Channel state information generating method and apparatus, channel state information receiving method and apparatus, and communication system

Abstract

Embodiments of the present application provide a channel state information (CSI) generating method and apparatus, a CSI receiving method and apparatus, and a communication system. The CSI generating apparatus is applied to a terminal device. The apparatus comprises a first processing unit. The first processing unit controls the terminal device to execute the following operation: the terminal device generates more than one first CSI reports, each first CSI report comprising information of a pre-coding matrix, wherein the information of the pre-coding matrix comprises information of a merge coefficient, at least part of the information of the merge coefficient is generated by an artificial intelligence (AI / ML) model, each first CSI report has a first portion and a second portion, and a priority order is provided for the second portions of the more than one first CSI reports.

Description

Method, device and communication system for generating and receiving channel state information Technical Field

[0001] The embodiments of the present application relate to the field of communication technologies. Background Art

[0002] Massive multiple-input multiple-output (MIMO) technology is one of the key technologies for 5G mobile communications. MIMO can provide higher channel capacity, but achieving these benefits depends on obtaining accurate channel state information.

[0003] In MIMO technology, terminal devices measure spatial channels and provide channel state information (CSI) back to the network. Based on this CSI, the network selects an appropriate precoding matrix for downlink transmission to the terminal, minimizing the probability of bit errors in the terminal's reception.

[0004] The channel state information generation and feedback process can be summarized as follows. The network device sends a channel state information reference signal (CSI-RS) to each terminal device. The terminal device estimates the channel using the received CSI-RS and obtains an estimate of the spatial channel matrix. The terminal device further uses the estimated spatial channel to obtain CSI. In new radio (NR) technology, CSI feedback is implicit. That is, the terminal device feeds back CSI in the form of recommended transmission parameters to the network device. These transmission parameters include the channel state information reference signal resource indicator (CQI), precoding matrix indicator (PMI), CSI-RS resource indicator (CRI), synchronization signal block resource indicator (SSBRI), layer indicator (LI), rank indicator (RI), and physical layer RSRP (L1-RSRP). The base station can directly use the parameters recommended by the terminal device for downlink transmission, or it can choose not to use the recommended parameters.

[0005] When using the traditional codebook method to feed back CSI, if the rank of the spatial channel matrix estimated by the terminal device is greater than 1, the RI fed back by the terminal device to the base station (if reported) may be greater than 1. In this case, the PMI is a multi-rank codebook. In NR Rel-15, two codebooks, type I and type II, are defined. The former is a conventional precision codebook and can be used for single-user multiple input multiple output (SU-MIMO) and multi-user multiple input multiple output (MU-MIMO) transmission. The latter is a high-precision codebook, mainly used in MU-MIMO scenarios. The latter has higher accuracy than the former, but has higher overhead. Both NR codebooks use a parameterized codebook structure and are divided into two levels (W=W1W2), where W1 describes the long-term, wideband characteristics of the channel and contains an oversampled DFT beam (group); W2 describes the short-term, subband characteristics of the channel. For the above two codebooks, the selection method of W1 is the same. Regarding the selection of W2, the type I codebook consists of a weighted column selection vector, which selects a beam for the subband from the oversampled beams in W1. In the high-precision type II codebook, W2 is used to linearly combine the DFT beams in W1.

[0006] To address the excessive overhead of the Type II codebook, Rel-16 defines an enhanced Type II codebook (e-type II codebook). The e-type II codebook still uses a two-level structure: reporting a set of wideband beams and then adding a set of narrowband combining coefficients to each beam. The enhancement to the Rel-16 e-type II codebook leverages frequency domain correlation to reduce reporting overhead. Furthermore, the e-type II CSI allows for a two-fold increase in the frequency domain granularity of PMI reporting.

[0007] It should be noted that the above introduction to the technical background is merely intended to provide a clear and complete description of the technical solutions of this application and facilitate understanding by those skilled in the art. Simply because these solutions are described in the background technology section of this application, it should not be assumed that the above technical solutions are well known to those skilled in the art.

[0008] Summary of the Invention

[0009] There is a certain delay in the generation of CSI after the terminal device measures the channel, and there is also a delay in the use of the CSI after the base station performs scheduling (such as MU-MIMO scheduling) after receiving the CSI. Therefore, the time at which the channel corresponding to the CSI is different from the time at which it is applied, which is called channel aging. In some scenarios, such as when the terminal device moves at a fast speed (for example, greater than or equal to 30km / h) or the surrounding environment changes rapidly, the channel aging problem will be serious. In order to cope with the channel aging problem, in Rel-18, an auto-regression (AR) algorithm is used to predict the channel at more than one moment in the future (relative to the moment when CSI is generated), and an enhanced type II codebook for predicted PMI is defined. In this application, we refer to it as the Rel-18 codebook. For the case of predicting the channel at one moment in the future, the Rel-18 codebook is similar to the Rel-16 codebook. In the case of predicting the channel at more than one time instant in the future, the Rel-18 codebook compresses the channel in the Doppler domain by utilizing the time correlation of the channels at more than one time instant.

[0010] With the development of artificial intelligence / machine learning (AI / ML) technology, applying AI / ML technology to the physical layer of wireless communications to solve the difficulties of traditional methods has become a current technical direction.

[0011] Figure 1 is a schematic diagram of AI / ML-based CSI feedback. The AI / ML module can include an AI / ML-based CSI generation component and an AI / ML-based CSI reconstruction component. The AI / ML-based CSI generation component includes an AI / ML model, which can include an AI / ML encoder and quantizer. Furthermore, the AI / ML model may also include a preprocessing module. This preprocessing module may not be included in the AI / ML model. An example of preprocessing performed by the preprocessing module is singular value decomposition (SVD), another example is a two-dimensional discrete Fourier transform (DFT), or other preprocessing methods. The AI / ML-based CSI reconstruction component includes an AI / ML reconstruction model, which includes a dequantizer and an AI / ML decoder. Furthermore, the AI / ML reconstruction model may also include a post-processing module.

[0012] As shown in Figure 1, in operation 101, the terminal device side uses the AI / ML-based CSI generation part to process and obtain CSI; the network device receives the CSI through the air interface; in operation 102, the network device uses the AI / ML-based CSI reconstruction part to process the received CSI to obtain recovered CSI.

[0013] The inventors of this application found that in the scenario where the spatial channel matrix or precoding matrix is ​​mapped to the angular delay domain or the angular delay Doppler domain and the AI / ML model is used to process the combining coefficients, how to determine the priority of the second part of the channel state information (CSI) report is a problem that needs to be solved.

[0014] In response to at least one of the above-mentioned problems or other similar problems, embodiments of the present application provide a method, apparatus, and communication system for generating and receiving channel state information, thereby enabling determination of the priority of the second part of a channel state information (CSI) report in a scenario where information on combining coefficients is generated using an artificial intelligence model.

[0015] According to one aspect of an embodiment of the present application, there is provided an apparatus for generating channel state information, which is applied to a terminal device. The apparatus includes a first processing unit, which controls the terminal device to perform the following operations:

[0016] The terminal device generates one or more first channel state information (CSI) reports, the first channel state information reports including precoding matrix information, wherein the precoding matrix information includes combining coefficient information, at least a portion of the combining coefficient information is generated by an artificial intelligence (AI / ML) model,

[0017] The first channel state information (CSI) report has a first part and a second part, and the second parts of more than one first channel state information (CSI) report have a priority order.

[0018] According to another aspect of an embodiment of the present application, there is provided an apparatus for receiving channel state information, which is applied to a network device. The apparatus includes a second processing unit that controls the network device to perform the following operations:

[0019] receiving one or more first channel state information (CSI) reports generated by a terminal device,

[0020] The first channel state information report includes information about a precoding matrix, wherein the information about the precoding matrix includes information about combining coefficients, and at least a portion of the information about the combining coefficients is generated by an artificial intelligence (AI / ML) model.

[0021] The first channel state information (CSI) report has a first part and a second part, and the second parts of more than one first channel state information (CSI) report have a priority order.

[0022] One of the beneficial effects of the embodiments of the present application is that the present application can determine the priority of the second part of the channel state information (CSI) report in a scenario where an artificial intelligence model is used to generate information on the combining coefficients.

[0023] With reference to the following description and accompanying drawings, specific embodiments of the present application are disclosed in detail, indicating the manner in which the principles of the present application can be employed. It should be understood that the embodiments of the present application are not limited in scope. Within the spirit and scope of the appended claims, the embodiments of the present application include many variations, modifications and equivalents.

[0024] Features described and / or illustrated with respect to one embodiment may be used in the same or similar manner in one or more other embodiments, combined with features in other embodiments, or substituted for features in other embodiments.

[0025] It should be emphasized that the term "include / comprising" when used herein refers to the presence of features, integers, steps or components, but does not exclude the presence or addition of one or more other features, integers, steps or components. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] The elements and features described in one figure or one embodiment of the present application can be combined with the elements and features shown in one or more other figures or embodiments. In addition, in the accompanying drawings, similar reference numerals represent corresponding parts in several figures and can be used to indicate corresponding parts used in more than one embodiment.

[0027] Figure 1 is a schematic diagram of CSI feedback based on AI / ML;

[0028] FIG2 is a schematic diagram of the communication system of the present application;

[0029] FIG3 is a schematic diagram of a method for generating channel state information according to an embodiment of the first aspect of the present application;

[0030] FIG4 is a schematic diagram of a method for generating channel state information according to embodiment 7 of the embodiment of the first aspect of the present application;

[0031] FIG5 is a schematic diagram of a method for receiving channel state information according to embodiment 7 of the embodiment of the first aspect of the present application;

[0032] FIG6 is a schematic diagram of a method for receiving channel state information according to an embodiment of the second aspect of the present application;

[0033] FIG7 is a schematic diagram of an apparatus for generating channel state information according to an embodiment of the third aspect of the present application;

[0034] FIG8 is a schematic diagram of an apparatus for receiving channel state information according to an embodiment of the fourth aspect of the present application;

[0035] FIG9 is a schematic diagram of a terminal device according to an embodiment of the fifth aspect;

[0036] FIG10 is a schematic diagram of a network device according to an embodiment of the fifth aspect. DETAILED DESCRIPTION

[0037] The above and other features of the present application will become apparent through the following description with reference to the accompanying drawings. In the description and the accompanying drawings, specific embodiments of the present application are disclosed in detail, which illustrate some embodiments in which the principles of the present application can be adopted. It should be understood that the present application is not limited to the described embodiments. On the contrary, the present application includes all modifications, variations and equivalents that fall within the scope of the appended claims.

[0038] In the embodiments of the present application, the terms "first", "second", etc. are used to distinguish different elements from the name, but do not indicate the spatial arrangement or temporal order of these elements, and these elements should not be limited by these terms. The term "and / or" includes any one and all combinations of one or more of the associated listed terms. The terms "comprising", "including", "having", etc. refer to the presence of the stated features, elements, components or components, but do not exclude the presence or addition of one or more other features, elements, components or components.

[0039] In the embodiments of this application, the singular forms "a," "the," etc. include plural forms and should be broadly understood to mean "a" or "a type" rather than being limited to "one." Furthermore, the term "said" should be understood to include both singular and plural forms, unless the context clearly indicates otherwise. Furthermore, the term "according to" should be understood to mean "at least in part based on...", and the term "based on" should be understood to mean "at least in part based on...", unless the context clearly indicates otherwise.

[0040] In the embodiments of the present application, the term "communication network" or "wireless communication network" may refer to a network that complies with any of the following communication standards, such as New Radio (NR), Long Term Evolution (LTE), Enhanced Long Term Evolution (LTE-A, LTE-Advanced), Wideband Code Division Multiple Access (WCDMA), High-Speed ​​Packet Access (HSPA), etc.

[0041] Furthermore, communication between devices in the communication system may be carried out according to communication protocols of any stage, for example, including but not limited to the following communication protocols: 1G (generation), 2G, 2.5G, 2.75G, 3G, 4G, 4.5G and 5G, New Radio (NR), etc., and / or other communication protocols currently known or to be developed in the future.

[0042] In the embodiments of the present application, the term "network device" refers to, for example, a device in a communication system that connects a terminal device to a communication network and provides services for the terminal device. Network devices may include, but are not limited to, the following devices: an integrated access and backhaul node (IAB-node), a base station (BS), an access point (AP), a transmission reception point (TRP), a broadcast transmitter, a mobility management entity (MME), a gateway, a server, a radio network controller (RNC), a base station controller (BSC), and the like.

[0043] Base stations may include, but are not limited to, NodeB (NB), evolved NodeB (eNodeB or eNB), and 5G base stations (gNB), among others. They may also include remote radio heads (RRHs), remote radio units (RRUs), relays, or low-power nodes (e.g., femeto, pico, etc.). The term "base station" may include some or all of their functions, and each base station may provide communication coverage for a specific geographic area. The term "cell" may refer to a base station and / or its coverage area, depending on the context in which the term is used.

[0044] In the embodiments of the present application, the term "user equipment" (UE) or "terminal equipment" (TE) refers to, for example, a device that accesses a communication network through a network device and receives network services. A terminal device can be fixed or mobile and may also be referred to as a mobile station (MS), a terminal, a subscriber station (SS), an access terminal (AT), a station, and so on.

[0045] Among them, terminal devices may include but are not limited to the following devices: cellular phones, personal digital assistants (PDAs), wireless modems, wireless communication devices, handheld devices, machine-type communication devices, laptop computers, cordless phones, smart phones, smart watches, digital cameras, etc.

[0046] For another example, in scenarios such as the Internet of Things (IoT), the terminal device can also be a machine or device for monitoring or measurement, including but not limited to: machine type communication (MTC) terminal, vehicle-mounted communication terminal, device-to-device (D2D) terminal, machine-to-machine (M2M) terminal, and so on.

[0047] In addition, the term "network side" or "network device side" refers to one side of the network, which can be a base station or one or more network devices as mentioned above. The term "user side" or "terminal side" or "terminal device side" refers to the user or terminal side, which can be a UE or one or more terminal devices as mentioned above.

[0048] In the following description, the terms "uplink control signal" and "uplink control information (UCI)" or "physical uplink control channel (PUCCH)" are interchangeable, and the terms "uplink data signal" and "uplink data information" or "physical uplink shared channel (PUSCH)" are interchangeable to avoid confusion.

[0049] The terms "downlink control signal" and "downlink control information (DCI)" or "physical downlink control channel (PDCCH)" are interchangeable, and the terms "downlink data signal" and "downlink data information" or "physical downlink shared channel (PDSCH)" are interchangeable.

[0050] In addition, sending or receiving PUSCH can be understood as sending or receiving uplink data carried by PUSCH, sending or receiving PUCCH can be understood as sending or receiving uplink information carried by PUCCH, and sending or receiving PRACH can be understood as sending or receiving preamble carried by PRACH; uplink signals can include uplink data signals and / or uplink control signals, etc., and can also be referred to as uplink transmission (UL transmission) or uplink information or uplink channels. Sending uplink transmission on uplink resources can be understood as sending the uplink transmission using the uplink resources. Similarly, downlink data / signals / channels / information can be understood accordingly.

[0051] In the embodiments of the present application, the high-layer signaling may be, for example, radio resource control (RRC) signaling; for example, an RRC message, including, for example, MIB, system information, or a dedicated RRC message; or an RRC information element (RRC IE). The high-layer signaling may also be, for example, MAC (Medium Access Control) signaling; or a MAC control element (MAC CE). However, the present application is not limited thereto.

[0052] The following describes the scenarios of the embodiments of the present application through examples, but the present application is not limited thereto.

[0053] Figure 2 is a schematic diagram of the communication system of the present application, which schematically illustrates a situation taking a terminal device and a network device as an example. As shown in Figure 2, the communication system 100 may include a network device 201 and a terminal device 202 (for simplicity, Figure 2 only illustrates one terminal device as an example).

[0054] In the embodiment of the present application, existing services or future services can be carried out between the network device 201 and the terminal device 202. For example, these services include but are not limited to: enhanced mobile broadband (eMBB), massive machine type communication (mMTC), and ultra-reliable and low-latency communication (URLLC), etc.

[0055] Among them, the terminal device 202 can send data to the network device 201, for example, using an authorized or unauthorized transmission mode. The network device 201 can receive data sent by one or more terminal devices 202 and feedback information to the terminal device 202, such as confirmation ACK / non-confirmation NACK information. The terminal device 202 can confirm the end of the transmission process, or can continue new data transmission, or can retransmit the data based on the feedback information.

[0056] In the following description of this application, artificial intelligence (AI) models may also be referred to as artificial intelligence / machine learning (AI / ML) models, and these two terms are interchangeable.

[0057] In the following embodiments of the present application, the signaling sent by the network device to the terminal device can be sent through downlink control information (DCI), and / or media access control element (MAC CE), and / or radio resource control (RRC) signaling.

[0058] In the following embodiments of the present application, the AI / ML-based CSI generation part and the AI / ML-based CSI reconstruction part are paired. The former can be applied to the terminal device side, and the latter can be applied to the network device side. If the terminal device uses a certain AI / ML-based CSI generation part, the network device must use the AI / ML-based CSI reconstruction part paired with the AI / ML-based CSI generation part to successfully reconstruct the channel information. If the network device uses a certain AI / ML-based CSI reconstruction part, the terminal device must use the AI / ML-based CSI generation part paired with the AI / ML-based CSI reconstruction part to successfully reconstruct the channel information on the network device side.

[0059] The AI / ML-based CSI generation part includes an AI / ML model, which can be used to generate one or more of precoding matrix information, rank indication (RI), layer indication (LI), channel resource indication (CRI), and channel quality indication (CQI). In addition, RI, LI, CRI, and CQI may not be generated by the AI / ML model. For example, the AI / ML-based CSI generation part may also include a module for generating RI, a module for generating LI, a module for generating CRI, and a module for generating CQI. The AI / ML-based CSI generation part may also include other modules, such as a module for truncating a bit sequence.

[0060] In various embodiments of the present application, reporting may refer to an action of a terminal device sending information to a network device. For example, a terminal device reporting a CSI report may refer to the terminal device sending a CSI report to a network device.

[0061] In various embodiments of the present application, the spatial basis may also be equivalently referred to as a spatial filter.

[0062] Embodiments of the first aspect

[0063] In the application scenario of the present application, the terminal device uses the received channel state information reference signal (CSI-RS) to estimate the (three-dimensional) spatial channel matrix, where one dimension represents the transmitting antenna port, one dimension represents the receiving antenna port, and one dimension represents the frequency domain.

[0064] In the application scenario of the present application, for the case where the precoding matrix is ​​mapped to the angular delay domain (or, for the (three-dimensional) spatial channel matrix at more than one time instant, the precoding matrix is ​​mapped to the angular delay Doppler domain), the terminal device performs a spatial domain DFT transform on the (two-dimensional) spatial channel matrix for each resource block (RB). And in the broadband sense (all RBs), according to the configuration of the network device, the spatial basis (which can be the L strongest spatial domain DFT vectors) is selected. Next, the terminal device performs a singular value decomposition (SVD) on each subband (two-dimensional) spatial channel matrix to obtain the singular values ​​and corresponding right singular vectors of each subband (two-dimensional) spatial channel matrix, and recommends the value corresponding to the rank indication (according to the RI restriction / rank restriction configured by the network device (if configured)), which is recorded as r. Next, the right singular (column) vectors corresponding to the largest singular values ​​of the (two-dimensional) spatial channel matrix of all subbands are arranged in rows into a matrix, which is called the precoding matrix of the first spatial domain layer. Similarly, similar operations are performed on the right singular vectors corresponding to the remaining singular values ​​to obtain r precoding matrices. For each spatial layer, that is, each of the r precoding matrices, a frequency domain DFT transform is performed to select the frequency domain basis (which can be the M strongest frequency domain DFT vectors). In this way, r sets of merging coefficients (or r merging coefficient matrices) are obtained, which are used as the input of the AI / ML model. For (three-dimensional) spatial channel matrices at more than one time, after selecting the frequency domain basis, a time domain DFT transform can be further performed on each spatial layer to select the time domain basis (which can be the Q strongest time domain DFT vectors). Thus, a set of three-dimensional merging coefficients obtained for each spatial layer (for all spatial layers, a total of r three-dimensional merging coefficient matrices) is used as the input of the AI / ML model.

[0065] In the above-mentioned application scenario of the present application, the difference between the process of generating CSI (at least part of it) using the AI / ML model and the process of generating CSI using the code book method is that after the terminal device selects the spatial domain basis and the frequency domain basis (or the spatial domain basis, the frequency domain basis and the time domain basis) according to the base station configuration, the terminal device processes the merging coefficient differently.

[0066] For example, in the method using a codebook, the processing method includes selecting the position of non-zero coefficients, finding the strongest coefficient, quantizing the amplitude and phase of the combined coefficients, etc. In this application, the processing method for the combined coefficients is to use the combined coefficients as the input of the AI / ML model, and the output of the AI / ML model is the information of the combined coefficients. The spatial domain basis (also applicable to the frequency domain basis and the time domain basis) is a set of orthogonal bases, and further, it is a set of DFT orthogonal bases.

[0067] For the transformation to the angle delay domain: For the spatial channel matrices at N time instants, the above method is used to obtain N sets of combining coefficients. The spatial basis (also applicable to the frequency domain basis) can be the same for these N time instants, or different for at least two time instants. These N sets of combining coefficients serve as input to the AI / ML model (N ≥ 1).

[0068] For the transformation to the Delay-Doppler domain, for spatial channel matrices at N > 1 time instants, compression is also performed in the time domain (using the time domain basis) to obtain a set of combining coefficients. The spatial domain basis (also applicable to the frequency domain basis) can be the same for these N time instants, or different for at least two time instants. This set of combining coefficients serves as the input to the AI / ML model.

[0069] The method of transforming the (three-dimensional) spatial channel matrix into the angle delay domain (for a three-dimensional spatial channel matrix with more than one time instant, into the angle delay Doppler domain) is as follows:

[0070] Split the (3D) spatial channel matrix at the receiving antenna port into Nr (2D) spatial channel matrices, where Nr is the number of receiving antenna ports. Perform a spatial DFT transform on each of these Nr (2D) spatial channel matrices, similar to the above method, to obtain L spatial bases in the broadband.

[0071] Next, for each of these Nr (two-dimensional) spatial channel matrices, a frequency domain DFT transform is performed similar to the above method to obtain M frequency domain bases, thereby obtaining Nr sets of combined coefficients (or Nr combined coefficient matrices), which are used as the input of the AI / ML model.

[0072] For (three-dimensional) spatial channel matrices with more than one time instant, after selecting the frequency domain basis, a time domain DFT transform can be further performed at each receive antenna port to select the time domain basis (which can be the Q strongest time domain DFT vectors). This results in a set of three-dimensional combining coefficients for each spatial layer (for all spatial layers, a total of Nr three-dimensional combining coefficient matrices) as input to the AI / ML model.

[0073] In this application, the method for processing the merging coefficient is also to use it as the input of the AI / ML model. The method is similar to the above-mentioned "precoding matrix" case, so it will not be repeated here.

[0074] In the following embodiments of the present application, the transformation of the precoding matrix into the angle delay domain (or angle delay Doppler domain) is taken as an example. For all embodiments, similar cases are applicable to the transformation of the "spatial channel matrix" into the angle delay domain (or angle delay Doppler domain), and no further details are given. For the case of transforming the "spatial channel matrix" into the angle delay domain (or angle delay Doppler domain), it is only necessary to change the discussion of the spatial layer in the "precoding matrix" case to the receiving antenna port. For example, in the "precoding matrix" case, consider that there are 4 receiving antenna ports, supporting 3 spatial layer transmissions, where for each spatial layer, the combining coefficient is used as the input of the AI / ML model. In the case of the "spatial channel matrix", there are correspondingly 4 receiving antenna ports, where for each receiving antenna port, the combining coefficient is used as the input of the AI / ML model.

[0075] An embodiment of the first aspect of the present application provides a method for generating channel state information, which is applied to a terminal device.

[0076] FIG3 is a schematic diagram of a method for generating channel state information. As shown in FIG3 , the method includes:

[0077] 301. The terminal device generates one or more first channel state information (CSI) reports, wherein the first channel state information report includes information of a precoding matrix, wherein the information of the precoding matrix includes information of a combining coefficient, and at least a portion of the information of the combining coefficient is generated by an artificial intelligence (AI / ML) model, wherein the first channel state information (CSI) report has a first part and a second part, and the second part of the one or more first channel state information (CSI) reports has a priority.

[0078] In 301, at least a portion of the combining coefficient information is obtained by processing the combining coefficients in the precoding matrix information and / or the combining coefficients in the spatial channel matrix information using an artificial intelligence (AI / ML) model, for example. The spatial channel matrix information may include: a spatial channel matrix and / or a representation of the spatial channel matrix in the angular delay domain.

[0079] In 301 , an output of an artificial intelligence (AI / ML) model may be in the form of a bit sequence having a certain bit width.

[0080] In some embodiments of 301, the first part includes at least part of information of a rank indication (RI), and / or a channel quality indication (CQI), and / or first information, wherein the first information and / or the rank indication (RI) are used to indicate the number of information bits of at least part of the second part.

[0081] The first information includes:

[0082] Artificial Intelligence (AI / ML) model information; and / or

[0083] The sum of the number of information bits of the information of the combining coefficients of all spatial layers or the maximum allowable sum, or the sum of the number of information bits of the precoding matrix information of all spatial layers or the maximum allowable sum.

[0084] The rank indication (RI), and / or at least a portion of the channel quality indication (CQI) information, and / or the first information are separately encoded.

[0085] In 301, the second part of the first channel state information (CSI) report includes information of the precoding matrix.

[0086] The first part and the second part of the first channel state information (CSI) report may be independently encoded.

[0087] In some embodiments, as shown in FIG3 , the method further includes:

[0088] 302. After the terminal device sends the first part of the first channel state information (CSI) report in full, it sends the second part.

[0089] The method of the present application is described in detail below through different embodiments. The above description of 301 and 302 is applicable to the following embodiments.

[0090] In addition, in each embodiment of the present application, the channel state information report and the CSI report have the same meaning, for example, the first channel state information report and the first CSI report have the same meaning.

[0091] Example 1:

[0092] The terminal device may receive a first configuration sent by the network device, where the first configuration includes information about the bit width of the combining coefficients. Furthermore, the first configuration may also include at least one of the following information: information about the number of spatial domain bases, information about the number of frequency domain bases, information about the number of time domain bases, and information about the amount of channel information included in a CSI report.

[0093] In some examples, the first configuration may include, for example:

[0094] Information on the number of spatial bases, information on the number of frequency domain bases, and information on the bit width of the combining coefficients; or

[0095] Information on the number of spatial domain bases, the number of frequency domain bases, the number of time domain bases, the number of channel information included in a CSI report, and the bit width of the combining coefficients; or

[0096] Information on the number of spatial domain bases, information on the number of frequency domain bases, information on the amount of channel information contained in a CSI report, and information on the bit width of the combining coefficient information.

[0097] The channel information refers to the information of the spatial channel at a moment. Furthermore, the amount of channel information contained in a channel state information (CSI) report refers to: how many moments of spatial channel matrix information is contained in a CSI report. This number is used to represent the length of the time domain basis vector. A channel state information (CSI) report contains more than one channel information, which can be understood as a channel state information (CSI) report containing more than one channel matrix. For a channel state information (CSI) report containing one channel information, one application scenario of this embodiment is to use the AI / ML method to compress the spatial channel information (or its representation in the angle delay domain) in the spatial domain and frequency domain to obtain CSI. For a channel state information (CSI) report containing more than one channel information, one application scenario of this embodiment is to use the AI / ML method to compress the spatial channel information (or its representation in the angle delay Doppler domain) in the spatial domain, frequency domain, and time domain to obtain CSI.

[0098] In addition, for descriptions of the information on the merging coefficients, the spatial basis, the frequency domain basis, the time domain basis, etc., reference can be made to the above descriptions of the application scenarios of this application and related technologies.

[0099] According to the first configuration, as described in 301 above, the first channel state information report generated by the terminal device may include information about the precoding matrix. The information about the precoding matrix includes:

[0100] Spatial domain basis information and / or frequency domain basis information, and combining coefficient information; or

[0101] Spatial domain basis information and / or frequency domain basis information and / or time domain basis information, and information on combining coefficients; or

[0102] Information on the merging coefficients.

[0103] Among them, the information of the merging coefficient is generated by the AI / ML model.

[0104] In some embodiments, the terminal device does not report one or more of the spatial basis information, the frequency domain basis information, and the time domain basis information. For example, after the network device configures the codebook subset restriction information (for example, in the first configuration) and the number of spatial basis information, there is only one choice of spatial basis, and the terminal device does not need to report the spatial basis information. For another example, if the network device configures the number of time domain basis information to be 2, and the number of channel information included in a CSI report is 2, then the time domain basis information is not reported.

[0105] In some implementations, the spatial basis (also applicable to the frequency and time domain basis) reported by the terminal device is the same for all transmission layers, which has the beneficial effect of simplifying implementation and reducing overhead. Alternatively, at least two transmission layers may have different spatial basis (also applicable to the frequency and time domain basis), which has the beneficial effect of improving the accuracy of CSI reporting.

[0106] A CSI report contains one or more channel information. In some embodiments, a CSI report contains more than one channel information. The interval between two adjacent channel information pieces can be configured by the network device and / or predefined, as specified by the standard. The interval can be a time interval. For example, the standard specifies that the interval can be 4ms, 5ms, 6ms, or 8ms, and the network device configures one of these four intervals. The configuration can be in the form of a numerical value or an index. In some embodiments, a CSI report contains more than two channel information pieces, for example, an integer in the range of 2-16. The interval between any two adjacent channel information pieces is the same; or at least two of the intervals are unequal. The spatial domain basis (also applicable to the frequency domain basis) can be the same for all channel information pieces contained in the CSI report, which has the beneficial effect of simplifying implementation and reducing reporting overhead. It can also be different for at least two channel information pieces contained in the CSI report, which has the beneficial effect of selecting an appropriate spatial domain basis (also applicable to the frequency domain basis) for the channel information piece based on its properties, thereby improving performance.

[0107] Example 2:

[0108] In the second embodiment, the combining coefficients in the precoding matrix information are input to the AI / ML model, and the AI / ML model outputs the information of the combining coefficients. The combining coefficients can be represented in the form of a matrix or a vector. For a channel state information (CSI) report containing a channel information, an application scenario of this embodiment is to use the AI / ML method to compress the spatial channel information (or the representation in the angle delay domain) in the spatial domain and the frequency domain to obtain CSI. For a channel state information (CSI) report containing more than one channel information, an application scenario of this embodiment is to use the AI / ML method to compress the spatial channel information (or the representation in the angle delay Doppler domain) in the spatial domain, the frequency domain, and the time domain to obtain CSI.

[0109] In some embodiments, all spatial layers use the same AI / ML model for inference, which has the beneficial effect of requiring fewer AI / ML models, simplifying implementation, reducing complexity, and saving storage. Inference refers to the process or operation of putting data into a trained AI / ML model to obtain output. In some embodiments, there can be at least two spatial layers (the number of all spatial layers is at least 2), using different AI / ML models for inference. The beneficial effect is that the most suitable AI / ML model is used for at least one spatial layer, thereby improving performance.

[0110] In some embodiments, a first way to input the merging coefficients is to put at least a portion of the merging coefficients of a spatial layer as a whole into an AI / ML model, such as an AI / ML-based CSI generation part or an AI / ML encoder. The beneficial effect is that the implementation is simple, clear, and unambiguous. Among them, at least a portion of the merging coefficients are, for example, all the merging coefficients of the spatial layer; or, it is possible that a portion of the merging coefficients are set to 0, and the remaining non-zero merging coefficients and / or the information of the position of the non-zero merging coefficients are input into the AI / ML model. If the position is determined by the terminal device, the terminal device reports the information of the position of the non-zero merging coefficients.

[0111] In some embodiments, a second method for inputting combining coefficients is to divide at least a portion of the combining coefficients of a spatial layer into more than one group, each of which is input to one or more artificial intelligence (AI / ML) models, such as an AI / ML-based CSI generation component or an AI / ML encoder. This advantageously allows all combining coefficients to be classified (divided into more than one group), and each group is input into the AI / ML model for processing, resulting in performance gains. For example, each group can be fed into the same AI / ML model; alternatively, combining coefficients of at least two groups can be fed into different AI / ML models.

[0112] In some implementations, the number of combining coefficients in each of the above groups is the same, or at least two groups may have different numbers of combining coefficients. The method for grouping at least a portion of the combining coefficients of a spatial layer into more than one group may be configured by a network device, and / or predefined, and / or specified by a standard.

[0113] For example, assume that downlink communication has only one transmission layer. All combining coefficients are represented by a matrix, such as matrix W2.

[0114] The first way of inputting the above-mentioned merging coefficient is: W2 is used as the input of the AI / ML model (such as the AI / ML-based CSI generation part or the AI / ML encoder).

[0115] The second way to input the combined coefficient is to decompose W2 into W2 = W 2,1 +W 2,2 , W 2,1 is the first set of combined coefficients, W 2,2 is the second set of combined coefficients.

[0116] W 2,1 The K0=6 merging coefficients with the largest amplitude in W2 are retained (note that the position of these K0=6 merging coefficients in W2 is ρ), and the rest of the positions are set to 0. 2,2 The merging coefficients of the positions other than K0=6 positions at position ρ in W2 are retained, and the elements at position ρ are set to 0.

[0117] You can use W 2,1 and W 2,2 As input to the same AI / ML model (such as the CSI generation part based on AI / ML or AI / ML encoder), two bit sequences (information of the combined coefficients) are obtained as output; or, W 2,1 and W 2,2 They are respectively used as inputs of two AI / ML models (such as the AI / ML-based CSI generation part or the AI / ML encoder), and two bit sequences (information of the combined coefficients) are obtained as outputs.

[0118] The above example can also be applied to scenarios where downlink communication has more than two transmission layers. In some embodiments, the K0 (i.e., the number of combining coefficients in a group) and the ρ (i.e., the position of the combining coefficients in a group) in the second method for inputting combining coefficients described above can be the same for all transmission layers. In this case, all spatial layers use the same AI / ML model for inference, which has the beneficial effect of reducing the number of AI / ML models required, simplifying implementation, reducing complexity, and saving storage. Alternatively, at least two spatial layers can use different AI / ML models for inference, which has the beneficial effect of using the most appropriate AI / ML model for each spatial layer, improving performance. In some embodiments, in the second method for inputting combining coefficients described above, the ρ can be different and the K0 can be the same for at least two transmission layers, or both the K0 and ρ can be different. In this case, all spatial layers use the same AI / ML model for inference, which has the beneficial effect of reducing the number of AI / ML models required, simplifying implementation, reducing complexity, and saving storage. There can also be at least two spatial layers, using different AI / ML models for inference. The beneficial effect is that for different spatial layers and different positions ρ, the AI / ML model that is most suitable for at least one spatial layer and / or at least one position is used to improve performance.

[0119] In some embodiments, the information on the number of merging coefficients of each of the groups (for example, the value of K0 mentioned above) or the information on the maximum allowable value of the number of merging coefficients of each of the groups (including the cases where it is the same for all spatial layers and different for at least two spatial layers) can be configured by the network device and / or predefined, as specified by the standard. It can be explicitly configured and / or predefined, as specified by the standard, in the form of a numerical value or an index. The beneficial effect is that it is simple, clear, and not prone to ambiguity. In other embodiments, the information on the number of merging coefficients of each of the groups or the information on the maximum allowable value can also be implicitly configured and / or predefined, as specified by the standard. The beneficial effect is that the configuration is flexible, and the value of K0 or the maximum allowable value can be determined by comprehensively considering multiple factors. For example, the value of K0 or the maximum allowable value is The definitions of β and L are given in the first embodiment and will not be repeated here. M1 is the number of frequency domain bases of the first spatial domain layer.

[0120] In some embodiments, the network device may further configure whether at least a portion of the merging coefficients of one of the spatial layers are divided into more than one group; and / or, at least a portion of the merging coefficients of one of the spatial layers are information of the input of the artificial intelligence (AI / ML) model, and / or information of the bit width of the output of the artificial intelligence (AI / ML) model; and / or, the merging coefficients of more than one of the groups of one of the spatial layers are information of the input of the artificial intelligence (AI / ML) model, and / or information of the bit width of the output of the artificial intelligence (AI / ML) model.

[0121] In some examples, the network device configures the terminal device to use the first method or the second method mentioned above to process the merging coefficient. In some examples, the network device also configures the information of the AI / ML model used by the terminal device. For example, the network device configures the terminal device to use the first method, and the network device also configures AI / ML model 1; for another example, the network device configures the terminal device to use the second method, and the network device also configures AI / ML model 3; for another example, the network device configures the terminal device to use the second method, and the number and position of the merging coefficients between the groups are the same, and the network device also configures AI / ML model 2 and AI / ML model 2; for another example, the network device configures the terminal device to use the second method, and the number and / or position of the merging coefficients between the groups are not exactly the same, and the network device also configures AI / ML model 1 and AI / ML model 8. The beneficial effects of the first method are simple operation, simple configuration, and relatively low complexity of the terminal device. In the second method, the number and position of the merging coefficients between the groups are the same, and the beneficial effect is that the terminal device can perform processing separately according to the magnitude of the merging coefficient. Specifically, W 2,1 The amplitude ratio of the elements in W 2,2 The amplitude of the elements in the equation is large. For example: W2,1 The magnitude of the elements in is on the order of 10 3 , and W 2,2 The magnitude of 70% of the elements is on the order of 10 1 If W 2,1 and W 2,2 Put together, such as W2, then it may be W 2,2 The elements in cannot be effectively recognized by AI / ML models. 2,1 and W 2,2 If processed separately, W 2,2 The elements in the merging coefficients are easier for AI / ML models to identify than the first approach, which can lead to performance gains. In the second approach, the number and / or position of merging coefficients vary between groups. This has the beneficial effect of using different AI / ML models to process merging coefficients with different properties (such as different orders of magnitude), allowing for better identification of the properties of different categories of merging coefficients, further leading to performance gains.

[0122] In some examples, the network device configures the terminal device to process the merging coefficient using the first or second method described above, and also configures the bit width information output by the AI / ML model (such as the CSI generation part based on AI / ML or the AI / ML encoder). The bit width information can be the bit width value, or the index of the bit width value, or the maximum bit width, or the index of the maximum bit width. For example, the network device configures the terminal device to use the first method, and the network device also configures the bit width of the AI / ML model output to be 100 bits; for another example, the bit width of the output of all AI / ML models paired with the terminal device and the network device is {80, 100, 120, 200} bits, and their indexes are {00, 01, 10, 11} respectively. The network device configures the terminal device using the second method, and the number and position of the merging coefficients between the groups are the same. The network device also configures the index 11, 00, or the network device also configures the index 01. For example, the network device configures the terminal device using the second method, and the number and / or position of the merging coefficients between the groups are not exactly the same. The network device also configures the index 11, 00.

[0123] In some implementations, the merging coefficient of a spatial layer includes: a merging coefficient at one moment, or a merging coefficient at two or more moments.

[0124] For example, according to the configuration of the network device, the terminal device uses the merging coefficients of more than one time dimension (for example, moment) of the same spatial layer as a whole as the input of the AI / ML model. The time dimension is the moment or the time domain basis. The former (that is, two or more two-dimensional merging coefficient matrices) does not use the time domain basis to process the channel information of more than two moments, and the latter (that is, a three-dimensional merging coefficient matrix) uses the time domain basis to process the channel information of more than two moments (for example, projecting the channel information of four moments onto two time domain bases). Similar to the description of this embodiment, the terminal device can use the first method or the second method mentioned above to process the merging coefficients. For the second method, the configuration of K0 (the value of K0 or the maximum allowable value) can be the same for all time dimensions (for example, moments), which has the beneficial effect of simple logic implementation. There can also be two time dimensions (for example, moments) where K0 is configured (the value of K0 or the maximum allowable value) differently. The beneficial effect is that different values ​​are configured for channel properties that may be different in different time dimensions (for example, moments), which can better analyze and describe channels in different time dimensions (for example, moments), bringing performance gains. Similar to the description in this embodiment, the configuration of K0 (the value of K0 or the maximum allowable value) can be explicit or implicit, and will not be repeated here. For the second method, the configuration of the AI / ML model information and / or the bit width information of the AI / ML model can also be the same for all time dimensions (for example, moments), or there can be two time dimensions (for example, moments) where they are configured differently. The method is similar and will not be repeated here.

[0125] Example 3:

[0126] Example 3 addresses the situation where the "number of channel information included in a CSI report" in the first configuration of the network device configuration is equal to 1. One application scenario of this embodiment of the present invention is to use AI / ML methods to compress spatial channel information (or its representation in the angular delay domain) in the spatial and frequency domains to obtain CSI.

[0127] In the third embodiment, the terminal device sends a CSI report (i.e., a first CSI report) on a physical uplink shared channel (PUSCH) or a physical uplink control channel (PUCCH). In some embodiments, the "number of channel information included in a CSI report" in the first configuration of the network device configuration is equal to 1. The CSI report (i.e., the first CSI report) includes two parts.

[0128] The first part includes a rank indication (RI, if a rank indication is reported), a channel quality indication (CQI), and first information. The first information is information of an AI / ML model (such as an AI / ML-based CSI generation part or an AI / ML encoder) and / or third information. The third information is "the sum of the bit widths of the information of the combining coefficients of all spatial layers" or "the maximum value of the sum of the bit widths of the information of the combining coefficients of all spatial layers" or "the sum of the bit widths of the precoding matrix information of all spatial layers" or "the maximum value of the sum of the bit widths of the precoding matrix information of all spatial layers" reported by the terminal device. The AI / ML model (such as an AI / ML-based CSI generation part or an AI / ML encoder) can be more than one, used to generate information on the combining coefficients of all spatial layers or information on the precoding matrix. For the case where the number of spatial layers exceeds 4, the channel quality indication is the first codeword of the channel quality indication.

[0129] The second part includes information of the precoding matrix. When the number of spatial domain layers exceeds 4 but does not exceed 8, the second part also includes a second codeword of a channel quality indicator.

[0130] The first part of the first CSI report and the second part of the first CSI report are independently encoded. The terminal device sends the second part of the first CSI report after sending the first part of the first CSI report in its entirety.

[0131] In some implementations of the third embodiment, the information in the second part of the first channel state information (CSI) report may have a first priority order, which may be predefined and configured by a network device and / or specified by a standard.

[0132] In some implementations, the information in the second part is divided into more than one set, each set has a priority order, and the first priority order may refer to the priority order between the sets.

[0133] In some embodiments, each piece of information within each set may also have a priority order. That is, each piece of information within each set may also have a priority ranking, for example, first, second, ..., Xth, etc., where a smaller ranking number indicates a higher priority. In this case, the first priority order can be obtained by combining the priority orders between the sets and the priority orders between the pieces of information within the sets.

[0134] In some examples, the one or more sets may include at least one of a first set, a second set, and a third set, and may also include more sets. In the examples below in this application, the first set may also be referred to as group 0, the second set may also be referred to as group 1, and the third set may also be referred to as group 2.

[0135] The priority of the first set is higher than that of the second set, and the priority of the second set is higher than that of the third set. Information with a higher priority is sent before information with a lower priority.

[0136] In some examples, the first set includes at least one of the following information: information about a spatial basis, information about a frequency basis, and information about combining coefficients of a first predetermined spatial layer. The second set may include information about combining coefficients of the first predetermined spatial layer and / or information about combining coefficients of a second predetermined spatial layer. The third set includes information about combining coefficients of a third predetermined spatial layer.

[0137] For example, it is assumed that the value corresponding to the rank indicator of the first CSI report or the number of downlink transmission layers is N. The priority order of each set in the first CSI report is as follows:

[0138] The first set (first in priority): spatial domain-based information (such as reports), frequency domain-based information (such as reports);

[0139] The second set (second in priority): information on the combining coefficients of the first spatial layer, ..., Information on the merging coefficients of the spatial layer;

[0140] The third set (third in priority): Information on the merging coefficients of the spatial layer, ..., information on the merging coefficients of the Nth spatial layer.

[0141] For another example, the priority order of each set in the first CSI report is as follows:

[0142] The first set (first in priority): spatial basis information (such as reported), frequency basis information (such as reported), and information on the combining coefficients of the first spatial layer;

[0143] The second set (second in priority): information on the combining coefficients of the second spatial layer, ..., Information on the merging coefficients of the spatial layer;

[0144] The third set (third in priority): Information on the merging coefficients of the spatial layer, ..., information on the merging coefficients of the Nth spatial layer.

[0145] In some implementations, the priority order between each information within each set may be, for example:

[0146] In the first set, the spatial basis information, the frequency basis information and the combining coefficient information of the first predetermined spatial layer each have a priority order; and / or

[0147] In the second set, information on combining coefficients of at least two spatial layers with different numbers each has a priority order; and / or

[0148] In the third set, information on combining coefficients of at least two spatial layers with different numbers each has a priority order.

[0149] In some examples, the priority order within the first set (ie, group 0) is:

[0150] The priority of spatial-domain-based information (e.g., reports) is higher than the priority of frequency-domain-based information (e.g., reports); or

[0151] The priority of frequency-domain-based information (such as reports) is higher than the priority of spatial-domain-based information (such as reports).

[0152] In some examples, there are also priorities within the second set (i.e., group 1) and / or within the third set (i.e., group 2), such that information on combining coefficients for a layer with a smaller spatial layer number has a higher priority than information on combining coefficients for a layer with a larger spatial layer number. For example, if m < n, information on combining coefficients for the mth spatial layer has a higher priority than information on combining coefficients for the nth spatial layer.

[0153] In at least some embodiments of the third embodiment, at least a portion of the merging coefficients of at least one spatial layer are divided into more than one group, each group of merging coefficients being input to one or more artificial intelligence (AI / ML) models, and the output of one or more artificial intelligence (AI / ML) models being information about the merging coefficients of each group, wherein the grouping information of the merging coefficients of at least two spatial layers is the same or different. For details regarding the grouping of merging coefficients, please refer to the second embodiment of this application.

[0154] For example:

[0155] The first set includes at least one of the following information: information of a spatial basis, information of a frequency basis, and information of a first group of combining coefficients of a first predetermined spatial layer;

[0156] The second set includes: information of a first group of merging coefficients of the first predetermined spatial layer and / or information of a first group of merging coefficients of a second predetermined spatial layer;

[0157] The third set includes: information of the second group of merging coefficients of all spatial layers.

[0158] The information of the first group of combined coefficients refers to the information of combining the first group of combined coefficients (for example, W 2,1 ) inputs the artificial intelligence model, which outputs the information of the merging coefficients; the second set of merging coefficients (W 2,2 ) information refers to the information of the merging coefficients output by the artificial intelligence model after the second set of merging coefficients are input into the artificial intelligence model.

[0159] in:

[0160] Within the first set, the information of the spatial basis, the information of the frequency basis, and the information of the first group of combining coefficients of the first predetermined spatial layer each have a priority order; and / or

[0161] In the second set, the information of the first group of combining coefficients of at least two spatial layers with different numbers each has a priority order; and / or

[0162] In the third set, the information of the second group of combining coefficients of at least two spatial layers with different numbers each has a priority order.

[0163] In some examples, the rank indicator of the first CSI report corresponds to a value or the number of downlink transmission layers of N. The priority order of each set in the first CSI report is as follows:

[0164] The first set (first in priority): spatial domain-based information (such as reports), frequency domain-based information (such as reports);

[0165] The second set (second in priority): W of the first spatial layer 2,1 (i.e., the first group of merged information) the output of the AI / ML model corresponding to (i.e., the information corresponding to the first group of merged information), ..., W of the Nth spatial layer 2,1 (i.e., the first set of merged information) corresponds to the output of the AI / ML model (i.e., the information corresponding to the first set of merged information), where W 2,1 The definition of is given in Example 2;

[0166] The third set (third in priority): W of the first spatial layer 2,2 (i.e., the second group of merged information) the output of the AI / ML model corresponding to (i.e., the information corresponding to the second group of merged information), ..., W of the Nth spatial layer 2,2 (i.e., the second set of combined information) the output of the AI / ML model corresponding to (i.e., the information corresponding to the second set of combined information), W 2,2 The definition of is given in Example 2.

[0167] For another example, the priority order of each set in the first CSI report is as follows:

[0168] The first set (first in priority): spatial basis information (such as reports), frequency basis information (such as reports), W of the first spatial layer 2,1 The output of the corresponding AI / ML model;

[0169] The second set (second in priority): W of the second spatial layer 2,1 The output of the corresponding AI / ML model, ..., W of the Nth spatial layer 2,1 The output of the corresponding AI / ML model, W 2,1 The definition of is given in Example 2;

[0170] The third set (third in priority): W of the first spatial layer 2,2 The output of the corresponding AI / ML model, ..., W of the Nth spatial layer 2,2 The output of the corresponding AI / ML model, W 2,2 The definition of is given in Example 2.

[0171] Within the first set, the information of the spatial basis, the information of the frequency domain basis, and the information of the first group of combining coefficients of the first predetermined spatial layer each have a priority order; and / or

[0172] In the second set, the information of the first group of combining coefficients of at least two spatial layers with different numbers each has a priority order; and / or

[0173] In the third set, the information of the second group of combining coefficients of at least two spatial layers with different numbers each has a priority order.

[0174] In some examples, the priority order among the information in the first set may be, for example, that the priority order of spatial-domain-based information (e.g., report) is higher than the priority order of frequency-domain-based information (e.g., report), and the priority order of frequency-domain-based information (e.g., report) is higher than the priority order of the first group of combining coefficients of the first predetermined spatial layer. The present application is not limited thereto, and there may be various examples of the priority order among the above-mentioned information.

[0175] In some embodiments, the information in the second set (i.e., group 1) and / or the information in the third set (i.e., group 2) also have priorities. For example, the information of the combining coefficients of the layer with a smaller spatial layer number has a higher priority than the information of the combining coefficients of the layer with a larger spatial layer number. For example, if m < n, then W of the mth spatial layer is 2,1The output of the corresponding AI / ML model has a higher priority than W of the nth spatial layer. 2,1 The priority of the output of the corresponding AI / ML model; W of the mth spatial layer 2,2 The output of the corresponding AI / ML model has a higher priority than W of the nth spatial layer. 2,2 The priority ranking of the output of the corresponding AI / ML model.

[0176] In the third embodiment, more than one first channel state information (CSI) report may have a second priority order, and the second part of more than one first channel state information report may have a third priority order.

[0177] In the following description of Example 3, unless otherwise specified, the CSI report refers to the first CSI report. It should be noted that although the following description of the second priority and the third priority is based on one or more CSI reports as an example, the content of the description is also applicable to the case where one or more first channel state information reports are combined with one or more second channel state information reports. Among them, the second channel state information report can be a CSI report generated based on a codebook, or a CSI report generated based on an AI / ML method and using the right singular vector of the spatial channel matrix estimated by the terminal device as the input of the AI / ML model (CSI generation part).

[0178] In some implementations of Example 3, the third priority is related to the first priority and the second priority. For example:

[0179] In the third priority order, the first priority order is higher than the second priority order; or

[0180] In the third priority order, the second priority order is higher than the first priority order; or

[0181] In the third priority order, the second priority order is independent of the first priority order; or

[0182] The third priority order is the same as the second priority order.

[0183] In some examples, in the third priority, the second priority is higher than the first priority. For example, the second priority of CSI report A is higher than that of CSI report B, then the terminal device sends CSI report A first according to the first priority, and after all CSI report A has been sent, it sends CSI report B first according to the first priority. The first priority within CSI report A and CSI report B is as given in Example 2, for example, the priority of Group 0 is higher than the priority of Group 1, and the priority of Group 1 is higher than the priority of Group 2. The third priority can be represented by Table 1. In Table 1 and subsequent tables of this application, the smaller the value of N (indicating the rank of the third priority) in Priority N, the higher the rank of the priority, and the description of Group 0, Group 1, and Group 2 in each table can refer to the above-mentioned relevant descriptions.

[0184] Table 1

[0185] In some examples, within the third priority order, the first priority order is higher than the second priority order. For example, the second priority order of CSI report A is higher than that of CSI report B. The first priority order within CSI report A and CSI report B is as described in Example 2. For example, the priority order of group 0 is higher than that of group 1, and the priority order of group 1 is higher than that of group 2. In this example, the third priority order can be represented by Table 2.

[0186] Table 2

[0187] In some examples, in the third priority order, the first priority order and the second priority order have no relationship. The first priority order is as given in Example 2, for example, the priority order of Group 0 is higher than the priority order of Group 1, and the priority order of Group 1 is higher than the priority order of Group 2. One possibility of the third priority order is: Group 0 of all CSI reports has the highest priority, and the priorities therein are arranged according to the second priority order; then the priorities are arranged according to the second priority order among the CSI reports, that is, the priority orders of Group 1 and Group 2 of the CSI reports with the higher second priority order are higher than any of the Group 1 and Group 2 of the CSI reports with the higher second priority order.

[0188] For example, the second priority of CSI report A is higher than that of CSI report B, and the third priority can be represented by Table 3.

[0189] Table 3

[0190] Among them, in Priority 0, the priority of group 0 of CSI report A is higher than that of group 0 of CSI report B. The above table can also be expressed as Table 4.

[0191] Table 4

[0192] In some embodiments, the third priority is the same as the second priority, that is, the third priority is independent of the first priority. For example, if the second priority of CSI report A is higher than that of CSI report B, the third priority can be represented by Table 5.

[0193] Table 5

[0194] As shown in FIG3 , in some implementations of Example 3, the method of the present application may further include:

[0195] 303. The terminal device discards at least part of the information of the second part of at least one of the first channel state information reports according to the third priority order; or, the terminal device regenerates at least part of the channel state information from at least part of the information of the second part of at least one of the first channel state information reports according to the third priority order and sends the regenerates at least part of the channel state information.

[0196] In some examples of 303, the CSI report sent by the terminal device may discard a part of its second part CSI according to the third priority. In some embodiments, the CSI report sent by the terminal device may select a part of the second part CSI of the CSI report (such as the second group of the second part of the CSI report) according to the fourth priority, and regenerate the part of the second part of the first CSI report to reduce its bit width. The generation method is an AI / ML method or a code book method. The generation method is configured by the network device and / or is predefined by the standard. The above-mentioned method of network device configuration is that the network device sends a second configuration through an RRC message. The second configuration can be a CSI report configuration or a newly defined configuration.

[0197] As shown in FIG3 , in some implementations of Example 3, the method of the present application may further include:

[0198] 304. The terminal device sends a channel state information sending failure report to the network device, and / or receives a configuration sent by the network device, where the configuration is at least used to indicate information required for the terminal device to generate at least a portion of the channel state information; and

[0199] 305. Generate at least a portion of new channel state information based on the configuration, and send at least a portion of the new channel state information.

[0200] In some embodiments of operations 304 and 305, the terminal device sends a CSI transmission failure report to the network device. After receiving the failure report, the network device may send a third configuration to the terminal device. The third configuration is used by the terminal device to regenerate CSI and send it to the network device. For example, the third configuration sent by the network device includes one or more of information about the number of spatial basis numbers, the number of frequency basis numbers, the number of channel information included in a CSI report, and information about the bit width of the combining coefficients. At least a portion of the content included in the third configuration differs from that of the first configuration.

[0201] The failure report may be sent via a dedicated physical random access channel (PRACH), a physical uplink control channel resource similar to a scheduling request (PUCCH SR-like resource), a two-step random access channel (RACH) on a PUSCH, an RRC message, or a media access control element (MAC CE), wherein the MAC CE may be newly defined. The third configuration may be sent via an RRC message or may be part of an existing configuration and activated via MAC CE signaling.

[0202] Example 4:

[0203] Example 4 considers the situation where the "number of channel information included in a CSI report" in the first configuration of the network device configuration is greater than 1. One application scenario of the embodiments of the present invention is to use AI / ML methods to compress spatial channel information (or its representation in the angle delay Doppler domain) in the spatial domain, frequency domain, and time domain to obtain CSI.

[0204] In the fourth embodiment, the terminal device sends a first CSI report on the PUSCH. In some embodiments, the "number of channel information included in a CSI report" in the first configuration of the network device configuration is greater than 1. The CSI report (referred to as the first CSI report) may include a channel quality indicator (CQI). The channel quality indicator may be of the following two types.

[0205] The first possibility: the channel quality indicator is unique.

[0206] The second possibility: the channel quality indication is not unique. The number of channel quality indications is specified by the standard or predefined, and there can be 2, ..., A, where the value of A is less than or equal to the "number of channel information contained in a CSI report" in the first configuration of the network device configuration. For example: if the "number of channel information contained in a CSI report" in the first configuration is equal to 4, and the standard specifies that the number of channel quality indications is 2, then the first channel quality indication is used to describe the first and second channel information, and the second channel quality indication is used to describe the third and fourth channel information. For another example: if the "number of channel information contained in a CSI report" in the first configuration is equal to 5, and the standard specifies that the number of channel quality indications is 2, then the first channel quality indication is used to describe the first and second channel information, and the second channel quality indication is used to describe the third, fourth, and fifth channel information.

[0207] In the fourth embodiment, the first CSI report includes two parts.

[0208] The first part of the first CSI report includes a rank indication (RI, if a rank indication is reported), a channel quality indication, and first information. The first information is information of an AI / ML model (such as an AI / ML-based CSI generation part or an AI / ML encoder) and / or third information. The third information is "the sum of the bit widths of the information of the combining coefficients of all spatial layers" or "the sum of the bit widths of the precoding matrix information of all spatial layers" reported by the terminal device. There can be more than one AI / ML model (such as an AI / ML-based CSI generation part or an AI / ML encoder) for generating information of the combining coefficients of all spatial layers or information of the precoding matrix. For the first possibility, the channel quality indication is the only channel quality indication. For the second possibility, the channel quality indication is the first channel quality indication.

[0209] The second part of the first CSI report includes information about the precoding matrix. For the second possibility, the second part also includes a second channel quality indicator, that is, the second part also includes at least part of the channel quality indicator information.

[0210] The first part of the first CSI report and the second part of the first CSI report are independently encoded. The terminal device sends the second part of the first CSI report after sending the first part of the first CSI report in its entirety.

[0211] In the fourth embodiment, the information in the second part of the first channel state information report has a first priority order.

[0212] In some embodiments, the information in the second portion is divided into one or more sets, each set having a priority order. In addition, the information within each set has a priority order. Thus, the first priority order can be a combination of the priority order of each set and the priority order of the information within each set.

[0213] In some embodiments, the one or more sets include at least one of a first set, a second set, and a third set, wherein the first set has a higher priority than the second set, and the second set has a higher priority than the third set.

[0214] The first set, the second set, and the third set may also be referred to as group 0, group 1, and group 2, respectively.

[0215] In some embodiments, the first set includes at least one of the following information: information on a spatial domain basis, information on a frequency domain basis, information on a time domain basis, a wideband channel quality indication in at least part of the channel quality indication information, and information on a combining coefficient of a first predetermined spatial domain layer.

[0216] The second set includes at least one of the following information: information on the combining coefficient of the first predetermined spatial layer, information on the combining coefficient of the second predetermined spatial layer, and the first predetermined subband second channel quality indicator in at least part of the channel quality indicator information.

[0217] The third set includes at least one of the following information: information on combining coefficients of a third predetermined spatial layer, and a second predetermined subband second channel quality indicator in at least part of the channel quality indicator information.

[0218] Within the first set, the spatial basis information, the frequency domain basis information, the time domain basis information, the wideband channel quality indicator, and the combining coefficient information of the first predetermined spatial layer each have a priority order; and / or

[0219] In the second set, the information of combining coefficients of at least two spatial layers with different numbers and the second channel quality indicator of the first predetermined subband each have a priority order; and / or

[0220] In the third set, the information of combining coefficients of at least two spatial layers with different numbers and the second channel quality indicator of the second predetermined subband each have a priority order.

[0221] For an explanation of the order of priority, please refer to Example 3.

[0222] In some examples, it is assumed that the value corresponding to the rank indicator of the first CSI report or the number of downlink transmission layers is N. The priority order of each group in the first CSI report can be, for example:

[0223] The first set (first in priority): spatial domain-based information (such as a report), frequency domain-based information (such as a report), time domain-based information (such as a report), and broadband second channel quality indication (such as a report).

[0224] The second set (second in priority): information on the combining coefficients of the first spatial layer, ..., Information on the combining coefficients of the spatial layer, and the second channel quality indicator (such as report) of the even-numbered / indexed (or odd-numbered) sub-band.

[0225] The third set (third in priority): Information on combining coefficients of the spatial layer, ..., information on combining coefficients of the Nth spatial layer, and second channel quality indication (such as report) of odd-numbered / indexed (or even-numbered) subbands.

[0226] In other examples, the priority order of the groups in the first CSI report may be, for example:

[0227] The first set (priority first): spatial basis information (such as reported), frequency basis information (such as reported), time basis information (such as reported), wideband second channel quality indicator (such as reported), and information on combining coefficients of the first spatial layer;

[0228] The second set (second in priority): information on the combining coefficients of the second spatial layer, ..., Information on combining coefficients of the spatial layer, and second channel quality indicators of even-numbered / odd-numbered subbands (e.g., reports);

[0229] The third set (third in priority): Information on combining coefficients of the spatial layer, ..., information on combining coefficients of the Nth spatial layer, and second channel quality indication (such as report) of odd-numbered / indexed (or even-numbered) subbands.

[0230] In at least one embodiment of the fourth embodiment, at least a portion of the merging coefficients of at least one spatial layer are divided into more than one group, each group of merging coefficients being input to one or more artificial intelligence (AI / ML) models, and the output of one or more artificial intelligence (AI / ML) models being information about the merging coefficients of each group, wherein the grouping information of the merging coefficients of at least two spatial layers is the same or different. For a description of the grouping of merging coefficients, reference may be made to the second embodiment.

[0231] In some embodiments of the fourth embodiment, when at least a portion of the combining coefficients of at least one spatial layer are divided into more than one group:

[0232] The first set includes at least one of the following information: information of a spatial domain basis, information of a frequency domain basis, information of a time domain basis, a wideband channel quality indicator in at least part of the channel quality indicator information, and information of a first group of combining coefficients of a first predetermined spatial domain layer;

[0233] The second set includes at least one of the following information: information of a first group of combining coefficients of the first predetermined spatial layer, information of a first group of combining coefficients of the second predetermined spatial layer, and a first predetermined subband second channel quality indicator in at least part of the channel quality indicator information;

[0234] The third set includes at least one of the following information: information of a second group of combining coefficients of all spatial layers, and a second predetermined subband second channel quality indicator in at least part of the channel quality indicator information.

[0235] in:

[0236] Within the first set, the spatial basis information, the frequency domain basis information, the time domain basis information, the wideband channel quality indicator, and the first group of combining coefficients of the first predetermined spatial layer each have a priority order; and / or

[0237] In the second set, the information of the first group of combining coefficients of at least two spatial layers with different numbers and the second channel quality indicator of the first predetermined subband each have a priority order; and / or

[0238] In the third set, the information of the second group of combining coefficients of at least two spatial layers with different numbers and the second predetermined sub-band second channel quality indicator each have a priority order.

[0239] In some examples, it is assumed that the value corresponding to the rank indicator of the first CSI report or the number of downlink transmission layers is N. The priority order of each group in the first CSI report is, for example, as follows:

[0240] The first set (first in priority): spatial domain-based information (such as a report), frequency domain-based information (such as a report), time domain-based information (such as a report), and wideband second channel quality indication (such as a report);

[0241] The second set (second in priority): W of the first spatial layer 2,1 The output of the corresponding AI / ML model, ..., W of the Nth spatial layer 2,1The output of the corresponding AI / ML model, even-numbered / indexed (or odd-numbered) subbands, where W 2,1 The definition of is given in Example 2;

[0242] The third set (third in priority): W of the first spatial layer 2,2 The output of the corresponding AI / ML model, ..., W of the Nth spatial layer 2,2 The output of the corresponding AI / ML model, odd-numbered / indexed (or even-numbered) subband second channel quality indicator (such as report), where W 2,2 The definition of is given in Example 2.

[0243] In other examples, it is assumed that the value corresponding to the rank indicator of the first CSI report or the number of downlink transmission layers is N. The priority order of each group in the first CSI report is as follows:

[0244] The first set (first in priority): spatial domain-based information (such as report), frequency domain-based information (such as report), time domain-based information (such as report), wideband second channel quality indicator (such as report), W of the first spatial layer 2,1 The output of the corresponding AI / ML model;

[0245] The second set (second in priority): W of the second spatial layer 2,1 The output of the corresponding AI / ML model, ..., W of the Nth spatial layer 2,1 The output of the corresponding AI / ML model, the even-numbered / indexed (or odd-numbered) sub-band 12th channel quality indicator (as reported), W 2,1 The definition of is given in Example 2;

[0246] The third set (third in priority): W of the first spatial layer 2,2 The output of the corresponding AI / ML model, ..., W of the Nth spatial layer 2,2 The output of the corresponding AI / ML model, odd-numbered / indexed (or even-numbered) subband second channel quality indication (such as report), W 2,2 The definition of is given in Example 2.

[0247] In addition, similar to the third embodiment, in the fourth embodiment, two or more CSI reports may have a second priority; in addition, the second part of one or more first channel state information reports may have a third priority.

[0248] The descriptions of the second priority and the third priority in the third embodiment are combined here and will not be repeated here.

[0249] The relevant descriptions about operations 303, 304, and 305 in the third embodiment are also applicable to the fourth embodiment. Therefore, the relevant contents are merged here and will not be repeated here.

[0250] Example 5

[0251] In embodiment five, the first channel state information report (for example, the first channel state information report of embodiment three or embodiment four) further includes information on the reporting order of information for representing the precoding matrices of N spatial domain layers, where N is a natural number greater than or equal to 2.

[0252] The information on the reporting order of the information for representing the precoding matrices for the N spatial domain layers is in the first part or the second part of the first channel state information report. When the information on the reporting order of the information for representing the precoding matrices for the N spatial domain layers is included in the second part, the information on the reporting order of the information for representing the precoding matrices for the N spatial domain layers and other content in the second part of the first channel state information report are encoded separately.

[0253] In some examples of the fifth embodiment, the order in which precoding matrix information for N spatial layers is reported is the order in which the artificial intelligence (AI / ML) models that generate the precoding matrix information and / or combining coefficient information for the N spatial layers are arranged. For example, if a total of N = 4 spatial layers are reported, the information "the order in which the precoding matrix information for the N spatial layers is reported" may be: information for AI / ML model 2, information for AI / ML model 6, information for AI / ML model 3, and information for AI / ML model 1; this indicates that the reported first spatial layer was generated by AI / ML model 2, the reported second spatial layer was generated by AI / ML model 6, the reported third spatial layer was generated by AI / ML model 3, and the reported fourth spatial layer was generated by AI / ML model 1. For another example, multiple groups may be pre-defined, each with its own index. Each group may include information for multiple AI / ML models arranged in sequence. In this way, the information "the order in which the precoding matrix information for the N spatial layers is reported" is reported using the group index.

[0254] In some examples of the fifth embodiment, the reporting order of the precoding matrix information of N spatial layers is: the order in which the bit widths of the precoding matrix information and / or combining coefficient information of the N spatial layers are arranged. For example, if a total of N=3 spatial layers are reported, the information "the reporting order of the precoding matrix information of the N spatial layers" may be: 60 bits, 100 bits, 30 bits; this indicates that the bit width of the reported precoding matrix information and / or combining coefficient information of the first spatial layer is 60 bits, the bit width of the reported precoding matrix information and / or combining coefficient information of the second spatial layer is 100 bits, and the bit width of the reported precoding matrix information and / or combining coefficient information of the third spatial layer is 30 bits. For another example, multiple groups may be predefined, each group having its own index. Each group may include information on multiple precoding matrices and / or combining coefficient bit widths arranged in sequence. In this way, the information "the reporting order of the precoding matrix information of the N spatial layers" is reported using the group index.

[0255] In some examples, the reporting order of the precoding matrix information of the N spatial domain layers is specified by the standard, or predefined, or agreed upon by the network device and the terminal device, or configured by the network device, or determined by the terminal device.

[0256] In the fifth embodiment, the N spatial domain layers may include the first predetermined spatial domain layer, the second predetermined spatial domain layer, and the third predetermined spatial domain layer described in the third and fourth embodiments.

[0257] The fifth embodiment is described below through some examples.

[0258] In the following example, information on the reporting order of information for representing precoding matrices for N spatial domain layers is in the second part of the first channel state information report, and the information on the reporting order of information for representing precoding matrices for N spatial domain layers and other contents in the second part of the first channel state information report are encoded separately.

[0259] In some examples, it is assumed that the value corresponding to the rank indicator of the first CSI report (i.e., the first channel state information report) or the number of layers of downlink transmission (i.e., the number of spatial layers) is N. The priority order of each part in the first CSI report is as follows:

[0260] The information of the reporting order of the precoding matrix information of N spatial layers (such as reporting), the information of the spatial basis (such as reporting), and the information of the frequency basis (such as reporting) are prioritized first;

[0261] The information of the merging coefficients of the first spatial layer, ..., The information of the merging coefficients of the spatial layer has the second highest priority;

[0262] No. The information of the merging coefficients of the spatial layers, ..., the information of the merging coefficients of the Nth spatial layer has the third priority.

[0263] In some examples, the priority order may also be:

[0264] The information on the reporting order of the precoding matrix information of the N spatial layers (such as reported), the information on the spatial basis (such as reported), the information on the frequency basis (such as reported), and the information on the combining coefficients of the first spatial layer are prioritized first;

[0265] The information of the merging coefficients of the second spatial layer, ..., The information of the merging coefficients of the spatial layer has the second highest priority;

[0266] No. The information of the merging coefficients of the spatial layers, ..., the information of the merging coefficients of the Nth spatial layer has the third priority.

[0267] In other examples, it is assumed that the value corresponding to the rank indicator of the first CSI report or the number of downlink transmission layers is N. The priority order of each part in the first CSI report is as follows:

[0268] The information of the reporting order of the precoding matrix information of N spatial layers (such as reporting), the information of the spatial basis (such as reporting), and the information of the frequency basis (such as reporting) are prioritized first;

[0269] W of the first spatial layer 2,1 The output of the corresponding AI / ML model, ..., W of the Nth spatial layer 2,1 The output of the corresponding AI / ML model is prioritized second, where W 2,1 The definition of can refer to Example 2;

[0270] W of the first spatial layer 2,2 The output of the corresponding AI / ML model, ..., W of the Nth spatial layer 2,2 The output of the corresponding AI / ML model is prioritized third, where W 2,2 The definition of can refer to Example 2.

[0271] In some other examples, the priority order may also be:

[0272] The reporting order of the precoding matrix information of N spatial layers (such as reported), the information of the spatial basis (such as reported), the information of the frequency basis (such as reported), the W of the first spatial layer 2,1 The output of the corresponding AI / ML model is prioritized first;

[0273] W of the second spatial layer 2,1 The output of the corresponding AI / ML model, ..., W of the Nth spatial layer 2,1 The output of the corresponding AI / ML model is prioritized second, where W 2,1 The definition of is in reference embodiment 2;

[0274] W of the first spatial layer 2,2 The output of the corresponding AI / ML model, ..., W of the Nth spatial layer 2,2 The output of the corresponding AI / ML model is prioritized third, where W 2,2 The definition of can refer to Example 2.

[0275] In some other examples, it is assumed that the value corresponding to the rank indicator of the first CSI report or the number of downlink transmission layers is N. The priority order of each part in the first CSI report is as follows:

[0276] Information (such as a report) on the order in which data of N spatial domain layers are arranged, with priority being given to spatial-based information (such as a report), frequency-domain-based information (such as a report), time-domain-based information (such as a report), and the wideband second channel quality indicator (such as a report) being ranked first;

[0277] The information of the merging coefficients of the first spatial layer, ..., Information on combining coefficients of the spatial layer, with the second channel quality indication (such as report) of the even-numbered / odd-numbered sub-band being prioritized second;

[0278] No. The information of the combining coefficients of the spatial layer, ..., the information of the combining coefficients of the Nth spatial layer, the priority of the second channel quality indication (such as report) of the odd-numbered / indexed (or even-numbered) sub-band is ranked third.

[0279] In this further example, the priority order may also be:

[0280] Information on the order of arrangement of data of N spatial layers (e.g., reported), spatial basis information (e.g., reported), frequency basis information (e.g., reported), time basis information (e.g., reported), wideband second channel quality indicator (e.g., reported), and information on combining coefficients of the first spatial layer are prioritized first;

[0281] The information of the merging coefficients of the second spatial layer, ..., The information of the combining coefficients of the spatial layer, the priority of the second channel quality indication (such as reporting) of the even-numbered / indexed (or odd-numbered) sub-band is ranked second;

[0282] No. The information of the combining coefficients of the spatial layer, ..., the information of the combining coefficients of the Nth spatial layer, the priority of the second channel quality indication (such as report) of the odd-numbered / indexed (or even-numbered) sub-band is ranked third.

[0283] In some further examples, it is assumed that the value corresponding to the rank indicator of the first CSI report or the number of downlink transmission layers is N. The priority order of each part in the first CSI report is as follows:

[0284] Information (such as a report) on the order in which data of N spatial domain layers are arranged, with priority being given to spatial-based information (such as a report), frequency-domain-based information (such as a report), time-domain-based information (such as a report), and the wideband second channel quality indicator (such as a report) being ranked first;

[0285] W of the first spatial layer 2,1 The output of the corresponding AI / ML model, ..., W of the Nth spatial layer 2,1 The output of the corresponding AI / ML model, the even number / index (or odd number) sub-band 12 channel quality indication (such as report) has the second highest priority, where W 2,1 The definition of refers to the aforementioned embodiment 2;

[0286] W of the first spatial layer 2,2 The output of the corresponding AI / ML model, ..., W of the Nth spatial layer 2,2 The output of the corresponding AI / ML model, the odd-numbered / indexed (or even-numbered) sub-band second channel quality indication (such as report) is ranked third in priority, where W 2,2 The definition of refers to the aforementioned embodiment 2.

[0287] In some further examples, the priority order may also be:

[0288] Information on the order of data of N spatial domain layers (such as reported), spatial basis information (such as reported), frequency domain basis information (such as reported), time domain basis information (such as reported), wideband second channel quality indicator (such as reported), W of the first spatial domain layer 2,1 The output of the corresponding AI / ML model is prioritized first;

[0289] W of the second spatial layer 2,1 The output of the corresponding AI / ML model, ..., W of the Nth spatial layer 2,1 The output of the corresponding AI / ML model, the even numbered / indexed (or odd numbered) sub-band 12th channel quality indication (such as report) is ranked second in the new 12th priority, where W 2,1 The definition of refers to the aforementioned embodiment 2;

[0290] W of the first spatial layer 2,2The output of the corresponding AI / ML model, ..., W of the Nth spatial layer 2,2 The output of the corresponding AI / ML model, the odd-numbered / indexed (or even-numbered) sub-band second channel quality indication (such as report) is ranked third in the new twelfth priority, where W 2,2 The definition of refers to the aforementioned embodiment 2.

[0291] Example 6

[0292] In the present application, the implementation method of the index of the spatial layer in the "1st spatial layer", "2nd spatial layer",..., "Nth spatial layer" involved in Example 3 and Example 4 can be specified by the standard, or predefined, or agreed upon by the network device and the terminal device, or configured by the network device, or determined by the terminal device.

[0293] In the sixth embodiment, the implementation of the index of each spatial layer is described.

[0294] Method 1: The order of the spatial layer indexes is the same as the reporting order of the precoding matrix information of N≥2 spatial layers in the fifth embodiment.

[0295] The beneficial effects are: the terminal device may have a clearer understanding of the channel environment around it, and the order of the spatial layers of the precoding matrix reported by the terminal device may reflect the order of importance of the spatial layers as considered by the terminal device; in addition, this method is simple to implement, avoids ambiguity, and is simple, clear and easy to understand.

[0296] Method 2: The order of the spatial layer indexes is arranged from large to small, or from small to large, according to the bit width of the precoding matrix information or the bit width of the combining coefficient information of each spatial layer of N ≥ 2 spatial layers. If the bit width of the precoding matrix information or the bit width of the combining coefficient information of at least two spatial layers is the same, the order of the indexes of the at least two spatial layers may be determined by the terminal device.

[0297] The beneficial effect of method 2 is: if arranged from large to small according to bit width, then the bit width may be more important to the spatial layer, and the precoding matrix information of the more important spatial layer is sent first; if arranged from small to large according to bit width, then the precoding matrix information of the spatial layer corresponding to the small bit width is sent first, and the precoding matrix information of as many spatial layers as possible can be sent when the uplink resources are limited.

[0298] Method 3: The order of the spatial layer indices is arranged from largest to smallest, or from smallest to largest, based on the eigenvalues ​​(singular values) corresponding to the eigenvectors (right singular vectors) corresponding to the precoding matrix information of each of N ≥ 2 spatial layers. If at least two spatial layers have the same eigenvalues ​​(singular values), the order of the indices of the at least two spatial layers may be determined by the terminal device.

[0299] The beneficial effect of the former is: if arranged from large to small according to the eigenvalue (singular value), then the eigenvalue (singular value) is likely to be more important to the spatial layer, and the precoding matrix information of the more important spatial layer is sent first; if arranged from small to large according to the eigenvalue (singular value), then the spatial layer corresponding to the small eigenvalue (singular value) may have a small bit width of the corresponding precoding matrix, and the precoding matrix information of the spatial layer corresponding to the small eigenvalue (singular value) is sent first, so that the precoding matrix information of as many spatial layers as possible can be sent when the uplink resources are limited.

[0300] Example 7

[0301] The seventh embodiment is independent of the first to sixth embodiments.

[0302] In the seventh embodiment, the network device sends a fourth configuration including at least one of "information on the amount of channel information included in a CSI report" and information on the bit width of precoding matrix information. The channel information is information on a spatial channel at a time instant.

[0303] Depending on the configuration of the network device, the CSI reported by the terminal device may include information about the precoding matrix. The precoding matrix information is generated by an AI / ML method / module. The input to the AI / ML method / module is the spatial channel matrix estimated by the terminal device using the CSI-RS or the right singular vectors (or eigenvectors) of the spatial channel matrix.

[0304] In some implementations, the “number of channel information included in one CSI report” in the fourth configuration of the network device configuration is equal to 1. The CSI report (referred to as the 51st CSI report) includes two parts.

[0305] The first part includes a rank indication (RI, if a rank indication is reported), a channel quality indication (CQI), and first information. The first information is information of an AI / ML model (such as an AI / ML-based CSI generation part or an AI / ML encoder) and / or third information. The third information is the "sum of the bit widths of all spatial layer precoding matrix information" reported by the terminal device. There can be more than one AI / ML model (such as an AI / ML-based CSI generation part or an AI / ML encoder) for generating information about the precoding matrices of all spatial layers. For the case where the number of spatial layers exceeds 4, the channel quality indication is the first codeword of the channel quality indication.

[0306] The second part includes information of the precoding matrix. When the number of spatial domain layers exceeds 4 but does not exceed 8, the second part also includes a second codeword of a channel quality indicator.

[0307] The first part of the 51st CSI report and the second part of the 51st CSI report are independently encoded. The terminal device sends the second part of the 51st CSI report after sending the first part of the 51st CSI report in its entirety.

[0308] In some implementations, the "number of channel information included in a CSI report" in the fourth configuration of the network device configuration is greater than 1. The CSI report (referred to as the 52nd CSI report) may include a channel quality indicator (CQI). The channel quality indicator may be of the following two types.

[0309] The first possibility: the channel quality indicator is unique.

[0310] The second possibility: the channel quality indication is not unique. The number of channel quality indications is specified by the standard or predefined, and there can be 2, ..., A, where the value of A is less than or equal to the "number of channel information contained in a CSI report" in the fourth configuration of the network device configuration. For example: if the "number of channel information contained in a CSI report" in the fourth configuration is equal to 4, and the standard specifies that the number of channel quality indications is 2, then the first channel quality indication is used to describe the first and second channel information, and the second channel quality indication is used to describe the third and fourth channel information. For another example: if the "number of channel information contained in a CSI report" in the fourth configuration is equal to 5, and the standard specifies that the number of channel quality indications is 2, then the first channel quality indication is used to describe the first and second channel information, and the second channel quality indication is used to describe the third, fourth, and fifth channel information.

[0311] The 52nd CSI report contains two parts.

[0312] The first part includes a rank indication (RI, if a rank indication is reported), a channel quality indication, and an eleventh information. The eleventh information is information of an AI / ML model (such as an AI / ML-based CSI generation part or an AI / ML encoder) and / or the thirteenth information. The thirteenth information is the "sum of the bit widths of all spatial layer precoding matrix information" reported by the terminal device. There can be more than one AI / ML model (such as an AI / ML-based CSI generation part or an AI / ML encoder) for generating information about precoding matrices for all spatial layers. For the first possibility, the channel quality indication is the only channel quality indication. For the second possibility, the channel quality indication is the first channel quality indication.

[0313] The second part includes information of the precoding matrix. For the second possibility, the second part also includes the second channel quality indicator.

[0314] The first part of the 52nd CSI report and the second part of the 52nd CSI report are independently encoded. The terminal device sends the second part of the 52nd CSI report after sending the first part of the 52nd CSI report in its entirety.

[0315] The CSI reported by the terminal device (the 51st CSI report and the 52nd CSI report) also includes information on "the reporting order of information on the precoding matrices of N spatial domain layers".

[0316] An example is the order in which the information of the AI / ML models that generate the precoding matrix information for these N spatial layers is arranged. For example, if a total of N = 4 spatial layers are reported, the information on the "reporting order of the precoding matrix information for the N spatial layers" can be: information on AI / ML model 2, information on AI / ML model 6, information on AI / ML model 3, and information on AI / ML model 1; indicating that the reported first spatial layer is generated by AI / ML model 2, the reported second spatial layer is generated by AI / ML model 6, the reported third spatial layer is generated by AI / ML model 3, and the reported fourth spatial layer is generated by AI / ML model 1. For another example, multiple groups can be pre-set, each with its own index, and each group can include information on multiple AI / ML models arranged in sequence. In this way, the information on the "reporting order of the precoding matrix information for the N spatial layers" is reported using the group index.

[0317] An example is: the order of the bit width of the information of the precoding matrix of these N spatial layers. For example, if a total of N=3 spatial layers are reported, the information of "the order of reporting the information of the precoding matrix of the N spatial layers" can be: 60 bits, 100 bits, 30 bits; indicating that the bit width of the information of the precoding matrix of the first spatial layer reported is 60 bits, the bit width of the information of the precoding matrix of the second spatial layer reported is 100 bits, and the bit width of the information of the precoding matrix of the third spatial layer reported is 30 bits. For another example, multiple groups can be pre-set, each group has its own index, and each group can include information of the bit width of multiple precoding matrix information arranged in order. In this way, the information of "the order of reporting the information of the precoding matrix of the N spatial layers" is reported by the group index.

[0318] If N=1, the CSI generated by the AI / ML model may not include the information on the "reporting order of the information of the precoding matrices of the N spatial layers". The information on the "reporting order of the information of the precoding matrices of the N spatial layers" (e.g., reported) may be:

[0319] Possibility one: In the first installment of CSI.

[0320] Possibility 2: In the second part of the CSI, the "information on the arrangement order of the data of the N spatial domain layers" should be encoded separately from other contents in the second part of the CSI.

[0321] A CSI report contains one or more channel information. In some embodiments, a CSI report contains more than one channel information, and the interval between two adjacent channel information can be configured by the network device and / or predefined, as specified by the standard. The interval can be a time interval. For example, the standard specifies that the interval can be 4ms, 5ms, 6ms, or 8ms, and the network device configures one of these options. The configuration can be in the form of a numerical value or an index. In some embodiments, a CSI report contains more than or equal to two channel information, for example, an integer in the range of 2-16. The intervals between any two adjacent channel information are the same; or there are at least two unequal intervals.

[0322] In the seventh embodiment, the second part of the CSI within a CSI report has a priority of 101, which is given by the spatial layer information. The implementation of the index of the spatial layer in "1st spatial layer", "2nd spatial layer", ..., "Nth spatial layer" can be specified by the standard, predefined, agreed upon by the network device and the terminal device, configured by the network device, or determined by the terminal device. The implementation can be as follows:

[0323] Method 1: The order of the spatial layer indexes is the same as the "reporting order of the precoding matrix information of N≥2 spatial layers" described in the fifth embodiment.

[0324] The beneficial effect is that the terminal device may have a clearer understanding of the channel environment around it, and the order of the spatial layers of the precoding matrix reported by the terminal device may reflect the order of importance of the spatial layers considered by the terminal device.

[0325] Another beneficial effect of having the order of precedence be the same as the order of reporting is that it simplifies implementation, avoids ambiguity, and makes it clear and understandable.

[0326] Method 2: The order of the spatial layer indexes is arranged from large to small, or from small to large, according to the bit width of the precoding matrix information of each spatial layer of N ≥ 2 spatial layers. If the bit width of the precoding matrix information of at least two spatial layers is the same, the order of the indexes of the at least two spatial layers may be determined by the terminal device.

[0327] The beneficial effect of the former is that a larger bit width may be more important to the spatial layer, and the information of the precoding matrix of the more important spatial layer is sent first.

[0328] The beneficial effect of the latter is that the precoding matrix information of the spatial domain layer corresponding to the smaller bit width is sent first, and the precoding matrix information of as many spatial domain layers as possible can be sent when the uplink resources are limited.

[0329] Method 3: The order of the spatial layer indices is arranged from largest to smallest, or from smallest to largest, based on the eigenvalues ​​(singular values) corresponding to the eigenvectors (right singular vectors) corresponding to the precoding matrix information of each of N ≥ 2 spatial layers. If at least two spatial layers have the same eigenvalues ​​(singular values), the order of the indices of the at least two spatial layers may be determined by the terminal device.

[0330] The beneficial effect of the former is that a large eigenvalue (singular value) is likely to be more important to the spatial layer, and the information of the precoding matrix of the more important spatial layer is sent first.

[0331] The beneficial effect of the latter is that the spatial layer corresponding to the small eigenvalue (singular value) may have a small bit width of the corresponding precoding matrix, and the information of the precoding matrix of the spatial layer corresponding to the small eigenvalue (singular value) is sent first. When the uplink resources are limited, the information of the precoding matrix of as many spatial layers as possible can be sent.

[0332] Some examples are given below, in which the implementation of the index of the spatial layers in "the first spatial layer", "the second spatial layer", ..., "the Nth spatial layer" can be any of the above three methods.

[0333] An implementation of the 101st priority order given below may be used when the number of channel information included in a CSI report is 1.

[0334] The 101st priority of the information of the precoding matrix of the first spatial layer is ranked first;

[0335] The information of the precoding matrix of the second spatial layer, ..., The 101st priority of the information of the precoding matrix of the spatial layer ranks second;

[0336] No. The information of the precoding matrix of the spatial domain layer, ..., the information of the precoding matrix of the Nth spatial domain layer has a 101st priority and ranks third.

[0337] An implementation of the 101st priority order given below may be used when the number of channel information included in a CSI report is 1.

[0338] Information (e.g., report) regarding the order in which data of N spatial layers are arranged, with the precoding matrix information of the first spatial layer being ranked first with a 101st priority;

[0339] The information of the precoding matrix of the second spatial layer, ..., The 101st priority of the information of the precoding matrix of the spatial layer ranks second;

[0340] No. The information of the precoding matrix of the spatial domain layer, ..., the information of the precoding matrix of the Nth spatial domain layer has a 101st priority and ranks third.

[0341] An implementation of the 101st priority order given below may be used when the number of channel information included in a CSI report is greater than one.

[0342] For the wideband second channel quality indicator (e.g., reported), the information of the precoding matrix of the first spatial layer has a 101st priority order;

[0343] The information of the precoding matrix of the second spatial layer, ..., For the information of the precoding matrix of the spatial layer, the second channel quality indicator (such as report) of the even-numbered / indexed (or odd-numbered) subband has the 101st priority and ranks second;

[0344] No. The information of the precoding matrix of the spatial layer, ..., the information of the precoding matrix of the Nth spatial layer, the 101st priority of the second channel quality indication (such as report) of the odd-numbered / indexed (or even-numbered) subband ranks third.

[0345] An implementation of the 101st priority order given below may be used when the number of channel information included in a CSI report is greater than one.

[0346] Information on the order of data of N spatial layers (e.g., reported), wideband second channel quality indicator (e.g., reported), and information on the precoding matrix of the first spatial layer with the 101st priority being first;

[0347] The information of the precoding matrix of the second spatial layer, ..., For the information of the precoding matrix of the spatial layer, the second channel quality indicator (such as report) of the even-numbered / indexed (or odd-numbered) subband has the 101st priority and ranks second;

[0348] No. The information of the precoding matrix of the spatial layer, ..., the information of the precoding matrix of the Nth spatial layer, the 101st priority of the second channel quality indication (such as report) of the odd-numbered / indexed (or even-numbered) subband ranks third.

[0349] For all implementations of the above priority order 101:

[0350] In some embodiments, the set consisting of all information ranked first in the 101st priority can be called Group 0, the set consisting of all information ranked second in the 101st priority can be called Group 1, and the set consisting of all information ranked third in the 101st priority can be called Group 2.

[0351] In some implementations, there is also a priority within group 0, for example, information (such as a report) about the order of data for the N spatial layers takes precedence over information about the precoding matrix for the first spatial layer. (There are two possibilities.)

[0352] In some implementations, there are also priorities within the first group and the second group. For example, the priority of the precoding matrix information of the layer with a smaller spatial layer number is higher than the priority of the precoding matrix information of the layer with a larger spatial layer number. For example, if m<n, the priority of the precoding matrix information of the mth spatial layer is higher than the priority of the precoding matrix information of the nth spatial layer.

[0353] According to the above description, embodiment seven may provide a method for generating channel state information and / or a method for receiving channel state information.

[0354] FIG4 is a schematic diagram of a method for generating channel state information according to Embodiment 7, which is applied to a terminal device. As shown in FIG4 , the method may include:

[0355] 401. The terminal device generates one or more channel state information (CSI) reports, where the channel state information reports include information of a precoding matrix and / or a reporting order of information of precoding matrices of N spatial layers (N>1), and at least a portion of the precoding matrix information is generated by an artificial intelligence (AI / ML) model, wherein the channel state information (CSI) report has a first part and a second part, and the second part of the one or more channel state information (CSI) reports has a priority order.

[0356] As shown in FIG4 , the method may further include:

[0357] 402. After the terminal device has completely sent the first part of the channel state information (CSI) report, it sends the second part.

[0358] 403. The terminal device discards at least part of the second part of at least one channel state information report according to a third priority order; or, the terminal device regenerates at least part of the channel state information from at least part of the second part of at least one channel state information report according to the third priority order and sends the regenerated channel state information.

[0359] 404. The terminal device sends a channel state information sending failure report to the network device, and / or receives a configuration sent by the network device, where the configuration is at least used to instruct the terminal device on information required to generate at least a portion of the channel state information; and

[0360] 405. Generate at least a portion of new channel state information based on the configuration, and send at least a portion of the new channel state information.

[0361] In the example shown in Figure 4, the channel state information (CSI) report may be, for example, the 51st channel state information (CSI) report or the 52nd channel state information (CSI) report in Example 7. In addition, for the description of the third priority, reference may be made to Example 3.

[0362] FIG5 is a schematic diagram of a method for receiving channel state information according to Embodiment 7. As shown in FIG5 , the method includes:

[0363] 501. Receive one or more channel state information (CSI) reports generated by a terminal device, wherein the channel state information report includes information of a precoding matrix and / or a reporting order of information of precoding matrices of N spatial layers (N>1), wherein at least a portion of the precoding matrix information is generated by an artificial intelligence (AI / ML) model, and the channel state information (CSI) report has a first part and a second part, and the second part of the one or more channel state information (CSI) reports has a priority.

[0364] In some embodiments, as shown in FIG5 , the method further includes:

[0365] 502. The network device receives a channel state information sending failure report sent by the terminal device, and / or sends a configuration to the terminal device, where the configuration is at least used to instruct the terminal device to generate at least a portion of information required for the channel state information; and

[0366] 503. Receive at least a portion of new channel state information generated by the terminal device based on the configuration.

[0367] In the example shown in FIG5 , the channel state information (CSI) report may be, for example, the 51st channel state information (CSI) report or the 52nd channel state information (CSI) report in the seventh embodiment.

[0368] According to an embodiment of the first aspect, it is possible to determine the priority of the second part of the channel state information (CSI) report in a scenario where information of a precoding matrix and / or information of a combining coefficient is generated using an artificial intelligence model.

[0369] Embodiments of the second aspect

[0370] The embodiment of the second aspect provides a method for receiving channel state information, which is applied to a network device, such as the network device 201 in Figure 2. For the parts of the embodiment of the second aspect that are the same as those of the embodiment of the first aspect, reference can be made to the description of the embodiment of the first aspect, and no repetition is given here.

[0371] FIG6 is a schematic diagram of a method for receiving channel state information according to an embodiment of the second aspect. The method includes:

[0372] 601. Receive one or more first channel state information (CSI) reports generated by a terminal device, wherein the first channel state information report includes information about a precoding matrix, wherein the information about the precoding matrix includes information about a combining coefficient, and at least a portion of the information about the combining coefficient is generated by an artificial intelligence (AI / ML) model, and the first channel state information (CSI) report has a first part and a second part, and the second part of the one or more first channel state information (CSI) reports has a priority.

[0373] In some embodiments, the information of the precoding matrix further includes information of a spatial domain basis, and / or information of a frequency domain basis, and / or information of a time domain basis.

[0374] In some embodiments, the first part includes at least a portion of information of a rank indication (RI), and / or a channel quality indication (CQI), and / or first information, wherein the first information and / or the rank indication (RI) are used to indicate the number of information bits of at least a portion of the second part.

[0375] In some embodiments, the first information includes:

[0376] Artificial Intelligence (AI / ML) model information; and / or

[0377] The sum of the number of information bits of the information of the combining coefficients of all spatial layers or the maximum allowable sum, or the sum of the number of information bits of the precoding matrix information of all spatial layers or the maximum allowable sum.

[0378] In some embodiments, the rank indication (RI), and / or at least a portion of the channel quality indication (CQI), and / or the first information are separately encoded.

[0379] In some embodiments, the second part includes information of the precoding matrix.

[0380] In some embodiments, the first portion and the second portion are independently encoded.

[0381] In some embodiments, the network device receives the second part after receiving the entire first part of the first channel state information (CSI) report.

[0382] In some embodiments, there is a first priority order between the information in the second part of the first channel state information report.

[0383] In some embodiments, the information in the second portion is divided into more than one set, and there is a priority order between the sets.

[0384] In some embodiments, there is a priority order between each information within each set.

[0385] In some embodiments, the one or more sets include at least one of a first set, a second set, and a third set, wherein the priority ranking of the first set is higher than the priority ranking of the second set, and the priority ranking of the second set is higher than the priority ranking of the third set.

[0386] In some embodiments, the first set includes at least one of the following information: information of a spatial domain basis, information of a frequency domain basis, information of a time domain basis, and information of a combining coefficient of a first predetermined spatial domain layer;

[0387] The second set includes: information on the merging coefficients of the first predetermined spatial layer and / or information on the merging coefficients of the second predetermined spatial layer;

[0388] The third set includes: information on the combining coefficients of the third predetermined spatial layer.

[0389] In some embodiments, within the first set, the information of the spatial basis, the information of the frequency domain basis, and the information of the combining coefficients of the first predetermined spatial layer each have a priority order; and / or

[0390] In the second set, information on combining coefficients of at least two spatial layers with different numbers each has a priority order; and / or

[0391] In the third set, information on combining coefficients of at least two spatial layers with different numbers each has a priority order.

[0392] In some embodiments, within the first set, the information of the spatial basis, the information of the frequency domain basis, the information of the time domain basis, and the information of the combining coefficients of the first predetermined spatial layer each have a priority order; and / or

[0393] In the second set, information on combining coefficients of at least two spatial layers with different numbers each has a priority order; and / or

[0394] In the third set, information on combining coefficients of at least two spatial layers with different numbers each has a priority order.

[0395] In some embodiments, at least a portion of the merging coefficients of at least one spatial layer is divided into more than one group, and the merging coefficients of each group are input to one or more artificial intelligence (AI / ML) models, and the output of one or more artificial intelligence (AI / ML) models is information of the merging coefficients of each group, wherein the grouping information of the merging coefficients of at least two spatial layers is the same or different.

[0396] In some embodiments, the first set includes at least one of the following information: information of a spatial domain basis, information of a frequency domain basis, information of a time domain basis, and information of a first group of combining coefficients of a first predetermined spatial domain layer;

[0397] The second set includes: information of a first group of merging coefficients of the first predetermined spatial layer and / or information of a first group of merging coefficients of a second predetermined spatial layer;

[0398] The third set includes: information of the second group of merging coefficients of all spatial layers.

[0399] In some embodiments, within the first set, the information of the spatial basis, the information of the frequency domain basis, and the information of the first group of combining coefficients of the first predetermined spatial layer each have a priority order; and / or

[0400] In the second set, the information of the first group of combining coefficients of at least two spatial layers with different numbers each has a priority order; and / or

[0401] In the third set, the information of the second group of combining coefficients of at least two spatial layers with different numbers each has a priority order.

[0402] In some embodiments, within the first set, the information of the spatial basis, the information of the frequency domain basis, the information of the time domain basis, and the information of the first group of combining coefficients of the first predetermined spatial layer each have a priority order; and / or

[0403] In the second set, the information of the first group of combining coefficients of at least two spatial layers with different numbers each has a priority order; and / or

[0404] In the third set, the information of the second group of combining coefficients of at least two spatial layers with different numbers each has a priority order.

[0405] In some embodiments, more than one of the first channel state information reports have a second priority order,

[0406] The second part of one or more of the first channel state information reports has a third priority order.

[0407] In some embodiments, in the third priority order, the first priority order is higher than the second priority order; or

[0408] In the third priority order, the second priority order is higher than the first priority order; or

[0409] In the third priority order, the second priority order is independent of the first priority order; or

[0410] The third priority order is the same as the second priority order.

[0411] In some embodiments, as shown in FIG6 , the method further includes:

[0412] 602. The network device receives a channel state information sending failure report sent by the terminal device, and / or sends a configuration to the terminal device, where the configuration is at least used to instruct the terminal device to generate information required for at least a portion of the channel state information; and

[0413] 603. Receive at least a portion of new channel state information generated by the terminal device based on the configuration.

[0414] In some embodiments, the number of channel information included in the first channel state information report is greater than 1,

[0415] The second part also includes at least part of the information of the channel quality indicator,

[0416] Information in the second part within the first channel state information report has a first priority.

[0417] In some embodiments, the channel information is information of a spatial channel at a time instant.

[0418] In some embodiments, the information in the second portion is divided into more than one set, and there is a priority order between the sets.

[0419] In some embodiments, there is a priority order between the information within each of the sets.

[0420] In some embodiments, the one or more sets include at least one of a first set, a second set, and a third set, wherein the priority ranking of the first set is higher than the priority ranking of the second set, and the priority ranking of the second set is higher than the priority ranking of the third set.

[0421] In some embodiments, the first set includes at least one of the following information: information of a spatial domain basis, information of a frequency domain basis, information of a time domain basis, a wideband channel quality indicator in at least part of the channel quality indicator information, and information of a combining coefficient of a first predetermined spatial layer;

[0422] The second set includes at least one of the following information: information on the combining coefficient of the first predetermined spatial layer, information on the combining coefficient of the second predetermined spatial layer, and a first predetermined subband second channel quality indicator in at least part of the channel quality indicator information;

[0423] The third set includes at least one of the following information: information on combining coefficients of a third predetermined spatial layer, and a second predetermined subband second channel quality indicator in at least part of the channel quality indicator information.

[0424] In some embodiments, within the first set, the spatial basis information, the frequency domain basis information, the time domain basis information, the wideband channel quality indicator, and the combining coefficient information of the first predetermined spatial layer each have a priority order; and / or

[0425] In the second set, the information of combining coefficients of at least two spatial layers with different numbers and the second channel quality indicator of the first predetermined subband each have a priority order; and / or

[0426] In the third set, the information of combining coefficients of at least two spatial layers with different numbers and the second channel quality indicator of the second predetermined subband each have a priority order.

[0427] In some embodiments, the first set includes at least one of the following information: information of a spatial domain basis, information of a frequency domain basis, information of a time domain basis, a wideband channel quality indicator in at least part of the channel quality indicator information, and information of a first set of combining coefficients of a first predetermined spatial layer;

[0428] The second set includes at least one of the following information: information of a first group of combining coefficients of the first predetermined spatial layer, information of a first group of combining coefficients of the second predetermined spatial layer, and a first predetermined subband second channel quality indicator in at least part of the channel quality indicator information;

[0429] The third set includes at least one of the following information: information of a second group of combining coefficients of all spatial layers, and a second predetermined subband second channel quality indicator in at least part of the channel quality indicator information.

[0430] In some embodiments, within the first set, the spatial basis information, the frequency domain basis information, the time domain basis information, the wideband channel quality indicator, and the first group of combining coefficients of the first predetermined spatial layer each have a priority order; and / or

[0431] In the second set, the information of the first group of combining coefficients of at least two spatial layers with different numbers and the second channel quality indicator of the first predetermined subband each have a priority order; and / or

[0432] In the third set, the information of the second group of combining coefficients of at least two spatial layers with different numbers and the second predetermined sub-band second channel quality indicator each have a priority order.

[0433] In some embodiments, the first channel state information report further includes information for reporting order of information representing precoding matrices of N spatial layers, where N is a natural number greater than or equal to 2.

[0434] In some embodiments, the order of reporting the information of the precoding matrices of the N spatial layers is:

[0435] an arrangement order of each of the artificial intelligence (AI / ML) models for generating information of precoding matrices and / or information of combining coefficients of the N spatial layers; or

[0436] The arrangement order of the bit widths of the precoding matrix information and / or the combining coefficient information of the N spatial domain layers.

[0437] In some embodiments, the information on the reporting order of the information for representing the precoding matrices of N spatial layers is in the first part or the second part of the first channel state information report.

[0438] In some embodiments, the reporting order of the precoding matrix information of the N spatial layers is specified by the standard, or predefined, or agreed upon by the network device and the terminal device, or configured by the network device, or determined by the terminal device.

[0439] In some embodiments, the order of the indexes of the N spatial layers is the same as the reporting order of the information of the precoding matrices of the N spatial layers, where N is a natural number greater than or equal to 2; or

[0440] The order of the indexes of the N spatial domain layers is the order in which the bit width of the precoding matrix information or the bit width of the combining coefficient information of each spatial domain layer of the N spatial domain layers are arranged from large to small or from small to large, wherein, if the bit width of the precoding matrix information or the bit width of the combining coefficient information of at least two spatial domain layers is the same, the order of the indexes of the at least two spatial domain layers may be determined by the terminal device; or

[0441] The order of the indexes of the N spatial domain layers is the order in which the singular values ​​corresponding to the right singular vectors of the precoding matrix corresponding to each of the N spatial domain layers are arranged from large to small or from small to large, wherein, if at least two spatial domain layers have the same eigenvalues ​​(singular values), the order of the indexes of the at least two spatial domain layers can be determined by the terminal device.

[0442] Embodiments of the third aspect

[0443] At least for the same problem as the embodiment of the first aspect, the embodiment of the third aspect of the present application provides a device for configuring channel state information, which is applied to a network device and corresponds to the embodiment of the first aspect.

[0444] FIG7 is a schematic diagram of an apparatus for configuring channel state information according to an embodiment of the third aspect. As shown in FIG7 , the apparatus 700 for configuring channel state information includes: a first processing unit 701 .

[0445] The first processing unit 701 causes the terminal device to perform the following operations:

[0446] The terminal device generates one or more first channel state information (CSI) reports, the first channel state information reports including precoding matrix information, wherein the precoding matrix information includes combining coefficient information, at least a portion of the combining coefficient information is generated by an artificial intelligence (AI / ML) model,

[0447] The first channel state information (CSI) report has a first part and a second part, and the second parts of more than one first channel state information (CSI) report have a priority order.

[0448] In some embodiments, the information of the precoding matrix further includes information of a spatial domain basis, and / or information of a frequency domain basis, and / or information of a time domain basis.

[0449] In some embodiments, the first part includes at least a portion of rank indication (RI), and / or channel quality indication (CQI) information, and / or first information,

[0450] The first information and / or the rank indication (RI) is used to indicate the number of information bits of at least a part of the second part.

[0451] In some embodiments, the first information includes:

[0452] Artificial Intelligence (AI / ML) model information; and / or

[0453] The sum of the number of information bits of the information of the combining coefficients of all spatial layers or the maximum allowable sum, or the sum of the number of information bits of the precoding matrix information of all spatial layers or the maximum allowable sum.

[0454] In some embodiments, the rank indication (RI), and / or at least a portion of the channel quality indication (CQI), and / or the first information are separately encoded.

[0455] In some embodiments, the second part includes information of the precoding matrix.

[0456] In some embodiments, the first portion and the second portion are independently encoded.

[0457] In some embodiments, the operations further include:

[0458] After the terminal device sends the first part of the first channel state information (CSI) report in full, it sends the second part.

[0459] In some embodiments, there is a first priority order between the information in the second part of the first channel state information report.

[0460] In some embodiments, the information in the second portion is divided into more than one set, and there is a priority order between the sets.

[0461] In some embodiments, there is a priority order between each information within each set.

[0462] In some embodiments, the one or more sets include at least one of a first set, a second set, and a third set, wherein the priority ranking of the first set is higher than the priority ranking of the second set, and the priority ranking of the second set is higher than the priority ranking of the third set.

[0463] In some embodiments, the first set includes at least one of the following information: information of a spatial domain basis, information of a frequency domain basis, information of a time domain basis, and information of a combining coefficient of a first predetermined spatial domain layer;

[0464] The second set includes: information on the merging coefficients of the first predetermined spatial layer and / or information on the merging coefficients of the second predetermined spatial layer;

[0465] The third set includes: information on the combining coefficients of the third predetermined spatial layer.

[0466] In some embodiments, within the first set, the information of the spatial basis, the information of the frequency domain basis, and the information of the combining coefficients of the first predetermined spatial layer each have a priority order; and / or

[0467] In the second set, information on combining coefficients of at least two spatial layers with different numbers each has a priority order; and / or

[0468] In the third set, information on combining coefficients of at least two spatial layers with different numbers each has a priority order.

[0469] In some embodiments, within the first set, the information of the spatial basis, the information of the frequency domain basis, the information of the time domain basis, and the information of the combining coefficients of the first predetermined spatial layer each have a priority order; and / or

[0470] In the second set, information on combining coefficients of at least two spatial layers with different numbers each has a priority order; and / or

[0471] In the third set, information on combining coefficients of at least two spatial layers with different numbers each has a priority order.

[0472] In some embodiments, at least a portion of the merging coefficients of at least one spatial layer is divided into more than one group, and the merging coefficients of each group are input to one or more artificial intelligence (AI / ML) models, and the output of one or more artificial intelligence (AI / ML) models is information of the merging coefficients of each group, wherein the grouping information of the merging coefficients of at least two spatial layers is the same or different.

[0473] In some embodiments, the first set includes at least one of the following information: information of a spatial domain basis, information of a frequency domain basis, information of a time domain basis, and information of a first group of combining coefficients of a first predetermined spatial domain layer;

[0474] The second set includes: information of a first group of merging coefficients of the first predetermined spatial layer and / or information of a first group of merging coefficients of a second predetermined spatial layer;

[0475] The third set includes: information of the second group of merging coefficients of all spatial layers.

[0476] In some embodiments, within the first set, the information of the spatial basis, the information of the frequency domain basis, and the information of the first group of combining coefficients of the first predetermined spatial layer each have a priority order; and / or

[0477] In the second set, the information of the first group of combining coefficients of at least two spatial layers with different numbers each has a priority order; and / or

[0478] In the third set, the information of the second group of combining coefficients of at least two spatial layers with different numbers each has a priority order.

[0479] In some embodiments, within the first set, the information of the spatial basis, the information of the frequency domain basis, the information of the time domain basis, and the information of the first group of combining coefficients of the first predetermined spatial layer each have a priority order; and / or

[0480] In the second set, the information of the first group of combining coefficients of at least two spatial layers with different numbers each has a priority order; and / or

[0481] In the third set, the information of the second group of combining coefficients of at least two spatial layers with different numbers each has a priority order.

[0482] In some embodiments, more than one of the first channel state information reports have a second priority order,

[0483] The second part of one or more of the first channel state information reports has a third priority order.

[0484] In some embodiments, in the third priority order, the first priority order is higher than the second priority order; or

[0485] In the third priority order, the second priority order is higher than the first priority order; or

[0486] In the third priority order, the second priority order is independent of the first priority order; or

[0487] The third priority order is the same as the second priority order.

[0488] In some embodiments, the operations further include:

[0489] The terminal device discards at least part of the second part of at least one first channel state information report according to the third priority order; or

[0490] The terminal device regenerates at least part of the channel state information from at least part of the second part of at least one first channel state information report according to the third priority and sends the regenerates at least part of the channel state information.

[0491] In some embodiments, the operations further include:

[0492] The terminal device sends a channel state information sending failure report to the network device, and / or receives a configuration sent by the network device, where the configuration is at least used to indicate information required for the terminal device to generate at least a portion of the channel state information; and

[0493] At least a portion of new channel state information is generated based on the configuration, and at least a portion of the new channel state information is transmitted.

[0494] In some embodiments, the number of channel information included in the first channel state information report is greater than 1,

[0495] The second part also includes at least part of the information of the channel quality indicator,

[0496] Information in the second part within the first channel state information report has a first priority.

[0497] In some embodiments, the channel information is information of a spatial channel at a time instant.

[0498] In some embodiments, the information in the second portion is divided into more than one set, and there is a priority order between the sets.

[0499] In some embodiments, there is a priority order between the information within each of the sets.

[0500] In some embodiments, the one or more sets include at least one of a first set, a second set, and a third set,

[0501] The priority of the first set is higher than the priority of the second set, and the priority of the second set is higher than the priority of the third set.

[0502] In some embodiments, the first set includes at least one of the following information: information of a spatial domain basis, information of a frequency domain basis, information of a time domain basis, a wideband channel quality indicator in at least part of the channel quality indicator information, and information of a combining coefficient of a first predetermined spatial layer;

[0503] The second set includes at least one of the following information: information on the combining coefficient of the first predetermined spatial layer, information on the combining coefficient of the second predetermined spatial layer, and a first predetermined subband second channel quality indicator in at least part of the channel quality indicator information;

[0504] The third set includes at least one of the following information: information on combining coefficients of a third predetermined spatial layer, and a second predetermined subband second channel quality indicator in at least part of the channel quality indicator information.

[0505] In some embodiments, within the first set, the spatial basis information, the frequency domain basis information, the time domain basis information, the wideband channel quality indicator, and the combining coefficient information of the first predetermined spatial layer each have a priority order; and / or

[0506] In the second set, the information of combining coefficients of at least two spatial layers with different numbers and the second channel quality indicator of the first predetermined subband each have a priority order; and / or

[0507] In the third set, the information of combining coefficients of at least two spatial layers with different numbers and the second channel quality indicator of the second predetermined subband each have a priority order.

[0508] In some embodiments, the first set includes at least one of the following information: information of a spatial domain basis, information of a frequency domain basis, information of a time domain basis, a wideband channel quality indicator in at least part of the channel quality indicator information, and information of a first set of combining coefficients of a first predetermined spatial layer;

[0509] The second set includes at least one of the following information: information of a first group of combining coefficients of the first predetermined spatial layer, information of a first group of combining coefficients of the second predetermined spatial layer, and a first predetermined subband second channel quality indicator in at least part of the channel quality indicator information;

[0510] The third set includes at least one of the following information: information of a second group of combining coefficients of all spatial layers, and a second predetermined subband second channel quality indicator in at least part of the channel quality indicator information.

[0511] In some embodiments, within the first set, the spatial basis information, the frequency domain basis information, the time domain basis information, the wideband channel quality indicator, and the first group of combining coefficients of the first predetermined spatial layer each have a priority order; and / or

[0512] In the second set, the information of the first group of combining coefficients of at least two spatial layers with different numbers and the second channel quality indicator of the first predetermined subband each have a priority order; and / or

[0513] In the third set, the information of the second group of combining coefficients of at least two spatial layers with different numbers and the second predetermined sub-band second channel quality indicator each have a priority order.

[0514] In some embodiments, the first channel state information report further includes information on a reporting order for information representing precoding matrices of N spatial layers, where N is a natural number greater than or equal to 2.

[0515] In some embodiments, the order of reporting the information of the precoding matrices of the N spatial layers is:

[0516] an arrangement order of each of the artificial intelligence (AI / ML) models for generating information of precoding matrices and / or information of combining coefficients of the N spatial layers; or

[0517] The arrangement order of the bit widths of the precoding matrix information and / or the combining coefficient information of the N spatial domain layers.

[0518] In some embodiments, the information on the reporting order of the information for representing the precoding matrices of N spatial layers is in the first part or the second part of the first channel state information report.

[0519] In some embodiments, the reporting order of the precoding matrix information of the N spatial layers is specified by the standard, or predefined, or agreed upon by the network device and the terminal device, or configured by the network device, or determined by the terminal device.

[0520] In some embodiments, the order of the indexes of the N spatial layers is the same as the reporting order of the precoding matrix information of the N spatial layers, where N is a natural number greater than or equal to 2; or

[0521] The order of the indexes of the N spatial domain layers is the order in which the bit width of the precoding matrix information or the bit width of the combining coefficient information of each spatial domain layer of the N spatial domain layers are arranged from large to small or from small to large, wherein, if the bit width of the precoding matrix information or the bit width of the combining coefficient information of at least two spatial domain layers is the same, the order of the indexes of the at least two spatial domain layers may be determined by the terminal device; or

[0522] The order of the indexes of the N spatial domain layers is the order in which the singular values ​​corresponding to the right singular vectors of the precoding matrix corresponding to each of the N spatial domain layers are arranged from large to small or from small to large, wherein, if at least two spatial domain layers have the same eigenvalues ​​(singular values), the order of the indexes of the at least two spatial domain layers can be determined by the terminal device.

[0523] Embodiments of the fourth aspect

[0524] An embodiment of the fourth aspect of the present application provides an apparatus for receiving channel state information, which is applied to a network device and corresponds to the method of the embodiment of the second aspect.

[0525] FIG8 is a schematic diagram of an apparatus for configuring channel state information according to an embodiment of the fourth aspect. As shown in FIG8 , the apparatus 800 includes: a second processing unit 801 .

[0526] In at least one embodiment, the second processing unit 801 controls the network device to perform the following operations:

[0527] receiving one or more first channel state information (CSI) reports generated by a terminal device,

[0528] The first channel state information report includes information about a precoding matrix, wherein the information about the precoding matrix includes information about combining coefficients, and at least a portion of the information about the combining coefficients is generated by an artificial intelligence (AI / ML) model.

[0529] The first channel state information (CSI) report has a first part and a second part, and the second parts of more than one first channel state information (CSI) report have a priority order.

[0530] In some embodiments, the information of the precoding matrix further includes information of a spatial domain basis, and / or information of a frequency domain basis, and / or information of a time domain basis.

[0531] In some embodiments, the first part includes at least a portion of information of a rank indication (RI), and / or a channel quality indication (CQI), and / or first information, wherein the first information and / or the rank indication (RI) are used to indicate the number of information bits of at least a portion of the second part.

[0532] In some embodiments, the first information includes:

[0533] Artificial Intelligence (AI / ML) model information; and / or

[0534] The sum of the number of information bits of the information of the combining coefficients of all spatial layers or the maximum allowable sum, or the sum of the number of information bits of the precoding matrix information of all spatial layers or the maximum allowable sum.

[0535] In some embodiments, the rank indication (RI), and / or at least a portion of the channel quality indication (CQI), and / or the first information are separately encoded.

[0536] In some embodiments, the second part includes information of the precoding matrix.

[0537] In some embodiments, the first portion and the second portion are independently encoded.

[0538] In some embodiments, the network device receives the second part after receiving the entire first part of the first channel state information (CSI) report.

[0539] In some embodiments, there is a first priority order between the information in the second part of the first channel state information report.

[0540] In some embodiments, the information in the second portion is divided into more than one set, and there is a priority order between the sets.

[0541] In some embodiments, there is a priority order between each information within each set.

[0542] In some embodiments, the one or more sets include at least one of a first set, a second set, and a third set,

[0543] The priority of the first set is higher than the priority of the second set, and the priority of the second set is higher than the priority of the third set.

[0544] In some embodiments, the first set includes at least one of the following information: information of a spatial domain basis, information of a frequency domain basis, information of a time domain basis, and information of a combining coefficient of a first predetermined spatial domain layer;

[0545] The second set includes: information on the merging coefficients of the first predetermined spatial layer and / or information on the merging coefficients of the second predetermined spatial layer;

[0546] The third set includes: information on the combining coefficients of the third predetermined spatial layer.

[0547] In some embodiments, within the first set, the information of the spatial basis, the information of the frequency domain basis, and the information of the combining coefficients of the first predetermined spatial layer each have a priority order; and / or

[0548] In the second set, information on combining coefficients of at least two spatial layers with different numbers each has a priority order; and / or

[0549] In the third set, information on combining coefficients of at least two spatial layers with different numbers each has a priority order.

[0550] In some embodiments, within the first set, the information of the spatial basis, the information of the frequency domain basis, the information of the time domain basis, and the information of the combining coefficients of the first predetermined spatial layer each have a priority order; and / or

[0551] In the second set, information on combining coefficients of at least two spatial layers with different numbers each has a priority order; and / or

[0552] In the third set, information on combining coefficients of at least two spatial layers with different numbers each has a priority order.

[0553] In some embodiments, at least a portion of the merging coefficients of at least one spatial layer is divided into more than one group, and the merging coefficients of each group are input to one or more artificial intelligence (AI / ML) models, and the output of one or more artificial intelligence (AI / ML) models is information of the merging coefficients of each group, wherein the grouping information of the merging coefficients of at least two spatial layers is the same or different.

[0554] In some embodiments, the first set includes at least one of the following information: information of a spatial domain basis, information of a frequency domain basis, information of a time domain basis, and information of a first group of combining coefficients of a first predetermined spatial domain layer;

[0555] The second set includes: information of a first group of merging coefficients of the first predetermined spatial layer and / or information of a first group of merging coefficients of a second predetermined spatial layer;

[0556] The third set includes: information of the second group of merging coefficients of all spatial layers.

[0557] In some embodiments, within the first set, the information of the spatial basis, the information of the frequency domain basis, and the information of the first group of combining coefficients of the first predetermined spatial layer each have a priority order; and / or

[0558] In the second set, the information of the first group of combining coefficients of at least two spatial layers with different numbers each has a priority order; and / or

[0559] In the third set, the information of the second group of combining coefficients of at least two spatial layers with different numbers each has a priority order.

[0560] In some embodiments, within the first set, the information of the spatial basis, the information of the frequency domain basis, the information of the time domain basis, and the information of the first group of combining coefficients of the first predetermined spatial layer each have a priority order; and / or

[0561] In the second set, the information of the first group of combining coefficients of at least two spatial layers with different numbers each has a priority order; and / or

[0562] In the third set, the information of the second group of combining coefficients of at least two spatial layers with different numbers each has a priority order.

[0563] In some embodiments, more than one of the first channel state information reports have a second priority order,

[0564] The second part of one or more of the first channel state information reports has a third priority order.

[0565] In some embodiments, in the third priority order, the first priority order is higher than the second priority order; or

[0566] In the third priority order, the second priority order is higher than the first priority order; or

[0567] In the third priority order, the second priority order is independent of the first priority order; or

[0568] The third priority order is the same as the second priority order.

[0569] In some embodiments, the operations further include:

[0570] The network device receives a channel state information sending failure report sent by the terminal device, and / or

[0571] Sending a configuration to the terminal device, the configuration being used to at least indicate information required for the terminal device to generate at least a portion of channel state information; and

[0572] Receive at least a portion of new channel state information generated by the terminal device based on the configuration.

[0573] In some embodiments, the number of channel information included in the first channel state information report is greater than 1,

[0574] The second part also includes at least part of the information of the channel quality indicator,

[0575] Information in the second part within the first channel state information report has a first priority.

[0576] In some embodiments, the channel information is information of a spatial channel at a time instant.

[0577] In some embodiments, the information in the second portion is divided into more than one set, and there is a priority order between the sets.

[0578] In some embodiments, there is a priority order between the information within each of the sets.

[0579] In some embodiments, the one or more sets include at least one of a first set, a second set, and a third set, wherein the priority ranking of the first set is higher than the priority ranking of the second set, and the priority ranking of the second set is higher than the priority ranking of the third set.

[0580] In some embodiments, the first set includes at least one of the following information: information of a spatial domain basis, information of a frequency domain basis, information of a time domain basis, a wideband channel quality indicator in at least part of the channel quality indicator information, and information of a combining coefficient of a first predetermined spatial layer;

[0581] The second set includes at least one of the following information: information on the combining coefficient of the first predetermined spatial layer, information on the combining coefficient of the second predetermined spatial layer, and a first predetermined subband second channel quality indicator in at least part of the channel quality indicator information;

[0582] The third set includes at least one of the following information: information on combining coefficients of a third predetermined spatial layer, and a second predetermined subband second channel quality indicator in at least part of the channel quality indicator information.

[0583] In some embodiments, within the first set, the spatial basis information, the frequency domain basis information, the time domain basis information, the wideband channel quality indicator, and the combining coefficient information of the first predetermined spatial layer each have a priority order; and / or

[0584] In the second set, the information of combining coefficients of at least two spatial layers with different numbers and the second channel quality indicator of the first predetermined subband each have a priority order; and / or

[0585] In the third set, the information of combining coefficients of at least two spatial layers with different numbers and the second channel quality indicator of the second predetermined subband each have a priority order.

[0586] In some embodiments, the first set includes at least one of the following information: information of a spatial domain basis, information of a frequency domain basis, information of a time domain basis, a wideband channel quality indicator in at least part of the channel quality indicator information, and information of a first set of combining coefficients of a first predetermined spatial layer;

[0587] The second set includes at least one of the following information: information of a first group of combining coefficients of the first predetermined spatial layer, information of a first group of combining coefficients of the second predetermined spatial layer, and a first predetermined subband second channel quality indicator in at least part of the channel quality indicator information;

[0588] The third set includes at least one of the following information: information of a second group of combining coefficients of all spatial layers, and a second predetermined subband second channel quality indicator in at least part of the channel quality indicator information.

[0589] In some embodiments, within the first set, the spatial basis information, the frequency domain basis information, the time domain basis information, the wideband channel quality indicator, and the first group of combining coefficients of the first predetermined spatial layer each have a priority order; and / or

[0590] In the second set, the information of the first group of combining coefficients of at least two spatial layers with different numbers and the second channel quality indicator of the first predetermined subband each have a priority order; and / or

[0591] In the third set, the information of the second group of combining coefficients of at least two spatial layers with different numbers and the second predetermined sub-band second channel quality indicator each have a priority order.

[0592] In some embodiments, the first channel state information report further includes information on a reporting order for information representing precoding matrices of N spatial layers, where N is a natural number greater than or equal to 2.

[0593] In some embodiments, the order of reporting the information of the precoding matrices of the N spatial layers is:

[0594] an arrangement order of each of the artificial intelligence (AI / ML) models for generating information of precoding matrices and / or information of combining coefficients of the N spatial layers; or

[0595] The arrangement order of the bit widths of the precoding matrix information and / or the combining coefficient information of the N spatial domain layers.

[0596] In some embodiments, the information on the reporting order of the information for representing the precoding matrices of N spatial layers is in the first part or the second part of the first channel state information report.

[0597] In some embodiments, the reporting order of the precoding matrix information of the N spatial layers is specified by the standard, or predefined, or agreed upon by the network device and the terminal device, or configured by the network device, or determined by the terminal device.

[0598] In some embodiments, the order of the indexes of the N spatial layers is the same as the reporting order of the precoding matrix information of the N spatial layers, where N is a natural number greater than or equal to 2; or

[0599] The order of the indexes of the N spatial domain layers is the order in which the bit width of the precoding matrix information or the bit width of the combining coefficient information of each spatial domain layer of the N spatial domain layers are arranged from large to small or from small to large, wherein, if the bit width of the precoding matrix information or the bit width of the combining coefficient information of at least two spatial domain layers is the same, the order of the indexes of the at least two spatial domain layers may be determined by the terminal device; or

[0600] The order of the indexes of the N spatial domain layers is the order in which the singular values ​​corresponding to the right singular vectors of the precoding matrix corresponding to each of the N spatial domain layers are arranged from large to small or from small to large, wherein, if at least two spatial domain layers have the same eigenvalues ​​(singular values), the order of the indexes of the at least two spatial domain layers can be determined by the terminal device.

[0601] Embodiments of the fifth aspect

[0602] An embodiment of the fifth aspect of the present application provides a communication system, which may include a network device and a terminal device.

[0603] FIG9 is a schematic diagram of a terminal device according to an embodiment of the fifth aspect. As shown in FIG9 , the terminal device 900 (e.g., corresponding to the terminal device 202 in FIG2 ) may include a processor 910 and a memory 920; the memory 920 stores data and programs and is coupled to the processor 910. It should be noted that this diagram is exemplary; other types of structures may be used to supplement or replace this structure to implement telecommunication functions or other functions.

[0604] For example, the processor 910 may be configured to execute a program to implement the method according to the first embodiment.

[0605] As shown in Figure 9 , the terminal device 900 may further include: a communication module 930, an input unit 940, a display 950, and a power supply 960. The functions of these components are similar to those in the prior art and are not described in detail here. It is worth noting that the terminal device 900 does not necessarily include all of the components shown in Figure 9 , and these components are not essential. Furthermore, the terminal device 900 may also include components not shown in Figure 9 , for which reference may be made to the prior art.

[0606] FIG10 is a schematic diagram of a network device according to an embodiment of the fifth aspect. As shown in FIG10 , network device 1000 (e.g., corresponding to network device 201 in FIG2 ) may include a processor 1010 (e.g., a central processing unit (CPU)) and a memory 1020; the memory 1020 is coupled to the processor 1010. The memory 1020 may store various data and may also store an information processing program 1030, which is executed under the control of the processor 1010.

[0607] For example, the processor 1010 can be configured to execute a program to implement the method as described in the embodiment of the second aspect.

[0608] In addition, as shown in FIG10 , the network device 1000 may further include: a transceiver 1040 and an antenna 1050; wherein, the functions of the above components are similar to those in the prior art and are not described in detail here. It is worth noting that the network device 1000 does not necessarily include all the components shown in FIG10 ; in addition, the network device 1000 may also include components not shown in FIG10 , and reference may be made to the prior art for details.

[0609] An embodiment of the present application also provides a computer program, wherein when the program is executed in a terminal device, the program causes the terminal device to execute the method described in the embodiment of the first aspect.

[0610] An embodiment of the present application also provides a storage medium storing a computer program, wherein the computer program enables a terminal device to execute the method described in the embodiment of the first aspect.

[0611] An embodiment of the present application also provides a computer program, wherein when the program is executed in a network device, the program causes the network device to execute the method described in the embodiment of the second aspect.

[0612] An embodiment of the present application also provides a storage medium storing a computer program, wherein the computer program enables a network device to execute the method described in the embodiment of the second aspect.

[0613] The above devices and methods of the present application can be implemented by hardware or by a combination of hardware and software. The present application relates to such a computer-readable program that, when executed by a logic component, enables the logic component to implement the devices or components described above, or enables the logic component to implement the various methods or steps described above. The present application also relates to a storage medium for storing the above program, such as a hard disk, a magnetic disk, an optical disk, a DVD, a flash memory, etc.

[0614] The method / device described in conjunction with the embodiments of the present application can be directly embodied as hardware, a software module executed by a processor, or a combination of the two. For example, one or more of the functional block diagrams shown in the figure and / or one or more combinations of functional block diagrams can correspond to various software modules of the computer program flow or to various hardware modules. These software modules can respectively correspond to the various steps shown in the figure. These hardware modules can be implemented by solidifying these software modules, for example, using a field programmable gate array (FPGA).

[0615] The software module may be located in RAM memory, flash memory, ROM memory, EPROM memory, EEPROM memory, registers, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art. A storage medium may be coupled to a processor so that the processor can read information from the storage medium and write information to the storage medium; or the storage medium may be an integral part of the processor. The processor and the storage medium may be located in an ASIC. The software module may be stored in the memory of the mobile terminal or in a memory card that can be inserted into the mobile terminal. For example, if the device (such as a mobile terminal) uses a large-capacity MEGA-SIM card or a large-capacity flash memory device, the software module may be stored in the MEGA-SIM card or the large-capacity flash memory device.

[0616] One or more of the functional blocks and / or one or more combinations of functional blocks described in the accompanying drawings may be implemented as a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic device, a discrete gate or transistor logic device, a discrete hardware component, or any appropriate combination thereof for performing the functions described in this application. One or more of the functional blocks and / or one or more combinations of functional blocks described in the accompanying drawings may also be implemented as a combination of computing devices, such as a combination of a DSP and a microprocessor, multiple microprocessors, one or more microprocessors in communication with a DSP, or any other such configuration.

[0617] The present application has been described above in conjunction with specific embodiments. However, those skilled in the art should understand that these descriptions are merely illustrative and are not intended to limit the scope of protection of the present application. Those skilled in the art may make various modifications and variations to the present application based on the spirit and principles of the present application, and such modifications and variations are also within the scope of the present application.

[0618] Regarding the implementation methods including the above embodiments, the following additional notes are also disclosed:

[0619] 1. A method for receiving channel state information, applied to a network device, the method comprising:

[0620] receiving one or more first channel state information (CSI) reports generated by a terminal device,

[0621] The first channel state information report includes information about a precoding matrix, wherein the information about the precoding matrix includes information about combining coefficients, and at least a portion of the information about the combining coefficients is generated by an artificial intelligence (AI / ML) model.

[0622] The first channel state information (CSI) report has a first part and a second part, and the second parts of more than one first channel state information (CSI) report have a priority order.

[0623] 2. The method as described in Note 1, wherein:

[0624] The first part and the second part are independently encoded.

[0625] 3. The method as described in Note 1, wherein:

[0626] The network device receives the second part after receiving the first part of the first channel state information (CSI) report in its entirety.

[0627] 4. The method as described in Note 1, wherein:

[0628] There is a first priority order between the information in the second part of the first channel state information report,

[0629] The information in the second part is divided into more than one set, and each set has a priority order.

[0630] There is a priority order between each information within each set.

[0631] The one or more sets include at least one of a first set, a second set, and a third set,

[0632] The priority of the first set is higher than the priority of the second set, and the priority of the second set is higher than the priority of the third set.

[0633] At least a portion of the merging coefficients of at least one spatial layer is divided into more than one group, each group of merging coefficients is input to one or more artificial intelligence (AI / ML) models, and the output of one or more artificial intelligence (AI / ML) models is information about the merging coefficients of each group.

[0634] The grouping information of the combining coefficients of at least two spatial layers is the same or different.

[0635] The first set includes at least one of the following information: information of a spatial domain basis, information of a frequency domain basis, information of a time domain basis, and information of a first group of combining coefficients of a first predetermined spatial domain layer;

[0636] The second set includes: information of a first group of merging coefficients of the first predetermined spatial layer and / or information of a first group of merging coefficients of a second predetermined spatial layer;

[0637] The third set includes: information of the second group of merging coefficients of all spatial layers.

[0638] Within the first set, the spatial basis information, the frequency domain basis information, the time domain basis information, and the first group of combining coefficients of the first predetermined spatial layer each have a priority order; and / or

[0639] In the second set, the information of the first group of combining coefficients of at least two spatial layers with different numbers each has a priority order; and / or

[0640] In the third set, the information of the second group of combining coefficients of at least two spatial layers with different numbers each has a priority order.

[0641] 5. The method as described in Note 1, wherein:

[0642] There is a first priority order between the information in the second part of the first channel state information report,

[0643] having a second priority order among the more than one first channel state information reports,

[0644] the second parts of one or more of said first channel state information reports having a third priority order,

[0645] In the third priority order, the first priority order is higher than the second priority order; or

[0646] In the third priority order, the second priority order is higher than the first priority order; or

[0647] In the third priority order, the second priority order is independent of the first priority order; or

[0648] The third priority order is the same as the second priority order.

[0649] 6. The method as described in Note 1, wherein:

[0650] The second part includes information of the precoding matrix,

[0651] The number of channel information included in the first channel state information report is greater than 1,

[0652] The second part also includes at least part of the information of the channel quality indicator,

[0653] Information in the second part within the first channel state information report has a first priority.

[0654] 7. The method as described in Supplementary Note 6, wherein:

[0655] The channel information is information about a spatial channel at a moment.

[0656] 8. The method as described in Supplementary Note 6, wherein:

[0657] The information in the second part is divided into more than one set, and each set has a priority order.

[0658] There is a priority order between the information within each set.

[0659] The one or more sets include at least one of a first set, a second set, and a third set,

[0660] The priority of the first set is higher than the priority of the second set, and the priority of the second set is higher than the priority of the third set.

[0661] 9. The method as described in Supplementary Note 8, wherein:

[0662] The first set includes at least one of the following information: spatial domain basis information, frequency domain basis information, time domain basis information, a wideband channel quality indicator in at least part of the channel quality indicator information, and information on a combining coefficient of a first predetermined spatial domain layer;

[0663] The second set includes at least one of the following information: information on the combining coefficient of the first predetermined spatial layer, information on the combining coefficient of the second predetermined spatial layer, and a first predetermined subband second channel quality indicator in at least part of the channel quality indicator information;

[0664] The third set includes at least one of the following information: information on the combining coefficient of the third predetermined spatial layer, a second predetermined subband second channel quality indicator in at least part of the channel quality indicator information,

[0665] Within the first set, the spatial basis information, the frequency domain basis information, the time domain basis information, the wideband channel quality indicator, and the combining coefficient information of the first predetermined spatial layer each have a priority order; and / or

[0666] In the second set, the information of combining coefficients of at least two spatial layers with different numbers and the second channel quality indicator of the first predetermined subband each have a priority order; and / or

[0667] In the third set, the information of combining coefficients of at least two spatial layers with different numbers and the second channel quality indicator of the second predetermined subband each have a priority order.

[0668] 10. The method as described in Supplementary Note 8, wherein:

[0669] The first set includes at least one of the following information: information of a spatial domain basis, information of a frequency domain basis, information of a time domain basis, a wideband channel quality indicator in at least part of the channel quality indicator information, and information of a first group of combining coefficients of a first predetermined spatial domain layer;

[0670] The second set includes at least one of the following information: information of a first group of combining coefficients of the first predetermined spatial layer, information of a first group of combining coefficients of the second predetermined spatial layer, and a first predetermined subband second channel quality indicator in at least part of the channel quality indicator information;

[0671] The third set includes at least one of the following information: information of a second group of combining coefficients of all spatial layers, a second predetermined subband second channel quality indicator in at least part of the channel quality indicator information,

[0672] Within the first set, the spatial basis information, the frequency domain basis information, the time domain basis information, the wideband channel quality indicator, and the first group of combining coefficients of the first predetermined spatial layer each have a priority order; and / or

[0673] In the second set, the information of the first group of combining coefficients of at least two spatial layers with different numbers and the second channel quality indicator of the first predetermined subband each have a priority order; and / or

[0674] In the third set, the information of the second group of combining coefficients of at least two spatial layers with different numbers and the second predetermined sub-band second channel quality indicator each have a priority order.

Claims

1. A device for generating channel state information, applied to a terminal device, the device comprising a first processing unit, the first processing unit controlling the terminal device to perform the following operations: The terminal device generates one or more first channel state information (CSI) reports, wherein the first channel state information reports include information of a precoding matrix, wherein: The precoding matrix information includes combining coefficient information, at least a portion of which is generated by an artificial intelligence (AI / ML) model. The first channel state information (CSI) report has a first part and a second part, and the second parts of more than one first channel state information (CSI) report have a priority order.

2. The device according to claim 1, wherein The information of the precoding matrix also includes information of a spatial domain basis, and / or information of a frequency domain basis, and / or information of a time domain basis.

3. The device according to claim 1, wherein There is a first priority order between the information in the second part of the first channel state information report.

4. The device according to claim 3, wherein The information in the second part is divided into one or more sets, and each set has a priority order.

5. The device according to claim 4, wherein There is a priority order between each information in each set.

6. The device according to claim 5, wherein The one or more sets include at least one of a first set, a second set, and a third set, The priority of the first set is higher than the priority of the second set, and the priority of the second set is higher than the priority of the third set.

7. The device according to claim 6, wherein The first set includes at least one of the following information: information of a spatial domain basis, information of a frequency domain basis, information of a time domain basis, and information of a combining coefficient of a first predetermined spatial domain layer; The second set includes: information on the merging coefficients of the first predetermined spatial layer and / or information on the merging coefficients of the second predetermined spatial layer; The third set includes: information on the combining coefficients of the third predetermined spatial layer.

8. The device according to claim 7, wherein In the first set, the information of the spatial basis, the information of the frequency domain basis, the information of the time domain basis, and the information of the combining coefficients of the first predetermined spatial layer each have a priority order; and / or In the second set, information on combining coefficients of at least two spatial layers with different numbers each has a priority order; and / or In the third set, information on combining coefficients of at least two spatial layers with different numbers each has a priority order.

9. The device according to claim 3, wherein having a second priority order among the more than one first channel state information reports, The second part of one or more of the first channel state information reports has a third priority order.

10. The device according to claim 9, wherein The operations further include: The terminal device discards at least part of the second part of at least one first channel state information report according to the third priority order; or The terminal device regenerates at least part of the channel state information from at least part of the second part of at least one first channel state information report according to the third priority and sends the regenerates at least part of the channel state information.

11. The device according to claim 1, wherein The number of channel information included in the first channel state information report is greater than 1, The second part also includes at least part of the information of the channel quality indicator, Information in the second part within the first channel state information report has a first priority.

12. The device according to claim 11, wherein The information in the second part is divided into one or more sets, and each set has a priority order.

13. The device of claim 12, wherein: There is a priority order between the information within each set.

14. The apparatus of claim 13, wherein: The one or more sets include at least one of a first set, a second set, and a third set, The priority of the first set is higher than the priority of the second set, and the priority of the second set is higher than the priority of the third set.

15. The apparatus of claim 14, wherein: The first set includes at least one of the following information: spatial domain basis information, frequency domain basis information, time domain basis information, a wideband channel quality indicator in at least part of the channel quality indicator information, and information on a combining coefficient of a first predetermined spatial domain layer; The second set includes at least one of the following information: information on the combining coefficient of the first predetermined spatial layer, information on the combining coefficient of the second predetermined spatial layer, and a first predetermined subband second channel quality indicator in at least part of the channel quality indicator information; The third set includes at least one of the following information: information on combining coefficients of a third predetermined spatial layer, and a second predetermined subband second channel quality indicator in at least part of the channel quality indicator information.

16. The apparatus of claim 15, wherein: Within the first set, the spatial basis information, the frequency domain basis information, the time domain basis information, the wideband channel quality indicator, and the combining coefficient information of the first predetermined spatial layer each have a priority order; and / or In the second set, the information of combining coefficients of at least two spatial layers with different numbers and the second channel quality indicator of the first predetermined subband each have a priority order; and / or In the third set, the information of combining coefficients of at least two spatial layers with different numbers and the second channel quality indicator of the second predetermined subband each have a priority order.

17. The apparatus of claim 1, wherein: The first channel state information report further includes information for indicating a reporting order of information of precoding matrices of N spatial domain layers, where N is a natural number greater than or equal to 2.

18. The apparatus of claim 17, wherein: The reporting order of the information of the precoding matrices of the N spatial layers is: an arrangement order of the artificial intelligence (AI / ML) models for generating information of precoding matrices and / or combining coefficients of the N spatial layers; or The arrangement order of the bit widths of the precoding matrix information and / or the combining coefficient information of the N spatial domain layers.

19. The apparatus of claim 17, wherein: The reporting order of the information of the precoding matrices of the N spatial domain layers is specified by the standard, or predefined, or agreed upon by the network device and the terminal device, or configured by the network device, or determined by the terminal device.

20. The apparatus of claim 1, wherein The order of the indexes of the N spatial domain layers is the same as the reporting order of the precoding matrix information of the N spatial domain layers, where N is a natural number greater than or equal to 2; or The order of the indexes of the N spatial layers is the order in which the bit width of the precoding matrix information or the bit width of the combining coefficient information of each spatial layer of the N spatial layers are arranged from large to small or from small to large; or The order of the indexes of the N spatial layers is the order in which the singular values corresponding to the right singular vectors of the precoding matrix corresponding to each spatial layer of the N spatial layers are arranged from large to small or from small to large.

Images