Channel state information prediction method and apparatus

Abstract

Provided in the embodiments of the present application are a channel state information (CSI) prediction method and apparatus. The CSI prediction apparatus is applied to a terminal device. The terminal device is configured with an artificial intelligence model or function for CSI prediction. The apparatus comprises a first receiver and a first processor, wherein the first receiver receives configuration information for CSI prediction from a network device, and the first receiver further receives a reference signal in a measurement window on the basis of the configuration information; and the first processor performs CSI-prediction-related processing on the basis of the received reference signal.

Description

Channel State Information Prediction Method and Apparatus Technical Field

[0001] The embodiments of this application relate to the field of communication technology. Background Technology

[0002] In NR Rel-18, artificial intelligence / machine learning (AI / ML) for the air interface was studied. AI / ML can be used for the following use cases: Channel State Information (CSI) feedback enhancement, beam management, and positioning enhancement. CSI feedback enhancement can include CSI prediction and CSI compression; beam management can include spatial beam prediction (BM case-1) and temporal beam prediction (BM case-2); positioning enhancement can include direct positioning and AI / ML-assisted positioning.

[0003] In some sub-use cases, a two-sided model can be used, meaning the AI / ML model is on both the terminal device side and the network device side. In other sub-use cases, a one-sided model can be used, meaning the AI / ML model is on either the terminal device side or the network device side. For beam management, the AI / ML model can be on both the terminal device side and / or the network device side.

[0004] In scenarios where AI / ML functions or models are used for CSI prediction, performance monitoring can be performed on the AI / ML functions or models to check their performance, thereby facilitating the control of the AI / ML functions or models. This control may be, for example, at least one of activation, deactivation, selection, switching, and fallback of the AI / ML function or model.

[0005] It should be noted that the above introduction to the technical background is only for the purpose of providing a clear and complete explanation of the technical solutions of this application and facilitating understanding by those skilled in the art. It should not be assumed that these technical solutions are known to those skilled in the art simply because they have been described in the background section of this application. Summary of the Invention

[0006] In scenarios where AI / ML functions or models are used for CSI prediction, the AI / ML functions or models can be configured on the terminal device side. The terminal device can measure the reference signal on one or more time instances in the observation window or measurement window, and predict the CSI on one or more time instances in the future prediction window.

[0007] In CSI prediction, AI / ML functions or models can be configured on the terminal device side. Network device-side equipment can configure at least one of the following for the terminal device: a resource set for inference, a resource set for performance monitoring, and a resource set for training data collection. The AI / ML function or model can utilize the resource set for inference to perform CSI prediction, the resource set for performance monitoring to monitor its performance, and the resource set for training data collection to obtain training data for training the AI / ML function or model.

[0008] The inventors discovered that when the terminal device is equipped with an artificial intelligence model or function for channel state information prediction (CSI prediction), it is necessary to enhance the measurement and / or reporting of reference signals. Further research is needed on how to perform channel state information prediction.

[0009] To address at least one of the above-mentioned problems, embodiments of this application provide a channel state information prediction method and apparatus.

[0010] According to one aspect of the embodiments of this application, a channel state information prediction apparatus is provided, applied to a terminal device, the terminal device being configured with an artificial intelligence model or function for channel state information (CSI) prediction, the apparatus comprising a first receiver and a first processor, wherein:

[0011] The first receiver receives configuration information from the network device for Channel State Information (CSI) prediction.

[0012] The first receiver also receives a reference signal in the measurement window according to the configuration information.

[0013] The first processor performs channel state information (CSI) prediction correlation processing based on the received reference signal.

[0014] According to another aspect of the embodiments of this application, a channel state information prediction apparatus is provided, applied to a network device, wherein the terminal device is configured with an artificial intelligence model or function for channel state information (CSI) prediction, the apparatus including a second transmitter, wherein:

[0015] The second transmitter sends configuration information for channel state information prediction to the terminal device;

[0016] The second transmitter sends a reference signal to the terminal device in the measurement window according to the configuration information.

[0017] The terminal device performs channel state information (CSI) prediction correlation processing based on the received reference signal.

[0018] The beneficial effects of the embodiments of this application include: the terminal device receives configuration information from the network device, receives a reference signal in the measurement window according to the configuration information, and then performs channel state information (CSI) prediction correlation processing based on the received reference signal. This enhances the channel state information prediction correlation processing, improves the accuracy of channel state information prediction, and enhances the performance and efficiency of AI / ML.

[0019] Specific embodiments of this application are disclosed in detail with reference to the following description and accompanying drawings, indicating how the principles of this application can be adopted. It should be understood that the embodiments of this application are not limited in scope. Within the spirit and scope of the appended claims, embodiments of this application include many changes, modifications, and equivalents.

[0020] Features described and / or illustrated for one embodiment may be used in the same or similar manner in one or more other embodiments, combined with features in other embodiments, or substituted for features in other embodiments.

[0021] It should be emphasized that the term "including / comprises" as used herein refers to the presence of a feature, whole, step, or component, but does not exclude the presence or addition of one or more other features, wholes, steps, or components. Attached Figure Description

[0022] The elements and features described in one drawing or embodiment of this application may be combined with elements and features shown in one or more other drawings or embodiments. Furthermore, in the drawings, similar reference numerals denote corresponding parts in several drawings and can be used to indicate corresponding parts used in more than one embodiment.

[0023] Figure 1 is a schematic diagram of a communication system according to an embodiment of this application;

[0024] Figure 2 is a schematic diagram of a channel state information prediction method according to an embodiment of this application;

[0025] Figure 3 is another schematic diagram of the channel state information prediction method according to an embodiment of this application;

[0026] Figure 4 is a schematic diagram of the measurement window and prediction window in an embodiment of this application;

[0027] Figure 5 is an example of a reasoning result report being cancelled according to an embodiment of this application;

[0028] Figure 6 is an example diagram showing that the reasoning results of an embodiment of this application are still reported;

[0029] Figure 7 is a schematic diagram of a channel state information prediction method according to an embodiment of this application;

[0030] Figure 8 is a schematic diagram of a channel state information prediction device according to an embodiment of this application;

[0031] Figure 9 is a schematic diagram of a channel state information prediction device according to an embodiment of this application;

[0032] Figure 10 is a schematic diagram of a terminal device according to an embodiment of this application;

[0033] Figure 11 is a schematic diagram of a network device according to an embodiment of this application. Detailed Implementation

[0034] Referring to the accompanying drawings, the foregoing and other features of this application will become apparent from the following description. Specific embodiments of this application are specifically disclosed in the description and drawings, illustrating partial implementations in which the principles of this application may be employed. It should be understood that this application is not limited to the described embodiments; rather, it includes all modifications, variations, and equivalents falling within the scope of the appended claims.

[0035] In the embodiments of this application, the terms "first," "second," etc., are used to distinguish different elements by name, but do not indicate the spatial arrangement or chronological order of these elements, and these elements should not be limited by these terms. The term "and / or" includes any one or more of the terms listed in association and all combinations thereof. The terms "comprising," "including," "having," etc., refer to the presence of the stated features, elements, components, or assemblies, but do not exclude the presence or addition of one or more other features, elements, components, or assemblies.

[0036] In the embodiments of this application, the singular forms "a," "the," etc., including the plural forms, should be broadly understood as "a kind" or "a class" rather than limited to the meaning of "an." Furthermore, the term "the" should be understood to include both the singular and plural forms, unless the context explicitly indicates otherwise. Additionally, the term "according to" should be understood as "at least partially based on…," and the term "based on" should be understood as "at least partially based on…," unless the context explicitly indicates otherwise.

[0037] In the embodiments of this application, the term "communication network" or "wireless communication network" may refer to a network that conforms to any of the following communication standards, such as Long Term Evolution (LTE), LTE-Advanced (LTE-A), Wideband Code Division Multiple Access (WCDMA), High-Speed ​​Packet Access (HSPA), etc.

[0038] Furthermore, communication between devices in a communication system can be carried out according to communication protocols at any stage, including but not limited to the following communication protocols: 1G (generation), 2G, 2.5G, 2.75G, 3G, 4G, 4.5G and 5G, New Radio (NR), future 6G, etc., and / or other currently known or future communication protocols.

[0039] In the embodiments of this application, the term "network device" refers, for example, to a device in a communication system that connects a terminal device to a communication network and provides services to that terminal device. Network devices may include, but are not limited to, the following devices: base station (BS), access point (AP), transmission reception point (TRP), broadcast transmitter, mobile management entity (MME), gateway, server, radio network controller (RNC), base station controller (BSC), etc.

[0040] Base stations can include, but are not limited to: NodeBs (or NBs), evolved NodeBs (eNodeBs or eNBs), and 5G base stations (gNBs), IAB hosts, etc. They can also include Remote Radio Heads (RRHs), Remote Radio Units (RRUs), relays, or low-power nodes (e.g., femeto, pico, etc.). The term "base station" can encompass some or all of their functions, and each base station can provide communication coverage to 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.

[0041] In the embodiments of this application, the terms "User Equipment" (UE) or "Terminal Equipment" (TE) refer, for example, to a device that accesses a communication network and receives network services through a network device. A terminal device can be fixed or mobile, and may also be referred to as a mobile station (MS), terminal, subscriber station (SS), access terminal (AT), station, etc.

[0042] The terminal device may 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, smartphone, smartwatch, digital camera, etc.

[0043] For example, in scenarios such as the Internet of Things (IoT), terminal devices can also be machines or devices for monitoring or measurement, such as including but not limited to: machine-type communication (MTC) terminals, vehicle communication terminals, device-to-device (D2D) terminals, machine-to-machine (M2M) terminals, and so on.

[0044] Furthermore, the terms "network side" or "network equipment side" refer to one side of the network, which can be a base station or include one or more network devices as described above. The terms "user side," "terminal side," or "terminal equipment side" refer to the side of the user or terminal, which can be a UE or include one or more terminal devices as described above. Unless otherwise specified, "equipment" can refer to either network equipment or terminal equipment.

[0045] The following examples illustrate the scenarios of embodiments of this application, but this application is not limited thereto.

[0046] Figure 1 is a schematic diagram of a communication system according to an embodiment of this application, illustrating the case of a terminal device and a network device as examples. As shown in Figure 1, the communication system 100 may include a network device 101 and terminal devices 102 and 103. For simplicity, Figure 1 only illustrates the case of two terminal devices and one network device, but the embodiments of this application are not limited to this.

[0047] In this embodiment of the application, network device 101 and terminal devices 102 and 103 can transmit existing services or services that can be implemented in the future. For example, these services may include, but are not limited to: enhanced mobile broadband (eMBB), massive machine-type communication (mMTC), and ultra-reliable and low-latency communication (URLLC), etc.

[0048] It is worth noting that Figure 1 shows that both terminal devices 102 and 103 are within the coverage area of ​​network device 101, but this application is not limited to this. Both terminal devices 102 and 103 may be outside the coverage area of ​​network device 101, or one terminal device 102 may be within the coverage area of ​​network device 101 while the other terminal device 103 may be outside the coverage area of ​​network device 101.

[0049] In the embodiments of this application, higher-layer signaling may be, for example, Radio Resource Control (RRC) signaling; for example, referred to as an RRC message, including MIB, system information, dedicated RRC messages; or referred to as an RRC information element. Higher-layer signaling may also be, for example, Medium Access Control (MAC) signaling; or referred to as a MAC control element. However, this application is not limited to these.

[0050] In the embodiments of this application, one or more AI / ML models can be configured and run in network devices and / or terminal devices. AI / ML models can be used for various signal processing functions in wireless communication, such as CSI prediction, CSI compression, beam prediction, positioning management, etc.; this application is not limited thereto.

[0051] In the various embodiments of this application, the following terms have the same meaning and can be used interchangeably: AI / ML, artificial intelligence, artificial intelligence, or machine learning.

[0052] In various embodiments of this application, AI / ML functionality / model may also be referred to as AI / ML function or model, artificial intelligence or machine learning function or model, artificial intelligence function or model, AI / ML function (functionality) / model (model), artificial intelligence function, artificial intelligence model, etc., which have the same meaning and can be used interchangeably in this application.

[0053] First aspect of the embodiments

[0054] This application provides a channel state information (CSI) prediction method, which is described from the perspective of a terminal device.

[0055] Figure 2 is a schematic diagram of a channel state information prediction method according to an embodiment of this application. As shown in Figure 2, the method includes:

[0056] Operation 201: The terminal device receives configuration information from the network device for Channel State Information (CSI) prediction;

[0057] Operation 202: The terminal device receives a reference signal in the measurement window according to the configuration information, and performs channel state information (CSI) prediction correlation processing based on the received reference signal.

[0058] It is worth noting that Figure 2 above is only an illustrative description of the embodiments of this application, but this application is not limited thereto. For example, the execution order between various operations can be appropriately adjusted, and other operations can be added or some operations can be removed. Those skilled in the art can make appropriate modifications based on the above content, and are not limited to the description in Figure 2 above.

[0059] In some embodiments, a functionality refers to an AI / ML feature / feature group enabled by a configuration, wherein the configuration is supported based on conditions indicated by the capabilities of the terminal device (e.g., UE).

[0060] For example, an AL / ML function can be one or more functions, or one or more logical models, or one or more sub-functions, or one or more features, or one or more feature groups.

[0061] For example, the function could be to use AI / ML for spatial beam prediction, or to use AI / ML for temporal beam prediction, or to use AI / ML for CSI prediction, or to use AI / ML for direct positioning, or to use AI / ML for assisted positioning, and so on.

[0062] In some embodiments, the AI / ML function / model can be used for channel state information prediction. The terminal device can measure the reference signal at one or more time instances within an observation window or prediction window, and input the measurement results into the AI / ML function / model to predict the CSI at one or more time instances within the prediction window in the future.

[0063] For ease of description, the prediction of channel state information based on AI / ML functions / models will be referred to as model inference or inference operation, the performance monitoring based on AI / ML functions / models will be referred to as performance monitoring, and the operation of collecting training data for training AI / ML functions / models will be referred to as training data collection.

[0064] In some embodiments of operation 201, the configuration information may include configuration information for one or more reference signals, such as CSI-RS configuration information, etc. This application is not limited thereto; further details regarding specific configuration information can be found in related technologies. In operation 201, the configuration information used for channel state information (CSI) prediction may include configuration information for training data collection, and / or configuration information for model inference, and / or configuration information for performance monitoring.

[0065] Figure 3 is another schematic diagram of the channel state information prediction method according to an embodiment of this application, illustrated using a terminal device configured with AI / ML as an example. As shown in Figure 3, the method includes the following operations 301, 302, 303, and 304:

[0066] 301. The terminal device receives configuration information from the network device; for example, the configuration information includes configuration information for model inference, and / or configuration information for performance monitoring, and / or configuration information for training data collection.

[0067] 302, The terminal device receives a reference signal; for example, the terminal device receives a reference signal at a time instance in a measurement window used for inference, and / or the terminal device receives a reference signal at a time instance in a measurement window used for performance monitoring, and / or the terminal device receives a reference signal at a time instance in a measurement window used for training data collection.

[0068] 303. The terminal device performs channel state information (CSI) prediction correlation processing based on the received reference signal, wherein the channel state information (CSI) prediction correlation processing includes, for example:

[0069] The terminal device measures a reference signal received at a time instance within a measurement window used for inference, and inputs the measurement result into an AI / ML function / model that outputs a prediction result for at least one time instance within a prediction window; or,

[0070] The terminal device measures a reference signal received at a time instance within a measurement window used for performance monitoring, and inputs the measurement result into an AI / ML function / model. This AI / ML function / model outputs a prediction result for at least one time instance within a prediction window, and calculates performance metrics based on the prediction result and the reference signal received at that time instance within the prediction window; or...

[0071] The terminal device measures the reference signal received at time instances in the measurement window and prediction window used for training data collection, and uses the measurement results as training data.

[0072] 304. The terminal device sends the processing result (i.e., the result obtained from operation 303) to the network device or the device for training AI / ML functions / models; for example, sending the CSI prediction result and / or the performance metric calculation result to the network device, and sending the training data to the device for training AI / ML functions / models.

[0073] Operation 301 above corresponds to operation 201 in Figure 2, and operations 302, 303 and 304 above correspond to operation 202 in Figure 2.

[0074] For example, the AI / ML function resides on the terminal device side. After enabling or activating the AI / ML function, the terminal device performs measurements based on reference signals from the network device side, uses AI / ML to predict channel state information based on the measurement results, and sends the prediction results to the network device.

[0075] It is worth noting that Figure 3 above is only an illustrative description of the embodiments of this application, but this application is not limited thereto. For example, the execution order between various operations can be appropriately adjusted, and other operations can be added or some operations can be removed. Those skilled in the art can make appropriate modifications based on the above content, and are not limited to the description in Figure 3 above.

[0076] The above illustrations depict channel state information (CSI) prediction related processing based on AI / ML, but this application is not limited thereto.

[0077] In some embodiments, the terminal device can measure reference signals transmitted over one or more time instances within a measurement window / observation window. The terminal-side AI / ML model / function can predict channel state information for one or more future time instances (i.e., the prediction window).

[0078] In this application, the terms measurement window, observation window, measurement window, and observation window have the same meaning and can be used interchangeably.

[0079] Figure 4 is a schematic diagram of the measurement window and prediction window according to an embodiment of this application. As shown in Figure 4, the measurement window may include multiple time instances (e.g., T1 to T4). The network device may send reference signals (e.g., CSI-RS) to the terminal device at each time instance. The terminal device may measure these CSI-RS and input the measurement results into an AI / ML model / function for inference, thereby predicting the channel state information of multiple time instances (e.g., T5 to T8) in the prediction window. As shown in Figure 5, the terminal device may report the inference results (i.e., the predicted channel state information of multiple time instances in the prediction window) to the network device.

[0080] However, in certain situations, such as due to cell discontinuous transmission (DTX) or terminal discontinuous reception (DRX), or collisions between CSI-RS and other reference signals or channels, or downlink control signaling indications (e.g., indications for power-saving downlink control signaling DCI 2_6), the reference signal used for measurement may not be transmitted on one or more time instances within the measurement window. In such cases, the input dimension of the AI / ML model will change, thus affecting the performance of inference operations. The following addresses these issues.

[0081] In some embodiments, for channel state information prediction with a terminal-side model, if at least some reference signals are not received on one or more time instances in the measurement window (or observation window) used for inference, the corresponding model inference and / or inference result reporting is cancelled or dropped; or, the terminal device still performs the corresponding model inference and reports the inference results.

[0082] For example, for channel state information prediction with a UE-side model, in the measurement / observation window, if the reference signal (e.g., CSI-RS) on one or more time instances or all time instances is not transmitted by the gNB, or if a portion of the reference signal (e.g., CSI-RS) on one or more time instances or all time instances is not transmitted by the gNB, the inference result report is cancelled / dropped.

[0083] Figure 5 is an example of an inference result report being cancelled according to an embodiment of this application. As shown in Figure 5, if the CSI-RS of time instance T3 in the measurement window is not received by the UE (or not sent by the gNB), the inference result report is cancelled or discarded.

[0084] For example, for channel state information prediction with a UE-side model, in the measurement / observation window, if the reference signal (e.g., CSI-RS) on one or more time instances or all time instances is not sent by the gNB, or if a portion of the reference signal (e.g., CSI-RS) on one or more time instances or all time instances is not sent by the gNB, the terminal device will still perform the corresponding model inference and report the inference results. That is, the inference result report is not cancelled or dropped.

[0085] In some embodiments, the measurement result corresponding to at least a portion of the reference signal that was not received is set to a predetermined value, such as null or zero, and the measurement result is input into an artificial intelligence model or function to perform inference and report the inference result.

[0086] For example, for channel state information prediction with a UE-side model, in the measurement / observation window, if the reference signal (e.g., CSI-RS) on one or more time instances or all time instances is not transmitted by the gNB, or if a portion of the reference signal (e.g., CSI-RS) on one or more time instances or all time instances is not transmitted by the gNB, the inference operation is still performed and the input of the artificial intelligence model or function corresponding to the untransmitted reference signal is set to 0 or null, and the terminal device still reports the inference result to the network device.

[0087] In some embodiments, the measurement result corresponding to at least a portion of the unreceived reference signal is set as the most recent measurement result prior to the one or more time instances. In some examples, the terminal device sets the input of the artificial intelligence model or function corresponding to the unreceived at least a portion of the reference signal as the measurement result of the previous reference signal of the unreceived at least a portion of the reference signal, and performs inference and reports the inference result.

[0088] For example, for channel state information prediction with a UE-side model, within the measurement / observation window, if a reference signal (e.g., CSI-RS) on one or more time instances or all time instances is not transmitted by the gNB, or if a portion of the reference signal (e.g., CSI-RS) on one or more time instances or all time instances is not transmitted by the gNB, the inference operation is still performed, and the input of the untransmitted reference signal is set to the most recent measurement result. Furthermore, the terminal device still reports the inference result to the network device.

[0089] Figure 6 is an example diagram showing that the inference result is still reported according to an embodiment of this application. As shown in Figure 6, if the CSI-RS of time instance T3 in the measurement window is not received by the UE (or not sent by the gNB), the inference operation is still performed, and the measurement result of time instance T2 can still be used for time instance T3. Furthermore, the terminal device still reports the inference result to the network device.

[0090] In some embodiments, the terminal device sets the measurement results corresponding to at least a portion of the unreceived reference signals (or, the input of an artificial intelligence model or function) based on the measurement results of the available reference signals, and performs inference and reports the inference results. In some examples, the measurement results corresponding to at least a portion of the unreceived reference signals are determined by the terminal device through interpolation based on the measurement results before and after the one or more time instances.

[0091] For example, in channel state information prediction with a UE-side model, within the measurement / observation window, if a reference signal (e.g., CSI-RS) on one or more time instances or all time instances is not transmitted by the gNB, or if a portion of the reference signal (e.g., CSI-RS) on one or more time instances or all time instances is not transmitted by the gNB, the inference operation is still performed, and the input of the untransmitted reference signal is determined by the UE. Furthermore, the terminal device still reports the inference results to the network device.

[0092] For example, still using Figure 6 as an example, the UE can process the existing available measurement results, such as interpolating the measurement results of time instance T2 before time instance T3 and time instance T4 after time instance T3, and then using the obtained result as the measurement result of time instance T3. This application is not limited to this; for example, other related information can also be used, and / or, operations such as averaging and weighted summation can be used.

[0093] In some embodiments, for channel state information prediction with a terminal-side model, if at least a portion of the reference signal is not received on one or more time instances in the measurement window (or observation window), and the number of said time instances exceeds a threshold (i.e., the number of time instances containing the unreceived at least a portion of the reference signal exceeds the threshold), then the inference and / or inference result reporting corresponding to the unreceived at least a portion of the reference signal is cancelled.

[0094] For example, if the number of time instances that have not transmitted a reference signal exceeds a certain threshold, which is configurable or predefined, the inference operation is canceled / abandoned, and the inference result report is canceled / discarded. Otherwise, the inference operation is still performed, and the inference result is still reported.

[0095] In some embodiments, if at least a portion of the reference signal is not received at a predetermined time instance in the measurement window (or observation window), the model inference and / or inference result report corresponding to the unreceived at least a portion of the reference signal is cancelled. The predetermined time instance includes the first or last time instance in the measurement window used for inference.

[0096] For example, if the reference signal is not transmitted at some predetermined time instances in the measurement / observation window, such as the first or last time instance in the measurement / observation window, the inference operation is canceled / abandoned, and the inference result report is canceled / discarded. Otherwise, the inference operation is still performed, and the inference result is still reported.

[0097] In some embodiments, a configured reference signal (e.g., a configured CSI-RS resource(s) or a part of a configured CSI-RS resource(s)) is not transmitted on one or more or all time instances within the measurement window, possibly for one of the following reasons:

[0098] - Discontinuous transmission in the cell (cell DTX);

[0099] -Discontinuous reception by the terminal (UE DRX);

[0100] -CSI-RS may conflict with other reference signals or channels;

[0101] -DCI indication, such as DCI format 2_6 for energy saving.

[0102] The above are just some examples of factors that may cause the reference signal to not be transmitted, but this application is not limited to these.

[0103] The above provides an illustrative explanation of model inference; the following section will explain performance monitoring.

[0104] In some embodiments, for channel state information prediction with a terminal-side model, if at least some reference signals are not received on one or more time instances used for performance monitoring or associated with performance monitoring, the corresponding performance monitoring and / or monitoring result report is cancelled; alternatively, the terminal device may still perform the corresponding performance monitoring and report the monitoring results. Here, performance monitoring can also be referred to as performance metric calculation, and the performance monitoring result can also be referred to as a performance metric.

[0105] In some embodiments, for CSI prediction with an end-side model, if at least some reference signals are not received on one or more time instances in the prediction window used for performance monitoring, then the one or more time instances are not used for performance metric calculation and / or the corresponding performance metrics are not reported.

[0106] For example, for performance monitoring using a UE-side model, if reference signals (e.g., CSI-RS) used for monitoring are not transmitted in one, multiple, or all time instances within the prediction window, or if a portion of the reference signals used for monitoring are not transmitted in one, multiple, or all time instances, then these time instances are not used for performance metric calculation. Furthermore, these performance metrics may also not be reported.

[0107] In some embodiments, for CSI prediction with an end-side model, if at least some reference signals are not received on one or more time instances in a prediction window used for performance monitoring, then all time instances of that prediction window are not used for performance metric calculation and / or the corresponding performance metrics are not reported.

[0108] For example, for performance monitoring using a UE-side model, if, within a prediction window, a reference signal (e.g., CSI-RS) used for monitoring is not transmitted in one, multiple, or all time instances, or if a portion of the reference signal used for monitoring in one, multiple, or all time instances is not transmitted, then all time instances in that prediction window will not be used for performance metric calculation. Furthermore, these performance metrics may also not be reported.

[0109] In some embodiments, for CSI prediction with an end-side model, if at least some reference signals are not received on one or more time instances in the prediction window used for performance monitoring, the performance metric calculation is restarted.

[0110] For example, within a prediction window, if a reference signal (e.g., CSI-RS) used for monitoring on one, multiple, or all time instances is not transmitted, or if a portion of the reference signal used for monitoring on one, multiple, or all time instances is not transmitted, the performance metric calculation restarts. For example, if a timer and / or counter are configured for performance monitoring, the timer and / or counter are restarted. Furthermore, these performance metrics and / or performance monitoring outputs may not be reported.

[0111] In some embodiments, the configured reference signal (e.g., a configured CSI-RS resource or a portion thereof) is not transmitted on one or more time instances within the prediction window, possibly for at least one of the following reasons:

[0112] - Discontinuous transmission in the cell (cell DTX);

[0113] -Discontinuous reception by the terminal (UE DRX);

[0114] -CSI-RS may conflict with other reference signals or channels;

[0115] -DCI indication, such as DCI format 2_6 for energy saving.

[0116] The above are just some examples of factors that may cause the reference signal to not be transmitted, but this application is not limited to these.

[0117] In some embodiments, for CSI prediction with an end-side model, if at least a portion of the reference signal is not received on one or more time instances in the measurement window (or observation window) associated with performance monitoring, then the one or more time instances are not used for performance metric calculation and / or the corresponding performance metrics are not reported.

[0118] For example, for performance monitoring using a UE-side model, if reference signals (e.g., CSI-RS) are not transmitted in one or more time instances or all time instances within a measurement / observation window, or if a portion of the reference signals are not transmitted in one or more time instances or all time instances, these time instances will not be used for performance metric calculation if the measurement / observation window is associated with performance monitoring. Furthermore, these performance metrics may also not be reported.

[0119] In some embodiments, for CSI prediction with an end-side model, if at least a portion of the reference signal is not received on one or more time instances in a measurement window (or observation window) associated with performance monitoring, then all time instances of the measurement window (or observation window) are not used for performance metric calculation and / or the corresponding performance metrics are not reported.

[0120] For example, for performance monitoring using a UE-side model, within a measurement / observation window, if reference signals (e.g., CSI-RS) are not transmitted in one or more time instances or all time instances, or if a portion of the reference signals are not transmitted in one or more time instances or all time instances, then all time instances of that measurement / observation window will not be used for performance metric calculation if the measurement / observation window is associated with performance monitoring. Furthermore, these performance metrics may also not be reported.

[0121] In some embodiments, for CSI prediction with an end-side model, if at least a portion of the reference signal is not received on one or more time instances in the measurement window (or observation window) associated with performance monitoring, the performance metric calculation is restarted.

[0122] For example, in a measurement / observation window, if a reference signal (e.g., CSI-RS) is not transmitted in one or more time instances or all time instances, or if a portion of the reference signal is not transmitted in one or more time instances or all time instances, the performance metric calculation restarts if the measurement / observation window is associated with performance monitoring. If a timer and / or counter is configured for performance monitoring, that timer and / or counter is restarted. Furthermore, these performance metrics may not be reported.

[0123] In some embodiments, the configured reference signal (e.g., configured CSI-RS resource or a portion thereof) is not transmitted on one or more time instances within the measurement / observation window, possibly for at least one of the following reasons:

[0124] - Discontinuous transmission in the cell (cell DTX);

[0125] -Discontinuous reception by the terminal (UE DRX);

[0126] -CSI-RS may conflict with other reference signals or channels;

[0127] -DCI indication, such as DCI format 2_6 for energy saving.

[0128] The above are just some examples of factors that may cause the reference signal to not be transmitted, but this application is not limited to these.

[0129] The above provides an illustrative explanation of performance monitoring; the following section will explain the collection of training data.

[0130] In some embodiments, for CSI prediction with an end-side model, if at least a portion of the reference signals used for data collection are not received, the corresponding data sample or dataset is dropped or marked.

[0131] For example, regarding the collection of training data for CSI using the UE-side model, if the configured reference signal or a portion thereof is not transmitted, the corresponding data sample is discarded, or the corresponding data sample is marked with a specific indicator, such as null, or the corresponding data set is deleted.

[0132] In some embodiments, the configured reference signal or a portion of the configured reference signal used for training data collection is not transmitted, possibly for at least one of the following reasons:

[0133] - Discontinuous transmission in the cell (cell DTX);

[0134] -Discontinuous reception by the terminal (UE DRX);

[0135] -CSI-RS may conflict with other reference signals or channels;

[0136] -DCI indication, such as DCI format 2_6 for energy saving.

[0137] The above are just some examples of factors that may cause the reference signal to not be transmitted, but this application is not limited to these.

[0138] The above embodiments are merely illustrative examples of embodiments of this application, but this application is not limited thereto, and appropriate modifications can be made based on the above embodiments. For example, the above embodiments can be used alone, or one or more of the above embodiments can be combined.

[0139] As can be seen from the above embodiments, the terminal device receives configuration information from the network device, receives a reference signal in the measurement window according to the configuration information, and then performs channel state information (CSI) prediction correlation processing based on the received reference signal. This enhances the channel state information prediction correlation processing, improves the accuracy of channel state information prediction, and enhances the performance and efficiency of AI / ML.

[0140] Second aspect of the embodiments

[0141] This application provides a channel state information prediction method, described from the perspective of a network device. The embodiments of the second aspect can be combined with the embodiments of the first aspect, and the content identical to that of the embodiments of the first aspect will not be repeated.

[0142] Figure 7 is a schematic diagram of a channel state information prediction method according to an embodiment of this application. As shown in Figure 7, the method includes:

[0143] Operation 701: Send configuration information for channel state information prediction to the terminal device;

[0144] Operation 702: According to the configuration information, send a reference signal to the terminal device in the measurement window.

[0145] In this application, the terminal device is configured with an artificial intelligence model or function for channel state information (CSI) prediction, and the terminal device can perform channel state information (CSI) prediction related processing based on the reference signal received in operation 702.

[0146] In some embodiments, if at least some of the reference signals are not received at one or more time instances in the measurement window used for inference, the terminal device performs the corresponding model inference and reports the inference results.

[0147] In some embodiments, the terminal device sets the input of the artificial intelligence model or function corresponding to the at least part of the reference signal that has not been received to null or zero, and performs inference and reports the inference results.

[0148] In some embodiments, the terminal device sets the input of the artificial intelligence model or function corresponding to the unreceived at least part of the reference signal as the measurement result of the previous reference signal of the unreceived at least part of the reference signal, and performs inference and reports the inference result.

[0149] In some embodiments, the terminal device sets the input of the artificial intelligence model or function corresponding to the at least part of the unreceived reference signals based on the measurement results of the available reference signals, and performs inference and reports the inference results.

[0150] In some embodiments, if at least a portion of the reference signal is not received on one or more time instances in the measurement window used for inference, the corresponding inference and / or inference result reporting is cancelled.

[0151] In some embodiments, if the number of time instances in which the at least some of the reference signals that were not received exceeds a threshold, the inference and / or inference result reporting corresponding to the at least some of the reference signals that were not received is cancelled.

[0152] In some embodiments, if the time instance in which the unreceived at least part of the reference signal is located is a predetermined time instance, the inference and / or inference result reporting corresponding to the unreceived at least part of the reference signal is cancelled.

[0153] In some embodiments, the predetermined time instance includes the first or last time instance in the measurement window used for inference.

[0154] In some embodiments, if at least a portion of the reference signal is not received on one or more time instances in the prediction window used for performance monitoring, then the one or more time instances are not used for performance metric calculation and / or the corresponding performance metrics are not reported.

[0155] In some embodiments, if at least some reference signals are not received on one or more time instances in a prediction window used for performance monitoring, then all time instances of the prediction window are not used for performance metric calculation and / or the performance metrics corresponding to all time instances of the prediction window are not reported.

[0156] In some embodiments, if at least a portion of the reference signal is not received on one or more time instances in the prediction window used for performance monitoring, the performance metric calculation is restarted.

[0157] In some embodiments, performance metrics associated with the prediction window are not reported.

[0158] In some embodiments, if at least a portion of the reference signal is not received on one or more time instances in a measurement window associated with performance monitoring, then the one or more time instances are not used for performance metric calculation and / or the corresponding performance metrics are not reported.

[0159] In some embodiments, if at least some reference signals are not received on one or more time instances of a measurement window associated with performance monitoring, then all time instances of the measurement window are not used for performance metric calculation and / or the performance metrics corresponding to all time instances of the prediction window are not reported.

[0160] In some embodiments, if at least a portion of the reference signal is not received on one or more time instances within a measurement window associated with performance monitoring, the performance metric calculation is restarted.

[0161] In some embodiments, performance metrics associated with the measurement window are not reported.

[0162] In some embodiments, if at least a portion of the reference signals used for training data collection are not received, the corresponding data samples or datasets are discarded or marked.

[0163] In some embodiments, the network device may receive feedback information and / or report information sent by the terminal device. For example, the terminal device may report inference results and / or performance monitoring results and / or training data collection results to the network device, but this application is not limited thereto.

[0164] The above embodiments are merely illustrative examples of embodiments of this application, but this application is not limited thereto, and appropriate modifications can be made based on the above embodiments. For example, the above embodiments can be used alone, or one or more of the above embodiments can be combined.

[0165] Third aspect of the embodiments

[0166] This application provides a channel state information prediction device. This device may be, for example, a terminal device, or one or more components or parts configured within a terminal device; details identical to those in the first and second aspects will not be repeated.

[0167] Figure 8 is a schematic diagram of a channel state information prediction device according to an embodiment of this application. As shown in Figure 8, the channel state information prediction device 800 according to an embodiment of this application includes a first receiver 801 and a first processor 802, wherein:

[0168] The first receiver 801 receives configuration information from the network device for Channel State Information (CSI) prediction.

[0169] The first receiver 801 also receives a reference signal in the measurement window according to the configuration information.

[0170] The first processor 802 performs channel state information (CSI) prediction correlation processing based on the received reference signal.

[0171] In some embodiments, as shown in FIG8, the channel state information prediction device 800 may further include a first transmitter 803, which sends report information / feedback information to the network device, but this application is not limited thereto.

[0172] In some embodiments, if at least a portion of the reference signal is not received on one or more time instances in the measurement window used for inference, the apparatus performs corresponding model inference and reports the inference results.

[0173] In some embodiments, the device sets the input of the artificial intelligence model or function corresponding to the at least part of the unreceived reference signals to null or zero, and performs inference and reports the inference results.

[0174] In some embodiments, the device sets the input of the artificial intelligence model or function corresponding to the unreceived at least partial reference signal as the measurement result of the previous reference signal of the unreceived at least partial reference signal, and performs inference and reports the inference result.

[0175] In some embodiments, the device sets the input of the artificial intelligence model or function corresponding to the at least part of the unreceived reference signals based on the measurement results of the available reference signals, and performs inference and reports the inference results.

[0176] In some embodiments, if at least a portion of the reference signal is not received on one or more time instances in the measurement window used for inference, the corresponding inference and / or inference result reporting is cancelled.

[0177] In some embodiments, if the number of time instances in which the at least some of the reference signals that were not received exceeds a threshold, the inference and / or inference result reporting corresponding to the at least some of the reference signals that were not received is cancelled.

[0178] In some embodiments, if the time instance in which the unreceived at least part of the reference signal is located is a predetermined time instance, the inference and / or inference result reporting corresponding to the unreceived at least part of the reference signal is cancelled.

[0179] In some embodiments, the predetermined time instance includes the first or last time instance in the measurement window used for inference.

[0180] In some embodiments, if at least a portion of the reference signal is not received on one or more time instances in the prediction window used for performance monitoring, then the one or more time instances are not used for performance metric calculation and / or the corresponding performance metrics are not reported.

[0181] In some embodiments, if at least some reference signals are not received on one or more time instances in a prediction window used for performance monitoring, then all time instances of the prediction window are not used for performance metric calculation and / or the performance metrics corresponding to all time instances of the prediction window are not reported.

[0182] In some embodiments, if at least a portion of the reference signal is not received on one or more time instances in the prediction window used for performance monitoring, the performance metric calculation is restarted.

[0183] In some embodiments, performance metrics associated with the prediction window are not reported.

[0184] In some embodiments, if at least a portion of the reference signal is not received on one or more time instances in a measurement window associated with performance monitoring, then the one or more time instances are not used for performance metric calculation and / or the corresponding performance metrics are not reported.

[0185] In some embodiments, if at least some reference signals are not received on one or more time instances of a measurement window associated with performance monitoring, then all time instances of the measurement window are not used for performance metric calculation and / or the performance metrics corresponding to all time instances of the prediction window are not reported.

[0186] In some embodiments, if at least a portion of the reference signal is not received on one or more time instances within a measurement window associated with performance monitoring, the performance metric calculation is restarted.

[0187] In some embodiments, performance metrics associated with the measurement window are not reported.

[0188] In some embodiments, if at least a portion of the reference signals used for training data collection are not received, the corresponding data samples or datasets are discarded or marked.

[0189] It is worth noting that the above description only covers the components or modules relevant to this application, but this application is not limited thereto. The channel state information prediction device 800 may also include other components or modules, and for details regarding these components or modules, please refer to relevant technologies.

[0190] Furthermore, for simplicity, Figure 8 only illustrates the connection relationships or signal flow between the various components or modules, but those skilled in the art should understand that various related technologies such as bus connections can be used. The aforementioned components or modules can be implemented using hardware facilities such as processors, memory, transmitters, and receivers; this application does not limit this implementation.

[0191] Fourth aspect of the embodiment

[0192] This application provides a channel state information prediction device. This device may be, for example, a network device, or one or more components or parts configured within a network device; details identical to those in the embodiments of the first to third aspects will not be repeated.

[0193] Figure 9 is another schematic diagram of a channel state information prediction device according to an embodiment of this application. As shown in Figure 9, the channel state information prediction device 900 includes a second transmitter 901, wherein:

[0194] The second transmitter 901 sends configuration information for channel state information prediction to the terminal device;

[0195] The second transmitter 901 sends a reference signal to the terminal device in the measurement window according to the configuration information.

[0196] In some embodiments, as shown in FIG9, the channel state information prediction device 900 may further include a second receiver 902, which receives report information / feedback information sent by the terminal device, but this application is not limited thereto.

[0197] In this application, the terminal device is configured with an artificial intelligence model or function for channel state information (CSI) prediction, and the terminal device performs channel state information (CSI) prediction related processing based on reference signals sent by the network device.

[0198] In some embodiments, if at least some of the reference signals are not received at one or more time instances in the measurement window used for inference, the terminal device performs the corresponding model inference and reports the inference results.

[0199] In some embodiments, the terminal device sets the input of the artificial intelligence model or function corresponding to the at least part of the reference signal that has not been received to null or zero, and performs inference and reports the inference results.

[0200] In some embodiments, the terminal device sets the input of the artificial intelligence model or function corresponding to the unreceived at least part of the reference signal as the measurement result of the previous reference signal of the unreceived at least part of the reference signal, and performs inference and reports the inference result.

[0201] In some embodiments, the terminal device sets the input of the artificial intelligence model or function corresponding to the at least part of the unreceived reference signals based on the measurement results of the available reference signals, and performs inference and reports the inference results.

[0202] In some embodiments, if at least a portion of the reference signal is not received on one or more time instances in the measurement window used for inference, the corresponding inference and / or inference result reporting is cancelled.

[0203] In some embodiments, if the number of time instances in which the at least some of the reference signals that were not received exceeds a threshold, the inference and / or inference result reporting corresponding to the at least some of the reference signals that were not received is cancelled.

[0204] In some embodiments, if the time instance in which the unreceived at least part of the reference signal is located is a predetermined time instance, the inference and / or inference result reporting corresponding to the unreceived at least part of the reference signal is cancelled.

[0205] In some embodiments, the predetermined time instance includes the first or last time instance in the measurement window used for inference.

[0206] In some embodiments, if at least a portion of the reference signal is not received on one or more time instances in the prediction window used for performance monitoring, then the one or more time instances are not used for performance metric calculation and / or the corresponding performance metrics are not reported.

[0207] In some embodiments, if at least some reference signals are not received on one or more time instances in a prediction window used for performance monitoring, then all time instances of the prediction window are not used for performance metric calculation and / or the performance metrics corresponding to all time instances of the prediction window are not reported.

[0208] In some embodiments, if at least a portion of the reference signal is not received on one or more time instances in the prediction window used for performance monitoring, the performance metric calculation is restarted.

[0209] In some embodiments, performance metrics associated with the prediction window are not reported.

[0210] In some embodiments, if at least a portion of the reference signal is not received on one or more time instances in a measurement window associated with performance monitoring, then the one or more time instances are not used for performance metric calculation and / or the corresponding performance metrics are not reported.

[0211] In some embodiments, if at least some reference signals are not received on one or more time instances of a measurement window associated with performance monitoring, then all time instances of the measurement window are not used for performance metric calculation and / or the performance metrics corresponding to all time instances of the prediction window are not reported.

[0212] In some embodiments, if at least a portion of the reference signal is not received on one or more time instances within a measurement window associated with performance monitoring, the performance metric calculation is restarted.

[0213] In some embodiments, performance metrics associated with the measurement window are not reported.

[0214] In some embodiments, if at least a portion of the reference signals used for training data collection are not received, the corresponding data samples or datasets are discarded or marked.

[0215] It is worth noting that the above description only covers the components or modules relevant to this application, but this application is not limited thereto. The channel state information prediction device 900 may also include other components or modules, and for details regarding these components or modules, please refer to relevant technologies.

[0216] Furthermore, for simplicity, Figure 9 only illustrates the connection relationships or signal flow between the various components or modules, but those skilled in the art should understand that various related technologies such as bus connections can be used. The aforementioned components or modules can be implemented using hardware facilities such as processors, memory, transmitters, and receivers; this application does not limit this implementation.

[0217] Fifth aspect of the embodiment

[0218] This application also provides a communication system, which can be referred to FIG1. ​​The contents that are the same as those in the embodiments of the first to fourth aspects will not be repeated.

[0219] In some embodiments, the communication system 100 may include at least:

[0220] Network devices that send configuration information for channel state information prediction;

[0221] The terminal device receives configuration information from the network device for channel state information prediction and performs channel state information (CSI) prediction correlation processing based on the received reference signal.

[0222] This application also provides a terminal device, but the application is not limited thereto and may also include other devices.

[0223] Figure 10 is a schematic diagram of a terminal device according to an embodiment of this application. As shown in Figure 10, the terminal device 1000 may include a processor 1010 and a memory 1020; the memory 1020 stores data and programs and is coupled to the processor 1010. It is worth noting that this figure is exemplary; other types of structures may also be used to supplement or replace this structure to implement telecommunications functions or other functions.

[0224] For example, processor 1010 may be configured to execute a program to implement the method described in the embodiments of the first aspect.

[0225] As shown in Figure 10, the terminal device 1000 may further include: a communication module 1030, an input unit 1040, a display 1050, and a power supply 1060. The functions of these components are similar to those in the prior art and will not be described in detail here. It is worth noting that the terminal device 1000 does not necessarily include all the components shown in Figure 10; these components are not essential. Furthermore, the terminal device 1000 may also include components not shown in Figure 10, which can be referred to in the prior art.

[0226] This application also provides a network device, such as a base station, but this application is not limited to this and may also include other network devices.

[0227] Figure 11 is a schematic diagram of the network device according to an embodiment of this application. As shown in Figure 11, the network device 1100 may include: a processor 1110 (e.g., a central processing unit CPU) and a memory 1120; the memory 1120 is coupled to the processor 1110. The memory 1120 can store various data; in addition, it also stores an information processing program 1130, and executes the program 1130 under the control of the processor 1110.

[0228] For example, processor 1110 may be configured to execute a program to implement the method described in the embodiments of the second aspect.

[0229] In addition, as shown in Figure 11, network device 1100 may also include: transceiver 1140 and antenna 1150, etc.; the functions of the above components are similar to those in the prior art, and will not be described in detail here. It is worth noting that network device 1100 does not necessarily have to include all the components shown in Figure 11; in addition, network device 1100 may also include components not shown in Figure 11, which can be referred to in the prior art.

[0230] This application also provides a computer program, wherein when the program is executed in a terminal device, the program causes the terminal device to perform the channel state information prediction method described in the first aspect of the embodiment.

[0231] This application also provides a storage medium storing a computer program, wherein the computer program causes a terminal device to execute the channel state information prediction method described in the first aspect of the embodiment.

[0232] This application also provides a computer program, wherein when the program is executed in a network device, the program causes the network device to perform the channel state information prediction method described in the second aspect of the embodiment.

[0233] This application also provides a storage medium storing a computer program, wherein the computer program causes a network device to perform the channel state information prediction method described in the second aspect of the embodiment.

[0234] The apparatus and methods described above in this application can be implemented in hardware or in combination with software. This application relates to a computer-readable program that, when executed by a logic component, enables the logic component to implement the apparatus or components described above, or to implement the various methods or steps described above. This application also relates to storage media for storing the above programs, such as hard disks, magnetic disks, optical disks, DVDs, flash memory, etc.

[0235] The methods / apparatus described in conjunction with the embodiments of this application can be directly embodied in hardware, software modules executed by a processor, or a combination of both. For example, one or more and / or combinations of one or more functional block diagrams shown in the figures can correspond to various software modules in a computer program flow, or to various hardware modules. These software modules can correspond to the various steps shown in the figures, respectively. These hardware modules can be implemented, for example, using a field-programmable gate array (FPGA) to embed these software modules.

[0236] The software module can reside in RAM memory, flash memory, ROM memory, EPROM memory, EEPROM memory, registers, hard disk, removable disk, CD-ROM, or any other form of storage medium known in the art. A storage medium can be coupled to the processor, enabling the processor to read information from and write information to the storage medium; or the storage medium can be an integral part of the processor. The processor and storage medium can reside in an ASIC. The software module can be stored in the memory of a 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 high-capacity MEGA-SIM card or a high-capacity flash memory device, the software module can be stored in the MEGA-SIM card or the high-capacity flash memory device.

[0237] One or more and / or one or more combinations of functional blocks described in the accompanying drawings can be implemented as a general-purpose processor, digital signal processor (DSP), application-specific integrated circuit (ASIC), field-programmable gate array (FPGA), or other programmable logic device, discrete gate or transistor logic device, discrete hardware component, or any suitable combination thereof for performing the functions described herein. One or more and / or one or more combinations of functional blocks described in the accompanying drawings can also be implemented as a combination of computing devices, such as a combination of a DSP and a microprocessor, multiple microprocessors, one or more microprocessors in communication with a DSP, or any other such configuration.

[0238] The present application has been described above with reference to specific embodiments. However, those skilled in the art should understand that these descriptions are exemplary and not intended to limit the scope of protection of the present application. Those skilled in the art can make various modifications and variations to the present application based on its spirit and principles, and these modifications and variations are also within the scope of the present application.

[0239] Regarding the implementation methods including the above embodiments, the following notes are also disclosed:

[0240] 1. A channel state information (CSI) prediction method, applied to a terminal device, said terminal device being configured with an artificial intelligence model or function for CSI prediction, the method comprising:

[0241] Receive configuration information from network devices for Channel State Information (CSI) prediction;

[0242] According to the configuration information, a reference signal is received in the measurement window, and channel state information (CSI) prediction correlation processing is performed based on the received reference signal.

[0243] 2. A channel state information (CSI) prediction method applied to a network device, wherein the terminal device is configured with an artificial intelligence model or function for CSI prediction, the method comprising:

[0244] Send configuration information for channel state information prediction to the terminal device;

[0245] Based on the configuration information, a reference signal is sent to the terminal device in the measurement window.

[0246] The terminal device performs channel state information (CSI) prediction correlation processing based on the received reference signal.

[0247] 3. A terminal device, comprising a memory and a processor, the memory storing a computer program, the processor being configured to execute the computer program to implement the channel state information prediction method as described in Appendix 1.

[0248] 4. A network device comprising a memory and a processor, the memory storing a computer program and the processor being configured to execute the computer program to implement the channel state information prediction method as described in Appendix 2.

[0249] 5. A computer program product comprising at least a computer program, which, when executed by a processor, causes a terminal device to perform the channel state information prediction method as described in Appendix 1.

[0250] 6. A computer program product comprising at least a computer program that, when executed by a processor, causes a network device to perform the channel state information prediction method as described in Appendix 2.

Claims

1. A channel state information prediction apparatus, applied to a terminal device, said terminal device being configured with an artificial intelligence model or function for channel state information (CSI) prediction, the apparatus comprising a first receiver and a first processor, wherein: The first receiver receives configuration information from the network device for Channel State Information (CSI) prediction. The first receiver also receives a reference signal in the measurement window according to the configuration information. The first processor performs channel state information (CSI) prediction correlation processing based on the received reference signal.

2. The apparatus of claim 1, wherein, If at least some of the reference signals are not received at one or more time instances in the measurement window used for inference, the device performs the corresponding model inference and reports the inference results.

3. The apparatus according to claim 2, wherein, The device sets the input of the artificial intelligence model or function corresponding to the at least part of the reference signal that has not been received to empty (null) or zero (0), and performs inference and reports the inference results.

4. The apparatus according to claim 2, wherein, The device sets the input of the artificial intelligence model or function corresponding to the unreceived at least part of the reference signal as the measurement result of the previous reference signal of the unreceived at least part of the reference signal, and performs inference and reports the inference result.

5. The apparatus according to claim 2, wherein, The device sets the input of the artificial intelligence model or function corresponding to the at least part of the unreceived reference signals based on the measurement results of the available reference signals, and performs inference and reports the inference results.

6. The apparatus of claim 1, wherein, If at least a portion of the reference signal is not received on one or more time instances within the measurement window used for inference, the corresponding inference and / or inference result reporting is cancelled.

7. The apparatus according to claim 6, wherein, If the number of time instances in which the at least some of the reference signals that were not received exceeds a threshold, the inference and / or inference result reporting corresponding to the at least some of the reference signals that were not received is cancelled.

8. The apparatus according to claim 6, wherein, If the time instance in which the unreceived at least part of the reference signal is located is a predetermined time instance, then the inference and / or inference result reporting corresponding to the unreceived at least part of the reference signal is cancelled.

9. The apparatus according to claim 8, wherein, The predetermined time instance includes either the first or the last time instance in the measurement window used for inference.

10. The apparatus of claim 1, wherein, If at least some reference signals are not received on one or more time instances in the prediction window used for performance monitoring, then the one or more time instances are not used for performance metric calculation and / or the corresponding performance metrics are not reported.

11. The apparatus of claim 1, wherein, If at least some reference signals are not received on one or more time instances in the prediction window used for performance monitoring, then all time instances of the prediction window are not used for performance metric calculation and / or the performance metrics corresponding to all time instances of the prediction window are not reported.

12. The apparatus of claim 1, wherein, If at least some of the reference signals are not received on one or more time instances in the prediction window used for performance monitoring, the performance metric calculation is restarted.

13. The apparatus of claim 12, wherein, Performance metrics related to the prediction window are not reported.

14. The apparatus of claim 1, wherein, If at least some reference signals are not received on one or more time instances in a measurement window associated with performance monitoring, then the one or more time instances are not used for performance metric calculations and / or the corresponding performance metrics are not reported.

15. The apparatus of claim 1, wherein, If at least some reference signals are not received on one or more time instances of the measurement window associated with performance monitoring, then all time instances of the measurement window are not used for performance metric calculation and / or the performance metrics corresponding to all time instances of the prediction window are not reported.

16. The apparatus of claim 1, wherein, If at least some of the reference signals are not received on one or more time instances in the measurement window associated with performance monitoring, the performance metric calculation is restarted.

17. The apparatus of claim 16, wherein, Performance metrics related to the measurement window are not reported.

18. The apparatus of claim 1, wherein, If at least some of the reference signals used for training data collection are not received, the corresponding data samples or datasets are discarded or labeled.

19. A channel state information prediction device, applied to network equipment, wherein, The terminal device is configured with an artificial intelligence model or function for channel state information (CSI) prediction, and the device includes a second transmitter, wherein: The second transmitter sends configuration information for channel state information prediction to the terminal device; The second transmitter sends a reference signal to the terminal device in the measurement window according to the configuration information. The terminal device performs channel state information (CSI) prediction correlation processing based on the received reference signal.

20. A communication system, comprising: Network devices that send configuration information for channel state information prediction; A terminal device receives configuration information from a network device for channel state information prediction, receives a reference signal in a measurement window based on the configuration information, and performs channel state information (CSI) prediction correlation processing based on the received reference signal.

Images