Method and apparatus for sending configuration information, method and apparatus for receiving configuration information, and communication system

Abstract

Provided in the embodiments of the present application are a method and apparatus for sending configuration information, a method and apparatus for receiving configuration information, and a communication system. The apparatus for sending configuration information is applied to a network device. The apparatus comprises a first processing unit, wherein the first processing unit controls the network device to execute the following operation: sending a first configuration to a terminal device, wherein the first configuration comprises: at least one of information of the number of spatial-domain bases, information of the number of frequency-domain bases, information of the number of time-domain bases and information of the number of pieces of channel information included in a channel state information (CSI) report; and information of a bit width of information of a combination coefficient, the information of the combination coefficient being obtained by means of using an artificial intelligence (AI / ML) model to process a combination coefficient in first precoding matrix information and / or a combination coefficient in spatial channel matrix information.

Description

Method, device and communication system for sending and receiving configuration 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 CSI feedback based on AI / ML. The AI / ML module may include an AI / ML-based CSI generation part and an AI / ML-based CSI reconstruction part. The AI / ML-based CSI generation part includes an AI / ML model, which may include an AI / ML encoder and a quantizer. In addition, the AI / ML model may also include a preprocessing module. The preprocessing module may also 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 two-dimensional discrete Fourier transform (DFT), or other preprocessing. The AI / ML-based CSI reconstruction part includes an AI / ML reconstruction model, which includes a dequantizer and an AI / ML decoder. In addition, 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 one or more spatial channel matrices or precoding matrices obtained through channel measurement and / or channel prediction are 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 configure the terminal device is a problem that needs to be solved.

[0014] In response to at least one of the above problems or other similar problems, the embodiments of the present application provide a method, apparatus, and communication system for sending and receiving configuration information, thereby enabling configuration of a terminal device. The terminal device can use an AI / ML model to process the merging coefficient based on the configuration information to obtain information about the merging coefficient.

[0015] According to one aspect of an embodiment of the present application, a device for sending configuration information is provided, which is applied to a network device. The device includes a first processing unit, which controls the network device to perform the following operations:

[0016] Sending a first configuration to a terminal device, the first configuration including: information on the number of spatial domain bases, information on the number of frequency domain bases, information on the number of time domain bases, and at least one of information on the amount of channel information included in a channel state information (CSI) report, and information on a bit width of information on combining coefficients;

[0017] The information of the combining coefficients is obtained by processing the combining coefficients in the first precoding matrix information and / or the combining coefficients in the spatial channel matrix information using an artificial intelligence (AI / ML) model.

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

[0019] receiving a first configuration sent by a network device, the first configuration including: information on the number of spatial domain bases, information on the number of frequency domain bases, information on the number of time domain bases, at least one of information on the amount of channel information included in a channel state information (CSI) report, and information on a bit width of combining coefficient information;

[0020] The information of the combining coefficients is obtained by processing the combining coefficients in the first precoding matrix information and / or the combining coefficients in the spatial channel matrix information using an artificial intelligence (AI / ML) model.

[0021] One of the beneficial effects of the embodiments of the present application is that the present application can configure the terminal device, and the terminal device can use the AI / ML model to process the merging coefficient based on the configuration information to obtain information about the merging coefficient.

[0022] 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.

[0023] 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.

[0024] 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

[0025] 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.

[0026] Figure 1 is a schematic diagram of CSI feedback based on AI / ML;

[0027] FIG2 is a schematic diagram of the communication system of the present application;

[0028] FIG3 is a schematic diagram of a method for sending configuration information according to an embodiment of the first aspect of the present application;

[0029] FIG4 is a schematic diagram of a method for receiving configuration information according to an embodiment of the second aspect of the present application;

[0030] FIG5 is a schematic diagram of an apparatus for sending configuration information according to an embodiment of the third aspect of the present application;

[0031] FIG6 is a schematic diagram of an apparatus for receiving configuration information according to an embodiment of the fourth aspect of the present application;

[0032] FIG7 is a schematic diagram of a terminal device according to an embodiment of the fifth aspect;

[0033] FIG8 is a schematic diagram of a network device according to an embodiment of the fifth aspect. DETAILED DESCRIPTION

[0034] 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.

[0035] 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.

[0036] 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.

[0037] 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.

[0038] 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.

[0039] 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 mobile management entity (MME), a gateway, a server, a radio network controller (RNC), a base station controller (BSC), and the like.

[0040] 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.

[0041] 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.

[0042] 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.

[0043] 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.

[0044] 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.

[0045] 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.

[0046] 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.

[0047] 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.

[0048] 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, an 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.

[0049] The following describes the scenarios of the embodiments of the present application through examples, but the present application is not limited thereto.

[0050] 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).

[0051] 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.

[0052] 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.

[0053] 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.

[0054] 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.

[0055] 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.

[0056] 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.

[0057] 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.

[0058] Embodiments of the first aspect

[0059] 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.

[0060] 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.

[0061] 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.

[0062] 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.

[0063] 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).

[0064] For the transformation to the Delay-Doppler domain, the spatial channel matrices at N time moments are compressed in the time domain (using a time-domain basis) to produce a set of combining coefficients. The spatial basis (also applicable to the frequency domain basis) can be the same for these N time moments, or different for at least two time moments. This set of combining coefficients serves as the input to the AI / ML model.

[0065] 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:

[0066] 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.

[0067] 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.

[0068] 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.

[0069] 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.

[0070] 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.

[0071] An embodiment of a first aspect of the present application provides a method for configuring channel state information, which is applied to a network device.

[0072] FIG3 is a schematic diagram of a method for sending configuration information. As shown in FIG3 , the method includes:

[0073] 301. Send a first configuration to a terminal device, wherein the first configuration includes: information on the number of spatial domain bases, information on the number of frequency domain bases, information on the number of time domain bases, and at least one of information on the quantity of channel information contained in a channel state information (CSI) report, and information on the bit width of the combining coefficient information.

[0074] In 301, combining coefficient information is obtained by processing combining coefficients in the first precoding matrix information and / or combining coefficients in the spatial channel matrix information using an artificial intelligence (AI / ML) model. 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.

[0075] In some examples of operation 301, the first configuration may include, for example:

[0076] 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

[0077] 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

[0078] 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.

[0079] The channel information refers to the spatial channel information at a given moment. Furthermore, the amount of channel information included in a channel state information (CSI) report refers to the number of spatial channel matrix information at each moment in time that the CSI report contains. This number represents the length of the time domain basis vector.

[0080] 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.

[0081] The above method is described in detail below through different embodiments.

[0082] Example 1:

[0083] In some implementations, the first configuration may be sent via a radio resource control (RRC) message.

[0084] In some examples, the first configuration can be configured by information (e.g., information elements and / or fields, etc.) added to the channel state information (CSI) report configuration, or by information (e.g., information elements and / or fields, etc.) that modifies the information in the channel state information (CSI) report configuration.

[0085] For example, a parameter for configuring the CSI generated using the AI / ML method included in the first configuration is defined in the channel state information (CSI) report configuration, wherein the parameter is used to describe the information of the number of spatial bases, and / or the information of the number of frequency domain bases, and / or the information of the number of time domain bases, and / or the information of the number of channel information contained in the CSI report and / or the bit width of the information of the combining coefficient; and / or

[0086] For another example, an information element (IE) and / or field is defined in the CSI report configuration, and the information element and / or field is used to configure the content included in the first configuration. The information element and / or field may be one or more than two. If there is one, the information element and / or field is used to configure all the content specified in the first configuration. If there are more than two, each information element and / or field may be used to configure one piece of information included in the first configuration, or at least one information element and / or field may be used to configure two or more pieces of information included in the first configuration.

[0087] In other examples, the first configuration is a separately defined configuration, i.e., the separately defined first configuration is not included in the channel state information (CSI) reporting configuration. The separately defined first configuration may be, for example, an AI / ML-based CSI reporting configuration or an uplink control information (UCI) configuration.

[0088] In some embodiments, as shown in FIG3 , the method may further include:

[0089] 302. Send a second configuration to the terminal device, where the second configuration includes information about a channel state information reference signal (CSI-RS) resource set used for channel measurement, and the number of the channel state information reference signal (CSI-RS) resource sets used for channel measurement is more than one.

[0090] The second configuration includes one or more CSI-RS resource sets for channel measurement, such as 1, 2, 3, or 4. The CSI-RS resource sets are configured by a higher-layer parameter such as trs-Info. The second configuration is sent via an RRC message.

[0091] The second configuration is associated with the first configuration. For example, the first configuration includes information about the second configuration.

[0092] The second configuration may be configured by information added to a channel state information (CSI) resource configuration, or by information modified from the information in the channel state information (CSI) resource configuration; or, the second configuration may be a separately defined configuration, such as a CSI resource configuration for generating CSI based on AI / ML.

[0093] In some implementations, the number of spatial bases (also applicable to frequency and time domain bases) 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 exist, each with a different number of spatial bases, which has the beneficial effect of improving CSI reporting accuracy. The spatial bases (also applicable to frequency and time domain bases) are a set of orthogonal bases, such as a set of DFT orthogonal bases.

[0094] In some implementations, the information about the number of spatial bases is explicitly represented, i.e., the number L or index of the spatial bases. This has the advantage of being simple to configure, easy to understand, and simple to implement. For example, when the number of spatial bases is the same for all transport layers, the network device configures the value of the number L of spatial bases.

[0095] In some implementations, information about the number of spatial bases is implicitly represented, which offers the advantage of flexible configuration, allowing for comprehensive consideration of multiple factors. For example, the number of spatial bases may be a function of the number of transmit antenna ports and a parameter, such as a scaling factor. There may be one or more optional parameters, which may be predefined, configured by the network device, and / or selected and reported to the network device by the terminal device.

[0096] In some implementations, the number of frequency domain bases is explicitly represented, i.e., the number or index of the frequency domain bases. This has the advantage of being simple to configure, easy to understand, and simple to implement. For example, when the number of frequency domain bases is the same for all transport layers, the network device configures the value of the number M of frequency domain bases.

[0097] In some embodiments, the information on the number of frequency domain bases is implicitly represented, which has the advantage of flexible configuration and comprehensive consideration of the number of frequency domain bases based on various factors. For example, if there are at least two transmission layers with different numbers of frequency domain bases, for the vth transmission layer, the network device configuration parameter p v and R, the number of frequency domain bases of this transmission layer is Where N3 is the number of frequency domain subbands occupied by transmission. This embodiment is only an example and does not limit the correspondence between "explicit representation / implicit representation" and "the number of frequency domain bases of all transmission layers is the same / the number of frequency domain bases of at least two transmission layers is different".

[0098] In some embodiments, the amount of channel information included in a CSI report is explicitly represented, i.e., as a numerical value or index of the amount, which has the beneficial effect of being simple to configure, easy to understand, and simple to implement. In some embodiments, the amount of channel information included in a CSI report is implicitly represented.

[0099] The number of channel information contained in a CSI report is equal to one or more than one. In some embodiments, the number of channel information contained in a CSI report is more than one, 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 four, and the configuration can be in the form of a numerical value or an index. For a channel state information (CSI) report containing one channel information, an application scenario of this embodiment is to use the AI / ML method to compress the spatial channel information (or its representation in the angular 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 its representation in the angular delay Doppler domain) in the spatial domain, the frequency domain, and the time domain to obtain CSI.

[0100] In some implementations, a CSI report may contain more than two pieces of channel information, for example, an integer in the range of 2-16. The intervals between any two adjacent pieces of channel information are the same, or at least two of the intervals are unequal. The spatial basis (also applicable to the frequency basis) can be the same for all pieces of channel information contained in a CSI report, which can simplify implementation and reduce reporting overhead. Alternatively, at least two pieces of channel information contained in a CSI report can be different, which can improve performance by selecting an appropriate spatial basis (also applicable to the frequency basis) based on the properties of the piece of channel information.

[0101] In some implementations, the number of time domain bases is explicitly represented, i.e., as a numerical value or index. This has the advantage of being simple to configure, easy to understand, and simple to implement. The number of time domain bases should not exceed the number of channel information contained in one CSI (if configured).

[0102] In some implementations, information regarding the number of time domain bases is implicitly represented, which has the beneficial effect of flexible configuration and reduced signaling overhead. For example, the number of time domain bases is a function of "the number of channel information contained in one CSI (if configured)." This function is predefined or configured by the network device, such as "the number of channel information contained in one CSI minus 1." In this case, information regarding the number of time domain bases can be omitted. By configuring "the number of channel information contained in one CSI," information regarding the number of time domain bases is obtained, thus reducing signaling overhead. The number of time domain bases should not exceed "the number of channel information contained in one CSI (if configured)."

[0103] In some implementations, the number of time domain bases may be 1, which has the beneficial effect of simple configuration, easy understanding, and simple implementation. The number of time domain bases may also be greater than 1, or not configured, which has the beneficial effect of saving signaling overhead.

[0104] In some embodiments, the information on the bit width of the information of the combined coefficients includes at least one of the following information: a numerical value or index of the bit width of the information of the combined coefficients; information on the artificial intelligence (AI / ML) model; and information on the maximum allowed bit width.

[0105] For example, the bit width of the information of the combined coefficients may be as follows:

[0106] 1. Bit-width value or index. The beneficial effect is that the configuration is simple and easy to understand and implement.

[0107] 2. AI / ML model information, such as identifiers or indexes. The AI / ML model is a consensus between the terminal device and the network device. Knowing the AI / ML model means knowing the bit width or maximum value of the output of its CSI generation component. This has the beneficial effect of avoiding redundancy and saving signaling overhead. Another benefit is that it avoids ambiguity caused by configuring the same information in two different ways.

[0108] 3. Information on the maximum allowable bit width, wherein the information on the maximum allowable bit width can be configured in the following forms:

[0109] Form 1: Explicit configuration, such as the value or index of the maximum allowed bit width. This has the advantage of being simple, understandable, and easy to implement.

[0110] Form 2: Implicit configuration, such as compression ratio. The benefit is flexible configuration.

[0111] Form 3: Implicit configuration, such as given through existing configuration. The beneficial effect is that it saves signaling overhead and has good compatibility with existing solutions. For example, the maximum value of the allowed bit width can be given by at least configuring the parameters of the codebook, such as the 3GPP Rel-18 enhanced type II codebook for predicted PMI, which defines the maximum number of non-zero combined coefficients and the quantization method of the non-zero coefficients. This information gives the first bit width, and the first bit width can be used as the maximum value of the allowed bit width that needs to be implicitly configured here.

[0112] In some embodiments, the first configuration further includes information on the number of non-zero merging coefficients, for example, for the vth transmission layer, the number (or maximum value) of non-zero merging coefficients is A v , v=1,2,…,l. At this time, the terminal device reserves A for the vth transmission layer v (or at most A v The largest merging coefficient is selected and the other merging coefficients are changed to 0.

[0113] One way to configure the information about the number of non-zero merging coefficients is to configure it explicitly, such as configuring A in a network device. v The value (or maximum value) or A v The index corresponding to the value (or maximum value) of , v=1,2,…,l. For v=1,2,…,l, A vThe values ​​(or maximum values) of can all be the same, or at least two can be different. Another method is implicit configuration, such as a network device configuration parameter β, where the number (or maximum value) of non-zero combining coefficients in each layer, or the total number (or maximum value of the total number) of non-zero combining coefficients is a function of β. An example of β is a parameter given in the 3GPP Rel-16 enhanced type II codebook or a parameter given in the 3GPP Rel-18 enhanced type II codebook for predicted PMI.

[0114] In some embodiments, the first configuration further includes codebook subset restriction information. For example, the codebook subset restriction information may be configured in the codebook configuration in the CSI report configuration, in the AI / ML-based CSI report configuration, in the UCI configuration, or in a configuration sent via an RRC message.

[0115] Example 2:

[0116] In the second embodiment, the combining coefficients in the precoding matrix information (for example, the first precoding matrix information) are input into the AI / ML model, and the AI / ML model outputs the combining coefficient information. The combining coefficients can be represented in the form of a matrix or a vector. For a channel state information (CSI) report containing one of the first precoding matrix 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 of the first precoding matrix 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.

[0117] 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.

[0118] 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.

[0119] 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.

[0120] 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.

[0121] For example, assume that downlink communication has only one transmission layer. All combining coefficients are represented by a matrix, such as matrix W2.

[0122] 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).

[0123] 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.

[0124] 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.

[0125] 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.

[0126] 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.

[0127] 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.

[0128] 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.

[0129] 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 magnitude 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 more easily recognized by the AI / ML model than in the first approach, which can lead to performance gains. In the second approach, the number and / or position of the merging coefficients in each group are different. This has the beneficial effect of using different AI / ML models to process merging coefficients with different properties (such as different orders of magnitude), which can better identify the properties of different categories of merging coefficients, further leading to performance gains.

[0130] 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.

[0131] 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.

[0132] 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.

[0133] Example 3:

[0134] In the third embodiment, as shown in FIG3 , the method further includes:

[0135] 303. The network device receives channel state information (CSI) sent by the terminal device, where the channel state information includes information of a second precoding matrix, and the information of the second precoding matrix includes information of the combining coefficients.

[0136] In addition, the information of the second precoding matrix also includes at least one of the following information: information of the spatial domain basis, information of the frequency domain basis, and information of the time domain basis.

[0137] At least one of the information of the spatial domain basis, the information of the frequency domain basis and the information of the time domain basis is the same for all transmission layers; or at least one of the information of the spatial domain basis, the information of the frequency domain basis and the information of the time domain basis is different for at least two transmission layers.

[0138] The information of the spatial domain basis includes the spatial domain basis and / or the index of the spatial domain basis in the spatial domain basis set; and / or the information of the frequency domain basis includes the frequency domain basis and / or the index of the frequency domain basis in the frequency domain basis set; and / or the information of the time domain basis includes the time domain basis and / or the index of the time domain basis in the time domain basis set.

[0139] For example, in some embodiments, depending on the configuration of the network device, the CSI reported by the terminal device may include information about the precoding matrix (i.e., information about the second precoding matrix). The information about the second precoding matrix may include information about the spatial basis and / or the frequency basis, and information about combining coefficients; or may include information about the spatial basis and / or the frequency basis and / or the time basis, and information about combining coefficients; or may include information about combining coefficients. The information about combining coefficients may be generated by an AI / ML method.

[0140] For example, 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 contained in a CSI report is 2, then the time domain basis information is not reported.

[0141] For example, 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 exist with different spatial bases, which has the beneficial effect of improving the accuracy of CSI reporting.

[0142] For example, in some embodiments, at least one of the spatial basis information, frequency domain basis information, and time domain basis information reported by the terminal device is an index in the spatial basis set, and / or the frequency domain basis set, and / or the time domain basis set. In some embodiments, at least one of the spatial basis information, frequency domain basis information, and time domain basis information reported by the terminal device may also be the basis itself. For example, the number of layers of downlink transmission is 1. The basis set of the entire spatial space is {v1, v2, ..., v S}, the basis set of the full frequency domain space is {u1, u2, ..., u F}, the basis set of the full space in the time domain / Doppler domain is {w1, w2, ..., w D The number of spatial bases reported by the terminal device explicitly configured by the network device is L = 2 ≤ S, the number of time domain bases reported by the terminal device explicitly configured by the network device is Q = 2 ≤ D, and the network device implicitly configures the number of frequency domain bases reported by the terminal device by configuring the values ​​of parameters p1 = 0.5, R = 1, N3 = 6, which is The spatial basis selected by the terminal device is {v2, v4}, and the frequency domain basis {u1, u3, u 10}, time domain basis {w1, w2}. The terminal device can report the spatial basis index 2, 4 or their binary representation, the frequency domain basis index 1, 3, 10 or their binary representation, and the time domain basis index 1, 2 or their binary representation. The terminal device can also report the spatial basis {v2, v4}, the frequency domain basis {u1, u3, u 10}, time domain basis {w1, w2}. The terminal device can also report the spatial basis index 2, 4 or its binary representation, the frequency domain basis {u1, u3, u 10}, time domain basis index 1, 2 or its binary representation.

[0143] For example, in some embodiments, the terminal device reports combining coefficient information. The terminal device determines whether to group the combining coefficients into N>1 groups (i.e., more than one group) based on the network device configuration, and generates the combining coefficient information using an AI / ML model (such as an AI / ML-based CSI generation component or an AI / ML encoder). The AI / ML model may be determined by the network device configuration.

[0144] In some implementations of Example 3, the terminal device sends CSI in an uplink channel.

[0145] For a channel state information (CSI) report containing one channel, one application scenario of this embodiment is to use AI / ML methods to compress the spatial channel information (or its representation in the angular delay domain) in the spatial and frequency domains to obtain CSI. For a channel state information (CSI) report containing more than one channel, one application scenario of this embodiment is to use AI / ML methods to compress the spatial channel information (or its representation in the angular delay Doppler domain) in the spatial, frequency, and time domains to obtain CSI.

[0146] According to an embodiment of the first aspect of the present application, in a scenario where the spatial channel matrix or precoding matrix is ​​mapped to the angle delay domain or the angle delay Doppler domain, and the AI / ML model is used to process the combining coefficient, the terminal device can be configured, and the terminal device can use the AI / ML model to process the combining coefficient based on the configuration information to obtain information about the combining coefficient.

[0147] Embodiments of the second aspect

[0148] The embodiment of the second aspect provides a method for receiving configuration information, which is applied to a terminal device, for example, the terminal device 202 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, which will not be repeated here.

[0149] FIG4 is a schematic diagram of a method for sending configuration information according to an embodiment of the second aspect. The method includes:

[0150] 401. Receive a first configuration sent by a network device, wherein the first configuration includes: information on the number of spatial domain bases, information on the number of frequency domain bases, information on the number of time domain bases, and at least one of information on the quantity of channel information contained in a channel state information (CSI) report, and information on the bit width of information on the combining coefficients.

[0151] The information of the combining coefficients is obtained by processing the combining coefficients in the first precoding matrix information and / or the combining coefficients in the spatial channel matrix information using an artificial intelligence (AI / ML) model.

[0152] In some embodiments, the channel information is information of a spatial channel at a time instant.

[0153] In some embodiments, the first configuration is configured by information added to a channel state information (CSI) reporting configuration, or by information modified from information in a channel state information (CSI) reporting configuration.

[0154] In some embodiments, the first configuration is a separately defined configuration.

[0155] In some embodiments, the method further comprises:

[0156] 402. Receive a second configuration sent by the network device, where the second configuration includes information about a channel state information reference signal (CSI-RS) resource set for channel measurement, and the number of the channel state information reference signal (CSI-RS) resource sets for channel measurement is more than one.

[0157] In some embodiments, the second configuration is associated with the first configuration. For example, the first configuration includes information about the second configuration.

[0158] In some embodiments, the second configuration is configured by information added to a channel state information (CSI) resource configuration, or by information modified from information in a channel state information (CSI) resource configuration, or the second configuration is a separately defined configuration.

[0159] In some embodiments, the number of said spatial bases is the same for all transmission layers, or the number of said spatial bases is different for at least two transmission layers; and / or

[0160] The number of the frequency domain bases is the same for all transmission layers, or the number of the frequency domain bases is different for at least two transmission layers; and / or

[0161] The number of the time domain bases is the same for all transmission layers, or the number of the time domain bases is different for at least two transmission layers; and / or

[0162] At least one of the information on the number of spatial domain bases, the information on the number of frequency domain bases, the information on the number of time domain bases, and the information on the quantity of channel information contained in the channel state information report is represented as a numerical value or an index, or at least one of the information on the number of spatial domain bases, the information on the number of frequency domain bases, the information on the number of time domain bases, and the information on the quantity of channel information contained in the channel state information report is represented implicitly.

[0163] In some embodiments, the channel state information report includes one or more channel information.

[0164] In some embodiments, the channel state information report includes more than one channel information, and the interval between two adjacent channel information is a time interval.

[0165] In some embodiments, the number of channel information included in the channel state information report is more than two, and the intervals between any two adjacent channel information are the same, or at least two of the intervals are not equal.

[0166] In some embodiments, at least one of the number of the spatial domain bases and the number of the frequency domain bases is the same for all channel information included in the one channel state information report, or at least one of the number of the spatial domain bases and the number of the frequency domain bases is different for at least two channel information included in the one channel state information report.

[0167] In some embodiments, the number of the time domain bases is one or more than one.

[0168] In some embodiments, the bit width information of the combining coefficient information includes at least one of the following information:

[0169] Information on the bit width of the information of the combining coefficients, such as a value or an index;

[0170] Information about the artificial intelligence (AI / ML) model;

[0171] Information about the maximum allowed bit width.

[0172] In some embodiments, the first configuration further comprises information on the number of non-zero merging coefficients, wherein the information on the number of non-zero merging coefficients is configured explicitly or implicitly; and / or

[0173] The first configuration also includes information on codebook subset restriction.

[0174] In some embodiments, all spatial layers use the same artificial intelligence (AI / ML) model, or at least two spatial layers use different artificial intelligence (AI / ML) models; and / or

[0175] At least a portion of the merging coefficients of a spatial layer is the input of the artificial intelligence (AI / ML) model, or at least a portion of the merging coefficients of a spatial layer is divided into more than one group, each of the groups is the input of more than one artificial intelligence (AI / ML) model, wherein each of the groups is the input of the same artificial intelligence (AI / ML) model or at least two of the groups are the input of different artificial intelligence (AI / ML) models.

[0176] In some embodiments, the number of merging coefficients of each of the groups is the same, or the number of merging coefficients of at least two of the groups is different; and / or

[0177] For more than two transmission layers of downlink communication, the number and / or position of combining coefficients of at least one of the groups are the same for all transmission layers, or the number and / or position of combining coefficients of at least one of the groups are different for at least two transmission layers.

[0178] In some embodiments, the information about the number of combining coefficients of each group or the information about the maximum value allowed is explicitly configured or implicitly configured; and / or

[0179] The information on the number of combining coefficients of each group or the information on the allowed maximum value is predefined, configured by the network device, or specified by a standard.

[0180] In some embodiments, the terminal device is further configured to:

[0181] whether at least a portion of the combining coefficients of one of said spatial layers are divided into more than one group; and / or

[0182] At least a portion of the combining coefficients of one of the spatial layers is information of an input of the artificial intelligence (AI / ML) model, and / or information of a bit width of an output of the artificial intelligence (AI / ML) model; and / or

[0183] The combining coefficients of more than one of the groups of the spatial layer 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.

[0184] In some embodiments, the merging coefficient of a spatial layer includes: a merging coefficient at one moment, or a merging coefficient at two or more moments.

[0185] In some embodiments, the method further comprises:

[0186] 403. Send channel state information (CSI) to the network device, where the channel state information includes information about a second precoding matrix, and the information about the second precoding matrix includes information about the combining coefficients.

[0187] In some embodiments, the information of the second precoding matrix further includes at least one of the following information:

[0188] The information of the spatial domain basis, the information of the frequency domain basis, and the information of the time domain basis.

[0189] In some embodiments, at least one of the information of the spatial domain basis, the information of the frequency domain basis, and the information of the time domain basis is the same for all transmission layers; or

[0190] At least one of the spatial domain basis information, the frequency domain basis information, and the time domain basis information is different for at least two transmission layers.

[0191] In some embodiments, the information of the spatial basis includes a spatial basis and / or an index of the spatial basis in a set of spatial basis; and / or

[0192] The information of the frequency domain basis includes the frequency domain basis and / or the index of the frequency domain basis in the frequency domain basis set; and / or

[0193] The information of the time domain basis includes the time domain basis and / or the index of the time domain basis in a time domain basis set.

[0194] Embodiments of the third aspect

[0195] 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 sending configuration information, which is applied to a network device and corresponds to the embodiment of the first aspect.

[0196] FIG5 is a schematic diagram of an apparatus for sending configuration information according to an embodiment of the third aspect. As shown in FIG5 , the apparatus 500 for configuring channel state information includes: a first processing unit 501 .

[0197] The first processing unit 501 causes the network device to perform the following operations:

[0198] Sending a first configuration to a terminal device, the first configuration including: information on the number of spatial domain bases, information on the number of frequency domain bases, information on the number of time domain bases, and at least one of information on the amount of channel information included in a channel state information (CSI) report, and information on a bit width of information on combining coefficients;

[0199] The information of the combining coefficients is obtained by processing the combining coefficients in the first precoding matrix information and / or the combining coefficients in the spatial channel matrix information using an artificial intelligence (AI / ML) model.

[0200] In some embodiments, the channel information is information of a spatial channel at a time instant.

[0201] In some embodiments, the first configuration is configured by information added to a channel state information (CSI) reporting configuration, or by information modified from information in a channel state information (CSI) reporting configuration.

[0202] In some embodiments, the first configuration is a separately defined configuration.

[0203] In some embodiments, the operations further include:

[0204] A second configuration is sent to the terminal device, where the second configuration includes information about a channel state information reference signal (CSI-RS) resource set used for channel measurement, and the number of the channel state information reference signal (CSI-RS) resource sets used for channel measurement is more than one.

[0205] In some embodiments, the second configuration is associated with the first configuration.

[0206] In some embodiments, the first configuration includes information of the second configuration.

[0207] In some embodiments, the second configuration is configured by information added to a channel state information (CSI) resource configuration, or by information modified from information in a channel state information (CSI) resource configuration, or the second configuration is a separately defined configuration.

[0208] In some embodiments, the number of said spatial bases is the same for all transmission layers, or the number of said spatial bases is different for at least two transmission layers; and / or

[0209] The number of the frequency domain bases is the same for all transmission layers, or the number of the frequency domain bases is different for at least two transmission layers; and / or

[0210] The number of the time domain bases is the same for all transmission layers, or the number of the time domain bases is different for at least two transmission layers; and / or

[0211] At least one of the information on the number of spatial domain bases, the information on the number of frequency domain bases, the information on the number of time domain bases, and the information on the quantity of channel information contained in the channel state information report is represented as a numerical value or an index, or at least one of the information on the number of spatial domain bases, the information on the number of frequency domain bases, the information on the number of time domain bases, and the information on the quantity of channel information contained in the channel state information report is represented implicitly.

[0212] In some embodiments, the channel state information report includes one or more channel information.

[0213] In some embodiments, the channel state information report includes more than one channel information, and the interval between two adjacent channel information is a time interval.

[0214] In some embodiments, the number of channel information included in the channel state information report is more than two, and the intervals between any two adjacent channel information are the same, or at least two of the intervals are not equal.

[0215] In some embodiments, at least one of the number of the spatial domain bases and the number of the frequency domain bases is the same for all channel information included in the one channel state information report, or at least one of the number of the spatial domain bases and the number of the frequency domain bases is different for at least two channel information included in the one channel state information report.

[0216] In some embodiments, the number of the time domain bases is one or more than one.

[0217] In some embodiments, the bit width information of the combining coefficient information includes at least one of the following information:

[0218] Information on the bit width of the information of the combining coefficients, such as a value or an index;

[0219] Information about the artificial intelligence (AI / ML) model;

[0220] Information about the maximum allowed bit width.

[0221] In some embodiments, the first configuration further comprises information on the number of non-zero merging coefficients, wherein the information on the number of non-zero merging coefficients is configured explicitly or implicitly; and / or

[0222] The first configuration also includes information on codebook subset restriction.

[0223] In some embodiments, all spatial layers use the same artificial intelligence (AI / ML) model, or at least two spatial layers use different artificial intelligence (AI / ML) models; and / or

[0224] At least a portion of the merging coefficients of a spatial layer is the input of the artificial intelligence (AI / ML) model, or at least a portion of the merging coefficients of a spatial layer is divided into more than one group, each of the groups is the input of more than one artificial intelligence (AI / ML) model, wherein each of the groups is the input of the same artificial intelligence (AI / ML) model or at least two of the groups are the input of different artificial intelligence (AI / ML) models.

[0225] In some embodiments, the number of merging coefficients of each of the groups is the same, or the number of merging coefficients of at least two of the groups is different; and / or

[0226] For more than two transmission layers of downlink communication, the number and / or position of combining coefficients of at least one of the groups are the same for all transmission layers, or the number and / or position of combining coefficients of at least one of the groups are different for at least two transmission layers.

[0227] In some embodiments, the information about the number of combining coefficients of each group or the information about the maximum value allowed is explicitly configured or implicitly configured; and / or

[0228] The information on the number of combining coefficients of each group or the information on the allowed maximum value is predefined, configured by the network device, or specified by a standard.

[0229] In some embodiments, the network device is further configured to:

[0230] whether at least a portion of the combining coefficients of one of said spatial layers are divided into more than one group; and / or

[0231] At least a portion of the combining coefficients of one of the spatial layers is information of an input of the artificial intelligence (AI / ML) model, and / or information of a bit width of an output of the artificial intelligence (AI / ML) model; and / or

[0232] The combining coefficients of more than one of the groups of the spatial layer 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.

[0233] In some embodiments, the merging coefficient of a spatial layer includes: a merging coefficient at one moment, or a merging coefficient at two or more moments.

[0234] In some embodiments, the operations further include:

[0235] Channel state information (CSI) sent by the terminal device is received, where the channel state information includes information of a second precoding matrix, and the information of the second precoding matrix includes information of the combining coefficients.

[0236] In some embodiments, the information of the second precoding matrix further includes at least one of the following information:

[0237] The information of the spatial domain basis, the information of the frequency domain basis, and the information of the time domain basis.

[0238] In some embodiments, at least one of the information of the spatial domain basis, the information of the frequency domain basis, and the information of the time domain basis is the same for all transmission layers; or

[0239] At least one of the spatial domain basis information, the frequency domain basis information, and the time domain basis information is different for at least two transmission layers.

[0240] In some embodiments, the information of the spatial basis includes a spatial basis and / or an index of the spatial basis in a set of spatial basis; and / or

[0241] The information of the frequency domain basis includes the frequency domain basis and / or the index of the frequency domain basis in the frequency domain basis set; and / or

[0242] The information of the time domain basis includes the time domain basis and / or the index of the time domain basis in a time domain basis set.

[0243] Embodiments of the fourth aspect

[0244] An embodiment of the fourth aspect of the present application provides an apparatus for receiving configuration information, which is applied to a terminal device and corresponds to the method of the embodiment of the second aspect.

[0245] Fig. 6 is a schematic diagram of an apparatus for receiving configuration information according to an embodiment of the fourth aspect. As shown in Fig. 6 , the apparatus 600 includes: a second processing unit 601 .

[0246] In at least one embodiment, the second processing unit 601 controls the terminal device to perform the following operations:

[0247] receiving a first configuration sent by a network device, the first configuration including: information on the number of spatial domain bases, information on the number of frequency domain bases, information on the number of time domain bases, at least one of information on the amount of channel information included in a channel state information (CSI) report, and information on a bit width of combining coefficient information;

[0248] The information of the combining coefficients is obtained by processing the combining coefficients in the first precoding matrix information and / or the combining coefficients in the spatial channel matrix information using an artificial intelligence (AI / ML) model.

[0249] In some embodiments, the channel information is information of a spatial channel at a time instant.

[0250] In some embodiments, the first configuration is configured by information added to a channel state information (CSI) reporting configuration, or by information modified from information in a channel state information (CSI) reporting configuration.

[0251] In some embodiments, the first configuration is a separately defined configuration.

[0252] In some embodiments, the operations further include:

[0253] Receive a second configuration sent by the network device, where the second configuration includes information about a channel state information reference signal (CSI-RS) resource set for channel measurement, and the number of the channel state information reference signal (CSI-RS) resource sets for channel measurement is more than one.

[0254] In some embodiments, the second configuration is associated with the first configuration.

[0255] In some embodiments, the first configuration includes information of the second configuration.

[0256] In some embodiments, the second configuration is configured by information added to a channel state information (CSI) resource configuration, or by information modified from information in a channel state information (CSI) resource configuration, or the second configuration is a separately defined configuration.

[0257] In some embodiments, the number of said spatial bases is the same for all transmission layers, or the number of said spatial bases is different for at least two transmission layers; and / or

[0258] The number of the frequency domain bases is the same for all transmission layers, or the number of the frequency domain bases is different for at least two transmission layers; and / or

[0259] The number of the time domain bases is the same for all transmission layers, or the number of the time domain bases is different for at least two transmission layers; and / or

[0260] At least one of the information on the number of spatial domain bases, the information on the number of frequency domain bases, the information on the number of time domain bases, and the information on the quantity of channel information contained in the channel state information report is represented as a numerical value or an index, or at least one of the information on the number of spatial domain bases, the information on the number of frequency domain bases, the information on the number of time domain bases, and the information on the quantity of channel information contained in the channel state information report is represented implicitly.

[0261] In some embodiments, the channel state information report includes one or more channel information.

[0262] In some embodiments, the channel state information report includes more than one channel information, and the interval between two adjacent channel information is a time interval.

[0263] In some embodiments, the number of channel information included in the channel state information report is more than two, and the intervals between any two adjacent channel information are the same, or at least two of the intervals are not equal.

[0264] In some embodiments, at least one of the number of the spatial domain bases and the number of the frequency domain bases is the same for all channel information included in the one channel state information report, or at least one of the number of the spatial domain bases and the number of the frequency domain bases is different for at least two channel information included in the one channel state information report.

[0265] In some embodiments, the number of the time domain bases is one or more than one.

[0266] In some embodiments, the bit width information of the combining coefficient information includes at least one of the following information:

[0267] Information on the bit width of the information of the combining coefficients, such as a value or an index;

[0268] Information about the artificial intelligence (AI / ML) model;

[0269] Information about the maximum allowed bit width.

[0270] In some embodiments, the first configuration further comprises information on the number of non-zero merging coefficients, wherein the information on the number of non-zero merging coefficients is configured explicitly or implicitly; and / or

[0271] The first configuration also includes information on codebook subset restriction.

[0272] In some embodiments, all spatial layers use the same artificial intelligence (AI / ML) model, or at least two spatial layers use different artificial intelligence (AI / ML) models; and / or

[0273] At least a portion of the merging coefficients of a spatial layer is the input of the artificial intelligence (AI / ML) model, or at least a portion of the merging coefficients of a spatial layer is divided into more than one group, each of the groups is the input of more than one artificial intelligence (AI / ML) model, wherein each of the groups is the input of the same artificial intelligence (AI / ML) model or at least two of the groups are the input of different artificial intelligence (AI / ML) models.

[0274] In some embodiments, the number of merging coefficients of each of the groups is the same, or the number of merging coefficients of at least two of the groups is different; and / or

[0275] For more than two transmission layers of downlink communication, the number and / or position of combining coefficients of at least one of the groups are the same for all transmission layers, or the number and / or position of combining coefficients of at least one of the groups are different for at least two transmission layers.

[0276] In some embodiments, the information about the number of combining coefficients of each group or the information about the maximum value allowed is explicitly configured or implicitly configured; and / or

[0277] The information on the number of combining coefficients of each group or the information on the allowed maximum value is predefined, configured by the network device, or specified by a standard.

[0278] In some embodiments, the terminal device is further configured to:

[0279] whether at least a portion of the combining coefficients of one of said spatial layers are divided into more than one group; and / or

[0280] At least a portion of the combining coefficients of one of the spatial layers is information of an input of the artificial intelligence (AI / ML) model, and / or information of a bit width of an output of the artificial intelligence (AI / ML) model; and / or

[0281] The combining coefficients of more than one of the groups of the spatial layer 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.

[0282] In some embodiments, the merging coefficient of a spatial layer includes: a merging coefficient at one moment, or a merging coefficient at two or more moments.

[0283] In some embodiments, the operations further include:

[0284] Channel state information (CSI) is sent to the network device, where the channel state information includes information of a second precoding matrix, and the information of the second precoding matrix includes information of the combining coefficients.

[0285] In some embodiments, the information of the second precoding matrix further includes at least one of the following information:

[0286] The information of the spatial domain basis, the information of the frequency domain basis, and the information of the time domain basis.

[0287] In some embodiments, at least one of the information of the spatial domain basis, the information of the frequency domain basis, and the information of the time domain basis is the same for all transmission layers; or

[0288] At least one of the spatial domain basis information, the frequency domain basis information, and the time domain basis information is different for at least two transmission layers.

[0289] In some embodiments, the information of the spatial basis includes a spatial basis and / or an index of the spatial basis in a set of spatial basis; and / or

[0290] The information of the frequency domain basis includes the frequency domain basis and / or the index of the frequency domain basis in the frequency domain basis set; and / or

[0291] The information of the time domain basis includes the time domain basis and / or the index of the time domain basis in a time domain basis set.

[0292] Embodiments of the fifth aspect

[0293] An embodiment of the fifth aspect of the present application provides a communication system, which may include a network device and a terminal device.

[0294] FIG7 is a schematic diagram of a terminal device according to an embodiment of the fifth aspect. As shown in FIG7 , the terminal device 700 (e.g., corresponding to the terminal device 202 in FIG2 ) may include a processor 710 and a memory 720; the memory 720 stores data and programs and is coupled to the processor 710. 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.

[0295] For example, the processor 710 may be configured to execute a program to implement the method according to the second embodiment.

[0296] As shown in Figure 7 , the terminal device 700 may further include: a communication module 730, an input unit 740, a display 750, and a power supply 760. 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 700 does not necessarily include all of the components shown in Figure 7 , and these components are not essential. Furthermore, the terminal device 700 may also include components not shown in Figure 7 , for which reference may be made to the prior art.

[0297] FIG8 is a schematic diagram of a network device according to an embodiment of the fifth aspect. As shown in FIG8 , network device 800 (e.g., corresponding to network device 201 in FIG2 ) may include a processor 810 (e.g., a central processing unit (CPU)) and a memory 820; the memory 820 is coupled to the processor 810. The memory 820 may store various data and may also store an information processing program 830, which is executed under the control of the processor 88.

[0298] For example, the processor 88 may be configured to execute a program to implement the method described in the embodiment of the first aspect.

[0299] In addition, as shown in FIG8 , network device 800 may further include: a transceiver 840 and an antenna 850, etc.; 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 network device 800 does not necessarily include all the components shown in FIG8 ; in addition, network device 800 may also include components not shown in FIG8 , and reference may be made to the prior art for details.

[0300] 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 second aspect.

[0301] 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 second aspect.

[0302] 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 first aspect.

[0303] 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 first aspect.

[0304] 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.

[0305] 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).

[0306] 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.

[0307] 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.

[0308] 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.

[0309] Regarding the implementation methods including the above embodiments, the following additional notes are also disclosed:

[0310] 1. A method for sending configuration information, applied to a network device, the method comprising:

[0311] Sending a first configuration to a terminal device, the first configuration including: information on the number of spatial domain bases, information on the number of frequency domain bases, information on the number of time domain bases, and at least one of information on the amount of channel information included in a channel state information (CSI) report, and information on a bit width of information on combining coefficients;

[0312] The information of the combining coefficient is obtained by processing the combining coefficient in the first precoding matrix information and / or the combining coefficient in the spatial channel matrix information using an artificial intelligence (AI / ML) model.

[0313] The method further comprises:

[0314] sending a second configuration to the terminal device, where the second configuration includes information of a channel state information reference signal (CSI-RS) resource set for channel measurement, where the number of the channel state information reference signal (CSI-RS) resource sets for channel measurement is one or more,

[0315] The second configuration is associated with the first configuration.

[0316] 2. The method as described in Note 1, wherein:

[0317] The first configuration includes information of the second configuration.

[0318] 3. The method as described in Note 1, wherein:

[0319] The second configuration is configured by information added to the channel state information (CSI) resource configuration, or configured by information after modifying the information in the channel state information (CSI) resource configuration, or the second configuration is a separately defined configuration.

[0320] 4. The method as described in Note 1, wherein:

[0321] The channel state information report includes one or more channel information.

[0322] The channel state information report includes more than one channel information, and the interval between two adjacent channel information is a time interval.

[0323] 5. The method as described in Note 4, wherein:

[0324] The number of channel information included in one channel state information report is more than two, and the intervals between any two adjacent channel information are the same, or at least two of the intervals are not equal.

[0325] 6. The method as described in Note 4, wherein:

[0326] At least one of the number of the spatial domain bases and the number of the frequency domain bases is the same for all channel information included in the channel state information report, or at least one of the number of the spatial domain bases and the number of the frequency domain bases is different for at least two pieces of channel information included in the channel state information report.

[0327] 7. The method as described in Note 1, wherein:

[0328] The number of the time domain bases is one or more than one.

[0329] 8. The method as described in Note 1, wherein:

[0330] The merging coefficient of a spatial layer includes: a merging coefficient at one moment, or a merging coefficient at two or more moments.

[0331] 9. The method as described in Supplement 1, wherein:

[0332] The method further comprises:

[0333] receiving channel state information (CSI) sent by the terminal device, the channel state information including information of a second precoding matrix, the information of the second precoding matrix including information of the combining coefficients,

[0334] The information of the second precoding matrix further includes at least one of the following information:

[0335] The information of the spatial domain basis, the information of the frequency domain basis, the information of the time domain basis,

[0336] At least one of the spatial domain basis information, the frequency domain basis information, and the time domain basis information is the same for all transmission layers; or

[0337] At least one of the spatial domain basis information, the frequency domain basis information, and the time domain basis information is different for at least two transmission layers.

[0338] 10. The method as described in Supplementary Note 9, wherein:

[0339] The information of the spatial basis includes the spatial basis and / or the index of the spatial basis in the spatial basis set; and / or

[0340] The information of the frequency domain basis includes the frequency domain basis and / or the index of the frequency domain basis in the frequency domain basis set; and / or

[0341] The information of the time domain basis includes the time domain basis and / or the index of the time domain basis in a time domain basis set.

Claims

1. A device for sending configuration information, applied to a network device, the device comprising a first processing unit, the first processing unit controlling the network device to perform the following operations: Sending a first configuration to a terminal device, where the first configuration includes: At least one of information on the number of spatial domain bases, information on the number of frequency domain bases, information on the number of time domain bases, and information on the amount of channel information included in a channel state information (CSI) report, and information on the bit width of information on combining coefficients; The information of the combining coefficients is obtained by processing the combining coefficients in the first precoding matrix information and / or the combining coefficients in the spatial channel matrix information using an artificial intelligence (AI / ML) model.

2. The device according to claim 1, wherein The channel information is information about a spatial channel at a moment.

3. The device according to claim 1, wherein The first configuration is configured by information added to a channel state information (CSI) reporting configuration, or by information obtained by modifying information in a channel state information (CSI) reporting configuration.

4. The device according to claim 1, wherein The first configuration is a separately defined configuration.

5. The device according to claim 1, wherein The channel state information report includes one or more channel information.

6. The device according to claim 1, wherein The bit width information of the information of the combined coefficients includes at least one of the following information: A value or index of the bit width of the information of the combining coefficients; information about the artificial intelligence (AI / ML) model; Information about the maximum allowed bit width.

7. The device according to claim 1, wherein The first configuration further includes information on the number of non-zero merging coefficients, where the information on the number of non-zero merging coefficients is configured explicitly or implicitly; and / or The first configuration also includes codebook subset restriction.

8. The device according to claim 1, wherein All spatial layers use the same artificial intelligence (AI / ML) model, or at least two spatial layers use different artificial intelligence (AI / ML) models; and / or At least a portion of the merging coefficients of a spatial layer is the input of the artificial intelligence (AI / ML) model, or at least a portion of the merging coefficients of a spatial layer is divided into more than one group, each of the groups is the input of more than one artificial intelligence (AI / ML) model, wherein each of the groups is the input of the same artificial intelligence (AI / ML) model or at least two of the groups are the input of different artificial intelligence (AI / ML) models.

9. The device according to claim 8, wherein The number of merging coefficients of each of the groups is the same, or the number of merging coefficients of at least two of the groups is different; and / or For more than two transmission layers of downlink communication, the number and / or position of combining coefficients of at least one of the groups are the same for all transmission layers, or the number and / or position of combining coefficients of at least one of the groups are different for at least two transmission layers.

10. The device according to claim 9, wherein The information on the number of combining coefficients of each group or the information on the maximum value allowed is explicitly configured or implicitly configured; and / or The information on the number of combining coefficients of each group or the information on the allowed maximum value is predefined, configured by the network device, or specified by a standard.

11. A device for receiving configuration information, applied to a terminal device, the device comprising a second processing unit, the second processing unit controlling the terminal device to perform the following operations: Receive a first configuration sent by a network device, where the first configuration includes: At least one of information on the number of spatial domain bases, information on the number of frequency domain bases, information on the number of time domain bases, and information on the amount of channel information included in a channel state information (CSI) report, and information on the bit width of information on combining coefficients; The information of the combining coefficients is obtained by processing the combining coefficients in the first precoding matrix information and / or the combining coefficients in the spatial channel matrix information using an artificial intelligence (AI / ML) model.

12. The device according to claim 11, wherein The first configuration is configured by information added to a channel state information (CSI) reporting configuration, or by information obtained by modifying information in a channel state information (CSI) reporting configuration.

13. The device according to claim 11, wherein The operations further include: Receive a second configuration sent by the network device, where the second configuration includes information about a channel state information reference signal (CSI-RS) resource set for channel measurement, and the number of the channel state information reference signal (CSI-RS) resource sets for channel measurement is more than one.

14. The device of claim 11, wherein: The number of the spatial bases is the same for all transmission layers, or the number of the spatial bases is different for at least two transmission layers; and / or The number of the frequency domain bases is the same for all transmission layers, or the number of the frequency domain bases is different for at least two transmission layers; and / or The number of the time domain bases is the same for all transmission layers, or the number of the time domain bases is different for at least two transmission layers; and / or At least one of the information on the number of spatial domain bases, the information on the number of frequency domain bases, the information on the number of time domain bases, and the information on the quantity of channel information contained in the channel state information report is represented as a numerical value or an index, or at least one of the information on the number of spatial domain bases, the information on the number of frequency domain bases, the information on the number of time domain bases, and the information on the quantity of channel information contained in the channel state information report is represented implicitly.

15. The apparatus of claim 11, wherein: The channel state information report includes one or more channel information.

16. The apparatus of claim 11, wherein: The bit width information of the information of the combined coefficients includes at least one of the following information: A value or index of the bit width of the information of the combining coefficients; Information about the artificial intelligence (AI / ML) model; Information about the maximum allowed bit width.

17. The apparatus of claim 11, wherein: All spatial layers use the same artificial intelligence (AI / ML) model, or at least two spatial layers use different artificial intelligence (AI / ML) models; and / or At least a portion of the merging coefficients of a spatial layer is an input to the artificial intelligence (AI / ML) model, or at least a portion of the merging coefficients of a spatial layer is divided into more than one group, each of the groups is an input to more than one artificial intelligence (AI / ML) model, wherein each group is the same artificial intelligence (AI / ML) model. The input of the model or at least two of the groups are inputs of different artificial intelligence (AI / ML) models.

18. The apparatus of claim 17, wherein: The terminal device is further configured: whether at least a portion of the combining coefficients of one of said spatial layers are divided into more than one group; and / or At least a portion of the combining coefficients of one of the spatial layers is information of an input of the artificial intelligence (AI / ML) model, and / or information of a bit width of an output of the artificial intelligence (AI / ML) model; and / or The combining coefficients of more than one of the groups of the spatial layer 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.

19. The apparatus of claim 11, wherein: The operations further include: Channel state information (CSI) is sent to the network device, where the channel state information includes information of a second precoding matrix, and the information of the second precoding matrix includes information of the combining coefficients.

20. The apparatus of claim 19, wherein The information of the second precoding matrix further includes at least one of the following information: The information of the spatial domain basis, the information of the frequency domain basis, and the information of the time domain basis.

Images