Channel state information enhancement method, apparatus, and communication system

Abstract

Embodiments of the present application provide a channel state information enhancement method, an apparatus, and a communication system. The apparatus is applied to a terminal device, and the apparatus comprises a first processor. The first processor is configured with an artificial intelligence function or model for performing channel state information compression; and the first processor is configured to perform at least one of the following operations: compression of channel state information in the spatial and frequency domains; compression of channel state information in the spatial, frequency, and time domains; and prediction and compression of channel state information.

Description

Enhanced method, apparatus and communication system for channel state information TECHNICAL FIELD

[0001] Embodiments of the present application relate to the field of communication technology. BACKGROUND

[0002] In 3GPP Release 18, the application of Artificial Intelligence (AI) and Machine Learning (ML) functions or models to the air interface is studied, including the application of AI / ML functions or models to Channel State Information (CSI) feedback compression. AI / ML-based CSI feedback compression adopts a two-sided model, i.e., AI / ML functions or models are located at the terminal device (UE) side and the network (NW) side (i.e., gNB side). In Rel-18, AI / ML-based feedback compression compresses CSI in the spatial frequency domain (SF-AI / ML CSI compression).

[0003] For the two-sided model, at the UE side, the UE performs measurements on reference signals (e.g., Channel State Information-Reference Signal, CSI-RS) to obtain a wireless channel; then, the UE can further obtain a feature vector of the wireless channel, and the feature vector will be used as the input of the AI / ML function or model at the UE side, i.e., the input of the encoder, to compress the CSI; then, the UE reports or sends the output of the encoder as the CSI feedback to the gNB; the received CSI feedback is used as the input of the AI / ML function or model at the gNB side, i.e., the input of the decoder; after decompression using the decoder, the decoder outputs the reconstructed CSI. This scenario of compressing channel state information in the spatial and frequency domains is referred to as Case-0.

[0004] In the Release 19 stage, the AI / ML-based CSI compression feedback enhancement sub-use case in the space-time-frequency domain (TSF-AI / ML CSI compression) is further studied. This sub-use case uses historical CSI information to help the CSI compression at the current time through AI / ML methods (e.g., RNN / GRU / LSTM models), aiming to obtain a lower compression rate or a higher feedback accuracy.

[0005] It should be noted that the above introduction to the technical background is only for the convenience of clearly and completely describing the technical scheme of the present application and facilitating the understanding of those skilled in the art. The above technical scheme cannot be considered as known to those skilled in the art only because it is described in the background section of the present application.

[0006] SUMMARY

[0007] The operations for AI / ML functions or models can include: inference, performance monitoring, and training data collection for artificial intelligence functions or models.

[0008] In each of the above operations, appropriate configurations are needed. The inventors have found that there is no uniform provision for some configurations in the above operations, for example:

[0009] For inference, for prediction and compression of channel state information (i.e., Case-3), the number of reported channel quality indicators / rank indicators (CQI / RI) needs to be determined, and for compression of channel state information in space, frequency and time domains (i.e., Case-2), the loss of uplink control information needs to be notified to the terminal device by the network device;

[0010] For performance monitoring, for Case-3, it is necessary to define how to configure the reference signal;

[0011] For training data collection, it is necessary to define how to send the training data, and in addition, if the reference signal is used for training data collection and inference, it is necessary to define how to report the channel quality indicator / rank indicator (CQI / RI).

[0012] To solve one or more of the above problems, the embodiments of the present application provide a channel state information enhancement method, device and communication system.

[0013] According to an aspect of the embodiments of the present application, a channel state information enhancement device is provided, applied to a terminal device, the device comprising a first processor:

[0014] The first processor is configured to perform an artificial intelligence function or model for channel state information compression; and

[0015] The first processor is configured to perform at least one of the following operations:

[0016] Compression of channel state information in space and frequency domains;

[0017] Compression of channel state information in space, frequency and time domains;

[0018] Prediction and compression of channel state information.

[0019] According to another aspect of embodiments of the present application, there is provided an apparatus for enhancing channel state information, applied to a network device, the apparatus comprising a second processor configured to:

[0020] configure an artificial intelligence function or model for channel state information compression for a terminal device; and

[0021] configure the terminal device to perform at least one of the following operations:

[0022] compression of channel state information in spatial domain and frequency domain;

[0023] compression of channel state information in spatial domain, frequency domain and time domain;

[0024] Prediction and compression of channel state information.

[0025] One of the beneficial effects of embodiments of the present application is that the configurations corresponding to different operations of the terminal device are explicitly defined, and the terminal device and the network device can have a unified understanding of the configurations of the corresponding operations.

[0026] Specific embodiments of the application are disclosed herein, and represented in the accompanying drawings, illustrating the principles of the application in a manner that can be employed by those skilled in the art. It is understood that the embodiments of the application are not limited in scope to the specific embodiments disclosed. Many modifications, variations, and equivalents of the disclosed embodiments are possible in the scope of the spirit and the terms of the claims.

[0027] Features described and / or illustrated with respect to one implementation can be used in the same or similar manner in one or more other implementations, in combination with other features in the other implementations, or in place of other features in the other implementations.

[0028] It should be emphasized that the term "comprises / comprising" when used in this text is taken to mean that the features, integers, steps or components referred to can be present or be added, but does not preclude one or more other features, integers, steps or components being present or added. BRIEF DESCRIPTION OF DRAWINGS

[0029] Elements and features of one or more embodiments of the application described in one figure or in one part of a figure can be combined with elements and features of one or more other figures or parts of figures in the same or another embodiment. Also, in the drawings, like reference numerals indicate corresponding parts throughout the several views, and can be used to indicate corresponding components in more than one embodiment.

[0030] Figure 1 is a schematic illustration of a communication system according to embodiments of the present application;

[0031] FIG. 2 is a schematic diagram of AI / ML based CSI compression (TSF-AI / ML CSI compression) feedback enhancement in space-time-frequency domain;

[0032] FIG. 3 is another schematic diagram of AI / ML based CSI compression (TSF-AI / ML CSI compression) feedback enhancement in space-time-frequency domain;

[0033] FIG. 4 is yet another schematic diagram of AI / ML based CSI compression (TSF-AI / ML CSI compression) feedback enhancement in space-time-frequency domain;

[0034] FIG. 5 is a schematic diagram of CSI compression plus prediction;

[0035] FIG. 6 is a schematic diagram of a method for enhancing channel state information according to an embodiment of the present application;

[0036] FIG. 7 is a schematic diagram of transmitting channel quality indication or rank indication (CQI / RI) in a prediction window;

[0037] FIG. 8 is another schematic diagram of transmitting channel quality indication or rank indication (CQI / RI) in a prediction window;

[0038] FIG. 9 is yet another schematic diagram of transmitting channel quality indication or rank indication (CQI / RI) in a prediction window;

[0039] FIG. 10 is a schematic diagram of calculating performance indicators;

[0040] FIG. 11 is another schematic diagram of calculating performance indicators;

[0041] FIG. 12 is a schematic diagram of a method for enhancing channel state information according to an embodiment of the second aspect of the present application;

[0042] FIG. 13 is a schematic diagram of an apparatus for enhancing channel state information according to an embodiment of the present application;

[0043] FIG. 14 is a schematic diagram of an apparatus for enhancing channel state information according to an embodiment of the present application;

[0044] FIG. 15 is a schematic block diagram of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0045] The foregoing and other features of the present application will become apparent to those skilled in the art upon consideration of the following description of specific embodiments of the application, taken in conjunction with the accompanying drawings. In the description of embodiments of the application, specific terminology is employed for the sake of clarity. However, the application is not intended to be limited to the specific terminology so selected. The above-mentioned and other aspects of the present application will become apparent and the application will be clearly understood from the following description, taken in conjunction with the accompanying drawings in which:

[0046] In the embodiments of the present application, the terms "first", "second", etc. are used to distinguish different elements from the point of view, but do not represent the spatial arrangement or time sequence of the elements, and the elements should not be limited by these terms. The term "and / or" includes any one and all combinations of the associated listed terms. The terms "include", "contain", "have", etc. refer to the existence of the stated features, elements, elements or components, but do not exclude the existence or addition of one or more other features, elements, elements or components.

[0047] In the embodiments of the present application, the singular form "one", "the" and the like includes the plural form, should be understood broadly as "one kind" or "a kind of", rather than limited to the meaning of "one"; In addition, the term "said" should be understood to include both singular and plural forms, unless the context clearly indicates otherwise. In addition, the term "according to" should be understood as "at least partially according to", and the term "based on" should be understood as "at least partially based on", unless the context clearly indicates otherwise.

[0048] In the embodiments of the present application, the term "communication network" or "wireless communication network" can refer to a network that complies with any communication standard, such as New Radio (NR), Long Term Evolution (LTE), LTE-Advanced (LTE-A), Wideband Code Division Multiple Access (WCDMA), High-Speed Packet Access (HSPA), etc.

[0049] In addition, the communication between devices in the communication system can be carried out according to any stage of the communication protocol, which can include but is 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 communication, etc., and / or other currently known or future to be developed communication protocols.

[0050] In the embodiments of the present application, the term "network device" refers to, for example, a device that accesses a terminal device to a communication network and provides services for the terminal device in a communication system. The network device can include, but is 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), and the like.

[0051] Wherein, the base station can include, but is not limited to: Node B (NodeB or NB), evolved Node B (eNodeB or eNB), 5G base station (gNB), 6G base station, and future base station, etc., and can also include remote radio head (RRH), remote radio unit (RRU), relay, or low-power node (such as femto, pico, etc.). And the term "base station" can include some or all functions of them, and each base station can provide communication coverage for a specific geographic 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.

[0052] 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. The user equipment can be fixed or mobile, and can also be referred to as a mobile station (MS), a terminal, a user, a subscriber station (SS), an access terminal (AT), a station, a mobile terminal (MT), and the like.

[0053] Wherein, the terminal device can include, but is not limited to, the following devices: cellular phone, personal digital assistant (PDA), wireless modem, wireless communication device, handheld device, machine type communication device, laptop computer, cordless phone, smart phone, smart watch, digital camera, and the like.

[0054] For another example, in scenarios such as Internet of Things (IoT), user equipment can also be a machine or device that performs monitoring or measurement, for example, can include but not limited to: machine type communication (MTC) terminal, vehicle-mounted communication terminal, device to device (D2D) terminal, machine to machine (M2M) terminal, terminal supporting sidelink communication, etc.

[0055] In addition, the term "network side" or "network device side" refers to the side of the network, which can be a certain base station, or can include one or more network devices as above. The term "user side" or "terminal side" or "terminal device side" refers to the side of the user or terminal, which can be a certain UE, or can include one or more terminal devices as above. In this article, "device" can refer to network device or terminal device without special indication.

[0056] The terms "uplink control signal" and "uplink control information (UCI)" or "physical uplink control channel (PUCCH)" can be interchangeable without causing confusion, and the terms "uplink data signal" and "uplink data information" or "physical uplink shared channel (PUSCH)" can be interchangeable;

[0057] The terms "downlink control signal" and "downlink control information (DCI)" or "physical downlink control channel (PDCCH)" can be interchangeable, and the terms "downlink data signal" and "downlink data information" or "physical downlink shared channel (PDSCH)" can be interchangeable.

[0058] In addition, the uplink signal can include an uplink data signal and / or an uplink control signal and / or a PRACH and / or a SRS (sounding reference signal) and the like, and can also be referred to as an uplink transmission (UL transmission) or uplink information or an uplink channel. Transmitting / receiving the uplink transmission on the uplink resource can be understood as transmitting / receiving the uplink transmission using the uplink resource. The downlink signal can include a downlink data signal and / or a downlink control signal and / or a synchronization signal (SS, for example, 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 and the like, and can also be referred to as a downlink transmission (DL transmission) or downlink information or a downlink channel. Transmitting / receiving the downlink transmission on the downlink resource can be understood as transmitting / receiving the downlink transmission using the downlink resource.

[0059] In the embodiments of the present application, the higher layer signaling can be, for example, radio resource control (RRC) signaling; the RRC signaling can include, for example, an RRC message, such as a broadcast / common RRC message / signaling (for example, a master information block (MIB), system information (SI), a dedicated RRC message / signaling; or an RRC information element (RRC IE); or information fields included in the RRC message or RRC information element (or information fields included in the information fields). The higher layer signaling can also be, for example, medium access control layer (MAC) signaling; or a MAC control element (MAC CE). However, the present application is not limited thereto.

[0060] In the embodiments of the present application, "at least one" and "one or more than one" can be interchangeable, "a plurality of" and "more than one" can be interchangeable, and "a plurality of" means at least two, or two or more.

[0061] In the embodiments of the present application, pre-defined means defined by a protocol or determined according to a rule defined by a protocol, without additional configuration. Configuration / indication means direct or indirect configuration / indication by a network device through higher layer signaling and / or physical layer signaling. The configuration / indication can be configured / indicated by introducing a higher layer parameter in the higher layer signaling, and the higher layer parameter means information fields and / or information elements / units / elements (IEs) in the higher layer signaling. The physical layer signaling can be, for example, control information (DCI) carried by a physical downlink control channel or sequence, but is not limited thereto.

[0062] For ease of description, a base station is described below as an example of an access network device.

[0063] In the following description, "if", "when" and "in the case of" can be used interchangeably without causing confusion.

[0064] The scenarios of the embodiments of the present application are described below by way of example, but the present application is not limited thereto.

[0065] FIG. 1 is a schematic diagram of a communication system according to an embodiment of the present application, which schematically illustrates a case taking a terminal device and a network device as an example. As shown in FIG. 1, the communication system 100 can include a network device 101, a terminal device 102 and a terminal device 103. For simplicity, FIG. 1 only takes two terminal devices and one network device as an example for illustration, but the embodiments of the present application are not limited thereto.

[0066] In the embodiments of the present application, the network device 101, the terminal device 102 and the terminal device 103 can perform existing services or future implementable services transmission. For example, these services can include but are not limited to: enhanced mobile broadband (eMBB), massive machine type communication (mMTC), ultra-reliable and low-latency communication (URLLC) and related communication of reduced capability terminal devices, etc.

[0067] Among them, the terminal devices 102 and 103 can be in an RRC_IDLE state, or an RRC_INACTIVE state or an RRC_CONNECTED state, and the terminal devices 102 and 103 can also communicate with the network device 101. For example, taking the terminal device 102 as an example, the terminal device 102 can send data to the network device 101, or can perform data retransmission. The network device 101 can send a paging message to the terminal device 102, and can also send data to the terminal device 102, and the terminal device 102 receives the data sent by the network device 101. In addition, different terminal devices can also communicate with each other, for example, the terminal device 102 and the terminal device 103 can exchange data.

[0068] It is worth noting that FIG. 1 shows that the terminal device 102 and the terminal device 103 are both in the coverage of the network device 101, but the present application is not limited thereto. The terminal device 102 and the terminal device 103 can both not be in the coverage of the network device 101, or one of the terminal device 102 and the terminal device 103 is in the coverage of the network device 101 and the other is out of the coverage of the network device 101.

[0069] In the embodiments of the present application, one or more AI / ML models can be configured and run in the network device and / or the terminal device. The AI / ML model can be used for various signal processing functions of wireless communication, such as CSI prediction, CSI compression, beam prediction, positioning management, etc.; the present application is not limited thereto.

[0070] In the Release 19 stage, the AI / ML-based CSI compression feedback enhancement sub-use case in the space-time-frequency domain (TSF-AI / ML CSI compression) is further studied. This sub-use case uses historical CSI information through an AI / ML function or model (for example, an RNN / GRU / LSTM model) to help the current time CSI compression, aiming to obtain a lower compression rate or a higher feedback accuracy.

[0071] FIG. 2 is a schematic diagram of AI / ML-based CSI compression (TSF-AI / ML CSI compression) feedback enhancement in the space-time-frequency domain. The scenario of FIG. 2 can also be referred to as Case-2.

[0072] As shown in FIG. 2, on the UE side, after the CSI measurement result is subjected to matrix decomposition (for example, SVD decomposition (singular value decomposition) or SVD decomposition (eigenvalue decomposition)), a feature vector is obtained, which is input to an encoder to generate CSI feedback information. On the network side, the CSI feedback information sent by the UE is decoded by a decoder to generate reconstructed CSI.

[0073] In some embodiments, the encoder and the decoder on the UE side can adopt an AI / ML method (for example, an RNN / LSTM / GRU cascade Transformer / CNN model, etc.). Among them, the AI / ML method can use time domain information (which can also be referred to as historical CSI information, side information, etc.) to assist the current CSI compression and / or decompression, aiming to obtain a higher compression rate or a higher feedback accuracy.

[0074] When time-domain information is utilized for CSI compression and / or decompression, whether the time-domain information is available and / or can be utilized is easily affected by factors such as rank change, CSI dropping (e.g., CSI dropping based on layer priority), uplink control information (UCI) loss, etc. When the time-domain information is unavailable, the performance of the AI / ML model will be deteriorated, or even cannot work.

[0075] In addition, the CSI time-domain correlation determines whether the historical CSI information is helpful for the current CSI compression and / or decompression. Too low correlation will lead to invalid input of the AI / ML model, which not only cannot improve the CSI compression performance, but even will be regarded as noise by the AI / ML model, leading to the performance deterioration of the CSI compression. Therefore, the AI / ML is more suitable for the scenario with better CSI time-domain correlation, which usually corresponds to the case of lower UE moving speed, or lower rank value and / or larger eigenvalue of the layer.

[0076] FIG. 3 is another schematic diagram of AI / ML-based CSI compression (TSF-AI / ML CSI compression) feedback enhancement in time-space-frequency domain. In the example shown in FIG. 3, the CSI compression at the UE side uses historical CSI information, while the CSI decompression at the network side does not use historical CSI information. The scenario of FIG. 3 can also be referred to as Case-1.

[0077] FIG. 4 is still another schematic diagram of AI / ML-based CSI compression (TSF-AI / ML CSI compression) feedback enhancement in time-space-frequency domain. In the example shown in FIG. 4, the CSI compression at the UE side does not use historical CSI information, while the CSI decompression at the network side uses historical CSI information. The scenario of FIG. 4 can also be referred to as Case-5.

[0078] FIG. 5 is a schematic diagram of CSI compression plus prediction. In the example shown in FIG. 5, the model at the UE side performs CSI compression and prediction based on CSI measurement results at multiple time instants. The scenario of FIG. 5 can also be referred to as Case-3. In addition, in other examples, not only the model at the UE side performs CSI compression and prediction based on CSI measurement results at multiple time instants, but also the model at the network side performs prediction, which is referred to as Case-4.

[0079] In the embodiments of the present application, the CSI compression can also be referred to as “CSI encoding”, “CSI generation” and the like, and the result of the operation of CSI compression, or CSI encoding, or CSI generation and the like is referred to as CSI feedback information, CSI reporting information and the like.

[0080] In the embodiments of the present application, the CSI decompression can also be referred to as "CSI decoding", "CSI reconstruction", "CSI recovery", "CSI reestablishment", and the like.

[0081] In the embodiments of the present application, the AI / ML model can also be referred to as an AI / ML method, an AI / ML unit, an AI / ML function, or an AI / ML element, and the like. On the UE side, the AI / ML model can also be referred to as an encoder, a CSI generation part, and the like. On the network device side, the AI / ML model can also be referred to as a decoder, a CSI reconstruction part, and the like.

[0082] In the embodiments of the present application, one or more AI / ML functions or models can be configured and run in the network device and / or the terminal device. The AI / ML functions or models can be used for various signal processing functions of wireless communication, such as channel state information (CSI) prediction, CSI compression, beam prediction, positioning management, and the like; the present application is not limited thereto.

[0083] In the embodiments of the present application, the following terms have the same meaning, and they can be replaced with each other: AI / ML, artificial intelligence, artificial intelligence or machine learning.

[0084] In the embodiments of the present application, the AI / ML functionality / model can also be referred to as an AI / ML function or model, an artificial intelligence or machine learning function or model, an artificial intelligence function or model, and the like, which have the same meaning and can be replaced with each other in the present application.

[0085] It should be noted that the operation processing method of the AI / ML function or model in the embodiments of the present application is applicable to use cases including but not limited to CSI compression feedback, but those skilled in the art can understand that the embodiments of the present application are also applicable to other use cases and / or scenarios that apply AI / ML functions or models.

[0086] Embodiments of the first aspect

[0087] The embodiments of the present application provide an enhanced method of channel state information, which is applied to a terminal device. The following will be described from the terminal device side and / or the network device side.

[0088] FIG. 6 is a schematic diagram of an enhanced method of channel state information according to an embodiment of the present application. As shown in FIG. 6, from the terminal device (UE) side, the method includes:

[0089] 601、The terminal device is configured with an artificial intelligence functionality or model for channel state information (CSI) compression; and

[0090] 602、The terminal device is configured to perform at least one of the following:

[0091] Compression of channel state information over spatial and frequency domains (Case-0);

[0092] Compression of channel state information over spatial, frequency and time domains (Case-2);

[0093] Prediction and compression of channel state information (Case-3).

[0094] The above embodiments explicitly define the configurations corresponding to different operations of the terminal device, and the terminal device and the network device can have a unified understanding of the configurations of the corresponding operations.

[0095] In some embodiments, the AI / ML model on the UE side and the AI / ML model on the network side can be corresponding or matched, i.e., a two-sided model. The present application is not limited thereto, and AI / ML model can also be used only on the UE side or only on the network side. In the subsequent content, unless otherwise specified, the AI / ML model is the model on the UE side and / or the model on the network side.

[0096] In some embodiments, the artificial intelligence functionality or model refers to an AI / ML feature / feature group enabled by a configuration, wherein the configuration is supported based on a condition indicated by a terminal device capability.

[0097] For example, the AL / ML functionality or model can be one or more functions or models, or can be one or more logical models, or can be one or more sub-functions, or can be one or more features, or can be one or more feature groups.

[0098] In the following, the present application is further described in conjunction with specific embodiments.

[0099] In the following embodiments, the time instance is, for example, a time or a time represented by other time units, etc. Among them, the other time units are, for example, a time slot, a frame or a sub-frame, etc.

[0100] In the following embodiments, the reference signal can be, for example, a channel state information reference signal (CSI-RS).

[0101] In each of the following embodiments, the terminal device can perform at least one of Model inference based on an AI / ML function or model, Performance monitoring for the AI / ML function or model, and Training data collection for the AI / ML function or model.

[0102] Embodiment 1

[0103] In Embodiment 1, the related configurations in Model inference are explained.

[0104] In the case where the terminal device is configured to perform prediction and compression of channel state information (e.g., Case-3 as described above):

[0105] For one prediction window, the terminal device transmits one channel quality indicator or rank indicator (CQI / RI) or multiple channel quality indicators or rank indicators (CQI / RI).

[0106] For example, the one channel quality indicator or rank indicator is applied to the predicted channel state information for all time instances within the one prediction window; or, in the multiple channel quality indicators or rank indicators, each channel quality indicator or rank indicator is applied to the predicted channel state information for one or more time instances within the one prediction window, respectively.

[0107] FIG. 7 is one example of transmitting channel quality indicator or rank indicator (CQI / RI) for one prediction window, FIG. 8 is another example of transmitting channel quality indicator or rank indicator (CQI / RI) for one prediction window, and FIG. 9 is yet another example of transmitting channel quality indicator or rank indicator (CQI / RI) for one prediction window.

[0108] As shown in the example of FIG. 7, the network device configures the terminal device with reference signals, e.g., channel state information reference signals (CSI-RSs), at each time instance of the observation window (i.e., T1, T2, T3, and T4). At each time instance of the prediction window (i.e., T5, T6, T7, and T8), the terminal device generates the predicted CSI corresponding to the time instance. Within the prediction window, the terminal device reports one CQI / RI (e.g., two CQIs for rank > 4), and the reported CQI / RI is applied to the predicted CSI for all time instances within the prediction window.

[0109] In the example as shown in FIG. 8, the network device configures the terminal device with reference signals, such as channel state information reference signals (CSI-RS), at each time instance (i.e., T1, T2, T3 and T4) of the observation window. At each time instance (i.e., T5, T6, T7 and T8) of the prediction window, the terminal device generates the predicted CSI corresponding to the time instance. Within the prediction window, the terminal device reports a plurality of CQI / RI, each of which corresponds to the predicted CSI of each time instance within the prediction window. For example, the number of CQI / RI reported by the terminal device is the same as the number of time instances within the prediction window, i.e., one reported CQI / RI is applied to the predicted CSI of one time instance within the prediction window.

[0110] In the example as shown in FIG. 9, the network device configures the terminal device with reference signals, such as channel state information reference signals (CSI-RS), at each time instance (i.e., T1, T2, T3 and T4) of the observation window. At each time instance (i.e., T5, T6, T7 and T8) of the prediction window, the terminal device generates the predicted CSI corresponding to the time instance. Within the prediction window, the terminal device reports a plurality of CQI / RI (e.g., K CQI / RI), and one CQI / RI corresponds to the predicted CSI of a plurality of time instances (e.g., L time instances) within the prediction window, i.e., there are N time instances within the prediction window, and N = K*L. For example, there are 4 (i.e., N = 4) time instances within the prediction window, and the terminal device reports 2 (i.e., K = ) CQI / RI, each of which corresponds to the predicted CSI of 2 (i.e., L = 2) time instances within the prediction window.

[0111] In addition, in this application, different reporting methods can be used for channel quality indication (CQI) and rank indication (RI), for example, the example of FIG. 7 is used to report RI, and the example of FIG. 9 is used to report CQI.

[0112] In the case where the terminal device is configured to compress channel state information in the spatial domain, the frequency domain and the time domain (e.g., Case-2 described above):

[0113] During the compression of channel state information, in the case where the uplink control information (UCI) carrying the channel state information report is lost, the terminal device receives the indication information sent by the network device, which is used to indicate that the uplink control information is lost.

[0114] In some examples, the indication information is sent through the scheduling downlink control information (DCI) used to schedule the physical uplink shared channel or the physical downlink shared channel (PUSCH / PDSCH). For example, the scheduling downlink control information can be DCI 0_1 / 0_2 / 1_1 / 1_2.

[0115] The scheduled downlink control information has a field corresponding to the indication information. For example, a new field can be added in the DCI field to indicate the uplink control information loss (UCI loss).

[0116] In some other examples, the indication information is sent through non-scheduled downlink control information (DCI). The non-scheduled downlink control information (DCI) can be DCI 0_1 / 0_2 / 1_1 / 1_2 that does not schedule the physical uplink shared channel or the physical downlink shared channel (PUSCH / PDSCH).

[0117] One or more fields of the non-scheduled downlink control information are used for verification, and a combination of predetermined values of the one or more fields can be used to indicate the uplink control information loss. If the verification is passed, the terminal device considers the information in the DCI to be valid; if the verification is not implemented, the terminal device discards the information in the DCI (for example, discards all information in the DCI). The predetermined values of the one or more fields can be predefined.

[0118] In the case where the terminal device is configured to compress the channel state information in the spatial domain, the frequency domain, and the time domain (for example, Case-2 described above):

[0119] The terminal device sends the channel state information (CSI) report through the medium access control control element (MAC-CE), and the acknowledgement information for the medium access control control element (MAC-CE) is used to indicate whether the channel state information report is received by the network device.

[0120] For example, the terminal device sends the CSI report to the network device through the MAC-CE, and the acknowledgement information (for example, acknowledgement / non-acknowledgement ACK / NACK) of the network device for the MAC-CE can be used to indicate whether the network device receives the channel state information report.

[0121] Embodiment 2

[0122] In embodiment 2, the related configurations in the performance monitoring operation are described.

[0123] In the case where the terminal device is configured to compress the channel state information in the spatial domain, the frequency domain, and the time domain (for example, Case-2 described above):

[0124] The terminal device calculates the performance metric of the artificial intelligence function or model for one time instance; or the terminal device calculates the performance metric of the artificial intelligence function or model for multiple time instances within a time window, respectively.

[0125] The terminal device can further perform the following operations:

[0126] The terminal device averages the multiple performance indicators calculated for the multiple time instances within a time window, and sends the average to the network device; or the terminal device sends the multiple performance indicators calculated for the multiple time instances within a time window to the network device.

[0127] FIG. 10 is an example of calculating a performance indicator, and FIG. 11 is another example of calculating a performance indicator.

[0128] As shown in the example of FIG. 10, for Case-2, the terminal device can calculate a performance indicator at one time instance (e.g., one time slot) for performance monitoring.

[0129] As shown in the example of FIG. 11, for Case-2, the terminal device can calculate a performance indicator at multiple time instances (e.g., multiple time slots) for performance monitoring. For example, a time window can be defined or configured for the terminal device, the time window including multiple time instances, the terminal device can calculate a performance indicator at each time instance of the time window, obtain multiple performance indicators within the time window, and send the multiple performance indicators within the time window to the network device, or calculate an average of the multiple performance indicators within the time window and send the average to the network device.

[0130] In this application, the terminal device determines to calculate a performance indicator at one time instance (e.g., the example of FIG. 10) or multiple time instances (e.g., the example of FIG. 11) according to at least one of a configuration of the network device and a capability of the terminal device.

[0131] In some examples of Embodiment 2, in a case where the terminal device is configured to perform prediction and compression of channel state information (Case-3):

[0132] The terminal device receives a reference signal at one or more time instances of a prediction window, the reference signal being used for performance monitoring of the artificial intelligence function or model.

[0133] The reference signal is, for example, a channel state information reference signal (CSI-RS).

[0134] For example, the prediction window has multiple time instances, and the network device configures and / or sends a reference signal for performance monitoring to the terminal device at each time instance of the prediction window.

[0135] For example, the prediction window has a plurality of time instances, and the network device configures and / or transmits the reference signal for performance monitoring to the terminal device at a part of the time instances of the prediction window. In one instance, the network device configures and / or transmits the reference signal for performance monitoring to the terminal device at one time instance of the prediction window.

[0136] In some examples of Embodiment 2, in the case where the terminal device is configured to perform the prediction and compression of channel state information (Case-3):

[0137] The compression of channel state information and the prediction of channel state information are performed respectively, and the terminal device monitors the artificial intelligence function or model used for the compression of channel state information and the artificial intelligence function or model used for the prediction of channel state information respectively.

[0138] For the artificial intelligence function or model used for the compression of channel state information, the terminal device calculates the performance indicator of the artificial intelligence function or model used for the compression of channel state information using the measured channel state information. The measured channel state information is obtained by the reference signal configured for inference operation or the reference signal for performance monitoring of the terminal device.

[0139] For example, the terminal device obtains the measured channel state information according to all or part of the reference signals for inference (e.g., prediction and compression) operation, and calculates the performance indicator of the artificial intelligence function or model used for the compression of channel state information using the measured channel state information; or the terminal device can be configured and transmitted with the reference signal for performance monitoring, and the terminal device obtains the measured channel state information according to the reference signal for performance monitoring, and calculates the performance indicator of the artificial intelligence function or model used for the compression of channel state information using the measured channel state information.

[0140] For the artificial intelligence function or model used for the prediction of channel state information, the terminal device receives the reference signal at one or more time instances of the prediction window, e.g., receives the reference signal at each time instance of the prediction window, or receives the reference signal at part (e.g., 1) of the time instances of the prediction window.

[0141] The terminal device calculates the performance indicator of the artificial intelligence function or model used for the prediction of channel state information according to the reference signal received at the prediction window.

[0142] For example, the terminal device calculates the performance indicator after measuring the reference signal for one time instance, and reports the calculated performance indicator; or the terminal device measures the reference signal for multiple time instances within one prediction window, and calculates the performance indicator for each time instance, and sends the multiple performance indicators (e.g., sends the multiple performance indicators through one report) or sends the average of the multiple performance indicators.

[0143] In the case of Case-3, the terminal device monitors the first performance indicator of the artificial intelligence function or model used for the compression of channel state information, and the second performance indicator of the artificial intelligence function or model used for the prediction of channel state information, and the first performance indicator and the second performance indicator can be sent separately (e.g., the first performance indicator and the second performance indicator are sent using independent reports, respectively), or the first performance indicator and the second performance indicator are sent together (e.g., the first performance indicator and the second performance indicator are sent using one report).

[0144] In some other examples of Embodiment 2, in the case where the terminal device is configured to perform the prediction and compression of channel state information (Case-3):

[0145] The compression of channel state information and the prediction of channel state information are jointly performed, wherein the terminal device jointly monitors the artificial intelligence function or model used for the compression of channel state information and the artificial intelligence function or model used for the prediction of channel state information.

[0146] The reference signals in the observation window can be used to calculate the performance indicator. For example, the terminal device receives the reference signals on one or more time instances of the observation window, and the terminal device calculates the performance indicator according to the reference signals on the one or more time instances, and the performance indicator is used to represent the performance of the artificial intelligence function or model used for the compression of channel state information and the performance of the artificial intelligence function or model used for the prediction of channel state information.

[0147] Embodiment 3

[0148] In Embodiment 3, the related configurations in the training data collection operation are described.

[0149] Embodiment 3 is applicable to the following scenarios: the scenario of the compression of channel state information in the spatial domain and the frequency domain (i.e., Case-0 described above); the scenario of the compression of channel state information in the spatial domain, the frequency domain, and the time domain (i.e., Case-2 described above); the scenario of the prediction and compression of channel state information (i.e., Case-3 described above).

[0150] In some examples of embodiment 3, the terminal device is configured with a periodic or semi-persistent reference signal for collecting data required for training of the artificial intelligence function or model. Wherein the periodicity of the reference signal is configurable; in addition, the periodicity of the reference signal depends on the artificial intelligence function or model supported by the terminal device.

[0151] The terminal device sends the collected data to the network device through Layer 1 signaling or non-Layer 1 signaling. Layer 1 signaling is, for example, a physical uplink control channel (PUCCH) or a physical uplink shared channel (PUSCH). Wherein, in the case of sending the collected data through the PUCCH, a new PUCCH format, for example, a long-PUCCH, can be used; in the case of sending the collected data through the PUSCH, the PUSCH can be a Configured Grant PUSCH (CG-PUSCH).

[0152] In embodiment 3, for CSI compression with a double-sided model, if Layer 1 signaling is used for training data collection (e.g., uplink control information UCI), when the reference signal used for inference is also used for training data collection, the reporting of CQI / RI needs to be defined.

[0153] For example, in the case of sending the collected data through Layer 1 signaling, when the reference signal used for inference operation is used to collect the data, any of the following options can be adopted:

[0154] Option 1, the channel quality indication or rank indication (CQI / RI) used for collecting data and the channel quality indication or rank indication (CQI / RI) used for inference operation are sent separately;

[0155] Option 2, the channel quality indication or rank indication used for collecting data is sent, or the channel quality indication or rank indication used for inference operation is sent, i.e., the sending of channel quality indication or rank indication (CQI / RI) is only for one of training data collection and inference operation;

[0156] Option 3, the channel quality indication or rank indication used for inference operation is sent, the channel quality indication or rank indication used for collecting data is calculated, for example, the channel quality indication or rank indication used for inference operation is calculated and sent, and the channel quality indication or rank indication used for training data collection is calculated but not sent.

[0157] Embodiments of the second aspect

[0158] The embodiment of the present application provides a channel state information enhancement method, which is applied to a network device and corresponds to the method of the embodiment of the first aspect. The same content as the embodiment of the first aspect will not be described herein again.

[0159] FIG. 12 is a schematic diagram of the channel state information enhancement method according to the embodiment of the second aspect of the present application. As shown in FIG. 12, from the network device (NW) side, the method comprises the following steps.

[0160] 1201. The network device configures an artificial intelligence function or model for channel state information (CSI) compression for a terminal device; and

[0161] 1202. The network device configures the terminal device to perform at least one of the following operations:

[0162] compression of channel state information in spatial domain and frequency domain (Case 0);

[0163] compression of channel state information in spatial domain, frequency domain and time domain (Case 2);

[0164] prediction and compression of channel state information (Case 3).

[0165] In some embodiments, in the case of configuring the terminal device to perform prediction and compression of channel state information (Case 3):

[0166] for one prediction window, receiving one channel quality indicator or rank indicator (CQI / RI) or multiple channel quality indicators or rank indicators (CQI / RI) sent by the terminal device.

[0167] In some embodiments, the one channel quality indicator or rank indicator is applied to the predicted channel state information of all time instances within the one prediction window; or

[0168] of the multiple channel quality indicators or rank indicators, each channel quality indicator or rank indicator is respectively applied to the predicted channel state information of one or more time instances within the one prediction window.

[0169] In some embodiments, in the case of configuring the terminal device to perform compression of channel state information in spatial domain, frequency domain and time domain (Case 2):

[0170] During the compression of channel state information, in the case of loss of uplink control information (UCI) carrying the channel state information report, sending indication information to the terminal device, the indication information being used to indicate the loss of the uplink control information.

[0171] In some embodiments, the indication information is sent through a scheduled downlink control information (DCI) used for scheduling a physical uplink shared channel or a physical downlink shared channel (PUSCH / PDSCH); or

[0172] The indication information is sent through a non-scheduled downlink control information (DCI).

[0173] In some embodiments, the scheduled downlink control information has a field corresponding to the indication information; or

[0174] One or more fields in the non-scheduled downlink control information are used for verification, and a predetermined value of the one or more fields is used to indicate that the uplink control information is missing.

[0175] In some embodiments, in a case where the terminal device is configured to compress channel state information in a spatial domain, a frequency domain, and a time domain (Case 2):

[0176] Receiving a performance metric of the artificial intelligence function or model calculated by the terminal device for one time instance; or

[0177] Receiving performance metrics of the artificial intelligence function or model calculated by the terminal device for multiple time instances within a time window, respectively.

[0178] In some embodiments, receiving an average of multiple performance metrics calculated by the terminal device for multiple time instances within a time window, respectively; or

[0179] Receiving multiple performance metrics calculated by the terminal device for multiple time instances within a time window, respectively.

[0180] In some embodiments, the network device configures the terminal device to calculate the performance metric for one time instance or multiple time instances.

[0181] In some embodiments, in a case where the terminal device is configured to predict and compress channel state information (Case 3):

[0182] Sending a reference signal to the terminal device at one or more time instances of a prediction window, the reference signal being used for performance monitoring of the artificial intelligence function or model.

[0183] In some embodiments, in a case where the terminal device is configured to predict and compress channel state information (Case 3):

[0184] The compression of channel state information and the prediction of channel state information are performed separately,

[0185] The terminal device monitors an artificial intelligence function or model used for the compression of channel state information and an artificial intelligence function or model used for the prediction of channel state information separately.

[0186] In some embodiments, the terminal device calculates a performance indicator of the artificial intelligence function or model used for the compression of channel state information using measured channel state information, wherein the measured channel state information is obtained through a reference signal configured for inference or a reference signal configured for performance monitoring for the terminal device.

[0187] In some embodiments, the terminal device is sent a reference signal at one or more time instances of a prediction window; and

[0188] A performance indicator of the artificial intelligence function or model used for the prediction of channel state information calculated by the terminal device according to the reference signal is received.

[0189] In some embodiments, the calculated performance indicator reported by the terminal device after each measurement for the reference signal is received; or

[0190] A plurality of performance indicators corresponding to a plurality of reference signals or an average of a plurality of performance indicators is received, which is sent by the terminal device after measuring the plurality of reference signals within one prediction window.

[0191] In some embodiments, a first performance indicator obtained by the artificial intelligence function or model used for the compression of channel state information and a second performance indicator obtained by the artificial intelligence function or model used for the prediction of channel state information are sent separately or together.

[0192] In some embodiments, in the case where the terminal device is configured to perform the prediction and compression of channel state information (Case 3):

[0193] The compression of channel state information and the prediction of channel state information are performed jointly,

[0194] The terminal device performs joint monitoring on the artificial intelligence function or model used for the compression of channel state information and the artificial intelligence function or model used for the prediction of channel state information.

[0195] In some embodiments,

[0196] A reference signal is sent to the terminal device at one or more time instances of an observation window; and

[0197] receiving a performance indicator calculated by the terminal device according to the reference signal, the performance indicator being used to represent performance of an artificial intelligence function or model used for compression of channel state information and performance of an artificial intelligence function or model used for prediction of channel state information.

[0198] In some embodiments, the terminal device is configured with a periodic or semi-persistent reference signal for collecting data required for training of an artificial intelligence function or model,

[0199] The periodicity of the reference signal is configurable and depends on the artificial intelligence function or model supported by the terminal device,

[0200] The collected data is received by the terminal device through layer 1 signaling or non-layer 1 signaling.

[0201] In some embodiments, the data is transmitted through a physical uplink control channel (PUCCH) or a physical uplink shared channel (PUSCH).

[0202] In some embodiments, in the case where the collected data is transmitted through layer 1 signaling, when the reference signal for inference operation is used to collect the data:

[0203] The channel quality indicator or rank indicator for collecting the data and the channel quality indicator or rank indicator for inference operation are transmitted separately;

[0204] The channel quality indicator or rank indicator for collecting the data is transmitted, or the channel quality indicator or rank indicator for inference operation is transmitted; or

[0205] The channel quality indicator or rank indicator for inference operation is transmitted, and the channel quality indicator or rank indicator for collecting the data is calculated.

[0206] Embodiments of the third aspect

[0207] Embodiments of the present application provide a device for setting a reference signal. The device may, for example, be a terminal device, or one or more components or assemblies configured in the terminal device, which corresponds to the method applied to the terminal device side in the embodiments of the first aspect. The same content as the embodiments of the first aspect will not be described again.

[0208] FIG. 13 is a schematic diagram of a channel state information enhancement device according to an embodiment of the present application. As shown in FIG. 13, the channel state information enhancement device 1300 includes a first processor 1301, a first receiver 1302, and a first transmitter 1303.

[0209] In some embodiments, the first processor is configured for artificial intelligence function or model for channel state information compression; and

[0210] The first processor is configured to perform at least one of the following:

[0211] Compression of channel state information on spatial domain and frequency domain;

[0212] Compression of channel state information on spatial domain, frequency domain and time domain;

[0213] Prediction and compression of channel state information.

[0214] In some embodiments, in the case where the first processor is configured to perform prediction and compression of channel state information:

[0215] For one prediction window, the first transmitter of the apparatus transmits one channel quality indicator or rank indicator or multiple channel quality indicators or rank indicators.

[0216] In some embodiments, the one channel quality indicator or rank indicator is applied to predicted channel state information of all time instances within the one prediction window; or

[0217] Among the multiple channel quality indicators or rank indicators, each channel quality indicator or rank indicator is respectively applied to predicted channel state information of one or more time instances within the one prediction window.

[0218] In some embodiments, in the case where the first processor is configured to perform compression of channel state information on spatial domain, frequency domain and time domain:

[0219] During compression of channel state information, in the case where uplink control information carrying channel state information report is lost, the first receiver of the apparatus receives indication information transmitted by a network device, the indication information being used to indicate that the uplink control information is lost.

[0220] In some embodiments, the indication information is transmitted through scheduled downlink control information, the scheduled downlink control information being used to schedule physical uplink shared channel or physical downlink shared channel; or

[0221] The indication information is transmitted through non-scheduled downlink control information.

[0222] In some embodiments, the scheduled downlink control information has a field corresponding to the indication information; or

[0223] One or more fields in the non-scheduled downlink control information are used for validation, and a predetermined value of the one or more fields is used to indicate that the uplink control information is missing.

[0224] In some embodiments, in a case where the first processor is configured to perform compression of channel state information in spatial domain, frequency domain and time domain:

[0225] The first processor calculates a performance indicator of the artificial intelligence function or model for one time instance; or

[0226] The first processor calculates a performance indicator of the artificial intelligence function or model for each of a plurality of time instances within a time window.

[0227] In some embodiments, the first processor averages a plurality of performance indicators calculated for each of a plurality of time instances within a time window, and the first transmitter of the apparatus transmits the average to the network device; or

[0228] The first transmitter of the apparatus transmits a plurality of performance indicators calculated for each of a plurality of time instances within a time window to the network device.

[0229] In some embodiments, the first processor determines to calculate the performance indicator for one time instance or a plurality of time instances according to at least one of a configuration of a network device and a capability of the terminal device.

[0230] In some embodiments, in a case where the first processor is configured to perform prediction and compression of channel state information:

[0231] The first receiver of the apparatus receives a reference signal on one or more time instances of a prediction window, the reference signal being used for performance monitoring of the artificial intelligence function or model.

[0232] In some embodiments, in a case where the first processor is configured to perform prediction and compression of channel state information:

[0233] The compression of channel state information and the prediction of channel state information are performed respectively,

[0234] The first processor respectively monitors an artificial intelligence function or model used for the compression of channel state information and an artificial intelligence function or model used for the prediction of channel state information.

[0235] In some embodiments, the first processor calculates a performance indicator of an artificial intelligence function or model used for compression of channel state information using measured channel state information, wherein the measured channel state information is obtained through a reference signal configured for inference operation or a reference signal configured for performance monitoring for the terminal device.

[0236] In some embodiments, the first receiver of the apparatus receives reference signals at one or more time instances of a prediction window; and

[0237] The first processor calculates a performance indicator of an artificial intelligence function or model used for prediction of channel state information according to the reference signals.

[0238] In some embodiments, the first transmitter of the apparatus reports the calculated performance indicator after each measurement for the reference signal; or

[0239] The first transmitter transmits a plurality of the performance indicators corresponding to a plurality of the reference signals within one of the prediction windows or an average of the plurality of the performance indicators after measurements for the plurality of the reference signals.

[0240] In some embodiments, the first processor monitors a first performance indicator obtained by an artificial intelligence function or model used for compression of channel state information and a second performance indicator obtained by an artificial intelligence function or model used for prediction of channel state information are transmitted separately or together.

[0241] In some embodiments, in a case where the first processor is configured to perform prediction and compression of channel state information:

[0242] The compression of channel state information and the prediction of channel state information are jointly performed,

[0243] The first processor jointly monitors an artificial intelligence function or model used for compression of channel state information and an artificial intelligence function or model used for prediction of channel state information.

[0244] In some embodiments, the first receiver of the apparatus receives reference signals at one or more time instances of an observation window; and

[0245] The first processor calculates a performance indicator according to the reference signals, the performance indicator being used to represent a performance of an artificial intelligence function or model used for compression of channel state information and a performance of an artificial intelligence function or model used for prediction of channel state information.

[0246] In some embodiments, the first processor is configured to periodically or semi-persistently transmit a reference signal, the reference signal being used to collect data required for training of an artificial intelligence function or model,

[0247] The periodicity of the reference signal is configurable and depends on the artificial intelligence function or model supported by the terminal device,

[0248] The first transmitter of the apparatus transmits the collected data to a network device through layer 1 signaling or non-layer 1 signaling.

[0249] In some embodiments, the data is transmitted through a physical uplink control channel or a physical uplink shared channel.

[0250] In some embodiments, in the case where the collected data is transmitted through layer 1 signaling, when the reference signal for inference operation is used to collect the data:

[0251] The channel quality indicator or rank indicator used to collect the data and the channel quality indicator or rank indicator used for inference operation are transmitted separately;

[0252] The channel quality indicator or rank indicator used to collect the data is transmitted, or the channel quality indicator or rank indicator used for inference operation is transmitted; or

[0253] The channel quality indicator or rank indicator used for inference operation is transmitted, and the channel quality indicator or rank indicator used to collect the data is calculated.

[0254] The above embodiments are only exemplarily described, but the present application is not limited thereto, and appropriate modifications can be made on the basis of the above embodiments. For example, the above embodiments can be used alone, or one or more of the above embodiments can be combined.

[0255] It is worth noting that the above only describes the components or modules related to the present application, but the present application is not limited thereto. The apparatus 1300 can also include other components or modules, and the specific content of these components or modules can be referred to related technologies.

[0256] In addition, for the sake of simplicity, only the connection relationship or signal path between the components or modules is exemplarily shown in FIG. 13, but it should be clear to those skilled in the art that various related technologies such as bus connection can be used. The above components or modules can be implemented by hardware facilities such as processors, memories, transmitters, receivers, etc.; the present application is not limited thereto.

[0257] Embodiments of the fourth aspect

[0258] The embodiment of the present application provides a device for enhancing channel state information. The device can be a network device, or can be one or more components or assemblies configured in the network device, which corresponds to the method applied to the network device side in the embodiment of the second aspect, and the same content as the embodiment of the second aspect will not be repeated.

[0259] FIG. 14 is a schematic diagram of the device for enhancing channel state information according to the embodiment of the present application. As shown in FIG. 14, the device 1400 for enhancing channel state information includes a second processor 1401, a second receiver 1402 and a second transmitter 1403.

[0260] In some embodiments, the second processor configures an artificial intelligence function or model for the terminal device to perform channel state information compression; and

[0261] The second processor configures the terminal device to perform at least one of the following operations:

[0262] Compression of channel state information in spatial domain and frequency domain;

[0263] Compression of channel state information in spatial domain, frequency domain and time domain;

[0264] Prediction and compression of channel state information.

[0265] In some embodiments, in the case of configuring the terminal device to perform prediction and compression of channel state information:

[0266] For one prediction window, the second receiver of the device receives one channel quality indicator or rank indicator or multiple channel quality indicators or rank indicators sent by the terminal device.

[0267] In some embodiments, the one channel quality indicator or rank indicator is applied to predicted channel state information of all time instances within the one prediction window; or

[0268] Among the multiple channel quality indicators or rank indicators, each channel quality indicator or rank indicator is respectively applied to predicted channel state information of one or more time instances within the one prediction window.

[0269] In some embodiments, in the case of configuring the terminal device to perform compression of channel state information in spatial domain, frequency domain and time domain:

[0270] During the compression of channel state information, in the case of loss of uplink control information carrying the channel state information report, the second transmitter of the device sends indication information to the terminal device, the indication information being used to indicate the loss of the uplink control information.

[0271] In some embodiments, the indication information is sent through a scheduled downlink control information, the scheduled downlink control information being used for scheduling a physical uplink shared channel or a physical downlink shared channel; or

[0272] The indication information is sent through a non-scheduled downlink control information.

[0273] In some embodiments, the scheduled downlink control information has a field corresponding to the indication information; or

[0274] One or more fields in the non-scheduled downlink control information are used for verification, and a predetermined value of the one or more fields is used to indicate that the uplink control information is lost.

[0275] In some embodiments, in a case where the terminal device is configured to perform compression of channel state information in a spatial domain, a frequency domain, and a time domain:

[0276] The second receiver of the apparatus receives a performance indicator of the artificial intelligence function or model calculated by the terminal device for one time instance; or

[0277] The second receiver of the apparatus receives performance indicators of the artificial intelligence function or model calculated by the terminal device for multiple time instances within a time window, respectively.

[0278] In some embodiments, the second receiver of the apparatus receives an average value of multiple performance indicators calculated by the terminal device for multiple time instances within a time window, respectively; or

[0279] The second receiver of the apparatus receives multiple performance indicators calculated by the terminal device for multiple time instances within a time window, respectively.

[0280] In some embodiments, the second processor of the apparatus configures the terminal device to calculate the performance indicator for one time instance or multiple time instances.

[0281] In some embodiments, in a case where the terminal device is configured to perform prediction and compression of channel state information:

[0282] The second transmitter of the apparatus sends a reference signal to the terminal device at one or more time instances of a prediction window, the reference signal being used for performance monitoring of the artificial intelligence function or model.

[0283] In some embodiments, in a case where the terminal device is configured to perform prediction and compression of channel state information:

[0284] The compression of channel state information and the prediction of channel state information are performed respectively,

[0285] The terminal device monitors an artificial intelligence function or model used for compression of channel state information and an artificial intelligence function or model used for prediction of channel state information, respectively.

[0286] In some embodiments, the terminal device calculates a performance indicator of the artificial intelligence function or model used for compression of channel state information using measured channel state information, wherein the measured channel state information is obtained through a reference signal configured for the terminal device for inference operation or a reference signal for performance monitoring.

[0287] In some embodiments, the terminal device is sent a reference signal at one or more time instances of a prediction window; and

[0288] The second receiver of the apparatus receives a performance indicator of the artificial intelligence function or model used for prediction of channel state information calculated by the terminal device based on the reference signal.

[0289] In some embodiments, the second receiver receives the calculated performance indicator reported by the terminal device after each measurement on the reference signal; or

[0290] The second receiver receives a plurality of the performance indicators corresponding to a plurality of the reference signals or an average of a plurality of the performance indicators sent by the terminal device after measuring on the plurality of the reference signals within one of the prediction windows.

[0291] In some embodiments, the first performance indicator obtained by the artificial intelligence function or model used for compression of channel state information and the second performance indicator obtained by the artificial intelligence function or model used for prediction of channel state information are sent separately or together.

[0292] In some embodiments, in a case where the terminal device is configured to perform prediction and compression of channel state information:

[0293] The compression of channel state information and the prediction of channel state information are jointly performed,

[0294] The terminal device jointly monitors the artificial intelligence function or model used for compression of channel state information and the artificial intelligence function or model used for prediction of channel state information.

[0295] In some embodiments, the terminal device is sent a reference signal at one or more time instances of an observation window; and

[0296] The second receiver of the apparatus receives a performance indicator calculated by the terminal device according to the reference signal, the performance indicator being used to represent performance of an artificial intelligence function or model used for compression of channel state information and performance of an artificial intelligence function or model used for prediction of channel state information.

[0297] In some embodiments, the second transmitter of the apparatus configures the terminal device with a periodic or semi-persistent reference signal used for collecting data required for training of an artificial intelligence function or model,

[0298] The periodicity of the reference signal is configurable and depends on an artificial intelligence function or model supported by the terminal device,

[0299] The second receiver of the apparatus receives the collected data sent by the terminal device through layer 1 signaling or non-layer 1 signaling.

[0300] In some embodiments, the data is sent through a physical uplink control channel or a physical uplink shared channel.

[0301] In some embodiments, in the case where the collected data is sent through layer 1 signaling, when a reference signal for inference operation is used to collect the data:

[0302] The channel quality indicator or rank indication used for collecting the data and the channel quality indicator or rank indication used for inference operation are sent separately;

[0303] The channel quality indicator or rank indication used for collecting the data is sent, or the channel quality indicator or rank indication used for inference operation is sent; or

[0304] The channel quality indicator or rank indication used for inference operation is sent, and the channel quality indicator or rank indication used for collecting the data is calculated.

[0305] The above various embodiments are only exemplarily described, but the present application is not limited thereto, and appropriate variations can be made on the basis of the above various embodiments. For example, the above various embodiments can be used alone, or one or more of the above various embodiments can be combined.

[0306] It is worth noting that the above only describes various components or modules related to the present application, but the present application is not limited thereto. The apparatus 1400 can also include other components or modules, and the specific content of these components or modules can be referred to related technologies.

[0307] Further, for simplicity, only the connection relationship or signal direction between each component or module is exemplarily shown in FIG. 14, but it should be understood by those skilled in the art that various related technologies such as bus connection can be adopted. Each component or module described above can be implemented by hardware facilities such as processor, memory, transmitter, receiver, etc.; the implementation of the present application is not limited thereto.

[0308] Embodiments of the fifth aspect

[0309] Embodiments of the present application provide a communication system, comprising a terminal device and a network device.

[0310] For example, the structure of the communication system can refer to FIG. 1. As shown in FIG. 1, the communication system 100 comprises a network device 101 and terminal devices 102 and 103. At least one of the terminal device 102, the terminal device 103 and the network device 101 can have the structure of the electronic device shown in FIG. 13, for example.

[0311] FIG. 15 is a schematic block diagram of the electronic device. As shown in FIG. 15, the electronic device 1500 can comprise a processor 1510 and a memory 1520; the memory 1520 is coupled to the processor 1510. The memory 1520 can store various data; in addition, it also stores a program 1530 for information processing, and executes the program 1530 under the control of the processor 1510 to receive or send various information.

[0312] In one embodiment, the processor 1510 can be configured to execute the enhanced method of channel state information in the first aspect embodiment and / or the enhanced method of channel state information in the second aspect embodiment.

[0313] In addition, as shown in FIG. 15, the electronic device 1500 can further comprise a transceiver 1540, an antenna 1550 and the like; the functions of the above components are similar to those of the prior art, which will not be described here. It should be noted that the electronic device 1500 does not necessarily include all the components shown in FIG. 15; in addition, the electronic device 1500 can also include components not shown in FIG. 15, which can refer to the prior art.

[0314] The embodiments of the present application also provide a computer program, wherein when the program is executed in a terminal device, the program causes the terminal device to execute the enhanced method of channel state information of the embodiments of the first aspect.

[0315] The embodiments of the present application also provide a storage medium storing a computer program, wherein the computer program causes a terminal device to execute the enhanced method of channel state information of the embodiments of the first aspect.

[0316] The embodiments of the present application further provide a computer program, which, when executed in a network device, causes the network device to perform the method for enhancing channel state information according to the embodiments of the second aspect.

[0317] The embodiments of the present application further provide a storage medium storing a computer program, which causes a network device to perform the method for enhancing channel state information according to the embodiments of the second aspect.

[0318] The apparatuses and methods described above can be implemented by hardware, or by hardware combined with software. The present application relates to a computer readable program, which, when executed by a logic component, causes the logic component to implement the apparatuses or constituent components described above, or causes 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.

[0319] The methods / apparatuses described in connection with the embodiments of the present application can be directly embodied as hardware, software modules executed by a processor, or a combination of the two. For example, one or more of the functional blocks shown in the functional block diagrams, and / or a combination of one or more of the functional blocks, can correspond to individual software modules of a computer program flow, or to individual hardware modules. These software modules can correspond to individual steps shown in the diagrams, respectively. These hardware modules can be implemented by, for example, fixing the software modules with a field programmable gate array (FPGA).

[0320] The software modules can be located in a RAM memory, a flash memory, a ROM memory, an EPROM memory, an EEPROM memory, a register, a hard disk, a mobile disk, a CD-ROM, or any other form of storage medium known in the art. A storage medium can be coupled to the processor, so that the processor can read information from, and write information to, the storage medium; or the storage medium can be integral to the processor. The processor and the storage medium can be located in an ASIC. The software modules can 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 MEGA-SIM card or a large-capacity flash memory device, the software modules can be stored in the MEGA-SIM card or the large-capacity flash memory device.

[0321] One or more of the functional blocks described in the figures and / or one or more combinations of the functional blocks can 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, discrete gate or transistor logic device, discrete hardware component, or any appropriate combination thereof, for performing the functions described in this disclosure. One or more of the functional blocks described in FIG. 9 or FIG. 10 and / or one or more combinations of the functional blocks can also be implemented as a combination of computing devices, such as a combination of a DSP and a microprocessor, a plurality of microprocessors, one or more microprocessors in conjunction with a DSP core, or any other such configuration.

[0322] The present application has been described above with the attachment to the specific embodiments, but it should be clear to those skilled in the art that the descriptions are exemplary and are not a limitation on the scope of protection of the present application. Those skilled in the art can make various modifications and changes to the present application according to the spirit and principles of the present application, and these modifications and changes are also within the scope of the present application.

[0323] According to the various embodiments disclosed in the embodiments of the present application, the following notes are also disclosed:

[0324] 1. An enhanced method of channel state information, applied to a terminal device, wherein the method comprises:

[0325] the terminal device is configured with an artificial intelligence function or model for performing channel state information compression; and

[0326] the terminal device is configured to perform at least one of the following operations:

[0327] compression of channel state information in spatial and frequency domains;

[0328] compression of channel state information in spatial, frequency and time domains;

[0329] prediction and compression of channel state information.

[0330] 2. An enhanced method of channel state information, applied to a network device, wherein the method comprises:

[0331] the network device configures a terminal device with an artificial intelligence function or model for performing channel state information compression; and

[0332] the network device configures the terminal device to perform at least one of the following operations:

[0333] compression of channel state information in spatial and frequency domains;

[0334] compression of channel state information in spatial, frequency and time domains;

[0335] Prediction and compression of channel state information.

[0336] 3. A terminal device comprising a memory storing a computer program and a processor configured to execute the computer program to implement the method of clause 1.

[0337] 4. A network device comprising a memory storing a computer program and a processor configured to execute the computer program to implement the method of clause 2.

[0338] 5. A computer program product comprising at least a computer program which, when executed by a processor, causes a terminal device to perform the method of clause 1.

[0339] 6. A computer program product comprising at least a computer program which, when executed by a processor, causes a network device to perform the method of clause 2.

Claims

1. An apparatus for enhancing channel state information, applied to a terminal device, the apparatus comprising a first processor configured to implement an artificial intelligence function or model for channel state information compression; and the first processor is configured to perform at least one of the following: compression of channel state information in spatial domain and frequency domain; compression of channel state information in spatial domain, frequency domain and time domain; prediction and compression of channel state information. 2.The apparatus of claim 1, wherein, in the case that the first processor is configured to perform prediction and compression of channel state information: the first transmitter of the apparatus transmits one channel quality indicator or rank indicator or multiple channel quality indicators or rank indicators for one prediction window. 3.The apparatus of claim 2, wherein, the one channel quality indicator or rank indicator is applied to predicted channel state information of all time instances within the one prediction window; or the multiple channel quality indicators or rank indicators are respectively applied to predicted channel state information of one or more time instances within the one prediction window. 4.The apparatus of claim 1, wherein, in the case that the first processor is configured to perform compression of channel state information in spatial domain, frequency domain and time domain: during compression of channel state information, in the case that uplink control information carrying a channel state information report is lost, the first receiver of the apparatus receives indication information transmitted by a network device, the indication information being used to indicate that the uplink control information is lost. 5.The apparatus of claim 4, wherein, the indication information is transmitted through scheduled downlink control information used to schedule a physical uplink shared channel or a physical downlink shared channel; or the indication information is transmitted through non-scheduled downlink control information. 6.The apparatus of claim 5, wherein, the scheduled downlink control information has a field corresponding to the indication information; or one or more fields in the non-scheduled downlink control information are used for verification, and a predetermined value of the one or more fields is used to indicate that the uplink control information is lost. 7.The apparatus of claim 1, wherein, in the case that the first processor is configured to perform compression of channel state information in spatial domain, frequency domain and time domain: the first processor calculates a performance indicator of the artificial intelligence function or model for one time instance; or the first processor calculates a performance indicator of the artificial intelligence function or model for multiple time instances within one time window respectively. 8.The apparatus of claim 7, wherein, the first processor averages multiple performance indicators calculated for multiple time instances within one time window respectively, and the first transmitter of the apparatus transmits the average to the network device; or the first transmitter of the apparatus transmits multiple performance indicators calculated for multiple time instances within one time window respectively to the network device. 9.The apparatus of claim 7, wherein, ​ ​ ​ ​ ​ ​ ​ ​ ​ ​ ​ ​ ​ ​ ​ ​ ​ ​ ​ ​ The first processor determines the performance indicator for one or more time instances according to at least one of a configuration of the network device and a capability of the terminal device. 10.The apparatus of claim 1, wherein, In a case where the first processor is configured to perform the prediction and the compression of the channel state information: The first receiver of the apparatus receives reference signals on one or more time instances of a prediction window, the reference signals being used for performance monitoring of the artificial intelligence function or model. 11.The apparatus of claim 1, wherein, In a case where the first processor is configured to perform the prediction and the compression of the channel state information: The compression of the channel state information and the prediction of the channel state information are performed separately, The first processor separately monitors a performance of the artificial intelligence function or model used by the compression of the channel state information and a performance of the artificial intelligence function or model used by the prediction of the channel state information. 12.The apparatus of claim 11, wherein, The first processor calculates a performance indicator of the artificial intelligence function or model used by the compression of the channel state information using measured channel state information, wherein, The measured channel state information is obtained through reference signals configured for the terminal device for inference operation or for performance monitoring. 13.The apparatus of claim 11, wherein, The first receiver of the apparatus receives reference signals on one or more time instances of a prediction window; and The first processor calculates a performance indicator of the artificial intelligence function or model used by the prediction of the channel state information according to the reference signals. 14.The apparatus of claim 13, wherein, The first transmitter of the apparatus reports the calculated performance indicator after each measurement for the reference signal; or The first transmitter transmits a plurality of the performance indicators corresponding to a plurality of the reference signals within one of the prediction windows or an average of the plurality of the performance indicators after measurements for the plurality of the reference signals. 15.The apparatus of claim 11, wherein, The first processor monitors a first performance indicator obtained by the artificial intelligence function or model used by the compression of the channel state information and a second performance indicator obtained by the artificial intelligence function or model used by the prediction of the channel state information are transmitted separately or together. 16.The apparatus of claim 1, wherein, In a case where the first processor is configured to perform the prediction and the compression of the channel state information: The compression of the channel state information and the prediction of the channel state information are performed jointly, The first processor jointly monitors the artificial intelligence function or model used by the compression of the channel state information and the artificial intelligence function or model used by the prediction of the channel state information. 17.The apparatus of claim 16, wherein, The first receiver of the apparatus receives reference signals on one or more time instances of an observation window; and and The first processor calculates a performance index according to the reference signal, the performance index being used to represent a performance of an artificial intelligence function or model used for compression of channel state information and a performance of an artificial intelligence function or model used for prediction of channel state information.

18. The apparatus of claim 1, wherein, The first processor is configured with a periodic or semi-persistent reference signal, the reference signal being used to collect data required for training of an artificial intelligence function or model, The periodicity of the reference signal is configurable and depends on an artificial intelligence function or model supported by the terminal device, The first transmitter of the apparatus transmits the collected data to a network device through layer 1 signaling or non-layer 1 signaling.

19. The apparatus of claim 18, wherein, The data is transmitted through a physical uplink control channel or a physical uplink shared channel.

20. The apparatus of claim 18, wherein, In a case where the transmitted data collected is transmitted through layer 1 signaling, when a reference signal for inference operation is used to collect the data: A channel quality indicator or rank indicator for collecting the data and a channel quality indicator or rank indicator for inference operation are transmitted separately; A channel quality indicator or rank indicator for collecting the data is transmitted, or a channel quality indicator or rank indicator for inference operation is transmitted; Or A channel quality indicator or rank indicator for inference operation is transmitted, and a channel quality indicator or rank indicator for collecting the data is calculated.

Images