Data collection method and apparatus

Abstract

Provided in the embodiments of the present application are a data collection method and apparatus. The data collection method comprises: a terminal device receiving, from a network device, configuration information used for collecting data; and on the basis of the configuration information, the terminal device acquiring data used for AI / ML functionality / model training.

Description

Data collection method and device Technical Field

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

[0002] NR Release 18 investigates artificial intelligence / machine learning (AI / ML) over the air interface. AI / ML can be used for the following use cases: channel state information (CSI) feedback enhancement, beam management, and positioning enhancement. CSI feedback enhancement can include CSI prediction and CSI compression; beam management can include spatial beam prediction (BM case-1) and temporal beam prediction (BM case-2); and positioning enhancement can include direct positioning and AI / ML-assisted positioning.

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

[0004] It should be noted that the above introduction to the technical background is merely intended to provide a clear and complete description of the technical solutions of this application and facilitate understanding by those skilled in the art. Simply because these solutions are described in the background technology section of this application, it should not be assumed that the above technical solutions are well known to those skilled in the art.

[0005] Summary of the Invention

[0006] The inventors discovered that terminal devices and / or network devices can utilize AI / ML functionality / models to predict beams based on beam measurement results, but there is currently no clear solution for how to collect data for AI / ML training.

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

[0008] According to one aspect of an embodiment of the present application, a data collection method is provided, comprising:

[0009] The terminal device receives configuration information for collecting data from the network device;

[0010] The terminal device obtains data for AI / ML functionality / model training based on the configuration information.

[0011] According to another aspect of an embodiment of the present application, a data collection device is provided, including:

[0012] a receiving unit configured to receive configuration information for collecting data from a network device;

[0013] A processing unit, which obtains data for AI / ML functionality / model training based on the configuration information.

[0014] According to another aspect of an embodiment of the present application, a data collection method is provided, comprising:

[0015] The network device sends configuration information for collecting data to the terminal device; the configuration information is used by the terminal device to obtain data for AI / ML functionality / model training.

[0016] According to another aspect of an embodiment of the present application, a data collection device is provided, including:

[0017] A sending unit that sends configuration information for collecting data to a terminal device; wherein the configuration information is used by the terminal device to obtain data for AI / ML functionality / model training.

[0018] According to another aspect of an embodiment of the present application, a communication system is provided, including:

[0019] a network device that sends configuration information for collecting data to a terminal device;

[0020] A terminal device acquires data for AI / ML functionality / model training based on the configuration information.

[0021] One of the beneficial effects of the embodiments of the present application is that the terminal device obtains data for AI / ML functionality / model training based on the configuration information, thereby obtaining accurate training data and improving the performance and efficiency of AI / ML.

[0022] With reference to the following description and accompanying drawings, specific embodiments of the present application are disclosed in detail, indicating the manner in which the principles of the present application can be employed. It should be understood that the embodiments of the present application are not limited in scope. Within the spirit and scope of the appended claims, the embodiments of the present application include many variations, modifications and equivalents.

[0023] Features described and / or illustrated with respect to one embodiment may be used in the same or similar manner in one or more other embodiments, combined with features in other embodiments, or substituted for features in other embodiments.

[0024] It should be emphasized that the term "include / comprising" when used herein refers to the presence of features, integers, steps or components, but does not exclude the presence or addition of one or more other features, integers, steps or components. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] The elements and features described in one figure or one embodiment of the present application can be combined with the elements and features shown in one or more other figures or embodiments. In addition, in the accompanying drawings, similar reference numerals represent corresponding parts in several figures and can be used to indicate corresponding parts used in more than one embodiment.

[0026] FIG1 is a schematic diagram of a communication system according to an embodiment of the present application;

[0027] FIG2 is a schematic diagram of a data collection method according to an embodiment of the present application;

[0028] FIG3 is a schematic diagram of AI / ML for beam management according to an embodiment of the present application;

[0029] FIG4 is a schematic diagram of a beam management method according to an embodiment of the present application;

[0030] FIG5 is an example diagram of data collection using set A and set B according to an embodiment of the present application;

[0031] FIG6 is an example diagram of collected data according to an embodiment of the present application;

[0032] FIG7 is an example diagram of collected data according to an embodiment of the present application;

[0033] FIG8 is an example diagram of collected data according to an embodiment of the present application;

[0034] FIG9 is a schematic diagram of data collection according to an embodiment of the present application;

[0035] FIG10 is an example diagram of collected data according to an embodiment of the present application;

[0036] FIG11 is an example diagram of reference signal transmission according to an embodiment of the present application;

[0037] FIG12 is an example diagram of collected data according to an embodiment of the present application;

[0038] FIG13 is an example diagram of collected data according to an embodiment of the present application;

[0039] FIG14 is a schematic diagram of data collection according to an embodiment of the present application;

[0040] FIG15 is an example diagram of collected data according to an embodiment of the present application;

[0041] FIG16 is a schematic diagram of a data collection method according to an embodiment of the present application;

[0042] FIG17 is a schematic diagram of a data collection device according to an embodiment of the present application;

[0043] FIG18 is a schematic diagram of a data collection device according to an embodiment of the present application;

[0044] FIG19 is a schematic diagram of a terminal device according to an embodiment of the present application;

[0045] Figure 20 is a schematic diagram of a network device according to an embodiment of the present application. DETAILED DESCRIPTION

[0046] The above and other features of the present application will become apparent through the following description with reference to the accompanying drawings. In the description and the accompanying drawings, specific embodiments of the present application are disclosed in detail, which illustrate some embodiments in which the principles of the present application can be adopted. It should be understood that the present application is not limited to the described embodiments. On the contrary, the present application includes all modifications, variations and equivalents that fall within the scope of the appended claims.

[0047] In the embodiments of the present application, the terms "first", "second", etc. are used to distinguish different elements from the name, but do not indicate the spatial arrangement or temporal order of these elements, and these elements should not be limited by these terms. The term "and / or" includes any one and all combinations of one or more of the associated listed terms. The terms "comprising", "including", "having", etc. refer to the presence of the stated features, elements, components or components, but do not exclude the presence or addition of one or more other features, elements, components or components.

[0048] In the embodiments of this application, the singular forms "a," "the," etc. include plural forms and should be broadly understood to mean "a" or "a type" rather than being limited to "one." Furthermore, the term "said" should be understood to include both singular and plural forms, unless the context clearly indicates otherwise. Furthermore, the term "according to" should be understood to mean "at least in part based on...", and the term "based on" should be understood to mean "at least in part based on...", unless the context clearly indicates otherwise.

[0049] In the embodiments of the present application, the term "communication network" or "wireless communication network" may refer to a network that complies with any of the following communication standards, such as Long Term Evolution (LTE), enhanced Long Term Evolution (LTE-A, LTE-Advanced), Wideband Code Division Multiple Access (WCDMA), High-Speed ​​Packet Access (HSPA), etc.

[0050] Furthermore, communication between devices in the communication system may be carried out according to communication protocols of any stage, for example, including but not limited to the following communication protocols: 1G (generation), 2G, 2.5G, 2.75G, 3G, 4G, 4.5G and 5G, New Radio (NR), future 6G, etc., and / or other communication protocols currently known or to be developed in the future.

[0051] In the embodiments of the present application, the term "network device" refers to, for example, a device in a communication system that connects a terminal device to the communication network and provides services to the terminal device. Network devices may include, but are not limited to, the following devices: base station (BS), access point (AP), transmission reception point (TRP), broadcast transmitter, mobile management entity (MME), gateway, server, radio network controller (RNC), base station controller (BSC), etc.

[0052] Among them, base stations may include but are not limited to: NodeB (NodeB or NB), evolved NodeB (eNodeB or eNB) and 5G base station (gNB), IAB host, etc., and may also include remote radio head (RRH, Remote Radio Head), remote radio unit (RRU, Remote Radio Unit), relay (relay) or low-power node (such as femeto, pico, etc.). The term "base station" can include some or all of their functions. Each base station can provide communication coverage for a specific geographical area. The term "cell" can refer to a base station and / or its coverage area, depending on the context in which the term is used.

[0053] In the embodiments of the present application, the term "user equipment" (UE) or "terminal equipment" (TE) refers to, for example, a device that accesses a communication network through a network device and receives network services. A terminal device can be fixed or mobile and may also be referred to as a mobile station (MS), a terminal, a subscriber station (SS), an access terminal (AT), a station, and so on.

[0054] Among them, terminal devices may include but are not limited to the following devices: cellular phones, personal digital assistants (PDAs), wireless modems, wireless communication devices, handheld devices, machine-type communication devices, laptop computers, cordless phones, smart phones, smart watches, digital cameras, etc.

[0055] For another example, in scenarios such as the Internet of Things (IoT), the terminal device can also be a machine or device for monitoring or measurement, including but not limited to: machine type communication (MTC) terminal, vehicle-mounted communication terminal, device-to-device (D2D) terminal, machine-to-machine (M2M) terminal, and so on.

[0056] In addition, the term "network side" or "network device side" refers to one side of the network, which can be a base station or one or more network devices as described above. The term "user side" or "terminal side" or "terminal device side" refers to the user or terminal side, which can be a UE or one or more terminal devices as described above. Unless otherwise specified herein, "device" can refer to either network equipment or terminal equipment.

[0057] The following describes the scenarios of the embodiments of the present application through examples, but the present application is not limited thereto.

[0058] FIG1 is a schematic diagram of a communication system according to an embodiment of the present application, schematically illustrating a situation using a terminal device and a network device as an example. As shown in FIG1 , a communication system 100 may include a network device 101 and terminal devices 102 and 103. For simplicity, FIG1 illustrates only two terminal devices and one network device as an example, but the embodiments of the present application are not limited thereto.

[0059] In the embodiment of the present application, existing services or future services can be transmitted between the network device 101 and the terminal devices 102 and 103. For example, these services may include but are not limited to: enhanced mobile broadband (eMBB), massive machine type communication (mMTC), and ultra-reliable and low-latency communication (URLLC), etc.

[0060] It is worth noting that FIG1 shows that both terminal devices 102 and 103 are within the coverage range of network device 101, but the present application is not limited thereto. Both terminal devices 102 and 103 may not be within the coverage range of network device 101, or one terminal device 102 may be within the coverage range of network device 101 while the other terminal device 103 is outside the coverage range of network device 101.

[0061] In the embodiments of the present application, the high-layer signaling may be, for example, radio resource control (RRC) signaling; for example, an RRC message, including, for example, an MIB, system information, or a dedicated RRC message; or an RRC information element (RRC IE). The high-layer signaling may also be, for example, MAC (Medium Access Control) signaling; or a MAC control element (MAC CE). However, the present application is not limited thereto.

[0062] In embodiments of the present application, one or more AI / ML models may be configured and run in a network device and / or a terminal device. The AI / ML models may be used for various signal processing functions in wireless communications, such as CSI prediction, CSI compression, beamforming, positioning management, and the like; however, the present application is not limited thereto.

[0063] Embodiments of the first aspect

[0064] An embodiment of the present application provides a data collection method, which is described from the perspective of a terminal device.

[0065] FIG2 is a schematic diagram of a data collection method according to an embodiment of the present application. As shown in FIG2 , the method includes:

[0066] 201, the terminal device receives configuration information for collecting data from the network device;

[0067] 202. The terminal device obtains data for AI / ML functionality / model training based on the configuration information.

[0068] It is worth noting that FIG2 above is merely a schematic illustration of an embodiment of the present application, and the present application is not limited thereto. For example, the execution order of the various operations may be appropriately adjusted, and other operations may be added or some operations may be reduced. Those skilled in the art may make appropriate modifications based on the above description, and are not limited to the description of FIG2 above.

[0069] In some embodiments, functionality refers to an AI / ML feature / feature group enabled by a configuration, where the configuration is supported based on conditions indicated by UE capabilities.

[0070] For example, the AL / ML function may be one or more functions, or one or more logical models, or one or more sub-functions, or one or more features, or one or more feature groups.

[0071] For another example, the function can be to use AI / ML for spatial beam prediction, or to use AI / ML for time beam prediction, or to use AI / ML for CSI prediction, or to use AI / ML for direct positioning, or to use AI / ML for assisted positioning, and so on.

[0072] In some embodiments, the configuration information for collecting data may include configuration information of one or more reference signals, such as CSI-RS configuration information, etc. The present application is not limited thereto, and reference may be made to related technologies for specific configuration information.

[0073] In some embodiments, an AI / ML functionality / model can be used for beam management. One or more reference signals are used for measurement, and the measurement results are input into the AI / ML functionality / model. Another one or more reference signals are used for inference at the output of the AI / ML functionality / model.

[0074] Figure 3 is a schematic diagram of AI / ML for beam management in an embodiment of the present application. As shown in Figure 3, one or more reference signals in the second reference signal resource set (set B) can be received and measured by the terminal device, and the measurement results can be used as input to the AI / ML. One or more reference signals in the first reference signal resource set (set A) can be used by the terminal device for the output of the AI / ML, for example, the measurement results can be used as label data or ground truth data for the AI / ML. For the specific content of AI / ML and set A and set B, please refer to the relevant technology and will not be repeated here.

[0075] FIG4 is another schematic diagram of the beam management method according to an embodiment of the present application, which is illustrated by taking a terminal device configured with AI / ML as an example. As shown in FIG4 , the method includes:

[0076] 401. A terminal device receives configuration information from a network device; for example, the configuration information includes a second reference signal resource set (set B) for beam measurement and a first reference signal resource set (set A) for beam prediction.

[0077] At 402 , the terminal device performs beam measurement and inputs the beam measurement results into an AI / ML functionality / model. For example, the measurement results of the reference signals in set B are used as input to the AI / ML, and the reference signals in set A are used for prediction (or inference).

[0078] 403. The terminal device sends the beam prediction result to the network device.

[0079] For example, the AI / ML function is located on the terminal device side. After the AI / ML function is enabled or activated, the terminal device performs beam measurement based on the reference signal from the network side, uses AI / ML to perform beam prediction based on the beam measurement results, and sends the prediction results to the network device.

[0080] It is worth noting that FIG4 above is merely a schematic illustration of an embodiment of the present application, and the present application is not limited thereto. For example, the execution order of the various operations may be appropriately adjusted, and other operations may be added or some operations may be reduced. Those skilled in the art may make appropriate modifications based on the above description, and are not limited to the description of FIG4 above.

[0081] The above schematically illustrates AI / ML-based beam management. The following describes data collection.

[0082] In some embodiments, first data (label data) for output of an AI / ML functionality / model is collected, and / or second data (input data) for input of an AI / ML functionality / model is collected; the first data and the second data are collected in association.

[0083] For example, for beam management with AI / ML operations, when collecting training data, data used as input to the AI / ML function / model (second data) and ground truth data (first data, also known as labeled data) can be collected. The input data and labeled data can be associated, for example, by placing the input data (second data) and labeled data (first data) into a single sample or group.

[0084] In some embodiments, one or more second reference signals in a second reference signal set (set B) for beam measurement are sent to the terminal device, and the terminal device measures the second reference signals and obtains the second data.

[0085] In some embodiments, one or more first reference signals in a first reference signal set (set A) for beam prediction are sent to the terminal device, and the terminal device measures the first reference signals and obtains the first data.

[0086] For example, the same reference signal as set B can be configured and sent to the UE to obtain data for AI / ML function / model input, that is, the UE measures the same reference signal as set B, and the measurement result is used as input data (second data).

[0087] For another example, the same reference signal as set A can be configured and sent to the UE to obtain ground truth data, that is, the UE measures the same reference signal as set A, and the measurement result is the ground truth data (first data).

[0088] Figure 5 is an example diagram of data collection using set A and set B according to an embodiment of the present application. As shown in Figure 5 , a second reference signal in set B can be configured and transmitted, and / or a first reference signal in set A can be configured and transmitted. The terminal device can obtain first data and / or second data based on the first reference signal and / or the second reference signal, and can store the first data and the second data in association with each other.

[0089] In some embodiments, the second data includes an index of the second reference signal and corresponding beam quality information, and the first data includes an index of the first reference signal and corresponding beam quality information. In other embodiments, the second data includes an index of the second reference signal, and the first data includes an index of the first reference signal.

[0090] For example, the data for set A and the data for set B may each include a reference signal index and a corresponding beam quality, such as L1-RSRP / L1-SINR. Alternatively, the data for set A and the data for set B may each include only a reference signal index. Whether the data for set A and / or the data for set B include only a reference signal index, or whether they include a reference signal index and a corresponding beam quality, may depend on the configuration of the network device or may also depend on the UE capabilities.

[0091] For another example, in one group, the number of data (second data) for set B may be the same as the number of reference signals in set B, or the number of data (second data) for set B may be less than the number of reference signals in set B. In one group, the number of data (first data) for set A may be the same as the number of reference signals in set A, or the number of data (first data) for set A may be less than the number of reference signals in set A.

[0092] For another example, only the same reference signal as set A can be configured and sent to the UE to obtain reference ground truth data. The terminal device can further distinguish which reference ground truth data can also be used for input data from the obtained reference ground truth data. Alternatively, the terminal device no longer distinguishes which reference ground truth data can be used for input data from the obtained reference ground truth data.

[0093] The following first describes the training data collection for spatial beam prediction (BM case-1) with a network-side model (NW-side model).

[0094] In some embodiments, for the network side model and spatial beam prediction, the second reference signal set (set B) used for beam measurement is not a subset of the first reference signal set (set A) used for beam prediction, then one or more second reference signals in the second reference signal set (set B) are used to collect the second data, and one or more first reference signals in the first reference signal set (set A) are used to collect the first data.

[0095] FIG6 is an example diagram of collected data according to an embodiment of the present application. For example, for beam management with AI / ML functions / models and BM case-1 (spatial beam prediction) on the network side, when collecting training data, if set B is not a subset of set A, the gNB can configure the same reference signal as set B and the same reference signal as set A for data collection. The input data (second data, measurement results of set B) and the ground truth data (first data, measurement results of set A) can be associated. As shown in FIG6, each group can include associated set A data (first data) and set B data (second data), and the UE can store the measurement results and report the collected data.

[0096] In some embodiments, for the network side model and spatial beam prediction, the second reference signal set (set B) used for beam measurement is a subset of the first reference signal set (set A) used for beam prediction, then one or more first reference signals in the first reference signal set (set A) are used to collect the first data, or, one or more second reference signals in the second reference signal set (set B) are used to collect the second data and one or more first reference signals in the first reference signal set (set A) are used to collect the first data.

[0097] Figure 7 is an example diagram of collected data according to an embodiment of the present application. For example, for beam management with AI / ML functionality / models and BM case-1 (spatial beam prediction) on the network side, when collecting training data, if set B is a subset of set A, the gNB can configure the same reference signals as set A for data collection. As shown in Figure 7, each group can include set A data (first data), and the UE can store measurement results and report the collected data.

[0098] For another example, if set B is a subset of set A, the gNB can configure the same reference signal as set B and the same reference signal as set A for data collection. The input data (second data, measurement results for set B) and the ground truth data (first data, measurement results for set A) can be associated. As shown in Figure 6, each group can include associated set A data (first data) and set B data (second data), and the UE can store the measurement results and report the collected data.

[0099] For another example, the difference between set A data (first data) and set B data (second data) is used as the collected data.

[0100] In some embodiments, for the network-side model and spatial beam prediction, the second reference signal set (set B) for beam measurement is associated with the second beam pattern and / or the first reference signal set (set A) for beam prediction is associated with the first beam pattern.

[0101] One or more second reference signals in the second reference signal set (set B) are used to collect the second data, the second beam pattern is indicated to the terminal device, and the second data and the second beam pattern are associated, and / or, one or more first reference signals in the first reference signal set (set A) are used to collect the first data, then the first beam pattern is indicated to the terminal device, and the first data and the first beam pattern are associated.

[0102] Figure 8 is an example diagram of collected data according to an embodiment of the present application. For example, if different beam patterns are applied to set A and / or set B of the network-side AI / ML function / model, when the reference signals of set A and / or set B are configured for data collection, the gNB may indicate the beam pattern of set A and / or set B to the UE, for example, via RRC and / or MAC CE and / or DCI.

[0103] As shown in Figure 8, the measurement results of set A and / or set B can be marked with the corresponding beam pattern. For example, each group corresponds to the identifier of a beam pattern; each group can include associated set A data (first data) and set B data (second data), and the UE can store the measurement results and report the collected data.

[0104] For another example, in a group, if the beam patterns of set A and set B are different, the measurement results of set A and set B can be marked with different beam patterns.

[0105] The following further describes the collection of training data for spatial beam prediction (BM case-1) with a terminal-side model (UE-side model).

[0106] In some embodiments, for the terminal side model and spatial beam prediction, the second reference signal set (set B) used for beam measurement is not a subset of the first reference signal set (set A) used for beam prediction, then one or more second reference signals in the second reference signal set (set B) are used to collect the second data, and one or more first reference signals in the first reference signal set (set A) are used to collect the first data.

[0107] For example, for beam management with AI / ML capabilities / models and BM case-1 (spatial beam prediction) on the UE side, when collecting training data, if set B is not a subset of set A, the gNB can configure the same reference signals as set B and the same reference signals as set A for data collection. The input data (second data, measurement results for set B) and the ground truth data (first data, measurement results for set A) can be associated. As shown in Figure 6, each group can include associated set A data (first data) and set B data (second data), and the UE can store the measurement results and report the collected data.

[0108] In some embodiments, for the terminal side model and spatial beam prediction, the second reference signal set (set B) used for beam measurement is a subset of the first reference signal set (set A) used for beam prediction, then one or more first reference signals in the first reference signal set (set A) are used to collect the first data, or, one or more second reference signals in the second reference signal set (set B) are used to collect the second data and one or more first reference signals in the first reference signal set (set A) are used to collect the first data.

[0109] For example, for beam management with AI / ML functions / models and BM case-1 (spatial beam prediction) on the terminal side, when collecting training data, if set B is a subset of set A, the gNB can configure the same reference signals as set A for data collection. As shown in Figure 7, set A data (first data) can be included in each group, and the UE can store measurement results and report the collected data.

[0110] For another example, if set B is a subset of set A, the gNB can configure the same reference signal as set B and the same reference signal as set A for data collection. The input data (second data, measurement results for set B) and the ground truth data (first data, measurement results for set A) can be associated. As shown in Figure 6, each group can include associated set A data (first data) and set B data (second data), and the UE can store the measurement results and report the collected data.

[0111] For another example, the difference between set A data (first data) and set B data (second data) is used as the collected data.

[0112] In some embodiments, for the terminal side model and spatial beam prediction, the second beam pattern supported / preferred by the second reference signal set (set B) for beam measurement and / or the first beam pattern supported / preferred by the first reference signal set (set A) for beam prediction is reported by the terminal device, and / or whether the second reference signal set (set B) is a subset of the first reference signal set (set A) is also reported by the terminal device;

[0113] One or more second reference signals in the second reference signal set (set B), and / or one or more first reference signals in the first reference signal set (set A), are configured according to a beam pattern supported by the terminal device.

[0114] Figure 9 is a schematic diagram of data collection according to an embodiment of the present application. For example, for beam management with AI / ML functionality / models and BM case-1 (spatial beam prediction) on the terminal side, during training data collection, the UE may report supported / preferred beam patterns for set A and / or set B (as shown in 901). In addition, the UE may also report whether set B is a subset of set A.

[0115] The gNB may configure reference signals for Set A and / or Set B based on the beam patterns supported by the UE (as shown in 902). The gNB may trigger RS ​​transmission for data collection (as shown in 903). If the UE supports multiple beam patterns for Set A and / or Set B, the gNB may configure and trigger RS ​​transmission multiple times (as shown in 904 and 905). The UE may collect data and report the collected data to the gNB (as shown in 906).

[0116] In some embodiments, a plurality of second beam patterns and / or a plurality of first beam patterns are supported by the terminal device;

[0117] One or more second reference signals in the second reference signal set (set B) are used to collect the second data, then one second beam pattern among the multiple second beam patterns is indicated to the terminal device, and the second data and the second beam pattern are associated, and / or, one or more first reference signals in the first reference signal set (set A) are used to collect the first data, then one first beam pattern among the multiple first beam patterns is indicated to the terminal device, and the first data and the first beam pattern are associated.

[0118] Figure 10 is an example diagram of collected data according to an embodiment of the present application. For example, if multiple beam patterns of set A and / or set B are supported by the UE, then when configuring reference signals of set A and / or set B for data collection, the gNB may indicate the beam patterns of set A and / or set B to the UE, for example, via RRC and / or MAC CE and / or DCI.

[0119] As shown in Figure 10, the measurement results of set A and / or set B can be marked with the corresponding beam pattern. For example, each group corresponds to the identifier of a beam pattern; each group can include associated set A data (first data) and set B data (second data), and the UE can store the measurement results and report the collected data.

[0120] For another example, in a group, if the beam patterns of set A and set B are different, the measurement results of set A and set B can be marked with different beam patterns.

[0121] The following further describes the training data collection for time beam prediction (BM case-2) with a network-side model (NW-side model).

[0122] In some embodiments, for the network side model and time beam prediction, the second reference signal set (set B) used for beam measurement is not a subset of the first reference signal set (set A) used for beam prediction, then one or more second reference signals for one or more time instances in the second reference signal set (set B) are used to collect the second data, and one or more first reference signals for one or more time instances in the first reference signal set (set A) are used to collect the first data.

[0123] Figure 11 is an example diagram of reference signal transmission according to an embodiment of the present application. For example, for beam management with AI / ML functionality / models and BM case-2 (time beam prediction) on the network side, when collecting training data, if set B is not a subset of set A, the gNB may configure the same reference signal as set B for one or more time instances and the same reference signal as set A for one or more time instances for data collection.

[0124] FIG12 is an example diagram of collected data according to an embodiment of the present application. For example, the input data (second data, measurement results for set B) and the ground truth data (first data, measurement results for set A) can be associated. As shown in FIG12 , each group can include associated set A data (first data) for one or more time instances and set B data (second data) for one or more time instances. The UE can store the measurement results and report the collected data.

[0125] In some embodiments, for the network side model and time beam prediction, the second reference signal set (set B) used for beam measurement is a subset of the first reference signal set (set A) used for beam prediction, then one or more first reference signals for one or more time instances in the first reference signal set (set A) are used to collect the first data, or, one or more second reference signals for one or more time instances in the second reference signal set (set B) are used to collect the second data and one or more first reference signals for one or more time instances in the first reference signal set (set A) are used to collect the first data.

[0126] In some embodiments, for the network-side model and time beam prediction, the second reference signal set (set B) used for beam measurement is associated with the second beam pattern and / or the first reference signal set (set A) used for beam prediction is associated with the first beam pattern.

[0127] One or more second reference signals in the second reference signal set (set B) are used to collect the second data, the second beam pattern is indicated to the terminal device, and the second data and the second beam pattern are associated, and / or, one or more first reference signals in the first reference signal set (set A) are used to collect the first data, then the first beam pattern is indicated to the terminal device, and the first data and the first beam pattern are associated.

[0128] Figure 13 is an example diagram of collected data according to an embodiment of the present application. For example, if different beam patterns are applied to set A and / or set B of the network-side AI / ML function / model, when the reference signals of set A and / or set B are configured for data collection, the gNB may indicate the beam pattern of set A and / or set B to the UE, for example, via RRC and / or MAC CE and / or DCI.

[0129] As shown in Figure 13, the measurement results of set A and / or set B can be marked with corresponding beam patterns. For example, each group corresponds to the identifier of a beam pattern; each group can include associated set A data (first data) for one or more time instances and set B data (second data) for one or more time instances. The UE can store the measurement results and report the collected data.

[0130] For another example, in a group, if the beam patterns of set A and set B are different, the measurement results of set A and set B can be marked with different beam patterns.

[0131] For another example, the collected set A data (first data) and / or set B data (second data) can also be associated with the number of time instances used for measurement and the intervals between the time instances used for measurement, and the collected set A data (first data) and / or set B data (second data) can also be associated with the number of time instances used for prediction and the intervals between the time instances used for prediction.

[0132] The following further explains the training data collection for time beam prediction (BM case-2) with a terminal-side model (UE-side model).

[0133] In some embodiments, for the terminal side model and time beam prediction, the second reference signal set (set B) used for beam measurement is not a subset of the first reference signal set (set A) used for beam prediction, then one or more second reference signals for one or more time instances in the second reference signal set (set B) are used to collect the second data, and one or more first reference signals for one or more time instances in the first reference signal set (set A) are used to collect the first data.

[0134] For example, for beam management with AI / ML capabilities / models and BM case-2 (time beam prediction) on the UE side, when collecting training data, if set B is not a subset of set A, the gNB can configure the same reference signals as set B and the same reference signals as set A for data collection. The input data (second data, measurement results for set B) and the ground truth data (first data, measurement results for set A) can be associated. As shown in Figure 12, each group can include associated set A data (first data) for one or more time instances and set B data (second data) for one or more time instances. The UE can store the measurement results and report the collected data.

[0135] In some embodiments, for the terminal side model and time beam prediction, the second reference signal set (set B) used for beam measurement is a subset of the first reference signal set (set A) used for beam prediction, then one or more first reference signals for one or more time instances in the first reference signal set (set A) are used to collect the first data, or, one or more second reference signals for one or more time instances in the second reference signal set (set B) are used to collect the second data and one or more first reference signals for one or more time instances in the first reference signal set (set A) are used to collect the first data.

[0136] In some embodiments, for the terminal side model and time beam prediction, the second beam pattern supported by the second reference signal set (set B) for beam measurement and / or the first beam pattern supported by the first reference signal set (set A) for beam prediction is reported by the terminal device, and / or whether the second reference signal set (set B) is a subset of the first reference signal set (set A) is reported by the terminal device, and / or the number of time instances supported or preferred (supported / perferred) for measurement is reported by the terminal device, and / or the number of time instances supported or preferred (supported / perferred) for time prediction is reported by the terminal device;

[0137] One or more second reference signals in the second reference signal set (set B), and / or one or more first reference signals in the first reference signal set (set A), are configured according to the beam patterns supported by the terminal device and / or the number of time instances supported or preferred by the terminal device.

[0138] Figure 14 is a schematic diagram of data collection in accordance with an embodiment of the present application. For example, for beam management with AI / ML functionality / model and BM case-2 (time beam prediction) on the terminal side, during training data collection, the UE may report supported / preferred beam patterns for set A and / or set B (as shown in 1401). In addition, the UE may also report the number of supported / preferred time instances for measurement and / or the number of supported / preferred time instances for time prediction.

[0139] The gNB may configure reference signals for set A and / or set B based on the beam patterns supported by the UE (as shown in 1402). The gNB may trigger RS ​​transmission for one or more time instances for data collection (as shown in 1403). If the UE supports multiple beam patterns for set A and / or set B, the gNB may configure and trigger RS ​​transmission multiple times (as shown in 1404 and 1405). The UE may collect data and report the collected data to the gNB (as shown in 1406).

[0140] In some embodiments, a plurality of second beam patterns and / or a plurality of first beam patterns are supported by the terminal device;

[0141] One or more second reference signals in the second reference signal set (set B) are used to collect the second data, then one second beam pattern among the multiple second beam patterns is indicated to the terminal device, and the second data and the second beam pattern are associated, and / or, one or more first reference signals in the first reference signal set (set A) are used to collect the first data, then one first beam pattern among the multiple first beam patterns is indicated to the terminal device, and the first data and the first beam pattern are associated.

[0142] FIG15 is an example diagram of collected data according to an embodiment of the present application. For example, if multiple beam patterns of set A and / or set B are supported by the UE, then when configuring reference signals of set A and / or set B for data collection, the gNB may indicate the beam patterns of set A and / or set B to the UE, for example, via RRC and / or MAC CE and / or DCI.

[0143] As shown in Figure 10, the measurement results of set A and / or set B can be marked with corresponding beam patterns. For example, each group corresponds to the identifier of a beam pattern; each group can include associated set A data (first data) for one or more time instances and set B data (second data) for one or more time instances. The UE can store the measurement results and report the collected data.

[0144] For another example, in a group, if the beam patterns of set A and set B are different, the measurement results of set A and set B can be marked with different beam patterns. For another example, in a group, the measurement results of set B for one or more time instances are included in the collected data.

[0145] For another example, the collected set A data (first data) and / or set B data (second data) can also be associated with the number of time instances used for measurement and the intervals between the time instances used for measurement, and the collected set A data (first data) and / or set B data (second data) can also be associated with the number of time instances used for prediction and the intervals between the time instances used for prediction.

[0146] The above schematically illustrates data collection, and the following schematically illustrates reference signal configuration and data reporting.

[0147] In some embodiments, the terminal device collects and / or stores the first data and / or the second data; and the terminal device reports the first data and / or the second data to the network device; wherein the reporting is initiated by the terminal device or triggered by the network device.

[0148] For example, the UE may store the collected data and, under certain conditions, trigger / initiate reporting by the UE, or by the network. The UE may report the collected data to the gNB.

[0149] In one example, if the accumulated data size has reached a certain threshold (the threshold may be predefined or configured by the network side), the UE may initiate a request to send the collected data.

[0150] In another example, a storage header room report can be introduced. For example, the storage header room can be defined as the available memory size. If the storage header room reaches a certain threshold, the UE can initiate a request to send the collected data.

[0151] For another example, the UE does not store the collected data; after the UE performs the measurement, the UE reports, for example, using UCI.

[0152] For another example, for training data collection, the data may be further labeled with one or more or all of the following information: cell ID, carrier ID, bandwidth part ID (BWP ID), and TCI state.

[0153] For another example, for training data collection, data (including model input data and / or ground truth data) can be associated with an AI / ML function / model. For example, the model input data and ground truth data can be associated with an AI / ML function / model ID. When triggering training data collection, the gNB can indicate the corresponding AI / ML function / model, for example, the AI / ML function / model ID.

[0154] For another example, when collecting training data, the AI / ML function / model may be enabled, i.e., data collection may be performed using AI / ML. Alternatively, the AI / ML function / model may not be enabled. For example, a UE with conventional beam management may also perform training data collection.

[0155] In some embodiments, the reference signal used to acquire the first data and the first reference signal set (set A) used for beam prediction are configured using the same configuration information. In other embodiments, the reference signal used to acquire the first data and the first reference signal set (set A) used for beam prediction are configured using different configuration information.

[0156] In some embodiments, the reference signal used to acquire the second data and the second reference signal set (set B) used for beam measurement are configured using the same configuration information. In other embodiments, the reference signal used to acquire the second data and the second reference signal set (set B) used for beam measurement are configured using different configuration information.

[0157] For example, the reference signals used to collect the model input data (second data) may be different from set B, and / or the reference signals used to collect the baseline real data (first data) may be different from set A. For another example, set B may be a subset of the reference signals used to collect the model input data (second data), and / or set A may be a subset of the reference signals used to collect the baseline real data (first data).

[0158] The above schematically illustrates reference signal configuration and data reporting. The following describes content related to overhead reduction.

[0159] In some embodiments, group common downlink control information (DCI) is used to trigger multiple terminal devices to perform measurements for data collection; the group common downlink control information (DCI) is a first DCI, and a first RNTI is used for the first DCI.

[0160] For example, a group-common DCI can be introduced to trigger multiple UEs or a group of UEs to perform measurements for data collection. For example, the group-common DCI can be newly defined, or a new RNTI value can be introduced for the group-common DCI. After receiving the group-common DCI, multiple UEs can perform measurements and collect data. Whether the UE reports or stores the measurement results may depend on network configuration and / or UE capabilities.

[0161] For another example, CSI-RS may be sent to multiple UEs on the same time resources and / or the same frequency resources.

[0162] For another example, for time beam prediction (BM case-2), when collecting ground truth data, different subsets of reference signals in set A can be sent at different time instances. For example, subset 1 of set A is sent at time 1, subset 2 of set A is sent at time 2, and so on.

[0163] The following describes content related to performance monitoring.

[0164] In some embodiments, the terminal device determines (checks) the performance of the AI / ML functionality / model when performing measurements for data collection; wherein at least a portion of the first data and / or at least a portion of the second data is associated with a performance metric of the AI / ML functionality / model.

[0165] For example, when the UE measures the reference signal used for data collection, the UE can also check the performance of the AI / ML function / model, such as SGCS. Some data samples / groups can be marked with the AI / ML performance metric, or all data samples / groups can be marked.

[0166] For another example, if the AI / ML performance metric is above a certain threshold, the corresponding data sample / group is discarded. If the AI / ML performance metric is below a certain threshold, the corresponding data sample / group is retained. Alternatively, if the AI / ML performance metric is below a certain threshold, the corresponding data sample / group is discarded. If the AI / ML performance metric is above a certain threshold, the corresponding data sample / group is retained.

[0167] For another example, if the performance of the AI / ML function / model is poor (e.g., below a threshold), the UE may initiate a request for data collection.

[0168] In some embodiments, one or more reference signals for AI / ML functionality / model monitoring are used for measurements in data collection.

[0169] For example, a reference signal set used for AI / ML functionality / model monitoring may also be used for data collection, or one or more subsets of a reference signal set used for AI / ML functionality / model monitoring may also be used for data collection.

[0170] The embodiments of the present application can be applied to both the UE-side model and the gNB-side model, but the present application is not limited thereto. Furthermore, the AI / ML of the embodiments of the present application can be used for beam management, such as temporal beam prediction and spatial beam prediction, but the present application is not limited thereto. For example, non-AI / ML methods can also be used for data collection.

[0171] The above embodiments are merely exemplary of the present invention, but the present invention is not limited thereto. Appropriate modifications may be made based on the above embodiments. For example, the above embodiments may be used alone, or one or more of the above embodiments may be combined.

[0172] As can be seen from the above embodiments, the terminal device obtains data for AI / ML functionality / model training based on the configuration information. This allows accurate training data to be obtained, improving the performance and efficiency of AI / ML.

[0173] Embodiments of the second aspect

[0174] The embodiment of the present application provides a data collection method, which is described from the perspective of a network device. The embodiment of the second aspect can be combined with the embodiment of the first aspect, and the same contents as the embodiment of the first aspect will not be repeated.

[0175] FIG16 is a schematic diagram of a data collection method according to an embodiment of the present application. As shown in FIG16 , the method includes:

[0176] 1601, the network device sends configuration information for collecting data to the terminal device;

[0177] As shown in FIG16 , the method may further include:

[0178] 1602. The terminal device obtains data for AI / ML functionality / model training based on the configuration information.

[0179] It is worth noting that FIG16 above is merely a schematic illustration of an embodiment of the present application, and the present application is not limited thereto. For example, the execution order of the various operations may be appropriately adjusted, and other operations may be added or some operations may be reduced. Those skilled in the art may make appropriate modifications based on the above description, and are not limited to the description of FIG16 above.

[0180] The above embodiments are merely exemplary of the present invention, but the present invention is not limited thereto. Appropriate modifications may be made based on the above embodiments. For example, the above embodiments may be used alone, or one or more of the above embodiments may be combined.

[0181] As can be seen from the above embodiments, the terminal device obtains data for AI / ML functionality / model training based on the configuration information. This allows accurate training data to be obtained, improving the performance and efficiency of AI / ML.

[0182] Embodiments of the third aspect

[0183] The embodiment of the present application provides a data collection device, which may be, for example, a terminal device, or one or more components or assemblies configured in the terminal device, and the same contents as those in the first and second aspects of the embodiment will not be repeated.

[0184] FIG17 is a schematic diagram of a data collection device according to an embodiment of the present application. As shown in FIG17 , the data collection device 1700 according to an embodiment of the present application includes:

[0185] A receiving unit 1701 receives configuration information for collecting data from a network device;

[0186] The processing unit 1702 obtains data for AI / ML functionality / model training based on the configuration information.

[0187] In some embodiments, first data (label data) for output of an AI / ML functionality / model is collected, and / or second data (input data) for input of an AI / ML functionality / model is collected; the first data and the second data are collected in association.

[0188] In some embodiments, one or more second reference signals in a second reference signal set (set B) for beam measurement are sent to the terminal device, and the terminal device measures the second reference signals and obtains the second data.

[0189] In some embodiments, one or more first reference signals in a first reference signal set (set A) for beam prediction are sent to the terminal device, and the terminal device measures the first reference signals and obtains the first data.

[0190] In some embodiments, the second data includes an index of the second reference signal and corresponding beam quality information, and the first data includes an index of the first reference signal and corresponding beam quality information; or, the second data includes an index of the second reference signal, and the first data includes an index of the first reference signal.

[0191] In some embodiments, for network-side models and spatial beam prediction,

[0192] The second reference signal set (set B) used for beam measurement is not a subset of the first reference signal set (set A) used for beam prediction, then one or more second reference signals in the second reference signal set (set B) are used to collect the second data, and one or more first reference signals in the first reference signal set (set A) are used to collect the first data.

[0193] In some embodiments, for network-side models and spatial beam prediction,

[0194] The second reference signal set (set B) used for beam measurement is a subset of the first reference signal set (set A) used for beam prediction, then one or more first reference signals in the first reference signal set (set A) are used to collect the first data, or, one or more second reference signals in the second reference signal set (set B) are used to collect the second data and one or more first reference signals in the first reference signal set (set A) are used to collect the first data.

[0195] In some embodiments, for the network-side model and spatial beam prediction, the second reference signal set (set B) for beam measurement is associated with a second beam pattern and / or the first reference signal set (set A) for beam prediction is associated with a first beam pattern.

[0196] In some embodiments, one or more second reference signals in the second reference signal set (set B) are used to collect the second data, then the second beam pattern is indicated to the terminal device, and the second data and the second beam pattern are associated, and / or, one or more first reference signals in the first reference signal set (set A) are used to collect the first data, then the first beam pattern is indicated to the terminal device, and the first data and the first beam pattern are associated.

[0197] In some embodiments, for the terminal side model and spatial beam prediction,

[0198] The second reference signal set (set B) used for beam measurement is not a subset of the first reference signal set (set A) used for beam prediction, then one or more second reference signals in the second reference signal set (set B) are used to collect the second data, and one or more first reference signals in the first reference signal set (set A) are used to collect the first data.

[0199] In some embodiments, for the terminal side model and spatial beam prediction,

[0200] The second reference signal set (set B) used for beam measurement is a subset of the first reference signal set (set A) used for beam prediction, then one or more first reference signals in the first reference signal set (set A) are used to collect the first data, or, one or more second reference signals in the second reference signal set (set B) are used to collect the second data and one or more first reference signals in the first reference signal set (set A) are used to collect the first data.

[0201] In some embodiments, for the terminal side model and spatial beam prediction,

[0202] The second beam pattern supported by the second reference signal set (set B) for beam measurement and / or the first beam pattern supported by the first reference signal set (set A) for beam prediction are reported by the terminal device, and / or whether the second reference signal set (set B) is a subset of the first reference signal set (set A) is also reported by the terminal device.

[0203] In some embodiments, for the terminal side model and spatial beam prediction,

[0204] One or more second reference signals in the second reference signal set (set B), and / or one or more first reference signals in the first reference signal set (set A), are configured according to a beam pattern supported by the terminal device.

[0205] In some embodiments, a plurality of second beam patterns and / or a plurality of first beam patterns are supported by the terminal device;

[0206] One or more second reference signals in the second reference signal set (set B) are used to collect the second data, then one second beam pattern among the multiple second beam patterns is indicated to the terminal device, and the second data and the second beam pattern are associated, and / or, one or more first reference signals in the first reference signal set (set A) are used to collect the first data, then one first beam pattern among the multiple first beam patterns is indicated to the terminal device, and the first data and the first beam pattern are associated.

[0207] In some embodiments, for network-side models and time beam prediction,

[0208] The second reference signal set (set B) used for beam measurement is not a subset of the first reference signal set (set A) used for beam prediction, then one or more second reference signals for one or more time instances in the second reference signal set (set B) are used to collect the second data, and one or more first reference signals for one or more time instances in the first reference signal set (set A) are used to collect the first data.

[0209] In some embodiments, for network-side models and time beam prediction,

[0210] The second reference signal set (set B) used for beam measurement is a subset of the first reference signal set (set A) used for beam prediction, then one or more first reference signals for one or more time instances in the first reference signal set (set A) are used to collect the first data, or, one or more second reference signals for one or more time instances in the second reference signal set (set B) are used to collect the second data and one or more first reference signals for one or more time instances in the first reference signal set (set A) are used to collect the first data.

[0211] In some embodiments, for the network side model and time beam prediction, the second reference signal set (set B) for beam measurement is associated with a second beam pattern and / or the first reference signal set (set A) for beam prediction is associated with a first beam pattern.

[0212] In some embodiments, one or more second reference signals in the second reference signal set (set B) are used to collect the second data, then the second beam pattern is indicated to the terminal device, and the second data and the second beam pattern are associated, and / or, one or more first reference signals in the first reference signal set (set A) are used to collect the first data, then the first beam pattern is indicated to the terminal device, and the first data and the first beam pattern are associated.

[0213] In some embodiments, the collected set A data (first data) and / or set B data (second data) can also be associated with the number of time instances used for measurement and the intervals between the time instances used for measurement, and the collected set A data (first data) and / or set B data (second data) can also be associated with the number of time instances used for prediction and the intervals between the time instances used for prediction.

[0214] In some embodiments, for the terminal side model and time beam prediction,

[0215] The second reference signal set (set B) used for beam measurement is not a subset of the first reference signal set (set A) used for beam prediction, then one or more second reference signals for one or more time instances in the second reference signal set (set B) are used to collect the second data, and one or more first reference signals for one or more time instances in the first reference signal set (set A) are used to collect the first data.

[0216] In some embodiments, for the terminal side model and time beam prediction,

[0217] The second reference signal set (set B) used for beam measurement is a subset of the first reference signal set (set A) used for beam prediction, then one or more first reference signals for one or more time instances in the first reference signal set (set A) are used to collect the first data, or, one or more second reference signals for one or more time instances in the second reference signal set (set B) are used to collect the second data and one or more first reference signals for one or more time instances in the first reference signal set (set A) are used to collect the first data.

[0218] In some embodiments, for the terminal side model and time beam prediction,

[0219] The second beam pattern supported by the second reference signal set (set B) for beam measurement and / or the first beam pattern supported by the first reference signal set (set A) for beam prediction are reported by the terminal device, and / or whether the second reference signal set (set B) is a subset of the first reference signal set (set A) is reported by the terminal device, and / or the number of time instances supported or preferred (supported / perferred) for measurement is reported by the terminal device, and / or the number of time instances supported or preferred (supported / perferred) for time prediction is reported by the terminal device.

[0220] In some embodiments, for the terminal side model and time beam prediction,

[0221] One or more second reference signals in the second reference signal set (set B), and / or one or more first reference signals in the first reference signal set (set A), are configured according to the beam patterns supported by the terminal device and / or the number of time instances supported or preferred by the terminal device.

[0222] In some embodiments, a plurality of second beam patterns and / or a plurality of first beam patterns are supported by the terminal device;

[0223] One or more second reference signals in the second reference signal set (set B) are used to collect the second data, then one second beam pattern among the multiple second beam patterns is indicated to the terminal device, and the second data and the second beam pattern are associated, and / or, one or more first reference signals in the first reference signal set (set A) are used to collect the first data, then one first beam pattern among the multiple first beam patterns is indicated to the terminal device, and the first data and the first beam pattern are associated.

[0224] In some embodiments, the collected set A data (first data) and / or set B data (second data) can also be associated with the number of time instances used for measurement and the intervals between the time instances used for measurement, and the collected set A data (first data) and / or set B data (second data) can also be associated with the number of time instances used for prediction and the intervals between the time instances used for prediction.

[0225] In some embodiments, the processing unit 1702 is further configured to collect and / or store the first data and / or the second data. As shown in FIG17 , the data collection device 1700 may further include:

[0226] The sending unit 1703 reports the first data and / or the second data to the network device; wherein the reporting is initiated by the terminal device or triggered by the network device.

[0227] In some embodiments, the reference signal used to obtain the first data and the first reference signal set (set A) used for beam prediction are configured by the same configuration information, or the reference signal used to obtain the first data and the first reference signal set (set A) used for beam prediction are configured by different configuration information.

[0228] In some embodiments, the reference signal used to obtain the second data and the second reference signal set (set B) used for beam measurement are configured by the same configuration information, or the reference signal used to obtain the second data and the second reference signal set (set B) used for beam measurement are configured by different configuration information.

[0229] In some embodiments, group common downlink control information (DCI) is used to trigger multiple terminal devices to perform measurements for data collection; the group common downlink control information (DCI) is a first DCI, and a first RNTI is used for the first DCI.

[0230] In some embodiments, the processing unit 1702 is further used to: determine (check) the performance of the AI / ML functionality / model when performing measurements for data collection; wherein at least a portion of the first data and / or at least a portion of the second data is associated with a performance metric of the AI / ML functionality / model.

[0231] In some embodiments, one or more reference signals for AI / ML functionality / model monitoring are used for measurements in data collection.

[0232] The above embodiments are merely exemplary of the present invention, but the present invention is not limited thereto. Appropriate modifications may be made based on the above embodiments. For example, the above embodiments may be used alone, or one or more of the above embodiments may be combined.

[0233] It is worth noting that the above description only describes the components or modules related to the present application, but the present application is not limited thereto. The data collection device 1700 may also include other components or modules. For details of these components or modules, please refer to the relevant art.

[0234] In addition, for the sake of simplicity, FIG17 only illustrates the connection relationship or signal direction between various components or modules. However, it should be clear to those skilled in the art that various related technologies such as bus connection can be used. The above-mentioned components or modules can be implemented by hardware facilities such as processors, memories, transmitters, and receivers; the implementation of this application is not limited to this.

[0235] As can be seen from the above embodiments, the terminal device obtains data for AI / ML functionality / model training based on the configuration information. This allows accurate training data to be obtained, improving the performance and efficiency of AI / ML.

[0236] Embodiments of the fourth aspect

[0237] The embodiment of the present application provides a data collection device, which may be, for example, a network device, or one or more components or assemblies configured on the network device, and the contents that are the same as those in the first to third aspects of the embodiment are not repeated here.

[0238] FIG18 is another schematic diagram of a data collection device according to an embodiment of the present application. As shown in FIG18 , the data collection device 1800 includes:

[0239] A sending unit 1801 sends configuration information for collecting data to a terminal device; wherein the configuration information is used by the terminal device to obtain data for AI / ML functionality / model training.

[0240] In some embodiments, as shown in FIG18 , the data collection device 1800 may further include:

[0241] The receiving unit 1802 receives the first data and / or the second data reported by the terminal device; wherein the reporting is initiated by the terminal device or triggered by a network device.

[0242] The above embodiments are merely exemplary of the present invention, but the present invention is not limited thereto. Appropriate modifications may be made based on the above embodiments. For example, the above embodiments may be used alone, or one or more of the above embodiments may be combined.

[0243] It is worth noting that the above description only describes the components or modules related to the present application, but the present application is not limited thereto. The data collection device 1800 may also include other components or modules. For details of these components or modules, please refer to the relevant art.

[0244] In addition, for the sake of simplicity, FIG18 only illustrates the connection relationship or signal direction between various components or modules. However, it should be clear to those skilled in the art that various related technologies such as bus connection can be used. The above-mentioned components or modules can be implemented by hardware facilities such as processors, memories, transmitters, and receivers; the implementation of this application is not limited to this.

[0245] As can be seen from the above embodiments, the terminal device obtains data for AI / ML functionality / model training based on the configuration information. This allows accurate training data to be obtained, improving the performance and efficiency of AI / ML.

[0246] Embodiments of the fifth aspect

[0247] An embodiment of the present application also provides a communication system, and reference may be made to FIG1 . The contents that are the same as those in the first to fourth aspects of the embodiments will not be repeated.

[0248] In some embodiments, the communication system 100 may include at least:

[0249] a network device that sends configuration information for collecting data to a terminal device;

[0250] A terminal device acquires data for AI / ML functionality / model training based on the configuration information.

[0251] The embodiment of the present application also provides a terminal device, but the present application is not limited thereto and may also be other devices.

[0252] Figure 19 is a schematic diagram of a terminal device according to an embodiment of the present application. As shown in Figure 19 , terminal device 1900 may include a processor 1910 and a memory 1920. Memory 1920 stores data and programs and is coupled to processor 1910. It should be noted that this diagram is exemplary; other types of structures may be used to supplement or replace this structure to implement telecommunication or other functions.

[0253] For example, the processor 1910 may be configured to execute a program to implement the data collection method as described in the embodiment of the first aspect. For example, the processor 1910 may be configured to perform the following control: receiving configuration information for collecting data from a network device; and obtaining data for AI / ML functionality / model training based on the configuration information.

[0254] As shown in Figure 19 , the terminal device 1900 may further include: a communication module 1930, an input unit 1940, a display 1950, and a power supply 1960. The functions of these components are similar to those in the prior art and are not described here in detail. It is worth noting that the terminal device 1900 does not necessarily include all of the components shown in Figure 19 , and these components are not essential. Furthermore, the terminal device 1900 may also include components not shown in Figure 19 , for which reference may be made to the prior art.

[0255] An embodiment of the present application further provides a network device, which may be, for example, a base station, but the present application is not limited thereto and may also be other network devices.

[0256] Figure 20 is a schematic diagram illustrating the structure of a network device according to an embodiment of the present application. As shown in Figure 20 , network device 2000 may include a processor 2010 (e.g., a central processing unit (CPU)) and a memory 2020. Memory 2020 is coupled to processor 2010. Memory 2020 can store various data and also stores an information processing program 2030, which is executed under the control of processor 2010.

[0257] For example, the processor 2010 may be configured to execute a program to implement the data collection method as described in the embodiment of the second aspect. For example, the processor 2010 may be configured to perform the following control: sending configuration information for collecting data to a terminal device; the configuration information is used by the terminal device to obtain data for AI / ML functionality / model training.

[0258] In addition, as shown in Figure 20, network device 2000 may further include: a transceiver 2040 and an antenna 2050; wherein, the functions of the above components are similar to those in the prior art and are not described here in detail. It is worth noting that network device 2000 does not necessarily include all the components shown in Figure 20; in addition, network device 2000 may also include components not shown in Figure 20, and reference may be made to the prior art for details.

[0259] An embodiment of the present application also provides a computer program, wherein when the program is executed in a terminal device, the program causes the terminal device to execute the data collection method described in the embodiment of the first aspect.

[0260] An embodiment of the present application also provides a storage medium storing a computer program, wherein the computer program enables a terminal device to execute the data collection method described in the embodiment of the first aspect.

[0261] An embodiment of the present application also provides a computer program, wherein when the program is executed in a network device, the program causes the network device to execute the data collection method described in the embodiment of the second aspect.

[0262] An embodiment of the present application also provides a storage medium storing a computer program, wherein the computer program enables a network device to execute the data collection method described in the embodiment of the second aspect.

[0263] The above devices and methods of the present application can be implemented by hardware or by a combination of hardware and software. The present application relates to such a computer-readable program that, when executed by a logic component, enables the logic component to implement the devices or components described above, or enables the logic component to implement the various methods or steps described above. The present application also relates to a storage medium for storing the above program, such as a hard disk, a magnetic disk, an optical disk, a DVD, a flash memory, etc.

[0264] The method / device described in conjunction with the embodiments of the present application can be directly embodied as hardware, a software module executed by a processor, or a combination of the two. For example, one or more of the functional block diagrams shown in the figure and / or one or more combinations of functional block diagrams can correspond to various software modules of the computer program flow or to various hardware modules. These software modules can respectively correspond to the various steps shown in the figure. These hardware modules can be implemented by solidifying these software modules, for example, using a field programmable gate array (FPGA).

[0265] The software module may be located in RAM memory, flash memory, ROM memory, EPROM memory, EEPROM memory, registers, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art. A storage medium may be coupled to a processor so that the processor can read information from the storage medium and write information to the storage medium; or the storage medium may be an integral part of the processor. The processor and the storage medium may be located in an ASIC. The software module may be stored in the memory of the mobile terminal or in a memory card that can be inserted into the mobile terminal. For example, if the device (such as a mobile terminal) uses a large-capacity MEGA-SIM card or a large-capacity flash memory device, the software module may be stored in the MEGA-SIM card or the large-capacity flash memory device.

[0266] One or more of the functional blocks and / or one or more combinations of functional blocks described in the accompanying drawings may be implemented as a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic device, a discrete gate or transistor logic device, a discrete hardware component, or any appropriate combination thereof for performing the functions described in this application. One or more of the functional blocks and / or one or more combinations of functional blocks described in the accompanying drawings may also be implemented as a combination of computing devices, such as a combination of a DSP and a microprocessor, multiple microprocessors, one or more microprocessors in communication with a DSP, or any other such configuration.

[0267] The present application has been described above in conjunction with specific embodiments. However, those skilled in the art should understand that these descriptions are merely illustrative and are not intended to limit the scope of protection of the present application. Those skilled in the art may make various modifications and variations to the present application based on the spirit and principles of the present application, and such modifications and variations are also within the scope of the present application.

[0268] Regarding the implementation methods including the above embodiments, the following additional notes are also disclosed:

[0269] 1. A data collection method comprising:

[0270] The terminal device receives configuration information for collecting data from the network device;

[0271] The terminal device obtains data for AI / ML functionality / model training based on the configuration information.

[0272] 2. A data collection method comprising:

[0273] The network device sends configuration information for collecting data to the terminal device; the configuration information is used by the terminal device to obtain data for AI / ML functionality / model training.

[0274] 3. A terminal device comprising a memory and a processor, wherein the memory stores a computer program, and the processor is configured to execute the computer program to implement the data collection method as described in Note 1.

[0275] 4. A network device comprising a memory and a processor, wherein the memory stores a computer program, and the processor is configured to execute the computer program to implement the data collection method as described in Note 2.

[0276] 5. A computer program product, comprising at least a computer program, wherein when the computer program is executed by a processor, the terminal device executes the data collection method as described in Note 1.

[0277] 6. A computer program product, comprising at least a computer program, wherein when the computer program is executed by a processor, the network device executes the data collection method as described in Note 2.

Claims

1. A data collection device comprising: a receiving unit configured to receive configuration information for collecting data from a network device; A processing unit that obtains data for AI / ML function / model training based on the configuration information.

2. The device according to claim 1, wherein First data for output of the AI / ML function / model is collected, and / or second data for input of the AI / ML function / model is collected; The first data and the second data are collected in association.

3. The device according to claim 1, wherein One or more second reference signals in a second reference signal set for beam measurement are sent to a terminal device, and the terminal device measures the second reference signals and obtains second data; and / or One or more first reference signals in a first reference signal set for beam prediction are sent to the terminal device, and the terminal device measures the first reference signals and obtains first data.

4. The device according to claim 3, wherein The second data includes an index of the second reference signal and corresponding beam quality information, and the first data includes an index of the first reference signal and corresponding beam quality information; Alternatively, the second data includes an index of the second reference signal, and the first data includes an index of the first reference signal.

5. The device according to claim 1, wherein For network-side models and spatial beam prediction, The second reference signal set used for beam measurement is not a subset of the first reference signal set used for beam prediction, then one or more second reference signals in the second reference signal set are used to collect second data, and one or more first reference signals in the first reference signal set are used to collect first data; or The second reference signal set used for beam measurement is a subset of the first reference signal set used for beam prediction, then one or more first reference signals in the first reference signal set are used to collect the first data, or, one or more second reference signals in the second reference signal set are used to collect the second data and one or more first reference signals in the first reference signal set are used to collect the first data.

6. The device according to claim 1, wherein For the network-side model and spatial beam prediction, the second reference signal set used for beam measurement is associated with the second beam pattern and / or the first reference signal set used for beam prediction is associated with the first beam pattern; One or more second reference signals in the second reference signal set are used to collect second data, the second beam pattern is indicated to the terminal device, and the second data and the second beam pattern are associated, and / or, one or more first reference signals in the first reference signal set are used to collect first data, the first beam pattern is indicated to the terminal device, and the first data and the first beam pattern are associated.

7. The device according to claim 1, wherein For terminal-side models and spatial beam prediction, The second reference signal set used for beam measurement is not a subset of the first reference signal set used for beam prediction, then one or more second reference signals in the second reference signal set are used to collect second data, and one or more first reference signals in the first reference signal set are used to collect first data; or The second reference signal set used for beam measurement is a subset of the first reference signal set used for beam prediction, then one or more first reference signals in the first reference signal set are used to collect the first data, or, one or more second reference signals in the second reference signal set are used to collect the second data and one or more first reference signals in the first reference signal set are used to collect the first data.

8. The device according to claim 1, wherein For terminal-side models and spatial beam prediction, A second beam pattern supported by a second reference signal set for beam measurement and / or a first beam pattern supported by a first reference signal set for beam prediction are reported by a terminal device, and / or whether the second reference signal set is a subset of the first reference signal set is also reported by the terminal device; One or more second reference signals in the second reference signal set, and / or one or more first reference signals in the first reference signal set, are configured according to a beam pattern supported by the terminal device.

9. The device according to claim 8, wherein A plurality of second beam patterns and / or a plurality of first beam patterns are supported by the terminal device; One or more second reference signals in the second reference signal set are used to collect second data, then one second beam pattern among the multiple second beam patterns is indicated to the terminal device, and the second data and the second beam pattern are associated, and / or, one or more first reference signals in the first reference signal set are used to collect first data, then one first beam pattern among the multiple first beam patterns is indicated to the terminal device, and the first data and the first beam pattern are associated.

10. The device according to claim 1, wherein For network side models and time beam prediction, If the second reference signal set used for beam measurement is not a subset of the first reference signal set used for beam prediction, then one or more second reference signals for one or more time instances in the second reference signal set are used to collect second data, and one or more second reference signals for one or more time instances in the first reference signal set are used to collect second data. The first reference signal is used to collect first data; or The second reference signal set used for beam measurement is a subset of the first reference signal set used for beam prediction, then one or more first reference signals for one or more time instances in the first reference signal set are used to collect the first data, or, one or more second reference signals for one or more time instances in the second reference signal set are used to collect the second data and one or more first reference signals for one or more time instances in the first reference signal set are used to collect the first data.

11. The device according to claim 1, wherein For the network-side model and time beam prediction, the second reference signal set used for beam measurement is associated with the second beam pattern and / or the first reference signal set used for beam prediction is associated with the first beam pattern; One or more second reference signals in the second reference signal set are used to collect second data, the second beam pattern is indicated to the terminal device, and the second data and the second beam pattern are associated; and / or one or more first reference signals in the first reference signal set are used to collect first data, the first beam pattern is indicated to the terminal device, and the first data and the first beam pattern are associated; and / or The first data and / or the second data are associated with the number of time instances used for measurement and the intervals between the time instances used for measurement, and the first data and / or the second data are associated with the number of time instances used for prediction and the intervals between the time instances used for prediction.

12. The device according to claim 1, wherein For the terminal side model and time beam prediction, The second reference signal set used for beam measurement is not a subset of the first reference signal set used for beam prediction, then one or more second reference signals for one or more time instances in the second reference signal set are used to collect second data, and one or more first reference signals for one or more time instances in the first reference signal set are used to collect first data; or The second reference signal set used for beam measurement is a subset of the first reference signal set used for beam prediction, then one or more first reference signals for one or more time instances in the first reference signal set are used to collect the first data, or, one or more second reference signals for one or more time instances in the second reference signal set are used to collect the second data and one or more first reference signals for one or more time instances in the first reference signal set are used to collect the first data.

13. The device according to claim 1, wherein For the terminal side model and time beam prediction, The second beam pattern supported by the second reference signal set for beam measurement and / or the first beam pattern supported by the first reference signal set for beam prediction are reported by the terminal device, and / or whether the second reference signal set is a subset of the first reference signal set is reported by the terminal device, and / or the number of time instances supported or preferred for measurement is reported by the terminal device, and / or the number of time instances supported or preferred for time prediction is reported by the terminal device; One or more second reference signals in the second reference signal set, and / or one or more first reference signals in the first reference signal set, are configured according to the beam patterns supported by the terminal device and / or the number of time instances supported or preferred by the terminal device.

14. The device according to claim 13, wherein A plurality of second beam patterns and / or a plurality of first beam patterns are supported by the terminal device; One or more second reference signals in the second reference signal set are used to collect second data, then one second beam pattern in the plurality of second beam patterns is indicated to the terminal device, and the second data and the second beam pattern are associated; and / or one or more first reference signals in the first reference signal set are used to collect first data, then one first beam pattern in the plurality of first beam patterns is indicated to the terminal device, and the first data and the first beam pattern are associated; and / or The first data and / or the second data are associated with the number of time instances used for measurement and the intervals between the time instances used for measurement, and the first data and / or the second data are associated with the number of time instances used for prediction and the intervals between the time instances used for prediction.

15. The device according to claim 1, wherein The processing unit is further configured to collect and / or store the first data and / or the second data; and the apparatus further comprises: A sending unit, which reports the first data and / or the second data to the network device; wherein the reporting is initiated by the terminal device or triggered by the network device.

16. The device according to claim 1, wherein The reference signal used to acquire the first data and the first reference signal set used for beam prediction are configured using the same configuration information, or the reference signal used to acquire the first data and the first reference signal set used for beam prediction are configured using different configuration information; and / or The reference signal used to obtain the second data and the second reference signal set used for beam measurement are configured through the same configuration information, or the reference signal used to obtain the second data and the second reference signal set used for beam measurement are configured through different configuration information.

17. The device according to claim 1, wherein The group common downlink control information is used to trigger multiple terminal devices to perform measurements for data collection; the group common downlink control information is a first DCI, and the first RNTI is used for the first DCI; and / or One or more reference signals for AI / ML function / model monitoring are used for measurements collected from the data.

18. The device according to claim 1, wherein The processing unit is further configured to determine, when performing measurements for data collection, a performance of the AI / ML function / model; wherein at least a portion of the first data and / or at least a portion of the second data is associated with a performance metric of the AI / ML function / model.

19. A data collection device comprising: A sending unit that sends configuration information for collecting data to a terminal device; wherein the configuration information is used by the terminal device to obtain data for AI / ML function / model training.

20. A communication system comprising: a network device that sends configuration information for collecting data to a terminal device; The terminal device obtains data for AI / ML function / model training based on the configuration information.

Images