Network assistance for odprs requests for ai / ML positioning data collection

Abstract

Described herein is a User Equipment, UE, comprising: at least one processor, and at least one memory storing instructions that, when executed by the at least one processor, cause the UE at least to: receive, from a network node, reference signal assistance information indicating one or more preferred reference signal configurations, wherein the reference signal assistance information comprises at least one of time-based configuration information or area-based configuration information; and send, to the network node, a reference signal request for artificial intelligence / machine learning, AI / ML, data collection based on the received reference signal assistance information.

Description

NETWORK ASSISTANCE FOR ODPRS REQUESTS FOR AI / ML POSITIONING DATA COLLECTIONTECHNOLOGY

[0001] The present disclosure relates to AI / ML model data collection in a network , in particular to AI / ML model data collection by a user equipment (UE) with assistance from the network.BACKGROUND

[0002] Any discussion of the background art throughout the specification should in no way be considered as an admission that such art is widely known or forms part of common general knowledge in the field.

[0003] With Artificial Intelligence / Machine Learning, AI / ML models being applied to both UE side and Network (NW) side, signalling / mechanism(s) are necessary so as to facilitate model training, inference, performance monitoring, data collection for both UE-sided and NW-sided AI / ML models.

[0004] Therein, data collection relates 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. The data may include: 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 / ML functionalities, and inference data needed as input for the AI / ML inference function.

[0005] In order to collect AI / ML data, UE may send a request to NW, requesting for a reference signal with which UE can perform related measurements to be used for AI / ML models.

[0006] However, requests coming from different UEs may not be accepted by the network, e.g., when the network cannot satisfy the request(s) due to e.g., over-demanding requests from the different UEs, a large number of requests, or load conditions in the network and etc.

[0007] Consequently, rejected requests result in wastage of UL resources since such requests from the UE are ignored by the network, creation of uncertainties in AI / ML operation (e.g. training, monitoring, inference) from the UE perspective, for which the use of requested reference signal transmission is intended, as it potentially interrupts or delays the respective AI / ML operation.

[0008] Hence, there is a need to provide more efficient mechanisms for handling requests from UE for AI / ML data collection so as to avoid UL resource wastage and to improve reliability (or availability) of AI / ML operations.SUMMARY

[0009] In accordance with a first aspect of the present disclosure, there is provided a User Equipment, UE, comprising:at least one processor, andat least one memory storing instructions that, when executed by the at least one processor, cause the UE at least to:receive, from a network node, reference signal assistance information indicating one or more preferred reference signal configurations, wherein the reference signal assistance information comprises at least one of time-based configuration information or areabased configuration information; andsend, to the network node, a reference signal request for artificial intelligence / machine learning, AI / ML, data collection based on the received reference signal assistance information.

[0010] In accordance with a second aspect of the present disclosure, there is provided a network node, comprising:at least one processor, andat least one memory storing instructions that, when executed by the at least one processor, cause the network node at least to:determine reference signal assistance information for indicating one or more preferred reference signal configurations, wherein the reference signal assistance information comprises at least one of time-based configuration information or area-based configuration information;send, to a user equipment, UE, the determined reference signal assistance information; andreceive, from the UE, a reference signal request for artificial intelligence / machine learning, AI / ML, data collection.

[0011] In accordance with a third aspect of the present disclosure, there is provided a method of a User Equipment, UE, the method comprising:receiving, from a network node, reference signal assistance information indicating one or more preferred reference signal configurations, wherein the reference signalassistance information comprises at least one of time-based configuration information or area-based configuration information; andsending, to the network node, a reference signal request for artificial intelligence / machine learning, AI / ML, data collection based on the received reference signal assistance information.

[0012] In accordance with a fourth aspect of the present disclosure, there is provided a method of a network node, the method comprising:determining reference signal assistance information for indicating one or more preferred reference signal configurations, wherein the reference signal assistance information comprises at least one of time-based configuration information or areabased configuration information;sending, to a user equipment, UE, the determined reference signal assistance information; andreceiving, from the UE, a reference signal request for artificial intelligence / machine learning, AI / ML, data collection.

[0013] In accordance with a fifth aspect of the present disclosure, there is provided a computer program comprising instructions for causing an apparatus to perform the method according to the third aspect, or for causing an apparatus to perform the method according to the fourth aspect.

[0014] In accordance with a sixth aspect of the present disclosure, there is provided a memory storing computer readable instructions for causing an apparatus to perform the method according to the third aspect, or for causing an apparatus to perform the method according to the fourth aspect.

[0015] In addition, according to some other example embodiments, there is provided, for example, a computer program product for a wireless communication device comprising at least one processor, including software code portions for performing the respective steps disclosed in the present disclosure, when said product is run on the device. The computer program product may include a computer-readable medium on which said software code portions are stored. Furthermore, the computer program product may be directly loadable into the internal memory of the computer and / or transmittable via a network by means of at least one of upload, download and push procedures.

[0016] While some example embodiments will be described herein with particular reference to the above application, it will be appreciated that the present disclosure is not limited to such a field of use, and is applicable in broader contexts.

[0017] Notably, it is understood that methods according to the present disclosure relate to methods of operating the apparatuses according to the above example embodiments and variations thereof, and that respective statements made with regard to the apparatuses likewise apply to the corresponding methods, and vice versa, such that similar description may be omitted for the sake of conciseness. In addition, the above aspects may be combined in many ways, even if not explicitly disclosed. The skilled person will understand that these combinations of aspects and features / steps are possible unless it creates a contradiction which is explicitly excluded.

[0018] Implementations of the disclosed apparatuses may include using, but not limited to, one or more processor, one or more application specific integrated circuit (ASIC) and / or one or more field programmable gate array (FPGA). Implementations of the apparatus may also include using other conventional and / or customized hardware such as software programmable processors, such as graphics processing unit (GPU) processors.

[0019] Other and further example embodiments of the present disclosure will become apparent during the course of the following discussion and by reference to the accompanying drawings.BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Example embodiments of the disclosure will now be described, by way of example only, with reference to the accompanying drawings in which:

[0021] Figure 1 schematically illustrates an example of a method for AI / ML data collection based on NW assistance according to an example embodiment of the present disclosure;

[0022] Figure 2 schematically illustrates another example of a method for AI / ML data collection based on NW assistance according to an example embodiment of the present disclosure;

[0023] Figure 3 schematically illustrates another example of a method for AI / ML data collection based on NW assistance according to an example embodiment of the present disclosure; and

[0024] Figure 4 illustrates a block diagram of an apparatus, according to an example embodiment of the present disclosure.DESCRIPTION OF EXAMPLE EMBODIMENTS

[0025] In the following, different exemplifying embodiments will be described using, as an example of a communication network to which examples of embodiments may be applied, acommunication network architecture based on 3 GPP standards for a communication network, such as a 5G / NR, without restricting the embodiments to such an architecture, however. It is apparent for a person skilled in the art that the embodiments may also be applied to other kinds of communication networks where mobile communication principles are integrated with a D2D (device-to-device) or V2X (vehicle to everything) configuration, such as SL (side link), e.g. Wi-Fi, worldwide interoperability for microwave access (WiMAX), Bluetooth®, personal communications services (PCS), ZigBee®, wideband code division multiple access (WCDMA), systems using ultra-wideband (UWB) technology, mobile ad-hoc networks (MANETs), wired access, etc. Furthermore, without loss of generality, the description of some examples of embodiments is related to a mobile communication network, but principles of the disclosure can be extended and applied to any other type of communication network, such as a wired communication network.

[0026] The following examples and embodiments are to be understood only as illustrative examples. Although the specification may refer to “an”, “one”, or “some” example(s) or embodiment(s) in several locations, this does not necessarily mean that each such reference is related to the same example(s) or embodiment(s), or that the feature only applies to a single example or embodiment. Single features of different embodiments may also be combined to provide other embodiments. Furthermore, terms like “comprising” and “including” should be understood as not limiting the described embodiments to consist of only those features that have been mentioned; such examples and embodiments may also contain features, structures, units, modules, etc., that have not been specifically mentioned.

[0027] A basic system architecture of a (tele)communication network including a mobile communication system where some examples of embodiments are applicable may include an architecture of one or more communication networks including wireless access network subsystem(s) and core network(s). Such an architecture may include one or more communication network control elements or functions, access network elements, radio access network elements, access service network gateways or base transceiver stations, such as a base station (BS), an access point (AP), a NodeB (NB), an eNB or a gNB, a distributed unit (DU) or a centralized / central unit (CU), which controls a respective coverage area or cell(s) and with which one or more communication stations such as communication elements or functions, like user devices or terminal devices, like a user equipment (UE), or another device having a similar function, such as a modem chipset, a chip, a module etc., which can also be part of a station, an element, a function or an application capable of conducting a communication, such as a UE, an element or function usable in a machine-to-machine communication architecture, orattached as a separate element to such an element, function or application capable of conducting a communication, or the like, are capable to communicate via one or more channels via one or more communication beams for transmitting several types of data in a plurality of access domains. Furthermore, core network elements or network functions, such as gateway network elements / functions, mobility management entities, a mobile switching center, servers, databases and the like may be included.

[0028] The following description may provide further details of alternatives, modifications and variances: a gNB comprises e.g., a node providing NR user plane and control plane protocol terminations towards the UE, and connected via the NG interface to the 5GC.

[0029] A gNB Central Unit (gNB-CU) comprises e.g., a logical node hosting e.g., RRC, SDAP and PDCP protocols of the gNB or RRC and PDCP protocols of the en-gNB that controls the operation of one or more gNB-DUs. The gNB-CU terminates the Fl interface connected with the gNB -DU.

[0030] A gNB Distributed Unit (gNB-DU) comprises e.g., a logical node hosting e.g., RLC, MAC and PHY layers of the gNB or en-gNB, and its operation is partly controlled by the gNB-CU. One gNB-DU supports one or multiple cells. One cell is supported by only one gNB-DU. The gNB-DU terminates the Fl interface connected with the gNB-CU.

[0031] A gNB-CU-Control Plane (gNB-CU-CP) comprises e.g., a logical node hosting e.g., the RRC and the control plane part of the PDCP protocol of the gNB-CU for an en-gNB or a gNB. The gNB-CU-CP terminates the El interface connected with the gNB-CU-UP and the Fl-C interface connected with the gNB-DU.

[0032] A gNB-CU-User Plane (gNB-CU-UP) comprises e.g., a logical node hosting e.g., the user plane part of the PDCP protocol of the gNB-CU for an en-gNB, and the user plane part of the PDCP protocol and the SDAP protocol of the gNB-CU for a gNB. The gNB-CU-UP terminates the El interface connected with the gNB-CU-CP and the Fl-U interface connected with the gNB-DU.

[0033] A gNB supports different protocol layers, e.g., Layer 1 (LI) - physical layer.

[0034] The layer 2 (L2) of NR is split into the following sublayers: Medium Access Control (MAC), Radio Link Control (RLC), Packet Data Convergence Protocol (PDCP) and Service Data Adaptation Protocol (SDAP).

[0035] Layer 3 (L3) includes e.g., Radio Resource Control (RRC).

[0036] A RAN (Radio Access Network) node or network node like e.g. a gNB, base station, gNB CU or gNB DU or parts thereof may be implemented using e.g. an apparatus with at least one processor and / or at least one memory (with computer-readable instructions (computerprogram)) configured to support and / or provision and / or process CU and / or DU related functionality and / or features, and / or at least one protocol (sub-)layer of a RAN (Radio Access Network), e.g. layer 2 and / or layer 3.

[0037] The gNB CU and gNB DU parts may e.g., be co-located or physically separated. The gNB DU may even be split further, e.g., into two parts, e.g., one including processing equipment and one including an antenna. A Central Unit (CU) may also be called BBU / REC / RCC / C-RAN / V-RAN, O-RAN, or part thereof. A Distributed Unit (DU) may also be called RRH / RRU / RE / RU, or part thereof. Hereinafter, in various example embodiments of the present disclosure, the CU-CP (or more generically, the CU) may also be referred to as a (first) network node that supports at least one of central unit control plane functionality or a layer 3 protocol of a radio access network; and similarly, the DU may be referred to as a (second) network node that supports at least one of distributed unit functionality or the layer 2 protocol of the radio access network.

[0038] A gNB-DU supports one or multiple cells, and could thus serve as e.g., a serving cell for a user equipment (UE).

[0039] A user equipment (UE) may include a wireless or mobile device, an apparatus with a radio interface to interact with a RAN (Radio Access Network), a smartphone, an in-vehicle apparatus, an loT device, a M2M device, or else. Such UE or apparatus may comprise: at least one processor; and at least one memory including computer program code; wherein the at least one memory and the computer program code are configured to, with the at least one processor, cause the apparatus at least to perform certain operations, like e.g. RRC connection to the RAN. A UE is e.g., configured to generate a message (e.g., including a cell ID) to be transmitted via radio towards a RAN (e.g., to reach and communicate with a serving cell). A UE may generate and transmit and receive RRC messages containing one or more RRC PDUs (Packet Data Units).

[0040] The UE may have different states.

[0041] A UE is e.g. , either in RRC_CONNECTED state or in RRC_IN ACTIVE state when an RRC connection has been established.

[0042] The general functions and interconnections of the described elements and functions, which also depend on the actual network type, are known to those skilled in the art and described in corresponding specifications, so that a detailed description thereof may omitted herein for the sake of conciseness. However, it is to be noted that several additional network elements and signaling links may be employed for a communication to or from an element, function or application, like a communication endpoint, a communication network controlelement, such as a server, a gateway, a radio network controller, and other elements of the same or other communication networks besides those described in detail herein below.

[0043] A communication network architecture as being considered in examples of embodiments may also be able to communicate with other networks, such as a public switched telephone network or the Internet. The communication network may also be able to support the usage of cloud services for virtual network elements or functions thereof, wherein it is to be noted that the virtual network part of the telecommunication network can also be provided by non-cloud resources, e.g. an internal network or the like. It should be appreciated that network elements of an access system, of a core network etc., and / or respective functionalities may be implemented by using any node, host, server, access node or entity etc. being suitable for such a usage. Generally, a network function can be implemented either as a network element on a dedicated hardware, as a software instance running on a dedicated hardware, or as a virtualized function instantiated on an appropriate platform, e.g., a cloud infrastructure.

[0044] Furthermore, a network element, such as communication elements, like a UE, a terminal device, control elements or functions, such as access network elements, like a base station / BS, a gNB, a radio network controller, a core network control element or function, such as a gateway element, or other network elements or functions, as described herein, and any other elements, functions or applications may be implemented by software, e.g., by a computer program product for a computer, and / or by hardware. For executing their respective processing, correspondingly used devices, nodes, functions or network elements may include several means, modules, units, components, etc. (not shown) which are required for control, processing and / or communication / signaling functionality. Such means, modules, units and components may include, for example, one or more processors or processor units including one or more processing portions for executing instructions and / or programs and / or for processing data, storage or memory units or means for storing instructions, programs and / or data, for serving as a work area of the processor or processing portion and the like (e.g. ROM, RAM, EEPROM, and the like), input or interface means for inputting data and instructions by software (e.g. floppy disc, CD-ROM, EEPROM, and the like), a user interface for providing monitor and manipulation possibilities to a user (e.g. a screen, a keyboard and the like), other interface or means for establishing links and / or connections under the control of the processor unit or portion (e.g. wired and wireless interface means, radio interface means including e.g. an antenna unit or the like, means for forming a radio communication part etc.) and the like, wherein respective means forming an interface, such as a radio communication part, can be also located on a remote site (e.g. a radio head or a radio station etc.). It is to be noted that inthe present specification processing portions should not be only considered to represent physical portions of one or more processors, but may also be considered as a logical division of the referred processing tasks performed by one or more processors. It should be appreciated that according to some examples, a so-called “liquid” or flexible network concept may be employed where the operations and functionalities of a network element, a network function, or of another entity of the network, may be performed in different entities or functions, such as in a node, host or server, in a flexible manner. In other words, a “division of labor” between involved network elements, functions or entities may vary case by case.

[0045] As illustrated above, the present disclosure generally seeks to improve efficiency in the handling of requests from one or more UEs for reference signals provided by the network, wherein the requested reference signals are for the UE to perform AI / ML model related data collection, so that reliability of AI / ML operations can be ensured.

[0046] According to the present disclosure, AI / ML data may be used for positioning purposes, or some other use case as well, e.g., beam management, mobility, resource allocation, transmission / reception, etc.

[0047] Therefore, in the following, when DL PRS is described, it merely serves the purpose of an illustrative example for explaining the technical issues and possible implementations of the proposed solution according to the present disclosure.

[0048] As per agreements in 3GPP RAN 1 #118 and RAN2 #129, UE may send on-demand PRS request to LMF in order to collect training data, i.e., Part A (positioning channel measurements) and / or Part B data (ground truth labels, e.g., location information). That is, by using the requested DL PRS transmission with characteristics desired by the UE, UE can perform positioning-related measurements and estimations to be used for UE-side AI / ML models for positioning.

[0049] However, the unsolicited on-demand PRS requests coming from the UEs may be easily rejected by the network, e.g., when the network cannot satisfy the request due to e.g., over-demanding requests, e.g., DL PRS with large bandwidth and frequency, etc., as well as large number requests with distinct or conflicting characteristics which the network may not satisfy depending on the load conditions on radio resources and the network processing capabilities,load conditions in the network depending on certain time of the day, or certain areas served by the network,prioritization of different types of DL transmissions (e.g., low priority for ODPRS), maintaining fairness for UEs in the system (priority for some UEs over other UEs), minimizing transmission of ODPRS with distinct characteristics in an attempt to maximize resource efficiency, andetc.

[0050] Consequently, rejected ODPRS requests:result in wastage of UL resources since such ODPRS requests from the UE are ignored by the network, andcreate uncertainties in AI / ML operation (e.g. training, monitoring, inference) from the UE perspective, for which the use of requested ODPRS transmission is intended, as it potentially interrupts or delays the respective AI / ML operation.

[0051] Therefore, in the above example, more efficient mechanisms for handling ODPRS requests for AI / ML data collection become necessary to avoid UL resource wastage and to improve reliability (or availability) of AI / ML operations.

[0052] In view of the above, it is proposed in accordance with the present disclosure a method for network (NW) to control UE on-demand PRS requests for data collection for UE-side positioning AI / ML models based on the NW preference. This allows the UE to avoid sending on-demand PRS request that are likely to be rejected by the network. In addition, the UEs can plan and adapt their data collection (e.g., training data collection) considering the network’s preferences in DL PRS transmission.

[0053] The present disclosure proposes a step of NW (e.g., LMF) providing assistance information to the UE, which indicates the preferred DL PRS configurations that UE may request via on-demand PRS (ODPRS) request for data collection for UE-side AI / ML models, via one or more of:• Time-based assistance info:o Preferred duration time (e.g., in terms of min., max., range, or set of values), ando Preferred start and / or stop time of DL PRS transmission that UE may request e.g., NW indicates that UE may request ODPRS transmission with a maximum duration of 1 hour, starting after 14:00 pm and ending before 17:00.• Area-based assistance info:o Preferred gNB / cell / TRPs that could transmit DL PRS, which UE may request;E.g., NW indicates that UE may request ODPRS to be transmitted from a certain list of TRP IDs only.• Further, the aforementioned assistance information may be combined witho Associated IDs that are preferred by network, which UE can request for ODPRS transmission:■ Associated IDs refer to IDs associated with certain configurations at NW-side (e.g., antenna configuration, beam configuration, or even one or more parameters of DL PRS configuration, etc.) which can be used to represent respective conditions without revealing the actual configuration details that could be implementation specific.o Purpose-based assistance info:■ Preferred reasons for which UE can request ODPRS,■ E.g., for AI / ML model training, model monitoring, model inference, or non-AI / ML positioning purposes for a certain time and area.o E.g., a combination of time and purpose-based configuration could be as follows: AI / ML model training in starting after 10:00 pm and ending before 7:00, and no time restriction for AI / ML model inference.o A preferred set of DL PRS configurations for a certain time and area, i.e., each available DL PRS configuration is provided with preferred time and areabased configuration.o Device-based assistance info (broadcast):■ Preferred devices: only certain UE devices may be preferred to request ODPRS at certain time and area. In this case, the preference may be based on e.g., type of UEs (e.g., loT-like UE or eMBB UE) or UE (or chip set within the UE) vendors.

[0054] Note that in the above example relating to AL / ML data collection using DL PRS, the specific reference signal DL PRS can be replaced, in accordance with the present disclosure with any other reference signal transmitted by the network node to the UE for the UE to perform AL / ML data collection.

[0055] References are now made to the figures. In particular, it is to be noted that identical or like reference numbers used in the figures of the present disclosure may, unless indicatedotherwise, indicate identical or like elements, such that repeated description thereof may be omitted for reasons of conciseness.

[0056] Figure 1 schematically illustrates an example of a method for AI / ML data collection based on NW assistance according to an example embodiment of the present disclosure. As illustrated in Figure 1, the method comprises the following steps performed by a UE.

[0057] Step S 101 : receiving, from a network node, reference signal assistance information indicating one or more preferred reference signal configurations, wherein the reference signal assistance information comprises at least one of time-based configuration information or areabased configuration information.

[0058] Step S102: sending, to the network node, a reference signal request for artificial intelligence / machine learning, AI / ML, data collection based on the received reference signal assistance information.

[0059] Accordingly, the network indicates, with the reference signal assistance information, the time-based configuration(s) and / or area-based configuration(s), such that the UE can take those configuration(s) into consideration in requesting for a corresponding reference signal, leading to reduced rejection possibility of the network for sending the requested reference signal.

[0060] Preferably, subsequent to step S102, the UE: receives a reference signal; performs measurements based on the received reference signal; and performs AI / ML data collection based on said measurements. Accordingly, with improved possibility of obtaining the requested reference signal, it can be ensured that the AI / ML operations at the UE are performed with higher reliability.

[0061] Preferably, prior to step S 101, the UE sends to the network node a reference signal assistance information request for requesting for the reference signal assistance information.

[0062] Preferably, the time-based configuration information is preferred by the network node, said time-based configuration information including at least one of: a duration for reference signal transmission, a start time for reference signal transmission, or a stop time for reference signal transmission. The duration time / start / stop time is for the reference signal that NW transmits (e.g., duration of DL PRS), and the assistance information indicates which values UE can request for these parameters of the reference signal, e.g., DL PRS (e.g., UE is not allowed to request a DL PRS transmission that lasts more than an hour, for example).

[0063] Preferably, the area-based configuration information is preferred by the network node, said area-based configuration information indicating at least one of: at least one gNBwhich the UE may request to send the reference signal to the UE, at least one cell which the UE may request to send the reference signal to the UE, at least one Transmission Reception Point, TRP, which the UE may request to the reference signal to the UE, or at least one beam which the UE may request to send the reference signal to the UE.

[0064] Preferably, the reference signal assistance information further comprises purposebased configuration information preferred by the network node, said purpose-based configuration information indicating at least one reason for the UE to send the reference signal request.

[0065] Preferably, the reference signal assistance information further comprises at least one identifier, ID, associated with one or more network node side conditions. In this case, these IDs are associated with one or more NW- side conditions, which may relate to reference signal transmission (e.g., antenna configuration), wherein NW doesn't want to reveal the actual value / setting of the parameter but only indicate an ID associated with such parameters (up to NW implementation.)

[0066] Preferably, the reference signal assistance information further comprises devicebased assistance information preferred by the network node, said device-based assistance information indicating at least one preferred device type for being allowed to request for a reference signal. The preferred device type may include e.g., loT device, eMBB device, or certain device vendor.

[0067] Preferably, the reference signal assistance information further comprises an acceptance rate of sending the requested reference signal to the UE in response to the reference signal request.

[0068] Preferably, the reference signal assistance information further comprises an indication for the UE to include, in the reference signal request, required information, wherein the required information comprises at least one of: device information related to the UE, at least one reason for the reference signal request, IDs of one or more configurations related to the reference signal, start time of said data collection, stop time of said data collection, or a duration of said data collection.

[0069] Preferably, the UE is prohibited from sending a reference signal request that doesn’t match with the one or more preferred reference signal configurations.

[0070] Preferably, the AI / ML data collection is performed for at least one of: positioning, beam management, mobility, resource allocation, transmission, or reception.

[0071] Accordingly, the network indicates its preferred configuration(s) related to the reference signal transmission, such that the UE can take those preferred configuration(s) intoconsideration in requesting for a corresponding reference signal, leading to further reduced rejection possibility of the network sending the requested reference signal.

[0072] Figure 2 schematically illustrates another example of a method for AI / ML data collection based on NW assistance according to an example embodiment of the present disclosure. As illustrated in Figure 2, the method comprises the following steps performed by a network node. The network node may be a LMF, another CN entity or a RAN node, e.g., AMF, gNB, 0AM.

[0073] Step S201: determining reference signal assistance information for indicating one or more preferred reference signal configurations, wherein the reference signal assistance information comprises at least one of time-based configuration information or area-based configuration information.

[0074] Step S202: sending, to a user equipment, UE, the determined reference signal assistance information.

[0075] Step S203: receiving, from the UE, a reference signal request for artificial intelligence / machine learning, AI / ML, data collection.

[0076] Preferably, subsequent to step S203, the network node determines, in response to the received reference signal request, to send to the UE a reference signal by the network node and / or one or more other network nodes.

[0077] The network node in steps S201-S203 may decide or select from a plurality of network nodes (including the network node in steps S201-S203) that can send to the UE the requested reference signal. The decision may be based on the requested configurations included indicated by the reference signal request and which network node is able to provide the requested reference signal.

[0078] Preferably, step S201 comprises that the network node determines the reference signal assistance information in response to a reference signal request received from the UE.

[0079] Preferably, step S201 comprises that the network node determines the reference signal assistance information based on data processing and load conditions of the network node and / or said one or more other network nodes and / or based on one or more other reference signal requests from at least one other UE, wherein the network node and / or said one or more other network nodes are configured to serve said UE and / or said at least one other UE.

[0080] Consequently, the network node can distribute the reference signal requests from different UEs in the network across different network nodes in the network, to meet the load conditions across the networks at different times and areas. Accordingly, the possibility that areference signal request from a UE being accepted by the network is improved, leading to improved efficiency of the request handling, as well as improved reliability of the AI / ML operations in the network.

[0081] Similar aspects relating to the reference signal assistance information are described above for Figure 1, which are not repeated here.

[0082] Figure 3 schematically illustrates another example of a method for AI / ML data collection based on NW assistance according to an example embodiment of the present disclosure. As illustrated in Figure 3, the method comprises the following steps performed by a system including a gNB, an EMF and a UE.

[0083] Note that the structure of the system or the network is merely an illustrative example, wherein the present disclosure applies to all networks where UE(s) communicate with a network node for obtaining a reference signal for AI / ML data collection.

[0084] Further, the example in Figure 3 applies to other kinds of reference signals for other AI / ML applications as described above.

[0085] Further, the example in Figure 3 applies to other kinds of network nodes as described above.

[0086] Step S301 (optional): UE determines the need for collecting data using DL PRS transmissions, e.g., in order to train UE-side AI / ML model for positioning.

[0087] Step S302 (optional): UE may request from NW the assistance information for sending on-demand PRS (ODPRS) requests for AI / ML data collection. Note that this step is optional. In other words, the UE may like to know about network preferences on ODPRS in advance so that:o it can minimize the risk of its ODPRS request being rejected by the network, ando plan its data collection activity in alignment with the network preference to avoid any interruptions during data collection.

[0088] Step S3O3: NW (e.g., LMF) determines the assistance information for ODPRS requests for AI / ML data collection, which may contain at least one or more of the following information:a. Time-based assistance: NW indicates the preferred and / or allowed duration time (e.g., in terms of min., max., range, or set of values), and preferred and / or allowed start and / or stop time of DL PRS transmission that UE may request;■ e.g., NW indicates that UE may request ODPRS transmission with a maximum duration of 1 hour, starting after 14:00 pm and ending before 17:00,b. Area-based assistance: NW indicates the preferred and / or allowed gNB / cell / TRP / beams that could transmit DL PRS for UE’s data collection purposes, which UE may request;■ E.g., NW indicates that UE may request ODPRS to be transmitted from a certain list of TRP IDs only.

[0089] Above options (a) and (b) in S3O3 enable NW to distribute the load associated with PRS transmissions across the network, over space and time, hence enable load balancing. For example, network may need to serve a high amount of traffic in certain cells and it cannot occupy same resources with DL PRS transmissions for certain periods of time due to requests coming from the UEs.

[0090] These options also enable the NW to bar / reserve certain areas for data collection, which might be restricted due to location-sensitive concerns, e.g., military bases, or conversely, to enable data collection in dedicated private areas, e.g., for positioning loT devices in a private factory network.

[0091] In order to determine above preferences, LMF may first determine the load conditions across different locations and times in its service area, such as based on: number / frequency of location requests from UEs, PRS transmissions that are active or configured in different locations, number / rate / duration of PRS configurations determined / rejected by different gNBs (it is up to gNB to configure DL PRS transmission upon the request coming from LMF. If gNB rejects a configuration, then it may be indicative of high load in that gNB). In turn, LMF can determine areas and times that are less loaded, and creates a preference based on that.

[0092] Furthermore, time and area-based assistance may be provided in combination with one or more of the following:■ Purpose-based assistance: NW indicates preferred reasons for UE can request ODPRS requests, e.g., for AI / ML model training, model monitoring, model inference, or non-AFML positioning purposes along with the time and area assistance.■ E.g., a combination of time and purpose-based configuration could be as follows: AI / ML model training starting after 10:00 pm andending before 7:00, and no time restriction for AI / ML model inference.■ A preferred set of DL PRS configurations for a certain time and area, i.e., each available DL PRS configuration is provided with preferred time and areabased configuration.■ Note that, currently the network can already provide a list of DL PRS configuration for the UE. According to the present disclosure, this is enhanced with attaching time and area information for the DL PRS configuration.■ Device-based assistance (broadcast): NW indicates that only certain UE devices may be preferred to request ODPRS at certain time and area. In this case, the preference may be based on e.g., type of UEs (e.g., loT-like UE or eMBB UE) or UE (or chip set within the UE) vendors.

[0093] In the embodiments according to the present disclosure, the above preference indications might be further provided with associated probability of NW accepting (or rejecting) the related requests. To illustrate, NW may indicate a preference for DL PRS transmission in certain area X with 40%, and in another area Y with 80%, with percentages representing probability of NW accepting DL PRS transmission request for respective areas.

[0094] The assistance information may also indicate whether UE is required to indicate one or more of the following, when sending its ODPRS request:a. Device information (e.g., vendor ID)b. Purpose of data collectionc. Desired Associated ID(s)aa. In one embodiment, UE is allowed (or not allowed at all) to indicate only a single Associated ID it desires for data collection. In an embodiment, UE is allowed to indicate multiple desired associated IDs, optionally, together with a preference order among them.d. Desired time and duration of data collection

[0095] Note that Step S3O3 can be triggered by requests for configuration coming from UE(s) or triggered by LMF internally. In the first case, LMF may determine a dedicated configuration for each UE individually, whereas in the latter, LMF may determine a common configuration for all UEs, e.g., served by a cell or an area.

[0096] Step S304: NW provides the determined assistance information for sending ODPRS requests for AI / ML data collection, to UE.

[0097] Step S305: UE sends ODPRS request for AI / ML data collection based on the assistance information provided by NW in the previous step.• That is, UE sends its ODPRS request for AI / ML data collection by taking into account the network preference on DL PRS transmission start time and duration as well as the area, and indicates the information that is required by NW in the provided assistance information.• In the embodiments, the request could be sent as a part of MO-LR, LPP ODPRS request, LPP Request Assistance Data, or another / new LPP or NAS protocol and / or message, e.g., LPP Request Assistance Data for Data Collection, which could be also a standalone request (e.g., a request sent for collecting measurement only and not for positioning).

[0098] Step S306 (optional): Upon receiving the request, NW determines a suitable DL PRS configuration for AI / ML data collection.• For this, NW may take into account different requests coming from multiple UEs.For example, in an embodiment, LMF may determine a superset of a PRS values requested by different UEs. E.g., UE1 requests PRS with { 100 MHz BW, 20 ms periodicity] and UE2 requests with {200 MHz, 100 ms periodicity], LMF then configures PRS with {200 MHz, 20 ms}.• LMF may coordinate with gNBs to determine the DL PRS configuration, as in legacy positioning.

[0099] Step S307 (optional): NW / LMF provides determined DL PRS configuration for AI / ML data collection to the UE.a. The indication could be via broadcast, multicast, or dedicated signaling as per their relevance to different UEs.b. In an embodiment, LMF indicates the determined configuration via LPP Provide Assistance Data message.

[0100] Step S3O8 (optional): TRPs transmit DL PRS according to determined DL PRS configuration.

[0101] Step S309 (optional): UE performs data collection such as by performing measurements using the provided configuration (e.g., time / power / phase / angle measurements using DL PRS), and storing measurements and / or provided ground truth information.

[0102] Step S310 (optional): UE utilizes the collected data, e.g., to train its AI / ML model for positioning.

[0103] Further embodiments according to the present disclosure and can be applied alternatively or in addition to the above embodiments according to Figures 1 to 3:Instead of EMF, another CN entity or a RAN node, e.g., AMF, gNB, 0AM may assume the roles described above.Instead of or in addition to DL PRS, other reference signals can be transmitted, e.g., for purposes of channel sounding or channel state information, synchronization, demodulation, etc., including CSI-RS, DMRS, PTRS, SRS, PSS / SSS, which could be especially relevant for AI / ML use cases other than positioning.Signaling between NW and UE for the above procedures may take place via different protocols, such as LPP (between LMF and UE), RRC (between gNB and UE), MAC (between gNB and UE), etc.

[0104] Figure 4 illustrates a block diagram for an apparatus 110, for implementing one or more example embodiments of the present disclosure. The apparatus 110 may be or comprise a terminal device, a base station, a next Generation NodeB (gNB) etc.

[0105] The apparatus 110 may comprise a processor 1104, for controlling the respective operations of the first apparatus 110. The processor 1104 may also be referred to as a central processing unit (CPU). The processor 1104 may, for example, be embodied in a variety of ways including circuitry, at least one processing core, one or more coprocessors, one or more multicore processors, one or more controllers, processing circuitry, other processing elements including integrated circuits (for example, an application specific integrated circuit (ASIC), a field programmable gate array (FPGA), and / or the like), or some combination thereof.

[0106] The apparatus 110 may comprise a memory 1102. The memory 1102 may include both read-only memory (ROM) and random access memory (RAM), and may provide instructions and data to the processors 1104. The memory 1102 and the processor 1104 of the apparatus 110, may be operatively coupled. The memory 1102 may store instructions, e.g. computer readable instructions / computer program code. The computer readable instructions / computer program code may be pre-stored to the memory 1102 or, alternatively or additionally, they may be received, by the apparatus 110, via an electromagnetic carrier signal and / or may be copied from a physical entity such as a computer program product. Execution of the computer readable instructions by the processor 1104, may cause the apparatus 110, tocarry out the example embodiments described herein, such as the steps as outlined in Figures 1 to 3.

[0107] The apparatus 110 may include transmitter / receiver (TX / RX) circuitry 1106, that may further include a transmitter 1108 and a receiver 1110. The TX / RX circuitry 1106 may enable the apparatus 110 to transmit or receive data. The apparatus 110 may include (not shown) multiple antennas, transmitters, and receivers.

[0108] In some example embodiments, the apparatus 110 may comprise means that enable it to perform the steps / operations in Figures 1 to 3 (as applicable). The means may be implemented in any suitable form. For example, the means may at least be implemented in a circuitry, a combination of the memory 1102, processor 1104, TX / RX circuitry 1106, or a software module.

[0109] It is noted that, although in the above-illustrated example embodiments (with reference to the figures), the messages communicated / exchanged between the network components / elements may appear to have specific / explicit names, depending on various implementations (e.g., the underlining technologies), these messages may have different names and / or be communicated / exchanged in different forms / formats, as can be understood and appreciated by the skilled person.

[0110] According to some example embodiments, there are also provided corresponding methods suitable to be carried out by the apparatuses (network elements / components) as described above, such as the UE, the CU, the DU, etc.

[0111] It should nevertheless be noted that the apparatus (device) features described above correspond to respective method features that may however not be explicitly described, for reasons of conciseness. The disclosure of the present document is considered to extend also to such method features. In particular, the present disclosure is understood to relate to methods of operating the devices described above, and / or to providing and / or arranging respective elements of these devices.

[0112] Further, according to some further example embodiments, there is also provided a respective apparatus (e.g., implementing the UE, the CU, the DU, etc., as described above) that comprises at least one processing circuitry, and at least one memory for storing instructions to be executed by the processing circuitry, wherein the at least one memory and the instructions are configured to, with the at least one processing circuitry, cause the respective apparatus to at least perform the respective steps as described above.

[0113] Yet in some other example embodiments, there is provided a respective apparatus (e.g., implementing the UE, the CU, the DU, etc., as described above) that comprises respective means configured to at least perform the respective steps as described above.

[0114] It is to be noted that examples of embodiments of the disclosure are applicable to various different network configurations. In other words, the examples shown in the above described figures, which are used as a basis for the above discussed examples, are only illustrative and do not limit the present disclosure in any way. That is, additional further existing and proposed new functionalities available in a corresponding operating environment may be used in connection with examples of embodiments of the disclosure based on the principles defined.

[0115] It should also to be noted that the disclosed example embodiments can be implemented in many ways using hardware and / or software configurations. For example, the disclosed embodiments may be implemented using dedicated hardware and / or hardware in association with software executable thereon. The components and / or elements in the figures are examples only and do not limit the scope of use or functionality of any hardware, software in combination with hardware, firmware, embedded logic component, or a combination of two or more such components implementing particular embodiments of the present disclosure.

[0116] It should further be noted that the description and drawings merely illustrate the principles of the present disclosure. Those skilled in the art will be able to implement various arrangements that, although not explicitly described or shown herein, embody the principles of the present disclosure and are included within its spirit and scope. Furthermore, all examples and embodiment outlined in the present disclosure are principally intended expressly to be only for explanatory purposes to help the reader in understanding the principles of the proposed method. Furthermore, all statements herein providing principles, aspects, and embodiments of the present disclosure, as well as specific examples thereof, are intended to encompass equivalents thereof.List of abbreviations:AMF access and mobility management functionCN core networkCSI-RS Channel State Information Reference SignalGT ground truthDMRS Demodulation Reference SignalLMF location management functionLPP LTE positioning protocolMO-LR Mobile Originating Location Request ODPRS On-demand PRSOTT Over-the-topPRS Positioning Reference SignalPSS primary synchronization signal PTRS Phase Tracking Reference Signal RS Reference SignalSRS Sounding Reference SignalSSS Secondary synchronization signal

Claims

CLAIMS:

1. A User Equipment, UE, comprising:at least one processor, andat least one memory storing instructions that, when executed by the at least one processor, cause the UE at least to:receive, from a network node, reference signal assistance information indicating one or more preferred reference signal configurations, wherein the reference signal assistance information comprises at least one of time-based configuration information or areabased configuration information; andsend, to the network node, a reference signal request for artificial intelligence / machine learning, AUML, data collection based on the received reference signal assistance information.

2. The UE according to claim 1, wherein the UE is further configured toreceive a reference signal;perform measurements based on the received reference signal; andperform AUML data collection based on said measurements.

3. The UE according to claim 1 or claim 2, wherein the UE is further configured to send to the network node a reference signal assistance information request for requesting for the reference signal assistance information.

4. The UE according to any one of claims 1 to 3, wherein the time-based configuration information is preferred by the network node, said time-based configuration information including at least one of:a duration for reference signal transmission,a start time for reference signal transmission, ora stop time for reference signal transmission.

5. The UE according to any one of claims 1 to 4, wherein the area-based configuration information is preferred by the network node, said area-based configuration information indicating at least one of:at least one gNB which the UE may request to send the reference signal to the UE, at least one cell which the UE may request to send the reference signal to the UE, at least one Transmission Reception Point, TRP, which the UE may request to the reference signal to the UE, orat least one beam which the UE may request to send the reference signal to the UE.

6. The UE according to any one of claims 1 to 5, wherein the reference signal assistance information further comprises purpose-based configuration information preferred by the network node, said purpose-based configuration information indicating at least one reason for the UE to send the reference signal request.

7. The UE according to any one of claims 1 to 6, wherein the reference signal assistance information further comprises at least one identifier, ID, associated with one or more network node side conditions.

8. The UE according to any one of claims 1 to 7, wherein the reference signal assistance information further comprises device-based assistance information preferred by the network node, said device-based assistance information indicating at least one preferred device type for being allowed to request for a reference signal.

9. The UE according to any one of claims 1 to 8, wherein the reference signal assistance information further comprises an acceptance rate of sending the requested reference signal to the UE in response to the reference signal request.

10. The UE according to any one of claims 1 to 9, wherein the reference signal assistance information further comprises an indication for the UE to include, in the reference signal request, required information, wherein the required information comprises at least one of:device information related to the UE,at least one reason for the reference signal request,IDs of one or more configurations related to the reference signal,start time of said data collection,stop time of said data collection, ora duration of said data collection.

11. The UE according to any one of claims 1 to 10, wherein the UE is further configured to: be prohibited from sending a reference signal request that doesn’t match with the one or more preferred reference signal configurations.

12. The UE according to any one of preceding claims, wherein the AI / ML data collection is performed for at least one of: positioning, beam management, mobility, resource allocation, transmission, or reception.

13. A network node, comprising:at least one processor, andat least one memory storing instructions that, when executed by the at least one processor, cause the network node at least to:determine reference signal assistance information for indicating one or more preferred reference signal configurations, wherein the reference signal assistance information comprises at least one of time-based configuration information or area-based configuration information;send, to a user equipment, UE, the determined reference signal assistance information; andreceive, from the UE, a reference signal request for artificial intelligence / machine learning, AUML, data collection.

14. The network node according to claim 13, wherein the network node is further configured to: determine, in response to the received reference signal request, to send to the UE a reference signal by the network node and / or one or more other network nodes.

15. The network node according to claim 13 or claim 14, wherein the time-based configuration information is preferred by the network node, said time-based configuration information including at least one of:a duration for reference signal transmission,a start time for reference signal transmission, ora stop time for reference signal transmission.

16. The network node according to any one of claims 13 to 15, wherein the area-based configuration information is preferred by the network node, said area-based configuration information indicating at least one of:at least one gNB which the UE may request to send the reference signal,at least one cell which the UE may request to send the reference signal,at least one Transmission Reception Point, TRP, which the UE may request to send the reference signal, orat least one beam which the UE may request to send the reference signal.

17. The network node according to any one of claims 13 to 16, wherein the reference signal assistance information further comprises purpose-based configuration information preferred by the network node, said purpose-based configuration information indicating at least one reason for the UE to send the reference signal request.

18. The network node according to any one of claims 13 to 17, wherein the reference signal assistance information further comprises at least one identifier, ID, associated with one or more network node side conditions.

19. The network node according to any one of claims 13 to 18, wherein the reference signal assistance information further comprises device-based assistance information preferred by the network node, said device-based assistance information indicating at least one preferred device type for being allowed to request for a reference signal.

20. The network node according to any one of claims 13 to 19, wherein the reference signal assistance information further comprises an acceptance rate of sending the requested reference signal to the UE in response to the reference signal request.

21. The network node according to any one of claims 13 to 20, wherein the reference signal assistance information further comprises an indication for the UE to include, in the reference signal request, required information, wherein the required information comprises at least one of:device information related to the UE,at least one reason for the reference signal request,IDs of one or more configurations related to the reference signal,start time of said data collection,stop time of said data collection, ora duration of said data collection.

22. The network node according to any one of claims 13 to 21, wherein the network node is configured to determine the reference signal assistance information in response to a reference signal request received from the UE.

23. The network node according to any one of claims 13 to 22, wherein the network node is configured to determine the reference signal assistance information based on data processing load conditions of the network node and / or said one or more other network nodes and / or based on one or more other reference signal requests from at least one other UE, wherein the network node and / or said one or more other network nodes are configured to serve said UE and / or said at least one other UE.

24. A method of a User Equipment, UE, the method comprising:receiving, from a network node, reference signal assistance information indicating one or more preferred reference signal configurations, wherein the reference signal assistance information comprises at least one of time-based configuration information or area-based configuration information; andsending, to the network node, a reference signal request for artificial intelligence / machine learning, AI / ML, data collection based on the received reference signal assistance information.

25. A method of a network node, the method comprising:determining reference signal assistance information for indicating one or more preferred reference signal configurations, wherein the reference signal assistance information comprises at least one of time-based configuration information or areabased configuration information;sending, to a user equipment, UE, the determined reference signal assistance information; andreceiving, from the UE, a reference signal request for artificial intelligence / machine learning, AI / ML, data collection.

26. A computer program comprising instructions for causing an apparatus to perform the method according to claim 24 or according to claim 25.

27. An apparatus comprising mean for performing the method according to claim 24 or according to claim 25.

Images