can be determined based on the UE's processing capabilities. For example, the bandwidth corresponding to the CSI feedback that a UE with poor performance can process can be used as the basic unit; that is, UEs with different processing capabilities can all use the basic unit as the processing granularity. The bandwidth corresponding to the CSI feedback can be the bandwidth of the downlink channel corresponding to the fed-back CSI.

[0064] For example, the basic unit for processing CS can be defined as 4 RBs or 8 RBs in the frequency domain. In one possible implementation, the basic unit can be determined based on the number of RBs in the BWP corresponding to the UE. For example, when the BWP bandwidth is > X RBs, the basic unit size is 8 RBs; otherwise, the basic unit size is 4 RBs.

[0065] In one embodiment, the CSI measurement resource includes I basic units, where I is a positive integer greater than or equal to 2.

[0066] When configuring CSI measurement resources for terminals that require CSI feedback, the network can allocate them using basic units as the unit of allocation. The network configures CSI measurement resources in integer numbers of basic units. For example, if the basic unit is 6 RBs, then the physical resources corresponding to the objects being measured and fed back, i.e., the CSI measurement resources, are integer multiples of 6 RBs.

[0067] In one embodiment, sending CSI feedback information containing the CSI feedback to the base station includes:

[0068] Send CSI feedback information containing CSI feedback corresponding to each of the multiple basic units.

[0069] CSI measurement resources can be divided into I basic units, and the CSI feedback corresponding to each basic unit can be determined. The CSI feedback from each basic unit can be combined into CSI feedback information, which is then sent to the base station. Here, I is a positive integer greater than or equal to 2. In this way, CSI feedback information of the CSI measurement resources can be fed back, realizing feedback on channel quality within the CSI measurement resource range. Of course, in all embodiments of this disclosure, the CSI measurement resources can also be divided into I basic units, and the CSI feedback corresponding to some of these basic units can be determined; then, these CSI feedbacks can be combined into CSI feedback information, which is then sent to the base station.

[0070] In this way, by using a basic unit smaller than CSI measurement resources (e.g., BWP bandwidth) as the granularity for CSI processing, UEs that do not have the capability to perform CSI processing at the CSI measurement resource granularity can perform CSI processing. This increases the types of UEs that can perform CSI processing, reduces the resource overhead of UEs with weak compression capabilities, and improves the efficiency of CSI feedback.

[0071] In one embodiment, the CSI measurement resource is a bandwidth portion (BWP).

[0072] The network can assign one or more BWPs to the UE. At the same time-domain location, the UE can activate one BWP for data transmission. The UE can perform channel measurements or predictions based on the activated BWP.

[0073] For example, such as Figure 3 As shown, a BWP can be divided into four basic units: H1 to H4. CSI processing is performed on each basic unit to obtain four CSI feedbacks. The four CSI feedbacks are then concatenated into a complete CSI feedback message and sent to the base station.

[0074] The basic unit is smaller than the CSI measurement resource indicated by the network side, and may include: the basic unit is a subband of BWP in the frequency domain.

[0075] In one embodiment, the basic unit covers N frequency domain resources corresponding to the Channel State Indication Reference Signal (CSI-RS) in the frequency domain, where N is a positive integer and N is less than M, where M is the total number of frequency domain resources corresponding to the CSI-RS indicated by the network side.

[0076] The network side can indicate the total number M of frequency domain resources for CSI-RS that the UE needs to measure. The CSI measurement resources can be the bandwidth occupied by M frequency domain resources. The UE can perform CSI processing with the bandwidth occupied by N frequency domain resources as the basic unit and obtain the CSI feedback corresponding to each basic unit.

[0077] In one embodiment, the time-domain locations of the M frequency-domain resources may be the same or different. The CSI processing results of CSI-RS at different time-domain locations can be sent to the base station through the same CSI feedback information.

[0078] In one embodiment, the N frequency domain resources are located in the same time domain.

[0079] or,

[0080] The time-domain locations of the N frequency domain resources are not all the same.

[0081] A basic unit can cover N frequency domain resources that have the same time domain location. A basic unit can also cover N frequency domain resources at different time domain locations. The UE can also compress N frequency domain resources at different time domain locations into one CSI feedback, that is, use N frequency domain resources at different time domain locations as a CSI processing unit.

[0082] In one embodiment, determining the CSI feedback corresponding to each basic unit based on the basic unit of CSI processing granularity includes:

[0083] The basic unit for determining the CSI processing granularity is determined; based on the machine learning model corresponding to the basic unit, the CSI corresponding to each basic unit is determined.

[0084] For example, the basic unit can be determined based on the UE's processing capabilities. For instance, the bandwidth corresponding to the CSI feedback that a UE with poor performance can process can be used as the basic unit; that is, UEs with different processing capabilities can all use the basic unit as the processing granularity. For example, the basic unit can also be determined based on the quantity of CSI measurement resources. If there are many CSI measurement resources, the basic unit can be configured to be larger; if there are few CSI measurement resources, the basic unit can be configured to be smaller.

[0085] Machine learning models can perform CSI processing on corresponding basic units to obtain CSI feedback from those units. Machine learning models can include AI models, etc.

[0086] For CSI measurement resources comprising multiple basic units, machine learning models can be used to process the CSI of each basic unit separately. One machine learning model can correspond to one or more basic units.

[0087] Different CSI measurement resources may contain different numbers of basic units. A machine learning model can be determined for each basic unit to be used in CSI processing. This machine learning model can be determined by the network-side device and configured for the UE, determined by the UE, or jointly determined by the UE and the network-side device.

[0088] In one possible implementation, the network side can designate different CSI measurement resources. The UE can determine the machine learning model for CSI processing from a pre-configured machine learning model. This eliminates the need to retrain or configure the machine learning model based on the parameters of each CSI measurement resource, thereby reducing the complexity of machine learning model management.

[0089] Machine learning models can be deployed on the UE side for processing such as CSI compression to obtain CSI feedback. Machine learning models can also be deployed on the network side, such as at base stations, to decompress CSI feedback. Machine learning models can be deployed on any node in the network; there are no restrictions on where they can be placed.

[0090] For example, the network side can determine the corresponding machine learning model based on the determined basic unit and deploy the model on the network. The UE can determine the corresponding machine learning model based on the determined basic unit and deploy the model on the UE side.

[0091] In one embodiment, the machine learning model corresponding to the basic unit is trained using the full-channel information and / or feature vectors corresponding to the basic unit.

[0092] Here, the machine learning model for each basic unit can be trained using the full-channel information and / or feature vector of the corresponding basic unit. This can improve the accuracy of the machine learning model in performing CSI processing on the basic unit.

[0093] For example, an AI model can be trained on the network side or at any node in the network based on basic units, with different basic units corresponding to different AI models. The input to the AI ​​model is the parameters of the basic unit performing CSI processing, such as the full-channel information and / or feature vector of the basic unit.

[0094] In one embodiment, the basic unit is determined based on the CSI measurement resources;

[0095] And / or,

[0096] The basic unit is determined based on the UE's ability to process CSI.

[0097] The basic unit can be determined by the UE or by the network side, such as the core network or base station. The UE or network side can determine the basic unit based on CSI measurement resources. For example, CSI measurement resources can be divided into multiple basic units. The bandwidth of each basic unit can be the same or different.

[0098] The UE or network side can determine the basic unit based on the UE's bandwidth capability for processing CSI. For example, the maximum bandwidth that the UE can process CSI can be used as the basic unit. Alternatively, the maximum bandwidth that a UE with weaker processing capabilities in the network can process CSI can be used as the basic unit. In this way, the basic unit can meet the processing capabilities of different types of UEs, improving the compatibility of CSI processing.

[0099] In one embodiment,

[0100] In response to the fact that the bandwidth of the CSI measurement resource in the frequency domain is greater than a bandwidth threshold, the bandwidth of the basic unit in the frequency domain is a first bandwidth;

[0101] or,

[0102] In response to the fact that the bandwidth of the CSI measurement resource in the frequency domain is less than or equal to the bandwidth threshold, the bandwidth of the basic unit in the frequency domain is the second bandwidth; wherein the first bandwidth is greater than the second bandwidth.

[0103] Here, when CSI measurement resources are large, such as when CSI measurement resources are greater than the bandwidth threshold, basic unit bits with larger bandwidth can be used; when CSI measurement resources are small, such as when CSI measurement resources are less than or equal to the bandwidth threshold, basic unit bits with smaller bandwidth can be used.

[0104] For example, if the BWP bandwidth is greater than X RBs, then the basic unit is 8 RBs. Otherwise, the basic unit is 4 RBs. Here, X can be 100, etc.

[0105] like Figure 4 As shown, this exemplary embodiment provides a CSI (Channel Status Indicator) feedback information transmission method, which can be executed by a base station of a cellular mobile communication system, including:

[0106] Step 401: Receive CSI feedback information sent by the UE for multiple basic units, wherein the CSI feedback information includes CSI feedback corresponding to each basic unit; wherein the CSI feedback is determined by the UE according to the basic unit corresponding to the CSI processing granularity, wherein the basic unit is smaller than the CSI measurement resources indicated by the network side.

[0107] UE can be a terminal such as a mobile phone in a communication system.

[0108] For example, the UE can use an AI model to process data within the CSI measurement resource range, using basic units as the processing granularity, to obtain the CSI feedback corresponding to each basic unit within the CSI measurement resource range.

[0109] In this embodiment of the disclosure, CSI measurement resources can be divided into I basic units, and I CSI feedbacks can be concatenated into a complete CSI feedback message and sent to the base station. Alternatively, all I CSI feedbacks can be sent to the base station, which can then concatenate them into a complete CSI feedback message.

[0110] In this embodiment of the disclosure, the UE can perform CSI processing on all or some basic units and generate CSI feedback information to send to the base station.

[0111] In this embodiment, the basic unit is smaller than the CSI measurement resource indicated by the network side. CSI can be used by the UE to feed back downlink channel quality to the base station. The CSI measurement resource can be the time-domain and / or frequency-domain resources of the downlink channel that CSI can feed back; in one implementation, the CSI measurement resource can be the UE's active BWP. In one implementation, the basic unit is smaller than the active BWP; that is, the UE's active BWP is divided into at least two basic units so that the UE determines CSI feedback for each basic unit.

[0112] CSI measurement resources can be indicated by the network side. The UE can measure the channel quality within the CSI measurement resource range and provide feedback via CSI.

[0113] For example, CSI measurement resources can be the full bandwidth used by the UE for current data communication with the base station, the bandwidth occupied by the CSI-RS configured on the network side, or a bandwidth range configured on the network side. The bandwidth occupied by the CSI-RS can be the bandwidth occupied by the CSI-RS at the same time domain location, or the bandwidth occupied by the CSI-RS at different time domain locations.

[0114] For example, the UE can use an AI model to process data at the basic unit level within the CSI measurement resource range, thereby obtaining the CSI feedback corresponding to each basic unit within the CSI measurement resource range.

[0115] The UE can divide CSI measurement resources into multiple basic units as the processing granularity, perform CSI processing on each basic unit, and obtain the corresponding CSI feedback for each basic unit. The processing can include any of the following: measurement, prediction, or compression.

[0116] A basic unit can be the smallest resource unit of the downlink channel corresponding to the CSI that the UE can feed back. The basic unit can be the time-domain and / or frequency-domain resources of the downlink channel. The basic unit can be determined based on the UE's processing capabilities. For example, the bandwidth corresponding to the CSI feedback that a UE with poor performance can process can be used as the basic unit; that is, UEs with different processing capabilities can all use the basic unit as the processing granularity. The bandwidth corresponding to the CSI feedback can be the bandwidth of the downlink channel corresponding to the fed-back CSI.

[0117] For example, the basic unit for processing CS can be defined as having 4 RBs or 8 RBs in the frequency domain. In one possible implementation, the basic unit can be determined based on the number of RBs in the BWP corresponding to the UE. For example, when the BWP bandwidth is > X RBs, the basic unit size is 8 RBs; otherwise, the basic unit size is 4 RBs.

[0118] The basic unit can be determined based on the UE's processing capabilities. For example, the bandwidth corresponding to the CSI feedback that can be processed with lower performance can be used as the basic unit, meaning that UEs with different processing capabilities can all process data using the basic unit as the processing granularity. The bandwidth corresponding to the CSI feedback can be the bandwidth of the downlink channel corresponding to the fed-out CSI.

[0119] In one embodiment, the CSI measurement resource includes I basic units, where I is a positive integer greater than or equal to 2.

[0120] When configuring CSI measurement resources for terminals that require CSI feedback, the network can allocate them using basic units as the unit of allocation. The network configures CSI measurement resources in integer numbers of basic units. For example, if the basic unit is 6 RBs, then the physical resources corresponding to the objects being measured and fed back, i.e., the CSI measurement resources, are integer multiples of 6 RBs.

[0121] In one embodiment, receiving CSI feedback information sent by the user equipment (UE) that includes CSI feedback corresponding to each basic unit includes:

[0122] Receive CSI feedback information containing CSI feedback corresponding to each of the multiple basic units.

[0123] CSI measurement resources can be divided into I basic units, and the corresponding CSI feedback for each basic unit can be determined. These CSI feedbacks can be combined into a single CSI feedback message and sent to the base station. Here, I is a positive integer greater than or equal to 2. In this way, the CSI of the CSI measurement resources can be fed back, enabling feedback on channel quality within the CSI measurement resource range.

[0124] For example, I CSI feedbacks can be concatenated into a complete CSI feedback message and sent to the base station. Alternatively, all I CSI feedbacks can be sent to the base station, which will then concatenate them into a complete CSI feedback message.

[0125] In this way, by using a basic unit smaller than CSI measurement resources (e.g., BWP bandwidth) as the granularity for CSI processing, UEs that do not have the capability to perform CSI processing at the CSI measurement resource granularity can perform CSI processing. This increases the types of UEs that can perform CSI processing, reduces the resource overhead of UEs with weak compression capabilities, and improves the efficiency of CSI feedback.

[0126] In one embodiment, the CSI measurement resource is a bandwidth portion (BWP).

[0127] The network can assign one or more BWPs to the UE. At the same time-domain location, the UE can activate one BWP for data transmission. The UE can perform channel measurements or predictions based on the activated BWP.

[0128] For example, such as Figure 3 As shown, a BWP can be divided into four basic units: H1 to H4. CSI processing is performed on each basic unit to obtain four CSI feedbacks. The four CSI feedbacks are then concatenated into a complete CSI feedback message and sent to the base station.

[0129] The basic unit is smaller than the CSI measurement resource indicated by the network side, and may include: the basic unit is a subband of BWP in the frequency domain.

[0130] In one embodiment, the basic unit covers N frequency domain resources corresponding to the Channel State Indication Reference Signal (CSI-RS) in the frequency domain, where N is a positive integer and N is less than M, where M is the total number of frequency domain resources corresponding to the CSI-RS indicated by the network side.

[0131] The network side can indicate the total number M of frequency domain resources for CSI-RS that the UE needs to measure. The CSI measurement resources can be the bandwidth occupied by M frequency domain resources. The UE can perform CSI processing with the bandwidth occupied by N frequency domain resources as the granularity, i.e., the basic unit, to obtain the CSI feedback corresponding to the basic unit.

[0132] In one embodiment, the time-domain locations of the M frequency-domain resources may be the same or different. The CSI processing results of CSI-RS at different time-domain locations can be sent to the base station through the same CSI feedback information.

[0133] In one embodiment,

[0134] The N frequency domain resources are in the same time domain position;

[0135] or,

[0136] The time-domain locations of the N frequency domain resources are not all the same.

[0137] A basic unit can cover N frequency domain resources that have the same time domain location. A basic unit can also cover N frequency domain resources at different time domain locations. The UE can also compress N frequency domain resources at different time domain locations into one CSI feedback, that is, use N frequency domain resources at different time domain locations as a CSI processing unit.

[0138] In one embodiment, such as Figure 5 As shown, the method further includes:

[0139] Step 501: Using the machine learning model corresponding to the basic unit, decompress the CSI corresponding to the basic unit.

[0140] Step 501 can be performed alone or in conjunction with step 401.

[0141] Machine learning models can perform CSI processing on corresponding basic units to obtain CSI feedback from those units. Machine learning models can include AI models, etc.

[0142] For CSI measurement resources comprising multiple basic units, machine learning models can be used to process the CSI of each basic unit separately. One machine learning model can correspond to one or more basic units.

[0143] Different CSI measurement resources may contain different numbers of basic units. A machine learning model can be determined for each basic unit to be used in CSI processing. This machine learning model can be determined by the network-side device and configured for the UE, determined by the UE, or jointly determined by the UE and the network-side device.

[0144] In one possible implementation, the network side can designate different CSI measurement resources. The UE can determine the machine learning model for CSI processing from a pre-configured machine learning model. This eliminates the need to retrain or configure the machine learning model based on the parameters of each CSI measurement resource, thereby reducing the complexity of machine learning model management.

[0145] Machine learning models can be deployed on the UE side for processing such as CSI compression to obtain CSI feedback. Machine learning models can also be deployed on the network side, such as at base stations, to decompress CSI feedback. Machine learning models can be deployed on any node in the network; there are no restrictions on where they can be placed.

[0146] For example, the network side can determine the corresponding machine learning model based on the determined basic unit and deploy the model on the network. The UE can determine the corresponding machine learning model based on the determined basic unit and deploy the model on the UE side.

[0147] In one embodiment, the machine learning model corresponding to the basic unit is trained using the full-channel information and / or feature vectors corresponding to the basic unit.

[0148] Here, the machine learning model for each basic unit can be trained using the full-channel information and / or feature vector of the corresponding basic unit. This can improve the accuracy of the machine learning model in performing CSI processing on the basic unit.

[0149] For example, an AI model can be trained on the network side or at any node in the network based on basic units, with different basic units corresponding to different AI models. The input to the AI ​​model is the parameters of the basic unit performing CSI processing, such as the full-channel information and / or feature vector of the basic unit.

[0150] In one embodiment, the basic unit is determined based on the CSI measurement resources;

[0151] And / or,

[0152] The basic unit is determined based on the UE's ability to process CSI.

[0153] The basic unit can be determined by the UE or by the network side, such as the core network or base station.

[0154] The UE or network side can determine basic units based on CSI measurement resources. For example, CSI measurement resources can be divided into multiple basic units. The bandwidth of each basic unit can be the same or different.

[0155] The UE or network side can determine the basic unit based on the UE's bandwidth capability for processing CSI. For example, the maximum bandwidth that the UE can process CSI can be used as the basic unit. Alternatively, the maximum bandwidth that a UE with weaker processing capabilities in the network can process CSI can be used as the basic unit. In this way, the basic unit can meet the processing capabilities of different types of UEs, improving the compatibility of CSI processing.

[0156] In one embodiment, in response to the CSI measurement resource having a bandwidth in the frequency domain greater than a bandwidth threshold, the bandwidth of the basic unit in the frequency domain is a first bandwidth;

[0157] or,

[0158] In response to the fact that the bandwidth of the CSI measurement resource in the frequency domain is less than or equal to the bandwidth threshold, the bandwidth of the basic unit in the frequency domain is the second bandwidth; wherein the first bandwidth is greater than the second bandwidth.

[0159] Here, when CSI measurement resources are large, such as when CSI measurement resources are greater than the bandwidth threshold, basic unit bits with larger bandwidth can be used; when CSI measurement resources are small, such as when CSI measurement resources are less than or equal to the bandwidth threshold, basic unit bits with smaller bandwidth can be used.

[0160] For example, if the BWP bandwidth is greater than X RBs, then the basic unit is 8 RBs. Otherwise, the basic unit is 4 RBs. Here, X can be 100, etc.

[0161] The following provides a specific example in conjunction with any of the above embodiments:

[0162] 1. Define the basic unit of CSI compression processing. The basic unit can be a frequency sub-band or N time-frequency resources used by CSI-RS.

[0163] Multiple basic unit sizes can be defined on the system side, and different basic unit sizes can be determined by different terminal processing capabilities or different system bandwidths. For example, the basic unit for CSI compression can be defined as 4 RBs or 8 RBs. When the BWP bandwidth is > X RBs, the basic unit size is 8 RBs. Otherwise, the basic unit size is 4 RBs.

[0164] AI models can be trained on the network side or server side based on the size of the basic unit; different basic unit structures correspond to different AI models. The input to the AI ​​model corresponds to the full-channel information or feature vectors of the basic unit processed by CSI.

[0165] In response to the definition of multiple basic processing units, the network / terminal side downloads the corresponding model according to the determined basic unit size and deploys the model on the network / terminal side.

[0166] 2. When configuring resources for CSI feedback to terminals, the network can configure them in basic units, with the configured resources being integers and the number of basic units. For example, if the basic processing unit is 6 RBs, then the physical resources corresponding to the objects for CSI measurement and feedback will be integer multiples of 6 RBs.

[0167] 3. Terminal-side actions

[0168] When performing CSI compression, the terminal performs CSI compression sequentially in the frequency domain, using basic units as the unit.

[0169] When the terminal performs CSI feedback, it feeds back the bits after CSI compression of N basic units.

[0170] 4. Base station side actions

[0171] When the base station receives CSI feedback, it divides the entire CSI feedback bits into feedback bits corresponding to N basic CSI processing units. The terminal decompresses the feedback bits corresponding to each processing unit and replies with the channel information corresponding to each processing unit.

[0172] This invention also provides a CSI feedback information transmission device, such as... Figure 6 As shown, the CSI feedback information transmission device 100, applied to the UE, includes

[0173] The first processing module 110 is configured to determine the CSI feedback corresponding to each basic unit based on the basic unit of CSI processing granularity, wherein the basic unit is smaller than the CSI measurement resources indicated by the network side.

[0174] The first transceiver module 120 is configured to send CSI feedback information, including the CSI feedback, to the base station.

[0175] In one embodiment, the CSI measurement resource is a bandwidth portion (BWP).

[0176] In one embodiment,

[0177] The basic unit covers N frequency domain resources corresponding to the Channel State Indication Reference Signal (CSI-RS) in the frequency domain, where N is a positive integer and N is less than M, where M is the total number of frequency domain resources corresponding to the CSI-RS indicated by the network side.

[0178] In one embodiment, the N frequency domain resources are located in the same time domain.

[0179] or,

[0180] The time-domain locations of the N frequency domain resources are not all the same.

[0181] In one embodiment, the first processing module 110 is specifically configured as follows:

[0182] Determine the basic unit of CSI processing granularity; use the machine learning model corresponding to the basic unit to determine the CSI feedback corresponding to the basic unit.

[0183] In one embodiment, the machine learning model corresponding to the basic unit is trained using the full-channel information and / or feature vectors corresponding to the basic unit.

[0184] In one embodiment, the first transceiver module 120 is specifically configured as follows:

[0185] Send CSI feedback information containing CSI feedback corresponding to each of the multiple basic units.

[0186] In one embodiment, the basic unit is determined based on the CSI measurement resources;

[0187] And / or,

[0188] The basic unit is determined based on the UE's ability to process CSI.

[0189] In one embodiment, in response to the CSI measurement resource having a bandwidth in the frequency domain greater than a bandwidth threshold, the bandwidth of the basic unit in the frequency domain is a first bandwidth;

[0190] or,

[0191] In response to the fact that the bandwidth of the CSI measurement resource in the frequency domain is less than or equal to the bandwidth threshold, the bandwidth of the basic unit in the frequency domain is the second bandwidth; wherein the first bandwidth is greater than the second bandwidth.

[0192] In one embodiment, the CSI measurement resource includes I basic units, where I is a positive integer greater than or equal to 2.

[0193] This invention also provides a CSI feedback information transmission device, such as... Figure 7 As shown, the CSI feedback information transmission device 200 is applied to a base station. The CSI feedback information transmission device 200 includes:

[0194] The second transceiver module 210 is configured to receive CSI feedback information for multiple basic units sent by a user equipment (UE), wherein the CSI feedback information includes CSI feedback corresponding to each basic unit; wherein the CSI feedback is determined by the UE according to the basic unit corresponding to the CSI processing granularity, and wherein the basic unit is smaller than the CSI measurement resources indicated by the network side.

[0195] In one embodiment, the CSI measurement resource is a bandwidth portion (BWP).

[0196] In one embodiment, the basic unit covers N frequency domain resources corresponding to the Channel State Indication Reference Signal (CSI-RS) in the frequency domain, where N is a positive integer and N is less than M, where M is the total number of frequency domain resources corresponding to the CSI-RS indicated by the network side.

[0197] In one embodiment, the N frequency domain resources are located in the same time domain.

[0198] or,

[0199] The time-domain locations of the N frequency domain resources are not all the same.

[0200] In one embodiment, the device 200 further includes:

[0201] The second processing module 220 is configured to use the machine learning model corresponding to the basic unit to decompress the CSI corresponding to the basic unit.

[0202] In one embodiment, the machine learning model corresponding to the basic unit is trained using the full-channel information and / or feature vectors corresponding to the basic unit.

[0203] In one embodiment, receiving CSI feedback information sent by the user equipment (UE) that includes CSI feedback corresponding to each basic unit includes:

[0204] Receive CSI feedback information containing CSI feedback corresponding to each of the multiple basic units.

[0205] In one embodiment, the basic unit is determined based on the CSI measurement resources;

[0206] And / or,

[0207] The basic unit is determined based on the UE's ability to process CSI.

[0208] In one embodiment, in response to the CSI measurement resource having a bandwidth in the frequency domain greater than a bandwidth threshold, the bandwidth of the basic unit in the frequency domain is a first bandwidth;

[0209] or,

[0210] In response to the fact that the bandwidth of the CSI measurement resource in the frequency domain is less than or equal to the bandwidth threshold, the bandwidth of the basic unit in the frequency domain is the second bandwidth; wherein the first bandwidth is greater than the second bandwidth.

[0211] In one embodiment, the CSI measurement resource includes I basic units, where I is a positive integer greater than or equal to 2.

[0212] In an exemplary embodiment, the first processing module 110, the first transceiver module 120, the second transceiver module 210, and the second processing module 220 may be implemented by one or more central processing units (CPUs), graphics processing units (GPUs), baseband processors (BPs), application-specific integrated circuits (ASICs), DSPs, programmable logic devices (PLDs), complex programmable logic devices (CPLDs), field-programmable gate arrays (FPGAs), general-purpose processors, controllers, microcontrollers (MCUs), microprocessors, or other electronic components to perform the aforementioned method.

[0213] Figure 8 This is a block diagram illustrating an apparatus 3000 for transmitting CSI feedback information according to an exemplary embodiment. For example, apparatus 3000 may be a mobile phone, computer, digital broadcast terminal, messaging device, game console, tablet device, medical device, fitness equipment, personal digital assistant, etc.

[0214] Reference Figure 8 The device 3000 may include one or more of the following components: processing component 3002, memory 3004, power supply component 3006, multimedia component 3008, audio component 3010, input / output (I / O) interface 3012, sensor component 3014, and communication component 3016.

[0215] Processing component 3002 typically controls the overall operation of device 3000, such as operations associated with display, telephone calls, data communication, camera operation, and recording. Processing component 3002 may include one or more processors 3020 to execute instructions to complete all or part of the steps of the methods described above. Furthermore, processing component 3002 may include one or more modules to facilitate interaction between processing component 3002 and other components. For example, processing component 3002 may include a multimedia module to facilitate interaction between multimedia component 3008 and processing component 3002.

[0216] Memory 3004 is configured to store various types of data to support the operation of device 3000. Examples of this data include instructions for any application or method operating on device 3000, contact data, phonebook data, messages, pictures, videos, etc. Memory 3004 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk.

[0217] Power supply component 3006 provides power to various components of device 3000. Power supply component 3006 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power to device 3000.

[0218] Multimedia component 3008 includes a screen that provides an output interface between device 3000 and the user. In some embodiments, the screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen may be implemented as a touchscreen to receive input signals from the user. The touch panel includes one or more touch sensors to sense touches, swipes, and gestures on the touch panel. The touch sensors may sense not only the boundaries of touch or swipe actions but also the duration and pressure associated with the touch or swipe operation. In some embodiments, multimedia component 3008 includes a front-facing camera and / or a rear-facing camera. When device 3000 is in an operating mode, such as a shooting mode or a video mode, the front-facing camera and / or rear-facing camera may receive external multimedia data. Each front-facing camera and rear-facing camera may be a fixed optical lens system or have focal length and optical zoom capabilities.

[0219] Audio component 3010 is configured to output and / or input audio signals. For example, audio component 3010 includes a microphone (MIC) configured to receive external audio signals when device 3000 is in an operating mode, such as call mode, recording mode, and voice recognition mode. The received audio signals may be further stored in memory 3004 or transmitted via communication component 3016. In some embodiments, audio component 3010 also includes a speaker for outputting audio signals.

[0220] I / O interface 3012 provides an interface between processing component 3002 and peripheral interface modules, such as keyboards, click wheels, buttons, etc. These buttons may include, but are not limited to, home buttons, volume buttons, start buttons, and lock buttons.

[0221] Sensor assembly 3014 includes one or more sensors for providing state assessments of various aspects of device 3000. For example, sensor assembly 3014 may detect the on / off state of device 3000, the relative positioning of components such as the display and keypad of device 3000, changes in the position of device 3000 or a component of device 3000, the presence or absence of user contact with device 3000, the orientation or acceleration / deceleration of device 3000, and temperature changes of device 3000. Sensor assembly 3014 may include a proximity sensor configured to detect the presence of nearby objects without any physical contact. Sensor assembly 3014 may also include an optical sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, sensor assembly 3014 may also include an accelerometer, a gyroscope, a magnetometer, a pressure sensor, or a temperature sensor.

[0222] Communication component 3016 is configured to facilitate wired or wireless communication between device 3000 and other devices. Device 3000 can access wireless networks based on communication standards, such as Wi-Fi, 2G, or 3G, or combinations thereof. In one exemplary embodiment, communication component 3016 receives broadcast signals or broadcast-related information from an external broadcast management system via a broadcast channel. In one exemplary embodiment, communication component 3016 also includes a near-field communication (NFC) module to facilitate short-range communication. For example, the NFC module may be implemented based on radio frequency identification (RFID) technology, Infrared Data Association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology, and other technologies.

[0223] In an exemplary embodiment, the apparatus 3000 may be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field-programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to perform the methods described above.

[0224] In an exemplary embodiment, a non-transitory computer-readable storage medium including instructions is also provided, such as a memory 3004 including instructions, which can be executed by a processor 3020 of the device 3000 to perform the above-described method. For example, the non-transitory computer-readable storage medium may be a ROM, random access memory (RAM), CD-ROM, magnetic tape, floppy disk, and optical data storage device, etc.

[0225] Other embodiments of the invention will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the embodiments of the invention that follow the general principles of the embodiments of the invention and include common knowledge or customary techniques in the art not disclosed in this disclosure. The specification and embodiments are to be considered exemplary only, and the true scope and spirit of the embodiments of the invention are indicated by the following claims.

[0226] It should be understood that the embodiments of the present invention are not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from their scope. The scope of the embodiments of the present invention is limited only by the appended claims.

Claims

1. A method for transmitting Channel State Indicator (CSI) feedback information, wherein, Performed by the user equipment (UE), including: The basic unit for determining the granularity of CSI processing is determined based on the CSI measurement resources indicated by the network side and the UE's ability to process CSI. Select a machine learning model corresponding to the basic unit from the pre-configured machine learning models, wherein the machine learning model corresponding to the basic unit is trained using the full-channel information and feature vector corresponding to the basic unit, and one machine learning model corresponds to multiple basic units; The CSI feedback corresponding to the basic unit is determined based on the machine learning model corresponding to the basic unit. The basic unit for determining the CSI processing granularity includes: using the maximum bandwidth that the UE can process CSI as the bandwidth of the basic unit in the frequency domain, wherein the basic unit is smaller than the CSI measurement resource; The basic unit covers N frequency domain resources corresponding to the Channel State Indication Reference Signal (CSI-RS) in the frequency domain, where N is a positive integer and N is less than M, where M is the total number of frequency domain resources corresponding to the CSI-RS indicated by the network side, and the N frequency domain resources have the same time domain position. Send CSI feedback information, including the CSI feedback, to the base station.

2. The method according to claim 1, wherein, The CSI measurement resource is a bandwidth portion (BWP), wherein the BWP is an active BWP.

3. The method according to claim 1, wherein, Sending CSI feedback information containing the CSI feedback to the base station includes: Send CSI feedback information containing CSI feedback corresponding to each of the aforementioned basic units.

4. The method according to any one of claims 1 to 3, wherein, The more CSI measurement resources a unit has, the larger the basic unit becomes; the fewer CSI measurement resources a unit has, the smaller the basic unit becomes.

5. The method according to any one of claims 1 to 4, wherein, The CSI measurement resource includes I basic units, where I is a positive integer greater than or equal to 2; Specifically, sending CSI feedback information containing the CSI feedback to the base station includes: combining the CSI feedback corresponding to the I basic units together into CSI feedback information, and sending the CSI feedback information to the base station.

6. A method for transmitting Channel State Indicator (CSI) feedback information, wherein, Performed by the base station, including: Receive CSI feedback information sent by the user equipment (UE) that includes CSI feedback corresponding to the basic unit; The basic unit is determined by the UE based on the CSI measurement resources indicated by the network side and the UE's ability to process CSI. Wherein, the CSI feedback corresponding to the basic unit is determined by the UE based on the machine learning model corresponding to the basic unit; The machine learning model corresponding to the basic unit is selected by the UE from a pre-configured machine learning model. The machine learning model corresponding to the basic unit is trained using the full-channel information and feature vectors corresponding to the basic unit. One machine learning model corresponds to multiple basic units. Wherein, the maximum bandwidth that the UE can process CSI is the bandwidth of the basic unit in the frequency domain, and the basic unit is less than the CSI measurement resources indicated by the network side; The basic unit covers N frequency domain resources corresponding to the Channel State Indication Reference Signal (CSI-RS) in the frequency domain, where N is a positive integer and less than M, where M is the total number of frequency domain resources corresponding to the CSI-RS indicated by the network side, and the N frequency domain resources are in the same time domain position.

7. The method according to claim 6, wherein, The CSI measurement resource is a bandwidth portion (BWP), wherein the BWP is an active BWP.

8. The method according to claim 6, wherein, The CSI feedback information received from the user equipment (UE) and containing CSI feedback corresponding to the basic unit includes: Receive CSI feedback information, which includes CSI feedback corresponding to some of the basic units.

9. The method according to any one of claims 6 to 8, wherein, The more CSI measurement resources a unit has, the larger the basic unit becomes; the fewer CSI measurement resources a unit has, the smaller the basic unit becomes.

10. The method according to any one of claims 6 to 9, wherein, The CSI measurement resource includes I basic units, where I is a positive integer greater than or equal to 2; The receiving of CSI feedback information sent by the user equipment UE, which includes CSI feedback corresponding to the basic unit, includes: receiving CSI feedback information composed of the CSI feedback corresponding to the I basic units sent by the user equipment UE.

11. A Channel State Indication (CSI) feedback information transmission device, wherein, Applied to User Equipment (UE), including: The first processing module is configured as a basic unit for determining the CSI processing granularity, wherein the basic unit is determined based on the CSI measurement resources indicated by the network side and the UE's ability to process CSI; Select a machine learning model corresponding to the basic unit from the pre-configured machine learning models, wherein the machine learning model corresponding to the basic unit is trained using the full-channel information and feature vector corresponding to the basic unit, and one machine learning model corresponds to multiple basic units; The CSI feedback corresponding to the basic unit is determined based on the machine learning model corresponding to the basic unit. The basic unit for determining the CSI processing granularity includes: taking the maximum bandwidth that the UE can process CSI as the bandwidth of the basic unit in the frequency domain, wherein the basic unit is smaller than the CSI measurement resource indicated by the network side; The basic unit covers N frequency domain resources corresponding to the Channel State Indication Reference Signal (CSI-RS) in the frequency domain, where N is a positive integer and N is less than M, where M is the total number of frequency domain resources corresponding to the CSI-RS indicated by the network side, and the N frequency domain resources have the same time domain position. The first transceiver module is configured to send CSI feedback information, including the CSI feedback, to the base station.

12. The apparatus according to claim 11, wherein, The CSI measurement resource is a bandwidth portion (BWP), wherein the BWP is an active BWP.

13. The apparatus according to claim 11, wherein, The first transceiver module is specifically configured as follows: Send CSI feedback information containing CSI feedback corresponding to each of the aforementioned basic units.

14. The apparatus according to any one of claims 11 to 13, wherein the larger the number of CSI measurement resources, the larger the basic unit; and the smaller the number of CSI measurement resources, the smaller the basic unit.

15. The apparatus according to any one of claims 11 to 13, wherein, The CSI measurement resource includes I basic units, where I is a positive integer greater than or equal to 2; The first transceiver module is configured to send CSI feedback information containing the CSI feedback to the base station in the following manner: combining the CSI feedback corresponding to the I basic units together into CSI feedback information and sending the CSI feedback information to the base station.

16. A Channel State Indication (CSI) feedback information transmission device, wherein, Applied to base stations, including: The second transceiver module is configured to receive CSI feedback information sent by the user equipment (UE) that includes CSI feedback corresponding to the basic unit; The basic unit is determined by the UE based on the CSI measurement resources indicated by the network side and the UE's ability to process CSI. Wherein, the CSI feedback corresponding to the basic unit is determined by the UE based on the machine learning model corresponding to the basic unit; The machine learning model corresponding to the basic unit is selected by the UE from a pre-configured machine learning model. The machine learning model corresponding to the basic unit is trained using the full-channel information and feature vectors corresponding to the basic unit. One machine learning model corresponds to multiple basic units. Wherein, the maximum bandwidth that the UE can process CSI is the bandwidth of the basic unit in the frequency domain, and the basic unit is less than the CSI measurement resources indicated by the network side; The basic unit covers N frequency domain resources corresponding to the Channel State Indication Reference Signal (CSI-RS) in the frequency domain, where N is a positive integer and less than M, where M is the total number of frequency domain resources corresponding to the CSI-RS indicated by the network side, and the N frequency domain resources are in the same time domain position.

17. The apparatus according to claim 16, wherein, The CSI measurement resource is a bandwidth portion (BWP), wherein the BWP is an active BWP.

18. The apparatus according to claim 16, wherein, The CSI feedback information received from the user equipment (UE) and containing CSI feedback corresponding to the basic unit includes: Receive CSI feedback information containing CSI feedback corresponding to each of the multiple basic units.

19. The apparatus according to any one of claims 16 to 18, wherein the larger the number of CSI measurement resources, the larger the basic unit; and the smaller the number of CSI measurement resources, the smaller the basic unit.

20. The apparatus according to any one of claims 16 to 18, wherein, The CSI measurement resource includes I basic units, where I is a positive integer greater than or equal to 2; The second transceiver module is configured to receive CSI feedback information sent by the user equipment UE, which includes CSI feedback corresponding to the basic unit, in the following manner: receiving CSI feedback information composed of the CSI feedback corresponding to the I basic units sent by the user equipment UE.

21. A communication device, comprising a processor, a memory, and an executable program stored in the memory and executable by the processor, wherein, When the processor runs the executable program, it performs the steps of the Channel State Indication (CSI) feedback information transmission method as described in any one of claims 1 to 5, or 6 to 10.

22. A storage medium having an executable program stored thereon, wherein, When the executable program is executed by a processor, it implements the steps of the Channel State Indication (CSI) feedback information transmission method as described in any one of claims 1 to 5, or 6 to 10.

Images