Time reporting in ai / ML data collection

Abstract

Example embodiments of the present disclosure are directed to time reporting in artificial intelligence (AI) machine learning (ML) data collection. A method comprises receiving, at a first apparatus and from a second apparatus, a timestamp configuration associated with AI / ML data collection; determining, based on the timestamp configuration, timestamp information associated with data generated by the first apparatus, wherein the timestamp information comprises Universal Time Coordinated (UTC) time information included based on a condition; and transmitting the data and the timestamp information. In this way, the UTC time information may be included in the timestamp information based on the condition, rather than being always included in the timestamp information for time reporting. As such, efficient delivery of the timestamp information for AI / ML data collection can be achieved.

Description

TIME REPORTING IN AI / ML DATA COLLECTIONCROSS-REFERENCE TO RELATED APPLICATION

[0001] This application claims priority from, and the benefit of, US Provisional Application No. 63 / 702346, filed October 2, 2024, which is hereby incorporated by reference in its entirety.FIELD

[0002] Various example embodiments of the present disclosure generally relate to the field of telecommunication and in particular, to methods, devices, apparatuses and computer readable storage medium for time reporting in artificial intelligence (Al) machine learning (ML) data collection.BACKGROUND

[0003] A communication network may serve as a facility that enables communications between two or more communication devices or provides communication devices access to a data network. A mobile or wireless communication network is one example of a communication network. A communication device may be provided with a service by an application server.

[0004] The communication network may operate in accordance with standards such as those provided by Third Generation Partnership Project (3GPP) or European Telecommunications Standards Institute (ETSI). Examples of standards provided by 3GPP are the so-called 3GPP standards for cellular technology generations, such as 3GPP standards for 4G technology, 5G technology, 6G technology etc.SUMMARY

[0005] In a first aspect of the present disclosure, there is provided a first apparatus. The first apparatus comprises at least one processor; and at least one memory storing instructions that, when executed by the at least one processor, cause the first apparatus at least to: receive, from a second apparatus, a timestamp configuration associated with artificial intelligence / machine learning (AI / ML) data collection; determine, based on the timestamp configuration, timestamp information associated with data generated by the first apparatus, wherein the timestamp information comprises Universal Time Coordinated (UTC) time information included based on a condition; and transmit the data and the timestamp information.

[0006] In a second aspect of the present disclosure, there is provided a second apparatus. The second apparatus comprises at least one processor; and at least one memory storing instructions that, when executed by the at least one processor, cause the second apparatus at least to: transmit, to a first apparatus, a timestamp configuration associated with artificial intelligence / machine learning(AI / ML) data collection; and receive, from the first apparatus, data generated by the first apparatus and timestamp information associated with the data, wherein the timestamp information is determined by the first apparatus based on the timestamp configuration, and the timestamp information comprises Universal Time Coordinated (UTC) time information included by the first apparatus based on a condition.

[0007] In a third aspect of the present disclosure, there is provided a method. The method comprises: receiving, from a second apparatus, a timestamp configuration associated with artificial intelligence / machine learning (AI / ML) data collection; determining, based on the timestamp configuration, timestamp information associated with data generated by the first apparatus, wherein the timestamp information comprises Universal Time Coordinated (UTC) time information included based on a condition; and transmitting the data and the timestamp information.

[0008] In a fourth aspect of the present disclosure, there is provided a method. The method comprises: transmitting, to a first apparatus, a timestamp configuration associated with artificial intelligence / machine learning (AI / ML) data collection; and receiving, from the first apparatus, data generated by the first apparatus and timestamp information associated with the data, wherein the timestamp information is determined by the first apparatus based on the timestamp configuration, and the timestamp information comprises Universal Time Coordinated (UTC) time information included by the first apparatus based on a condition.

[0009] In a fifth aspect of the present disclosure, there is provided a first apparatus. The first apparatus comprises means for receiving, from a second apparatus, a timestamp configuration associated with artificial intelligence / machine learning (AI / ML) data collection; means for determining, based on the timestamp configuration, timestamp information associated with data generated by the first apparatus, wherein the timestamp information comprises Universal Time Coordinated (UTC) time information included based on a condition; and means for transmitting the data and the timestamp information.

[0010] In a sixth aspect of the present disclosure, there is provided a second apparatus. The second apparatus comprises means for transmitting, to a first apparatus, a timestamp configuration associated with artificial intelligence / machine learning (AI / ML) data collection; and means for receiving, from the first apparatus, data generated by the first apparatus and timestamp information associated with the data, wherein the timestamp information is determined by the first apparatus based on the timestamp configuration, and the timestamp information comprises Universal Time Coordinated (UTC) time information included by the first apparatus based on a condition.

[0011] In a seventh aspect of the present disclosure, there is provided a computer readable medium. The computer readable medium comprises instructions stored thereon for causing anapparatus to perform at least the method according to the third aspect.

[0012] In an eighth aspect of the present disclosure, there is provided a computer readable medium. The computer readable medium comprises instructions stored thereon for causing an apparatus to perform at least the method according to the fourth aspect.

[0013] It is to be understood that the Summary section is not intended to identify key or essential features of embodiments of the present disclosure, nor is it intended to be used to limit the scope of the present disclosure. Other features of the present disclosure will become easily comprehensible through the following description.BRIEF DESCRIPTION OF THE DRAWINGS

[0014] Some example embodiments will now be described with reference to the accompanying drawings, where:

[0015] FIG. 1 illustrates an example communication environment in which example embodiments of the present disclosure can be implemented;

[0016] FIG. 2 illustrates a signaling chart for time reporting in AI / ML data collection according to example embodiments of the present disclosure;

[0017] FIG. 3 illustrates a signaling chart for time reporting based on an AI / ML data collection configuration according to example embodiments of the present disclosure;

[0018] FIG. 4 illustrates a flowchart of a method implemented at a first apparatus in accordance with some example embodiments of the present disclosure;

[0019] FIG. 5 illustrates a flowchart of a method implemented at a second apparatus in accordance with some example embodiments of the present disclosure;

[0020] FIG. 6 illustrates a simplified block diagram of a device that is suitable for implementing example embodiments of the present disclosure; and

[0021] FIG. 7 illustrates a block diagram of an example computer readable medium in accordance with some example embodiments of the present disclosure.

[0022] Throughout the drawings, the same or similar reference numerals represent the same or similar element.DETAILED DESCRIPTION

[0023] Principle of the present disclosure will now be described with reference to some example embodiments. It is to be understood that these embodiments are described only for the purpose of illustration and help those skilled in the art to understand and implement the present disclosure, without suggesting any limitation as to the scope of the disclosure. Embodiments described herein can be implemented in various manners other than the ones described below.

[0024] In the following description and claims, unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skills in the art to which this disclosure belongs.

[0025] References in the present disclosure to “one embodiment,” “an embodiment,” “an example embodiment,” and the like indicate that the embodiment described may include a particular feature, structure, or characteristic, but it is not necessary that every embodiment includes the particular feature, structure, or characteristic. Moreover, such phrases are not necessarily referring to the same embodiment. Further, when a particular feature, structure, or characteristic is described in connection with an embodiment, it is submitted that it is within the knowledge of one skilled in the art to affect such feature, structure, or characteristic in connection with other embodiments whether or not explicitly described.

[0026] It shall be understood that although the terms “first,” “second,”..., etc. in front of noun(s) and the like may be used herein to describe various elements, these elements should not be limited by these terms. These terms are only used to distinguish one element from another and they do not limit the order of the noun(s). For example, a first element could be termed a second element, and similarly, a second element could be termed a first element, without departing from the scope of example embodiments. As used herein, the term “and / or” includes any and all combinations of one or more of the listed terms.

[0027] As used herein, “at least one of the following: ” and “at least one of ” and similar wording, where the list of two or more elements are joined by “and” or “or”, mean at least any one of the elements, or at least any two or more of the elements, or at least all the elements.

[0028] As used herein, unless stated explicitly, performing a step “in response to A” does not indicate that the step is performed immediately after “A” occurs and one or more intervening steps may be included.

[0029] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of example embodiments. As used herein, the singular forms “a”, “an” and “the” are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms “comprises”, “comprising”, “has”, “having”, “includes” and / or “including”, when used herein, specify the presence of stated features, elements, and / or components etc., but do not preclude the presence or addition of one or more other features, elements, components and / or combinations thereof.

[0030] As used in this application, the term “circuitry” may refer to one or more or all of the following:(a) hardware-only circuit implementations (such as implementations in only analogand / or digital circuitry) and(b) combinations of hardware circuits and software, such as (as applicable):(i) a combination of analog and / or digital hardware circuit(s) with software / firmware and(ii) any portions of hardware processor(s) with software (including digital signal processor(s)), software, and memory(ies) that work together to cause an apparatus, such as a mobile phone or server, to perform various functions) and(c) hardware circuit(s) and or processor(s), such as a microprocessor(s) or a portion of a microprocessor(s), that requires software (e.g., firmware) for operation, but the software may not be present when it is not needed for operation.

[0031] This definition of circuitry applies to all uses of this term in this application, including in any claims. As a further example, as used in this application, the term circuitry also covers an implementation of merely a hardware circuit or processor (or multiple processors) or portion of a hardware circuit or processor and its (or their) accompanying software and / or firmware. The term circuitry also covers, for example and if applicable to the particular claim element, a baseband integrated circuit or processor integrated circuit for a mobile device or a similar integrated circuit in server, a cellular network device, or other computing or network device.

[0032] As used herein, the term “communication network” refers to a network following any suitable communication standards, such as New Radio (NR), Long Term Evolution (LTE), LTE- Advanced (LTE-A), Wideband Code Division Multiple Access (WCDMA), High-Speed Packet Access (HSPA), Narrow Band Internet of Things (NB-loT) and so on. Furthermore, the communications between a terminal device and a network device in the communication network may be performed according to any suitable generation communication protocols, including, but not limited to, the first generation (1 G), the second generation (2G), 2.5G, 2.75G, the third generation (3G), the fourth generation (4G), 4.5G, the fifth generation (5G), 5.5G, the sixth generation (6G) communication protocols, and / or any other protocols either currently known or to be developed in the future. Embodiments of the present disclosure may be applied in various communication systems. Given the rapid development in communications, there will of course also be future type communication technologies and systems with which the present disclosure may be embodied. It should not be seen as limiting the scope of the present disclosure to only the aforementioned system.

[0033] As used herein, the term “network device” refers to a node in a communication network via which a terminal device accesses the network and receives services therefrom. The network device may refer to a base station (BS) or an access point (AP), for example, a node B (NodeB or NB), an evolved NodeB (eNodeB or eNB), an NR NB (also referred to as a gNB), a Remote RadioUnit (RRU), a radio header (RH), a remote radio head (RRH), a relay, an Integrated Access and Backhaul (IAB) node, a low power node such as a femto, a pico, a non-terrestrial network (NTN) or non-ground network device such as a satellite network device, a low earth orbit (LEO) satellite and a geosynchronous earth orbit (GEO) satellite, an aircraft network device, and so forth, depending on the applied terminology and technology. In some example embodiments, radio access network (RAN) split architecture comprises a Centralized Unit (CU) and a Distributed Unit (DU) at an IAB donor node. An IAB node comprises a Mobile Terminal (IAB-MT) part that behaves like a UE toward the parent node, and a DU part of an IAB node behaves like a base station toward the next-hop IAB node.

[0034] The term “terminal device” refers to any end device that may be capable of wireless communication. By way of example rather than limitation, a terminal device may also be referred to as a communication device, user equipment (UE), a Subscriber Station (SS), a Portable Subscriber Station, a Mobile Station (MS), or an Access Terminal (AT). The terminal device may include, but not limited to, a mobile phone, a cellular phone, a smart phone, voice over IP (VoIP) phones, wireless local loop phones, a tablet, a wearable terminal device, a personal digital assistant (PDA), portable computers, desktop computer, image capture terminal devices such as digital cameras, gaming terminal devices, music storage and playback appliances, vehicle-mounted wireless terminal devices, wireless endpoints, mobile stations, laptop-embedded equipment (LEE), laptop-mounted equipment (LME), USB dongles, smart devices, wireless customer-premises equipment (CPE), an Internet of Things (loT) device, a watch or other wearable, a head-mounted display (HMD), a vehicle, a drone, a medical device and applications (e.g., remote surgery), an industrial device and applications (e.g., a robot and / or other wireless devices operating in an industrial and / or an automated processing chain contexts), a consumer electronics device, a device operating on commercial and / or industrial wireless networks, and the like. The terminal device may also correspond to a Mobile Termination (MT) part of an IAB node (e.g., a relay node). In the following description, the terms “terminal device”, “communication device”, “terminal”, “user equipment” and “UE” may be used interchangeably.

[0035] A core network function as described herein may be implemented as a core network entity that includes a combination of hardware processing circuit and software and / or firmware comprising machine-readable instructions, or software comprising machine-readable instructions that are executable by at least one processor of hardware processing circuit of an apparatus. A hardware processing circuit includes at least one processor and at least one memory storing machine-readable instructions that are executable by the at least one processor of the hardware processing circuit. A processor includes any or some combination of an accelerator, a microprocessor, a core of a multicore microprocessor, a microcontroller, a programmable integrated circuit, a programmable gate array, a digital signal processor, a central processing unit, a graphic processing unit, a tensor processingunit. Memory includes any or some combination of volatile or non-volatile memory (e.g., a flash memory, cache, a random-access memory (RAM), and / or a read-only memory (ROM)). The memory stores the machine-readable instructions of the software and / or firmware for execution by the at least one processor of the hardware processing circuit. The machine-readable instructions are executable by the at least one processor of the hardware processing circuit cause the hardware processing circuit to perform the actions or operations of the methods described herein. For example, the session management function described herein may be implemented as a session management entity and the session management policy control function described herein may be implemented as a session management policy control entity, respectively.

[0036] As used herein, the term “resource,” “transmission resource,” “resource block,” “physical resource block” (PRB), “uplink resource,” or “downlink resource” may refer to any resource for performing a communication, for example, a communication between a terminal device and a network device, such as a resource in time domain, a resource in frequency domain, a resource in space domain, a resource in code domain, or any other combination of the time, frequency, space and / or code domain resource enabling a communication, and the like. In the following, unless explicitly stated, a resource in both frequency domain and time domain will be used as an example of a transmission resource for describing some example embodiments of the present disclosure. It is noted that example embodiments of the present disclosure are equally applicable to other resources in other domains.

[0037] With the development of communication technologies, AI / ML has been used in various communication environments. For example, augmenting the air-interface with features enabling support of AI / ML-based algorithms may potentially offer enhanced performance e.g., improved throughput, robustness, accuracy or reliability, etc. depending on the use cases as well as reduced complexity / overhead.

[0038] To this end, 3GPP is now actively pursuing AI / ML for Air Interface, for example, investigating and specifying the necessary signaling of necessary measurement enhancements. Use cases such as channel state information (CSI) feedback enhancement, beam management, and positioning accuracy enhancements are considered.

[0039] Particularly, data collection for AI / ML is under investigation. The AI / ML data collection may refer to a process of collecting data by the network nodes, management entity, or UE for the purpose of AI / ML model training, data analytics and inference. In other words, the data collection may provide input data to the Model Training, Management, and Inference functions. For example, the data collection process may collect training data needed as input for the AI / ML Model training function, monitoring data needed as input for the management of AI / ML models or AI / MLfunctionalities, and / or inference data needed as input for the AI / ML inference function.

[0040] Further, aspects regarding the data collection for AI / ML positioning have been identified in 3GPP TR 38.843. The data collection for AI / ML positioning may include collecting a ground-truth label which is reported from the label data generation entity, a measurement (corresponding to model input) which is reported from the measurement data generation entity, and timestamp information at least for and / or associated with collected data. The timestamp information may be reported from the data generation entity together with the collected data and / or as location management function (LMF) assistance signaling. Separate timestamps for the measurement and ground-truth label may be involved when the measurement and ground-truth label are generated by different entities.

[0041] Currently, the LTE positioning protocol (LPP) supports universal time coordinated (UTC) time or NR-TimeStamp that contains a system frame number (SFN) and also a slot and symbol number as timestamps for location information reported from the UE to the LMF (as defined in 3GPP TS 37.355).

[0042] For NR-based positioning, i.e., downlink time difference of arrival (DL-TDOA) and / or downlink angle of departure (DL-AoD), the timestamp for the estimated location can be chosen between SFN-time (NR-TimeStamp) and UTC-time, while non-radio access technology (RAT) based positioning methods use the UTC-time. Further, for RAT-based methods, timestamps for the measurements are expressed via the NR-TimeStamp. Additionally, for measurement reporting from a gNB to the LMF over the NR positioning protocol A (NRPPa), time in seconds relative to 00:00:00 on 1 January 1900 (also referred to as UTC time for convenience) can be optionally reported along with mandatory SFN information as per TS 38.445.

[0043] The SFN information carries the NR-TimeStamp which may include not only the SFN number but also the slot number, and hence it can capture the time resolution in milliseconds (ms). However, since the SFN number ranges from 0 to 1023 in a SFN cycle, and each radio frame has a fixed duration of 10 ms, any data collection and reporting of the collected data beyond 10.24 ms (which may be referred to as “SFN cycle length” in the following) results in SFN ambiguity.

[0044] Usage of UTC time may resolve the time information ambiguity. For example, UTC time in milliseconds may be reported. However, the reporting of UTC time information, in particular at ms-level of precision, increases the signaling overhead. Hence, always reporting UTC time information is not desirable.

[0045] In accordance with some example embodiments of the present disclosure, there is provided a solution for time reporting in AI / ML data collection. In this solution, a first apparatus receives, from a second apparatus, a timestamp configuration associated with AI / ML data collection;determines, based on the timestamp configuration, timestamp information associated with data generated by the first apparatus. The timestamp information comprises UTC time information included based on a condition. The first apparatus further transmits the data and the timestamp information.

[0046] In this way, the UTC time information can be included in the timestamp information associated with AI / ML data based on a condition, rather than being always included in the timestamp information for time reporting. As such, efficient delivery of the timestamp information for AI / ML data collection can be achieved.

[0047] Note that, although some discussions above are related to AI / ML data collection for positioning, the solutions provided according to embodiments of the present disclosure may be applied in other suitable usage scenarios.

[0048] Example embodiments of the present disclosure will be described in detail below with reference to the accompanying drawings.

[0049] FIG. 1 illustrates an example communication environment 100 in which example embodiments of the present disclosure can be implemented. In the communication environment 100, a plurality of communication devices, including a first apparatusl 10 and a second apparatus 120, can communicate with each other.

[0050] In some examples of FIG. 1 , the first apparatus 110 may be or comprised in an AI / ML data generating device, e.g., a UE, or a radio access node (RAN) node. The second apparatus 120 may be or comprised in an AI / ML data receiving device or an AI / ML data collection configuration device, e.g., a core network device. For example, in scenarios of AI / ML data collection for positioning, the first apparatus 110 may be or comprised in a UE or a RAN node, and the second apparatus 120 may be or comprised in the LMF.

[0051] In some other examples of FIG. 1 , the first apparatus 110 may be or comprised in an AI / ML data generating device, e.g., a UE, and the second apparatus 120 may be or comprised in an AI / ML data receiving device, e.g., a RAN node, or vice versa. For example, in use cases in RAN, the AI / ML data generating device may be a UE and the AI / ML data receiving device may be a gNB. In some other examples, the second apparatus 120, when operating as a data receiving device and a data collection configuration device, may also communicate with a further data generating device in addition to the first apparatus 110. The first apparatus 110 may generate measurement data as input to AI / ML models and the further data generating device may generate ground truth labels corresponding to the measurement data, or vice versa.

[0052] It is to be understood that the number of devices and their connections shown in FIG. 1 are only for the purpose of illustration without suggesting any limitation. The communication environment 100 may include any suitable number of devices configured to implementing exampleembodiments of the present disclosure. By way of example rather than limitation, in some example embodiments, the communication environment 100 may further comprise one or more apparatuses (not shown in FIG. 1).

[0053] Communications in the communication environment 100 may be implemented according to any proper communication protocol(s), comprising, but not limited to, cellular communication protocols, wireless local network communication protocols such as Institute for Electrical and Electronics Engineers (IEEE) 802.11 and the like, and / or any other protocols currently known or to be developed in the future. Moreover, the communication may utilize any proper wireless communication technology, comprising but not limited to: Code Division Multiple Access (CDMA), Frequency Division Multiple Access (FDMA), Time Division Multiple Access (TDMA), Frequency Division Duplex (FDD), Time Division Duplex (TDD), Multiple-Input Multiple-Output (MIMO), Orthogonal Frequency Division Multiple (OFDM), Discrete Fourier Transform spread OFDM (DFT-s- OFDM) and / or any other technologies currently known or to be developed in the future.

[0054] Reference is made to FIG. 2. FIG. 2 illustrates a signaling chart 200 for time reporting in AI / ML model data collection according to some example embodiments of the present disclosure. For the purposes of discussion, the signaling chart 200 will be discussed with reference to FIG. 1 , for example, by using the first apparatus 110 and the second apparatus 120, and the first apparatus 110 operates as a data generating device and the second apparatus 120 operates as a data collection configuration device and a data receiving device.

[0055] As illustrated in FIG. 2, the first apparatus 110 receives, from the second apparatus 120, a timestamp configuration 2020 associated with AI / ML data collection. The timestamp configuration may indicate reporting timestamp information corresponding to generated / collected AI / ML data. Additionally, the timestamp configuration may indicate how to determine / include / report time information associated with the generated / collected AI / ML data. In some embodiments, the timestamp configuration may be included in an AI / ML data collection configuration, and the first apparatus 110 may generate the AI / ML data based on the AI / ML data collection configuration.

[0056] Based on the timestamp configuration 2020, the first apparatus 110 determines 2030 timestamp information associated with data generated by the first apparatus 110, and the timestamp information comprises UTC time information included based on a condition. The timestamp information may refer to any suitable time information for time reporting, e.g., timestamps. The UTC time information may refer to UTC time of any suitable format. For example, the UTC time may be in the form of the form of YYMMDDhhmmssZ. In some embodiments, the UTC time information may represent a time instant relative to 00:00:00 on 1 January 1900 as previously defined. In some embodiments, the UTC time information may represent a time instant in seconds or millisecondsdepending on practical use cases.

[0057] The condition for inclusion of the UTC time information in the timestamp information may specify that the UTC time information is to be included or reported in certain cases and only for some, not all of data records in the generated data. In other words, based on the condition, the first apparatus 110 decides whether to include the UTC time information associated with the generated data in the timestamp information for time reporting and may further determine for which data records the UTC time information is to be included. This inclusion of the UTC time information may be also referred to as conditional inclusion of UTC time information for convenience.

[0058] In some embodiments, the condition may be indicated by the timestamp configuration 2020. That is, the data receiving device may indicate the condition to the data generating device, to configure the data generating device to report UTC time information in a specific way. Alternatively or in addition, the condition may be standardized or left to implementation of the first apparatus 110.

[0059] In some embodiments, based on the condition, the first apparatus 110 may, in accordance with a determination that data records in the generated data span for more than one system frame number (SFN) cycle, include the UTC time information associated with the data in the timestamp information. Conversely, the first apparatus 110 may, in accordance with a determination that data records in the data span for less than or equal to one SFN cycle, refrain from including the UTC time information associated with the data in the timestamp information. In other words, the first apparatus 110 may determine whether to include the UTC time information based on a duration of the data records to be reported, i.e., the duration of data generation between the two data reporting time instants (from the last reporting time). If the duration is longer than the SFN cycle length, the first apparatus 110 may determine to include the UTC time information in the timestamp information for time reporting.

[0060] As discussed above, in one SFN cycle, the SFN number ranges from 0 to 1023, thus any data collection and reporting of the collected data beyond 10.24 ms results in SFN ambiguity. Therefore, including the UTC time information only when there is a change in SFN cycle between data records in the data of channel measurements and / or labels can resolve the SFN time information ambiguity with reduced signaling overhead.

[0061] In some embodiments, the first apparatus 110 may include the UTC time information in the timestamp information for time reporting further based on an order of the data records in the generated / collected data. In other words, the first apparatus 110 may arrange the data records of the generated / collected data in a report to the second apparatus 120, e.g., a data collection report. The first apparatus 110 may conditionally include the UTC time information for some of the data recordsin the report based on the order of the data records in the report.

[0062] In some embodiments, the first apparatus 110 may arrange data records in the data in an order indicated by a data arrangement format. The data arrangement format may indicate arranging the data records without a specific order, i.e. , the data records can be arranged in any order and without requiring any arrangement rule / format. Alternatively, data arrangement format may indicate arranging the data records corresponding to a same system frame number (SFN) cycle in a group. In other words, the data records may be arranged in an order where the data records associated with the same SFN cycle are always ordered together. Alternatively, the data arrangement format may indicate arranging the data records in a chronological order or non-decreasing time. In the case where there is a data record for each frame, the data records may be arranged in a strict chronological order.

[0063] In some embodiments, similar to the condition for inclusion of the UTC time information, the data arrangement format may be indicated by the timestamp configuration 2020. That is, the data receiving device may indicate the condition to the data generating device, to configure the data generating device to arrange the data records in the report in a specific way. In some embodiments, the exact data arrangement format to be used by the data generating device may be indicated in the timestamp configuration 2020. In some alternative embodiments, a list of data arrangement formats may be provided in the timestamp configuration. Then, the data generating device may choose a data arrangement format for use and indicate the selected format to the data receiving device. Alternatively, the data arrangement format may be standardized or left to implementation of the first apparatus 110.

[0064] Based on the condition and the data arrangement formation, the first apparatus 110 may include the UTC time information for specific data records in the generated / collected data for time reporting. In some embodiments, each data record may be identified with a record identifier (ID) and then the UTC information may be reported as a table mapping the record ID of the conditionally selected record and the UTC information associated with the selected record.

[0065] In some embodiments, the first apparatus 110 may, in accordance with a determination that the data records in the arranged data are arranged without a specific order, include a UTC time instance associated with a first data record in the timestamp information. The first data record and a previous consecutive data record for the first data record in the arranged data correspond to different SFN cycles.

[0066] In other words, only when there is a change in SFN cycle between two consecutive data records in the data, for example, the data of channel measurements and / or labels, the UTC time information is included in the timestamp information for time reporting. Table 1 captures an example for this case. In this example, one data record in the data collection report contains one data sampleand the time information associated with the data sample.Table 1 : An example of conditional UTC time inclusion

[0067] As can be seen from Table 1 , when the SFN cycle changes between two consecutive data records, a UTC time value is included. For example, when the SFN cycle changes from cycle 1 to cycle 3, a UTC time value for record#4 is included. When the SFN cycle changes from cycle 3 to cycle 1 , a UTC time value for record#? is included, when the SFN cycle changes from cycle 1 to cycle 3 again, a UTC time value for record#8 is included.

[0068] In some example embodiments, the first apparatus may, in accordance with a determination that data records corresponding to a same SFN cycle in the arranged data are arranged in a group, include a UTC time instance associated with a data record of the group in the timestamp information, this data record being a head data record in the group with the same SFN cycle after a SFN cycle change. The first apparatus may further refrain from including a UTC time instance associated with a further data record in the group with the same SFN cycle in the timestamp information.

[0069] In other words, the UTC time information is included only for the first / head record after a SFN cycle change. The first apparatus 110 may include the UTC information once for each SFN cycle (within the data generation period). Table 2 captures an example for this case. In thisexample, one data record in the data collection report contains one data sample and the time information associated with the data sample.Table 2: An example of conditional UTC time inclusion

[0070] As can be seen from Table 2, one UTC time value is included for one SFN cycle, and the one UTC time value corresponds to the first / head data record of the records with the same SFN cycle in the report.

[0071] In some embodiments, the first apparatus 110 may, in accordance with a determination that the data records in the arranged data are in a strict chronological order or nondecreasing time, include a UTC time instance associated with a head data record in the arranged data in the timestamp information; and refrain from including a UTC time instance associated with a further data record in the arranged data in the timestamp information. In other words, if the data records are arranged or ordered strictly in a chronological manner by the data generating node, the data generating node may include the UTC information only once e.g., for the first / head data record in all of the data records in the data collection report.

[0072] In some embodiments, the first apparatus 110 may determine 2030 the timestamp information further based on inclusion of one or more timestamp contents. The one or more timestampcontents may comprise any suitable existing timestamp content, e.g., contents in the NR-TimeStamp. For example, the one or more timestamp contents may comprise at least one of: a system frame number, a subframe number, a slot number, or a symbol number.

[0073] Similar to the condition and / or the data arrangement format, the inclusion of one or more timestamp contents may be indicated by the timestamp configuration 2020. This enables the data generating device to control the tradeoff between reporting / timing granularity vs. signaling overhead depending on requirements for a given AI / ML data collection task. Alternatively, the inclusion of one or more timestamp contents may be standardized or left to implementation of the first apparatus 110.

[0074] Then, the first apparatus 110 transmits 2050, to the second apparatus 120, the generated data and the determined timestamp information. Based on the determined timestamp information, the second apparatus 120 may determine at least one UTC time instance for the data records in the data. For example, the second apparatus 120 may determine the UTC time for each data record in the report to resolve SFN ambiguity.

[0075] Note that, although the above embodiments are described with reference to the first apparatus 110 and the second apparatus 120, the data generating node, the data receiving node, and / or the AI / ML data collection configuration node may be the same or different nodes. In the example of FIG. 2, the data receiving node and the AI / ML data collection configuration node are assumed to be the same node. However, in some other examples, the data receiving node and the data collection configuration node may be different. For example, the timestamp configuration may be transmitted from the second apparatus 120 but a different data receiving apparatus may receive the data and timestamp information from the first apparatus 110.

[0076] Further, the signaling between the first apparatus 110 and the second apparatus 120 may vary depending on practical use cases. In some examples, e.g., for AI / ML-based positioning use case, the LMF (operating as the second apparatus 120) may provide the UE (operating as the first apparatus 110) the timestamp configuration 2020 via an LPP request location information message, LPP assistance data message, or a new message that is introduced for AI / ML data collection purposes.

[0077] Similarly, the LMF may provide the gNB (operating as a further data generating apparatus) the timestamp configuration 2020 via a NRPPa measurement request message or a new message introduced for AI / ML data collection purposes. In some other examples, e.g., use cases in RAN, the timestamp configuration may be provided by the gNB (operating as the data receiving / collection configuration apparatus) to the UE (operating as the data generating apparatus) via a radio resource control (RRC) or media access control (MAC) signaling (e.g., via an RRCReconfiguration message).

[0078] With the solutions as illustrated in FIG. 2, efficient signaling mechanisms are proposed for delivering timestamp information for AI / ML data collection purposes with low signaling overhead while not resulting in any ambiguities and providing high level of timing granularity.

[0079] Reference is now made to FIG. 3. FIG. 3 illustrates a signaling chart 300 for time reporting based on an AI / ML data collection configuration according to some example embodiments of the present disclosure. The signaling chart 300 may be deemed as a detailed example of the signaling chart 200. In FIG. 3, a data generating node 310 (e.g., a UE) and a data receiving node 320 (e.g., an LMF) are involved in the process of time reporting in AI / ML data collection. The data generating node 310 may be an example of the first apparatus 110 in FIG. 1 and the data receiving node 320 may be an example of the second apparatus 120 in FIG. 1. Particularly, as illustrated in FIG. 3, the data receiving node 310 also operates as a data collection configuration node, i.e., configures how to collect / arrange / organ ize the AI / ML data.

[0080] As illustrated in FIG. 3, at Step 1 , the data generating node 310 receives from the data receiving node 320 as well as the data collection configuring node, an AI / ML data collection configuration which includes an AI / ML data time-stamp configuration. The AI / ML data time-stamp configuration may be an example of the timestamp configuration as illustrated in FIG. 2.

[0081] The time-stamp configuration indicates a data arrangement format which configures the UE to arrange data records in the generated data. For example, the data arrangement format may indicate arranging data records in any order (without requiring any ordering rule / format), or a strict chronological order (non-decreasing time), or an order where the data records associated with a SFN cycle are always ordered together.

[0082] The time-stamp configuration further indicates a condition for UTC time information inclusion, which configures the UE to include the UTC time based on the data arrangement format and a duration of data generation between two data reporting time instants (i.e., a duration since the last reporting time). Here, the UE is configured to include the UTC time information only if the data records to be reported span for more than the SFN cycle length, i.e., 10.24 seconds. Additionally, depending on the condition and / or the data arrangement format, the UTC time information for the following data record(s) may be included in the timestamp information for time reporting.

[0083] As an example, in the case of a strict chronological ordering (non-decreasing time) of data, only the first record, i.e., the head data record of all the data records to be reported is reported with the corresponding UTC time. In the case where the data records associated with the same SFN cycle are always ordered together, only the first (head) record after a SFN cycle change is reported with the corresponding UTC time. In the case of ‘any data order’, the corresponding UTC informationis included only when there is a change in SFN cycle between two consecutive data records, e.g., channel measurements and / or labels in the report. The principles are similar to the above discussion with reference to FIG. 2 and details are omitted herein.

[0084] The time-stamp configuration further includes contents of NR-TimeStamp. This configures which of the fields in the NR-TimeStamp information UE should include in its timestamp information associated with the AI / ML data, e.g., the measurement and / or the label. For example, the contents such as the SFN, slot number, symbol number, cell ID, and so on may be indicated to be included in the timestamp information for time reporting.

[0085] At Step 2, the data generating node 310 generates the AI / ML training data (measurement and / or label) as per the received AI / ML data collection configuration. At Step 3, the data generating node 310 arranges the generated data as per the data arrangement format indicated in the time-stamp configuration.

[0086] At Step 4, the data generating node 310 includes the following in the timestamp information as per the time-stamp configuration: NR-TimeStamp information for each record, which may include a SFN, slot number, symbol number., etc. as per the time-stamp configuration; and UTC information for only the selected record as per the condition indicated in the time-stamp config (which in turn depends on the data arrangement format).

[0087] At Step 5, the data generating node 310 sends the AI / ML training data to the data receiving node 320, e.g., LMF, with the associated timestamp information as per the AI / ML data timestamp configuration.

[0088] At Step 6, based on at least the received timestamp information, the data arrangement format and the time span of the data (i.e., if it is longer than 10.24 sec), the data receiving node 320, e.g., LMF, determines the UTC time for each record to resolve SFN ambiguity. The determination of the UTC time for a data record may be based on simple offsetting of the reported UTC time of the conditionally selected record using the relative time (time difference) between the data record and the conditionally selected record. The relative time difference may be computed using the SFN information.

[0089] At Step 7, the data receiving node 320, e.g., LMF, uses the collected data for AI / ML training purposes. Note that, the time information is particularly useful for mapping the measurement and the corresponding label when the measurement and the label for the training data are generated by two different data generating nodes. So, at the beginning of the Step 7, the LMF may create the training data set by putting together the measurement and the label that share the same timestamp.

[0090] As illustrated in FIG. 2 and FIG. 3, the solutions according to the example embodiments of the present disclosure allow to report time information for the AI / ML training data(measurement and / or label) for AI / ML positioning in an unambiguous and resource efficient manner (i.e., with reduced signaling overhead). Further, it enables controlling the tradeoff between reporting / timing granularity (e.g., from system frame-level to symbol-level) vs. signaling overhead depending on requirements for a given AI / ML data collection task.

[0091] FIG. 4 shows a flowchart of an example method 400 implemented at a first apparatus in accordance with some example embodiments of the present disclosure. For the purpose of discussion, the method 400 will be described from the perspective of the first apparatus 110 in FIG. 1.

[0092] At block 410, the first apparatus 110 receives, from the second apparatus 120, a timestamp configuration associated with artificial intelligence / machine learning (AI / ML) data collection.

[0093] At block 420, the first apparatus 110 determines, based on the timestamp configuration, timestamp information associated with data generated by the first apparatus, wherein the timestamp information comprises Universal Time Coordinated (UTC) time information included based on a condition.

[0094] At block 430, the first apparatus 110 transmits the data and the timestamp information.

[0095] In some example embodiments, the method 400 further comprises: in accordance with a determination that data records in the data span for more than one system frame number (SFN) cycle, including the UTC time information associated with the data in the timestamp information; and in accordance with a determination that data records in the data span for less than or equal to one SFN cycle, refraining from including the UTC time information associated with the data in the timestamp information.

[0096] In some example embodiments, the timestamp configuration indicates the condition, and the first apparatus is caused to determine the timestamp information by: determine the timestamp information by including the UTC time information in the timestamp information based on the condition.

[0097] In some example embodiments, the method 400 further comprises: arranging data records in the data in an order indicated by a data arrangement format, wherein the data arrangement format indicates one of the following: arranging the data records without a specific order, arranging the data records corresponding to a same system frame number (SFN) cycle in a group, or arranging the data records in a chronological order or non-decreasing time.

[0098] In some example embodiments, the first apparatus is caused to include the UTC time information associated with the data in the timestamp information further based on the order of the data records in the arranged data.

[0099] In some example embodiments, the first apparatus is caused to include the UTCtime information associated with the data by: in accordance with a determination that the data records in the arranged data are arranged without a specific order, including a UTC time instance associated with a first data record in the timestamp information, the first data record and a previous consecutive data record for the first data record in the arranged data corresponding to different SFN cycles.

[0100] In some example embodiments, the first apparatus is caused to include the UTC time information associated with the data by: in accordance with a determination that data records corresponding to a same SFN cycle in the arranged data are arranged in a group, including a UTC time instance associated with a second data record of the group in the timestamp information, the second data record being a head data record in the group with the same SFN cycle after a SFN cycle change; and refraining from including a UTC time instance associated with a further data record in the group with the same SFN cycle in the timestamp information.

[0101] In some example embodiments, the first apparatus is caused to include the UTC time information associated with the data by: in accordance with a determination that the data records in the arranged data are in a strict chronological order or non-decreasing time, including a UTC time instance associated with a head data record in the arranged data in the timestamp information; and refraining from including a UTC time instance associated with a further data record in the arranged data in the timestamp information.

[0102] In some example embodiments, the timestamp configuration indicates the data arrangement format.

[0103] In some example embodiments, the method 400 further comprises: determining the timestamp information further based on the inclusion of one or more timestamp contents. In some example embodiments, the one or more timestamp contents comprise at least one of: a system frame number, a subframe number, a slot number, or a symbol number.

[0104] In some example embodiments, the first apparatus is caused to receive the timestamp configuration by receiving an AI / ML data collection configuration including the timestamp configuration, and the first apparatus is caused to generate the AI / ML data based on the AI / ML data collection configuration.

[0105] In some example embodiments, the first apparatus is or comprised in a terminal device or a network device, and the second apparatus is or comprised in a core network device.

[0106] FIG. 5 shows a flowchart of an example method 500 implemented at a second apparatus in accordance with some example embodiments of the present disclosure. For the purpose of discussion, the method 500 will be described from the perspective of the second apparatus 120 in FIG. 1.

[0107] At block 510, the second apparatus 120 transmits, to the first apparatus 110, atimestamp configuration associated with artificial intelligence / machine learning (AI / ML) data collection.

[0108] At block 520, the second apparatus 120 receives, from the first apparatus 110, data generated by the first apparatus and timestamp information associated with the data, wherein the timestamp information is determined by the first apparatus based on the timestamp configuration, and the timestamp information comprises Universal Time Coordinated (UTC) time information included by the first apparatus based on a condition.

[0109] In some example embodiments, the timestamp configuration indicates the condition for inclusion of UTC time information associated with the data in the timestamp information.

[0110] In some example embodiments, the condition for inclusion of UTC time information indicates: in accordance with a determination that data records in the data span for more than one SFN cycle, including UTC time information associated with the data in the timestamp information; and in accordance with a determination that data records in the data span for less than or equal to one SFN cycle, refraining from including UTC time information associated with the data in the timestamp information.

[0111] In some example embodiments, the timestamp configuration indicates a data arrangement format configured for arranging data records in the data in an order indicated by the data arrangement format.

[0112] In some example embodiments, the data arrangement format indicates one of the following: arranging the data records in the data without a specific order, arranging data records corresponding to a same system frame number (SFN) cycle in the data in a group, or arranging the data records in the data in a chronological order or non-decreasing time.

[0113] In some example embodiments, the timestamp configuration indicates including the UTC time information associated with the data in the timestamp information based on the order of data records in the arranged data.

[0114] In some example embodiments, including the UTC time information associated with the data in the timestamp information comprises: in accordance with a determination that the data records in the arranged data are arranged without a specific order, including a UTC time instance associated with a first data record in the timestamp information, the first data record and a previous consecutive data record for the first data record in the arranged data corresponding to different SFN cycles.

[0115] In some example embodiments, including the UTC time information associated with the data in the timestamp information comprises: in accordance with a determination that data records corresponding to a same SFN cycle in the arranged data are arranged in a group, including a UTC time instance associated with a second data record of the group in the timestamp information, thesecond data record being a head data record in the group with the same SFN cycle after a SFN cycle change; and refraining from including a UTC time instance associated with a further data record in the group with the same SFN cycle in the timestamp information.

[0116] In some example embodiments, including the UTC time information associated with the data in the timestamp information comprises: in accordance with a determination that the data records in the arranged data are in a strict chronological order or non-decreasing time, including a UTC time instance associated with a head data record in the arranged data in the timestamp information; and refraining from including a UTC time instance associated with a further data record in the arranged data in the timestamp information.

[0117] In some example embodiments, the timestamp configuration indicates an inclusion of one or more timestamp contents associated with the data in the timestamp information. In some example embodiments, the one or more timestamp contents comprise at least one of: a system frame number, a subframe number, a slot number, or a symbol number.

[0118] In some example embodiments, the method 500 further comprises: determining at least one UTC time instance for data records in the data based on the timestamp information.

[0119] In some example embodiments, the second apparatus is caused to transmit the timestamp configuration by transmitting an AI / ML data collection configuration including the timestamp configuration.

[0120] In some example embodiments, the first apparatus is or comprised in a terminal device or a network device, and the second apparatus is or comprised in a core network device.

[0121] In some example embodiments, a first apparatus capable of performing any of the method 400 (for example, the first apparatus 110 in FIG. 1 may comprise means for performing the respective operations of the method 400. The means may be implemented in any suitable form. For example, the means may be implemented in a circuitry or software module. The first apparatus may be implemented as or included in the first apparatus 110 in FIG. 1 .

[0122] In some example embodiments, the first apparatus comprises means for receiving, from a second apparatus, a timestamp configuration associated with artificial intelligence / machine learning (AI / ML) data collection; means for determining, based on the timestamp configuration, timestamp information associated with data generated by the first apparatus, wherein the timestamp information comprises Universal Time Coordinated (UTC) time information included based on a condition; and means for transmitting the data and the timestamp information.

[0123] In some example embodiments, the first apparatus further comprises: means for in accordance with a determination that data records in the data span for more than one system frame number (SFN) cycle, including the UTC time information associated with the data in the timestampinformation; and means for in accordance with a determination that data records in the data span for less than or equal to one SFN cycle, refraining from including the UTC time information associated with the data in the timestamp information.

[0124] In some example embodiments, the timestamp configuration indicates the condition, and the means for determining the timestamp information may comprise means for determining the timestamp information by including the UTC time information in the timestamp information based on the condition.

[0125] In some example embodiments, the first apparatus further comprises: means for arranging data records in the data in an order indicated by a data arrangement format, wherein the data arrangement format indicates one of the following: arranging the data records without a specific order, arranging the data records corresponding to a same system frame number (SFN) cycle in a group, or arranging the data records in a chronological order or non-decreasing time.

[0126] In some example embodiments, the means for including the UTC time information associated with the data in the timestamp information comprises means for including the UTC time information associated with the data in the timestamp information further based on the order of the data records in the arranged data.

[0127] In some example embodiments, the means for including the UTC time information associated with the data may comprise means for: in accordance with a determination that the data records in the arranged data are arranged without a specific order, including a UTC time instance associated with a first data record in the timestamp information, the first data record and a previous consecutive data record for the first data record in the arranged data corresponding to different SFN cycles.

[0128] In some example embodiments, the means for including the UTC time information associated with the data may comprise means for: in accordance with a determination that data records corresponding to a same SFN cycle in the arranged data are arranged in a group, including a UTC time instance associated with a second data record of the group in the timestamp information, the second data record being a head data record in the group with the same SFN cycle after a SFN cycle change; and refraining from including a UTC time instance associated with a further data record in the group with the same SFN cycle in the timestamp information.

[0129] In some example embodiments, the means for including the UTC time information associated with the data may comprise means for: in accordance with a determination that the data records in the arranged data are in a strict chronological order or non-decreasing time, including a UTC time instance associated with a head data record in the arranged data in the timestamp information; and refraining from including a UTC time instance associated with a further data recordin the arranged data in the timestamp information.

[0130] In some example embodiments, the timestamp configuration indicates the data arrangement format.

[0131] In some example embodiments, the first apparatus further comprises: means for determining the timestamp information further based on the inclusion of one or more timestamp contents. In some example embodiments, the one or more timestamp contents comprise at least one of: a system frame number, a subframe number, a slot number, or a symbol number.

[0132] In some example embodiments, the means for receiving the timestamp configuration may comprise means for receiving an AI / ML data collection configuration including the timestamp configuration, and the first apparatus may further comprise means for generating the AI / ML data based on the AI / ML data collection configuration.

[0133] In some example embodiments, the first apparatus is or comprised in a terminal device or a network device, and the second apparatus is or comprised in a core network device.

[0134] In some example embodiments, a second apparatus capable of performing any of the method 500 (for example, the second apparatus 120 in FIG. 1 may comprise means for performing the respective operations of the method 500. The means may be implemented in any suitable form. For example, the means may be implemented in a circuitry or software module. The second apparatus may be implemented as or included in the second apparatus 120 in FIG. 1.

[0135] In some example embodiments, the second apparatus comprises means for transmitting, to a first apparatus, a timestamp configuration associated with artificial i ntelligence / mach ine learning (AI / ML) data collection; and means for receiving, from the first apparatus, data generated by the first apparatus and timestamp information associated with the data, wherein the timestamp information is determined by the first apparatus based on the timestamp configuration, and the timestamp information comprises Universal Time Coordinated (UTC) time information included by the first apparatus based on a condition.

[0136] In some example embodiments, the timestamp configuration indicates the condition for inclusion of UTC time information associated with the data in the timestamp information.

[0137] In some example embodiments, the condition for inclusion of UTC time information indicates: in accordance with a determination that data records in the data span for more than one SFN cycle, including UTC time information associated with the data in the timestamp information; and in accordance with a determination that data records in the data span for less than or equal to one SFN cycle, refraining from including UTC time information associated with the data in the timestamp information.

[0138] In some example embodiments, the timestamp configuration indicates a dataarrangement format configured for arranging data records in the data in an order indicated by the data arrangement format.

[0139] In some example embodiments, the data arrangement format indicates one of the following: arranging the data records in the data without a specific order, arranging data records corresponding to a same system frame number (SFN) cycle in the data in a group, or arranging the data records in the data in a chronological order or non-decreasing time.

[0140] In some example embodiments, the timestamp configuration indicates including the UTC time information associated with the data in the timestamp information based on the order of data records in the arranged data.

[0141] In some example embodiments, including the UTC time information associated with the data in the timestamp information comprises: in accordance with a determination that the data records in the arranged data are arranged without a specific order, including a UTC time instance associated with a first data record in the timestamp information, the first data record and a previous consecutive data record for the first data record in the arranged data corresponding to different SFN cycles.

[0142] In some example embodiments, including the UTC time information associated with the data in the timestamp information comprises: in accordance with a determination that data records corresponding to a same SFN cycle in the arranged data are arranged in a group, including a UTC time instance associated with a second data record of the group in the timestamp information, the second data record being a head data record in the group with the same SFN cycle after a SFN cycle change; and refraining from including a UTC time instance associated with a further data record in the group with the same SFN cycle in the timestamp information.

[0143] In some example embodiments, including the UTC time information associated with the data in the timestamp information comprises: in accordance with a determination that the data records in the arranged data are in a strict chronological order or non-decreasing time, including a UTC time instance associated with a head data record in the arranged data in the timestamp information; and refraining from including a UTC time instance associated with a further data record in the arranged data in the timestamp information.

[0144] In some example embodiments, the timestamp configuration indicates an inclusion of one or more timestamp contents associated with the data in the timestamp information. In some example embodiments, the one or more timestamp contents comprise at least one of: a system frame number, a subframe number, a slot number, or a symbol number.

[0145] In some example embodiments, the second apparatus further comprises: means for determining at least one UTC time instance for data records in the data based on the timestampinformation.

[0146] In some example embodiments, the means for transmitting the timestamp configuration may comprise means for transmitting an AI / ML data collection configuration including the timestamp configuration.

[0147] In some example embodiments, the first apparatus is or comprised in a terminal device or a network device, and the second apparatus is or comprised in a core network device.

[0148] FIG. 6 is a simplified block diagram of a device 600 that is suitable for implementing example embodiments of the present disclosure. The device 600 may be provided to implement a communication device, for example, the first apparatus 110 or the second apparatus 120 as shown in FIG. 1. As shown, the device 600 includes one or more processors 610, one or more memories 620 coupled to the processor 610, and one or more communication modules 640 coupled to the processor 610.

[0149] The communication module 640 is for bidirectional communications. The communication module 640 has one or more communication interfaces to facilitate communication with one or more other modules or devices. The communication interfaces may represent any interface that is necessary for communication with other network elements. In some example embodiments, the communication module 640 may include at least one antenna.

[0150] The processor 610 may be of any type suitable to the local technical network and may include one or more of the following: general purpose computers, special purpose computers, microprocessors, digital signal processors (DSPs) and processors based on multicore processor architecture, as non-limiting examples. The device 600 may have multiple processors, such as an application specific integrated circuit chip that is slaved in time to a clock which synchronizes the main processor.

[0151] The memory 620 may include one or more non-volatile memories and one or more volatile memories. Examples of the non-volatile memories include, but are not limited to, a Read Only Memory (ROM) 624, an electrically programmable read only memory (EPROM), a flash memory, a hard disk, a compact disc (CD), a digital video disk (DVD), an optical disk, a laser disk, and other magnetic storage and / or optical storage. Examples of the volatile memories include, but are not limited to, a random-access memory (RAM) 622 and other volatile memories that will not last in the powerdown duration.

[0152] A computer program 630 includes computer executable instructions that are executed by the associated processor 610. The instructions of the program 630 may include instructions for performing operations / acts of some example embodiments of the present disclosure. The program 630 may be stored in the memory, e.g., the ROM 624. The processor 610 may performany suitable actions and processing by loading the program 630 into the RAM 622.

[0153] The example embodiments of the present disclosure may be implemented by means of the program 630 so that the device 600 may perform any process of the disclosure as discussed with reference to FIG. 2 to FIG.5. The example embodiments of the present disclosure may also be implemented by hardware or by a combination of software and hardware.

[0154] In some example embodiments, the program 630 may be tangibly contained in a computer readable medium which may be included in the device 600 (such as in the memory 620) or other storage devices that are accessible by the device 600. The device 600 may load the program 630 from the computer readable medium to the RAM 622 for execution. In some example embodiments, the computer readable medium may include any types of non-transitory storage medium, such as ROM, EPROM, a flash memory, a hard disk, CD, DVD, and the like. The term “non-transitory,” as used herein, is a limitation of the medium itself (i.e. , tangible, not a signal) as opposed to a limitation on data storage persistency (e.g., RAM vs. ROM).

[0155] FIG. 7 shows an example of the computer readable medium 700 which may be in form of CD, DVD or other optical storage disk. The computer readable medium 700 has the program 630 stored thereon.

[0156] Generally, various embodiments of the present disclosure may be implemented in hardware or special purpose circuits, software, logic or any combination thereof. Some aspects may be implemented in hardware, and other aspects may be implemented in firmware or software which may be executed by a controller, microprocessor or other computing device. Although various aspects of embodiments of the present disclosure are illustrated and described as block diagrams, flowcharts, or using some other pictorial representations, it is to be understood that the block, apparatus, system, technique or method described herein may be implemented in, as non-limiting examples, hardware, software, firmware, special purpose circuits or logic, general purpose hardware or controller or other computing devices, or some combination thereof.

[0157] Some example embodiments of the present disclosure also provide at least one computer program product tangibly stored on a computer readable medium, such as a non-transitory computer readable medium. The computer program product includes computer-executable instructions, such as those included in program modules, being executed in a device on a target physical or virtual processor, to carry out any of the methods as described above. Generally, program modules include routines, programs, libraries, objects, classes, components, data structures, or the like that perform particular tasks or implement particular abstract data types. The functionality of the program modules may be combined or split between program modules as desired in various embodiments. Machine-executable instructions for program modules may be executed within a localor distributed device. In a distributed device, program modules may be located in both local and remote storage media.

[0158] Program code for carrying out methods of the present disclosure may be written in any combination of one or more programming languages. The program code may be provided to a processor or controller of a general-purpose computer, special purpose computer, or other programmable data processing apparatus, such that the program code, when executed by the processor or controller, cause the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code may execute entirely on a machine, partly on the machine, as a stand-alone software package, partly on the machine and partly on a remote machine or entirely on the remote machine or server.

[0159] In the context of the present disclosure, the computer program code or related data may be carried by any suitable carrier to enable the device, apparatus or processor to perform various processes and operations as described above. Examples of the carrier include a signal, computer readable medium, and the like.

[0160] The computer readable medium may be a computer readable signal medium or a computer readable storage medium. A computer readable medium may include but not limited to an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of the computer readable storage medium would include an electrical connection having one or more wires, a portable computer diskette, a hard disk, a random-access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0161] Further, although operations are depicted in a particular order, this should not be understood as requiring that such operations be performed in the particular order shown or in sequential order, or that all illustrated operations be performed, to achieve desirable results. In certain circumstances, multitasking and parallel processing may be advantageous. Likewise, although several specific implementation details are contained in the above discussions, these should not be construed as limitations on the scope of the present disclosure, but rather as descriptions of features that may be specific to particular embodiments. Unless explicitly stated, certain features that are described in the context of separate embodiments may also be implemented in combination in a single embodiment. Conversely, unless explicitly stated, various features that are described in the context of a single embodiment may also be implemented in a plurality of embodiments separately or in any suitable subcombination.

[0162] Although the present disclosure has been described in languages specific to structural features and / or methodological acts, it is to be understood that the present disclosure defined in the appended claims is not necessarily limited to the specific features or acts described above. Rather, the specific features and acts described above are disclosed as example forms of implementing the claims.

Claims

WHAT IS CLAIMED IS:1 . A first apparatus comprising: at least one processor; and at least one memory storing instructions that, when executed by the at least one processor, cause the first apparatus at least to: receive, from a second apparatus, a timestamp configuration associated with artificial intelligence / machine learning (AI / ML) data collection; determine, based on the timestamp configuration, timestamp information associated with data generated by the first apparatus, wherein the timestamp information comprises Universal Time Coordinated (UTC) time information included based on a condition; and transmit the data and the timestamp information.

2. The first apparatus of claim 1 , wherein the first apparatus is caused to: in accordance with a determination that data records in the data span for more than one system frame number (SFN) cycle, including the UTC time information associated with the data in the timestamp information; and in accordance with a determination that data records in the data span for less than or equal to one SFN cycle, refraining from including the UTC time information associated with the data in the timestamp information.

3. The first apparatus of any of claims 1 to 2, wherein the timestamp configuration indicates the condition, and the first apparatus is caused to determine the timestamp information by: determine the timestamp information by including the UTC time information in the timestamp information based on the condition.

4. The first apparatus of any of claims 1 to 3, wherein the first apparatus is further caused to: arrange data records in the data in an order indicated by a data arrangement format, wherein the data arrangement format indicates one of the following: arranging the data records without a specific order, arranging the data records corresponding to a same system frame number (SFN) cycle in a group, or arranging the data records in a chronological order or non-decreasing time.

5. The first apparatus of claim 4, wherein the first apparatus is caused to include the UTC time information associated with the data in the timestamp information further based on the order of the data records in the arranged data.

6. The first apparatus of claim 5, wherein the first apparatus is caused to include the UTC time information associated with the data by: in accordance with a determination that the data records in the arranged data are arranged without a specific order, including a UTC time instance associated with a first data record in the timestamp information, the first data record and a previous consecutive data record for the first data record in the arranged data corresponding to different SFN cycles.

7. The first apparatus of claim 5, wherein the first apparatus is caused to include the UTC time information associated with the data by: in accordance with a determination that data records corresponding to a same SFN cycle in the arranged data are arranged in a group, including a UTC time instance associated with a second data record of the group in the timestamp information, the second data record being a head data record in the group with the same SFN cycle after a SFN cycle change; and refraining from including a UTC time instance associated with a further data record in the group with the same SFN cycle in the timestamp information.

8. The first apparatus of claim 5, wherein the first apparatus is caused to include the UTC time information associated with the data by: in accordance with a determination that the data records in the arranged data are in a strict chronological order or non-decreasing time, including a UTC time instance associated with a head data record in the arranged data in the timestamp information; and refraining from including a UTC time instance associated with a further data record in the arranged data in the timestamp information.

9. The first apparatus of any of claims 4 to 8, wherein the timestamp configuration indicates the data arrangement format.

10. The first apparatus of any of claims 1 to 9, wherein the timestamp configuration indicates an inclusion of one or more timestamp contents, and the first apparatus is caused to: determine the timestamp information further based on the inclusion of one or more timestamp contents.11 . The first apparatus of claim 10, wherein the one or more timestamp contents comprise at least one of: a system frame number, a subframe number, a slot number, or a symbol number.

12. The first apparatus of any of claims 1 to 11 , wherein the first apparatus is caused to receive the timestamp configuration by receiving an AI / ML data collection configuration including the timestamp configuration, and the first apparatus is caused to generate the AI / ML data based on the AI / ML data collection configuration.

13. The first apparatus of claim 12, wherein the first apparatus is or comprised in a terminal device or a network device, and the second apparatus is or comprised in a core network device.

14. A second apparatus comprising: at least one processor; and at least one memory storing instructions that, when executed by the at least one processor, cause the second apparatus at least to: transmit, to a first apparatus, a timestamp configuration associated with artificial intelligence / machine learning (AI / ML) data collection; and receive, from the first apparatus, data generated by the first apparatus and timestamp information associated with the data, wherein the timestamp information is determined by the first apparatus based on the timestamp configuration, and the timestamp information comprises Universal Time Coordinated (UTC) time information included by the first apparatus based on a condition.

15. The second apparatus of claim 14, wherein the timestamp configuration indicates the condition for inclusion of UTC time information associated with the data in the timestamp information.

16. The second apparatus of claim 15, wherein the condition for inclusion of UTC time information indicates: in accordance with a determination that data records in the data span for more than one SFN cycle, including UTC time information associated with the data in the timestamp information; and in accordance with a determination that data records in the data span for less than or equal to one SFN cycle, refraining from including UTC time information associated with the data in the timestamp information.

17. The second apparatus of any of claims 14 to 16, wherein the timestamp configuration indicates a data arrangement format configured for arranging data records in the data in an order indicated by the data arrangement format.

18. The second apparatus of claim 17, wherein the data arrangement format indicates one of the following: arranging the data records in the data without a specific order, arranging data records corresponding to a same system frame number (SFN) cycle in the data in a group, or arranging the data records in the data in a chronological order or non-decreasing time.

19. The second apparatus of claim 18, wherein the timestamp configuration indicates including the UTC time information associated with the data in the timestamp information based on the order of data records in the arranged data.

20. The second apparatus of claim 19, wherein including the UTC time information associated with the data in the timestamp information comprises: in accordance with a determination that the data records in the arranged data are arranged without a specific order, including a UTC time instance associated with a first data record in the timestamp information, the first data record and a previous consecutive data record for the first data record in the arranged data corresponding to different SFN cycles.21 . The second apparatus of claim 20, wherein including the UTC time information associated with the data in the timestamp information comprises: in accordance with a determination that data records corresponding to a same SFN cycle in the arranged data are arranged in a group,including a UTC time instance associated with a second data record of the group in the timestamp information, the second data record being a head data record in the group with the same SFN cycle after a SFN cycle change; and refraining from including a UTC time instance associated with a further data record in the group with the same SFN cycle in the timestamp information.

22. The second apparatus of claim 20, wherein including the UTC time information associated with the data in the timestamp information comprises: in accordance with a determination that the data records in the arranged data are in a strict chronological order or non-decreasing time, including a UTC time instance associated with a head data record in the arranged data in the timestamp information; and refraining from including a UTC time instance associated with a further data record in the arranged data in the timestamp information.

23. The second apparatus of any of claims 14 to 22, wherein the timestamp configuration indicates an inclusion of one or more timestamp contents associated with the data in the timestamp information.

24. The second apparatus of claim 23, wherein the one or more timestamp contents comprise at least one of: a system frame number, a subframe number, a slot number, or a symbol number.

25. The second apparatus of any of claims 14 to 24, wherein the second apparatus is further caused to: determine at least one UTC time instance for data records in the data based on the timestamp information.

26. The second apparatus of any of claims 14 to 25, wherein the second apparatus is caused to transmit the timestamp configuration by transmitting an AI / ML data collection configuration including the timestamp configuration.

27. The second apparatus of any of claims 14 to 26, wherein the first apparatus is or comprised in a terminal device or a network device, and the second apparatus is or comprised in a core network device.

28. A method comprising: receiving, at a first apparatus and from a second apparatus, a timestamp configuration associated with artificial intelligence / machine learning (AI / ML) data collection; determining, based on the timestamp configuration, timestamp information associated with data generated by the first apparatus, wherein the timestamp information comprises Universal Time Coordinated (UTC) time information included based on a condition; and transmitting the data and the timestamp information.

29. A method comprising: transmitting, from a second apparatus and to a first apparatus, a timestamp configuration associated with artificial intelligence / machine learning (AI / ML) data collection; and receiving, from the first apparatus, data generated by the first apparatus and timestamp information associated with the data, wherein the timestamp information is determined by the first apparatus based on the timestamp configuration, and the timestamp information comprises Universal Time Coordinated (UTC) time information included by the first apparatus based on a condition.

Images