Channel state information processing method and apparatus, and communication system

Abstract

The embodiments of the present application provide a channel state information (CSI) processing method and apparatus, and a communication system. The method comprises: a terminal device receiving CSI resource configuration information and CSI reporting configuration information from a network device; and on the basis of the CSI resource configuration information and the CSI reporting configuration information, the terminal device sending CSI feedback information, wherein the CSI feedback information comprises information for indicating a CSI reconstruction operation of the network device.

Description

Channel state information processing method, device and communication system Technical Field

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

[0002] In NR (New Radio) Rel-18 (Release 18), research was conducted on artificial intelligence / machine learning (AI / ML) for the air interface. AI / ML can be used for the following use cases: CSI (channel state information) feedback enhancement, beam management, and positioning enhancement. CSI feedback enhancement can include CSI prediction and CSI compression; beam management can include spatial beam prediction and temporal beam prediction; and positioning enhancement can include direct positioning and AI / ML-assisted positioning. These use cases are only preliminary selections; new use cases may be added or existing use cases may be enhanced in Rel-19 (Release 19).

[0003] With the introduction of these use cases, standardization efforts are underway to develop new protocols, processes, and signaling to support the reliable operation of AI / ML and ensure its effective benefits. These protocol-related methods and approaches are not only targeted at 5G-Advanced standards and commercial networks and devices, but can also be applied to 6G networks and devices beyond.

[0004] It should be noted that the above introduction to the technical background is merely for the purpose of providing a clear and complete description of the technical solutions of this application and facilitating 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.

[0005] Summary of the Invention

[0006] The inventors discovered that for the CSI compression sub-use case using time-domain information within the CSI feedback enhancement use case, current CSI processing methods are only applicable when the number of data transmission layers is fixed (i.e., fixed rank). It is unclear how to perform CSI processing when rank adaptation causes the rank value to change.

[0007] In response to at least one of the above problems, embodiments of the present application provide a method, apparatus, and communication system for processing channel state information.

[0008] According to one aspect of an embodiment of the present application, a method for processing channel state information is provided, which is applied to a terminal device, wherein the method includes: the terminal device receiving CSI resource configuration information and CSI reporting configuration information from a network device; and the terminal device sending CSI feedback information based on the CSI resource configuration information and the CSI reporting configuration information, wherein the CSI feedback information includes information for indicating a CSI reconstruction operation of the network device.

[0009] According to another aspect of an embodiment of the present application, a method for processing channel state information is provided, which is applied to a network device, wherein the method includes: the network device sends CSI resource configuration information and CSI reporting configuration information to a terminal device; and the network device receives CSI feedback information sent by the terminal device, wherein the CSI feedback information includes information for indicating a CSI reconstruction operation of the network device.

[0010] According to another aspect of an embodiment of the present application, a channel state information processing device is provided, which is configured in a terminal device, wherein the device includes: a receiving unit, which receives CSI resource configuration information and CSI reporting configuration information from a network device; and a sending unit, which sends CSI feedback information based on the CSI resource configuration information and the CSI reporting configuration information, wherein the CSI feedback information includes information for indicating a CSI reconstruction operation of the network device.

[0011] According to another aspect of an embodiment of the present application, a channel state information processing device is provided, which is configured in a network device, wherein the device includes: a sending unit, which sends CSI resource configuration information and CSI reporting configuration information to a terminal device; and a receiving unit, which receives CSI feedback information sent by the terminal device, wherein the CSI feedback information includes information for indicating a CSI reconstruction operation of the network device.

[0012] According to another aspect of an embodiment of the present application, a terminal device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor is configured to execute the computer program to implement the channel state information processing method on the terminal device side.

[0013] According to another aspect of an embodiment of the present application, a network device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor is configured to execute the computer program to implement the channel state information processing method on the network device side.

[0014] According to another aspect of an embodiment of the present application, a communication system is provided, wherein the system includes: a network device that sends CSI resource configuration information and CSI reporting configuration information to a terminal device, and receives CSI feedback information sent by the terminal device; and

[0015] A terminal device receives the CSI resource configuration information and the CSI reporting configuration information, and sends CSI feedback information according to the CSI resource configuration information and the CSI reporting configuration information, wherein the CSI feedback information includes information for instructing the network device to reconstruct the CSI operation.

[0016] One of the beneficial effects of the embodiments of the present application is that a terminal device receives CSI resource configuration information and CSI reporting configuration information from a network device, and sends CSI feedback information based on the CSI resource configuration information and the CSI reporting configuration information, wherein the CSI feedback information includes information for indicating a CSI reconstruction operation of the network device. By including information for indicating a CSI reconstruction operation of the network device in the CSI feedback information, the CSI reconstruction operation can be accurately performed regardless of whether the rank is fixed or the rank is adaptive, thereby helping to improve the throughput of the communication system.

[0017] 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.

[0018] 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.

[0019] 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

[0020] 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.

[0021] FIG1 is a schematic diagram of a communication system according to an embodiment of the present application;

[0022] FIG2 is a schematic diagram of a CSI compression feedback enhancer use case of the spatiotemporal frequency domain-artificial intelligence / machine learning embodiment of the present application;

[0023] FIG3 is a schematic diagram of a method for processing channel state information according to an embodiment of the present application;

[0024] FIG4 is another schematic diagram of a method for processing channel state information according to an embodiment of the present application;

[0025] FIG5 is a schematic diagram of a device for processing channel state information according to an embodiment of the present application;

[0026] FIG6 is another schematic diagram of a device for processing channel state information according to an embodiment of the present application;

[0027] FIG7 is a schematic diagram of the structure of a network device according to an embodiment of the present application;

[0028] FIG8 is a schematic diagram of a terminal device according to an embodiment of the present application. DETAILED DESCRIPTION

[0029] The foregoing and other features of the present application will become apparent from the following description with reference to the accompanying drawings. In the description and drawings, specific embodiments of the present application are disclosed, which illustrate some embodiments in which the principles of the present application can be employed. 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 falling within the scope of the appended claims. Various embodiments of the present application are described below with reference to the accompanying drawings. These embodiments are merely illustrative and are not intended to limit the present application.

[0030] 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.

[0031] 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.

[0032] 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.

[0033] 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), 6G and future communications, etc., and / or other currently known or future developed communication protocols.

[0034] 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 to the terminal device. Network devices may include, but are not limited to, the following devices: base station (BS), access point (AP), transmission reception point (TRP), broadcast transmitter, mobile management entity (MME), gateway, server, radio network controller (RNC), base station controller (BSC), etc.

[0035] Among them, base stations may include but are not limited to: NodeB (NodeB or NB), evolved NodeB (eNodeB or eNB), 5G base station (gNB), 6G base station and future base stations, etc., and may also include remote radio heads (RRH, Remote Radio Head), remote radio units (RRU, Remote Radio Unit), relays or low-power nodes (such as femto, pico, etc.). The term "base station" can include some or all of their functions. Each base station can provide communication coverage for a specific geographical area. The term "cell" can refer to a base station and / or its coverage area, depending on the context in which the term is used.

[0036] 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 user equipment may be fixed or mobile and may also be referred to as a mobile station (MS), terminal, user, subscriber station (SS), access terminal (AT), station, mobile terminal (MT), etc.

[0037] 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.

[0038] For another example, in scenarios such as the Internet of Things (IoT), the user equipment may also be a machine or device for monitoring or measurement, such as but not limited to: machine type communication (MTC) terminals, vehicle-mounted communication terminals, device-to-device (D2D) terminals, machine-to-machine (M2M) terminals, terminals that support sidelink communication, and the like.

[0039] 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 described 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 described above. Unless otherwise specified herein, "device" can refer to either network equipment or terminal equipment.

[0040] To avoid confusion, 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.

[0041] 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.

[0042] In addition, the uplink signal may include an uplink data signal and / or an uplink control signal and / or a PRACH and / or an SRS (sounding reference signal), etc., which may also be referred to as an uplink transmission (UL transmission) or an uplink information or an uplink channel. Sending / receiving an uplink transmission on an uplink resource may be understood as sending / receiving the uplink transmission using the uplink resource. The downlink signal may include a downlink data signal and / or a downlink control signal and / or a synchronization signal (SS, such as PSS / SSS) and / or a broadcast channel (PBCH) and / or an SSB (SS / PBCH block, including PSS, SSS and PBCH and its DMRS) and / or a CSI-RS, etc., which may also be referred to as a downlink transmission (DL transmission) or a downlink information or a downlink channel. Sending / receiving a downlink transmission on a downlink resource may be understood as sending / receiving the downlink transmission using the downlink resource.

[0043] In an embodiment of the present application, high-layer signaling may be, for example, radio resource control (RRC) signaling; RRC signaling includes, for example, an RRC message, for example, a broadcast / public RRC message / signaling (e.g., a master information block (MIB), system information (SI), a dedicated RRC message / signaling; or an RRC information element (RRC information element, RRC IE); or an information field included in an RRC message or an RRC information element (or an information field included in an information field). High-layer signaling may also be, for example, a medium access control layer (MAC) signaling; or a MAC control element (MAC control element, MAC CE). However, the present application is not limited thereto.

[0044] In the embodiments of the present application, "at least one" and "one or more than one" can be interchanged, "multiple" and "more than one" can be interchanged, and "multiple" means at least two, or two or more than two.

[0045] In the embodiments of the present application, predefined means specified in the protocol or determined according to the rules specified in the protocol, and no additional configuration is required. Configuration / indication refers to direct or indirect configuration / indication by the network device through high-layer signaling and / or physical layer signaling. Configuration / indication can be achieved by introducing high-layer parameters in high-layer signaling, and high-layer parameters refer to information fields (fields) and / or information elements / information units / information elements (IEs) in high-layer signaling. Physical layer signaling refers to, for example, control information (DCI) carried by the physical downlink control channel or control information carried by the sequence, but is not limited thereto.

[0046] For ease of description, the following description will be made using a base station as an example of an access network device. In the following description, "if ...", "under ..." and "when ..." can be used interchangeably without causing confusion.

[0047] The following describes the scenarios of the embodiments of the present application through examples, but the present application is not limited thereto.

[0048] FIG1 is a schematic diagram of a communication system according to an embodiment of the present application, schematically illustrating a situation taking a terminal device and a network device as an example. As shown in FIG1 , a communication system 100 may include a network device 101, a terminal device 102, and a terminal device 103. For simplicity, FIG1 illustrates only two terminal devices and one network device as an example, but the embodiments of the present application are not limited thereto.

[0049] In the embodiment of the present application, existing services or future services can be transmitted between the network device 101, the terminal device 102, and the terminal device 103. For example, these services may include, but are not limited to, enhanced mobile broadband (eMBB), massive machine type communication (mMTC), ultra-reliable and low-latency communication (URLLC), and related communications of terminal devices with reduced capabilities, etc.

[0050] Among them, terminal devices 102 and 103 can be in the RRC_IDLE state, the RRC_INACTIVE state, or the RRC_CONNECTED state. Terminal devices 102 and 103 can also communicate with network device 101. For example, taking terminal device 102 as an example, terminal device 102 can send data to network device 101 or retransmit data. Network device 101 can send a paging message to terminal device 102 or send data to terminal device 102, and terminal device 102 receives data sent by network device 101. In addition, different terminal devices can also communicate with each other. For example, terminal device 102 and terminal device 103 can exchange data.

[0051] It is worth noting that FIG1 shows that terminal device 102 and terminal device 103 are both within the coverage range of network device 101, but the present application is not limited thereto. Terminal device 102 and terminal device 103 may both be outside the coverage range of network device 101, or one of terminal device 102 and terminal device 103 may be within the coverage range of network device 101 and the other may be outside the coverage range of network device 101.

[0052] In embodiments of the present application, one or more AI / ML models may be configured and run in a network device and / or a terminal device. The AI / ML models may be used for various signal processing functions in wireless communications, such as CSI prediction, CSI compression, beamforming, positioning management, and the like; however, the present application is not limited thereto.

[0053] Regarding the CSI compression feedback sub-use case, the relevant content is shown in Table 1:

[0054] Table 1

[0055] Figure 2 is a schematic diagram of a TSF-AI / ML CSI compression feedback enhancement sub-use case in accordance with an embodiment of the present application. As shown in Figure 2, on the UE side, the CSI measurement result is subjected to matrix decomposition (e.g., SVD decomposition (singular value decomposition) or EVD decomposition (eigenvalue decomposition)) to obtain a feature vector, which is input to an encoder, which generates CSI feedback information. On the network side, the CSI feedback information sent by the UE is decoded by a decoder to generate reconstructed CSI.

[0056] In some embodiments, the encoder and decoder on the UE side may use AI / ML methods (e.g., RNN / LSTM / GRU cascade Transformer / CNN models). The AI / ML method may utilize time domain information (also referred to as historical CSI information, side information, or similar names) to assist in current CSI compression and / or decompression, aiming to achieve higher compression rates or higher feedback accuracy.

[0057] When using time-domain information for CSI compression and / or decompression, the availability and / or usability of time-domain information is easily affected by factors such as rank changes, CSI discard (e.g., CSI discard based on layer priority), and uplink control information (UCI) loss. If time-domain information is unavailable and / or unusable, the performance of the AI / ML model will deteriorate or even fail.

[0058] Furthermore, CSI time-domain correlation determines whether historical CSI information contributes to current CSI compression and / or decompression. Too low a correlation will result in invalid input to the AI / ML model, which will not only fail to improve CSI compression performance but may even be treated as noise by the AI / ML model, degrading CSI compression performance. Therefore, AI / ML is more suitable for scenarios with good CSI time-domain correlation, which typically corresponds to lower UE mobility or layers with lower rank values ​​and / or larger eigenvalues.

[0059] In the embodiments of the present application, CSI compression may also be referred to as "CSI encoding", "CSI generation" or other similar names, and the results of operations such as CSI compression, CSI encoding, or CSI generation may be referred to as CSI feedback information, CSI reporting information or other similar names.

[0060] In the embodiment of the present application, CSI decompression may also be referred to as "CSI decoding", "CSI reconstruction", "CSI recovery", "CSI reconstruction" or similar names.

[0061] In the embodiments of the present application, the AI / ML model may also be referred to as an AI / ML method, an AI / ML unit, an AI / ML function, or a similar AI / ML element. On the UE side, the AI / ML model may also be referred to as an encoder, a CSI generation part, or similar terms. On the network device side, the AI / ML model may also be referred to as a decoder, a CSI reconstruction part, or similar terms.

[0062] Embodiments of the first aspect

[0063] The present invention provides a method for processing channel state information, which is described from the perspective of a terminal device. FIG3 is a schematic diagram of the method for processing channel state information according to an embodiment of the present invention. As shown in FIG3 , the method includes:

[0064] 301: The terminal device receives CSI resource configuration information and CSI reporting configuration information from the network device; and

[0065] 302: The terminal device sends CSI feedback information according to the CSI resource configuration information and the CSI reporting configuration information, where the CSI feedback information includes information for instructing the network device to reconstruct the CSI.

[0066] It is worth noting that FIG3 above is merely a schematic illustration of an embodiment of the present application, and the present application is not limited thereto. For example, the execution order of the various operations may be appropriately adjusted, and other operations may be added or some operations may be reduced. Those skilled in the art may make appropriate modifications based on the above description, and are not limited to the description of FIG3 above.

[0067] According to the above embodiment, the terminal device receives CSI resource configuration information and CSI reporting configuration information from the network device, and sends CSI feedback information based on the CSI resource configuration information and the CSI reporting configuration information, wherein the CSI feedback information includes information for indicating the network device's CSI reconstruction operation. By including information for indicating the network device's CSI reconstruction operation in the CSI feedback information, the CSI reconstruction operation can be accurately performed regardless of whether the rank is fixed or the rank is adaptively caused to change the rank value, thereby helping to improve the throughput of the communication system.

[0068] In some embodiments, the UE may use CSI feedback information generated by a model (AI / ML model) based on artificial intelligence (AI) or machine learning (ML); the network device may use the AI / ML model to reconstruct the CSI. The AI / ML model on the UE side and the AI / ML model on the network side may correspond or match. The present application is not limited to this, and the AI / ML model may be used only on the UE side, or only on the network side. In the subsequent content, unless otherwise specified, the AI / ML model may be a model on the UE side or a model on the network side.

[0069] In some embodiments, the UE may report information related to its AI / ML model / function to the network device through terminal capability reporting, for example, including the capability of AI / ML-based CSI compression (for example, whether the AI / ML model can be used, and / or whether time domain information can be used, etc.).

[0070] The network device understands the terminal device's ability to perform CSI compression based on the AI / ML model based on the capability reporting information. As a result, the network device can configure CSI resources and CSI reporting for the terminal device based on the terminal device's capabilities.

[0071] In some embodiments, the CSI resource configuration information and / or the CSI reporting configuration information may be sent to the terminal device via RRC signaling. The present application is not limited thereto, and the above configuration information may also be sent via other means.

[0072] In some embodiments, the CSI resource configuration information can be used to configure one or more CSI-RS resources, and the period or time domain interval of the CSI-RS can be configured according to the information of the AI / ML model.

[0073] For example, the period or time interval of the CSI-RS can be configured to be the same as the period or time interval of the training data used by the AI / ML model during training, thereby ensuring the consistency of AI / ML model training and reasoning.

[0074] For example, the period of the training data used by the AI / ML model during training can be equal or equally spaced in the time domain. In this case, the CSI-RS resource configured by the CSI resource configuration information can be at least one of the following: periodic CSI-RS, semi-persistent CSI-RS, or aperiodic CSI-RS with equal intervals in the time domain (aperiodic CSI-RS burst). As a result, the period of the CSI measurement results of the terminal device is also equal or equally spaced in the time domain, thereby ensuring the consistency of AI / ML model training and reasoning.

[0075] In some embodiments, the CSI reporting configuration information can be used to instruct the terminal device to report a feature vector (also referred to as CSI) based on the terminal-side AI / ML model. In the CSI reporting configuration information, the network device can configure one or more CSI generation methods for the terminal device. The terminal device can select a corresponding CSI generation method from one or more CSI generation methods configured by the network device. The present application is not limited to this, and the CSI generation method on the terminal side may also be one or more predefined methods.

[0076] If a terminal device is configured or predefined with multiple CSI generation methods, the terminal device needs to indicate to the network device the CSI generation method to use. In an embodiment of the present application, the terminal device can indicate the CSI generation method to use or instruct the network device to perform a CSI reconstruction operation in the CSI feedback information sent to the network device. The CSI generation method on the UE side corresponds to the CSI reconstruction operation of the network device. This helps the network device reconstruct the CSI using the appropriate CSI reconstruction operation, thereby improving system throughput.

[0077] In some embodiments, on the terminal device side, the CSI feedback information may include information generated based on an artificial intelligence (AI) or machine learning (ML) model. For example, the precoding matrix information is compressed using the AI / ML model to generate a precoding matrix indication PMI. In order to distinguish it from the PMI generated without using the AI / ML model, in the embodiment of the present application, the PMI generated using the AI / ML model may be referred to as AI-PMI. However, the present application is not limited thereto, and the AI / ML model may be used to compress or process other CSI measurement results.

[0078] In some embodiments, on the UE side, the AI / ML model may generate the CSI feedback information using the first time domain information. Since the first time domain information is referenced when generating the CSI feedback information, compression efficiency and / or feedback accuracy can be improved. The present application is not limited thereto, and the AI / ML model may also not use the first time domain information to generate the CSI feedback information.

[0079] In some embodiments, the first time domain information may be related to the previous or previous CSI measurement results. As shown in Figure 2, the input of the AI / ML model is the first time domain information S1(td) (d is the time interval) and the CSI measurement obtained by the eigenvector V(t) (which is referred to as the CSI measurement result, for example, the terminal device receives the CSI-RS, performs channel estimation based on the CSI-RS, and obtains the eigenvector through matrix decomposition), and the output is the updated first time domain information S1(t) and CSI feedback information R(t). The first time domain information S1(t) is information related to the eigenvector V(t). Since the first time domain information S1(td) is also referenced when generating the first time domain information S1(t), the first time domain information S1(t) can also be related to the eigenvector V(td), or it can also be related to the eigenvector V(td)…V(ti*d), where i≥1.

[0080] In some embodiments, the first time domain information may include a previous CSI measurement result, or the first time domain information may include a previous plurality of CSI measurement results.

[0081] In some embodiments, the first time domain information may include information generated based on a previous CSI measurement result, or information generated based on multiple previous CSI measurement results.

[0082] In some embodiments, on the UE side, when the AI / ML model uses the first time domain information to generate CSI feedback information, the initially activated AI / ML model may generate CSI feedback information using the initial first time domain information.

[0083] The initial first time domain information may be predefined, configured by the network device, or generated based on the time domain information before the AI / ML model is initially activated. For example, the value of the initial first time domain information may be predefined, or the reset method of the initial first time domain information may be predefined. For another example, the network device may configure the value of the initial first time domain information, or the reset method of the initial first time domain information. For another example, before the AI / ML model is initially activated, the terminal device generates legacy CSI feedback information in a legacy manner, then the initial first time domain information may be generated based on the legacy CSI feedback information, and so on. The initial first time domain information on the terminal side and the initial second time domain information on the network side may correspond, for example, the values ​​of the two correspond, and / or the reset methods of the two correspond, and / or the methods of generating the initial first time domain information and the initial second time domain information based on the time domain information before the initial activation correspond.

[0084] In some embodiments, on the network device side, the network device's CSI reconstruction operation may include reconstructing the CSI based on an artificial intelligence (AI) or machine learning (ML) model. For example, the AI / ML model may be used to decompress the AI-PMI in the received CSI feedback information to generate precoding matrix information. However, the present application is not limited thereto, and the AI / ML model may be used to decompress or process other CSI measurement results.

[0085] In some embodiments, the AI / ML model may reconstruct the CSI using the second time domain information. The present application is not limited thereto, and the AI / ML model may also not reconstruct the CSI using the second time domain information.

[0086] In some embodiments, the second time domain information may be related to the previous or previous CSI feedback information. As shown in Figure 2, the input of the AI / ML model is the second time domain information S2(td) and the CSI feedback information R'(t) (the CSI feedback information R'(t) is, for example, the information after the CSI feedback information R(t) passes through the channel), and the output is the second time domain information S2(t) and the feature vector V'(t). The second time domain information S2(t) is information related to the CSI feedback information R'(t). Since the second time domain information S2(td) is also referenced when generating the second time domain information S2(t), the second time domain information S2(t) can also be related to R'(td), or, it can also be related to R'(td)…R'(ti*d), where i≥1.

[0087] In some embodiments, the second time domain information may include the previous CSI feedback information, or the second time domain information may include the previous CSI feedback information of multiple times.

[0088] In some embodiments, the second time domain information may include information generated based on the previous CSI feedback information, or information generated based on multiple previous CSI feedback information.

[0089] In some embodiments, when the AI / ML model reconstructs the CSI using the second time domain information, the initially activated AI / ML model may reconstruct the CSI using the initial second time domain information.

[0090] The initial second time domain information may be predefined or generated based on time domain information before the AI / ML model is initially activated. The initial second time domain information on the network side may correspond to the initial first time domain information on the terminal side.

[0091] In some embodiments, the CSI feedback information may indicate a CSI reconstruction operation on the network device side, either implicitly or explicitly. Taking a CSI reconstruction operation using second time domain information as an example, indicating the CSI reconstruction operation on the network device side may include indicating operations related to the second time domain information in the CSI reconstruction operation, for example, indicating whether the CSI reconstruction operation includes a reset operation on at least a portion of the second time domain information and / or a reset method for the reset operation.

[0092] In some embodiments, the CSI feedback information may include channel quality indication (CQI) information, precoding matrix indication (PMI) information, rank indication (RI) information, etc. Taking implicitly indicating the CSI reconstruction operation as an example, the RI information may be used to indicate the CSI reconstruction operation of the network device.

[0093] In some embodiments, RI information can be used to indicate operations related to the second time domain information during CSI reconstruction. For example, on the network side, if the RI information value differs from the RI information value in the previous CSI feedback information, the CSI reconstruction operation may include resetting at least a portion of the second time domain information, and the AI / ML model reconstructs the CSI using the reset second time domain information.

[0094] For another example, on the terminal side, when the value of the RI information is different from the value of the RI information in the previous CSI feedback information, the operation of generating the CSI feedback information may include resetting at least a portion of the first time domain information, and the AI / ML model generates the CSI feedback information using the reset first time domain information. The reset operation on the terminal side corresponds to the reset operation on the network side.

[0095] In some embodiments, on the network side, some or all layers of the second time domain information may be reset. In other words, the reset second time domain information includes time domain information of some or all layers. On the terminal side, some or all layers of the first time domain information may be reset. In other words, the reset first time domain information includes time domain information of some or all layers.

[0096] In some embodiments, the time domain information of different layers can be reset in the same or different ways. For example, the network device configures the same or different reset methods for the terminal device at different layers, and the terminal device uses the corresponding reset method at different layers; accordingly, the network device also uses the corresponding reset method at different layers.

[0097] On the terminal device side, the terminal device may reset at least a portion of the first time domain information according to a first reset method; correspondingly, on the network device side, the network device may reset at least a portion of the second time domain information according to the first reset method. The first reset method may include at least one of the following: resetting to a default value; or resetting to the most recent available historical time domain information.

[0098] In some embodiments, resetting to a default value may mean: when at least a portion of the time domain information is unavailable or unusable, setting at least a portion of the time domain information to a default value, such as all zeros. The present application is not limited thereto, and the default value may also be other values.

[0099] For example, on the terminal device side, when at least a portion of the first time domain information is unavailable or unusable, this portion of the first time domain information may be set as a default value on the terminal side.

[0100] On the network device side, when at least a portion of the second time domain information is unavailable or unusable, the portion of the second time domain information can be set as a default value on the network side. The default value on the network side and the default value on the terminal side can be the same or different.

[0101] For example, on the terminal side: at time t, rank = 2, the AI / ML model generates the first time domain information S1(t) of the second layer;

[0102] At time t+d, rank=1, the AI / ML model uses the information of the first layer in the first time domain information S1(t) to generate the first time domain information S1(t+d) of layer 1;

[0103] At time t+2d, rank = 2. Since the previous first time domain information S1(t+d) only has one layer, the second layer information of the first time domain information S1(t+d) cannot be obtained. The terminal device can set the second layer information of the first time domain information S1(t+d) to zero. The AI / ML model generates the two-layer first time domain information S1(t+2d) based on the first layer information of the first time domain information S1(t+d) and the all-zero second layer information.

[0104] On the network side: At time t, rank = 2, the AI / ML model generates the second time domain information S2(t) of the second layer;

[0105] At time t+d, rank=1, the AI / ML model uses the information of the first layer in the second time domain information S2(t) to generate the second time domain information S2(t+d) of layer 1;

[0106] At time t+2d, rank = 2. Since the previous second time domain information S2(t+d) only has one layer, the layer 2 information of the second time domain information S2(t+d) cannot be obtained. The network device can set the layer 2 information of the second time domain information S2(t+d) to zero. The two-layer second time domain information S2(t+2d) is generated based on the layer 1 information of the second time domain information S2(t+d) and the all-zero layer 2 information.

[0107] In some embodiments, resetting to the most recent available historical time domain information may mean that when at least a portion of the time domain information is unavailable or unusable, the portion of the time domain information may be set as the most recent available historical time domain information. For example, the most recent historical time domain information may be searched for by layer, and the most recent historical time domain information of the layer may be used as the time domain information of the layer.

[0108] For example, on the terminal device side, when at least a portion of the first time domain information is not obtainable or unavailable, this portion of the first time domain information may be set as the most recent obtainable first time domain information.

[0109] On the network device side, when at least a portion of the second time domain information is unavailable or unusable, this portion of the second time domain information may be set as the latest available second time domain information.

[0110] For example, on the terminal side: at time t, rank = 2, the AI / ML model generates the first time domain information S1(t) of the second layer;

[0111] At time t+d, rank=1, the AI / ML model uses the information of the first layer in the first time domain information S1(t) to generate the first time domain information S1(t+d) of layer 1;

[0112] At time t+2d, rank = 3. Since the previous first time domain information S1(t+d) only has one layer, the second and third layers of information of the first time domain information S1(t+d) cannot be obtained. For the second layer, the most recent first time domain information is the second layer of the first time domain information S1(t). For the third layer, the most recent first time domain information is not available. In this case, the AI / ML model can use the first layer information in the first time domain information S1(t+d), the second layer information of the first time domain information S1(t), and the all-zero third layer information to generate the three layers of first time domain information S1(t+2d).

[0113] On the network side: At time t, rank = 2, the AI / ML model generates the second time domain information S2(t) of the second layer;

[0114] At time t+d, rank=1, the AI / ML model uses the information of the first layer in the second time domain information S2(t) to generate the second time domain information S2(t+d) of layer 1;

[0115] At time t+2d, rank = 3. Since the previous second time domain information S2(t+d) only has one layer, the second and third layers of information of the second time domain information S1(t+d) cannot be obtained. For the second layer, the most recent second time domain information is the second layer of information of the second time domain information S2(t). For the third layer, the most recent second time domain information cannot be obtained. In this case, the AI / ML model can use the first layer of information in the second time domain information S2(t+d), the second layer of information of the second time domain information S2(t), and the all-zero third layer information to generate the three layers of second time domain information S2(t+2d).

[0116] The present application is not limited to this. When at least a part of the second time domain information is not obtainable or available, the entire second time domain information (for example, all layers) can also be set to the most recent second time domain information that can be obtained. For example, at time t, rank = 2, at time t+d, rank = 1; at time t+2d, rank = 2. Since the previous second time domain information S2(t+d) has only one layer, the second layer information of the second time domain information S1(t+d) cannot be obtained. In this case, the AI / ML model can use the information of the first and second layers in the second time domain information S2(t) to generate two layers of second time domain information S1(t+2d). Alternatively, the most recent second time domain information can also be obtained by other means. Similarly, when at least a part of the first time domain information is not obtainable or available, the entire first time domain information (for example, all layers) can also be set to the most recent first time domain information that can be obtained.

[0117] In some embodiments, the obtainable latest historical time domain information may include the obtainable latest historical time domain information within a time window.

[0118] For example, on the terminal device side, the available most recent first time domain information may include the available most recent first time domain information within the time window. In addition, if the most recent first time domain information does not exist within the time window, the AI / ML model may set the corresponding first time domain information to a default value.

[0119] On the network device side, the available most recent second time domain information may include the available most recent second time domain information within the time window. In addition, if the most recent second time domain information does not exist within the time window, the AI / ML model may set the corresponding second time domain information to a default value.

[0120] For example, the time window is two time intervals d before the current moment. On the terminal side: at time t, rank = 2, the AI / ML model generates the first time domain information S1(t) of the second layer;

[0121] At time t+d, rank=1, the AI / ML model uses the information of the first layer in the first time domain information S1(t) to generate the first time domain information S1(t+d) of layer 1;

[0122] At time t+2d, rank=1, the AI / ML model can use the information of the first layer in the first time domain information S1(t+d) to generate the first time domain information S1(t+2d) of layer 1;

[0123] At time t+3d, rank=2. For time t+3d, the time window is [t+d, t+3d]. Since there is no first time domain information of the second layer in the time window, the AI / ML model uses the first layer information in the first time domain information S1(t+2d) and the all-zero second layer information to generate the second layer of first time domain information S1(t+3d).

[0124] On the network side: At time t, rank = 2, the AI / ML model generates the second time domain information S2(t) of the second layer;

[0125] At time t+d, rank=1, the AI / ML model uses the information of the first layer in the second time domain information S2(t) to generate the second time domain information S2(t+d) of layer 1;

[0126] At time t+2d, rank=1, the AI / ML model can use the information of the first layer in the second time domain information S2(t+d) to generate the second time domain information S2(t+2d) of layer 1;

[0127] At time t+3d, rank=2. For time t+3d, the time window is [t+d, t+3d]. Since there is no second-layer second time domain information in the time window, the AI / ML model uses the first-layer information in the second time domain information S2(t+2d) and the all-zero second-layer information to generate the second-layer second time domain information S2(t+3d).

[0128] In some embodiments, the position of the time window and / or the size of the time window may be the same or different for different layers. The position of the time window and / or the size of the time window may be included in the CSI reporting configuration information.

[0129] In some embodiments, on the UE side, the first reset mode may be predefined or network configured. On the network side, the first reset mode may be predefined.

[0130] In some embodiments, for each layer of the second time domain information, the first reset method may include only one reset method. Thus, the terminal device does not need to indicate the first reset method to the network device, which can save signaling overhead, and the method is simple and easy to implement.

[0131] In some embodiments, taking the explicit indication of CSI reconstruction as an example, the network device may be instructed to reconstruct CSI by first indication information. For example, the CSI feedback information may include channel quality indication (CQI) information, precoding matrix indication (PMI) information, rank indication (RI) information, and the first indication information.

[0132] In some embodiments, the first indication information is used to indicate an operation related to the second time domain information in the CSI reconstruction operation. For example, the first indication information is used to indicate whether the CSI reconstruction operation includes a reset operation and / or a second reset mode of the reset operation on at least a portion of the second time domain information.

[0133] On the terminal side, the UE may generate the first indication information based on an operation related to the first time domain information in the operation of generating the CSI feedback information. For example, the first indication information may be generated based on whether generating the CSI feedback information includes a reset operation and / or a second reset method of the reset operation on at least a portion of the first time domain information. In other words, the reset operation of the first time domain information on the terminal side corresponds to the first indication information.

[0134] The CSI reconstruction operation indicated by the first indication information may include resetting at least a portion of the second time domain information. For example, resetting some or all layers of the second time domain information. In other words, the reset second time domain information includes time domain information of some or all layers.

[0135] The first indication information may be related to the rank value indicated by the rank indication information (referred to as RI value for short). For example, the first indication information may indicate a reset operation of a layer of unavailable second time domain information due to a change in the rank value. For example, the rank value indicated by the rank indication information changes from r to r+Δ, Δ>0, and the first indication information is used to indicate a reset operation of the second time domain information for layers r+1,…, layer r+Δ.

[0136] In some embodiments, when a network device configures a second reset mode for a terminal device, the presence or absence of first indication information may indicate whether the CSI reconstruction operation includes a reset operation for at least a portion of the second time domain information. For example, if the first indication information is included in the CSI feedback information, the CSI reconstruction operation includes a reset operation; otherwise, the CSI reconstruction operation does not include a reset operation, or vice versa. For another example, the first indication information may be a single-bit information. If the single-bit information has a value of 1, the CSI reconstruction operation includes a reset operation; otherwise, the CSI reconstruction operation does not include a reset operation, or vice versa.

[0137] In some embodiments, when the network device configures multiple second reset modes for the terminal device, the presence or absence of the first indication information can be used to indicate whether the CSI reconstruction operation includes a reset operation on at least a portion of the second time domain information; and the value of the first indication information can be used to indicate the mode of the reset operation (i.e., the second reset mode). For example, if the first indication information is included in the CSI feedback information, the CSI reconstruction operation includes a reset operation; otherwise, the CSI reconstruction operation does not include a reset operation. When the network device configures the terminal device with a second reset mode in M, the first indication information can be used through an M-bit bitmap or bits to indicate the specific second reset mode.

[0138] For another example, when the network device has configured multiple second reset methods for the terminal device, the value of the first indication information can be used to indicate whether the CSI reconstruction operation includes a reset operation on at least a part of the second time domain information and the reset operation method (i.e., the second reset method). For example, when the network device has configured M second reset methods for the terminal device, the above information can be indicated by an M-bit bitmap. For example, when the M-bit bitmap is all zero, no reset operation is required; when the mth (1≤m≤M) bit in the M-bit bitmap is 1, it indicates that the second reset method corresponding to the mth bit is used; and vice versa. Alternatively, it can also be done through bits to indicate whether a reset operation and a second reset mode are included.

[0139] In some embodiments, the first indication information may also be combined with the aforementioned RI information to indicate whether the CSI reconstruction operation includes a reset operation on at least a portion of the second time domain information and the manner of the reset operation (i.e., a second reset manner). For example, whether the reset operation is included is indicated by a change in the rank value in the RI information, and the specific second reset manner is indicated by the presence or absence of the first indication information and / or the value of the first indication information.

[0140] For example, when the value of the RI information is different from the value of the RI information in the previous CSI feedback information, the CSI reconstruction operation includes a reset operation; the first indication information is transmitted through an M-bit bitmap or The present application is not limited thereto, and the above information can also be indicated by a method.

[0141] The reporting of the first indication information may be determined based on the CSI reporting configuration information. For example, the second reset mode of the reset operation for the CSI reconfiguration operation includes one reset mode. In this case, the first indication information may be omitted. Since the second reset mode only includes one reset mode, the specific reset mode does not need to be indicated by the first indication information. Therefore, the first indication information may be omitted.

[0142] For another example, if only one layer of the CSI reconstruction operation utilizes the second time domain information during the reset operation, the first indication information may be omitted. For example, if the first layer of the CSI reconstruction operation utilizes the second time domain information during the reset operation, the second time domain information of the first layer can always be obtained / used regardless of how the rank value changes. Therefore, no reset operation is required, and the first indication information may be omitted.

[0143] In some embodiments, the second reset method includes at least one of the following: resetting to a default value; or resetting to the most recent available second time domain information. The relevant information is the same or similar to the aforementioned first reset method, and its content is incorporated herein and will not be further described.

[0144] In some embodiments, the time domain information of different layers may be reset in the same or different manners. For example, the network device may configure the same or different second reset manners for different layers, and / or the first indication information may indicate the same or different second reset manners for different layers of time domain information that need to be reset.

[0145] In some embodiments, the first indication information may be included in the first part (part 1) of the CSI feedback information so as to send the first indication information in a control channel. The present application is not limited thereto, and the first indication information may also be included in other parts of the CSI feedback information.

[0146] Below, the CSI processing method of an embodiment of the present application is exemplarily described by taking the use of an AI / ML model to compress the precoding matrix to generate an AI-PMI as an example.

[0147] In some embodiments, the AI / ML model may be one of the following types: a Rank specific AI / ML model; a Rank common AI / ML model; a Layer specific AI / ML model; a Layer specific and rank common AI / ML model; a Layer specific and rank specific AI / ML model; a Layer common AI / ML model; a Layer common and rank common AI / ML model; or a Layer common and rank specific AI / ML model.

[0148] In some embodiments, the AI / ML model on the terminal side can extract and utilize the time domain information on the terminal side through neural networks such as RNN / LSTM / GRU cascade Transformer / CNN and their deformations. When the time domain information needs to be reset, the time domain information is the time domain information reset according to the network configuration information; the AI / ML model on the network side can extract and utilize the time domain information on the network side through neural networks such as RNN / LSTM / GRU cascade Transformer / CNN and their deformations. When the time domain information needs to be reset, the time domain information is the time domain information reset according to the CSI feedback information.

[0149] The terminal device can receive CSI-RS for channel measurement and report CSI feedback information based on the received configuration information. The CSI feedback information may include: RI, CQI, AI-PMI, and first indication information. The AI-PMI is the output of the feature vector after being compressed by the terminal-side AI / ML model.

[0150] Example 1: The terminal device is configured with a method to reset the time domain information

[0151] When the terminal device is configured with a method for resetting time domain information, the first indication information may be the default none.

[0152] The network device receives the CSI feedback information reported by the terminal, recovers the feature vector through the network-side AI / ML model, and performs downlink PDSCH scheduling.

[0153] When the rank value indicated by the currently reported RI is r+Δ, where r is the last reported RI value and Δ>0, and the AI / ML model is layer-specific / common and rank-common, historical information related to layers r+1,…, and r+Δ on the network side is unavailable / unavailable. The terminal device needs to reset the time domain information for layers r+1,…, and r+Δ on the terminal side according to the configured operations, calculate the AI-PMI, and provide the CSI feedback information. The network device needs to reset the time domain information for layers r+1,…, and r+Δ on the network side according to the configured operations and restore the CSI.

[0154] When the rank value of the RI indicated in this report and the last report is r, the time domain information of layer 1 to layer r can be obtained / used without resetting the time domain information.

[0155] If the currently reported RI value is r-Δ, where r is the last reported RI value and Δ ≠ 0, and the AI / ML model is layer-specific / common and rank-specific, for example, the time domain information for layers 1 through r-Δ is unavailable. The terminal device must reset the time domain information for these layers according to the configured operation, calculate the AI-PMI, and provide the CSI feedback information. The network device must reset the time domain information for network-side layers 1, ..., and r-Δ according to the configured operation and restore the CSI.

[0156] Example 2: The terminal device is configured with multiple ways to reset the time domain information

[0157] The terminal receives configuration information from the network device, starts the terminal-side AI / ML model and provides CSI feedback. The terminal device determines the first indication information based on the change in the RI value.

[0158] When the RI value reported this time is r+Δ, where r is the last reported RI value and Δ>0, and the AI / ML model is a layer-specific / common and rank-common model, for example, historical related information of layers r+1,…, and r+Δ on the network side is unavailable / unavailable, and the network device needs to reset the time domain information of layers r+1,…, and r+Δ. The terminal device determines a method for resetting the time domain information based on its own situation (e.g., time domain correlation / mobility speed) and / or other information (e.g., CSI discard, UCI loss). When the time domain correlation is poor, the terminal device resets the time domain information on the terminal side to the terminal side default value, compresses the feature vector of the AI / ML model on the terminal side to AI-PMI, and instructs the network device to reset the network side time domain information to the network side default value through first indication information. When the time domain correlation is good, the terminal device resets the time domain information on the terminal side to the most recent historical time domain information available on the terminal side, compresses the feature vector of the AI / ML model on the terminal side to AI-PMI, and instructs the network device to reset the network side time domain information to the most recent historical time domain information available through first indication information.

[0159] When the RI values ​​reported this time and last time are both r, the time domain information of layer 1 to layer r can be obtained / used without resetting the time domain information.

[0160] When the RI value reported this time is r-Δ, where r is the last reported RI value and Δ≠0, and the AI / ML model is a layer-specific / common and rank-specific model, for example, the time domain information for layers 1 to min(r,r-Δ) is unavailable / unavailable, and the network device needs to reset the time domain information for these layers according to the configured operation method. When the time domain correlation is poor, the terminal device resets the time domain information of these layers on the terminal side to the terminal-side default value, compresses the feature vector of the AI / ML model on the terminal side to AI-PMI, and instructs the network device to reset the time domain information of these layers on the network side to the network-side default value through the first indication information. When the time domain correlation is good, the terminal device resets the time domain information of these layers on the terminal side to the most recent historical time domain information available on the terminal side, compresses the feature vector of the AI / ML model on the terminal side to AI-PMI, and instructs the network device to reset the time domain information of these layers on the network side to the most recent historical time domain information available through the first indication information.

[0161] In some embodiments, the AI / ML model on the terminal side may not utilize time domain correlation, and the AI / ML model on the network side may utilize time domain correlation. In this case, the terminal device does not need to perform any operation on the time domain information. However, the terminal device can still determine the operation of the network side time domain information based on RI changes, its own situation (for example, time domain correlation, mobile speed, etc.) and / or other information (for example, CSI discard, UCI loss, etc.) and feedback to the network side through the first indication information. The network device can operate the network side time domain information based on the first indication information. The present application is not limited to this. The network device can also determine the operation of the network side time domain information based on the reported RI changes, uplink SRS or reported TDCP (Time Domain Correlation Parameter, time domain correlation parameter). The first indication information reported by the terminal device is only for reference.

[0162] The above embodiments are merely exemplary of the present invention, but the present invention is not limited thereto. Appropriate modifications may be made based on the above embodiments. For example, the above embodiments may be used alone, or one or more of the above embodiments may be combined.

[0163] According to the above embodiment, the terminal device receives CSI resource configuration information and CSI reporting configuration information from the network device, and sends CSI feedback information based on the CSI resource configuration information and the CSI reporting configuration information, wherein the CSI feedback information includes information for indicating the network device's CSI reconstruction operation. By including information for indicating the network device's CSI reconstruction operation in the CSI feedback information, the CSI reconstruction operation can be accurately performed regardless of whether the rank is fixed or the rank is adaptively caused to change the rank value, thereby helping to improve the throughput of the communication system.

[0164] Embodiments of the second aspect

[0165] The embodiment of the present application provides a method for processing channel state information, which is described from the perspective of a network device. The embodiment of the second aspect can be combined with the embodiment of the first aspect or implemented separately, and the same contents as the embodiment of the first aspect will not be repeated.

[0166] FIG4 is another schematic diagram of a method for processing channel state information according to an embodiment of the present application. As shown in FIG4 , the method includes:

[0167] 401: The network device sends CSI resource configuration information and CSI reporting configuration information to the terminal device; and

[0168] 402. The network device receives CSI feedback information sent by the terminal device, where the CSI feedback information includes information for instructing the network device to reconstruct the CSI.

[0169] In some embodiments, the CSI feedback information includes information generated based on an artificial intelligence (AI) or machine learning (ML) model.

[0170] In some embodiments, the model generates the CSI feedback information using first time domain information.

[0171] In some embodiments, the first time domain information is related to a previous CSI measurement result or results of a previous plurality of times.

[0172] In some embodiments, the first time domain information includes a previous CSI measurement result or results of multiple previous measurements; and / or the first time domain information includes information generated based on the previous CSI measurement result or results of multiple previous measurements.

[0173] In some embodiments, the terminal device generates the CSI feedback information corresponding to the network device's CSI reconstruction operation. For example, the terminal device's operation on the first time domain information corresponds to the network device's operation on the second time domain information.

[0174] In some embodiments, the initially activated model generates the CSI feedback information using initial first time domain information.

[0175] In some embodiments, the initial first time domain information is predefined, or configured by a network device, or generated according to time domain information before the model is initially activated.

[0176] In some embodiments, the CSI reconstruction operation of the network device includes reconstructing the CSI based on an artificial intelligence (AI) or machine learning (ML) model.

[0177] In some embodiments, the model reconstructs the CSI using second time domain information.

[0178] In some embodiments, the second time domain information is related to the previous CSI feedback information or the previous multiple CSI feedback information.

[0179] In some embodiments, the second time domain information includes the previous CSI feedback information or multiple previous CSI feedback information; and / or the second time domain information includes information generated based on the previous CSI feedback information or multiple previous CSI feedback information.

[0180] In some embodiments, the initially activated model reconstructs the CSI using initial second time domain information.

[0181] In some embodiments, the initial second time domain information is predefined or generated according to time domain information before the model is initially activated.

[0182] In some embodiments, the CSI feedback information includes rank indication (RI) information, and the RI information is used to indicate the CSI reconstruction operation.

[0183] In some embodiments, the RI information is used to indicate an operation related to the second time domain information in the CSI reconstruction operation.

[0184] In some embodiments, the value of the RI information is different from the value of the RI information in the previous CSI feedback information, and the CSI reconstruction operation includes resetting at least a portion of the second time domain information.

[0185] In some embodiments, the resetting operation includes resetting at least a portion of the second time domain information according to a first resetting manner.

[0186] In some embodiments, the first reset mode is predefined.

[0187] In some embodiments, the first reset method includes 1 reset method.

[0188] In some embodiments, the reset second time domain information includes time domain information of part or all layers.

[0189] In some embodiments, temporal information of different layers is reset in the same or different ways.

[0190] In some embodiments, the CSI feedback information includes first indication information, and the first indication information is used to indicate the CSI reconstruction operation.

[0191] In some embodiments, the first indication information is used to indicate an operation related to the second time domain information in the CSI reconstruction operation.

[0192] In some embodiments, the first indication information is used to indicate whether the CSI reconstruction operation includes a reset operation on at least a portion of the second time domain information and / or a second reset mode of the reset operation.

[0193] In some embodiments, the reset second time domain information includes time domain information of part or all layers.

[0194] In some embodiments, temporal information of different layers is reset in the same or different ways.

[0195] In some embodiments, the second resetting manner includes at least one of the following: resetting to a default value; or resetting to the most recent second time domain information available.

[0196] In some embodiments, the latest obtainable historical second time domain information includes the latest obtainable historical second time domain information within a time window.

[0197] In some embodiments, for different layers, the position of the time window and / or the size of the time window are the same or different.

[0198] In some embodiments, the position of the time window and / or the size of the time window are included in the CSI reporting configuration information.

[0199] In some embodiments, the first indication information is related to a value of rank indication information.

[0200] In some embodiments, the value of the rank indication information changes from r to r+Δ, Δ>0, and the first indication information is used to indicate a reset operation of the second time domain information about layers r+1, ..., layer r+Δ.

[0201] In some embodiments, the reporting of the first indication information is determined according to the CSI reporting configuration information.

[0202] In some embodiments, the second reset mode of the reset operation of the reconstructed CSI operation includes one reset mode, and the first indication information is default; and / or the reset operation of the reconstructed CSI operation only utilizes one layer of the second time domain information, and the first indication information is default.

[0203] In some embodiments, the first indication information is included in the first part of the CSI feedback information.

[0204] In some embodiments, the CSI resource configuration information is used to configure one or more CSI-RS resources.

[0205] In some embodiments, the CSI-RS resource includes at least one of the following: periodic CSI-RS; semi-persistent CSI-RS; or aperiodic CSI-RS bursts equally spaced in time domain.

[0206] Regarding the specific actions in operations 401 and 402, the specific content of CSI resource configuration information, CSI reporting configuration information, CSI feedback information, etc., as well as other behaviors of the network device or other information received / sent, please refer to the records in the embodiment of the first aspect, and no further description will be given here.

[0207] The above embodiments are merely exemplary of the present invention, but the present invention is not limited thereto. Appropriate modifications may be made based on the above embodiments. For example, the above embodiments may be used alone, or one or more of the above embodiments may be combined.

[0208] According to the above embodiment, the network device sends CSI resource configuration information and CSI reporting configuration information to the terminal device, and receives CSI feedback information sent by the terminal device, wherein the CSI feedback information includes information for instructing the network device to reconstruct the CSI operation. By including information for instructing the network device to reconstruct the CSI operation in the CSI feedback information, the CSI reconstruction operation can be accurately performed regardless of whether the rank is fixed or the rank value changes due to rank adaptation, which helps to improve the throughput of the communication system.

[0209] Embodiments of the third aspect

[0210] The embodiment of the present application provides a channel state information processing device. The device may be, for example, a terminal device, or one or more components or assemblies configured in the terminal device. The device corresponds to the embodiment of the first aspect, and the same contents as the embodiment of the first aspect are not repeated here.

[0211] FIG5 is a schematic diagram of a channel state information processing apparatus according to an embodiment of the present application. As shown in FIG5 , the channel state information processing apparatus 500 includes:

[0212] The receiving unit 501 receives CSI resource configuration information and CSI reporting configuration information from a network device; and

[0213] The sending unit 502 sends CSI feedback information according to the CSI resource configuration information and the CSI reporting configuration information, where the CSI feedback information includes information for instructing the network device to perform a CSI reconstruction operation.

[0214] In some embodiments, the CSI feedback information includes information generated based on an artificial intelligence (AI) or machine learning (ML) model.

[0215] In some embodiments, the model generates the CSI feedback information using first time domain information.

[0216] In some embodiments, when the RI changes, the model reconstructs the CSI using the reset first time domain information.

[0217] In some embodiments, the first time domain information is related to a previous CSI measurement result or results of a previous plurality of times.

[0218] In some embodiments, the first time domain information includes a previous CSI measurement result or results of multiple previous measurements; and / or the first time domain information includes information generated based on the previous CSI measurement result or results of multiple previous measurements.

[0219] In some embodiments, the terminal device generates the CSI feedback information corresponding to the network device's CSI reconstruction operation. For example, the terminal device's operation on the first time domain information corresponds to the network device's operation on the second time domain information.

[0220] In some embodiments, the operation of the terminal device generating the CSI feedback information is related to the value of rank indication RI information (for example, related to RI changes).

[0221] In some embodiments, the initially activated model generates the CSI feedback information using initial first time domain information.

[0222] In some embodiments, the initial first time domain information is predefined, or configured by a network device, or generated according to time domain information before the model is initially activated.

[0223] In some embodiments, the CSI reconstruction operation of the network device includes reconstructing the CSI based on an artificial intelligence (AI) or machine learning (ML) model.

[0224] In some embodiments, the model reconstructs the CSI using second time domain information.

[0225] In some embodiments, when the RI changes, the model reconstructs the CSI using reset second time domain information. In some embodiments, the second time domain information is related to the previous CSI feedback information or multiple previous CSI feedback information.

[0226] In some embodiments, the second time domain information includes the previous CSI feedback information or multiple previous CSI feedback information; and / or the second time domain information includes information generated based on the previous CSI feedback information or multiple previous CSI feedback information.

[0227] In some embodiments, the initially activated model reconstructs the CSI using initial second time domain information.

[0228] In some embodiments, the initial second time domain information is predefined or generated according to time domain information before the model is initially activated.

[0229] In some embodiments, the CSI feedback information includes rank indication (RI) information, and the RI information is used to indicate the CSI reconstruction operation.

[0230] In some embodiments, the RI information is used to indicate an operation related to the second time domain information in the CSI reconstruction operation.

[0231] In some embodiments, the value of the RI information is different from the value of the RI information in the previous CSI feedback information, and the CSI reconstruction operation includes resetting at least a portion of the second time domain information.

[0232] In some embodiments, the resetting operation includes resetting at least a portion of the second time domain information according to a first resetting manner.

[0233] In some embodiments, the first reset mode is predefined.

[0234] In some embodiments, the first reset method includes 1 reset method.

[0235] In some embodiments, the reset second time domain information includes time domain information of part or all layers.

[0236] In some embodiments, temporal information of different layers is reset in the same or different ways.

[0237] In some embodiments, the CSI feedback information includes first indication information, and the first indication information is used to indicate the CSI reconstruction operation.

[0238] In some embodiments, the operation of the terminal device to generate the CSI feedback information corresponds to the first indication information.

[0239] In some embodiments, the first indication information is used to indicate an operation related to the second time domain information in the CSI reconstruction operation.

[0240] In some embodiments, the first indication information is used to indicate whether the CSI reconstruction operation includes a reset operation on at least a portion of the second time domain information and / or a second reset mode of the reset operation.

[0241] In some embodiments, the reset second time domain information includes time domain information of part or all layers.

[0242] In some embodiments, temporal information of different layers is reset in the same or different ways.

[0243] In some embodiments, the second resetting manner includes at least one of the following: resetting to a default value; or resetting to the most recent second time domain information available.

[0244] In some embodiments, the latest obtainable historical second time domain information includes the latest obtainable historical second time domain information within a time window.

[0245] In some embodiments, for different layers, the position of the time window and / or the size of the time window are the same or different.

[0246] In some embodiments, the position of the time window and / or the size of the time window are included in the CSI reporting configuration information.

[0247] In some embodiments, the first indication information is related to a value of rank indication information.

[0248] In some embodiments, the value of the rank indication information changes from r to r+Δ, Δ>0, and the first indication information is used to indicate a reset operation of the second time domain information about layers r+1, ..., layer r+Δ.

[0249] In some embodiments, the reporting of the first indication information is determined according to the CSI reporting configuration information.

[0250] In some embodiments, the second reset mode of the reset operation of the reconstructed CSI operation includes one reset mode, and the first indication information is default; and / or the reset operation of the reconstructed CSI operation only utilizes one layer of the second time domain information, and the first indication information is default.

[0251] In some embodiments, the first indication information is included in the first part of the CSI feedback information.

[0252] In some embodiments, the CSI resource configuration information is used to configure one or more CSI-RS resources.

[0253] In some embodiments, the CSI-RS resource includes at least one of the following: periodic CSI-RS; semi-persistent CSI-RS; or aperiodic CSI-RS bursts equally spaced in time domain.

[0254] The above embodiments are merely exemplary of the present invention, but the present invention is not limited thereto. Appropriate modifications may be made based on the above embodiments. For example, the above embodiments may be used alone, or one or more of the above embodiments may be combined.

[0255] According to the above embodiment, the terminal device receives CSI resource configuration information and CSI reporting configuration information from the network device, and sends CSI feedback information based on the CSI resource configuration information and the CSI reporting configuration information, wherein the CSI feedback information includes information for indicating the network device's CSI reconstruction operation. By including information for indicating the network device's CSI reconstruction operation in the CSI feedback information, the CSI reconstruction operation can be accurately performed regardless of whether the rank is fixed or the rank is adaptively caused to change the rank value, thereby helping to improve the throughput of the communication system.

[0256] Embodiments of the fourth aspect

[0257] This embodiment of the present application provides a device for processing channel state information. The device may be, for example, a network device, or one or more components or assemblies configured on the network device. This device corresponds to the embodiment of the second aspect, and the contents identical to those of the embodiment of the second aspect are not repeated here.

[0258] FIG6 is another schematic diagram of a channel state information processing apparatus according to an embodiment of the present application. As shown in FIG6 , the channel state information processing apparatus 600 includes:

[0259] A sending unit 601, which sends CSI resource configuration information and CSI reporting configuration information to the terminal device; and

[0260] The receiving unit 602 receives CSI feedback information sent by the terminal device, where the CSI feedback information includes information for instructing the network device to reconstruct the CSI.

[0261] In some embodiments, the CSI feedback information includes information generated based on an artificial intelligence (AI) or machine learning (ML) model.

[0262] In some embodiments, the model generates the CSI feedback information using first time domain information.

[0263] In some embodiments, the first time domain information is related to a previous CSI measurement result or results of a previous plurality of times.

[0264] In some embodiments, the first time domain information includes a previous CSI measurement result or results of multiple previous measurements; and / or the first time domain information includes information generated based on the previous CSI measurement result or results of multiple previous measurements.

[0265] In some embodiments, the terminal device generates the CSI feedback information corresponding to the network device's CSI reconstruction operation. For example, the terminal device's operation on the first time domain information corresponds to the network device's operation on the second time domain information.

[0266] In some embodiments, the initially activated model generates the CSI feedback information using initial first time domain information.

[0267] In some embodiments, the initial first time domain information is predefined, or configured by a network device, or generated according to time domain information before the model is initially activated.

[0268] In some embodiments, the CSI reconstruction operation of the network device includes reconstructing the CSI based on an artificial intelligence (AI) or machine learning (ML) model.

[0269] In some embodiments, the model reconstructs the CSI using second time domain information.

[0270] In some embodiments, the second time domain information is related to the previous CSI feedback information or the previous multiple CSI feedback information.

[0271] In some embodiments, the second time domain information includes the previous CSI feedback information or multiple previous CSI feedback information; and / or the second time domain information includes information generated based on the previous CSI feedback information or multiple previous CSI feedback information.

[0272] In some embodiments, the initially activated model reconstructs the CSI using initial second time domain information.

[0273] In some embodiments, the initial second time domain information is predefined or generated according to time domain information before the model is initially activated.

[0274] In some embodiments, the CSI feedback information includes rank indication (RI) information, and the RI information is used to indicate the CSI reconstruction operation.

[0275] In some embodiments, the RI information is used to indicate an operation related to the second time domain information in the CSI reconstruction operation.

[0276] In some embodiments, the value of the RI information is different from the value of the RI information in the previous CSI feedback information, and the CSI reconstruction operation includes resetting at least a portion of the second time domain information.

[0277] In some embodiments, the resetting operation includes resetting at least a portion of the second time domain information according to a first resetting manner.

[0278] In some embodiments, the first reset mode is predefined.

[0279] In some embodiments, the first reset method includes 1 reset method.

[0280] In some embodiments, the reset second time domain information includes time domain information of part or all layers.

[0281] In some embodiments, temporal information of different layers is reset in the same or different ways.

[0282] In some embodiments, the CSI feedback information includes first indication information, and the first indication information is used to indicate the CSI reconstruction operation.

[0283] In some embodiments, the first indication information is used to indicate an operation related to the second time domain information in the CSI reconstruction operation.

[0284] In some embodiments, the first indication information is used to indicate whether the CSI reconstruction operation includes a reset operation on at least a portion of the second time domain information and / or a second reset mode of the reset operation.

[0285] In some embodiments, the reset second time domain information includes time domain information of part or all layers.

[0286] In some embodiments, temporal information of different layers is reset in the same or different ways.

[0287] In some embodiments, the second resetting manner includes at least one of the following: resetting to a default value; or resetting to the most recent second time domain information available.

[0288] In some embodiments, the latest obtainable historical second time domain information includes the latest obtainable historical second time domain information within a time window.

[0289] In some embodiments, for different layers, the position of the time window and / or the size of the time window are the same or different.

[0290] In some embodiments, the position of the time window and / or the size of the time window are included in the CSI reporting configuration information.

[0291] In some embodiments, the first indication information is related to a value of rank indication information.

[0292] In some embodiments, the value of the rank indication information changes from r to r+Δ, Δ>0, and the first indication information is used to indicate a reset operation of the second time domain information about layers r+1, ..., layer r+Δ.

[0293] In some embodiments, the reporting of the first indication information is determined according to the CSI reporting configuration information.

[0294] In some embodiments, the second reset mode of the reset operation of the reconstructed CSI operation includes one reset mode, and the first indication information is default; and / or the reset operation of the reconstructed CSI operation only utilizes one layer of the second time domain information, and the first indication information is default.

[0295] In some embodiments, the first indication information is included in the first part of the CSI feedback information.

[0296] In some embodiments, the CSI resource configuration information is used to configure one or more CSI-RS resources.

[0297] In some embodiments, the CSI-RS resource includes at least one of the following: periodic CSI-RS; semi-persistent CSI-RS; or aperiodic CSI-RS bursts equally spaced in time domain.

[0298] The above embodiments are merely exemplary of the present invention, but the present invention is not limited thereto. Appropriate modifications may be made based on the above embodiments. For example, the above embodiments may be used alone, or one or more of the above embodiments may be combined.

[0299] According to the above embodiment, the network device sends CSI resource configuration information and CSI reporting configuration information to the terminal device, and receives CSI feedback information sent by the terminal device, wherein the CSI feedback information includes information for instructing the network device to reconstruct the CSI operation. By including information for instructing the network device to reconstruct the CSI operation in the CSI feedback information, the CSI reconstruction operation can be accurately performed regardless of whether the rank is fixed or the rank value changes due to rank adaptation, which helps to improve the throughput of the communication system.

[0300] Embodiments of the fifth aspect

[0301] An embodiment of the present application also provides a communication system, and reference may be made to FIG1 . The contents that are the same as those in the embodiments of the first to fourth aspects will not be repeated.

[0302] In some implementations, the communication system 100 may include at least: a network device and a terminal device. The network device sends CSI resource configuration information and CSI reporting configuration information to the terminal device, and receives CSI feedback information sent by the terminal device. The terminal device receives the CSI resource configuration information and the CSI reporting configuration information, and sends CSI feedback information based on the CSI resource configuration information and the CSI reporting configuration information, where the CSI feedback information includes information for instructing the network device to perform a CSI reconstruction operation.

[0303] An embodiment of the present application further provides a network device, which may be, for example, a base station, but the present application is not limited thereto and may also be other network devices.

[0304] Figure 7 is a schematic diagram illustrating the structure of a network device according to an embodiment of the present application. As shown in Figure 7, network device 700 may include a processor 710 (e.g., a central processing unit (CPU)) and a memory 720; memory 720 is coupled to processor 710. Memory 720 may store various data and may also store an information processing program 730, which is executed under the control of processor 710.

[0305] For example, the processor 710 may be configured to execute a program to implement operations of the network device in the method according to the embodiment of the second aspect. For example, the processor 710 may be configured to perform the following control: the network device sends CSI resource configuration information and CSI reporting configuration information to the terminal device, and receives CSI feedback information sent by the terminal device, where the CSI feedback information includes information for instructing the network device to perform a CSI reconstruction operation.

[0306] In addition, as shown in FIG7 , network device 700 may further include: a transceiver (receiver and / or transmitter) 740 and an antenna 750, etc.; wherein, the functions of the above components are similar to those in the related art and are not described here in detail. It is worth noting that network device 700 does not necessarily include all the components shown in FIG7 ; in addition, network device 700 may also include components not shown in FIG7 , and reference may be made to the related art for details.

[0307] The embodiment of the present application also provides a terminal device, but the present application is not limited thereto and may also be other devices.

[0308] Figure 8 is a schematic diagram of a terminal device according to an embodiment of the present application. As shown in Figure 8 , terminal device 800 may include a processor 810 and a memory 820. Memory 820 stores data and programs and is coupled to processor 810. 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 or other functions.

[0309] For example, the processor 810 may be configured to execute a program to implement the method according to the embodiment of the first aspect. For example, the processor 810 may be configured to perform the following control: the terminal device receives the CSI resource configuration information and the CSI reporting configuration information, and sends CSI feedback information according to the CSI resource configuration information and the CSI reporting configuration information, where the CSI feedback information includes information for instructing the network device to perform a CSI reconstruction operation.

[0310] As shown in Figure 8 , the terminal device 800 may further include: a communication module 830, an input unit 840, a display 850, and a power supply 860. The functions of these components are similar to those in the related art and are not described in detail here. It is worth noting that the terminal device 800 does not necessarily include all of the components shown in Figure 8 , and the above components are not essential. Furthermore, the terminal device 800 may also include components not shown in Figure 8 , for which reference may be made to the related art.

[0311] An embodiment of the present application further provides a computer program, wherein when the program is executed in a terminal device, the program causes the terminal device to execute the method described in the embodiment of the first aspect.

[0312] An embodiment of the present application further provides a storage medium storing a computer program, wherein the computer program enables a terminal device to execute the method described in the embodiment of the first aspect.

[0313] An embodiment of the present application further provides a computer program, wherein when the program is executed in a network device, the program causes the network device to execute the method described in the embodiment of the second aspect.

[0314] An embodiment of the present application further provides a storage medium storing a computer program, wherein the computer program enables a network device to execute the method described in the embodiment of the second aspect.

[0315] 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.

[0316] 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).

[0317] 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.

[0318] 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.

[0319] 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.

[0320] Regarding the implementation methods including the above embodiments, the following additional notes are also disclosed:

[0321] 1. A method for processing channel state information (CSI), applied to a terminal device, wherein the method comprises:

[0322] The terminal device receives CSI resource configuration information and CSI reporting configuration information from the network device; and

[0323] The terminal device sends CSI feedback information according to the CSI resource configuration information and the CSI reporting configuration information, where the CSI feedback information includes information for instructing the network device to reconstruct the CSI operation.

[0324] 2. The method according to the preceding and following supplementary notes, wherein:

[0325] The first time domain information on the terminal side includes the previous CSI measurement results or the previous multiple CSI measurement results; and / or

[0326] The first time domain information includes information generated according to the previous CSI measurement results or the previous multiple CSI measurement results.

[0327] 3. The method according to the aforementioned note, wherein:

[0328] The operation of the terminal device to generate the CSI feedback information corresponds to the CSI reconstruction operation of the network device.

[0329] 4. The method according to the preceding and following supplementary notes, wherein:

[0330] The initially activated model generates the CSI feedback information using initial first time domain information;

[0331] The initial first time domain information is predefined, or configured by a network device, or generated according to time domain information before the model is initially activated.

[0332] 5. The method according to the preceding and following supplementary notes, wherein:

[0333] The second time domain information on the network side includes the previous CSI feedback information or the previous multiple CSI feedback information; and / or

[0334] The second time domain information includes information generated according to the previous CSI feedback information or the previous multiple CSI feedback information.

[0335] 6. The method according to the preceding and following supplementary notes, wherein:

[0336] The initially activated model reconstructs the CSI using initial second time domain information;

[0337] The initial second time domain information is predefined or generated according to time domain information before the model is initially activated.

[0338] 7. The method according to the preceding and following supplementary notes, wherein:

[0339] The reset second time domain information includes time domain information of part or all layers;

[0340] The temporal information of different layers may be reset in the same or different ways.

[0341] 8. The method according to the preceding and following supplementary notes, wherein:

[0342] For different layers, the position of the time window and / or the size of the time window are the same or different;

[0343] The position of the time window and / or the size of the time window are included in the CSI reporting configuration information.

[0344] 9. The method according to the preceding and following supplementary notes, wherein:

[0345] The value of the rank indication information changes from r to r+Δ, Δ>0, and the first indication information is used to indicate a reset operation of the second time domain information of layers r+1, ..., layer r+Δ;

[0346] The second resetting mode of the resetting operation of the reconstructing CSI operation includes one resetting mode, and the first indication information is default; and / or

[0347] The reset operation of the CSI reconstruction operation uses the second time domain information for only one layer, and the first indication information is defaulted;

[0348] The first indication information is included in the first part of the CSI feedback information.

[0349] 10. The method according to the preceding and following supplementary notes, wherein:

[0350] The CSI resource configuration information is used to configure one or more CSI-RS resources;

[0351] The CSI-RS resource includes at least one of the following:

[0352] periodic CSI-RS;

[0353] semi-persistent CSI-RS; or

[0354] Aperiodic CSI-RS bursts are equally spaced in time domain.

Claims

1. A channel state information (CSI) processing device, configured in a terminal device, wherein: The device comprises: a receiving unit, configured to receive CSI resource configuration information and CSI reporting configuration information from a network device; and A sending unit is configured to send CSI feedback information according to the CSI resource configuration information and the CSI reporting configuration information, wherein the CSI feedback information includes information for instructing the network device to perform a CSI reconstruction operation.

2. The device according to claim 1, wherein The CSI feedback information includes information generated based on an artificial intelligence or machine learning model.

3. The device according to claim 2, wherein The model generates the CSI feedback information using first time domain information.

4. The device according to claim 3, wherein The first time domain information is related to the previous CSI measurement result or results of the previous multiple times; and / or The related operation of the terminal device on the first time domain information is related to rank indication (RI) information; and / or The related operation of the terminal device on the first time domain information corresponds to the related operation of the network device on the second time domain information; and / or In a case where the value of the RI information is different from the value of the RI information in the previous CSI feedback information, the first time domain information is the reset first time domain information.

5. The device according to claim 1, wherein The CSI reconstruction operation of the network device includes reconstructing the CSI based on an artificial intelligence or machine learning model.

6. The device according to claim 5, wherein The model reconstructs the CSI using second time domain information.

7. The device according to claim 6, wherein The second time domain information is related to the previous CSI feedback information or the previous multiple CSI feedback information.

8. The device according to claim 1, wherein The CSI feedback information includes rank indication (RI) information, and the RI information is used to indicate the CSI reconstruction operation.

9. The device according to claim 8, wherein The RI information is used to indicate an operation related to the second time domain information in the CSI reconstruction operation.

10. The device according to claim 9, wherein A value of the RI information is different from a value of the RI information in the previous CSI feedback information, and the CSI reconstruction operation includes resetting at least a portion of the second time domain information; and / or The value of the RI information is different from the value of the RI information in the previous CSI feedback information, and the second time domain information is reset second time domain information.

11. The device according to claim 10, wherein The resetting operation includes resetting at least a portion of the second time domain information according to a first resetting manner.

12. The device according to claim 11, wherein The first reset mode is predefined; and / or The first reset method includes 1 reset method.

13. The device according to claim 1, wherein The CSI feedback information includes first indication information, where the first indication information is used to indicate the CSI reconstruction operation.

14. The device according to claim 13, wherein The first indication information is used to indicate an operation related to the second time domain information in the CSI reconstruction operation; and / or The first indication information corresponds to an operation related to the first time domain information in the operation of generating CSI feedback information of the terminal device.

15. The device according to claim 14, wherein The first indication information is used to indicate whether the CSI reconstruction operation includes a reset operation on at least a portion of the second time domain information and / or a second reset mode of the reset operation.

16. The device according to claim 15, wherein The second reset mode includes at least one of the following: Reset to default values; or Reset to the most recent available second time domain information.

17. The device according to claim 16, wherein The latest obtainable second time domain information includes the latest obtainable second time domain information within a time window.

18. The device according to claim 13, wherein The first indication information is related to a value of the rank indication information; and / or The reporting of the first indication information is determined according to the CSI reporting configuration information.

19. A channel state information (CSI) processing device, configured in a network device, wherein: The device comprises: a sending unit, configured to send CSI resource configuration information and CSI reporting configuration information to a terminal device; and A receiving unit receives CSI feedback information sent by the terminal device, where the CSI feedback information includes information for instructing the network device to reconstruct the CSI operation.

20. A communication system, wherein: The system comprises: A network device that sends CSI resource configuration information and CSI reporting configuration information to a terminal device, and receives CSI feedback information sent by the terminal device; and A terminal device receives the CSI resource configuration information and the CSI reporting configuration information, and sends CSI feedback information according to the CSI resource configuration information and the CSI reporting configuration information, wherein the CSI feedback information includes information for instructing the network device to reconstruct the CSI operation.

Images