Network control of non-standardized ai / ML data collection for GNB-side models

Abstract

A method includes: determining a policy for collection of data and transfer of data for machine learning purposes; receiving, from a server, a request for the collection of the data; determining at least one network entity related to the request for the collection of the data; receiving, from the at least one network entity, collected data associated with the request within a container decodable by the server, based on the policy; and transmitting, to the server, the container decodable by the server comprising the collected data.

Description

Network Control Of Non-Standardized AI / ML Data Collection For GNB-Side ModelsTECHNICAL FIELD

[0001] The examples and non-limiting example embodiments relate generally to communications and, more particularly, to network control of non- standardized AI / ML data collection for gNB-side models.BACKGROUND

[0002] It is known estimate the position of one or more network devices in a communication network.SUMMARY

[0003] According to an example embodiment, a method may include: determining a policy for collection of data and transfer of data for machine learning purposes; receiving, from a server, a request for the collection of the data; determining at least one network entity related to the request for the collection of the data; receiving, from the at least one network entity, collected data associated with the request within a container decodable by the server, based on the policy; and transmitting, to the server, the container decodable by the server comprising the collected data.

[0004] According to an example embodiment, a method may include: performing at least one of: receiving, from at least one network entity or a server, a container decodable by the apparatus, wherein the container comprises a request addressed to the apparatus for collection of data associated with machine learning purposes, or receiving, directly from the server, the request for collection of data associated with machine learning purposes without the container; collecting the data; and performing at least one of: transmitting, to at least one network entity or directly to the server, the collected data associated with the request within a container decodable by the server that requested the data, or transmitting, directly to the server, the collected data associated with the request.

[0005] According to an example embodiment, a method may include: transmitting, to a management entity or to at least one network entity, a request for collection of data for machine learning purposes; and performing at least one of: receiving, from the management entity or the at least one network entity, collected data associated with the request within a container decodable by the apparatus, or receiving, from the at least one network entity, the collected data associated with the request.

[0006] According to an example embodiment, a method may include: receiving, from a management entity, a request for data associated with machine learning purposes; wherein the request is associated with a container decodable by at least one network entity; transmitting, to the at least one network entity, the container decodable by the at least one network entity comprising a request addressed to the at least one network entity for collection of the data; receiving, from the at least one network entity, the collected data associated with the request within a container decodable by a server; and transmitting, to the management entity or directly to the server, the collected data associated with the request within the container decodable by the server.

[0007] According to an example embodiment, a method may include: receiving, from at least one network entity or a location management function, a configuration to transmit at least one uplink signal or transmission, based on a configuration of physical signaling; and transmitting the at least one uplink signal or transmission to the at least one network entity, based on the configuration of physical signaling; wherein the at least one uplink signal or transmission is configured to be used with the at least one network entity to collect nonstandardized data related to machine learning purposes.

[0008] Other example embodiments are provided or described for each of the example methods, including: means for performing any of the example methods; a non-transitory computer-readable storage medium comprising instructions stored thereon that, when executed by at least one processor, are configured to cause the at least one processor to perform any of the example methods; and an apparatus including at least one processor, and at least one memory storing instructions that, when executed by the at least one processor, cause the apparatus at least to perform any of the example methods.

[0009] The details of one or more examples of embodiments are set forth in the accompanying drawings and the description below. Other features will be apparent from the description and drawings, and from the claims.BRIEF DESCRIPTION OF THE DRAWINGS

[0010] The foregoing aspects and other features are explained in the following description, taken in connection with the accompanying drawings.

[0011] FIG. 1 shows a signaling flow for an embodiment of the examples described herein.

[0012] FIG. 2 shows a signaling flow for an embodiment of the examples described herein.

[0013] FIG. 3 is a block diagram of one possible and non-limiting system in which the example embodiments may be practiced.

[0014] FIG. 4 is an example apparatus configured to implement the examples described herein.

[0015] FIG. 5 shows a representation of an example of non-volatile memory media used to store instructions that implement the examples described herein.

[0016] FIG. 6 is an example method, based on the examples described herein.

[0017] FIG. 7 is an example method, based on the examples described herein.

[0018] FIG. 8 is an example method, based on the examples described herein.

[0019] FIG. 9 is an example method, based on the examples described herein.

[0020] FIG. 10 is an example method, based on the examples described herein.

[0021] FIG. 11 shows an example overall request sent by a server for data collection.DETAILED DESCRIPTION OF EXAMPLE EMBODIMENTS

[0022] The examples described herein relate to data collection for AI / ML for positioning within the scope of the study item AI / ML for Air Interface in 3GPP. The examples described herein further relate to the use case of NG-RAN node assisted positioning with a gNB-sidemodel, and AI / ML assisted positioning, including data collection for ML-based positioning, training, and model monitoring.

[0023] A location management function (LMF) can request or provide capabilities of a UE related to positioning, request / provide assistance data (e.g., reference nodes and configuration of positioning signal), and request / provide location information: location measurement data and / or location estimate from the target, using the LPP protocol to communicate with a target device (UE), and NRPPa protocol to communicate with a gNB.

[0024] The LMF decides on the positioning method (based on QoS, UE / gNB capabilities), and invokes it at UE / gNB, either via UE-based positioning: UE calculates the location estimate, or UE-assisted / NW-based positioning: UE provides measurements, LMF calculates the location estimate. The LMF may combine all results and determine a single location estimate as well as the accuracy of the estimate and velocity.

[0025] PRUs are UEs with known location, supporting UL / DL positioning measurements, which can be collected by the LMF and compared with the known PRU location to determine correction terms for other nearby UEs.

[0026] NWDAF involvement in data collection for positioning. According to TS 23.288, the NWDAF may collect location information for a target UE or a group of target UEs from the LCS system. The collected location related information can include: the location estimate of the UE, the time stamp of the location estimate, the velocity of the UE as defined in TS 23.032

[0034] , information about the positioning method used to obtain the location estimate of the UE, indication of an area event, when the UE enters, is within or leaves the geographical area, or indication of a motion event when the UE moves by more than some predefined straight line distance from a previous location.

[0027] NWDAF checks user consent taking the purpose for data collection and usage of these data into account. NWDAF checks the user consent by retrieving the user consent information from UDM. The user consent is subscription information stored in the UDM, which includes: a) whether the user authorizes the collection and usage of its data for a particular purpose, and b) the purpose for data collection, e.g. analytics or model training.

[0028] For the data generation entity and termination entity deployed at different entities, it may be assumed for CSI enhancement and beam management use cases, for model training,training data can be generated by UE / gNB and terminated at a gNB / OAM / OTT server, and for the positioning enhancement use case, for model training, training data can be generated by UE / gNB and terminated at LMF / OTT server.

[0029] In the agreed positioning use-cases according to the ongoing RANI SI in Rel-18, a gNB-side model can be considered as NW-side model, and this corresponds to the case where the gNB performs at least inference of the model. TR 38.843 indicates that an UE-side (AI / ML) model refers to an AI / ML Model whose inference is performed entirely at the UE, and that a network-side (AI / ML) model refers to An AI / ML Model whose inference is performed entirely at the network.

[0030] Whereas training of gNB-side models remains as an open problem. As one option, the entity that trains the gNB-side model might be the gNB vendor, which uses a server external to the 3GPP network.

[0031] To train the models, the external vendor server needs to collect data from the network, mainly related to UL / DL positioning-related measurements and / or UE location information. Most of the positioning-related data has been standardized within the LCS framework, for example time-based or angle-based measurements at the gNB side as well as UE location information (e.g., absolute location coordinates) are well-defined with corresponding fields in NRPPa and LPP messages, respectively.

[0032] However, it may not be possible to specify / standardize all data that are required for gNB-side models, e.g., the model input, since each vendor might develop and deploy arbitrarily different models, which they may further not prefer to disclose. The gNB vendor may want to train their model outside 3GPP network considering non-standardized auxiliary inputs such as SNR, Doppler, sensor measurements etc. For example, a gNB may utilize Doppler measurements as model input, which is however not specified in NRPPa. Similarly, gNB might be able to conduct non-configured measurements (e.g., gNB may passively monitor any ongoing UL SRS transmission it is not configured with) by internal implementation, which will be used as input to the gNB-side model.

[0033] Collecting non-standardized data (for training, as well as monitoring, retraining and updating gNB-side AI / ML models) is in particular favourable for gNB vendors, due to following reasons: 1) gNB vendor may develop models considering different gNB category, power, memory and computational capabilities of the gNB and may not disclose such detailsto network. 2) Similarly, gNB vendors would not disclose / expose the details of their AIML model for positioning purposes deployed at the gNB, which could be a part of their proprietary algorithm. 3) It would not be practical (or even possible) to standardize each granularity desired by different vendors, e.g., IdB step RSRP, 0.25dB step, etc. to the point which requires inefficient signalling, like floating point, to cover all the different cases. 4) It isn’t easy to add new datatypes for non- standardized data collection because of the delay between defining the requirements, generating agreements in all the 3GPP WG’s that get affected by the proposed changes and then waiting for RAN / SA / CT plenary to integrate the changes into the spec. This cycle could be longer than 6 months, not including the implementation and deployment time, which could take another 6-12 months.

[0034] Currently, there is no framework for the gNB vendor server to collect nonstandardized positioning-related data from a 3GPP network. Specifically, for gNB -sided model offline training, the existing Rel-18 positioning framework is not suitable for data collection; therefore, it requires further enhancements. It would be for the benefit of the network to control flow of data going to external parties although such data may not need to be standardized.

[0035] Described herein is a framework for the network to enable control and management of collecting non-standardized data by vendor servers external to the gNB (e.g., OTT server), which use this data to train their gNB-side models (as well as other LCM purposes such as monitoring, retraining, and updating) and for machine learning purposes generally. Considered herein is the positioning use case in the examples; however, the idea applies in general to any ML use case (e.g., CSI feedback, beam management, etc.) relying on gNB- side models.

[0036] In the term gNB may correspond to a gNB as well as different parts of a gNB, e.g., centralized unit (CU), distributed unit (DU), or transmission-reception point (TRP). For example, each TRP may utilize a different ML model, and the data collection may relate to each of them separately.

[0037] In the herein described method, a managing entity which is part of the 3GPP network first defines a non-standardized data collection policy for the data transfer that could take place between gNB and external server (mainly with regards to how and what can be transferred). For example, the network (e.g., the managing entity) may define a policy as “Xtype of measurements from a certain area / region of interest / cell / time can be shared with server of vendor Y”. In an example embodiment, the managing entity could be a trace collection entity (TCE), which is used for minimization of drive test (MDT).

[0038] Once the policy is agreed between the network entities and the external server; and based on the agreed data collection configurations, the non-standard data can be delivered to the external server, as described in the following.

[0039] After acquiring such policy, the external server sends its request for nonstandardized data collection to the network based on this policy, which may consist of: i) metadata field; ii) transparent container; and iii) PHY signaling requirements (optional).

[0040] The metadata field indicates any standardized information associated with the context of the non-standardized data, so as to enable the network control over the data collection as much as possible, such as type of requested data (e.g., measurements done using UL SRS), vendor information of the gNB / server, area / time-related information of the requested data, size of the requested data, etc. (see the next section for more detailed examples).

[0041] The transparent container contains the actual gNB-vendor / implementation- specific requirements / request for the non-standardized data collection, which is only visible to the gNB, and not necessarily to the network, e.g., a non-standard Doppler measurement request.

[0042] The PHY signaling requirements indicate standardized configuration information of signals associated with the requested data collection, such as UL SRS bandwidth, periodicity, etc. that would be necessary to collect non-standardized data, which the network can setup to assist collection of the non-standardized data. Note that the PHY signaling requirements is an optional field, and network may not be obliged to setup such required signaling configurations in the network for data collection. The collected data itself may be collected using the physical signaling configuration (e.g., by receiving and measuring the configured physical layer signal transmission).

[0043] The network then triggers any relevant data collection entities, e.g., LMF for positioning, based on the request, let the gNB know about the content of the actual request (i.e., by forwarding the transparent container), and optionally configures any necessary PHY signaling, e.g., transmission of UL signal or transmission (e.g. UL SRS) by UE(s) to enablenon- standardized data collection.

[0044] The gNB, after collecting the requested non- standardized data, provides the collected data via transparent container back to the external server via network, again accompanied by metadata complying with the data collection policy.

[0045] With the method described herein, the network gains control over the collection and transfer of non-standardized data without necessarily requiring access to the actual content of the collected data.

[0046] The signaling flow of the herein described method is illustrated in FIG. 1.

[0047] It is assumed that there exists a managing entity in the network for data collection. This entity could be a core network (CN) entity or function, e.g., for the positioning AI / ML use case it could be LMF, AMF, and / or NWDAF. Yet, for other AI / ML use cases, it could be a RAN node, e.g., gNB. This entity could be also (a part of) the 0AM, e.g., having control over CN and / or RAN. For the sake of generality, this is kept as a separate entity, different from LMF or gNB in the embodiments. There could be a single / centralized managing entity / network function for data collection that is responsible for all AI / ML related use cases, which may then communicate with respective entities for each use case, e.g., LMF for positioning.

[0048] Policy determination and provision (110): The managing entity 80 determines 112 the policy on non-standardized data collection (to be shared with external parties and / or one or more gNBs 70), which consists of at least one or more of the following (1-3):

[0049] 1. Allowed / disallowed data content that can be transferred (from gNB to the external server), e.g.: with respect to type of data (e.g., positioning measurements, CSI measurements, UL SRS measurements, time / angle / power / phase-based measurements, GNSS data, Bluetooth data, sensor data, etc.), information associated with measurements (e.g., allowed configuration information, etc.), with respect to area (e.g., notification area, geographical area, serving cell, etc.) that the collected data or UE / gNB belongs to, or with respect to vendor / device (manufacturer, hardware, software info) of involved gNB(s) / UE(s). Note: there might be (privacy / GDPR) agreements with different vendors in order to collect or share the data from the network, which might be used to determine the policy.

[0050] 2. The meta-data fields that gNB needs to indicate when transferring data, e.g.: type of measurement (as above), vendor / device info of gNB, timestamp info of data, location info of data (e.g., location of gNB), any session info that the data belongs to (e.g., certain LPP session for positioning), or characteristics of data, e.g., quality, likelihood, confidence level of estimation per sample, per dataset, etc.

[0051] 3. Whether a certain protocol (e.g., NRPPa) needs to be used when transferring the data, for example, when transferring positioning-related measurements, gNB must send it through LMF via NRPPa.

[0052] Note that the actual policy is up to implementation, and may be configured by the NWDAF, 0AM or network vendor. As a part of this configuration, any identifiers of the external servers, such as their IP addresses could be registered to control the data transfer to them.

[0053] The managing entity 80 provides this policy (116, 120) to the external server / vendor 82 and / or gNB 70, unsolicited or upon request (114, 118) from external server 82 and / or gNB 70, as well as provides notifications on any updates with regards to the policy. In an embodiment, the policy is provided to gNB 70 via a core network entity 90, e.g., LMF 99. In the embodiments where LMF 99 is the managing entity 80, it could provide such policy information to gNBs 70 via NRPPa.

[0054] In the embodiments, the order of the above steps might be different, e.g., first a request for a policy comes from an external server / vendor 82 and / or a gNB 70, or a UE 10, then the managing entity 80 determines a policy, which it could then provide the policy to the server / vendor 82 and / or the gNB 70.

[0055] The method includes data collection, which may include steps 1 through 6 below.

[0056] Step 1 (101): The external server 82 sends the request for data collection to the managing entity 80, containing at least one or more of the following (1-3):

[0057] 1. Metadata field indicates any standardized information associated with the nonstandardized data collection request, so as to enable the network control over the data collection as much as possible, such as: location / area / PLMN and ID of the gNB(s) 70 that are requested for data collection, type of requested data (e.g., UL SRS measurements, ULmeasurements, time / angle / power / phase-based measurements, etc.), vendor / device information (manufacturer, hardware, software info) of the entities involved in the requested data as well as of the requesting entity, area information (e.g., notification area, geographical area, serving cell of the UE 10, etc.) of the requested data, time -related information of the requested data, e.g., date, time frame, periodicity, on-demand / event-triggered, size of the requested data, e.g., number of measurements / samples, data volume, e.g., X gigabytes (GBs) or Y kilobytes (KBs), or data fragmentation configuration if data exceeds certain limits.

[0058] 2. Transparent container contains the actual gNB-vendor / implementation- specific requirements / request for the non-standardized data collection, which is only decodable by the gNB, and not necessarily to the network, e.g., a non-standard Doppler measurement request.

[0059] 3. PHY signaling requirements indicate standardized configuration information of signals associated with the requested data collection, such as UL SRS bandwidth, periodicity, etc. that would be necessary to collect non-standardized data, which the network can setup to assist collection of the non-standardized data. In an embodiment, QoS requirements for the related use case, e.g., positioning accuracy, could be also indicated, which could be further associated with or sent alternative to PHY signaling requirements. Note that this is an optional field, and network may not be obliged to setup such required signaling configurations in the network for data collection.

[0060] At 122, the managing entity 80 transmits to the vendor server 92 whether the managing entity 80 accepts or rejects the request sent at 101.

[0061] Step 2 (102): Upon receiving the request, managing entity 80 determines the involved network entities in the requested data, e.g., LMF 99 for positioning and gNB 70 for CSI feedback use cases of AI / ML respectively. For this, managing entity 80 can get information about serving EMF 99 and serving / neighboring gNB 70 of the involved UE(s) 10 from other CN entities, e.g., AMF. In an embodiment, the managing entity 80 may select the related network entities, e.g., gNBs 70, based on the metadata field of the request, such as depending on area information, vendor information, etc. For example, if the request relates to data collection from certain cell / area, the managing entity 80 then could select (a set of) gNB(s) 70 or LMF(s) 00 that are serving the requested area. In another embodiment, the managing entity may accept / reject the non-standardized data collection request coming from the external server before forwarding it to the other involved entities.

[0062] Step 3 (103): Depending on the policy, managing entity 80 informs the involved entities about the request. In an embodiment, it can forward the metadata of the request as well as the PHY signaling requirements to the determined network entities such as LMF, and it can forward the transparent container to the gNB(s).

[0063] Step 4 (104): Involved entities may configure required PHY signaling (124), depending on the requested information, e.g., LMF 99 may (at 128) configure UEs 10 to transmit UL SRS with certain characteristics (e.g., bandwidth, periodicity) so as to enable gNB 70 to collect (requested non- standardized) data. In the embodiments, the involved network entities may accept / reject the request coming from the managing entity, e.g., for PHY signaling, such as depending on their resource availability. In case the involved network entities configure PHY signaling different than the one indicated in the request, e.g., due to resource constraints (Example: server requires UL SRS transmission with 100 MHz, but LMF configures 50 MHz only), they may also indicate this difference to the managing entity 80, which could inform the external server 82 when providing the response in Step 6 (106).

[0064] At 126, the LMF 99 informs the managing entity 80 about the configuration, for example if the configuration is different from the request. At 130, the LMF 99 configures or triggers the gNB 70 for measurements, for example, the LMF 99 may provide to the gNB(s) 70 a UL SRS configuration. At 132, the managing entity 80 transmits to the LMF 99, or to the gNB 70 via the LMF, a transparent container carrying the non-standardized data request. At 134, the LMF 99 transmits to the gNB(s) 70 the transparent container carrying the nonstandardized data request.

[0065] Step 5 (105): The gNB 70, upon receiving the transparent container for the nonstandardized data request and any associated configurations for required PHY signaling, conducts data collection, e.g., measurements, e.g., if the requested data is not already available at the gNB 70.

[0066] Step 6 (106): gNB 70 provides the response to the data request with a container not necessary decodable by the network (but decodable by the external server and in some examples by the managing entity 80) that could contain the actual collected non-standardized data, as well as mandatory metadata fields complying with the policy. The metadata field may contain information as in the request for the data collection, e.g., describing the data content with standardized fields, or simply it may consist of ID / session information of the request.

[0067] At 136, the managing entity 80 forwards the requested data to the vendor server 82 (with metadata and a transparent container carrying non-standardized data) for gNB-side models.

[0068] In the embodiments, the gNB provides the data collection response directly to the managing entity, or first to the involved network entity, e.g., to LMF via NRPPa, which then provides it to the managing entity. The managing entity finally forwards the response to the external server, depending on its policy, e.g., by checking the information in the metadata fields.

[0069] A signaling flow for an alternative embodiment (for less NW involvement) is shown in FIG. 2.

[0070] In the alternative embodiment shown in FIG. 2, the external entity 82 sends the data collection request directly (201) to the involved gNB 70, in a transparent manner to the network. [Step 1 (201)].

[0071] As in the main embodiment, prior to (or after) Step 1, at 210, the network, i.e., managing entity 80, may determine and share the policy for non-standardized data collection with the external server 82 and / or gNB 70. In addition, the managing entity may also share the policy internally with the network entities, e.g., LMF. [Step 0 (200, 210)].

[0072] As in the main embodiment, the external server 82 may also indicate required PHY signaling for the data collection. In this embodiment, gNB 70 may request necessary configuration from the involved entities by itself, e.g., may configure / trigger UE 10 for UL SRS transmission, e.g., for CSI / beam management use cases. In an embodiment, gNB 10 may request necessary configuration from the network side, e.g., core network entities such as LMF (e.g., for positioning use case). [Step 2 (202)].

[0073] Step 2 (202) is optional. Alternatively, or in addition to Step 2 (202), gNB 70 may collect data whenever LMF 99 is triggering positioning a UE 10, e.g., using UL positioning methods. gNB 70 can then accumulate and store collected data across different positioning sessions, to be reported for the non-standardized data collection request.

[0074] As in the main embodiment, gNB 70 collects the requested non-standard data, if not already available. [Step 3 (203)] .

[0075] The gNB 70 then requests from the managing entity 80, permission to transfer the collected non-standard data to the external serve 82, by indicating the associated metadata fields with the collected as in the main embodiment [Step 4 (204-1)]. At 204-1, the managing entity 80 transmits to the gNB 70 an indication of whether the managing entity 80 accepts or rejects the request sent at 204-1.

[0076] In the embodiments, the gNB 70 may send the request first to the involved network entities, e.g., to LMF 99 via NRPPa in the case of positioning-related data. These entities may accept / reject the request based on the data collection policy that may be provided by the managing entity to these entities beforehand in Step 0 (200).

[0077] Step 4 (204- 1 , 204-2) is optional in the embodiments. Namely, the network may trust the gNB 70 or server 82 upon provision of the policy in Step 0 (200) and may not require further request for each data transfer individually (which could be indicated as a part of the policy - and can be (non-)acknowledged by the gNB 70 and / or server 82).

[0078] Based on the permission, gNB 70 transfers non-standard data to the external server 82 in a transparent manner to the network [Step 5 (205)].

[0079] FIG. 3 shows a block diagram of one possible and non-limiting example of a cellular network 1 that is connected to a user equipment (UE) 10. A number of network elements are shown in the cellular network of FIG. 3: a base station 70; and a core network 90.

[0080] In FIG. 3, a user equipment (UE) 10 is in wireless communication via radio link 11 with the base station 70 of the cellular network 1. A UE 10 is a wireless communication device, such as a mobile device, that is configured to access a cellular network. The UE 10 is illustrated with one or more antennas 28. The ellipses 2 indicate there could be multiple UEs 10 in wireless communication via radio links with the base station 70. The UE 10 includes one or more processors 13, one or more memories 15, and other circuitry 16. The other circuitry 16 includes one or more receivers (Rx(s)) 17 and one or more transmitters (Tx(s)) 18. A program 12 is used to cause the UE 10 to perform the operations described herein. For a UE 10, the other circuitry 16 could include circuitry such as for user interface elements (not shown) like a display.

[0081] The base station 70, as a network element of the cellular network 1, provides the UE 10 access to cellular network 1 and to the data network 91 via the core network 90 (e.g., viaa user plane function (UPF) of the core network 90). The base station 70 is illustrated as having one or more antennas 58. In general, the base station 70 is referred to as RAN node 70 herein. An example of a RAN node 70 is a gNB. There are, however, many other examples of RAN nodes including an eNB (LTE base station) or transmission reception point (TRP). The base station 70 includes one or more processors 73, one or more memories 75, and other circuitry 76. The other circuitry 76 includes one or more receivers (Rx(s)) 77 and one or more transmitters (Tx(s)) 78. A program 72 is used to cause the base station 70 to perform the operations described herein.

[0082] It is noted that the base station 70 may instead be implemented via other wireless technologies, such as Wi-Fi (a wireless networking protocol that devices use to communicate without direct cable connections). In the case of Wi-Fi, the link 11 could be characterized as a wireless link.

[0083] Two or more base stations 70 communicate using, e.g., link(s) 79. The link(s) 79 may be wired or wireless or both and may implement, e.g., an Xn interface for fifth generation (5G), an X2 interface for LTE, or other suitable interface for other standards.

[0084] The cellular network 1 may include a core network 90, as a third illustrated element or elements, that may include core network functionality, and which provide connectivity via a link or links 81 with a data network 91, such as a telephone network and / or a data communications network (e.g., the Internet). The core network 90 includes one or more processors 93, one or more memories 95, and other circuitry 96. The other circuitry 96 includes one or more receivers (Rx(s)) 97 and one or more transmitters (Tx(s)) 98. A program 92 is used to cause the core network 90 to perform the operations described herein.

[0085] The core network 90 could be a 5GC (5G core network). The core network 90 can implement or comprise multiple network functions (NF(s)) 99, and the program 92 may comprise one or more of the NFs 99. A 5G core network may use hardware such as memory and processors and a virtualization layer. It could be a single standalone computing system, a distributed computing system, or a cloud computing system. The NFs 99, as network elements, of the core network could be containers or virtual machines running on the hardware of the computing system(s) making up the core network 90.

[0086] Core network functionality for 5G may include access and mobility management functionality that is provided by a network function 99 such as an access and mobilitymanagement function (AMF(s)), session management functionality that is provided by a network function such as a session management function (SMF). Core network functionality for access and mobility management in an LTE network may be provided by an MME (Mobility Management Entity) and / or SGW (Serving Gateway) functionality, which routes data to the data network. Many others are possible, as illustrated by the examples in FIG. 3: AMF; SMF; MME; SGW; gateway mobile location center (GMLC); location management functions (LMFs); unified data management (UDM); unified data repository (UDR); network repository function (NRF); and / or evolved serving mobile location center (E-SMLC). These are merely exemplary core network functionality that may be provided by the core network 90, and note that both 5G and LTE core network functionality might be provided by the core network 90. The radio access network (RAN) node 70 is coupled via a backhaul link 31 to the core network 90. The RAN node 70 and the core network 90 may include an NG interface for 5G, or an SI interface for LTE, or other suitable interface for other radio access technologies for communicating via the backhaul link 31.

[0087] In the data network 91, there is a computer-readable medium 94. The computer- readable medium 94 contains instructions that, when downloaded and installed into the memories 15, 75, or 95 of the corresponding UE 10, base station 70, and / or core network element(s) 90, and executed by processor(s) 13, 73, or 93, cause the respective device to perform corresponding actions described herein. The computer-readable medium 94 may be implemented in other forms, such as via a compact disc or memory stick.

[0088] The programs 12, 72, and 92 contain instructions stored by corresponding one or more memories 15, 75, or 95. These instructions, when executed by the corresponding one or more processors 13, 73, or 93, cause the corresponding apparatus 10, 70, or 90, to perform the operations described herein. The computer readable memories 15, 75, or 95 may be of any type suitable to the local technical environment and may be implemented using any suitable data storage technology, such as semiconductor-based memory devices, flash memory, firmware, magnetic memory devices and systems, optical memory devices and systems, fixed memory and removable memory. The computer readable memories 15, 75, and 95 may be means for performing storage functions. The processors 13, 73, and 93, may be of any type suitable to the local technical environment, and may include one or more of general- purpose computers, special purpose computers, microprocessors, digital signal processors (DSPs) and processors based on a multi-core processor architecture, as non-limitingexamples. The processors 13, 73, and 93 may be means for causing their respective apparatus to perform functions, such as those described herein.

[0089] The receivers 17, 77, and 97, and the transmitters 18, 78, and 98 may implement wired or wireless interfaces. The receivers and transmitters may be grouped together as transceivers.

[0090] FIG. 4 is an example apparatus 400, which may be implemented in hardware, configured to implement the examples described herein. The apparatus 400 comprises at least one processor 402 (e.g. an FPGA and / or CPU), one or more memories 404 including computer program code 405, the computer program code 405 having instructions to carry out the methods described herein, wherein the at least one memory 404 and the computer program code 405 are configured to, with the at least one processor 402, cause the apparatus 400 to implement circuitry, a process, component, module, or function (implemented with control module 406) to implement the examples described herein, including network control of nonstandardized AI / ML data collection for gNB-side models. The memory 404 may be a non- transitory memory, a transitory memory, a volatile memory (e.g. RAM), or a non-volatile memory (e.g. ROM). Data collection 430 of the control module implements the herein described aspects related to network control of non-standardized AI / ML data collection for gNB-side models.

[0091] The apparatus 400 includes a display and / or RO interface 408, which includes user interface (UI) circuitry and elements, that may be used to display aspects or a status of the methods described herein (e.g., as one of the methods is being performed or at a subsequent time), or to receive input from a user such as with using a keypad, camera, touchscreen, touch area, microphone, biometric recognition, one or more sensors, etc. The apparatus 400 includes one or more communication e.g. network (N / W) interfaces (I / F(s)) 410. The communication I / F(s) 410 may be wired and / or wireless and communicate over the Internet / other network(s) via any communication technique including via one or more links 424. The link(s) 424 may be the link(s) 11 and / or 79 and / or 31 and / or 81 from FIG. 3. The link(s) 11 and / or 79 and / or 31 and / or 81 from FIG. 3 may also be implemented using transceiver(s) 416 and corresponding wireless link(s) 426. The communication I / F(s) 410 may comprise one or more transmitters or one or more receivers.

[0092] The transceiver 416 comprises one or more transmitters 418 and one or morereceivers 420. The transceiver 416 and / or communication I / F(s) 410 may comprise standard well-known components such as an amplifier, filter, frequency-converter, (de)modulator, and encoder / decoder circuitries and one or more antennas, such as antennas 414 used for communication over wireless link 426.

[0093] The control module 406 of the apparatus 400 comprises one of or both parts 406-1 and / or 406-2, which may be implemented in a number of ways. The control module 406 may be implemented in hardware as control module 406-1, such as being implemented as part of the one or more processors 402. The control module 406-1 may be implemented also as an integrated circuit or through other hardware such as a programmable gate array. In another example, the control module 406 may be implemented as control module 406-2, which is implemented as computer program code (having corresponding instructions) 405 and is executed by the one or more processors 402. For instance, the one or more memories 404 store instructions that, when executed by the one or more processors 402, cause the apparatus 400 to perform one or more of the operations as described herein. Furthermore, the one or more processors 402, the one or more memories 404, and example algorithms (e.g., as flowcharts and / or signaling diagrams), encoded as instructions, programs, or code, are means for causing performance of the operations described herein.

[0094] The apparatus 400 to implement the functionality of control 406 may be UE 10, base station 70 (e.g. gNB 70), or core network 90 including any of the network functions 99 such as LMF 99, which network functions 99 may be implemented with a network entity. Thus, processor 402 may correspond to processor(s) 13, processor(s) 73 and / or processor(s) 93, memory 404 may correspond to one or more memories 15, one or more memories 75 and / or one or more memories 95, computer program code 405 may correspond to program 12, program 72, or program 92, communication I / F(s) 410 and / or transceiver 416 may correspond to other circuitry 16, other circuitry 76, or other circuitry 96, and antennas 414 may correspond to antennas 28 or antennas 58.

[0095] Alternatively, apparatus 400 and its elements may not correspond to either of UE 10, base station 70, or core network and their respective elements, as apparatus 400 may be part of a self-organizing / optimizing network (SON) node or other node, such as a node in a cloud. Apparatus 400 may also correspond to managing entity 80 or vendor server 82. Managing entity 80 may be a network entity of the core network 90. Apparatus 400 may also correspond to a centralized unit (CU) of a base station (e.g. base station 70) or distributed unit(DU) of the base station 70.

[0096] The apparatus 400 may also be distributed throughout the network (e.g. 91) including within and between apparatus 400 and any network element (such as core network 90 and / or the base station 70 and / or the UE 10).

[0097] Interface 412 enables data communication and signaling between the various items of apparatus 400, as shown in FIG. 4. For example, the interface 412 may be one or more buses such as address, data, or control buses, and may include any interconnection mechanism, such as a series of lines on a motherboard or integrated circuit, fiber optics or other optical communication equipment, and the like. Computer program code (e.g. instructions) 405, including control 406 may comprise object-oriented software configured to pass data or messages between objects within computer program code 405. The apparatus 400 need not comprise each of the features mentioned, or may comprise other features as well. The various components of apparatus 400 may at least partially reside in a common housing 428, or a subset of the various components of apparatus 400 may at least partially be located in different housings, which different housings may include housing 428.

[0098] FIG. 5 shows a schematic representation of non-volatile memory media 500a (e.g. computer / compact disc (CD) or digital versatile disc (DVD)) and 500b (e.g. universal serial bus (USB) memory stick) and 500c (e.g. cloud storage for downloading instructions and / or parameters 502 or receiving emailed instructions and / or parameters 502) storing instructions and / or parameters 502 which when executed by a processor allows the processor to perform one or more of the steps of the methods described herein.

[0099] FIG. 6 is an example method 600, based on the example embodiments described herein. At 610, the method includes determining a policy for collection of data and transfer of data for machine learning purposes. At 620, the method includes receiving, from a server, a request for the collection of the data. At 630, the method includes determining at least one network entity related to the request for the collection of the data. At 640, the method includes receiving, from the at least one network entity, collected data associated with the request within a container decodable by the server, based on the policy. At 650, the method includes transmitting, to the server, the container decodable by the server comprising the collected data. Method 600 may be performed by managing entity 80, a network entity implementing a network function 99 of the core network 90, or apparatus 400.

[0100] FIG. 7 is an example method 700, based on the example embodiments described herein. At 710, the method includes performing at least one of: receiving, from at least one network entity or a server, a container decodable by the apparatus, wherein the container comprises a request addressed to the apparatus for collection of data associated with machine learning purposes, or receiving, directly from the server, the request for collection of data associated with machine learning purposes without the container. At 720, the method includes collecting the data. At 730, the method includes performing at least one of: transmitting, to at least one network entity or directly to the server, the collected data associated with the request within a container decodable by the server that requested the data, or transmitting, directly to the server, the collected data associated with the request. Method 700 may be performed by network node 70 (e.g. a gNB) or apparatus 400.

[0101] FIG. 8 is an example method 800, based on the example embodiments described herein. At 810, the method includes transmitting, to a management entity or to at least one network entity, a request for collection of data for machine learning purposes. At 820, the method includes performing at least one of: receiving, from the management entity or the at least one network entity, collected data associated with the request within a container decodable by the apparatus, or receiving, from the at least one network entity, the collected data associated with the request. Method 800 may be performed by external vendor server 82, a network entity implementing a network function 99 of the core network 90, or apparatus 400.

[0102] FIG. 9 is an example method 900, based on the example embodiments described herein. At 910, the method includes receiving, from a management entity, a request for data associated with machine learning purposes. At 920, the method includes wherein the request is associated with a container decodable by at least one network entity. At 930, the method includes transmitting, to the at least one network entity, the container decodable by the at least one network entity comprising a request addressed to the at least one network entity for collection of the data. At 940, the method includes receiving, from the at least one network entity, the collected data associated with the request within a container decodable by a server. At 950, the method includes transmitting, to the management entity or directly to the server, the collected data associated with the request within the container decodable by the server. Method 900 may be performed by LMF 99 or apparatus 400.

[0103] FIG. 10 is an example method 1000, based on the example embodiments describedherein. At 1010, the method includes receiving, from at least one network entity or a location management function, a configuration to transmit at least one uplink signal or transmission, based on a configuration of physical signaling. At 1020, the method includes transmitting the at least one uplink signal or transmission to the at least one network entity, based on the configuration of physical signaling. At 1030, the method includes wherein the at least one uplink signal or transmission is configured to be used with the at least one network entity to collect non-standardized data related to machine learning purposes. Method 1000 may be performed by user equipment (UE) 10 or apparatus 400.

[0104] FIG. 11 shows an example overall message or request 1110 sent by the server 82. The overall message or request 1110 includes or is associated with a container 1140 carrying the information requesting or configuring gNB 70 for non-standardized data collection. The container 1140 carries a non-standardized data collection request or configuration, and the container 1140 is decodable by the gNB 70 and the sever 82. The container 1140 is not necessarily visible or decodable by the network. For example, the container 1140 may or may not be decodable by EMF 99, managing entity 80, or UE 10. The request 1110 may correspond to the request sent at 101 by the vendor server 82 in FIG. 1, or to the request sent at 201 by the vendor server in FIG. 2. As shown in FIG. 11, the overall request sent by the server 1110 includes or is associated with metadata fields decodable by the network 1120, and physical signaling requirements decodable by the network 1130.

[0105] The following examples are provided and described herein.

[0106] Example 1. An apparatus including: at least one processor; and at least one memory storing instructions that, when executed by the at least one processor, cause the apparatus at least to: determine a policy for collection of data and transfer of data for machine learning purposes; receive, from a server, a request for the collection of the data; determine at least one network entity related to the request for the collection of the data; receive, from the at least one network entity, collected data associated with the request within a container decodable by the server, based on the policy; and transmit, to the server, the container decodable by the server comprising the collected data.

[0107] Example 2. The apparatus of example 1, wherein the instructions, when executed by the at least one processor, cause the apparatus at least to receive information associated with the request for the collection of the data, wherein the information comprises at least one ormore of: metadata that indicates standardized information associated with the request for the collection of the data, or a container decodable by the at least one network entity configured to collect the data, wherein the container decodable by the at least one network entity comprises at least one non-standardized requirement specific to the at least one network entity related to the request for the collection of the data, or at least one physical signaling requirement that indicates standardized configuration information of signaling associated with the request for the collection of data.

[0108] Example 3. The apparatus of example 2, wherein the instructions, when executed by the at least one processor, cause the apparatus at least to: transmit, to the at least one network entity, the container decodable by the at least one network entity; wherein the container decodable by the at least one network entity comprises a request addressed to the at least one network entity for the collection of data.

[0109] Example 4. The apparatus of any of examples 2 to 3, wherein the instructions, when executed by the at least one processor, cause the apparatus at least to: transmit, to the at least one network entity, the at least one physical signaling requirement that indicates the standardized configuration information of signaling associated with the request for the collection of data.

[0110] Example 5. The apparatus of example 4, wherein the collected data received from the at least one network entity is collected based on the at least one physical signaling requirement transmitted to the at least one network entity.

[0111] Example 6. The apparatus of any of examples 4 to 5, wherein the instructions, when executed by the at least one processor, cause the apparatus at least to: receive, from the at least one network entity, an indication of a determined configuration of physical signaling.

[0112] Example 7. The apparatus of example 6, wherein the indication of the determined configuration of physical signaling is received from the at least one network entity in response to the determined configuration of physical signaling being different from the at least one physical signaling requirement transmitted to the at least one network entity.

[0113] Example 8. The apparatus of any of examples 2 to 7, wherein: the container decodable by the server is the same as or a representation of the container decodable by the at least one network entity, or the container decodable by the server is different from thecontainer decodable by the at least one network entity.

[0114] Example 9. The apparatus of any of examples 1 to 8, wherein the instructions, when executed by the at least one processor, cause the apparatus at least to: transmit, to the at least one network entity, a configuration of physical signaling; and wherein the collected data received from the at least one network entity is collected based on the configuration of physical signaling transmitted to the at least one network entity.

[0115] Example 10. The apparatus of any of examples 1 to 9, wherein the instructions, when executed by the at least one processor, cause the apparatus at least to: determine whether to accept or reject the request for the collection of data; and transmit, to the server, an indication of the determining to accept or reject the request for the collection of data.

[0116] Example 11. The apparatus of any of examples 1 to 10, wherein the instructions, when executed by the at least one processor, cause the apparatus at least to: transmit, to the at least one network entity, the request for the collection of data.

[0117] Example 12. The apparatus of any of examples 1 to 11, wherein the instructions, when executed by the at least one processor, cause the apparatus at least to: transmit, to the at least one network entity or to the server, an indication of the policy for collection of data and transfer of data for the machine learning purposes.

[0118] Example 13. The apparatus of example 12, wherein the instructions, when executed by the at least one processor, cause the apparatus at least to: receive, from the at least one network entity or the server, a request to indicate the policy.

[0119] Example 14. The apparatus of any of examples 1 to 13, wherein the instructions, when executed by the at least one processor, cause the apparatus at least to: receive, from the at least one network entity, a request for permission to transfer the collected data; and transmit, to the at least one network entity, an indication that the permission to transfer the collected data is granted or denied.

[0120] Example 15. The apparatus of any of examples 1 to 14, wherein the at least one network entity comprises a location management function, a base station, or a gNB.

[0121] Example 16. The apparatus of any of examples 1 to 15, wherein the collected data comprises non-standardized data associated with the machine learning purposes.

[0122] Example 17. The apparatus of example 16, wherein the machine learning purposes are associated with the at least one network entity.

[0123] Example 18. The apparatus of any of examples 1 to 17, wherein the apparatus comprises a trace collection entity used for minimization of drive test.

[0124] Example 19. The apparatus any of examples 1 to 18, wherein the container decodable by the server is decodable by the apparatus.

[0125] Example 20. The apparatus of any of examples 1 to 19, wherein the container decodable by the server is not decodable by at least one network node.

[0126] Example 21. The apparatus of any of examples 1 to 20, wherein the apparatus comprises a management entity.

[0127] Example 22. An apparatus including: at least one processor; and at least one memory storing instructions that, when executed by the at least one processor, cause the apparatus at least to: perform at least one of: receive, from at least one network entity or a server, a container decodable by the apparatus, wherein the container comprises a request addressed to the apparatus for collection of data associated with machine learning purposes, or receive, directly from the server, the request for collection of data associated with machine learning purposes without the container; collect the data; and perform at least one of: transmit, to at least one network entity or directly to the server, the collected data associated with the request within a container decodable by the server that requested the data, or transmit, directly to the server, the collected data associated with the request.

[0128] Example 23. The apparatus of example 22, wherein the at least one network entity comprises a location management function, or a management entity.

[0129] Example 24. The apparatus of any of examples 22 to 23, wherein the at least one network entity comprises a trace collection entity used for minimization of drive test.

[0130] Example 25. The apparatus of any of examples 22 to 24, wherein: the container decodable by the server is the same as or a representation of the container decodable by the apparatus, or the container decodable by the server is different from the container decodable by the apparatus.

[0131] Example 26. The apparatus of any of examples 22 to 25, wherein the instructions, when executed by the at least one processor, cause the apparatus at least to: receive, from the at least one network entity, a configuration of physical signaling associated with the request.

[0132] Example 27. The apparatus of any of examples 22 to 26, wherein the collected data transmitted to the at least one network entity is collected based on the configuration of physical signaling.

[0133] Example 28. The apparatus of any of examples 22 to 27, wherein the instructions, when executed by the at least one processor, cause the apparatus at least to: receive, from the at least one network entity, an indication of a policy for collection of data and transfer of data for the machine learning purposes, wherein the at least one network entity comprises a management entity.

[0134] Example 29. The apparatus of example 28, wherein the collecting of the data is based on the policy, and the transmitting of the collected data to the at least one network entity or directly to the server is based on the policy.

[0135] Example 30. The apparatus of any of examples 28 to 29, wherein the instructions, when executed by the at least one processor, cause the apparatus at least to: transmit, to the management entity, a request to indicate the policy for collection of data and transfer of data for the machine learning purposes.

[0136] Example 31. The apparatus of any of examples 22 to 30, wherein the instructions, when executed by the at least one processor, cause the apparatus at least to: transmit, to a management entity or a location management function, a request for permission to transfer the collected data; and receive, from the management entity or the location management function, an indication that the permission to transfer the collected data is granted or denied.

[0137] Example 32. The apparatus of any of examples 22 to 31, wherein the instructions, when executed by the at least one processor, cause the apparatus at least to: receive, from a location management function, a configuration to perform at least one measurement related to the collection of data, based on a configuration of physical signaling; and perform the at least one measurement based on the configuration of physical signaling, wherein the collected data is based on the at least one measurement.

[0138] Example 33. The apparatus of any of examples 22 to 32, wherein the instructions, when executed by the at least one processor, cause the apparatus at least to: configure a user equipment to transmit at least one uplink signal or transmission, based on a configuration of physical signaling; and receive the at least one uplink signal or transmission based on the configuration of physical signaling.

[0139] Example 34. The apparatus of example 33, wherein the uplink signal or transmission comprises an uplink sounding reference signal.

[0140] Example 35. The apparatus of any of examples 22 to 34, wherein the collected data comprises non-standardized data associated with the machine learning purposes.

[0141] Example 36. The apparatus of any of examples 22 to 35, wherein the instructions, when executed by the at least one processor, cause the apparatus at least to: transmit, to the at least one network entity or directly to the server, standardized data associated with the machine learning purposes.

[0142] Example 37. The apparatus of any of examples 22 to 36, wherein the apparatus comprises a base station or a gNB.

[0143] Example 38. An apparatus including: at least one processor; and at least one memory storing instructions that, when executed by the at least one processor, cause the apparatus at least to: transmit, to a management entity or to at least one network entity, a request for collection of data for machine learning purposes; and perform at least one of: receive, from the management entity or the at least one network entity, collected data associated with the request within a container decodable by the apparatus, or receive, from the at least one network entity, the collected data associated with the request.

[0144] Example 39. The apparatus of example 38, wherein the instructions, when executed by the at least one processor, cause the apparatus at least to transmit, to the management entity or to the at least one network entity, information associated with the request for the collection of the data, wherein the information comprises at least one or more of: metadata that indicates standardized information associated with the request for the collection of data, or a container decodable by the at least one network entity configured to collect the data, wherein the container decodable by the at least one network entity comprises at least one non-standardized requirement specific to the at least one network entity related to the request for the collectionof the data, or at least one physical signaling requirement that indicates standardized configuration information of signaling associated with the request for the collection of data.

[0145] Example 40. The apparatus of example 39, wherein: the container decodable by the apparatus is the same as or a representation of the container decodable by the at least one network entity, or the container decodable by the apparatus is different from the container decodable by the at least one network entity.

[0146] Example 41. The apparatus of any of examples 38 to 40, wherein the instructions, when executed by the at least one processor, cause the apparatus at least to: receive, from the management entity or the at least one network entity, an indication of whether the request was accepted or rejected.

[0147] Example 42. The apparatus of any of examples 38 to 41, wherein the instructions, when executed by the at least one processor, cause the apparatus at least to: transmit, to the management entity, a request to indicate a policy for collection of data and transfer of data for the machine learning purposes; and receive, from the management entity, an indication of the policy for collection of data and transfer of data for the machine learning purposes; wherein the request for collection of data for the machine learning purposes associated with the at least one network entity is based on the policy.

[0148] Example 43. The apparatus of any of examples 38 to 42, wherein the collected data comprises non-standardized data associated with the machine learning purposes associated with the at least one network entity.

[0149] Example 44. The apparatus of example 43, wherein the instructions, when executed by the at least one processor, cause the apparatus at least to: receive, from the management entity or the at least one network entity, standardized data associated with the machine learning purposes associated with the at least one network entity.

[0150] Example 45. The apparatus of any of examples 38 to 44, wherein the apparatus comprises an external vendor server.

[0151] Example 46. An apparatus including: at least one processor; and at least one memory storing instructions that, when executed by the at least one processor, cause the apparatus at least to: receive, from a management entity, a request for data associated with machinelearning purposes; wherein the request is associated with a container decodable by at least one network entity; transmit, to the at least one network entity, the container decodable by the at least one network entity comprising a request addressed to the at least one network entity for collection of the data; receive, from the at least one network entity, the collected data associated with the request within a container decodable by a server; and transmit, to the management entity or directly to the server, the collected data associated with the request within the container decodable by the server.

[0152] Example 47. The apparatus of example 46, wherein: the container decodable by the at least one network entity is the same as or a representation of the container decodable by the server, or the container decodable by the at least one network entity is different from the container decodable by the server.

[0153] Example 48. The apparatus of any of examples 46 to 47, wherein the instructions, when executed by the at least one processor, cause the apparatus at least to: receive, from the management entity, a configuration of physical signaling associated with the request.

[0154] Example 49. The apparatus of any of examples 46 to 48, wherein the instructions, when executed by the at least one processor, cause the apparatus at least to: determine a configuration of physical signaling, based on the request.

[0155] Example 50. The apparatus of example 49, wherein the instructions, when executed by the at least one processor, cause the apparatus at least to: transmit, to the management entity, an indication of the determined configuration of physical signaling.

[0156] Example 51. The apparatus of example 50, wherein the instructions, when executed by the at least one processor, cause the apparatus at least to: receive, from the management entity, a configuration of physical signaling associated with the request; wherein the indication of the determined configuration of physical signaling is transmitted to the management entity in response to the determined configuration of physical signaling being different from the received configuration of physical signaling.

[0157] Example 52. The apparatus of any of examples 49 to 51, wherein the instructions, when executed by the at least one processor, cause the apparatus at least to: configure the at least one network entity to perform at least one measurement, based on the determined configuration of physical signaling; and configure a user equipment to transmit at least oneuplink signal or transmission, based on the determined configuration of physical signaling.

[0158] Example 53. The apparatus of example 52, wherein the at least one uplink signal or transmission comprises an uplink sounding reference signal.

[0159] Example 54. The apparatus of any of examples 46 to 53, wherein the collected data comprises non-standardized data associated with the machine learning purposes.

[0160] Example 55. The apparatus of any of examples 46 to 54, wherein the container decodable by the at least one network entity is decodable by the management entity.

[0161] Example 56. The apparatus of any of examples 46 to 55, wherein the container decodable by the server is decodable by the management entity.

[0162] Example 57. The apparatus of any of examples 46 to 56, wherein the apparatus comprises a location management function.

[0163] Example 58. An apparatus including: at least one processor; and at least one memory storing instructions that, when executed by the at least one processor, cause the apparatus at least to: receive, from at least one network entity or a location management function, a configuration to transmit at least one uplink signal or transmission, based on a configuration of physical signaling; and transmit the at least one uplink signal or transmission to the at least one network entity, based on the configuration of physical signaling; wherein the at least one uplink signal or transmission is configured to be used with the at least one network entity to collect non-standardized data related to machine learning purposes.

[0164] Example 59. The apparatus of example 58, wherein the configuration of physical signaling comprises at least one or more of: a bandwidth of the at least one uplink signal or transmission, or a periodicity for transmission of the at least one uplink signal or transmission.

[0165] Example 60. The apparatus of any of examples 58 to 59, wherein the uplink signal or transmission comprises an uplink sounding reference signal.

[0166] Example 61. The apparatus of any of examples 58 to 60, wherein the apparatus comprises a user equipment.

[0167] Example 62. A method including: determining a policy for collection of data and transfer of data for machine learning purposes; receiving, from a server, a request for thecollection of the data; determining at least one network entity related to the request for the collection of the data; receiving, from the at least one network entity, collected data associated with the request within a container decodable by the server, based on the policy; and transmitting, to the server, the container decodable by the server comprising the collected data.

[0168] Example 63. A method including: performing at least one of: receiving, from at least one network entity or a server, a container decodable by the apparatus, wherein the container comprises a request addressed to the apparatus for collection of data associated with machine learning purposes, or receiving, directly from the server, the request for collection of data associated with machine learning purposes without the container; collecting the data; and performing at least one of: transmitting, to at least one network entity or directly to the server, the collected data associated with the request within a container decodable by the server that requested the data, or transmitting, directly to the server, the collected data associated with the request.

[0169] Example 64. A method including: transmitting, to a management entity or to at least one network entity, a request for collection of data for machine learning purposes; and performing at least one of: receiving, from the management entity or the at least one network entity, collected data associated with the request within a container decodable by the apparatus, or receiving, from the at least one network entity, the collected data associated with the request.

[0170] Example 65. A method including: receiving, from a management entity, a request for data associated with machine learning purposes; wherein the request is associated with a container decodable by at least one network entity; transmitting, to the at least one network entity, the container decodable by the at least one network entity comprising a request addressed to the at least one network entity for collection of the data; receiving, from the at least one network entity, the collected data associated with the request within a container decodable by a server; and transmitting, to the management entity or directly to the server, the collected data associated with the request within the container decodable by the server.

[0171] Example 66. A method including: receiving, from at least one network entity or a location management function, a configuration to transmit at least one uplink signal or transmission, based on a configuration of physical signaling; and transmitting the at least oneuplink signal or transmission to the at least one network entity, based on the configuration of physical signaling; wherein the at least one uplink signal or transmission is configured to be used with the at least one network entity to collect non-standardized data related to machine learning purposes.

[0172] Example 67. An apparatus including: means for determining a policy for collection of data and transfer of data for machine learning purposes; means for receiving, from a server, a request for the collection of the data; means for determining at least one network entity related to the request for the collection of the data; means for receiving, from the at least one network entity, collected data associated with the request within a container decodable by the server, based on the policy; and means for transmitting, to the server, the container decodable by the server comprising the collected data.

[0173] Example 68. An apparatus including: means for performing at least one of: receiving, from at least one network entity or a server, a container decodable by the apparatus, wherein the container comprises a request addressed to the apparatus for collection of data associated with machine learning purposes, or receiving, directly from the server, the request for collection of data associated with machine learning purposes without the container; means for collecting the data; and means for performing at least one of: transmitting, to at least one network entity or directly to the server, the collected data associated with the request within a container decodable by the server that requested the data, or transmitting, directly to the server, the collected data associated with the request.

[0174] Example 69. An apparatus including: means for transmitting, to a management entity or to at least one network entity, a request for collection of data for machine learning purposes; and means for performing at least one of: receiving, from the management entity or the at least one network entity, collected data associated with the request within a container decodable by the apparatus, or receiving, from the at least one network entity, the collected data associated with the request.

[0175] Example 70. An apparatus including: means for receiving, from a management entity, a request for data associated with machine learning purposes; wherein the request is associated with a container decodable by at least one network entity; means for transmitting, to the at least one network entity, the container decodable by the at least one network entity comprising a request addressed to the at least one network entity for collection of the data;means for receiving, from the at least one network entity, the collected data associated with the request within a container decodable by a server; and means for transmitting, to the management entity or directly to the server, the collected data associated with the request within the container decodable by the server.

[0176] Example 71. An apparatus including: means for receiving, from at least one network entity or a location management function, a configuration to transmit at least one uplink signal or transmission, based on a configuration of physical signaling; and means for transmitting the at least one uplink signal or transmission to the at least one network entity, based on the configuration of physical signaling; wherein the at least one uplink signal or transmission is configured to be used with the at least one network entity to collect non-standardized data related to machine learning purposes.

[0177] Example 72. A non-transitory program storage device readable by a machine, tangibly embodying a program of instructions executable by the machine for performing operations, the operations including: determining a policy for collection of data and transfer of data for machine learning purposes; receiving, from a server, a request for the collection of the data; determining at least one network entity related to the request for the collection of the data; receiving, from the at least one network entity, collected data associated with the request within a container decodable by the server, based on the policy; and transmitting, to the server, the container decodable by the server comprising the collected data.

[0178] Example 73. A non-transitory program storage device readable by a machine, tangibly embodying a program of instructions executable by the machine for performing operations, the operations including: performing at least one of: receiving, from at least one network entity or a server, a container decodable by the apparatus, wherein the container comprises a request addressed to the apparatus for collection of data associated with machine learning purposes, or receiving, directly from the server, the request for collection of data associated with machine learning purposes without the container; collecting the data; and performing at least one of: transmitting, to at least one network entity or directly to the server, the collected data associated with the request within a container decodable by the server that requested the data, or transmitting, directly to the server, the collected data associated with the request.

[0179] Example 74. A non-transitory program storage device readable by a machine,tangibly embodying a program of instructions executable by the machine for performing operations, the operations including: transmitting, to a management entity or to at least one network entity, a request for collection of data for machine learning purposes; and performing at least one of: receiving, from the management entity or the at least one network entity, collected data associated with the request within a container decodable by the apparatus, or receiving, from the at least one network entity, the collected data associated with the request.

[0180] Example 75. A non-transitory program storage device readable by a machine, tangibly embodying a program of instructions executable by the machine for performing operations, the operations including: receiving, from a management entity, a request for data associated with machine learning purposes; wherein the request is associated with a container decodable by at least one network entity; transmitting, to the at least one network entity, the container decodable by the at least one network entity comprising a request addressed to the at least one network entity for collection of the data; receiving, from the at least one network entity, the collected data associated with the request within a container decodable by a server; and transmitting, to the management entity or directly to the server, the collected data associated with the request within the container decodable by the server.

[0181] Example 76. A non-transitory program storage device readable by a machine, tangibly embodying a program of instructions executable by the machine for performing operations, the operations including: receiving, from at least one network entity or a location management function, a configuration to transmit at least one uplink signal or transmission, based on a configuration of physical signaling; and transmitting the at least one uplink signal or transmission to the at least one network entity, based on the configuration of physical signaling; wherein the at least one uplink signal or transmission is configured to be used with the at least one network entity to collect non-standardized data related to machine learning purposes.

[0182] References to a ‘computer’, ‘processor’, etc. should be understood to encompass not only computers having different architectures such as single / multi-processor architectures and sequential or parallel architectures but also specialized circuits such as field- programmable gate arrays (FPGAs), application specific circuits (ASICs), signal processing devices and other processing circuitry. References to computer program, instructions, code etc. should be understood to encompass software for a programmable processor or firmware such as, for example, the programmable content of a hardware device whether instructionsfor a processor, or configuration settings for a fixed-function device, gate array or programmable logic device etc.

[0183] The memories as described herein may be implemented using any suitable data storage technology, such as semiconductor based memory devices, flash memory, magnetic memory devices and systems, optical memory devices and systems, non-transitory memory, transitory memory, fixed memory and removable memory. The memories may comprise a database for storing data.

[0184] As used herein, the term ‘circuitry’ may refer to the following: (a) hardware circuit implementations, such as implementations in analog and / or digital circuitry, and (b) combinations of circuits and software (and / or firmware), such as (as applicable): (i) a combination of processor(s) or (ii) portions of processor(s) / software including digital signal processor(s), software, and memories that work together to cause an apparatus to perform various functions, and (c) circuits, such as a microprocessor(s) or a portion of a microprocessor(s), that require software or firmware for operation, even if the software or firmware is not physically present. As a further example, as used herein, the term ‘circuitry’ would also cover an implementation of merely a processor (or multiple processors) or a portion of a processor and its (or their) accompanying software and / or firmware. The term ‘circuitry’ would also cover, for example and if applicable to the particular element, a baseband integrated circuit or applications processor integrated circuit for a mobile phone or a similar integrated circuit in a server, a cellular network device, or another network device.

[0185] It should be understood that the foregoing description is only illustrative. Various alternatives and modifications may be devised by those skilled in the art. For example, features recited in the various dependent claims could be combined with each other in any suitable combination(s). In addition, features from different example embodiments described above could be selectively combined into a new example embodiment. Accordingly, this description is intended to embrace all such alternatives, modifications and variances which fall within the scope of the appended claims.

[0186] The following acronyms and abbreviations that may be found in the specification and / or the drawing figures are given as follows (the abbreviations and acronyms may be appended with each other or with other characters using e.g. a dash, hyphen, slash, or number, and may be case insensitive):3GPP third generation partnership project4G fourth generation5G fifth generation5GC 5G core networkAl artificial intelligenceAMF access and mobility management functionASIC application- specific integrated circuitCD compact / computer discCN core networkCPU central processing unitCSI channel state informationCT core network and terminalsCU centralized unitDL downlinkDSP digital signal processorDU distributed unitDVD digital versatile disc eNB evolved Node B (e.g., an LTE base station)EPC evolved packet coreE-SMLC evolved serving mobile location centerFPGA field-programmable gate arrayGDPR General Data Protection RegulationGMLC gateway mobile location center gNB next generation node B, base station for 5G / NR, i.e., a node providing NR user plane and control plane protocol terminations towards the UE, and connected via the NG interface to the 5GCGNSS global navigation satellite systemID identifier or identityI / F interfaceI / O input / outputIP internet protocolLCS location servicesLCM life cycle managementLMF location management functionLPP LTE positioning protocolLTE long term evolution (4G)MDT minimization of drive testML machine learningMME mobility management entityNF network functionNG new generationNG-RAN new generation radio access networkNR new radioNRF network repository functionNRPPa NR positioning protocol AN / W networkNWDAF network data analytics functionGAM operations, administration and maintenance or managementOTT over the topPHY physical (e.g. physical layer)PLMN public land mobile networkPRU positioning reference unitQoS quality of serviceRAM random access memoryRAN radio access networkRANI radio layer 1Rel releaseROM read-only memoryRSRP reference signal received powerRx receiver or receptionSI interface connecting the eNB to the EPCSA system aspectsSGW serving gatewaySI study itemSMF session management functionSNR signal to noise ratioSON self-organizing / optimizing networkSRS sounding reference signalstd standardizedTCE trace collection entityTR technical reportTRP transmission reception pointTS technical specificationTx transmitter or transmissionUDM unified data managementUDR unified data repositoryUE user equipment (e.g., a wireless, typically mobile device)UI user interfaceUL uplinkUPF user plane functionUSB universal serial busWG working groupWi-Fi wireless networking protocol that devices use to communicate without direct cable connectionsX2 network interface between RAN nodes and between RAN and the core networkXn network interface between NG-RAN nodes

Claims

CLAIMSWhat is claimed is:

1. An apparatus comprising: at least one processor; and at least one memory storing instructions that, when executed by the at least one processor, cause the apparatus at least to: determine a policy for collection of data and transfer of data for machine learning purposes; receive, from a server, a request for the collection of the data; determine at least one network entity related to the request for the collection of the data; receive, from the at least one network entity, collected data associated with the request within a container decodable by the server, based on the policy; and transmit, to the server, the container decodable by the server comprising the collected data.

2. The apparatus of claim 1, wherein the instructions, when executed by the at least one processor, cause the apparatus at least to receive information associated with the request for the collection of the data, wherein the information comprises at least one or more of: metadata that indicates standardized information associated with the request for the collection of the data, or a container decodable by the at least one network entity configured to collect the data, wherein the container decodable by the at least one network entity comprises at least one non-standardized requirement specific to the at least one network entityrelated to the request for the collection of the data, or at least one physical signaling requirement that indicates standardized configuration information of signaling associated with the request for the collection of data.

3. The apparatus of claim 2, wherein the instructions, when executed by the at least one processor, cause the apparatus at least to: transmit, to the at least one network entity, the container decodable by the at least one network entity; wherein the container decodable by the at least one network entity comprises a request addressed to the at least one network entity for the collection of data.

4. The apparatus of any of claims 2 to 3, wherein the instructions, when executed by the at least one processor, cause the apparatus at least to: transmit, to the at least one network entity, the at least one physical signaling requirement that indicates the standardized configuration information of signaling associated with the request for the collection of data.

5. The apparatus of claim 4, wherein the collected data received from the at least one network entity is collected based on the at least one physical signaling requirement transmitted to the at least one network entity.

6. The apparatus of any of claims 4 to 5, wherein the instructions, when executed by the at least one processor, cause the apparatus at least to: receive, from the at least one network entity, an indication of a determined configuration of physical signaling.

7. The apparatus of claim 6, wherein the indication of the determined configuration of physical signaling is received from the at least one network entity in response to the determined configuration of physical signaling being different from the at least one physical signaling requirement transmitted to the at least one network entity.

8. The apparatus of any of claims 2 to 7, wherein: the container decodable by the server is the same as or a representation of the container decodable by the at least one network entity, or the container decodable by the server is different from the container decodable by the at least one network entity.

9. The apparatus of any of claims 1 to 8, wherein the instructions, when executed by the at least one processor, cause the apparatus at least to: transmit, to the at least one network entity, a configuration of physical signaling; and wherein the collected data received from the at least one network entity is collected based on the configuration of physical signaling transmitted to the at least one network entity.

10. The apparatus of any of claims 1 to 9, wherein the instructions, when executed by the at least one processor, cause the apparatus at least to: determine whether to accept or reject the request for the collection of data; and transmit, to the server, an indication of the determining to accept or reject the request for the collection of data.

11. The apparatus of any of claims 1 to 10, wherein the instructions, when executed by the at least one processor, cause the apparatus at least to: transmit, to the at least one network entity, the request for the collection of data.

12. The apparatus of any of claims 1 to 11, wherein the instructions, when executed by the at least one processor, cause the apparatus at least to: transmit, to the at least one network entity or to the server, an indication of the policy for collection of data and transfer of data for the machine learning purposes.

13. The apparatus of claim 12, wherein the instructions, when executed by the at leastone processor, cause the apparatus at least to: receive, from the at least one network entity or the server, a request to indicate the policy.

14. The apparatus of any of claims 1 to 13, wherein the instructions, when executed by the at least one processor, cause the apparatus at least to: receive, from the at least one network entity, a request for permission to transfer the collected data; and transmit, to the at least one network entity, an indication that the permission to transfer the collected data is granted or denied.

15. The apparatus of any of claims 1 to 14, wherein the at least one network entity comprises a location management function, a base station, or a gNB.

16. The apparatus of any of claims 1 to 15, wherein the collected data comprises nonstandardized data associated with the machine learning purposes.

17. The apparatus of claim 16, wherein the machine learning purposes are associated with the at least one network entity.

18. The apparatus of any of claims 1 to 17, wherein the apparatus comprises a trace collection entity used for minimization of drive test.

19. The apparatus any of claims 1 to 18, wherein the container decodable by the server is decodable by the apparatus.

20. The apparatus of any of claims 1 to 19, wherein the container decodable by the server is not decodable by at least one network node.

21. The apparatus of any of claims 1 to 20, wherein the apparatus comprises a management entity.

22. An apparatus comprising: at least one processor; andat least one memory storing instructions that, when executed by the at least one processor, cause the apparatus at least to: perform at least one of: receive, from at least one network entity or a server, a container decodable by the apparatus, wherein the container comprises a request addressed to the apparatus for collection of data associated with machine learning purposes, or receive, directly from the server, the request for collection of data associated with machine learning purposes without the container; collect the data; and perform at least one of: transmit, to at least one network entity or directly to the server, the collected data associated with the request within a container decodable by the server that requested the data, or transmit, directly to the server, the collected data associated with the request.

23. The apparatus of claim 22, wherein the at least one network entity comprises a location management function, or a management entity.

24. The apparatus of any of claims 22 to 23, wherein the at least one network entity comprises a trace collection entity used for minimization of drive test.

25. The apparatus of any of claims 22 to 24, wherein: the container decodable by the server is the same as or a representation of the container decodable by the apparatus, or the container decodable by the server is different from the container decodable by the apparatus.

26. The apparatus of any of claims 22 to 25, wherein the instructions, when executed by the at least one processor, cause the apparatus at least to: receive, from the at least one network entity, a configuration of physical signaling associated with the request.

27. The apparatus of any of claims 22 to 26, wherein the collected data transmitted to the at least one network entity is collected based on the configuration of physical signaling.

28. The apparatus of any of claims 22 to 27, wherein the instructions, when executed by the at least one processor, cause the apparatus at least to: receive, from the at least one network entity, an indication of a policy for collection of data and transfer of data for the machine learning purposes, wherein the at least one network entity comprises a management entity.

29. The apparatus of claim 28, wherein the collecting of the data is based on the policy, and the transmitting of the collected data to the at least one network entity or directly to the server is based on the policy.

30. The apparatus of any of claims 28 to 29, wherein the instructions, when executed by the at least one processor, cause the apparatus at least to: transmit, to the management entity, a request to indicate the policy for collection of data and transfer of data for the machine learning purposes.

31. The apparatus of any of claims 22 to 30, wherein the instructions, when executed by the at least one processor, cause the apparatus at least to: transmit, to a management entity or a location management function, a request for permission to transfer the collected data; and receive, from the management entity or the location management function, an indication that the permission to transfer the collected data is granted or denied.

32. The apparatus of any of claims 22 to 31, wherein the instructions, when executedby the at least one processor, cause the apparatus at least to: receive, from a location management function, a configuration to perform at least one measurement related to the collection of data, based on a configuration of physical signaling; and perform the at least one measurement based on the configuration of physical signaling, wherein the collected data is based on the at least one measurement.

33. The apparatus of any of claims 22 to 32, wherein the instructions, when executed by the at least one processor, cause the apparatus at least to: configure a user equipment to transmit at least one uplink signal or transmission, based on a configuration of physical signaling; and receive the at least one uplink signal or transmission based on the configuration of physical signaling.

34. The apparatus of claim 33, wherein the uplink signal or transmission comprises an uplink sounding reference signal.

35. The apparatus of any of claims 22 to 34, wherein the collected data comprises nonstandardized data associated with the machine learning purposes.

36. The apparatus of any of claims 22 to 35, wherein the instructions, when executed by the at least one processor, cause the apparatus at least to: transmit, to the at least one network entity or directly to the server, standardized data associated with the machine learning purposes.

37. The apparatus of any of claims 22 to 36, wherein the apparatus comprises a base station or a gNB.

38. An apparatus comprising: at least one processor; and at least one memory storing instructions that, when executed by the at least oneprocessor, cause the apparatus at least to: transmit, to a management entity or to at least one network entity, a request for collection of data for machine learning purposes; and perform at least one of: receive, from the management entity or the at least one network entity, collected data associated with the request within a container decodable by the apparatus, or receive, from the at least one network entity, the collected data associated with the request.

39. The apparatus of claim 38, wherein the instructions, when executed by the at least one processor, cause the apparatus at least to transmit, to the management entity or to the at least one network entity, information associated with the request for the collection of the data, wherein the information comprises at least one or more of: metadata that indicates standardized information associated with the request for the collection of data, or a container decodable by the at least one network entity configured to collect the data, wherein the container decodable by the at least one network entity comprises at least one non-standardized requirement specific to the at least one network entity related to the request for the collection of the data, or at least one physical signaling requirement that indicates standardized configuration information of signaling associated with the request for the collection of data.

40. The apparatus of claim 39, wherein: the container decodable by the apparatus is the same as or a representation of the container decodable by the at least one network entity, or the container decodable by the apparatus is different from the containerdecodable by the at least one network entity.

41. The apparatus of any of claims 38 to 40, wherein the instructions, when executed by the at least one processor, cause the apparatus at least to: receive, from the management entity or the at least one network entity, an indication of whether the request was accepted or rejected.

42. The apparatus of any of claims 38 to 41, wherein the instructions, when executed by the at least one processor, cause the apparatus at least to: transmit, to the management entity, a request to indicate a policy for collection of data and transfer of data for the machine learning purposes; and receive, from the management entity, an indication of the policy for collection of data and transfer of data for the machine learning purposes; wherein the request for collection of data for the machine learning purposes associated with the at least one network entity is based on the policy.

43. The apparatus of any of claims 38 to 42, wherein the collected data comprises nonstandardized data associated with the machine learning purposes associated with the at least one network entity.

44. The apparatus of claim 43, wherein the instructions, when executed by the at least one processor, cause the apparatus at least to: receive, from the management entity or the at least one network entity, standardized data associated with the machine learning purposes associated with the at least one network entity.

45. The apparatus of any of claims 38 to 44, wherein the apparatus comprises an external vendor server.

46. An apparatus comprising: at least one processor; andat least one memory storing instructions that, when executed by the at least one processor, cause the apparatus at least to: receive, from a management entity, a request for data associated with machine learning purposes; wherein the request is associated with a container decodable by at least one network entity; transmit, to the at least one network entity, the container decodable by the at least one network entity comprising a request addressed to the at least one network entity for collection of the data; receive, from the at least one network entity, the collected data associated with the request within a container decodable by a server; and transmit, to the management entity or directly to the server, the collected data associated with the request within the container decodable by the server.

47. The apparatus of claim 46, wherein: the container decodable by the at least one network entity is the same as or a representation of the container decodable by the server, or the container decodable by the at least one network entity is different from the container decodable by the server.

48. The apparatus of any of claims 46 to 47, wherein the instructions, when executed by the at least one processor, cause the apparatus at least to: receive, from the management entity, a configuration of physical signaling associated with the request.

49. The apparatus of any of claims 46 to 48, wherein the instructions, when executed by the at least one processor, cause the apparatus at least to: determine a configuration of physical signaling, based on the request.

50. The apparatus of claim 49, wherein the instructions, when executed by the at least one processor, cause the apparatus at least to: transmit, to the management entity, an indication of the determined configuration of physical signaling.

51. The apparatus of claim 50, wherein the instructions, when executed by the at least one processor, cause the apparatus at least to: receive, from the management entity, a configuration of physical signaling associated with the request; wherein the indication of the determined configuration of physical signaling is transmitted to the management entity in response to the determined configuration of physical signaling being different from the received configuration of physical signaling.

52. The apparatus of any of claims 49 to 51, wherein the instructions, when executed by the at least one processor, cause the apparatus at least to: configure the at least one network entity to perform at least one measurement, based on the determined configuration of physical signaling; and configure a user equipment to transmit at least one uplink signal or transmission, based on the determined configuration of physical signaling.

53. The apparatus of claim 52, wherein the at least one uplink signal or transmission comprises an uplink sounding reference signal.

54. The apparatus of any of claims 46 to 53, wherein the collected data comprises nonstandardized data associated with the machine learning purposes.

55. The apparatus of any of claims 46 to 54, wherein the container decodable by the at least one network entity is decodable by the management entity.

56. The apparatus of any of claims 46 to 55, wherein the container decodable by the server is decodable by the management entity.

57. The apparatus of any of claims 46 to 56, wherein the apparatus comprises a locationmanagement function.

58. An apparatus comprising: at least one processor; and at least one memory storing instructions that, when executed by the at least one processor, cause the apparatus at least to: receive, from at least one network entity or a location management function, a configuration to transmit at least one uplink signal or transmission, based on a configuration of physical signaling; and transmit the at least one uplink signal or transmission to the at least one network entity, based on the configuration of physical signaling; wherein the at least one uplink signal or transmission is configured to be used with the at least one network entity to collect non-standardized data related to machine learning purposes.

59. The apparatus of claim 58, wherein the configuration of physical signaling comprises at least one or more of: a bandwidth of the at least one uplink signal or transmission, or a periodicity for transmission of the at least one uplink signal or transmission.

60. The apparatus of any of claims 58 to 59, wherein the uplink signal or transmission comprises an uplink sounding reference signal.

61. The apparatus of any of claims 58 to 60, wherein the apparatus comprises a user equipment.

62. A method comprising: determining a policy for collection of data and transfer of data for machine learning purposes;receiving, from a server, a request for the collection of the data; determining at least one network entity related to the request for the collection of the data; receiving, from the at least one network entity, collected data associated with the request within a container decodable by the server, based on the policy; and transmitting, to the server, the container decodable by the server comprising the collected data.

63. A method comprising: performing at least one of: receiving, from at least one network entity or a server, a container decodable by the apparatus, wherein the container comprises a request addressed to the apparatus for collection of data associated with machine learning purposes, or receiving, directly from the server, the request for collection of data associated with machine learning purposes without the container; collecting the data; and performing at least one of: transmitting, to at least one network entity or directly to the server, the collected data associated with the request within a container decodable by the server that requested the data, or transmitting, directly to the server, the collected data associated with the request.

64. A method comprising: transmitting, to a management entity or to at least one network entity, a request for collection of data for machine learning purposes; andperforming at least one of: receiving, from the management entity or the at least one network entity, collected data associated with the request within a container decodable by the apparatus, or receiving, from the at least one network entity, the collected data associated with the request.

65. A method comprising: receiving, from a management entity, a request for data associated with machine learning purposes; wherein the request is associated with a container decodable by at least one network entity; transmitting, to the at least one network entity, the container decodable by the at least one network entity comprising a request addressed to the at least one network entity for collection of the data; receiving, from the at least one network entity, the collected data associated with the request within a container decodable by a server; and transmitting, to the management entity or directly to the server, the collected data associated with the request within the container decodable by the server.

66. A method comprising: receiving, from at least one network entity or a location management function, a configuration to transmit at least one uplink signal or transmission, based on a configuration of physical signaling; and transmitting the at least one uplink signal or transmission to the at least one network entity, based on the configuration of physical signaling; wherein the at least one uplink signal or transmission is configured to be used with the at least one network entity to collect non-standardized data related to machinelearning purposes.

67. An apparatus comprising: means for determining a policy for collection of data and transfer of data for machine learning purposes; means for receiving, from a server, a request for the collection of the data; means for determining at least one network entity related to the request for the collection of the data; means for receiving, from the at least one network entity, collected data associated with the request within a container decodable by the server, based on the policy; and means for transmitting, to the server, the container decodable by the server comprising the collected data.

68. An apparatus comprising: means for performing at least one of: receiving, from at least one network entity or a server, a container decodable by the apparatus, wherein the container comprises a request addressed to the apparatus for collection of data associated with machine learning purposes, or receiving, directly from the server, the request for collection of data associated with machine learning purposes without the container; means for collecting the data; and means for performing at least one of: transmitting, to at least one network entity or directly to the server, the collected data associated with the request within a container decodable by the server that requested the data, ortransmitting, directly to the server, the collected data associated with the request.

69. An apparatus comprising: means for transmitting, to a management entity or to at least one network entity, a request for collection of data for machine learning purposes; and means for performing at least one of: receiving, from the management entity or the at least one network entity, collected data associated with the request within a container decodable by the apparatus, or receiving, from the at least one network entity, the collected data associated with the request.

70. An apparatus comprising: means for receiving, from a management entity, a request for data associated with machine learning purposes; wherein the request is associated with a container decodable by at least one network entity; means for transmitting, to the at least one network entity, the container decodable by the at least one network entity comprising a request addressed to the at least one network entity for collection of the data; means for receiving, from the at least one network entity, the collected data associated with the request within a container decodable by a server; and means for transmitting, to the management entity or directly to the server, the collected data associated with the request within the container decodable by the server.

71. An apparatus comprising: means for receiving, from at least one network entity or a location managementfunction, a configuration to transmit at least one uplink signal or transmission, based on a configuration of physical signaling; and means for transmitting the at least one uplink signal or transmission to the at least one network entity, based on the configuration of physical signaling; wherein the at least one uplink signal or transmission is configured to be used with the at least one network entity to collect non-standardized data related to machine learning purposes.

72. A non-transitory program storage device readable by a machine, tangibly embodying a program of instructions executable by the machine for performing operations, the operations comprising: determining a policy for collection of data and transfer of data for machine learning purposes; receiving, from a server, a request for the collection of the data; determining at least one network entity related to the request for the collection of the data; receiving, from the at least one network entity, collected data associated with the request within a container decodable by the server, based on the policy; and transmitting, to the server, the container decodable by the server comprising the collected data.

73. A non-transitory program storage device readable by a machine, tangibly embodying a program of instructions executable by the machine for performing operations, the operations comprising: performing at least one of: receiving, from at least one network entity or a server, a container decodable by the apparatus, wherein the container comprises a request addressed to the apparatus for collection of data associated with machinelearning purposes, or receiving, directly from the server, the request for collection of data associated with machine learning purposes without the container; collecting the data; and performing at least one of: transmitting, to at least one network entity or directly to the server, the collected data associated with the request within a container decodable by the server that requested the data, or transmitting, directly to the server, the collected data associated with the request.

74. A non-transitory program storage device readable by a machine, tangibly embodying a program of instructions executable by the machine for performing operations, the operations comprising: transmitting, to a management entity or to at least one network entity, a request for collection of data for machine learning purposes; and performing at least one of: receiving, from the management entity or the at least one network entity, collected data associated with the request within a container decodable by the apparatus, or receiving, from the at least one network entity, the collected data associated with the request.

75. A non-transitory program storage device readable by a machine, tangibly embodying a program of instructions executable by the machine for performing operations, the operations comprising: receiving, from a management entity, a request for data associated with machine learning purposes;wherein the request is associated with a container decodable by at least one network entity; transmitting, to the at least one network entity, the container decodable by the at least one network entity comprising a request addressed to the at least one network entity for collection of the data; receiving, from the at least one network entity, the collected data associated with the request within a container decodable by a server; and transmitting, to the management entity or directly to the server, the collected data associated with the request within the container decodable by the server.

76. A non-transitory program storage device readable by a machine, tangibly embodying a program of instructions executable by the machine for performing operations, the operations comprising: receiving, from at least one network entity or a location management function, a configuration to transmit at least one uplink signal or transmission, based on a configuration of physical signaling; and transmitting the at least one uplink signal or transmission to the at least one network entity, based on the configuration of physical signaling; wherein the at least one uplink signal or transmission is configured to be used with the at least one network entity to collect non-standardized data related to machine learning purposes.

Images