Prediction method and apparatus and configuration method and apparatus

Abstract

Embodiments of the present application provide a prediction method and apparatus and a configuration method and apparatus. The prediction method comprises: a terminal device receives, from a network device, configuration information for configuring channel state information prediction or temporal beam prediction; and the terminal device performs the channel state information prediction or temporal beam prediction on the basis of an AI / ML model / function and on the basis of the configuration information.

Description

Prediction and configuration method and apparatus TECHNICAL FIELD

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

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

[0003] In some sub-use cases, a bilateral model can be used, i.e. the AI / ML model is at the terminal device side and at the network device side. In other sub-use cases, a unilateral model can be used, i.e. the AI / ML model is at the terminal device side or at the network device side. For beam management, the AI / ML model can be at the terminal device side and / or at the network device side.

[0004] It should be noted that the above introduction to the technical background is only for the convenience of clearly and completely describing the technical solutions of the present application, and for the convenience of understanding by those skilled in the art. The above technical solutions cannot be considered as known to those skilled in the art merely because they are described in the background section of the present application.

[0005] SUMMARY

[0006] The inventors have found that there is currently no specific solution for how to perform channel state information prediction (CSI prediction) or temporal beam prediction based on AI / ML.

[0007] To address at least one of the above problems, embodiments of the present application provide a prediction and configuration method and apparatus.

[0008] According to an aspect of embodiments of the present application, a prediction method is provided, comprising:

[0009] The terminal device receives configuration information from the network device for configuring channel state information prediction (CSI prediction) or temporal beam prediction (temporal beam prediction);

[0010] The terminal device performs channel state information prediction or temporal beam prediction according to the configuration information based on the AI / ML model / function.

[0011] According to another aspect of embodiments of the present application, a prediction apparatus is provided, comprising:

[0012] a receiver configured to receive configuration information for configuring channel state information prediction (CSI prediction) or temporal beam prediction (temporal beam prediction) from a network device;

[0013] a processor configured to perform channel state information prediction or temporal beam prediction according to the configuration information based on an AI / ML model / function.

[0014] According to another aspect of embodiments of the present application, a configuration method is provided, comprising:

[0015] a network device sending configuration information for configuring channel state information prediction (CSI prediction) or temporal beam prediction (temporal beam prediction) to a terminal device;

[0016] wherein the configuration information is used by the terminal device to perform channel state information prediction or temporal beam prediction based on an AI / ML model / function.

[0017] According to another aspect of embodiments of the present application, a configuration apparatus is provided, comprising:

[0018] a transmitter configured to send configuration information for configuring channel state information prediction (CSI prediction) or temporal beam prediction (temporal beam prediction) to a terminal device;

[0019] wherein the configuration information is used by the terminal device to perform channel state information prediction or temporal beam prediction based on an AI / ML model / function.

[0020] According to another aspect of embodiments of the present application, a communication system is provided, comprising:

[0021] a network device sending configuration information for configuring channel state information prediction (CSI prediction) or temporal beam prediction (temporal beam prediction) to a terminal device;

[0022] a terminal device performing channel state information prediction or temporal beam prediction according to the configuration information based on an AI / ML model / function.

[0023] One of the beneficial effects of the embodiments of the present application is that the terminal device performs channel state information prediction or time beam prediction according to the configuration information based on the AI / ML model / function. In this way, the accuracy of the prediction can be improved, and the performance and efficiency of AI / ML can be improved.

[0024] Specific embodiments of the application are disclosed in detail in the following description and claims, indicating the ways in which the principles of the application can be employed. It should be understood that the application is not limited in scope to the specific embodiments described herein. In the appended claims, the application includes all changes, modifications and alterations of this specific application within the scope of the claims. It is intended that the application outlive its inventor(s) and that it be enshrined as a fossil, showing a level of ingenuity that this inventor is required to maintain.

[0025] Features described and / or illustrated with respect to one implementation can be used in one or more other implementations in the same or similar manner, in combination with or in place of features in other implementations, or in some cases, in place of some features of the same implementation.

[0026] It should be emphasized that the term "comprises / comprising" when used in this specification is taken to mean the presence of stated features, integers, steps or components but does not preclude the presence or addition of one or more other features, integers, steps, components or groups thereof. BRIEF DESCRIPTION OF DRAWINGS

[0027] Elements and features of the embodiments of the application described in one or more figures or implementations can be combined with elements and features illustrated in one or more other figures or implementations. Additionally, in the drawings, like reference numerals designate corresponding parts throughout the several views, and can be used to designate like components in more than one implementation.

[0028] FIG. 1 is a schematic diagram of a communication system according to an embodiment of the present application;

[0029] FIG. 2 is a schematic diagram of a prediction method according to an embodiment of the present application;

[0030] FIG. 3 is a schematic diagram of AI / ML for prediction according to an embodiment of the present application;

[0031] FIG. 4 is a schematic diagram of a prediction method according to an embodiment of the present application;

[0032] FIG. 5 is a schematic diagram of training data collection according to an embodiment of the present application;

[0033] FIG. 6 is a schematic diagram of training data collection according to an embodiment of the present application;

[0034] FIG. 7 is a schematic diagram of transmitting a reference signal according to an embodiment of the present application;

[0035] FIG. 8 is a schematic diagram of transmitting a reference signal according to an embodiment of the present application;

[0036] FIG. 9 is a schematic diagram of transmitting a reference signal according to an embodiment of the present application;

[0037] FIG. 10 is a schematic diagram of transmitting a reference signal according to an embodiment of the present application;

[0038] FIG. 11 is a schematic diagram of a configuration method according to an embodiment of the present application;

[0039] FIG. 12 is a schematic diagram of a prediction device according to an embodiment of the present application;

[0040] FIG. 13 is a schematic diagram of a configuration device according to an embodiment of the present application;

[0041] FIG. 14 is a schematic diagram of a terminal device according to an embodiment of the present application;

[0042] FIG. 15 is a schematic diagram of a network device according to an embodiment of the present application. DETAILED DESCRIPTION

[0043] 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 present application, which are not intended to limit the scope of the application. In describing specific embodiments of the application, specific terminology is used for the sake of clarity. However, the use of such terminology is not intended to limit the scope of the application, since alternative embodiments of the application can employ techniques that are similar to those described in connection with the described embodiments.

[0044] In the embodiments of the present application, the terms "first", "second", and the like are used to distinguish different elements from each other, but do not indicate 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 "comprise", "include", "have", and the like, refer to the presence of the stated features, elements, elements, or components, but do not exclude the presence or addition of one or more other features, elements, elements, or components.

[0045] In the embodiments of the present application, the singular form "a", "an", and the like includes the plural form, should be understood broadly as "one" or "a kind of", and not limited to the meaning of "one"; in addition, the term "said" should be understood as including 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.

[0046] In the embodiments of the present application, the term "communication network" or "wireless communication network" can refer to a network conforming to any communication standard, such as Long Term Evolution (LTE), LTE-Advanced (LTE-A), Wideband Code Division Multiple Access (WCDMA), High-Speed Packet Access (HSPA), and the like.

[0047] In addition, the communication between devices in the communication system can be carried out according to any phase 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), future 6G, and the like, and / or other currently known or to be developed in the future communication protocols.

[0048] In the embodiments of the present application, the term "network device" refers to a device that accesses a terminal device to a communication network and provides services for the terminal device in the communication system, for example. 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.

[0049] Among them, the base station can include but is not limited to: Node B (NodeB or NB), evolved Node B (eNodeB or eNB), and 5G base station (gNB), IAB donor, and the like, and can also include remote radio head (RRH), remote radio unit (RRU), relay, or low-power node (such as femto, pico, and the like). In addition, the term "base station" can include some or all functions thereof, 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.

[0050] 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 terminal equipment can be fixed or mobile, and can also be referred to as a mobile station (MS), a terminal, a subscriber station (SS), an access terminal (AT), a station, and the like.

[0051] The terminal equipment can include, but is not limited to, the following devices: a cellular phone, a personal digital assistant (PDA), a wireless modem, a wireless communication device, a handheld device, a machine type communication device, a laptop computer, a cordless phone, a smart phone, a smart watch, a digital camera, and the like.

[0052] For another example, in an Internet of Things (IoT) scenario or the like, the terminal equipment can also be a machine or device that performs monitoring or measurement, and can include, but is not limited to, the following devices: a machine type communication (MTC) terminal, a vehicle-mounted communication terminal, a device-to-device (D2D) terminal, a machine-to-machine (M2M) terminal, and the like.

[0053] 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 described above. The term "user side" or "terminal side" or "terminal equipment 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 described above. In this document, "device" can refer to a network device or a terminal device unless otherwise specified.

[0054] The following describes the scenarios of the embodiments of the present application by way of examples, but the present application is not limited thereto.

[0055] 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 equipment and a network device as an example. As shown in FIG. 1, the communication system 100 can include a network device 101 and terminal equipments 102 and 103. For simplicity, FIG. 1 only takes two terminal equipments and one network device as an example for illustration, but the embodiments of the present application are not limited thereto.

[0056] In the embodiments of the present application, the network device 101 and the terminal devices 102, 103 can perform existing services or future implementable service transmission. For example, these services can include, but are not limited to: enhanced mobile broadband (eMBB), massive machine type communication (mMTC), and ultra-reliable and low-latency communication (URLLC), etc.

[0057] It is worth noting that FIG. 1 shows that both terminal devices 102, 103 are within the coverage of the network device 101, but the present application is not limited thereto. Both terminal devices 102, 103 can be outside the coverage of the network device 101, or one terminal device 102 is within the coverage of the network device 101 and the other terminal device 103 is outside the coverage of the network device 101.

[0058] In the embodiments of the present application, the higher layer signaling can be, for example, radio resource control (RRC) signaling; for example, referred to as an RRC message, for example, including MIB, system information, dedicated RRC message; or referred to as an RRC IE. The higher layer signaling can also be, for example, MAC (Medium Access Control) signaling; or referred to as a MAC CE. However, the present application is not limited thereto.

[0059] For time beam prediction (BM case-2), in the case of having an AI / ML model / function at the terminal device side, the terminal device can measure the reference signal on one or more time instances (observation window) and predict the beam for one or more future time instances (prediction window).

[0060] In NR Rel-18, AI / ML for CSI feedback enhancement, including CSI compression and CSI prediction, is also studied. For CSI prediction, the AI / ML model / function is located at the terminal device side. Through CSI prediction, the terminal device can measure the reference signal on one or more time instances (observation window) and predict the CSI for one or more future time instances (prediction window).

[0061] 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 models 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.

[0062] Embodiments of the first aspect

[0063] The embodiments of the present application provide a prediction method, which is described from the terminal device side.

[0064] FIG. 2 is a schematic diagram of a prediction method according to an embodiment of the present application. As shown in FIG. 2, the method comprises:

[0065] 201. The terminal device receives configuration information for configuring channel state information prediction (CSI prediction) or temporal beam prediction from the network device;

[0066] 202. The terminal device performs channel state information prediction or temporal beam prediction according to the configuration information based on an AI / ML model / function.

[0067] It is worth noting that the above FIG. 2 only schematically illustrates the embodiments of the present application, but the present application is not limited thereto. For example, the execution order between the various operations can be appropriately adjusted, and in addition, some operations can be added or some operations can be reduced. Those skilled in the art can make appropriate modifications based on the above description, and the present application is not limited to the description of the above FIG. 2.

[0068] In some embodiments, the functionality refers to an AI / ML feature / feature group enabled by a configuration, wherein the configuration is supported based on a condition indicated by a UE capability.

[0069] For example, the AL / ML functionality can be one or more functions, 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.

[0070] For another example, the functionality can be spatial beam prediction using AI / ML, or can be temporal beam prediction using AI / ML, or can be CSI prediction using AI / ML, or can be direct positioning using AI / ML, or can be positioning assisted by AI / ML, etc.

[0071] In some embodiments, AI / ML functionality / model can be used for CSI prediction. One or more reference signals are used for measurement and the measurement results are input to the AI / ML functionality / model, and one or more CSIs are used for the output of the AI / ML functionality / model for inference.

[0072] In some embodiments, AI / ML functionality / model can be used for time beam prediction. One or more reference signals are used for measurement and the measurement results are input to the AI / ML functionality / model, and one or more beams are used for the output of the AI / ML functionality / model for inference.

[0073] For convenience of description, the CSI prediction or time beam prediction based on AI / ML functionality / model is referred to as model inference or inference operation, the training data collection based on AI / ML functionality / model is referred to as training data collection (the training data collection can also use non-AI / ML method), and the performance monitoring based on AI / ML functionality / model is referred to as performance monitoring.

[0074] In some embodiments, the network device can send configuration information of one or more reference signals, such as CSI-RS configuration information, etc. The present application is not limited thereto, and the specific configuration information can also be referred to related technologies. The configuration information can include configuration information for training data collection, and / or configuration information for model inference, and / or configuration information for performance monitoring.

[0075] FIG. 3 is a schematic diagram of AI / ML for prediction according to an embodiment of the present application. As shown in FIG. 3, one or more reference signals can be received and measured by the terminal device, and the measurement results can be input to the AI / ML, and the CSI or beam can be used by the terminal device for the output of the AI / ML, for example, the measurement results are used as the label data or ground truth data of the AI / ML. The specific content of the AI / ML can be referred to related technologies, which will not be described here.

[0076] FIG. 4 is another schematic diagram of the prediction method of the embodiments of the present application, taking the terminal device configured with AI / ML as an example. As shown in FIG. 4, the method includes:

[0077] 401. The terminal device receives configuration information from the network device; for example, the configuration information includes a reference signal resource set for measurement;

[0078] 402. The network device sends a reference signal (for example, CSI-RS) to the terminal device;

[0079] 403. The terminal device performs prediction based on AI / ML; that is, the terminal device receives the reference signal and performs measurement, and inputs the measurement result into the AI / ML functionality / model; for example, the measurement result of the CSI-RS is input into the AI / ML as input, and the CSI or beam is used for prediction (or inference).

[0080] It is worth noting that the above FIG. 4 only schematically illustrates the embodiments of the present application, but the present application is not limited thereto. For example, the execution order between the operations can be appropriately adjusted, and in addition, some operations can be added or some operations can be reduced. Those skilled in the art can make appropriate modifications based on the above description, and the present application is not limited to the above FIG. 4.

[0081] The above schematically illustrates the CSI prediction or time beam prediction based on AI / ML, but the present application is not limited thereto.

[0082] The following first describes the CSI prediction.

[0083] In some embodiments, the configuration information includes indication information (associated ID) indicating the conditions and / or configurations of the terminal device and / or the network device for the channel state information prediction (CSI prediction).

[0084] For example, for AI / ML operation, consistency between training and inference is ensured, that is, some configurations and conditions on the network device side are the same in the training and inference processes. An associated ID can be introduced. For example, in the same cell, through the same associated ID, the terminal device can take similar properties.

[0085] For example, for CSI prediction with AI / ML functionality / model on the UE side, in order to ensure consistency between training and inference, the gNB can configure an indicator to indicate the configuration and / or condition of the network device side for CSI prediction, and the indicator indicates the configuration and / or condition.

[0086] In some embodiments, for the indication information (association ID) with the same value, the terminal device assumes / determines / considers that at least one of the following characteristics in the same cell is the same or similar: antenna configuration of the network device; CSI-RS periodicity; bandwidth and / or subband size; scenario of the cell.

[0087] For example, using the same ID value, at least within the same cell, the UE can consider that at least one of the following has the same attribute or similar attribute (the present application is not limited to the following attributes):

[0088] -antenna configuration on the gNB side, for example: number of antenna ports (i.e. number of CSI-RS ports) of the gNB downlink, TxRU mapping;

[0089] -periodicity of CSI-RS;

[0090] -bandwidth and subband size

[0091] -scenario of the cell, for example: indoor scenario, outdoor scenario, proportion of indoor scenario and outdoor scenario; line-of-sight condition (LoS), non-line-of-sight condition (NLos), proportion of line-of-sight condition and non-line-of-sight condition.

[0092] In some embodiments, the indication information (association ID) is configured for model inference and training data collection. For example, the indication information (association ID) for model inference and training data collection can be configured through the same RRC; for another example, the indication information (association ID) for model inference and training data collection can be configured through different RRC.

[0093] For example, the association ID can be configured for inference. In order to perform inference, the association ID can be configured through the CSI framework, i.e. the association ID for inference can be configured in the CSI report configuration (CSI-ReportConfig), CSI resource setting (CSI-ResourceConfig) or CSI-RS resource set configuration.

[0094] For example, the association ID can be configured for training data collection. For training data collection, the association ID can be configured through the CSI framework, i.e. the association ID for training data collection can be configured in the CSI report configuration (CSI-ReportConfig), the CSI resource setting (CSI-ResourceConfig), or the CSI-RS resource set configuration.

[0095] In some embodiments, the indication information (association ID) is associated with a cell identity and / or a cell group identity;

[0096] A cell identity is configured to the terminal device; for the indication information (association ID) with the same value, the terminal device assumes that the condition and / or configuration of channel state information prediction (CSI prediction) is the same in the same cell for the same cell identity;

[0097] and / or

[0098] A cell group identity is configured to the terminal device, and a cell group includes one or more cells; for the indication information (association ID) with the same value, the terminal device assumes that the condition and / or configuration of channel state information prediction (CSI prediction) is the same in different cells of the same cell group for the same cell group identity.

[0099] For example, for CSI prediction, the association ID can be used together with the cell ID. That is, for the same cell ID, the UE assumes that the condition and / or configuration is the same for the cells with the same association ID.

[0100] For example, a cell group including one or more cells can be introduced, and a cell group ID can be configured for the UE. In the same cell group (i.e. the same cell group ID), the UE assumes that the condition and / or configuration is the same between the cells with the same association ID.

[0101] In some embodiments, the indication information (association ID) is used for data classification for training data collection;

[0102] The training data includes at least one of the following: indication information (association ID), cell identity, cell group identity, condition and / or configuration, or the training data includes at least one of the following: indication information (association ID), cell identity, cell group identity; and the condition and / or configuration includes at least: CSI-RS port number and / or CSI-RS period.

[0103] For example, for training data collection, the association ID can be collected to classify the data. In addition, the configuration / condition can also be collected, including the port number of CSI-RS, the period of CSI-RS, etc. In addition, the cell ID and / or the cell group ID can also be collected.

[0104] In some examples, the association ID, the cell ID and / or the cell group ID are included in the training data set. In addition, the configuration / condition, such as the port number of CSI-RS, the period of CSI-RS, etc., are also included in the data set.

[0105] In other examples, the association ID, the cell ID and / or the cell group ID are included in the training data set. In addition, the configuration / condition, such as the port number of CSI-RS, the period of CSI-RS, etc., are not included in the data set.

[0106] In some embodiments, for training data collection, the speed of the terminal device is used for data classification; the speed information of the terminal device is included in the data set (explicitly), or the speed information of the terminal device is associated with the data set (implicitly).

[0107] For example, for training data collection of CSI prediction, the UE speed can be used to classify the data explicitly, or the UE speed can be used to classify the data implicitly. In addition, the UE speed information can be included in the data set explicitly, or the UE speed information can be included in the data set implicitly.

[0108] In some embodiments, the terminal device receives a request sent by the network device; the terminal device reports the speed information to the network device according to the request; and the network device configures a reference signal for the training data collection, and the collected training data includes or is associated with the speed information.

[0109] For example, the gNB can first request the UE to report the UE speed information, and then the gNB can configure a reference signal for the UE for training data collection.

[0110] FIG. 5 is a schematic diagram of training data collection according to an embodiment of the present application. As shown in FIG. 5, the training data collection includes:

[0111] 501, the network device requests the terminal device to report speed information;

[0112] 502, the terminal device reports speed information to the network device according to the request;

[0113] 503, the network device configures a reference signal for the training data collection;

[0114] 504, the terminal device performs measurement and collects training data; and

[0115] 505, the terminal device reports a training data set to the network device, and the collected training data includes or is associated with the speed information.

[0116] It is worth noting that the above FIG. 5 only schematically illustrates the embodiments of the present application, but the present application is not limited thereto. For example, the execution order between the operations can be appropriately adjusted, and in addition, some operations can be added or some operations can be reduced. Those skilled in the art can make appropriate modifications based on the above description, and the present application is not limited to the above FIG. 5.

[0117] In some embodiments, the terminal device receives a request sent by the network device; the terminal device measures and / or reports time-domain channel properties (TDCP) according to the request, wherein TDCP represents channel correlation in time domain and can reflect speed information of the terminal device; and the network device configures a reference signal for the training data collection, and the collected training data includes or is associated with the time-domain channel properties (TDCP).

[0118] For example, for training data collection, the gNB can first request the UE to measure time-domain channel properties (TDCP) and report TDCP, wherein TDCP represents channel correlation in time domain and can reflect UE speed information. The gNB can send a reference signal for the UE to measure and (optionally) report TDCP. Then, the gNB can further configure a reference signal for the UE to collect training data. The TDCP information can be included in the data set to classify the data.

[0119] FIG. 6 is a schematic diagram of training data collection according to an embodiment of the present application. As shown in FIG. 6, the training data collection includes:

[0120] 601, the network device requests the terminal device to report speed-related TDCP;

[0121] 602, the network device configures a reference signal for measuring the TDCP;

[0122] 603, the terminal device performs measurement and obtains the TDCP; and

[0123] 604, the terminal device reports the TDCP to the network device;

[0124] 605, the network device configures a reference signal for the training data collection;

[0125] 606, the terminal device performs measurement and collects training data; and

[0126] 607, the terminal device reports a set of training data to the network device, the collected training data including or being associated with the TDCP.

[0127] It is worth noting that the above Figure 6 only schematically illustrates the embodiments of the present application, but the present application is not limited thereto. For example, the execution order between the operations can be appropriately adjusted, and in addition, some operations can be added or some operations can be reduced. Those skilled in the art can make appropriate modifications based on the above content, and the present application is not limited to the above Figure 6.

[0128] In some embodiments, for model inference, the terminal device reports AI / ML function information supported or applicable to the network device, and / or in the case of a change in the speed of the terminal device, reports updated AI / ML function information supported or applicable to the network device.

[0129] For example, for inference of CSI prediction, the UE can report AI / ML function supported or AI / ML function applicable. For another example, if the UE speed changes, the UE can report to update the AI / ML function supported or the AI / ML function applicable.

[0130] In some embodiments, the AI / ML function information supported or applicable indicates or is associated with at least one of the following:

[0131] CSI-RS period supported or preferred;

[0132] Number of time instances in the observation window supported or preferred;

[0133] Number of time instances in the prediction window supported or preferred;

[0134] Terminal device speed corresponding to the AI / ML function information supported or applicable;

[0135] Channel-related information in time domain (e.g., TDCP) corresponding to the supported or applicable AI / ML function information.

[0136] In some embodiments, the terminal device receives a reference signal for model inference from the network device; wherein the reference signal is configured by the network device according to the supported or applicable AI / ML function information.

[0137] For example, the gNB configures the reference signal for inference according to the supported or applicable AI / ML function reported by the UE. The reference signal configuration includes, for example, the configuration of CSI-RS period, observation window and prediction window, etc.

[0138] FIG. 7 is a schematic diagram of transmitting a reference signal according to an embodiment of the present application. As shown in FIG. 7, transmitting a reference signal includes:

[0139] 701, the terminal device reports the supported or applicable AI / ML function information to the network device;

[0140] 702, the network device configures the reference signal for inference.

[0141] It is worth noting that the above FIG. 7 only illustrates the embodiments of the present application schematically, but the present application is not limited thereto. For example, the execution order between the operations can be adjusted appropriately, and in addition, some operations can be added or some operations can be reduced. Those skilled in the art can make appropriate modifications based on the above content, and the present application is not limited to the above FIG. 7.

[0142] In some embodiments, the terminal device receives a reference signal for model inference from the network device; wherein the reference signal is configured by the network device according to the supported or applicable AI / ML function information, and the reference signal configuration corresponding to the AI / ML function supported or applicable to the terminal device is adjusted (scaled) according to the speed of the terminal device and / or channel-related information in time domain.

[0143] For example, the gNB can adjust (scale) the reference signal configuration according to the supported or applicable AI / ML function reported by the UE and the UE speed information or channel-related information (e.g., TDCP). The reference signal configuration includes, for example, the configuration of CSI-RS period, observation window and prediction window, etc.

[0144] For example, the UE report can support a CSI-RS period of 10ms at a UE speed of 30km / h. If the UE speed becomes 60km / h, the gNB can configure a CSI-RS period of 5ms.

[0145] FIG. 8 is a schematic diagram of transmitting reference signals according to an embodiment of the present application. As shown in FIG. 8, the transmitting reference signals include:

[0146] 801, the terminal device reports to the network device AI / ML function information supported or applicable to the terminal device;

[0147] 802, the terminal device reports to the network device speed information or TDCP;

[0148] 803, the network device configures reference signals for inference; wherein the network device adjusts (scales) the reference signal configuration according to the speed and / or TDCP of the terminal device.

[0149] It is worth noting that the above FIG. 8 only schematically illustrates the embodiments of the present application, but the present application is not limited thereto. For example, the execution order between the operations can be appropriately adjusted, and in addition, some operations can be added or some operations can be reduced. Those skilled in the art can make appropriate modifications based on the above description, and the present application is not limited to the above FIG. 8.

[0150] In some embodiments, the terminal device measures and / or reports time domain channel properties (TDCP) related to the speed of the terminal device; reports to the network device updated AI / ML function information supported or applicable to the terminal device; receives information of activated AI / ML function and reference signals for model inference from the network device; wherein the reference signals are configured by the network device according to the AI / ML function information supported or applicable to the terminal device, or the reference signal configuration corresponding to the AI / ML function supported or applicable to the terminal device is adjusted (scaled) by the network device according to the speed of the terminal device and / or channel related information in time domain.

[0151] For example, the gNB can first configure the reference signals to the UE, so that the UE measures and optionally reports the measured TDCP. Alternatively, the UE can trigger / request the gNB to configure the reference signals for the UE to measure and optionally report the measured TDCP.

[0152] In some examples, after measurement, the UE can update the applicable AI / ML function and report the updated applicable AI / ML function to the gNB; the gNB configures the activated AI / ML function and the reference signals for inference according to the updated AI / ML function.

[0153] FIG. 9 is a schematic diagram of transmitting reference signals according to an embodiment of the present application. As shown in FIG. 9, the transmitting reference signals include:

[0154] 901, the terminal device reports the AI / ML function information supported or applicable to the network device to the network device;

[0155] 902, the network device configures a reference signal for measuring the TDCP;

[0156] 903, the terminal device performs measurement and obtains the TDCP;

[0157] 904, the terminal device reports the updated AI / ML function supported or applicable to the network device to the network device, and optionally also reports the TDCP;

[0158] 905, the network device configures the activated AI / ML function and configures a reference signal for inference.

[0159] It is worth noting that the above Figure 9 only schematically illustrates the embodiments of the present application, but the present application is not limited thereto. For example, the execution order between the operations can be appropriately adjusted, and in addition, some operations can be added or some operations can be reduced. Those skilled in the art can make appropriate modifications based on the above content, and the present application is not limited to the above Figure 9.

[0160] In some other examples, after measurement, the UE can report the measured TDCP, and the gNB can scale the reference signal configuration according to the TDCP reported by the UE.

[0161] Figure 10 is a schematic diagram of transmitting a reference signal according to an embodiment of the present application. As shown in Figure 10, transmitting a reference signal includes:

[0162] 1001, the terminal device reports the AI / ML function information supported or applicable to the network device to the network device;

[0163] 1002, the network device configures a reference signal for measuring the TDCP;

[0164] 1003, the terminal device performs measurement and obtains the TDCP;

[0165] 1004, the terminal device reports the TDCP to the network device;

[0166] 1005, the network device configures a reference signal for inference; wherein the network device scales the reference signal configuration according to the TDCP.

[0167] It is notable that the above Fig. 10 only schematically illustrates the embodiments of the present application, but the present application is not limited thereto. For example, the execution order between the respective operations can be appropriately adjusted, and furthermore, some operations can be added or some operations can be removed. A person skilled in the art can appropriately modify based on the above description, and the present application is not limited to the above Fig. 10.

[0168] The temporal beam prediction will be described again below.

[0169] In some embodiments, the configuration information includes indication information (associated ID) for indicating the condition and / or configuration of the terminal device and / or the network device for the temporal beam prediction.

[0170] For example, for AI / ML operation, consistency between training and inference is ensured, that is, some configurations and conditions of the network device side are the same in the training and inference processes. An associated ID can be introduced. For example, in the same cell, through the same associated ID, the terminal device can take similar properties.

[0171] For example, for the temporal beam prediction (BM case-2) with AI / ML function / model on the UE side, in order to ensure the consistency between training and inference, the gNB can configure an indicator to indicate the configuration and / or condition of the network device side for the temporal beam prediction (BM case-2), and the indicator indicates the configuration and / or condition.

[0172] In some embodiments, for the indication information (associated ID) with the same value, the terminal device assumes that at least one of the following properties in the same cell is the same or similar: downlink transmission beam (DL Tx beam); and / or CSI-RS period; and / or CSI-RS port number.

[0173] For example, using the same ID value, at least in the same cell, the UE can consider that at least one of the following has the same property or similar property (the present application is not limited to the following properties):

[0174] - downlink transmission beam;

[0175] - and / or the period of CSI-RS;

[0176] - and / or the number of CSI-RS ports.

[0177] In some embodiments, the indication information (association ID) is configured for model inference and training data collection. For example, the indication information (association ID) for model inference and training data collection can be configured through the same RRC; for another example, the indication information (association ID) for model inference and training data collection can be configured through different RRCs.

[0178] In some embodiments, the indication information (association ID) is associated with a cell identity and / or a cell group identity;

[0179] A cell identity is configured to the terminal device; for the indication information (association ID) with the same value, the terminal device assumes that the condition and / or configuration of time beam prediction (BM case-2) is the same within the same cell for the same cell identity;

[0180] and / or

[0181] A cell group identity is configured to the terminal device, one cell group including one or more cells; for the indication information (association ID) with the same value, the terminal device assumes that the condition and / or configuration of time beam prediction (BM case-2) is the same within different cells of the same cell group for the same cell group identity.

[0182] For example, for time beam prediction (BM case-2), the association ID can be used together with the cell ID. That is, for the same cell ID, the UE assumes that the condition and / or configuration is the same for the cells with the same association ID.

[0183] For another example, a cell group including one or more cells can be introduced, and a cell group ID can be configured to the UE. Within the same cell group (i.e., the same cell group ID), the UE assumes that the condition and / or configuration is the same between the cells with the same association ID.

[0184] In some embodiments, the indication information (association ID) is used for data classification for training data collection;

[0185] The training data includes at least one of the following: indication information (association ID), cell identity, cell group identity, condition and / or configuration, or the training data includes at least one of the following: indication information (association ID), cell identity, cell group identity; and the condition and / or configuration includes at least: CSI-RS periodicity and / or CSI-RS port number.

[0186] For example, for training data collection, the association ID can be collected to classify the data. In addition, the configuration / condition can also be collected, including the port number of CSI-RS, CSI-RS periodicity, etc. In addition, the cell ID and / or cell group ID can also be collected.

[0187] In some examples, the association ID, cell ID and / or cell group ID are included in the training data set. In addition, the configuration / condition, such as CSI-RS periodicity, CSI-RS port number, etc., are also included in the data set.

[0188] In other examples, the association ID, cell ID and / or cell group ID are included in the training data set. In addition, the configuration / condition, such as CSI-RS periodicity, CSI-RS port number, etc., are not included in the data set.

[0189] In some embodiments, for training data collection, the speed of the terminal device is used for data classification; the speed information of the terminal device is included in the data set (explicitly), or the speed information of the terminal device is associated with the data set (implicitly).

[0190] For example, for training data collection related to time beam prediction (BM case-2), the UE speed can be used to classify the data explicitly, or the UE speed can be used to classify the data implicitly. In addition, the UE speed information can be included in the data set explicitly, or the UE speed information can be included in the data set implicitly.

[0191] In some embodiments, the terminal device receives a request sent by the network device; the terminal device reports the speed information to the network device according to the request; and the network device configures a reference signal for the training data collection, and the collected training data includes or is associated with the speed information.

[0192] For example, the gNB can first request the UE to report the UE speed information, and then the gNB can configure a reference signal for the UE for training data collection. For training data collection, reference can also be made to FIG. 5.

[0193] In some embodiments, the terminal device receives a request sent by the network device; the terminal device measures and / or reports a time-domain channel property (TDCP) related to the speed of the terminal device according to the request; wherein the network device configures a reference signal for the training data collection, and the collected training data includes or is associated with the time-domain channel property (TDCP).

[0194] For example, for training data collection, the gNB can first request the UE to measure and report a time-domain channel property (TDCP), where the TDCP represents the channel correlation in time domain and can reflect the UE speed information. The gNB can send a reference signal for the UE to measure and (optionally) report the TDCP. Then, the gNB can further configure a reference signal for collecting training data from the UE. The TDCP information can be included in the data set to classify the data. Reference can also be made to FIG. 6 for training data collection.

[0195] In some embodiments, for model inference, the terminal device reports AI / ML function information supported or applicable to the network device, and / or reports updated AI / ML function information supported or applicable to the network device in the case of a change in the speed of the terminal device.

[0196] For example, for inference related to time beam prediction (BM case-2), the UE can report AI / ML function supported or applicable. For another example, if the UE speed changes, the UE can report to update the AI / ML function supported or applicable.

[0197] In some embodiments, the AI / ML function information supported or applicable indicates or is associated with at least one of the following:

[0198] supported or preferred CSI-RS periodicity;

[0199] supported or preferred number of time instances in an observation window;

[0200] supported or preferred number of time instances in a prediction window;

[0201] terminal device speed corresponding to the AI / ML function information supported or applicable;

[0202] channel correlation information (e.g., TDCP) in time domain corresponding to the AI / ML function information supported or applicable.

[0203] In some embodiments, the terminal device receives reference signals for model inference from the network device; wherein the reference signals are configured by the network device according to the supported or applicable AI / ML function information.

[0204] For example, the gNB configures reference signals for inference according to the supported or applicable AI / ML function reported by the UE. The reference signal configuration includes, for example, configuration of CSI-RS periodicity, observation window and prediction window, etc. Reference can be made to FIG. 7.

[0205] In some embodiments, the terminal device receives reference signals for model inference from the network device; wherein the reference signals are configured by the network device according to the supported or applicable AI / ML function information, and the reference signal configuration corresponding to the AI / ML function supported or applicable to the terminal device is scaled according to the speed of the terminal device and / or channel correlation information in time domain.

[0206] For example, the gNB can scale the reference signal configuration according to the supported or applicable AI / ML function reported by the UE, and UE speed information or channel correlation information (e.g. TDCP). The reference signal configuration includes, for example, configuration of CSI-RS periodicity, observation window and prediction window, etc. Reference can be made to FIG. 8.

[0207] For example, the UE report can support a CSI-RS periodicity of 10 ms at a UE speed of 30 km / h. If the UE speed becomes 60 km / h, the gNB can configure a CSI-RS periodicity of 5 ms.

[0208] In some embodiments, the terminal device measures and / or reports time domain channel properties (TDCP) related to the speed of the terminal device; reports updated supported or applicable AI / ML function information to the network device; receives information of activated AI / ML function and reference signals for model inference from the network device; wherein the reference signals are configured by the network device according to the supported or applicable AI / ML function information, or the reference signal configuration corresponding to the AI / ML function supported or applicable to the terminal device is scaled according to the speed of the terminal device and / or channel correlation information in time domain.

[0209] For example, the gNB can first configure reference signals to the UE so that the UE can perform measurements and optionally report the measured TDCP. Alternatively, the UE can trigger / request the gNB to configure reference signals for the UE to perform measurements and optionally report the measured TDCP.

[0210] In some examples, after the measurement, the UE can update the applicable AI / ML function and report the updated applicable AI / ML function to the gNB; the gNB configures the activated AI / ML function and configures the reference signal for inference according to the updated AI / ML function. Reference can be made to FIG. 9.

[0211] In some other examples, after the measurement, the UE can report the measured TDCP, and the gNB can scale the reference signal configuration according to the TDCP reported by the UE. Reference can be made to FIG. 10.

[0212] The above various embodiments are only exemplarily described, but the present application is not limited thereto, and can be appropriately modified 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.

[0213] As can be seen from the above embodiments, the terminal device performs channel state information prediction or temporal beam prediction according to the configuration information based on the AI / ML model / function. In this way, the accuracy of the prediction can be improved, and the performance and efficiency of AI / ML can be improved.

[0214] Embodiments of the second aspect

[0215] The embodiments of the present application provide a configuration method, which is described from the network device side. The embodiments of the second aspect can be combined with the embodiments of the first aspect, and the same content as the embodiments of the first aspect will not be described again.

[0216] FIG. 11 is a schematic diagram of a configuration method according to an embodiment of the present application. As shown in FIG. 11, the method comprises:

[0217] 1101, the network device sends configuration information for configuring channel state information prediction (CSI prediction) or temporal beam prediction to the terminal device.

[0218] As shown in FIG. 11, the method can further comprise:

[0219] 1102, the terminal device performs channel state information prediction or temporal beam prediction according to the configuration information based on the AI / ML model / function.

[0220] It is worth noting that the above FIG. 11 only exemplarily describes the embodiments of the present application, but the present application is not limited thereto. For example, the execution order between the various operations can be appropriately adjusted, and in addition, some operations can be added or some operations can be reduced. Those skilled in the art can appropriately modify the above content, and the present application is not limited to the above FIG. 11.

[0221] In some embodiments, the configuration information comprises indication information (association ID) for indicating conditions and / or configurations of the terminal device and / or the network device for the channel state information prediction (CSI prediction).

[0222] In some embodiments, for the indication information (association ID) with the same value, the terminal device assumes that the following at least one of the same cell is the same or similar: antenna configuration of the network device; CSI-RS periodicity; bandwidth and / or sub-band size; scene of the cell, for example: indoor scene, outdoor scene, proportion of indoor scene and outdoor scene; line-of-sight condition (LoS), non-line-of-sight condition (NLos), proportion of line-of-sight condition and non-line-of-sight condition.

[0223] In some embodiments, the indication information (association ID) is associated with a cell identity and / or a cell group identity;

[0224] The cell identity is configured to the terminal device; for the indication information (association ID) with the same value, the terminal device assumes that the conditions and / or configurations of the channel state information prediction (CSI prediction) for the same cell identity are the same in the same cell;

[0225] And / or

[0226] The cell group identity is configured to the terminal device, and one cell group comprises one or more cells; for the indication information (association ID) with the same value, the terminal device assumes that the conditions and / or configurations of the channel state information prediction (CSI prediction) for the same cell group identity are the same in different cells of the same cell group.

[0227] In some embodiments, for training data collection, the indication information (association ID) is used for data classification;

[0228] Wherein, the training data comprises at least one of the following: indication information (association ID), cell identity, cell group identity, conditions and / or configurations, or the training data comprises at least one of the following: indication information (association ID), cell identity, cell group identity;

[0229] The condition and / or configuration at least includes: a number of CSI-RS ports and / or a CSI-RS period.

[0230] In some embodiments, for training data collection, the speed of the terminal device is used for data classification; the speed information of the terminal device is included in the data set (explicitly), or the speed information of the terminal device is associated with the data set (implicitly).

[0231] In some embodiments, the network device sends a request to the terminal device; the terminal device reports speed information to the network device according to the request; the network device configures a reference signal for the training data collection and receives training data, wherein the collected training data includes or is associated with the speed information.

[0232] In some embodiments, the network device sends a request to the terminal device; the terminal device measures and / or reports time domain channel properties (TDCP) related to the speed of the terminal device according to the request; the network device configures a reference signal for the training data collection and receives training data, wherein the collected training data includes or is associated with the time domain channel properties (TDCP).

[0233] In some embodiments, for model inference, the network device receives AI / ML function information reported by the terminal device that supports or is applicable, and / or the network device receives updated AI / ML function information reported by the terminal device in the case of a change in the speed of the terminal device.

[0234] In some embodiments, the supported or applicable AI / ML function information indicates or is associated with at least one of the following:

[0235] A supported or preferred CSI-RS period;

[0236] A number of supported or preferred time instances in an observation window;

[0237] A number of supported or preferred time instances in a prediction window;

[0238] A terminal device speed corresponding to the supported or applicable AI / ML function information;

[0239] Channel-related information on a time domain corresponding to the supported or applicable AI / ML function information.

[0240] In some embodiments, the network device sends a reference signal for model inference to the terminal device; wherein the reference signal is configured by the network device according to the supported or applicable AI / ML function information.

[0241] In some embodiments, the network device sends a reference signal for model inference to the terminal device; wherein the reference signal is configured by the network device according to the supported or applicable AI / ML function information, and the reference signal configuration corresponding to the AI / ML function supported or applicable to the terminal device is scaled according to the speed of the terminal device and / or channel-related information in the time domain.

[0242] In some embodiments, the network device receives the time-domain channel property (TDCP) related to the speed of the terminal device reported by the terminal device; and the updated supported or applicable AI / ML function information; the network device sends information for activating the AI / ML function and a reference signal for model inference; wherein the reference signal is configured by the network device according to the supported or applicable AI / ML function information, or the reference signal configuration corresponding to the AI / ML function supported or applicable to the terminal device is scaled according to the speed of the terminal device and / or channel-related information in the time domain.

[0243] In some embodiments, the configuration information includes indication information (association ID) for indicating the conditions and / or configurations of the terminal device and / or the network device for the temporal beam prediction.

[0244] In some embodiments, the indication information (association ID) is associated with a cell identity and / or a cell group identity;

[0245] The cell identity is configured to the terminal device; for the indication information (association ID) with the same value, the terminal device assumes that the conditions and / or configurations of the temporal beam prediction for the same cell identity are the same within the same cell;

[0246] and / or

[0247] A cell group identifier is configured to the terminal device, one cell group comprising one or more cells; for the indication information (association ID) with the same value, the terminal device assumes that the condition and / or configuration of the temporal beam prediction for the same cell group identifier are the same in different cells of the same cell group.

[0248] In some embodiments, the indication information (association ID) is used for data classification for training data collection;

[0249] In some embodiments, the indication information (association ID), the cell identifier, the cell group identifier, the condition and / or configuration are included in the training data.

[0250] The condition and / or configuration at least includes the CSI-RS periodicity and / or the number of CSI-RS ports.

[0251] In some embodiments, the speed of the terminal device is used for data classification for training data collection; the speed information of the terminal device is included in the data set (explicitly), or the speed information of the terminal device is associated with the data set (implicitly).

[0252] In some embodiments, the network device sends a request to the terminal device; the terminal device reports the speed information to the network device according to the request; the network device configures the reference signal for the training data collection and receives the training data, wherein the collected training data includes or is associated with the speed information.

[0253] In some embodiments, the network device sends a request to the terminal device; the terminal device measures and / or reports the time domain channel property (TDCP) related to the speed of the terminal device according to the request; the network device configures the reference signal for the training data collection and receives the training data, wherein the collected training data includes or is associated with the time domain channel property (TDCP).

[0254] In some embodiments, for model inference, the network device receives the AI / ML function information reported by the terminal device that supports or is applicable, and / or the network device receives the updated AI / ML function information reported by the terminal device in the case that the speed of the terminal device changes.

[0255] In some embodiments, the supported or applicable AI / ML function information indicates or relates to at least one of:

[0256] a supported or preferred CSI-RS periodicity;

[0257] a supported or preferred number of time instances in an observation window;

[0258] a supported or preferred number of time instances in a prediction window;

[0259] a terminal device speed corresponding to the supported or applicable AI / ML function information;

[0260] channel-related information in time domain corresponding to the supported or applicable AI / ML function information.

[0261] In some embodiments, the network device sends a reference signal for model inference to the terminal device; wherein the reference signal is configured by the network device according to the supported or applicable AI / ML function information.

[0262] In some embodiments, the network device sends a reference signal for model inference to the terminal device; wherein the reference signal is configured by the network device according to the supported or applicable AI / ML function information, and the reference signal configuration corresponding to the AI / ML function supported or applicable to the terminal device is scaled according to the speed of the terminal device and / or channel-related information in time domain.

[0263] In some embodiments, the network device receives time-domain channel properties (TDCP) related to the speed of the terminal device reported by the terminal device; receives updated supported or applicable AI / ML function information; the network device sends information for activating AI / ML function and reference signal for model inference; wherein the reference signal is configured by the network device according to the supported or applicable AI / ML function information, or the reference signal configuration corresponding to the AI / ML function supported or applicable to the terminal device is scaled according to the speed of the terminal device and / or channel-related information in time domain.

[0264] In some embodiments, the network device can send configuration information to the terminal device. The network device can receive feedback information and / or report information sent by the terminal device. For example, the terminal device can report inference results and / or performance monitoring results and / or training data collection results to the network device, and the present application is not limited thereto.

[0265] The above embodiments are only illustrative of the embodiments of the present application, but the present application is not limited thereto, and can be appropriately modified on the basis of the above embodiments. For example, the above embodiments can be used alone or in combination of one or more of the above embodiments.

[0266] As can be seen from the above embodiments, the network device sends configuration information to the terminal device, and the configuration information is used by the terminal device to perform channel state information prediction or temporal beam prediction based on an AI / ML model / function. In this way, the accuracy of prediction can be improved, and the performance and efficiency of AI / ML can be improved.

[0267] Embodiments of the third aspect

[0268] The embodiments of the present application provide a prediction device. The device may, for example, be a terminal device, or one or more components or assemblies configured in the terminal device. The same content as the embodiments of the first and second aspects will not be described again.

[0269] FIG. 12 is a schematic diagram of a prediction device according to an embodiment of the present application. As shown in FIG. 12, the prediction device 1200 according to an embodiment of the present application includes a receiver 1201 and a processor 1202, and can further include a transmitter 1203.

[0270] The receiver 1201 receives configuration information for configuring channel state information prediction (CSI prediction) or temporal beam prediction from a network device;

[0271] The processor 1202 performs channel state information prediction or temporal beam prediction based on an AI / ML model / function according to the configuration information.

[0272] In some embodiments, the configuration information includes indication information (association ID) for indicating conditions and / or configurations of the terminal device and / or the network device for the channel state information prediction (CSI prediction).

[0273] In some embodiments, for the indication information (association ID) with the same value, the terminal device assumes that at least one of the following characteristics in the same cell is the same or similar: antenna configuration of the network device; CSI-RS period; bandwidth and / or sub-band size; scene of the cell.

[0274] In some embodiments, the indication information (association ID) is associated with a cell identity and / or a cell group identity;

[0275] A cell identity is configured to the terminal device; for the indication information (association ID) with the same value, the terminal device assumes that the condition and / or configuration of channel state information prediction (CSI prediction) is the same in the same cell for the same cell identity;

[0276] and / or

[0277] A cell group identity is configured to the terminal device, and one cell group includes one or more cells; for the indication information (association ID) with the same value, the terminal device assumes that the condition and / or configuration of channel state information prediction (CSI prediction) is the same in different cells of the same cell group for the same cell group identity.

[0278] In some embodiments, for training data collection, the indication information (association ID) is used for data classification;

[0279] In some embodiments, for training data collection, the indication information (association ID) is used for data classification;

[0280] The condition and / or configuration (condition / configuration) at least includes: the number of CSI-RS ports and / or the CSI-RS period.

[0281] In some embodiments, for training data collection, the speed of the terminal device is used for data classification; the speed information of the terminal device is included in the data set (explicitly), or the speed information of the terminal device is associated with the data set (implicitly).

[0282] In some embodiments, the receiver 1201 receives a request sent by the network device;

[0283] The transmitter 1203 reports speed information to the network device according to the request; wherein the network device configures a reference signal for the training data collection, and the collected training data includes or is associated with the speed information.

[0284] In some embodiments, the receiver 1201 receives a request sent by the network device;

[0285] The transmitter 1203 measures and / or reports time domain channel properties (TDCP) related to the speed of the terminal device according to the request; wherein the network device configures reference signals for the training data collection, and the collected training data includes or is associated with the time domain channel properties (TDCP).

[0286] In some embodiments, for model inference,

[0287] The transmitter 1203 reports AI / ML function information supported or applicable to the network device, and / or, in the case of a change in the speed of the terminal device, reports updated AI / ML function information supported or applicable to the network device.

[0288] In some embodiments, the AI / ML function information supported or applicable indicates or is associated with at least one of the following:

[0289] Supported or preferred CSI-RS periodicity;

[0290] Number of time instances supported or preferred in the observation window;

[0291] Number of time instances supported or preferred in the prediction window;

[0292] Terminal device speed corresponding to the AI / ML function information supported or applicable;

[0293] Channel-related information in the time domain corresponding to the AI / ML function information supported or applicable.

[0294] In some embodiments, the receiver 1201 receives reference signals for model inference from the network device; wherein the reference signals are configured by the network device according to the AI / ML function information supported or applicable.

[0295] In some embodiments, the receiver 1201 receives reference signals for model inference from the network device; wherein the reference signals are configured by the network device according to the AI / ML function information supported or applicable, and the reference signal configuration corresponding to the AI / ML function supported or applicable to the terminal device is adjusted (scaled) according to the speed of the terminal device and / or channel-related information in the time domain.

[0296] In some embodiments, the transmitter 1203 measures and / or reports time domain channel properties (TDCP) related to the speed of the terminal device; reports updated AI / ML function information supported or applicable to the network device;

[0297] The receiver 1201 receives information of activated AI / ML functions from the network device and reference signals for model inference; wherein the reference signals are configured by the network device according to the supported or applicable AI / ML function information, or the reference signal configuration corresponding to the AI / ML function supported or applicable to the terminal device is adjusted (scaled) according to the speed of the terminal device and / or channel-related information in the time domain.

[0298] In some embodiments, the configuration information includes indication information (association ID) for indicating the conditions and / or configurations of the terminal device and / or the network device for the temporal beam prediction.

[0299] In some embodiments, the indication information (association ID) is associated with a cell identity and / or a cell group identity;

[0300] The cell identity is configured to the terminal device; for the indication information (association ID) with the same value, the terminal device assumes that the conditions and / or configurations of the temporal beam prediction for the same cell identity are the same within the same cell;

[0301] And / or

[0302] The cell group identity is configured to the terminal device, and one cell group includes one or more cells; for the indication information (association ID) with the same value, the terminal device assumes that the conditions and / or configurations of the temporal beam prediction for the same cell group identity are the same in different cells of the same cell group.

[0303] In some embodiments, the indication information (association ID) is used for data classification for training data collection;

[0304] Wherein, the training data includes at least one of the following: indication information (association ID), cell identity, cell group identity, condition and / or configuration, or the training data includes at least one of the following: indication information (association ID), cell identity, cell group identity;

[0305] The condition and / or configuration at least includes: a CSI-RS period and / or a CSI-RS port number.

[0306] In some embodiments, for training data collection, the speed of the terminal device is used for data classification; the speed information of the terminal device is included in the data set (explicitly), or the speed information of the terminal device is associated with the data set (implicitly).

[0307] In some embodiments, the receiver 1201 receives a request sent by the network device;

[0308] The transmitter 1203 reports speed information to the network device according to the request; wherein the network device configures a reference signal for the training data collection, and the collected training data includes or is associated with the speed information.

[0309] In some embodiments, the receiver 1201 receives a request sent by the network device;

[0310] The transmitter 1203 measures and / or reports time-domain channel properties (TDCP) related to the speed of the terminal device according to the request; wherein the network device configures a reference signal for the training data collection, and the collected training data includes or is associated with the time-domain channel properties (TDCP).

[0311] In some embodiments, for model inference,

[0312] The transmitter 1203 reports the supported or applicable AI / ML function information to the network device, and / or, in the case of a change in the speed of the terminal device, reports updated supported or applicable AI / ML function information to the network device.

[0313] In some embodiments, the supported or applicable AI / ML function information indicates or is associated with at least one of the following:

[0314] A supported or preferred CSI-RS period;

[0315] A number of time instances supported or preferred in an observation window;

[0316] A number of time instances supported or preferred in a prediction window;

[0317] A terminal device speed corresponding to the supported or applicable AI / ML function information;

[0318] Channel-related information in a time domain corresponding to the supported or applicable AI / ML function information.

[0319] In some embodiments, the receiver 1201 receives a reference signal for model inference from the network device; wherein the reference signal is configured by the network device according to the supported or applicable AI / ML function information.

[0320] In some embodiments, the receiver 1201 receives a reference signal for model inference from the network device; wherein the reference signal is configured by the network device according to the supported or applicable AI / ML function information, and the reference signal configuration corresponding to the AI / ML function supported or applicable to the terminal device is scaled according to the speed of the terminal device and / or channel-related information in a time domain.

[0321] In some embodiments, the transmitter 1203 measures and / or reports time-domain channel properties (TDCP) related to the speed of the terminal device; reports the updated supported or applicable AI / ML function information to the network device;

[0322] The receiver 1201 receives information of activated AI / ML function and a reference signal for model inference from the network device; wherein the reference signal is configured by the network device according to the supported or applicable AI / ML function information, or the reference signal configuration corresponding to the AI / ML function supported or applicable to the terminal device is scaled according to the speed of the terminal device and / or channel-related information in a time domain.

[0323] The above embodiments are only exemplary, and the present application is not limited thereto. The above embodiments can be appropriately modified 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.

[0324] 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 prediction device 1200 can also include other components or modules, and the specific content of these components or modules can be referred to related technologies.

[0325] In addition, for the sake of simplicity, only the connection relationship or signal path between the components or modules is exemplarily shown in FIG. 12, 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 realized by hardware facilities such as processors, memories, transmitters, receivers, etc.; the present application is not limited thereto.

[0326] From the above embodiments, the terminal device performs channel state information prediction or temporal beam prediction according to the configuration information based on the AI / ML model / function. In this way, the accuracy of prediction can be improved, and the performance and efficiency of AI / ML can be improved.

[0327] Embodiments of the fourth aspect

[0328] Embodiments of the present application provide a configuration device. The device may, for example, be a network device, or a certain component or assembly configured in the network device. The same content as the embodiments of the first to third aspects will not be described again.

[0329] FIG. 13 is another schematic diagram of the configuration device according to an embodiment of the present application. As shown in FIG. 13, the configuration device 1300 includes a transmitter 1301, and can further include a processor 1302 and a receiver 1303.

[0330] The transmitter 1301 transmits configuration information for configuring channel state information prediction (CSI prediction) or temporal beam prediction to a terminal device; wherein the configuration information is used by the terminal device to perform channel state information prediction or temporal beam prediction based on an AI / ML model / function.

[0331] The above embodiments are only exemplary descriptions of the embodiments of the present application, 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.

[0332] It should be noted that the above only describes the components or modules related to the present application, but the present application is not limited thereto. The configuration device 1300 can further include other components or modules, and the specific content of these components or modules can be referred to the related art.

[0333] In addition, for simplicity, only the connection relationship or signal path between the components or modules is exemplarily shown in FIG. 13, but those skilled in the art should understand that various related technologies such as bus connection can be used. The above components or modules can be realized by hardware facilities such as processors, memories, transmitters, receivers, etc.; the present application is not limited thereto.

[0334] From the above embodiments, the network device transmits configuration information to the terminal device, and the configuration information is used by the terminal device to perform channel state information prediction or temporal beam prediction based on an AI / ML model / function. In this way, the accuracy of prediction can be improved, and the performance and efficiency of AI / ML can be improved.

[0335] Embodiments of the fifth aspect

[0336] Embodiments of the present application also provide a communication system, which can refer to FIG. 1, and the same content as the embodiments of the first to fourth aspects will not be described here.

[0337] In some embodiments, the communication system 100 can at least include:

[0338] a network device, which sends configuration information for configuring channel state information prediction or temporal beam prediction to a terminal device;

[0339] a terminal device, which performs channel state information prediction or temporal beam prediction according to the configuration information based on an AI / ML model / function.

[0340] Embodiments of the present application also provide a terminal device, but the present application is not limited thereto, and can also be other devices.

[0341] FIG. 14 is a schematic diagram of a terminal device according to an embodiment of the present application. As shown in FIG. 14, the terminal device 1400 can include a processor 1410 and a memory 1420; the memory 1420 stores data and programs and is coupled to the processor 1410. It is worth noting that this figure is exemplary; other types of structures can also be used to supplement or replace this structure to achieve telecommunication functions or other functions.

[0342] For example, the processor 1410 can be configured to execute programs to implement the prediction method according to the embodiments of the first aspect. For example, the processor 1410 can be configured to perform the following control: receiving configuration information for configuring channel state information prediction or temporal beam prediction from a network device; performing channel state information prediction or temporal beam prediction according to the configuration information based on an AI / ML model / function.

[0343] As shown in FIG. 14, the terminal device 1400 can also include a communication module 1430, an input unit 1440, a display 1450, and a power supply 1460. The functions of the above-mentioned components are similar to those of the prior art, and will not be described here. It is worth noting that the terminal device 1400 does not necessarily include all the components shown in FIG. 14, and the above-mentioned components are not essential; in addition, the terminal device 1400 can also include components not shown in FIG. 14, which can refer to the prior art.

[0344] Embodiments of the present application also provide a network device, which can be a base station, but the present application is not limited thereto, and can also be other network devices.

[0345] Fig. 15 is a schematic diagram of a network device according to an embodiment of the present application. As shown in Fig. 15, the network device 1500 can include a processor 1510 (e.g., a central processing unit, CPU) and a memory 1520, wherein the memory 1520 is coupled to the processor 1510. The memory 1520 can store various data. In addition, the memory 1520 can store a program 1530 for information processing, and execute the program 1530 under the control of the processor 1510.

[0346] For example, the processor 1510 can be configured to execute the program to implement the configuration method according to an embodiment of the second aspect. For example, the processor 1510 can be configured to perform the following control: sending configuration information for configuring channel state information prediction or time beam prediction to a terminal device; wherein the configuration information is used by the terminal device to perform AI / ML model / function-based channel state information prediction or time beam prediction.

[0347] In addition, as shown in Fig. 15, the network device 1500 can further include a transceiver 1540, an antenna 1550, etc. The functions of the above components are similar to those of the prior art, and will not be described here. It should be noted that the network device 1500 does not necessarily include all the components shown in Fig. 15. In addition, the network device 1500 can also include components not shown in Fig. 15, which can be referred to the prior art.

[0348] The embodiments of the present application also provide a computer program, which, when executed in a terminal device, causes the terminal device to perform the prediction method according to the embodiments of the first aspect.

[0349] The embodiments of the present application also provide a storage medium storing a computer program, which causes a terminal device to perform the prediction method according to the embodiments of the first aspect.

[0350] The embodiments of the present application also provide a computer program, which, when executed in a network device, causes the network device to perform the configuration method according to the embodiments of the second aspect.

[0351] The embodiments of the present application also provide a storage medium storing a computer program, which causes a network device to perform the configuration method according to the embodiments of the second aspect.

[0352] 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 above-described apparatuses or components, or causes the logic component to implement the above-described various methods or steps. 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.

[0353] 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 thereof. For example, one or more of the functional blocks shown in the figures 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. The software modules can correspond to individual steps shown in the figures. The hardware modules can be implemented by, for example, fixing the software modules using a field programmable gate array (FPGA).

[0354] 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 (e.g., the 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.

[0355] One or more of the functional blocks shown in the figures and / or a combination of one or more 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, discrete hardware components, or any appropriate combination thereof, for performing the functions described in the present application. One or more of the functional blocks shown in the figures and / or a combination of one or more of the functional blocks 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 core, or any other such configuration.

[0356] The present application is described above in connection with specific embodiments, but those skilled in the art will understand that the description is merely exemplary and is not intended to limit the scope of the present application. Those skilled in the art can make various modifications and variations to the present application according to the spirit and principles of the present application, and these modifications and variations are also within the scope of the present application.

[0357] In connection with the embodiments including the above embodiments, the following notes are also disclosed:

[0358] 1. A prediction method comprising:

[0359] A terminal device receives configuration information for configuring channel state information prediction (CSI prediction) or temporal beam prediction from a network device;

[0360] The terminal device performs channel state information prediction or temporal beam prediction according to the configuration information based on an AI / ML model / function.

[0361] 2. A configuration method comprising:

[0362] A network device sends configuration information for configuring channel state information prediction (CSI prediction) or temporal beam prediction to a terminal device;

[0363] The configuration information is used by the terminal device to perform channel state information prediction or temporal beam prediction based on an AI / ML model / function.

[0364] 3. A terminal 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 prediction method of Note 1.

[0365] 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 configuration method of Note 2.

[0366] 5. A computer program product comprising at least a computer program, which, when executed by a processor, causes a terminal device to perform the prediction method of Note 1.

[0367] 6. A computer program product comprising at least a computer program, which, when executed by a processor, causes a network device to perform the configuration method of Note 2.

Claims

1. A prediction apparatus, comprising: a receiver configured to receive configuration information for configuring channel state information prediction or time beam prediction from a network device; a processor configured to perform channel state information prediction or time beam prediction according to the configuration information based on an AI / ML model / function.

2. The apparatus of claim 1, wherein, the configuration information comprises indication information indicating conditions and / or configurations of the channel state information prediction for a terminal device and / or the network device; for the indication information having the same value, the terminal device assumes that at least one of the following is the same or similar in the same cell: antenna configuration of the network device; CSI-RS periodicity; bandwidth and / or sub-band size; scenario of the cell.

3. The apparatus of claim 2, wherein, the indication information is associated with a cell identity and / or a cell group identity; a cell identity is configured to the terminal device; for the indication information having the same value, the terminal device assumes that the conditions and / or configurations of the channel state information prediction are the same within the same cell for the same cell identity; and / or a cell group identity is configured to the terminal device, one cell group comprising one or more cells; for the indication information having the same value, the terminal device assumes that the conditions and / or configurations of the channel state information prediction are the same in different cells of the same cell group for the same cell group identity.

4. The apparatus of claim 2, wherein, for training data collection, the indication information is used for data classification; wherein the training data comprises at least one of the following: indication information, cell identity, cell group identity, conditions and / or configurations, or the training data comprises at least one of the following: indication information, cell identity, cell group identity; the conditions and / or configurations comprise at least: CSI-RS port number and / or CSI-RS periodicity.

5. The apparatus of claim 2, wherein, for training data collection, the speed of the terminal device is used for data classification; the speed information of the terminal device is included in a data set or is associated with the data set.

6. The apparatus of claim 5, wherein, the receiver receives a request sent by the network device; the apparatus further comprises: a transmitter configured to report speed information to the network device according to the request; wherein the network device configures reference signals for the training data collection, and the collected training data comprises or is associated with the speed information.

7. The apparatus of claim 5, wherein, the receiver receives a request sent by the network device; the apparatus further comprises: a transmitter configured to measure and / or report time domain channel characteristics related to the speed of the terminal device according to the request; wherein the network device configures reference signals for the training data collection, and the collected training data comprises or is associated with the time domain channel characteristics.

8. The apparatus of claim 2, wherein, for model inference, the apparatus further comprises: a transmitter configured to report AI / ML function information supported or applicable to the network device, and / or, in the case of a change in the speed of the terminal device, to report updated AI / ML function information supported or applicable to the network device; the AI / ML function information supported or applicable indicates or is associated with at least one of the following: supported or preferred CSI-RS periodicity; number of time instances supported or preferred in an observation window; a number of time instances supported or preferred in the prediction window; a terminal device speed corresponding to the supported or applicable AI / ML function information; channel related information in time domain corresponding to the supported or applicable AI / ML function information.

9. The apparatus of claim 8, wherein, the receiver receives reference signals for model inference from the network device; wherein the reference signals are configured by the network device according to the supported or applicable AI / ML function information; or, the receiver receives reference signals for model inference from the network device; wherein the reference signals are configured by the network device according to the supported or applicable AI / ML function information, and the reference signal configuration corresponding to the AI / ML function supported or applicable to the terminal device is adjusted according to the terminal device speed and / or channel related information in time domain.

10. The apparatus of claim 8, wherein, the apparatus further comprises: a transmitter that measures and / or reports time domain channel characteristics related to the terminal device speed; reports updated supported or applicable AI / ML function information to the network device; the receiver receives information of activated AI / ML function and reference signals for model inference from the network device; wherein the reference signals are configured by the network device according to the supported or applicable AI / ML function information, or the reference signal configuration corresponding to the AI / ML function supported or applicable to the terminal device is adjusted according to the terminal device speed and / or channel related information in time domain.

11. The apparatus of claim 1, wherein, the configuration information comprises indication information used to indicate conditions and / or configurations of time beam prediction for the terminal device and / or the network device.

12. The apparatus of claim 11, wherein, the indication information is associated with a cell identity and / or a cell group identity; a cell identity is configured to the terminal device; for the indication information with the same value, the terminal device assumes that the conditions and / or configurations of time beam prediction for the same cell identity are the same within the same cell; and / or a cell group identity is configured to the terminal device, one cell group comprises one or more cells; for the indication information with the same value, the terminal device assumes that the conditions and / or configurations of time beam prediction for the same cell group identity are the same within different cells of the same cell group.

13. The apparatus of claim 11, wherein, for training data collection, the indication information is used for data classification; wherein the training data comprises at least one of the following: the indication information, the cell identity, the cell group identity, the conditions and / or configurations, or the training data comprises at least one of the following: the indication information, the cell identity, the cell group identity; the conditions and / or configurations at least comprise CSI-RS periodicity and / or CSI-RS port number.

14. The apparatus of claim 11, wherein, for training data collection, the terminal device speed is used for data classification; the terminal device speed information is included in the data set, or the terminal device speed information is associated with the data set.

15. The apparatus of claim 14, wherein, the receiver receives a request sent by the network device; the apparatus further comprises: a transmitter configured to report speed information to the network device according to the request; wherein the network device configures reference signals for the training data collection, and the collected training data includes or is associated with the speed information; or the transmitter is configured to measure and / or report time-domain channel characteristics related to the speed of the terminal device according to the request; wherein the network device configures reference signals for the training data collection, and the collected training data includes or is associated with the time-domain channel characteristics.

16. The apparatus of claim 11, wherein, For model inference, the apparatus further comprises: a transmitter configured to report AI / ML function information supported or applicable to the terminal device to the network device, and / or, in the case of a change in the speed of the terminal device, to report updated AI / ML function information supported or applicable to the terminal device to the network device; the AI / ML function information supported or applicable indicates or is associated with at least one of the following: a preferred CSI-RS periodicity; a number of time instances in an observation window supported or preferred; a number of time instances in a prediction window supported or preferred; a terminal device speed corresponding to the AI / ML function information supported or applicable; channel-related information in the time domain corresponding to the AI / ML function information supported or applicable.

17. The apparatus of claim 16, wherein the receiver receives reference signals for model inference from the network device; wherein the reference signals are configured by the network device according to the AI / ML function information supported or applicable; or the receiver receives reference signals for model inference from the network device; wherein the reference signals are configured by the network device according to the AI / ML function information supported or applicable, and adjusted according to the speed of the terminal device and / or channel-related information in the time domain corresponding to the AI / ML function supported or applicable to the terminal device.

18. The apparatus of claim 16, wherein, The apparatus further comprises: a transmitter configured to measure and / or report time-domain channel characteristics related to the speed of the terminal device; and to report updated AI / ML function information supported or applicable to the network device; the receiver receives information of activated AI / ML functions and reference signals for model inference from the network device; wherein the reference signals are configured by the network device according to the AI / ML function information supported or applicable, or adjusted according to the speed of the terminal device and / or channel-related information in the time domain corresponding to the AI / ML function supported or applicable to the terminal device.

19. A configuration apparatus comprising: a transmitter configured to transmit configuration information for configuring channel state information prediction or time beam prediction to a terminal device; wherein the configuration information is used by the terminal device to perform AI / ML model / function-based channel state information prediction or time beam prediction.

20. A communication system comprising: a network device configured to transmit configuration information for configuring channel state information prediction or time beam prediction to a terminal device; A terminal device, based on an AI / ML model / function, performs channel state information prediction or time beam prediction according to the configuration information.

Images