Security for AI / ML model storage and sharing

Abstract

An embodiment includes a method for a consumer network function (NFc). Such method includes sending a first request to a network repository function (NRF) for a first access token associated with a machine learning (ML) model generated, owned, and / or maintained by a producer NF (NFp). The first request includes an analysis identifier (ID) associated with the ML model, a vendor ID associated with the NFc, and an ID associated with the NFp. Such method includes receiving a first response from the NRF including the first access token and sending a second request for the ML model to the NFp. The second request includes the first access token, the analysis ID, and the vendor ID associated with the NFc. Such method includes receiving a second response from the NFp including a universal resource locator associated with a second NF of the communication network from which the ML model can be obtained.

Description

[Technical Field]

[0001] The present application relates generally to the field of communication networks, and more particularly to techniques for security of artificial intelligence / machine learning (AI / ML) models used to generate analytics in communication networks (e.g., 5G core networks). [Background technology]

[0002] The fifth generation (5G) of cellular systems is currently being standardized within the Third Generation Partnership Project (3GPP). 5G is being developed for maximum flexibility to support a variety of use cases, including enhanced mobile broadband (eMBB), machine-based communications (MTC), ultra-reliable low-latency communications (URLLC), sidelink device-to-device (D2D), and several other use cases.

[0003] At a high level, a 5G system (5GS) consists of an Access Network (AN) and a Core Network (CN). The AN provides UEs with connectivity to the CN via base stations, such as gNBs or ng-eNBs described below. The CN contains various Network Functions (NFs) that provide a wide range of different functions, such as session management, connection management, charging, and authentication.

[0004] FIG. 1 shows a high-level diagram of an exemplary 5G network architecture, including a Next Generation Radio Access Network (NG-RAN, 199) and a 5G Core (5GC, 198). The NG-RAN may include one or more gNodeBs (gNBs, e.g., 100, 150) connected to the 5GC via one or more NG interfaces (e.g., 102, 152). More specifically, the gNBs may be connected to one or more Access and Mobility Management Functions (AMFs) in the 5GC via respective NG-C interfaces and to one or more User Plane Functions (UPFs) in the 5GC via respective NG-U interfaces. Various other Network Functions (NFs) may be included in the 5GC, as described in more detail below.

[0005] Additionally, gNBs may be connected to each other via one or more Xn interfaces (e.g., 140 between gNBs 100, 150). The radio technology for NG-RAN is often referred to as New Radio (NR). With respect to the NR interface to the UE, each of the gNBs may support frequency division duplexing (FDD), time division duplexing (TDD), or a combination thereof. Each of the gNBs may serve a geographic coverage area including one or more cells and, in some cases, may use various directional beams to provide coverage in each cell.

[0006] The NG RAN logical node shown in Figure 1 includes a centralized unit (CU or gNB-CU) and one or more distributed units (DU or gNB-DU). The CU (e.g., 110) is a logical node that hosts upper layer protocols and performs various gNB functions, such as controlling the operation of the DU. In contrast, the DUs (e.g., 120, 130) are distributed logical nodes that host lower layer protocols and can include various subsets of gNB functions depending on functional split options. The CU connects to one or more DUs through respective F1 logical interfaces (e.g., 122, 132 in Figure 1).

[0007] Another change in 5G networks (e.g., in 5GC) is that the legacy peer-to-peer interfaces and protocols found in previous generation networks are modified and / or replaced by a service-based architecture (SBA) in which a network function (NF) provides one or more services to one or more service consumers. This may be done, for example, by a Hypertext Transfer Protocol / Representational State Transfer (HTTP / REST) ​​application programming interface (API). Generally, various services are self-contained functions that can be changed and modified in a decoupled manner without affecting other services.

[0008] Furthermore, services are composed of various "service operations," which are more granular divisions of the overall service functionality. Interactions between service consumers and producers can be of type "request / response" or "subscribe / notify." In 5G SBA, a Network Repository Function (NRF) enables any network function to discover services offered by other network functions, and a Data Storage Function (DSF) enables any network function to store its context. This 5G SBA model is based on principles including modularity, reusability, and self-containment of NFs, which can enable network deployments to take advantage of the latest virtualization and software technologies.

[0009] A 5GC NF of particular interest in this disclosure is the Network Data Analysis Function (NWDAF). This NF provides network analysis information (e.g., statistical information of past events and / or predictive information) to other NFs at the network slice instance level. The NWDAF can collect data from any 5GC NF. Note that a "network slice" is a logical partition of a 5G network that provides specific network capabilities and characteristics, e.g., supporting a particular service. A network slice instance is a set of NF instances and the required network resources (e.g., computation, storage, communication) that provide the capabilities and characteristics of the network slice.

[0010] Machine learning (ML) is a type of artificial intelligence (AI) that focuses on using data and algorithms to mimic the way humans learn, gradually improving accuracy as more data becomes available. ML algorithms build models based on sample (or "training") data, which are then used to make predictions or decisions. ML algorithms can be used in a wide variety of applications (e.g., medicine, email filtering, speech recognition, etc.) where it is difficult or infeasible to develop traditional algorithms to perform the required tasks. A subset of ML is closely related to computing statistics.

[0011] The 5G system architecture allows any NF to obtain analytics from the NWDAF using the Data Collection and Coordination Function (DCCF) and associated Ndccf services. The NWDAF can also store and retrieve analytics information from the Analysis and Data Repository Function (ADRF). 3GPP TS 23.288 (v17.2.0) specifies that the NWDAF is the primary NF for computing analytics reports and categorizes the NWDAF into two sub-functions (or logical functions): the Analysis Logical Function (AnLF), which performs the analytics procedures, and the Model Training Logical Function (MTLF), which performs the training and retraining of ML models used by the AnLF. Summary of the Invention

[0012] AI / ML models (or more simply, ML models) are considered important intellectual property of their owners (e.g., 5GC vendors), and therefore their confidentiality and integrity must be protected at all times. 3GPP is considering the feasibility of sharing or storing ML models in network equipment that may be provided by different vendors. In this configuration, the ML model should be protected from access and use by consumer NFs provided by a vendor different from the vendor of the ML model. However, there is currently no specified solution to this requirement.

[0013] It is an objective of embodiments of the present disclosure to address these and other issues, problems, and / or difficulties related to ML model security, thereby facilitating the otherwise advantageous deployment of ML models for network analysis.

[0014] Some embodiments of the present disclosure include a method (e.g., a procedure) for a consumer NF (NFc) of a communication network (e.g., 5GC).

[0015] The example methods include sending a first request to a network repository function (NRF) of the communication network for a first access token associated with an ML model generated, owned, and / or maintained by a producer NF (NFp) of the communication network. The first request includes an analysis ID associated with the ML model, a vendor ID associated with the NFc, and an ID associated with the NFp. The example methods also include receiving a first response from the NRF including the first access token and sending a second request for the ML model to the NFp. The second request includes the first access token, the analysis ID, and the vendor ID associated with the NFc. The example methods also include receiving a second response from the NFp including a URL associated with a second NF of the communication network from which the ML model can be obtained.

[0016] In some embodiments, the second NF associated with the URL is an NFp, and these example methods also include obtaining the ML model from the NFp using the URL and the first access token.

[0017] In other embodiments, the second NF associated with the URL is an ADRF of the communication network, and these exemplary methods include the following operations: sending a third request to the NRF for a second access token associated with the ML model, wherein the third request includes an analysis ID associated with the ML model, a vendor ID associated with the NRF, and an ID associated with the ADRF; receiving a third response from the first NF, the third response including the second access token; Use the second access token and URL to obtain the ML model from the ADRF. Also includes.

[0018] Other embodiments include exemplary methods (e.g., procedures) for NFp of a communication network (e.g., 5GC).

[0019] The example methods include receiving a second request from an NFc of the communication network for an ML model generated, owned, and / or maintained by the NFp. The second request includes a first access token issued by an NRF of the communication network, an analysis ID associated with the ML model, and a vendor ID associated with the NFc. The example methods also include authorizing the NFc to access the ML model associated with the analysis ID based on the first access token. The example methods also include sending the NFc a second response based on authorizing the NFc, the response including a URL associated with a second NF of the communication network from which the ML model can be obtained.

[0020] In some embodiments, the second NF associated with the URL is an NFp, and these example methods may also include providing the ML model to an NFc using the URL and the first access token.

[0021] In other embodiments, the second NF associated with the URL is an ADRF of the communication network, and these exemplary methods include the following operations: sending a first request to the ADRF to store an ML model, wherein the first request includes: an analysis ID associated with the ML model; an interoperability ID including or associated with a list of vendors enabled to access the ML model; and a URL associated with the NFp from which the ML model may be obtained; Submitting the ML model to the ADRF using the URL associated with the NFp; and receiving a first response from the ADRF that includes a URL associated with the ADRF, which is sent in a second response to the NFc; Also includes.

[0022] Other embodiments include methods (e.g., procedures) for an NRF of a communication network (e.g., 5GC).

[0023] These example methods may include registering the following information in a profile for an NFp of the communication network: a first analysis ID associated with an ML model generated, owned, and / or maintained by the NFp; and an interoperability ID including or associated with a list of vendors enabled to access the ML model. These example methods may also include receiving a first request from an NFc of the communication network for a first access token associated with the ML model. The first request includes the first analysis ID associated with the ML model, a vendor ID associated with the NFc, and an ID associated with the NFp. These example methods also include authorizing the NFc to access the ML model based on a match, correspondence, or relationship between the vendor ID included in the first request and the interoperability ID registered in the profile for the NFp. These example methods also include sending a first response to the NFc including the first access token.

[0024] In some embodiments, these exemplary methods include the following operations: receiving a third request from the NFc for a second access token associated with the ML model, wherein the third request includes an analysis ID associated with the ML model, a vendor ID associated with the NFc, and an ID associated with the ADRF; authorizing the NFc to access the ML model based on a match, correspondence, or relationship between the vendor ID included in the third request and an interoperability ID registered in a profile for the NFp; sending a third response to the NFc that includes the second access token; and Also includes.

[0025] Other embodiments include methods (e.g., procedures) for ADRF in a communication network (e.g., 5GC).

[0026] These example methods may include receiving a first request from an NFp of a communications network to store an ML model generated, owned, and / or maintained by the NFp. The first request includes the following: an analysis ID associated with the ML model; an interoperability ID including or associated with a list of vendors enabled to access the ML model; and a URL associated with the NFp from which the ML model may be obtained. These example methods may also include obtaining the ML model from the NFp using the URL associated with the NFp. These example methods may also include sending a first response to the NFp including a URL associated with the ADRF from which the ML model may be obtained.

[0027] In some embodiments, these example methods may also include providing the ML model to an NFc of the communication network using a URL associated with the ADRF. In some of these embodiments, providing the ML model to the NFc includes verifying a second access token issued by the NRF and provided by the NFc.

[0028] In the various embodiments summarized above, the NFc may be an NWDAF(AnLF) and / or the NFp may be an NWDAF(MTLF).

[0029] Other embodiments include NFs, NFs, NRFs, and ADRFs (or network equipment configured to implement such NFs) configured to perform operations corresponding to any of the example methods described herein. Other embodiments also include a non-transitory computer-readable medium storing computer-executable instructions that, when executed by a processing circuit, configure such NFs to perform operations corresponding to any of the example methods described herein.

[0030] These and other disclosed embodiments may provide various benefits and / or advantages: By providing ML model owners / producers with the ability to protect ML models during various transmission, storage, and retrieval scenarios, embodiments improve the security of sensitive and / or confidential ML models, thereby facilitating the deployment of such models in multi-vendor communication networks, such as 5GC.

[0031] These and other objects, features, and advantages of the present disclosure will become apparent from a reading of the following detailed description when taken in light of the drawings briefly described below. [Brief explanation of the drawings]

[0032] [Figure 1] FIG. 1 illustrates aspects of an exemplary 5G network architecture. [Figure 2] FIG. 1 illustrates aspects of an exemplary 5G network architecture. [Figure 3] FIG. 1 is a signaling diagram of network procedures for authorization and authentication of AI / ML model transfers. [Figure 4] FIG. 1 is a signaling diagram of a procedure involving an NWDAF (AnLF), an NRF, and an NWDAF (MTLF), in accordance with some embodiments of the present disclosure. [Figure 5] FIG. 10 is a signaling diagram of another procedure involving an NWDAF (AnLF), an NRF, an NWDAF (MTLF), and an ADRF in accordance with another embodiment of the present disclosure. [Figure 6] FIG. 1 illustrates an example method (e.g., procedure) for a consumer NF of a communication network, in accordance with various embodiments of the present disclosure. [Figure 7] FIG. 1 illustrates an example method (e.g., procedure) for a producer NF of a communication network, in accordance with various embodiments of the present disclosure. [Figure 8] FIG. 1 illustrates an example method (e.g., procedure) for a Network Repository Function (NRF) of a communication network, in accordance with various embodiments of the present disclosure. [Figure 9] FIG. 1 illustrates an example method (e.g., procedure) for ADRF in a communication network, in accordance with various embodiments of the present disclosure. [Figure 10] FIG. 1 illustrates a communication system in accordance with various embodiments of the present disclosure. [Figure 11] FIG. 1 illustrates a UE in accordance with various embodiments of the present disclosure. [Figure 12] FIG. 1 illustrates a network node according to various embodiments of the present disclosure. [Figure 13] FIG. 1 illustrates a host computing system in accordance with various embodiments of the present disclosure. [Figure 14] FIG. 1 is a block diagram of a virtualization environment in which functionality implemented by some embodiments of the present disclosure may be virtualized. [Figure 15]FIG. 1 illustrates communication between a host computing system, a network node, and a UE over multiple connections, in accordance with various embodiments of the present disclosure. DETAILED DESCRIPTION OF THE INVENTION

[0033] The embodiments briefly summarized above will now be described more fully with reference to the accompanying drawings. These descriptions are provided as examples to explain the subject matter to those skilled in the art and should not be construed as limiting the scope of the subject matter to only the embodiments described herein. More particularly, examples illustrating the operation of various embodiments in accordance with the advantages described above are provided below.

[0034] In general, all terms used herein should be interpreted according to their ordinary meaning in the relevant technical field unless a different meaning is expressly given and / or implied from the context in which the term is used. All references to an element, apparatus, component, means, step, etc. should be openly interpreted as referring to at least one instance of that element, apparatus, component, means, step, etc., unless expressly stated otherwise. The acts of any method and / or procedure disclosed herein need not be performed in the exact order disclosed, unless an act is explicitly described as following or preceding another act and / or if it is implicit that an act must follow or precede another act. Any feature of any embodiment disclosed herein may be applied to any other disclosed embodiment, as appropriate. Similarly, any advantage of any embodiment described herein may be applied to any other disclosed embodiment, as appropriate.

[0035] Additionally, the following terms are used throughout the description provided below: Radio Access Node: As used herein, a "radio access node" (or equivalently, a "radio network node," "radio access network node," or "RAN node") may be any node in a radio access network (RAN) that operates to transmit and / or receive signals wirelessly. Some examples of radio access nodes include, but are not limited to, base stations (e.g., gNBs in a 3GPP 5G / NR network or enhanced or eNBs in a 3GPP LTE network), base station distributed elements (e.g., CUs and DUs), high-power or macro base stations, low-power base stations (e.g., micro, pico, femto, or home base stations), aggregated access backhaul (IAB) nodes, transmission points (TPs), transmit reception points (TRPs), remote radio units (RRUs or RRHs), and relay nodes. Core network node: As used herein, a "core network node" is any type of node in a core network. Some examples of core network nodes include, for example, a Mobility Management Entity (MME), a Serving Gateway (SGW), a PDN Gateway (P-GW), a Policy and Charging Rules Function (PCRF), an Access and Mobility Management Function (AMF), a Session Management Function (SMF), a User Plane Function (UPF), a Charging Function (CHF), a Policy Control Function (PCF), an Authentication Server Function (AUSF), a Location Management Function (LMF), etc. Wireless Device: As used herein, a "wireless device" (or "WD" for short) is any type of device that is capable of, set up, configured, and / or operable to communicate wirelessly with network nodes and / or other wireless devices. Communicating wirelessly may involve sending and / or receiving radio signals using electromagnetic waves, radio waves, infrared waves, and / or other types of signals suitable for conveying information over the air. Unless otherwise noted, the term "wireless device" is used interchangeably herein with "user equipment" (or "UE" for short), and both of these terms have a different meaning than the term "network node." Wireless Node: As used herein, a "wireless node" may be either a "wireless access node" (or equivalent term) or a "wireless device." Network Node: As used herein, a "network node" is any node that is part of either the radio access network (e.g., radio access node or equivalent terminology) or the core network (e.g., the core network node described above) of a cellular communications network. Functionally, a network node is equipment that is capable of, set up, configured, and / or operative to communicate, directly or indirectly, with wireless devices and / or other network nodes or equipment in the cellular communications network to enable and / or provide wireless access to wireless devices and / or to perform other functions (e.g., administration) in the cellular communications network. Node: As used herein, the term "node" (without a prefix) may be any type of node in or with a wireless network (including a RAN and / or core network), including a radio access node (or equivalent term), a core network node, or a wireless device. However, the term "node" may be limited to a particular type (e.g., a radio access node) based on the particular characteristics of the node in a given context.

[0036] The above definitions are not intended to be exclusive. In other words, various of the above terms may be explained and / or explained elsewhere in this disclosure using the same or similar terminology. Nevertheless, to the extent such other explanations and / or explanations contradict the above definitions, the above definitions shall control.

[0037] It should be noted that the description provided herein focuses on 3GPP cellular communication systems, and therefore 3GPP terminology or terminology similar to 3GPP terminology is generally used, however, the concepts disclosed herein are not limited to 3GPP systems and may be applied in any system that can benefit from the concepts, principles, and / or embodiments described herein.

[0038] 2 shows an example non-roaming reference architecture for 5GC (200) with a service-based interface in the control plane (CP) and various 3GPP-specified NFs. These include: The Application Function (AF, using the Naf interface) interacts with the 5GC to provide provisioning information to the network operator and to subscribe to certain events occurring in the operator's network. The AF offers control of flow resources according to what has been negotiated with the network, i.e., the application to which the service is delivered, at a layer (i.e., the transport layer) different from the layer at which the service is requested (i.e., the signaling layer). The AF communicates dynamic session information to the PCF (via the N5 interface), including a description of the media to be delivered by the transport layer. The Policy Control Function (PCF, using the Npcf interface) supports a unified policy framework for governing network behavior by providing PCC rules (e.g., regarding the treatment of each service data flow under the PCC's control) to the SMF via the N7 reference point. The PCF provides policy control decisions and flow-based charging control to the SMF, including service data flow detection, gating, QoS, and flow-based charging (excluding credit control). The PCF receives session and media-related information from the AF and informs the AF of traffic (or user) plane events. User Plane Function (UPF) - Supports handling of user plane traffic based on rules received from the SMF, including packet inspection and different enforcement actions (e.g., event detection and reporting). The UPF communicates with the RAN (e.g., NG-RNA) via the N3 reference point, with the SMF (described below) via the N4 reference point, and with the external packet data network (PDN) via the N6 reference point. The N9 reference point is for communication between two UPFs. The Session Management Function (SMF, using the Nsmf interface) interacts with the decoupling traffic (or user) plane, including creating, updating, and deleting Protocol Data Unit (PDU) sessions with the User Plane Function (UPF), and managing session context, e.g., for event reporting. For example, the SMF performs data flow detection (based on filter specifications contained in PCC rules), online and offline charging interactions, and policy enforcement. The Charging Function (CHF, using the Nchf interface) is responsible for converged online and offline charging functionality. The Charging Function provides quota management (for online charging), reauthorization triggers, rating conditions, etc. and is informed of usage reports by the SMF. Quota management involves granting a specific number of units (e.g., bytes, seconds) for a service. The CHF also interacts with the billing system. The Access and Mobility Management Function (AMF, using the Namf interface) terminates the RAN CP interface and handles all mobility and connection management for the UE (similar to the MME in the EPC). The AMF communicates with the UE via the N1 reference point and with the RAN (e.g., NG-RAN) via the N2 reference point. Network Exposure Function (NEF) with Nnef interface - serves as the entry point into the operator's network by securely exposing network capabilities and events offered by 3GPP NFs to the AF and by providing a way for the AF to securely provide information to the 3GPP network. For example, the NEF provides services that allow the AF to provision specific subscription data (e.g., expected UE behavior) for various UEs. · Network Repository Function (NRF, 220) using the Nnrf interface - provides service registration and discovery, allowing NFs to identify suitable services available from other NFs. Network Slice Selection Function (NSSF) using Nnssf interface - A "network slice" is a logical partition of a 5G network that provides specific network capabilities and characteristics, e.g., supporting a specific service. A network slice instance is a set of NF instances and the required network resources (e.g., computation, storage, communication) that provide the capabilities and characteristics of the network slice. The NSSF enables other NFs (e.g., AMF) to identify a network slice instance that is suitable for a UE's desired service. Authentication Server Function (AUSF) using Nausf interface - Based on the user's home network (HPLMN), the Authentication Server Function (AUSF) performs user authentication and calculates security keying material for various purposes. · Network Data Analysis Facility (NWDAF, 210) using the Nnwdaf interface, described above and in more detail below. Location Management Function (LMF) using Nlmf interface - supports various functions related to determining the UE location, including determining the location for the UE and obtaining any of the following: DL location measurements or location estimates from the UE, UL location measurements from the NG RAN, and non-UE related assistance data from the NG RAN.

[0039] The Unified Data Management (UDM) function supports the generation of 3GPP authentication credentials, user identification handling, access authorization based on subscription data, and other subscriber-related functions. To provide this functionality, the UDM uses subscription data (including authentication data) stored in the 5GC Unified Data Repository (UDR). The UDR supports the storage and retrieval of policy data by the PCF and application data by the NEF.

[0040] The NRF allows any NF to discover services offered by other NFs, and the Data Storage Function (DSF) allows any NF to store its context. In addition, the NEF provides exposure of 5GC capabilities and events to AFs within and outside of 5GC. For example, the NEF provides a service that allows AFs to provision specific subscription data (e.g., expected UE behavior) for various UEs.

[0041] The communication link between the UE and the 5G network (AN and CN) can be grouped into two different hierarchies: the UE communicates with the CN through the Non-Access Stratum (NAS) and with the AN through the Access Stratum (AS). All NAS communication takes place between the UE and the AMF via the NAS protocol (N1 interface in Figure 2). Security for communication through these hierarchies is provided by the NAS protocol (for the NAS) and the PDCP protocol (for the AS).

[0042] 3GPP Rel-17 extends the SBA by adding a data management framework, including a Data Collection and Coordination Function (DCCF) and a Messaging Framework Adapter Function (MFAF), which are specified in detail in 3GPP TR 23.700-91 (v17.0.0). The data management framework is backward compatible with the Rel-16 NWDAF functions described above. For Rel-17, the baseline for services offered by the DCCF (e.g., to the NWDAF) is the Rel-16 NF service used to obtain the data. For example, the baseline for the DCCF service used by the NWDAF consumer to obtain UE mobility data is Namf_EventExposure.

[0043] 3GPP TS 23.288 (v17.2.0) specifies that the NWDAF is the primary network function for computing analytical reports. The 5G system architecture allows any NF to obtain analytics from the NWDAF using the DCCF function and associated Ndccf services. The NWDAF can also store and retrieve analytical information from the Analysis Data Repository Function (ADRF).

[0044] 3GPP TS 23.288 also categorizes the NWDAF into two sub-functions (or logical functions): the NWDAF Analysis Logical Function (NWDAF AnLF), which performs analysis procedures, and the NWDAF Model Training Logical Function (NWDAF MTLF), which performs training and retraining of ML models used by the NWDAF AnLF. Hereinafter, the terms "AnLF," "NWDAF AnLF," and "NWDAF(AnLF)" will be used interchangeably. Similarly, the terms "MTLF," "NWDAF MTLF," and "NWDAF(MTLF)" will be used interchangeably.

[0045] 3GPP TS 23.288 (v17.2.0) specifies a subscribe / notify procedure for a consumer NF to retrieve ML models associated with one or more analysis IDs whenever new ML models are trained and made available by the NWDAF MTLF. This is called ML model provisioning and is implemented by the Nnwdaf_MLModelProvision service.

[0046] 3GPP TR 33.738 (v0.2.0) describes research into security aspects of enablers for network automation for 5G. One of the research objectives is security for AI / ML model sharing and storage, identified as "Key Issue #3." The following text from 3GPP TR 33.378 describes various aspects of this issue. In this text, "NFc" refers to consumer NF and "NFp" refers to producer NF from the perspective of the AI / ML in question.

[0047] ***Start 3GPP Text*** 5.3.1 Problem Details AI / ML models are shared between NWDAFs and / or NFs (in other words, between NWDAFs, between ADRFs, etc.). In different scenarios, the NF producer of an AI / ML model can store the model in the ADRF, NWDAF, or other entity. The Analytical Data Repository Facility (ADRF) has been extended to store AI / ML models to facilitate the distribution and sharing of those models among NFs. Because AI / ML models and their algorithms are generally proprietary (i.e., subject to the intellectual property rights of their designers), it is essential to ensure that only NFs that actually have authorization to access the AI / ML models can read and use them. Moreover, the ADRF itself cannot be considered a fully trusted entity that stores highly confidential AI / ML data models; those models are, in fact, publicly available at rest in the ADRF. The current authorization scheme specified by 3GPP for SBA only works at the service level or resource / operation level range. This authorization granularity may not be sufficient in AI / ML model sharing scenarios, because the ADRF (Analysis Data Repository Function) or NWDAF, or any other network function that may store the AI / ML model, cannot verify whether the NF consumer is authorized to retrieve the AI / ML model. 5.3.2 Security Threats An unauthorized NFc, who in principle is not entitled to retrieve a particular model stored by an NFp, may be able to gain access to the storage entity and retrieve the model. Without protection against accessing and reading AI / ML models from the ADRF stored by the NFp, a compromised ADRF may expose algorithms and sensitive data to unauthorized entities, which can easily misuse and / or further distribute it to other entities, causing a larger data security breach. 5.3.3 Potential Security Requirements AI / ML models must be protected between the entity that generates the ML model or stores the ML model in the ADRF (e.g., the NWDAF containing the MTLF, the NFp) and the entity that consumes the model (the NFc). The ADRF (Analysis Data Repository Function), or any other network function that may store an AI / ML model, must be able to authorize the NFc to retrieve that AI / ML model. NF service consumers must be authorized to access AI / ML models in the ADRF (or any other NF that may store ML models, e.g., NWDAF MTLF). ***END 3GPP TEXT***

[0048] 3GPP TR 33.738 also describes a solution for authorization and authentication of AI / ML model transfer, identified as "Solution #2." This security solution protects AI / ML models between a first entity (e.g., NF) that generates the AI / ML model (or stores the AI / ML model in the ADRF) and a second entity (NFc) that consumes the model. In this solution, an authorization token is used by the ADRF to verify that the NFc is allowed to access the ML model.

[0049] Figure 3 shows a signaling diagram for this solution for authorization and authentication of AI / ML model transfer. As shown in Figure 3, the signaling is between the NWDAF (AnLF) / NFc, the authorization server (e.g., NRF), the NWDAF (MTLF), and the ADRF. While the operations shown in Figure 3 are numerically labeled, this is intended for ease of explanation and does not require or imply any particular order of operations unless otherwise stated below.

[0050] In operation 1, the MTLF trains an ML model and sends it to the ADRF by invoking the ADRF_DataManagement_StorageRequest(ML model) service operation. In addition to model metadata, this message can include the ML model ID, analysis ID, vendor ID, a MAC or SHA256 signature of the application binary, the environment required for ML model execution, a URL / link to retrieve the settings, and a private / signature key / certificate to generate authentication credentials. The MTLF may send the ML model encrypted using a symmetric key (e.g., an AES key) before storage.

[0051] In operation 2, the ADRF stores the ML model and response as specified in 3GPP TS 23.288 (v17.6.0), except that the storage is performed by the ADRF. In operation 3, the NFc (e.g., NWDAF AnLF) contacts the NRF and requests an access token using existing procedures specified in 3GPP TS 33.501 (v17.7.0). In operation 4, the NRF sends the access token along with the MTLF ID using existing procedures specified in 3GPP TS 23.288.

[0052] In operation 5, the NWDAF (AnLF) requests an ML model ID from the NWDAF (MTLF) using the Nnwdaf_MLModelProvision service operation with the access token, and the NWDAF (MTLF) retrieves the ML model ID based on the ML analysis ID and / or ADRF ID. The NWDAF (MTLF) also verifies the received access token. In operation 6, the NWDAF (MTLF) sends a Nnwdaf_MLModelProvision response that includes the encryption key used to encrypt the AI / ML model in operation 1. Additionally, the NWDAF (MTLF) receives the following: A nonce shared in action 1 as part of the metadata; a MAC or hash of a binary or random number shared in operation 1 as part of the data; The public part of the signing key is the private key of the MTLF, which was shared in operation 1. Proofs generated by the MTLF's signing key, e.g., JWT tokens or certificates The ADRF may include a one-time credential for accessing the model, including any of the following:

[0053] The one-time certificate may be used to limit the number of accesses from the NFc. Even so, the "one-time" certificate may be used as a regular authorization token to access the ML model multiple times, i.e., not just once as the name suggests.

[0054] In operation 7, the NWDAF (AnLF) requests the ML model using the ADRF service procedures, including the one-time certificate received in operation 6. In operation 8, the ADRF verifies the one-time certificate and, if the verification is successful, provides the NWDAF (AnLF) with the stored AI / ML model.

[0055] As stated above, AI / ML models are considered important intellectual property of their owners (e.g., 5GC vendors), and therefore, their confidentiality and integrity must be protected at all times. 3GPP is considering the feasibility of sharing or storing AI / ML models in network equipment that may be provided by different vendors. In this configuration, the AI / ML models should be protected from access and use by consumer NFs provided by a different vendor than the AI / ML models. However, there is currently no specified solution to this requirement. For example, the solution shown in Figure 3 does not provide the security needed in a multi-vendor network environment.

[0056] Embodiments of the present disclosure address these and other issues, problems, and / or difficulties by providing secure AI / ML model sharing between an NFp (e.g., an NWDAF MTLF) and an NFc (e.g., an NWDAF AnLF), optionally via AI / ML model storage at the ADRF. Such authorization may be based on an access token granted by the NRF pursuant to registration of model-related information by the NFp. The registered information may include interoperability information (e.g., an interoperability ID) from which the NRF can determine whether the requesting NFc is associated with a vendor that is authorized to access the AI / ML model.

[0057] Embodiments of the present disclosure may provide various benefits and / or advantages: By providing AI / ML model owners / producers with the ability to protect their AI / ML models during various transmission, storage, and retrieval scenarios, embodiments may improve the security of sensitive and / or confidential AI / ML models, thereby facilitating the deployment of such models in multi-vendor communication networks, such as 5GC.

[0058] In the following description of various embodiments, the terms NFp and NWDAF(MTLF) may be used interchangeably, and the terms NFc and NWDAF(AnLF) may be used interchangeably. Similarly, the terms "model," "ML model," and "AI / ML model" may be used interchangeably.

[0059] 4 shows a signaling diagram of a procedure involving an NWDAF (AnLF) 410, an NRF 420, and an NWDAF (MTLF) 430, in accordance with some embodiments of the present disclosure. While the operations shown in FIG. 4 are numerically labeled, this is intended for ease of explanation and does not require or imply any particular order of operations, unless otherwise stated below.

[0060] In operation 0a, the NWDAF (MTLF) registers ML model information in its NF profile in the NRF. The registered ML model information may include an interoperability ID for the ML model and an analysis ID (for the analysis generated by the ML model). The interoperability ID includes or is associated with a list of vendor IDs that are enabled to access the ML model associated with the analysis ID. In operation 0b, the NWDAF (AnLF) registers various information, including a vendor ID and one or more analysis IDs supported by the NWDAF (AnLF), in its NF profile in the NRF. The NRF may verify the vendor ID registered by the NWDAF (AnLF) based on authentication of the NWDAF (AnLF), for example, using a certificate or client certificate assertion (CCA). Alternatively, the NRF may verify the vendor ID registered by the NWDAF (AnLF) based on other trusted information registered in the profile of the NWDAF (AnLF) in the NRF.

[0061] In operation 1, the NWDAF (MTLF) performs one or more operations to secure the ML model associated with the analysis ID, such as encryption and / or integrity protection. The NWDAF (MTLF) may have pre-trained the ML model before performing these security operations. The security algorithms and keys used for operation 1 may be vendor-specific and / or outside the scope of the 3GPP specifications.

[0062] In operation 2, the NWDAF (AnLF) discovers the NWDAF (MTLF) via the NRF using existing procedures specified in 3GPP TS 23.288. For example, the NWDAF (AnLF) uses the analysis ID in question to select a suitable NFp, which in this case is the NWDAF (MTLF) that is the owner of the associated ML model.

[0063] In operation 3, the NWDAF (AnLF) invokes the Nnrf_AccessToken_Get request service operation on the NRF to obtain an access token. The NWDAF (AnLF) includes its vendor ID and one of its supported analysis IDs, previously registered in operation 0b. The NWDAF (AnLF) also includes an identifier of the target NF of the operation, in other words, the NWDAF (MTLF). In some variations, the NWDAF (AnLF) may also include an identifier of its own NF instance and / or NF type.

[0064] In operation 4, the NRF verifies that the NWDAF (AnLF) is authorized to access the ML model identified by the received analysis ID based on the information previously registered in operation 0a by the owner NWDAF (MTLF). For example, the NRF verifies that the vendor ID of the NWDAF (AnLF) received in operation 3 is among the list of vendor IDs associated with the interoperability ID. Once verified, the NRF grants an access token ("token1") and sends the access token to the NWDAF (MTLF) in a reply service operation.

[0065] As an example, the claims of token1 must include the analysis ID, the target NF instance (i.e., that of the NWDAF(ANLF)), and the service action to which it applies. Optionally, the claims of the token may include the vendor ID of the NWDAF(AnLF), which indicates that the validation was performed by the NRF (and does not need to be performed by the NWDAF(MTLF)).

[0066] In operation 5, the NWDAF(AnLF) invokes the Nnwdaf_MLModelProvision_Subscribe (or Nnwdaf_MLModelInfo_Request) service operation to the NWDAF(MTLF) to retrieve the ML model. The NWDAF(AnLF) includes its vendor ID, token1, and the analysis ID used to obtain token1 from the NRF. In operation 6, the NWDAF(MTLF) verifies, based on the received token1, that the NWDAF(AnLF) is authorized to retrieve the ML model associated with the analysis ID. If verified, the NWDAF(MTLF) invokes the reply service operation to send the NWDAF(AnLF) a URL associated with the NWDAF(MTLF) from which the ML model can be obtained.

[0067] In operation 7, the NWDAF (AnLF) fetches the ML model from the NWDAF (MTLF) via the URL (MTLF) received in operation 6 and using the access token (token1) received in operation 4. Prior to providing the ML model, the NWDAF (MTLF) again verifies that the NWDAF (AnLF) is authorized to access the ML model based on token1.

[0068] In operation 8, the NWDAF (AnLF) performs various security operations, such as decryption and integrity checks, on the retrieved ML model. These security operations may be based on the corresponding security operations performed by the NWDAF (MTLF) in operation 1. The security algorithms and keys used for this operation may be vendor-specific and / or outside the scope of the 3GPP specifications.

[0069] In some variations, the ML model information is obtained via a URL in a manner similar to that shown in Figure 4, but using a different service, message, and / or protocol. The signaling flow for these embodiments is the same as that shown in Figure 4, but other download services, messages, and / or protocols may be used in acts 3-7. As an example, the ML model may be obtained by URL via an unspecified procedure that is vendor implementation specific.

[0070] 5 shows a signaling diagram of a procedure involving an NWDAF (AnLF) 510, an NRF 520, an NWDAF (MTLF) 530, and an ADRF 540, in accordance with another embodiment of the present disclosure. While the operations shown in FIG. 5 are numerically labeled, this is intended for ease of explanation and does not require or imply any particular order of operations, unless otherwise stated below.

[0071] Actions 0a-b are identical to the corresponding actions in Figure 4 described above. Action 0c is identical to action 1 described above with respect to Figure 4.

[0072] In operation 1, the NWDAF (MTLF) invokes the Nadrf_DataManagement_StorageRequest service operation on the selected ADRF and includes a URL associated with the MTLF from which the ML model can be obtained. In some variations, the URL (MTLF) may be a one-time use URL. The NWDAF (MTLF) also includes the analysis ID and interoperability ID associated with the ML model, which were registered in operation 0a.

[0073] In act 1a, the ADRF securely fetches the protected ML model from the NWDAF (MTLF) using the URL (MTLF) received in act 1. In some embodiments, during this procedure, the NWDAF (MTLF) verifies that the fetching ADRF instance is the same ADRF instance (or a related ADRF instance, e.g., one that is part of the same NF set) to which the NWDAF (MTLF) sent the request in act 1.

[0074] In some embodiments, the ADRF may also request an access token from the NRF, which the ADRF provides when fetching the ML model. Based on this access token, the NWDAF (MTLF) verifies that the fetching ADRF is authorized to access the ML model. The ADRF can obtain this access token in a manner similar to that described below for operations 7a-b. For example, the ADRF's token request message may include its vendor ID, the analysis ID associated with the ML model, and the identifier of the target NF of the operation, in other words, the NWDAF (MTLF). In some variations, the NWDAF (AnLF) may also include identifiers of its own NF instance and / or NF type.

[0075] In operation 2, after storing the fetched ML model, the ADRF responds to the NWDAF (MTLF) by sending a URL associated with the ADRF from which the ML model can be obtained by the NWDAF (MTLF) or other NFs. In operation 2a, the ADRF registers with the NRF (e.g., in the ADRF's NF profile) the analysis ID and interoperability ID associated with the ML model, along with an identifier of the NWDAF (MTLF) that is the source / owner of the ML model.

[0076] Actions 3 and 4a-b are the same as actions 2-4, respectively, described above with respect to the embodiment shown in FIG.

[0077] In operation 5, the NWDAF (AnLF) invokes the Nnwdaf_MLModelProvision_Subscribe (or Nnwdaf_MLModelInfo_Request) service operation to the NWDAF (MTLF) to retrieve the ML model. The NWDAF (AnLF) includes the access token ("token1") received in operation 4a along with its vendor ID and analysis ID used to request the access token in operation 4a.

[0078] In operation 6, the NWDAF (MTLF) verifies that the NWDAF (AnLF) is authorized to retrieve the ML model associated with the analysis ID based on the received token1. If verified, the NWDAF (MTLF) invokes a response service operation to send the NWDAF (AnLF) a URL associated with the NWDAF (MTLF) from which the ML model can be obtained. Specifically, the NWDAF (MTLF) sends the URL (ADRF) received from the ADRF in operation 2.

[0079] In operation 7a, the NWDAF (AnLF) invokes the Nnrf_AccessToken_Get request service operation on the NRF to obtain an access token for obtaining the ML model from the ADRF. The NWDAF (AnLF) includes the identifier of the target NF of the operation, i.e., the ADRF, along with its vendor ID and the analysis ID associated with the ML model. In some variations, the NWDAF (AnLF) may also include identifiers of its own NF instance and / or NF type and / or identifiers of the NF instance and / or NF type of the NWDAF (MTLF).

[0080] In operation 7b, the NRF verifies that the NWDAF (AnLF) is authorized to access the ML model based on verifying that the vendor ID received in operation 7a is one of the vendors associated with the interoperability ID for the ML model associated with the analysis ID received in operation 7a. For example, the NRF can retrieve the interoperability ID registered by the NWDAF (MTLF) in operation 0a. If the verification is successful, the NRF authorizes the NWDAF (AnLF) and grants an access token (token2), which is sent to the NWDAF (AnLF) in a response service operation.

[0081] As an example, the claims in token2 should include the analysis ID, the target NF instance (i.e., that of the NWDAF(ANLF)), and the service action to which it applies. Optionally, the claims in the token may include the vendor ID of the NWDAF(AnLF), which indicates that the validation was performed by the NRF (and does not need to be performed by the NWDAF(MTLF)).

[0082] In operation 8, the NWDAF (AnLF) fetches the ML model from the ADRF via the URL (ADRF) received in operation 6 and using the access token (token2) received in operation 7b. Prior to providing the ML model, the ADRF verifies that the NWDAF (AnLF) is authorized to access the ML model based on token2. If the claim in token2 does not include the vendor ID of the NWDAF (AnLF), the ADRF also verifies that the vendor ID of the NWDAF (AnLF) is included in the interoperability ID associated with the ML model referenced by the URL (ADRF).

[0083] In operation 9, the NWDAF (AnLF) performs various security operations, such as decryption and integrity checks, on the retrieved ML model. These security operations may be based on the corresponding security operations performed by the NWDAF (MTLF) in operation 1. The security algorithms and keys used for this operation may be vendor-specific and / or outside the scope of the 3GPP specifications.

[0084] In some variations, the ML model information is obtained via a URL in a manner similar to that shown in Figure 5, but using a different service, message, and / or protocol. The signaling flow for these embodiments is the same as that shown in Figure 4, although other download services, messages, and / or protocols may be used in operations 1-2a and 4a-8. By way of example, the ML model may be obtained by URL via an unspecified procedure that is vendor implementation specific.

[0085] Although the embodiments are described above in the particular context of the NWDAF and its logical functions MTLF and AnLF, those skilled in the art will understand that the principles underlying the above-described embodiments are equally applicable to other NFs, logical functions, nodes, etc. that perform similar operations as these respective entities (e.g., with different names).

[0086] These embodiments described above may be further illustrated with reference to FIGS. 6-9 , which depict example methods (e.g., procedures) for a consumer NF, a producer NF, an NRF, and an ADRF, respectively. In other words, various features of the operations described below correspond to the various embodiments described above. The example methods illustrated in FIGS. 6-9 may be used cooperatively (e.g., with each other and with other procedures described herein) to provide benefits, advantages, and / or solutions to problems described herein. Although the example methods are illustrated in FIGS. 6-9 by particular blocks in a particular order, the operations corresponding to the blocks may be performed in a different order than shown, and may be combined and / or divided into blocks and / or operations having different functionality than shown. Optional blocks and / or operations are indicated by dashed lines.

[0087] More specifically, Figure 6 illustrates an example method (e.g., procedure) for a consumer NF (NFc) of a communications network (e.g., 5GC) in accordance with various embodiments of the present disclosure. The example method illustrated in Figure 6 may be performed by an NFc, such as an NWDAF (AnLF), or by network equipment implementing an NWDAF (AnLF), as described elsewhere herein.

[0088] The exemplary method includes the operation of block 620, in which an NFc sends a first request to an NRF of the communication network for a first access token associated with an ML model generated, owned, and / or maintained by a producer NF (NFp) of the communication network. The first request includes an analysis ID associated with the ML model, a vendor ID associated with the NFc, and an ID associated with the NFp. The exemplary method also includes the operation of block 630, in which the NFc receives a first response from the NRF, the first response including the first access token. The exemplary method also includes the operation of block 640, in which the NFc sends a second request for the ML model to the NFp. The second request includes the first access token, the analysis ID, and the vendor ID associated with the NFc. The exemplary method also includes the operation of block 650, in which the NFc receives a second response from the NFp, the second response including a URL associated with a second NF of the communication network from which the ML model can be obtained.

[0089] In some embodiments, the NFc is an NWDAF(AnLF) and / or the NFp is an NWDAF(MTLF).

[0090] In some embodiments, the second NF associated with the URL is NFp, and the example method also includes the operation of block 660, where NFc obtains the ML model from NFp using the URL and the first access token. Figure 4 shows examples of these embodiments.

[0091] In another embodiment, the second NF associated with the URL is an ADRF of the communication network, and the exemplary method comprises the following operations labeled with the corresponding block number: (670) Sending to the NRF a third request for a second access token associated with the ML model, wherein the third request includes an analysis ID associated with the ML model, a vendor ID associated with the NRF, and an ID associated with the ADRF; (680) receiving a third response from the first NF, the third response including the second access token; (690) Using the second access token and URL to obtain the ML model from the ADRF. Also includes.

[0092] FIG. 5 shows examples of these embodiments.

[0093] In some embodiments, the example method also includes the operation of block 695, in which the NFc performs a second security operation on the resulting ML model (e.g., from block 660 or 690). The second security operation corresponds to the first security operation performed on the ML model by the NFp. In some of these embodiments, the first security operation includes encryption and / or integrity protection, and the second security operation includes decryption corresponding to the encryption and / or an integrity check corresponding to the integrity protection.

[0094] In some embodiments, the exemplary method also includes the operation of block 610, where NFc is calculated in the NRF as follows: The vendor ID associated with the NFc; and One or more analysis IDs associated with ML models supported by NFc, including analysis IDs associated with ML models generated, owned, and / or maintained by NFp; and Register.

[0095] In some embodiments, the exemplary method also includes the operations of block 615, where the NFc performs a discovery procedure with the NRF to identify the NFp based on the analysis ID. The first request is sent (e.g., at block 620) in response to the discovery procedure.

[0096] In some embodiments, the first response from the NRF (e.g., at block 630) is based on a match, correspondence, or relationship between the vendor ID included in the first request and the interoperability ID associated with the NFp and the ML model. In some embodiments, the second response from the NFp (e.g., at block 650) is based on a match, correspondence, or relationship between the vendor ID included in the second request and the interoperability ID associated with the NFp and the ML model.

[0097] In addition, Figure 7 illustrates an example method (e.g., procedure) for an NFp of a communications network (e.g., 5GC) according to various embodiments of the present disclosure. The example method illustrated in Figure 7 may be performed by an NFp such as an NWDAF (MTLF) or by network equipment implementing an NWDAF (MTLF), as described elsewhere herein.

[0098] The example method includes the operation of block 750, in which the NFp receives a second request from an NFc of the communication network for an ML model created, owned, and / or maintained by the NFp. The second request includes a first access token issued by an NRF of the communication network, an analysis ID associated with the ML model, and a vendor ID associated with the NFc. The example method also includes the operation of block 760, in which, based on the first access token, the NFp authorizes the NFc to access the ML model associated with the analysis ID. The example method also includes the operation of block 770, in which, based on authorizing the NFc, the NFp sends the NFc a second response including a URL associated with a second NF of the communication network from which the ML model may be obtained.

[0099] In some embodiments, the NFc is an NWDAF(AnLF) and / or the NFp is an NWDAF(MTLF).

[0100] In some embodiments, the second NF associated with the URL is an NFp, and the example method also includes the operations of block 780, where the NFp provides the ML model to the NFc using the URL and the first access token. Figure 4 shows examples of these embodiments.

[0101] In another embodiment, the second NF associated with the URL is an ADRF of the communication network, and the exemplary method comprises the following operations labeled with the corresponding block number: (720) Sending a first request to the ADRF to store an ML model, wherein the first request includes the following: an analysis ID associated with the ML model; an interoperability ID including or associated with a list of vendors enabled to access the ML model; and a URL associated with the NFp from which the ML model can be obtained; (730) Submitting the ML model to ADRF using the URL associated with the NFp; and (740) receiving from the ADRF a first response including a URL associated with the ADRF, which is sent in a second response to the NFc (e.g., at block 770); Also includes.

[0102] FIG. 5 shows examples of these embodiments.

[0103] In some of these embodiments, providing the ML model to the ADRF in block 730 includes operations in sub-block 731, in which the NFp may verify the third access token issued by the NRF and provided by the ADRF. In some of these embodiments, the second response (e.g., in block 770) also includes an identifier of the ADRF in which the ML model is stored.

[0104] In some embodiments, the example method also includes the operation of block 715, in which the NFp performs a first security operation on the ML model before providing it to the NFc (e.g., at 780) or before providing it to the ADRF (e.g., at block 730). The first security operation includes encryption and / or integrity protection.

[0105] In some embodiments, the example method also includes the operation of block 710, in which the NFp registers with the NRF of the communication network the following information: an analysis ID associated with the ML model and an interoperability ID that includes or is associated with a list of vendors that are enabled to access the ML model.

[0106] In addition, Figure 8 illustrates an example method (e.g., procedure) for an NRF of a communication network (e.g., 5GC) according to various embodiments of the present disclosure. The example method illustrated in Figure 8 may be performed by an NRF or by network equipment implementing an NRF, as described elsewhere herein.

[0107] The exemplary method includes the operations of block 850, in which the NRF registers the following information in a profile for an NFp of the communication network: a first analysis ID associated with an ML model generated, owned, and / or maintained by the NFp; and an interoperability ID including or associated with a list of vendors enabled to access the ML model. The exemplary method also includes the operations of block 860, in which the NRF receives a first request for a first access token associated with the ML model from an NFc of the communication network. The first request includes the first analysis ID associated with the ML model, a vendor ID associated with the NFc, and an ID associated with the NFp. The exemplary method also includes the operations of block 860, in which the NRF authorizes the NFc to access the ML model based on a match, correspondence, or relationship between the vendor ID included in the first request and the interoperability ID registered in the profile for the NFp. The example method also includes the operation of block 870, in which the NRF sends a first response to the NFc that includes the first access token.

[0108] In some embodiments, the exemplary method comprises the following operations, labeled with the corresponding block numbers: (880) receiving a third request from the NFc for a second access token associated with the ML model, wherein the third request includes an analysis ID associated with the ML model, a vendor ID associated with the NFc, and an ID associated with the ADRF of the communication network; (885) authorizing the NFc to access the ML model based on a match, correspondence, or relationship between the vendor ID included in the third request and an interoperability ID registered in the profile for the NFp; sending a third response to (890)NFc that includes the second access token; Also includes.

[0109] Figure 5 shows examples of these embodiments. In some of these embodiments, the exemplary method includes the following operations, labeled with the corresponding block numbers: (830) receiving a fourth request from the ADRF for a third access token associated with the ML model, wherein the fourth request includes an analysis ID associated with the ML model, a vendor ID associated with the ADRF, and an ID associated with the NFp; (835) authorizing the ADRF to access the ML model based on a match, correspondence, or relationship between the vendor ID included in the fourth request and the interoperability ID registered in the profile for the NFp; and sending a fourth response to the (840) ADRF containing the third access token; Also includes.

[0110] In some embodiments, the example method also includes the operation of block 815, in which the NRF registers the following information in a profile for an NFc of the communication network: a vendor ID associated with the NFc and one or more analysis IDs associated with ML models supported by the NFc, including the first analysis ID.

[0111] In some embodiments, the example method also includes the operation of block 820, in which the NRF registers the following information in a profile for the ADRF of the communication network: a first analysis ID associated with the ML model, an interoperability ID, and an ID associated with the NFp.

[0112] In some embodiments, the NFc is an NWDAF(AnLF) and / or the NFp is an NWDAF(MTLF).

[0113] In addition, Figure 9 illustrates an example method (e.g., procedure) for an ADRF of a communications network (e.g., 5GC) according to various embodiments of the present disclosure. The example method illustrated in Figure 9 may be performed by an ADRF or by network equipment implementing an ADRF, as described elsewhere herein.

[0114] The exemplary method includes the operation of block 910, in which the ADRF receives a first request from an NFp of a communication network to store an ML model created, owned, and / or maintained by the NFp. The first request includes the following: an analysis ID associated with the ML model; an interoperability ID including or associated with a list of vendors enabled to access the ML model; and a URL associated with the NFp from which the ML model can be obtained. The exemplary method also includes the operation of block 940, in which the ADRF obtains the ML model from the NFp using the URL associated with the NFp. The exemplary method also includes the operation of block 950, in which the ADRF sends the NFp a first response including the URL associated with the ADRF from which the ML model can be obtained.

[0115] Figure 5 illustrates an example in which the ADRF performs operations corresponding to the exemplary method illustrated by Figure 9. In some embodiments, the exemplary method includes the following operations, labeled with corresponding block numbers: (920) sending a fourth request to the NRF of the communication network in response to the first request for a third access token associated with the ML model, wherein the fourth request includes an analysis ID associated with the ML model, a vendor ID associated with the ADRF, and an ID associated with the NFp; (930) receiving a fourth response from the NRF, the fourth response including the third access token; Also includes.

[0116] In such an embodiment, obtaining the ML model from the NFp (e.g., at block 940) is based on the third access token.

[0117] In some embodiments, the example method also includes the operations of block 970, where the ADRF provides the ML model to an NFc of the communication network using a URL associated with the ADRF. In some of these embodiments, providing the ML model to the NFc in block 970 includes the operations of sub-block 971, where the ADRF verifies a second access token issued by the NRF and provided by the NFc.

[0118] In some embodiments, the exemplary method also includes the operation of block 960, in which the ADRF registers the following information with the NRF of the communication network: the first analysis ID, the interoperability ID, and the ID associated with the NFp.

[0119] In some embodiments, the NFc is an NWDAF(AnLF) and / or the NFp is an NWDAF(MTLF).

[0120] While various embodiments are described above with respect to methods, techniques, and / or procedures, those skilled in the art will readily appreciate that such methods, techniques, and / or procedures may be embodied in various combinations of hardware and software in a variety of systems, communication devices, computing devices, control devices, apparatuses, non-transitory computer-readable media, computer program products, and the like.

[0121] 10 illustrates an example of a communications system 1000 according to some embodiments. In this example, the communications system 1000 includes a communications network 1002 including an access network 1004 (e.g., a RAN) and a core network 1006 including one or more core network nodes 1008. The access network 1004 includes one or more access network nodes, such as network nodes 1010a-b (one or more of which may be generically referred to as network node 1010), or any other similar 3GPP access node or non-3GPP access point. The network node 1010 facilitates direct or indirect connectivity of UEs 1012a-d (one or more of which may be generically referred to as UEs 1012) to the core network 1006, such as by connecting the UEs 1012a-d to the core network 1006 via one or more wireless connections.

[0122] Exemplary wireless communication over a wireless connection includes sending and / or receiving wireless signals using electromagnetic waves, radio waves, infrared waves, and / or other types of signals suitable for conveying information without the use of wires, cables, or other material conductors. Moreover, in different embodiments, communication system 1000 may include any number of wired or wireless networks, network nodes, UEs, and / or any other components or systems that may facilitate or participate in the communication of data and / or signals, whether via wired or wireless connections. Communication system 1000 may include and / or interface with any type of communication, telecommunication, data, cellular, wireless network, and / or other similar type systems.

[0123] The UE 1012 may be any of a wide variety of communication devices, including a wireless device configured, configured, and / or operable to communicate wirelessly with the network node 1010 and other communication devices. Similarly, the network node 1010 is configured, capable of, configured, and / or operable to communicate, directly or indirectly, with the UE 1012 and / or with other network nodes or equipment in the communications network 1002 to enable and / or provide network access, such as wireless network access, and / or to perform other functions, such as administration, in the communications network 1002.

[0124] In the depicted example, the core network 1006 connects the network node 1010 to one or more hosts, such as the host 1016. These connections may be direct or indirect through one or more intermediary networks or devices. In other examples, the network node may be directly coupled to the host. The core network 1006 includes one or more core network nodes (e.g., 1008) structured with hardware and software components. Features of these components may be substantially similar to those described with respect to the UEs, network nodes, and / or hosts, and therefore, those descriptions are generally applicable to the corresponding components of the core network node 1008. Exemplary core network nodes include one or more of a Mobile Switching Center (MSC), a Mobility Management Entity (MME), a Home Subscriber Server (HSS), an Access and Mobility Management Function (AMF), a Session Management Function (SMF), an Authentication Server Function (AUSF), a Subscription Identifier De-concealing Function (SIDF), a Unified Data Management (UDM), a Security Edge Protection Proxy (SEPP), a Network Publishing Function (NEF), and / or a User Plane Function (UPF).

[0125] The host 1016 may be owned or under the control of, and operated by or on behalf of, a service provider other than the operator or provider of the access network 1004 and / or the communication network 1002. The host 1016 may host various applications to provide one or more services. Examples of such applications include live and pre-recorded audio / video content, data collection services such as retrieving and compiling data about various ambient conditions detected by multiple UEs, analytics functions, social media, functions for controlling or possibly interacting with remote devices, functions for an alarm and surveillance center, or any other such function performed by a server.

[0126] 10 enables connectivity between UEs, network nodes, and hosts. In that sense, the communication system may be configured to operate according to predefined rules or procedures, such as a particular standard, including, but not limited to, Global System for Mobile Communications (GSM), Universal Mobile Telecommunications System (UMTS), Long Term Evolution (LTE), and / or other suitable 2G, 3G, 4G, 5G standards, or any applicable future generation standard (e.g., 6G), a wireless local area network (WLAN) standard such as the Institute of Electrical and Electronics Engineers (IEEE) 802.11 standard (WiFi), and / or any low power wide area network (LPWAN) standard such as Worldwide Interoperability for Microwave Access (WiMax), Bluetooth, Z-Wave, near field communications (NFC) ZigBee, LiFi, and / or LoRa and Sigfox.

[0127] In some examples, the communication network 1002 is a cellular network that implements 3GPP standardized features. Thus, the communication network 1002 may support network slicing to provide different logical networks to different devices connected to the communication network 1002. For example, the communication network 1002 may provide Ultra-Reliable Low-Latency Communication (URLLC) services to some UEs while providing enhanced Mobile Broadband (eMBB) services to other UEs and / or massive machine-based communication (mMTC) / massive IoT services to still further UEs.

[0128] In some examples, the UE 1012 is configured to transmit and / or receive information without direct human interaction. For example, the UE may be designed to transmit information to the access network 1004 on a predetermined schedule, when triggered by an internal or external event, or in response to a request from the access network 1004. Furthermore, the UE may be configured to operate in a single or multi-RAT or multi-standard mode. For example, the UE may operate in any one or a combination of Wi-Fi, NR (New Radio), and LTE, or in other words, be configured for multi-radio dual connectivity (MR-DC), such as E-UTRAN (Evolved UMTS Terrestrial Radio Access Network) New Radio-Dual Connectivity (EN-DC).

[0129] In this example, the hub 1014 communicates with the access network 1004 to facilitate indirect communication between one or more UEs (e.g., UEs 1012c and / or 1012d) and a network node (e.g., network node 1010b). In some examples, the hub 1014 may be a controller, a router, a content source, a content analyzer, or any of the other communication devices described herein with respect to UEs. For example, the hub 1014 may be a broadband router that enables access to the core network 1006 for the UE. As another example, the hub 1014 may be a controller that sends commands or instructions to one or more actuators in the UE. The commands or instructions may be received from the UE, the network node 1010, or may be due to executable code, scripts, processes, or other instructions in the hub 1014. As another example, the hub 1014 may be a data collector that acts as temporary storage for UE data and, in some embodiments, may perform analysis or other processing of the data. As another example, the hub 1014 may be a content source. For example, for a UE that is a VR headset, display, loudspeaker, or other media distribution device, the hub 1014 may retrieve, via a network node, VR assets, video, audio, or other media or data related to sensory information, which the hub 1014 then provides to the UE either directly, after performing local processing, and / or after adding additional local content. In yet another example, the hub 1014 acts as a proxy server or orchestrator for the UEs, particularly if one or more of the UEs are low energy IoT devices.

[0130] The hub 1014 may have a constant / permanent or intermittent connection to the network node 1010b. The hub 1014 may also enable different communication schemes and / or schedules between the hub 1014 and the UEs (e.g., UEs 1012c and / or 1012d) and between the hub 1014 and the core network 1006. In other examples, the hub 1014 is connected to the core network 1006 and / or one or more UEs via a wired connection. Moreover, the hub 1014 may be configured to connect to an M2M service provider through the access network 1004 and / or to another UE via a direct connection. In some scenarios, a UE may establish a wireless connection with the network node 1010 while still connected via a wired or wireless connection through the hub 1014. In some embodiments, the hub 1014 may be a dedicated hub, i.e., a hub whose primary function is to route communications from / to the UE to / from the network node 1010b. In other embodiments, the hub 1014 may be a non-dedicated hub, i.e., a device that is capable of operating to route communications between the UE and the network node 1010b, but that is further capable of operating as a communication initiation and / or termination point for some data channels.

[0131] 11 illustrates a UE 1100, according to some embodiments. Examples of a UE include, but are not limited to, a smartphone, a mobile phone, a cell phone, a voice-over-IP (VoIP) phone, a wireless local loop phone, a desktop computer, a personal digital assistant (PDA), a wireless camera, a gaming console or device, a music storage device, a playback appliance, a wearable terminal device, a wireless endpoint, a mobile station, a tablet, a laptop computer, a laptop embedded equipment (LEE), a laptop mounted equipment (LME), a smart device, a wireless customer premises equipment (CPE), a vehicle-mounted or vehicle-embedded / integrated wireless device, etc. Other examples include any UE identified by 3GPP, including a narrowband Internet of Things (NB-IoT) UE, a machine-type communication (MTC) UE, and / or an enhanced MTC (eMTC) UE.

[0132] A UE may support device-to-device (D2D) communications, for example, by implementing 3GPP standards for sidelink communications, dedicated short-range communications (DSRC), vehicle-to-vehicle (V2V), vehicle-to-infrastructure (V2I), or vehicle-to-everything (V2X). In other examples, a UE may not necessarily have a user in the sense of a human user who owns and / or operates an associated device. Instead, a UE may represent a device (e.g., a smart sprinkler controller) that is intended for sale to or operation by a human user but may not be associated with or initially be associated with a particular human user. Alternatively, a UE may represent a device (e.g., a smart power meter) that is not intended for sale to or operation by an end user but may be associated with or operated for the user's benefit.

[0133] The UE 1100 includes a processing circuit 1102 that is operably coupled via a bus 1104 to an input / output interface 1106, a power source 1108, a memory 1110, a communication interface 1112, and possibly other components not explicitly shown. Some UEs may utilize all or a subset of the components shown in FIG. 11 . The level of integration between components may vary from UE to UE. Additionally, some UEs may include multiple instances of a component, such as multiple processors, memories, transceivers, transmitters, receivers, etc.

[0134] The processing circuit 1102 is configured to process instructions and data and may be configured to implement any sequential state machine that operates to execute instructions stored in the memory 1110 as a machine-readable computer program. The processing circuit 1102 may be implemented as one or more hardware-implemented state machines (e.g., in discrete logic, a field programmable gate array (FPGA), an application-specific integrated circuit (ASIC), etc.), programmable logic together with appropriate firmware, one or more stored computer programs such as a microprocessor or digital signal processor (DSP) together with appropriate software, a general-purpose processor, or any combination of the above. For example, the processing circuit 1102 may include multiple central processing units (CPUs).

[0135] In this example, the input / output interface 1106 may be configured to provide one or more interfaces to an input device, an output device, or one or more input and / or output devices. Examples of output devices include a speaker, a sound card, a video card, a display, a monitor, a printer, an actuator, an emitter, a smart card, another output device, or any combination thereof. An input device may allow a user to capture information into the UE 1100. Examples of input devices include a touch-sensitive or presence-sensitive display, a camera (e.g., a digital camera, a digital video camera, a webcam, etc.), a microphone, a sensor, a mouse, a trackball, a directional pad, a trackpad, a scroll wheel, a smart card, etc. A presence-sensitive display may include a capacitive or resistive touch sensor for detecting input from a user. The sensor may be, for example, an accelerometer, a gyroscope, a tilt sensor, a force sensor, a magnetometer, a light sensor, a proximity sensor, a biometric sensor, etc., or any combination thereof. An output device may use the same type of interface port as the input device. For example, a universal serial bus (USB) port may be used to accommodate input and output devices.

[0136] In some embodiments, the power source 1108 is structured as a battery or battery pack. Other types of power sources may be used, such as an external power source (e.g., an electrical outlet), a photovoltaic device, or a battery. The power source 1108 may further include power circuitry for delivering power to various portions of the UE 1100 from the power source 1108 itself and / or from an external power source via an interface such as an input circuit or a power cable. Delivering power may be for charging the power source 1108, for example. The power circuitry may perform any formatting, conversion, or other modification on the power from the power source 1108 to make it suitable for the respective components of the UE 1100 being powered.

[0137] The memory 1110 may be or be configured to include memory, such as random access memory (RAM), read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), magnetic disk, optical disk, hard disk, removable cartridge, flash drive, etc. In one example, the memory 1110 includes one or more application programs 1114, such as an operating system, a web browser application, a widget, a gadget engine, or other applications, and corresponding data 1116. The memory 1110 may store any of a variety of different operating systems or combinations of operating systems for use by the UE 1100.

[0138] The memory 1110 may be configured to include several physical drive units, such as a redundant array of independent disks (RAID), flash memory, a USB flash drive, an external hard disk drive, a thumb drive, a pen drive, a key drive, a high-density digital versatile disc (HD-DVD) optical disc drive, an internal hard disk drive, a Blu-ray optical disc drive, a holographic digital data storage (HDDS) optical disc drive, an external mini dual in-line memory module (DIMM), a synchronous dynamic random access memory (SDRAM), an external micro-DIMM SDRAM, a smart card memory such as a tamper-resistant module in the form of a universal integrated circuit card (UICC) including one or more subscriber identity modules (SIMs), such as a USIM and / or ISIM, other memory, or any combination thereof. The UICC may be, for example, an embedded UICC (eUICC), an integrated UICC (iUICC), or a removable UICC, commonly known as a "SIM card." The memory 1110 may enable the UE 1100 to access, offload, or upload data, instructions, application programs, etc. stored on a temporary or non-transitory memory medium. An article of manufacture, such as an article of manufacture utilizing the communication system, may be tangibly embodied as or in the memory 1110, which may be or comprise a device-readable storage medium.

[0139] The processing circuit 1102 may be configured to communicate with an access network or other networks using a communication interface 1112. The communication interface 1112 may comprise one or more communication subsystems and may include or be communicatively coupled to an antenna 1122. The communication interface 1112 may include one or more transceivers used to communicate, such as by communicating with one or more remote transceivers of another device capable of wireless communication (e.g., another UE or network node in the access network). Each transceiver may include a transmitter 1118 and / or a receiver 1120 suitable for providing network communication (e.g., optical, electrical, frequency allocation, etc.). Moreover, the transmitter 1118 and receiver 1120 may be coupled to one or more antennas (e.g., 1122) and may share circuit components, software, or firmware, or alternatively, may be implemented separately.

[0140] In the illustrated embodiment, the communication capabilities of communication interface 1112 may include cellular communication, Wi-Fi communication, LPWAN communication, data communication, voice communication, multimedia communication, short-range communication such as Bluetooth, near-field communication, location-based communication such as using a Global Positioning System (GPS) to determine location, another similar communication capability, or any combination thereof. Communications may be implemented in accordance with one or more communication protocols and / or standards, such as IEEE 802.11, Code Division Multiple Access (CDMA), Wideband Code Division Multiple Access (WCDMA), GSM, LTE, New Radio (NR), UMTS, WiMax, Ethernet, Transmission Control Protocol / Internet Protocol (TCP / IP), Synchronous Optical Networking (SONET), Asynchronous Transfer Mode (ATM), QUIC, Hypertext Transfer Protocol (HTTP), etc.

[0141] Regardless of the type of sensor, the UE may provide an output of data captured by the UE's sensors to a network node via a wireless connection through the UE's communications interface 1112. Data captured by the UE's sensors may be communicated to a network node via another UE over a wireless connection. The output may be periodic (e.g., once every 15 minutes when reporting sensed temperature), in response to a triggering event (e.g., an alert is sent when humidity is detected), in response to a request (e.g., a user-initiated request), random (e.g., to even out the load from reporting from several sensors), or a continuous stream (e.g., a live video feed of a patient).

[0142] 12 illustrates a network node 1200 according to some embodiments. Examples of network nodes include, but are not limited to, access points (e.g., wireless access points) and base stations (e.g., wireless base stations, Node Bs, eNBs, gNBs, etc.).

[0143] Base stations may be categorized based on the amount of coverage they provide (or, stated another way, their transmit power level) and may therefore be referred to as femto, pico, micro, or macro base stations depending on the amount of coverage provided. A base station may be a relay node or a relay donor node that controls a relay. A network node may also include one or more (or all) parts of a distributed radio base station, such as a centralized digital unit and / or a remote radio unit (RRU), sometimes referred to as a remote radio head (RRH). Such remote radio units may or may not be integrated with an antenna, as in an antenna-integrated radio. Portions of a distributed radio base station may also be referred to as nodes in a distributed antenna system (DAS).

[0144] Other examples of network nodes include a multiple transmission point (multi-TRP) 5G access node, a multi-standard radio (MSR) equipment such as an MSR BS, a network controller such as a radio network controller (RNC) or a base station controller (BSC), a base transceiver station (BTS), a transmission point, a transmitting node, a multi-cell / multicast coordination entity (MCE), an operation and maintenance (O&M) node, an operation support system (OSS) node, a self-organizing network (SON) node, a positioning node (e.g., an evolved serving mobile location center (E-SMLC)), and / or a minimization of drive test (MDT).

[0145] As a more specific example, one or more network nodes 1200 may be configured to perform operations by various NFs in the various methods or procedures described herein. As a more specific example, one or more network nodes 1200 may be configured to perform operations by a consumer NF (e.g., an NWDAF AnLF), a producer NF (e.g., an NWDAF MTLF), an NRF, and an ADRF.

[0146] The network node 1200 includes a processing circuit 1202, a memory 1204, a communication interface 1206, and a power source 1208. The network node 1200 may be composed of multiple physically separate components (e.g., a Node B component and an RNC component, or a BTS component and a BSC component, etc.), each of which may have their own respective components. In some scenarios in which the network node 1200 comprises multiple separate components (e.g., a BTS component and a BSC component), one or more of the separate components may be shared among several network nodes. For example, a single RNC may control multiple Node Bs. In such scenarios, each unique Node B and RNC pair may, in some instances, be considered a single separate network node. In some embodiments, the network node 1200 may be configured to support multiple radio access technologies (RATs). In such embodiments, some components may be duplicated (e.g., separate memory 1204 for different RATs) and some components may be reused (e.g., the same antenna 1210 may be shared by different RATs). Network node 1200 may also include multiple sets of the various shown components for different wireless technologies, e.g., GSM, WCDMA, LTE, NR, WiFi, Zigbee, Z-wave, LoRaWAN, radio frequency identification (RFID), or Bluetooth wireless technologies, integrated into network node 1200. These wireless technologies may be integrated into the same or different chips or sets of chips and other components within network node 1200.

[0147] The processing circuit 1202 may comprise one or more combinations of a microprocessor, controller, microcontroller, central processing unit, digital signal processor, application specific integrated circuit, field programmable gate array, or any other suitable computing device, resource, or combination of hardware, software, and / or coded logic operable to provide the network node 1200 functionality, either alone or in conjunction with other network node 1200 components such as memory 1204.

[0148] In some embodiments, the processing circuit 1202 comprises a system on a chip (SOC). In some embodiments, the processing circuit 1202 includes one or more of a radio frequency (RF) transceiver circuit 1212 and a baseband processing circuit 1214. In some embodiments, the RF transceiver circuit 1212 and the baseband processing circuit 1214 may be on separate chips (or sets of chips), boards, or units, such as a radio unit and a digital unit. In alternative embodiments, some or all of the RF transceiver circuit 1212 and the baseband processing circuit 1214 may be on the same chip or set of chips, board, or unit.

[0149] The memory 1204 may comprise any form of volatile or non-volatile computer-readable memory, including, but not limited to, persistent storage, solid-state memory, remotely mounted memory, magnetic media, optical media, random access memory (RAM), read-only memory (ROM), mass storage media (e.g., hard disk), removable storage media (e.g., flash drive, compact disc (CD) or digital video disc (DVD)), and / or any other volatile or non-volatile, non-transitory device-readable and / or computer-executable memory device that stores information, data, and / or instructions that can be used by the processing circuit 1202. The memory 1204 may store any suitable instructions, data, or information, including applications including one or more of computer programs, software, logic, rules, code, tables, and / or other instructions (collectively denoted computer program 1204a, which may be in the form of a computer program product) that can be executed by the processing circuit 1202 and utilized by the network node 1200. The memory 1204 may be used to store calculations performed by the processing circuit 1202 and / or data received via the communication interface 1206. In some embodiments, the processing circuit 1202 and the memory 1204 are integrated.

[0150] The communications interface 1206 is used for wired or wireless communication of signaling and / or data between network nodes, access networks, and / or UEs. As shown, the communications interface 1206 comprises a port / terminal 1216 for sending and receiving data to and from a network, e.g., over a wired connection. The communications interface 1206 also includes a radio front-end circuit 1218 that is coupled to an antenna 1210 or, in some embodiments, may be part of the antenna 1210. The radio front-end circuit 1218 comprises a filter 1220 and an amplifier 1222. The radio front-end circuit 1218 may be connected to the antenna 1210 and the processing circuit 1202. The radio front-end circuit may be configured to condition signals communicated between the antenna 1210 and the processing circuit 1202. The radio front-end circuit 1218 may receive digital data to be sent to another network node or UE via a wireless connection. The radio front-end circuitry 1218 may convert the digital data into radio signals having appropriate channel and bandwidth parameters using a combination of filters 1220 and / or amplifiers 1222. The radio signals may then be transmitted via the antenna 1210. Similarly, when receiving data, the antenna 1210 may collect the radio signals, which are then converted into digital data by the radio front-end circuitry 1218. The digital data may be passed to the processing circuitry 1202. In other embodiments, the communication interface may comprise different components and / or different combinations of components.

[0151] In some alternative embodiments, network node 1200 does not include a separate radio front-end circuit 1218; instead, processing circuit 1202 includes the radio front-end circuitry and is connected to antenna 1210. Similarly, in some embodiments, all or a portion of RF transceiver circuitry 1212 is part of communications interface 1206. In still other embodiments, communications interface 1206 includes one or more ports or terminals 1216, radio front-end circuitry 1218, and RF transceiver circuitry 1212 as part of a radio unit (not shown), and communications interface 1206 communicates with baseband processing circuitry 1214 that is part of a digital unit (not shown).

[0152] The antenna 1210 may include one or more antennas or an antenna array configured to send and / or receive wireless signals. The antenna 1210 may be coupled to the radio front-end circuitry 1218 and may be any type of antenna capable of wirelessly transmitting and receiving data and / or signals. In some embodiments, the antenna 1210 is separate from the network node 1200 and connectable to the network node 1200 through an interface or port.

[0153] The antenna 1210, the communication interface 1206, and / or the processing circuit 1202 may be configured to perform any receiving operation and / or some obtaining operation described herein as being performed by a network node. Any information, data, and / or signal may be received from a UE, another network node, and / or any other network equipment. Similarly, the antenna 1210, the communication interface 1206, and / or the processing circuit 1202 may be configured to perform any transmitting operation described herein as being performed by a network node. Any information, data, and / or signal may be transmitted to a UE, another network node, and / or any other network equipment.

[0154] The power source 1208 provides power to the various components of the network node 1200 in a form suitable for each component (e.g., at the voltage and current levels required for each respective component). The power source 1208 may further comprise, or be coupled to, power management circuitry for supplying the components of the network node 1200 with power for performing the functions described herein. For example, the network node 1200 may be connectable to an external power source (e.g., a power grid, an electrical outlet) via an input circuit or interface such as an electrical cable, whereby the external power source supplies power to the power circuitry of the power source 1208. As a further example, the power source 1208 may comprise a power source in the form of a battery or battery pack connected to or integrated in the power circuitry. The battery may provide backup power in the event that the external power source fails.

[0155] 12 to provide certain aspects of the network node's functionality, including any of the functionality described herein and / or functionality necessary to support the subject matter described herein. For example, network node 1200 may include user interface devices to enable input of information into network node 1200 and output of information from network node 1200. This may enable a user to perform diagnostic, maintenance, repair, and other administrative functions for network node 1200.

[0156] 13 is a block diagram of a host 1300, which may be an embodiment of the host 1016 of FIG. 10, in accordance with various aspects described herein. The host 1300 may be or comprise various combinations of hardware and / or software, including a standalone server, a blade server, a cloud-implemented server, a distributed server, a virtual machine, a container, or processing resources in a server farm. The host 1300 may provide one or more services to one or more UEs.

[0157] Host 1300 includes a processing circuit 1302 operably coupled to an input / output interface 1306, a network interface 1308, a power supply 1310, and a memory 1312 via a bus 1304. In other embodiments, other components may be included. Features of these components may be substantially similar to those described with respect to the devices of previous figures, such as FIGS. 11 and 12, and therefore, those descriptions are generally applicable to the corresponding components of host 1300.

[0158] Memory 1312 may include one or more computer programs, including one or more host application programs 1314 and data 1316, which may include user data, e.g., data generated by a UE for host 1300 or data generated by host 1300 for the UE. Embodiments of host 1300 may utilize only a subset or all of the shown components. Host application program 1314 may be implemented in a container-based architecture and may provide support for video codecs (e.g., Versatile Video Coding (VVC), High Efficiency Video Coding (HEVC), Advanced Video Coding (AVC), MPEG, VP9) and audio codecs (e.g., FLAC, Advanced Audio Coding (AAC), MPEG, G.711), including transcoding for multiple different classes, types, or implementations of UE (e.g., handsets, desktop computers, wearable display systems, heads-up display systems). The host application program 1314 may also provide user authentication and license checks, and may periodically report health, route, and content availability to a central node, such as a device in the core network or a device on the edge of the core network. Thus, the host 1300 may select and / or direct different hosts for over-the-top services for the UE. The host application program 1314 may support various protocols, such as HTTP Live Streaming (HLS) protocol, Real-Time Messaging Protocol (RTMP), Real-Time Streaming Protocol (RTSP), Dynamic Adaptive Streaming over HTTP (MPEG-DASH), etc.

[0159] FIG. 14 is a block diagram illustrating a virtualization environment 1400 in which functionality implemented by some embodiments may be virtualized. In this context, virtualizing means creating a virtual version of an apparatus or device, which may include virtualizing a hardware platform, storage devices, and networking resources. Virtualization, as used herein, may apply to any device described herein, or components thereof, and relates to implementations in which at least a portion of functionality is implemented as one or more virtual components. Some or all of the functionality described herein may be implemented as virtual components executed by one or more virtual machines (VMs) implemented in one or more virtual environments 1400 hosted by one or more of the hardware nodes, such as a network node, a UE, a core network node, or a hardware computing device acting as a host. Furthermore, in embodiments in which the virtual node does not require wireless connectivity (e.g., to a core network node or host), then the node may be fully virtualized.

[0160] An application 1402 (which may alternatively be referred to as a software instance, a virtual appliance, a network function, a virtual node, a virtual network function, etc.) is run in the virtualized environment 1400 to implement some of the features, functions, and / or benefits of some of the embodiments disclosed herein.

[0161] For example, various NFs (or portions thereof) described herein with respect to other figures may be implemented as virtual network functions 1402 in the virtualized environment 1400. As a more specific example, a consumer NF (e.g., an NWDAF AnLF), a producer NF (e.g., an NWDAF MTLF), an NRF, and / or an ADRF may be implemented as virtual network functions 1402 in the virtualized environment 1400.

[0162] The hardware 1404 includes processing circuitry, memory that stores software and / or instructions executable by the hardware processing circuitry, and / or other hardware devices described herein, such as network interfaces, input / output interfaces, etc. Software is executed by the processing circuitry to instantiate one or more virtualization layers 1406 (also called hypervisors or virtual machine monitors (VMMs)), provide VMs 1408a-b (one or more of which may be generally referred to as VMs 1408), and / or implement any of the functions, features, and / or benefits described with respect to some embodiments described herein. The virtualization layer 1406 may present to the VMs 1408 a virtual operating platform that appears to be networking hardware.

[0163] The VMs 1408 may comprise virtual processing, virtual memory, virtual networking or interfaces, and virtual storage, and may be run by a corresponding virtualization layer 1406. Different embodiments of instances of virtual appliances 1402 may be implemented on one or more of the VMs 1408, and the implementations may be done in different ways. Hardware virtualization is referred to in some contexts as network functions virtualization (NFV). NFV may be used to consolidate many network equipment types onto industry-standard high-volume server hardware, physical switches, and physical storage, which may be located in data centers and customer premises equipment.

[0164] In the context of NFV, each VM 1408 may be a software implementation of a physical machine that runs programs as if those programs were running on a physical, non-virtualized machine. Each VM 1408 and the portion of the hardware 1404 on which it runs, whether hardware dedicated to that VM and / or hardware shared by that VM with other VMs, form a separate virtual network element. Further, in the context of NFV, a virtual network function is responsible for handling a particular network function running in one or more VMs 1408 on the hardware 1404 and corresponds to the application 1402.

[0165] The hardware 1404 may be implemented in a standalone network node with general or specific components. The hardware 1404 may implement some functions via virtualization. Alternatively, the hardware 1404 may be part of a larger cluster of hardware (e.g., as in a data center or CPE) where many hardware nodes cooperate and are managed via a management and orchestration 1410 that, among other things, oversees the lifecycle management of the application 1402. In some embodiments, the hardware 1404 is coupled to one or more radio units, each including one or more transmitters and one or more receivers, which may be coupled to one or more antennas. The radio units may communicate directly with other hardware nodes via one or more appropriate network interfaces and may be used in combination with virtual components to provide a virtual node with wireless capabilities, such as a wireless access node or base station. In some embodiments, some signaling may be provided using a control system 1412, which may alternatively be used for communication between the hardware nodes and the radio units.

[0166] 15 shows a communication diagram of a host 1502 communicating with a UE 1506 via a network node 1504 over a partial wireless connection, according to some embodiments. Exemplary implementations according to various embodiments of a UE (such as the UE 1012a of FIG. 10 and / or the UE 1100 of FIG. 11), a network node (such as the network node 1010a of FIG. 10 and / or the network node 1200 of FIG. 12), and a host (such as the host 1016 of FIG. 10 and / or the host 1300 of FIG. 13) described in the previous paragraphs will now be described with reference to FIG. 15.

[0167] Similar to the host 1300, an embodiment of the host 1502 includes hardware such as a communications interface, processing circuitry, and memory. The host 1502 also includes software stored on or accessible by the host 1502 and executable by the processing circuitry. The software includes a host application that may be operable to provide services to a remote user, such as a UE 1506 connecting via an over-the-top (OTT) connection 1550 extending between the UE 1506 and the host 1502. In providing services to the remote user, the host application may provide user data that is transmitted using the OTT connection 1550.

[0168] The network node 1504 includes hardware that enables the network node 1504 to communicate with the host 1502 and the UE 1506. The connection 1560 may be direct or may pass through one or more other intermediate networks, such as a core network (similar to the core network 1006 of FIG. 10) and / or one or more public, private, or hosted networks. For example, the intermediate network may be a backbone network or the Internet.

[0169] The UE 1506 includes hardware and software stored on or accessible by the UE 1506 and executable by the UE's processing circuitry. The software includes a client application, such as a web browser or operator-specific "app," which, with the support of the host 1502, may be operable to provide services to a human or non-human user via the UE 1506. An executing host application on the host 1502 may communicate with an executing client application via an OTT connection 1550 that terminates at the UE 1506 and the host 1502. In providing services to the user, the UE's client application may receive request data from the host application on the host and provide user data in response to the request data. The OTT connection 1550 may transfer both request data and user data. The UE's client application may interact with the user to generate user data that the UE's client application provides to the host application through the OTT connection 1550.

[0170] The OTT connection 1550 may extend via a connection 1560 between the host 1502 and a network node 1504 and via a wireless connection 1570 between the network node 1504 and the UE 1506 to provide connectivity between the host 1502 and the UE 1506. The connections 1560 and wireless connections 1570 through which the OTT connection 1550 may be provided are depicted abstractly to show communication between the host 1502 and the UE 1506 via the network node 1504, without explicit reference to any intermediary devices and the precise routing of messages through these devices.

[0171] As an example of transmitting data over the OTT connection 1550, in step 1508, the host 1502 provides user data, which may be performed by executing a host application. In some embodiments, the user data is associated with a particular human user interacting with the UE 1506. In other embodiments, the user data is associated with the UE 1506 sharing data with the host 1502 without explicit human interaction. In step 1510, the host 1502 initiates a transmission carrying the user data toward the UE 1506. The host 1502 may initiate the transmission in response to a request sent by the UE 1506. The request may be caused by human interaction with the UE 1506 or by the operation of a client application executing on the UE 1506. The transmission may proceed via the network node 1504 in accordance with the teachings of the embodiments described throughout this disclosure. Thus, in step 1512, the network node 1504 transmits the user data carried in the transmission initiated by the host 1502 to the UE 1506, in accordance with the teachings of embodiments described throughout this disclosure. In step 1514, the UE 1506 receives the user data carried in the transmission, which may be performed by a client application executing on the UE 1506 associated with the host application executed by the host 1502.

[0172] In some examples, the UE 1506 executes a client application that provides user data to the host 1502. The user data may be provided in reaction or response to data received from the host 1502. Thus, in step 1516, the UE 1506 may provide the user data, which may be performed by executing the client application. In providing the user data, the client application may further consider user input received from a user via an input / output interface of the UE 1506. Regardless of the particular manner in which the user data is provided, the UE 1506 initiates transmission of the user data towards the host 1502 via the network node 1504 in step 1518. In step 1520, the network node 1504 receives the user data from the UE 1506 and initiates transmission of the received user data towards the host 1502, in accordance with the teachings of embodiments described throughout this disclosure. In step 1522, the host 1502 receives the user data carried in the transmission initiated by the UE 1506.

[0173] One or more of the various embodiments improve the performance of OTT services provided to the UE 1506 using the OTT connection 1550, of which the radio connection 1570 forms the final segment. For example, by providing AI / ML model owners / producers with the ability to protect their AI / ML models during various transmission, storage, and retrieval scenarios, the embodiments improve the security of sensitive and / or confidential AI / ML models, thereby facilitating the deployment of such models in multi-vendor communication networks, such as 5GC. In this manner, the embodiments facilitate improved network performance based on deployed AI / ML models, thereby increasing the value of OTT services delivered over the thus-improved networks.

[0174] In an exemplary scenario, factory status information may be collected and analyzed by the host 1502. As another example, the host 1502 may process audio and video data that may have been retrieved from UEs for use in creating maps. As another example, the host 1502 may collect and analyze real-time data to assist in controlling vehicular congestion (e.g., controlling traffic lights). As another example, the host 1502 may store surveillance video uploaded by UEs. As another example, the host 1502 may store or control access to media content, such as video, audio, VR or AR, that the host 1502 may broadcast, multicast, or unicast to UEs. As other examples, the host 1502 may be used for energy pricing, remote control of non-time-critical electrical loads to balance power generation needs, location services, presentation services (such as compiling diagrams, etc. from data collected from remote devices), or any other function of collecting, retrieving, storing, analyzing, and / or transmitting data.

[0175] In some examples, measurement procedures may be provided for the purpose of monitoring data rates, latency, and other factors that one or more embodiments improve upon. There may further be optional network functionality for reconfiguring the OTT connection 1550 between the host 1502 and the UE 1506 in response to fluctuations in the measurement results. The measurement procedures and / or the network functionality for reconfiguring the OTT connection may be implemented in software and hardware in the host 1502 and / or the UE 1506. In some embodiments, sensors (not shown) may be deployed in or in association with other devices through which the OTT connection 1550 passes, and the sensors may participate in the measurement procedures by providing values ​​of the monitored quantities exemplified above or other physical quantities from which software can calculate or estimate the monitored quantities. Reconfiguration of the OTT connection 1550 may include message formats, retransmission settings, preferred routing, etc., and the reconfiguration need not directly change the operation of the network node 1504. Such procedures and functionality are known and may be practiced in the art. In some embodiments, the measurements may involve proprietary UE signaling that facilitates measurements of throughput, propagation time, latency, etc. by the host 1502. The measurements may be implemented in particular by causing empty or "dummy" messages to be sent using the OTT connection 1550 while software monitors propagation time, errors, etc.

[0176] The foregoing merely illustrates the principles of the present disclosure. Various modifications and alterations to the described embodiments will be apparent to those skilled in the art in light of the teachings herein. It will be appreciated that those skilled in the art will be able to devise numerous systems, configurations, and procedures that are not explicitly shown or described herein, but which embody the principles of the present disclosure and thereby fall within the spirit and scope of the present disclosure. As should be understood by those skilled in the art, the various embodiments can be used in conjunction with, and interchangeably with, one another.

[0177] The term unit as used herein may have its usual meaning in the field of electronics, electrical devices, and / or electronic devices, and may include, for example, electrical and / or electronic circuits, devices, modules, processors, memories, logical solid and / or discrete devices, computer programs or instructions, etc., for performing respective tasks, procedures, calculations, output, and / or display functions, etc., such as those described herein.

[0178] Any suitable step, method, feature, function, or benefit disclosed herein may be implemented through one or more functional units or modules of one or more virtual devices. Each virtual device may comprise several of these functional units. These functional units may be implemented via processing circuitry, which may include one or more microprocessors or microcontrollers, as well as other digital hardware, which may include digital signal processors (DSPs), dedicated digital logic, and the like. The processing circuitry may be configured to execute program code stored in memory, which may include one or several types of memory, such as read-only memory (ROM), random access memory (RAM), cache memory, flash memory devices, optical storage devices, and the like. The program code stored in memory includes program instructions for implementing one or more communication and / or data communication protocols, as well as instructions for performing one or more of the techniques described herein. In some implementations, the processing circuitry may be used to cause each functional unit to perform a corresponding function according to one or more embodiments of the present disclosure.

[0179] As described herein, devices and / or apparatus may be represented by semiconductor chips, chipsets, or (hardware) modules comprising such chips or chipsets, but this does not exclude the possibility that the functionality of a device or apparatus may, instead of being implemented in hardware, be implemented as a software module, such as a computer program or computer program product comprising executable software code portions for execution on or running on a processor. Moreover, the functionality of a device or apparatus may be implemented by any combination of hardware and software. A device or apparatus may also be considered an assembly of multiple devices and / or apparatus, whether functionally cooperating with each other or independent of each other. Moreover, devices and apparatus may be implemented in a distributed manner throughout a system, so long as the functionality of the device or apparatus is preserved. Such and similar principles are deemed to be known to those skilled in the art.

[0180] Unless otherwise specified, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this disclosure belongs. It will be further understood that the terms used herein should be interpreted as having a meaning that is consistent with the meaning of those terms in the context of this specification and the related art, and should not be interpreted in an idealized or overly formal sense unless expressly so defined herein.

[0181] Additionally, some terms used in this disclosure, including the specification and drawings, may be used synonymously in some instances (e.g., "data" and "information"). It is understood that although these terms (and / or other terms that may be synonymous with each other) may be used synonymously herein, there may be instances when it is not intended that such words be used synonymously.

[0182] Exemplary embodiments of the techniques and apparatus described herein include, but are not limited to, the following enumerated embodiments. A1. A method for a consumer network function (NFc) of a communications network, the method comprising: sending a first request to a Network Repository Function (NRF) of the communication network for a first access token associated with a machine learning (ML) model generated, owned, and / or maintained by a producer NF (NFp) of the communication network, wherein the first request includes an analysis identifier (ID) associated with the ML model, a vendor ID associated with the NFc, and an ID associated with the NFp; receiving a first response from the NRF, the first response including the first access token; sending a second request for the ML model to the NFp, wherein the second request includes the first access token, the analysis ID, and a vendor ID associated with the NFc; receiving, from the NFp, a second response including a Universal Resource Locator (URL) associated with a second NF of the communication network from which the ML model may be obtained; A method comprising: A2. The second NF associated with the URL is NFp, and the method further includes obtaining the ML model from the NFp using the URL and the first access token; The method of embodiment A1. A3. The second NF associated with the URL is an Analytical Data Repository Facility (ADRF) of the communications network; and The method is: sending a third request to the NRF for a second access token associated with the ML model, wherein the third request includes an analysis ID associated with the ML model, a vendor ID associated with the NRF, and an ID associated with the ADRF; receiving a third response from the NRF, the third response including the second access token; Use the URL and the second access token to obtain the ML model from the ADRF. further comprising: The method of embodiment A1. A4. The method of embodiment A2 or A3, further comprising performing a second security operation on the obtained ML model, wherein the second security operation corresponds to the first security operation performed on the ML model by the NFp. A5. The first security operation includes encryption and / or integrity protection; the second security operation includes decryption corresponding to encryption and / or integrity checking corresponding to integrity protection; The method of embodiment A4. A6. The method of any one of embodiments A1 to A5, further comprising registering with the NRF: a vendor ID associated with the NFc and one or more analysis IDs associated with ML models supported by the NFc, including analysis IDs associated with ML models generated, owned, and / or maintained by the NFp. A7. The following, namely: the first response from the NRF is based on a match, correspondence, or relationship between the vendor ID included in the first request and the interoperability ID associated with the NFp and the ML model; and a second response from the NFp based on a match, correspondence, or relationship between the vendor ID included in the second request and the interoperability ID associated with the NFp and the ML model; The method of any one of embodiments A1 to A6, wherein one or more of the following applies: A8. The method of any one of embodiments A1 to A7, further comprising conducting a discovery procedure with the NRF to identify the NFp based on the analysis ID, wherein the first request is sent in response to the discovery procedure. A9. The following, namely: NFc is the Analysis Logic Function (AnLF) of the Network Data Analysis Facility (NWDAF), and NFp is the Model Training Logic Function (MTLF) of the Network Data Analysis Function (NWDAF), The method of any one of embodiments A1 to A8, wherein one or more of the following applies. B1. A method for a producer network function (NFp) of a communications network, the method comprising: receiving a second request for a machine learning (ML) model generated, owned, and / or maintained by the NFp from a consumer NF (NFc) of the communication network, wherein the second request includes: a first access token issued by a Network Repository Function (NRF) of the communications network; An analysis identifier (ID) associated with the ML model; and The vendor ID associated with the NFc and receiving a second request, the second request including: Authorizing the NFc to access the ML model associated with the analysis ID based on the first access token; sending, based on authorizing the NFc, a second response to the NFc, the second response including a universal resource locator (URL) associated with a second NF of the communication network from which the ML model may be obtained; A method comprising: B2. The second NF associated with the URL is NFp, The method further includes providing the ML model to the NFc using the URL and the first access token. The method of embodiment B1. B3. The second NF associated with the URL is an Analytical Data Repository Function (ADRF) of the communications network; and The method is: sending a first request to the ADRF to store the ML model, wherein the first request comprises: The analysis ID associated with the ML model, and an interoperability ID that includes or is associated with a list of vendors that are enabled to access the ML model; A URL associated with the NFp from which the ML model can be obtained; sending a first request, the first request including: Provide the ML model to the ADRF using the URL associated with the NFp; and receiving a first response from the ADRF, the first response including a URL associated with the ADRF, which is sent in a second response to the NFc; further comprising: The method of embodiment B1. B4. The method of embodiment B3, wherein providing the ML model to the ADRF comprises verifying a third access token issued by the NRF and provided by the ADRF. B5. The method of embodiment B3 or B4, wherein the second response also includes an identifier of the ADRF in which the ML model is stored. B6. The method of any one of embodiments B2 to B5, further comprising performing a first security operation on the ML model before providing the ML model to the NF or before providing the ML model to the ADRF, wherein the first security operation comprises encryption and / or integrity protection. B7. The Network Repository Function (NRF) of the telecommunications network shall be provided with the following information: The analysis ID associated with the ML model, and Contains a list of vendors that have been granted access to the ML model, or an interoperability ID associated with the list. The method of any one of embodiments B1 to B6, further comprising registering. B8. The following, namely: NFc is the Analysis Logic Function (AnLF) of the Network Data Analysis Facility (NWDAF), and NFp is the Model Training Logic Function (MTLF) of the Network Data Analysis Function (NWDAF), The method of any one of embodiments B1 to B8, wherein one or more of the following applies: C1. A method for a Network Repository Function (NRF) of a communications network, the method comprising: registering the following information in a profile for a producer NF (NFp) of a communication network: a first analysis identifier (ID) associated with a machine learning (ML) model generated, owned, and / or maintained by the NFp, and an interoperability ID including or associated with a list of vendors enabled to access the ML model; receiving a first request for a first access token associated with an ML model from a consumer NF (NFc) of a communication network, wherein the first request includes a first analysis ID associated with the ML model, a vendor ID associated with the NFc, and an ID associated with the NFp; authorizing the NFc to access the ML model based on a match, correspondence, or relationship between a vendor ID included in the first request and an interoperability ID registered in a profile for the NFp; sending a first response to the NFc, the first response including the first access token; A method comprising: C2. Receiving a third request from the NFc for a second access token associated with the ML model, wherein the third request includes an analysis ID associated with the ML model, a vendor ID associated with the NFc, and an ID associated with the ADRF; authorizing the NFc to access the ML model based on a match, correspondence, or relationship between the vendor ID included in the third request and an interoperability ID registered in a profile for the NFp; sending a third response to the NFc, the third response including the second access token; The method of embodiment C1, further comprising: C3. Receiving a fourth request from an Analytical Data Repository Function (ADRF) of the communication network for a third access token associated with the ML model, wherein the fourth request includes an analysis ID associated with the ML model, a vendor ID associated with the ADRF, and an ID associated with the NFp; authorizing the NFc to access the ML model based on a match, correspondence, or relationship between the vendor ID included in the fourth request and an interoperability ID registered in a profile for the NFp; sending a fourth response to the ADRF, the fourth response including the third access token; and The method of embodiment C2, further comprising: C4. The following information is included in the profile for the consumer NF (NFc) of the communication network: The vendor ID associated with the NFc, and one or more analysis IDs associated with the ML models supported by the NFc, including a first analysis ID; The method of any one of embodiments C1 to C3, further comprising registering. C5. The method of any one of embodiments C1 to C4, further comprising registering the following information in a profile for an Analytical Data Repository Function (ADRF) of the communication network: a first analytical ID, an interoperability ID, and an ID associated with the NFp. C6. The following, namely: NFc is the Analysis Logic Function (AnLF) of the Network Data Analysis Facility (NWDAF), and NFp is the Model Training Logic Function (MTLF) of the Network Data Analysis Function (NWDAF), The method of any one of embodiments C1 to C5, wherein one or more of the following applies: D1. A method for an Analytical Data Repository Function (ADRF) of a communications network, the method comprising: receiving a first request from a producer network function (NFp) of a communications network to store a machine learning (ML) model generated, owned, and / or maintained by the NFp, wherein the first request comprises: An analysis identifier (ID) associated with the ML model; and an interoperability ID that includes or is associated with a list of vendors that are enabled to access the ML model; a universal resource locator (URL) associated with the NFp from which the ML model may be obtained; and receiving a first request, the first request including: Obtaining an ML model from the NFp using a URL associated with the NFp; sending to the NFp a first response including a URL associated with the ADRF from which the ML model may be obtained; A method comprising: D2. sending a fourth request for a third access token associated with the ML model to a Network Repository Function (NRF) of the communication network in response to the first request, wherein the fourth request includes an analysis ID associated with the ML model, a vendor ID associated with the ADRF, and an ID associated with the NFp; receiving a fourth response from the NRF, the fourth response including the third access token; further comprising wherein obtaining the ML model from the NFp is based on a third access token, The method of embodiment D1. D3. The method of embodiment D1 or D2, further comprising providing the ML model to a consumer network function (NFc) of the communications network using a URL associated with the ADRF. D4. The method of embodiment D3, wherein providing the ML model to the NFc comprises verifying a second access token issued by the NRF and provided by the NFc. D5. The method of any one of embodiments D1 to D4, further comprising registering the following information with a Network Repository Function (NRF) of the communication network: the first analysis ID, an interoperability ID, and an ID associated with the NFp. D6. The following, namely: NFc is the Analysis Logic Function (AnLF) of the Network Data Analysis Facility (NWDAF), and NFp is the Model Training Logic Function (MTLF) of the Network Data Analysis Function (NWDAF), The method of embodiment D4, wherein one or more of the following applies: D7. The method of any one of embodiments D3 to D5, wherein the ML model obtained from the NFp is encrypted and / or integrity protected. E1. A Consumer Network Function (NFc) of a communications network, the NFc is implemented by an operably coupled communication interface circuit and a processing circuit; the processing circuitry and the interface circuitry are configured to perform operations corresponding to any of the methods described in embodiments A1 to A9. Consumer Network Functions (NFc). E2. A Consumer Network Function (NFc) of a communications network, the NFc configured to perform operations corresponding to any of the methods described in embodiments A1 to A9. E3. A non-transitory computer-readable medium storing computer-executable instructions that, when executed by processing circuitry associated with a consumer network function (NFc) of a communications network, configure the NFc to perform operations corresponding to any of the methods described in embodiments A1 to A9. E4. A computer program product comprising computer-executable instructions that, when executed by processing circuitry associated with a consumer network function (NFc) of a communications network, configure the NFc to perform operations corresponding to any of the methods described in embodiments A1 to A9. F1. A producer network function (NFp) of a communications network, comprising: the NFp is implemented by an operably coupled communication interface circuit and a processing circuit; the processing circuitry and the interface circuitry configured to perform operations corresponding to any of the methods described in embodiments B1 to B8. Producer Network Function (NFp). F2. A producer network function (NFp) of a communications network, the NFp configured to perform operations corresponding to any of the methods described in embodiments B1 to B8. F3. A non-transitory computer-readable medium storing computer-executable instructions that, when executed by processing circuitry associated with a producer network function (NFp) of a communications network, configure the NFp to perform operations corresponding to any of the methods described in embodiments B1 to B8. F4. A computer program product comprising computer-executable instructions that, when executed by processing circuitry associated with a producer network function (NFp) of a communications network, configure the NFp to perform operations corresponding to any of the methods described in embodiments B1 to B8. G1. A Network Repository Function (NRF) of a communications network, the NRF is implemented by an operably coupled communications interface circuit and processing circuit; the processing circuitry and the interface circuitry configured to perform operations corresponding to any of the methods described in embodiments C1 to C6. Network Repository Facility (NRF). G2. A network repository function (NRF) of a communication network, the NRF configured to perform operations corresponding to any of the methods described in embodiments C1 to C6. G3. A non-transitory computer-readable medium storing computer-executable instructions that, when executed by processing circuitry associated with a Network Repository Function (NRF) of a communications network, configure the NRF to perform operations corresponding to any of the methods described in embodiments C1 to C6. G4. A computer program product comprising computer-executable instructions that, when executed by processing circuitry associated with a Network Repository Function (NRF) of a communications network, configure the NRF to perform operations corresponding to any of the methods described in embodiments C1 to C6. H1. An Analytical Data Repository Function (ADRF) of a communications network, comprising: the ADRF is implemented by an operably coupled communications interface circuit and processing circuit; the processing circuitry and the interface circuitry configured to perform operations corresponding to any of the methods described in embodiments D1 to D7. Analytical Data Repository Facility (ADRF). H2. An analytical data repository function (ADRF) of a communications network, the ADRF configured to perform operations corresponding to any of the methods described in embodiments D1 to D7. H3. A non-transitory computer-readable medium storing computer-executable instructions that, when executed by processing circuitry associated with an Analytical Data Repository Function (ADRF) of a communications network, configure the ADRF to perform operations corresponding to any of the methods described in embodiments D1 to D7. H4. A computer program product comprising computer-executable instructions that, when executed by processing circuitry associated with an Analytical Data Repository Function (ADRF) of a communications network, configure the ADRF to perform operations corresponding to any of the methods described in embodiments D1 to D7.

Claims

1. 1. A method for consumer network functionality (NFc) of a communication network, comprising: sending (620) to a Network Repository Function (NRF) of the communication network a first request for a first access token associated with a machine learning (ML) model generated, owned, and / or maintained by a producer NF (NFp) of the communication network, wherein the first request includes an analysis identifier (ID) associated with the ML model, a vendor ID associated with the NFc, and an ID associated with the NFp; receiving (630) a first response from the NRF that includes the first access token; sending 640 a second request for the ML model to the NFp, wherein the second request includes the first access token, the analysis ID, and the vendor ID associated with the NFc; receiving (650) from the NFp a second response including a Universal Resource Locator (URL) associated with a second NF of the communication network from which the ML model can be obtained; A method comprising:

2. the second NF associated with the URL is the NFp, the method further comprising: obtaining (660) the ML model from the NFp using the URL and the first access token; The method of claim 1.

3. the second NF associated with the URL is an Analytical Data Repository Function (ADRF) of the communications network; The method comprises: Sending (670) a third request to the NRF for a second access token associated with the ML model, wherein the third request includes the analysis ID associated with the ML model, the vendor ID associated with the NFc, and an ID associated with the ADRF; receiving (680) a third response from the NRF that includes the second access token; obtaining (690) the ML model from the ADRF using the URL and the second access token; further comprising: The method of claim 1.

4. 4. The method of claim 2 or 3, further comprising: performing (695) a second security operation on the obtained ML model, wherein the second security operation corresponds to a first security operation performed on the ML model by the NFp.

5. the first security operation includes encryption and / or integrity protection; the second security operation includes a decryption corresponding to the encryption and / or an integrity check corresponding to the integrity protection; The method of claim 4.

6. 6. The method of claim 1, further comprising: registering (610) with the NRF the following: the vendor ID associated with the NFc; and one or more analysis IDs associated with ML models supported by the NFc, including the analysis IDs associated with the ML models generated, owned, and / or maintained by the NFp.

7. The following, i.e., the first response from the NRF is based on a match, correspondence, or relationship between the vendor ID included in the first request and an interoperability ID associated with the NFp and the ML model; and the second response from the NFp is based on a match, correspondence, or relationship between the vendor ID included in the second request and the interoperability ID associated with the NFp and the ML model.

7. The method of claim 1, wherein one or more of the following applies:

8. 8. The method of claim 1, further comprising: performing (620) a discovery procedure with the NRF to identify the NFp based on the analysis ID, wherein the first request is sent in response to the discovery procedure.

9. The following, i.e., The NFc is an Analysis Logic Function (AnLF) of a Network Data Analysis Function (NWDAF); and The NFp is a Model Training Logic Function (MTLF) of the Network Data Analysis Function (NWDAF); 9. The method of claim 1 , wherein one or more of the following applies:

10. 1. A method for a Producer Network Function (NFp) of a communication network, comprising: receiving (750) a second request for a machine learning (ML) model generated, owned, and / or maintained by the NFp from a consumer NF (NFc) of the communication network, wherein the second request includes: a first access token issued by a Network Repository Function (NRF) of the communications network; and an analysis identifier (ID) associated with the ML model; a vendor ID associated with said NFc; receiving 750 a second request including: Authorizing the NFc to access the ML model associated with the analysis ID based on the first access token (760); sending (770) a second response to the NFc based on authorizing the NFc, the second response including a Universal Resource Locator (URL) associated with a second NF of the communication network from which the ML model can be obtained; A method comprising:

11. the second NF associated with the URL is the NFp, the method further comprising providing (780) the ML model to the NFc using the URL and the first access token. The method of claim 10.

12. the second NF associated with the URL is an Analytical Data Repository Function (ADRF) of the communications network; The method comprises: Sending 720 a first request to the ADRF to store the ML model, wherein the first request comprises: the analysis ID associated with the ML model; and an interoperability ID containing or associated with a list of vendors that are allowed to access the ML model; a URL associated with the NFp from which the ML model can be obtained; and sending (720) a first request, the first request including: providing (730) the ML model to the ADRF using the URL associated with the NFp; receiving (740) from the ADRF a first response including the URL associated with the ADRF, which is sent in the second response to the NFc; further comprising: The method of claim 10.

13. 13. The method of claim 12, wherein providing the ML model to the ADRF (730) comprises verifying (731) a third access token issued by the NRF and provided by the ADRF.

14. The method of claim 12 or 13, wherein the second response also includes an identifier of the ADRF in which the ML model is stored.

15. 15. The method of claim 11, further comprising: performing (715) a first security operation on the ML model before providing the ML model to the NF or before providing the ML model to the ADRF, wherein the first security operation comprises encryption and / or integrity protection.

16. The Network Repository Function (NRF) of said communications network is provided with the following information: the analysis ID associated with the ML model; and an interoperability ID containing or associated with a list of vendors that are allowed to access the ML model; The method of any one of claims 10 to 15, further comprising registering (710)

17. The following, i.e., The NFc is an Analysis Logic Function (AnLF) of a Network Data Analysis Function (NWDAF); and The NFp is a Model Training Logic Function (MTLF) of the Network Data Analysis Function (NWDAF); 18. The method of any one of claims 10 to 17, wherein one or more of the following apply:

18. 1. A method for a Network Repository Function (NRF) of a communication network, comprising: In the profile for the producer NF (NFp) of said communication network, the following information is included: a first analysis identifier (ID) associated with a machine learning (ML) model generated, owned, and / or maintained by the NFp; an interoperability ID containing or associated with a list of vendors that are allowed to access the ML model; Registering (810) receiving (850) a first request for a first access token associated with the ML model from a consumer NF (NFc) of the communication network, wherein the first request includes the first analysis ID associated with the ML model, a vendor ID associated with the NFc, and an ID associated with the NFp; authorizing the NFc to access the ML model based on a match, correspondence, or relationship between the vendor ID included in the first request and the interoperability ID registered in the profile for the NFp (860); sending (870) a first response to the NFc, the first response including the first access token; A method comprising:

19. receiving (880) a third request from the NFc for a second access token associated with the ML model, wherein the third request includes the analysis ID associated with the ML model, the vendor ID associated with the NFc, and an ID associated with an Analytical Data Repository Function (ADRF) of the communications network; authorizing the NFc to access the ML model based on a match, correspondence, or relationship between the vendor ID included in the third request and the interoperability ID registered in the profile for the NFp (885); sending (890) a third response to the NFc that includes the second access token; 20. The method of claim 18, further comprising:

20. receiving 830 a fourth request from the ADRF for a third access token associated with the ML model, wherein the fourth request includes the analysis ID associated with the ML model, the vendor ID associated with the ADRF, and an ID associated with the NFp; authorizing the ADRF to access the ML model based on a match, correspondence, or relationship between the vendor ID included in the fourth request and the interoperability ID registered in the profile for the NFp (835); sending (840) a fourth response to the ADRF that includes the third access token; 20. The method of claim 19, further comprising:

21. In the profile for the consumer NF (NFc) of said communication network, the following information is recorded: a vendor ID associated with the NFc; and one or more analysis IDs associated with an ML model supported by the NFc, the analysis ID including the first analysis ID; 21. The method of claim 18, further comprising registering (815).

22. 22. The method of claim 18, further comprising: registering (820) the following information in a profile for an Analytical Data Repository Function (ADRF) of the communication network: the first analytical ID, the interoperability ID, and the ID associated with the NFp.

23. The following, i.e., The NFc is an Analysis Logic Function (AnLF) of a Network Data Analysis Function (NWDAF); and The NFp is a Model Training Logic Function (MTLF) of the Network Data Analysis Function (NWDAF); 23. The method of any one of claims 18 to 22, wherein one or more of the following apply:

24. 1. A method for an Analytical Data Repository Function (ADRF) of a communications network, comprising: receiving (910) a first request from a producer network function (NFp) of the communication network to store a machine learning (ML) model generated, owned, and / or maintained by the NFp, wherein the first request comprises: an analysis identifier (ID) associated with the ML model; an interoperability ID containing or associated with a list of vendors that are allowed to access the ML model; a Universal Resource Locator (URL) associated with the NFp from which the ML model can be obtained; and receiving 910 a first request, the first request including: obtaining 940 the ML model from the NFp using the URL associated with the NFp; sending (960) to the NFp a first response including a URL associated with the ADRF from which the ML model can be obtained; A method comprising:

25. sending (920) a fourth request for a third access token associated with the ML model to a Network Repository Function (NRF) of the communication network in response to the first request, wherein the fourth request includes the analysis ID associated with the ML model, a vendor ID associated with the ADRF, and an ID associated with the NFp; receiving (930) a fourth response from the NRF that includes the third access token; further comprising wherein obtaining the ML model from the NFp (940) is based on the third access token; 25. The method of claim 24.

26. 26. The method of claim 24 or 25, further comprising providing (970) the ML model to a Consumer Network Function (NFc) of the communications network using the URL associated with the ADRF.

27. 27. The method of claim 26, wherein providing the ML model to the NFc (970) comprises verifying (971) a second access token issued by the NRF and provided by the NFc.

28. 28. The method of any one of claims 24 to 27, further comprising registering (960) the following information with a Network Repository Function (NRF) of the communication network: a first analysis ID, the interoperability ID, and the ID associated with the NFp.

29. The following, i.e., The NFc is an Analysis Logic Function (AnLF) of a Network Data Analysis Function (NWDAF); and The NFp is a Model Training Logic Function (MTLF) of the Network Data Analysis Function (NWDAF); 29. The method of claim 28, wherein one or more of the following apply:

30. 29. The method of any one of claims 26 to 28, wherein the ML model obtained from the NFp is encrypted and / or integrity protected.

31. A network device (1008, 1200, 1400) configured to implement a Consumer Network Function (NFc) (410, 510) of a communication network (198, 200, 1002), wherein the network device comprises: a communication interface circuit (1206, 1404) configured to communicate with network devices implementing other network functions (NFs) of said communication network; a processing circuit (1202, 1404) operably coupled to said communication interface circuit, wherein said processing circuit and said communication interface circuit: Sending a first request to a Network Repository Function (NRF) (420, 520) of the communication network for a first access token associated with a machine learning (ML) model generated, owned, and / or maintained by a producer NF (NFp) (430, 530) of the communication network, wherein the first request includes an analysis identifier (ID) associated with the ML model, a vendor ID associated with the NFc, and an ID associated with the NFp; receiving a first response from the NRF, the first response including the first access token; sending a second request for the ML model to the NFp, wherein the second request includes the first access token, the analysis ID, and the vendor ID associated with the NFc; receiving from the NFp a second response including a Universal Resource Locator (URL) associated with a second NF of the communication network from which the ML model can be obtained; a processing circuit (1202, 1404) configured to perform A network device (1008, 1200, 1400) comprising:

32. 32. The network equipment of claim 31, wherein said processing circuitry and said communications interface circuitry are further configured to perform operations corresponding to any of the methods described in claims 2 to 9.

33. A network device (1008, 1200, 1400) configured to implement a Consumer Network Function (NFc) (410, 510) of a communication network (198, 200, 1002), wherein the network device comprises: Sending a first request to a Network Repository Function (NRF) (420, 520) of the communication network for a first access token associated with a machine learning (ML) model generated, owned, and / or maintained by a producer NF (NFp) (430, 530) of the communication network, wherein the first request includes an analysis identifier (ID) associated with the ML model, a vendor ID associated with the NFc, and an ID associated with the NFp; receiving a first response from the NRF, the first response including the first access token; sending a second request for the ML model to the NFp, wherein the second request includes the first access token, the analysis ID, and the vendor ID associated with the NFc; receiving from the NFp a second response including a Universal Resource Locator (URL) associated with a second NF of the communication network from which the ML model can be obtained; a network device (1008, 1200, 1400) further configured to:

34. 34. The network device of claim 33, further configured to perform operations corresponding to any of the methods of claims 2 to 9.

35. A non-transitory computer-readable medium (1204, 1404) storing computer-executable instructions that, when executed by a processing circuit (1202, 1404) associated with a Consumer Network Function (NFc) (410, 510) of a communications network (198, 200, 1002), configures the NFc to perform operations corresponding to any of the methods described in claims 1 to 9.

36. A computer program product (1204a, 1404a) comprising computer-executable instructions that, when executed by a processing circuit (1202, 1404) associated with a Consumer Network Function (NFc) (410, 510) of a communication network (198, 200, 1002), configures the NFc to perform operations corresponding to any of the methods described in claims 1 to 9.

37. A network device (1008, 1200, 1400) configured to implement a producer network function (NFp) (430, 530) of a communications network (198, 200, 1002), wherein the network device comprises: a communication interface circuit (1206, 1404) configured to communicate with network devices implementing other network functions (NFs) of said communication network; a processing circuit (1202, 1404) operably coupled to said communication interface circuit, wherein said processing circuit and said communication interface circuit: receiving a second request for a machine learning (ML) model generated, owned, and / or maintained by the NFp from a consumer NF (NFc) (410, 510) of the communication network, wherein the second request includes: a first access token issued by a Network Repository Function (NRF) (420, 520) of said communications network; an analysis identifier (ID) associated with the ML model; a vendor ID associated with said NFc; receiving a second request, the second request including: authorizing the NFc to access the ML model associated with the analysis ID based on the first access token; sending, based on authorizing the NFc, a second response to the NFc, the second response including a Universal Resource Locator (URL) associated with a second NF of the communication network from which the ML model can be obtained; a processing circuit (1202, 1404) configured to perform A network device (1008, 1200, 1400) comprising:

38. 38. The network equipment of claim 37, wherein said processing circuitry and said communications interface circuitry are further configured to perform operations corresponding to any of the methods of claims 11 to 17.

39. A network device (1008, 1200, 1400) configured to implement a producer network function (NFp) (430, 530) of a communications network (198, 200, 1002), wherein the network device comprises: receiving a second request for a machine learning (ML) model generated, owned, and / or maintained by the NFp from a consumer NF (NFc) (410, 510) of the communication network, wherein the second request includes: a first access token issued by a Network Repository Function (NRF) (420, 520) of said communications network; an analysis identifier (ID) associated with the ML model; a vendor ID associated with said NFc; receiving a second request, the second request including: authorizing the NFc to access the ML model associated with the analysis ID based on the first access token; sending, based on authorizing the NFc, a second response to the NFc, the second response including a Universal Resource Locator (URL) associated with a second NF of the communication network from which the ML model can be obtained; a network device (1008, 1200, 1400) further configured to:

40. 40. A network device according to claim 39, further configured to perform operations corresponding to any of the methods according to claims 11 to 17.

41. A non-transitory computer-readable medium (1204, 1404) storing computer-executable instructions that, when executed by a processing circuit (1202, 1404) associated with a producer network function (NFp) (430, 530) of a communications network (198, 200, 1002), configure the NFp to perform operations corresponding to any of the methods described in claims 10 to 17.

42. A computer program product (1204a, 1404a) comprising computer-executable instructions that, when executed by a processing circuit (1202, 1404) associated with a producer network function (NFp) (430, 530) of a communication network (198, 200, 1002), configures the NFp to perform operations corresponding to any of the methods described in claims 10 to 17.

43. A network device (1008, 1200, 1400) configured to implement a Network Repository Function (NRF) (420, 520) of a communications network (198, 200, 1002), wherein the network device comprises: a communication interface circuit (1206, 1404) configured to communicate with network devices implementing other network functions (NFs) of said communication network; a processing circuit (1202, 1404) operably coupled to said communication interface circuit, wherein said processing circuit and said communication interface circuit: In the profile for the producer NF (NFp) (430, 530) of said communication network, the following information is included: a first analysis identifier (ID) associated with a machine learning (ML) model generated, owned, and / or maintained by the NFp; an interoperability ID containing or associated with a list of vendors that are allowed to access the ML model; To register the receiving a first request for a first access token associated with the ML model from a consumer NF (NFc) (410, 510) of the communication network, wherein the first request includes the first analysis ID associated with the ML model, a vendor ID associated with the NFc, and an ID associated with the NFp; authorizing the NFc to access the ML model based on a match, correspondence, or relationship between the vendor ID included in the first request and the interoperability ID registered in the profile for the NFp; sending a first response to the NFc, the first response including the first access token; a processing circuit (1202, 1404) configured to perform A network device (1008, 1200, 1400) comprising:

44. 44. The network equipment of claim 43, wherein said processing circuitry and said communications interface circuitry are further configured to perform operations corresponding to any of the methods of claims 19 to 23.

45. A network device (1008, 1200, 1400) configured to implement a Network Repository Function (NRF) (420, 520) of a communications network (198, 200, 1002), wherein the network device comprises: In the profile for the producer NF (NFp) (430, 530) of said communication network, the following information is included: a first analysis identifier (ID) associated with a machine learning (ML) model generated, owned, and / or maintained by the NFp; an interoperability ID containing or associated with a list of vendors that are allowed to access the ML model; To register the receiving a first request for a first access token associated with the ML model from a consumer NF (NFc) (410, 510) of the communication network, wherein the first request includes the first analysis ID associated with the ML model, a vendor ID associated with the NFc, and an ID associated with the NFp; authorizing the NFc to access the ML model based on a match, correspondence, or relationship between the vendor ID included in the first request and the interoperability ID registered in the profile for the NFp; sending a first response to the NFc, the first response including the first access token; a network device (1008, 1200, 1400) further configured to:

46. 46. ​​A network device according to claim 45, further configured to perform operations corresponding to any of the methods according to claims 19 to 23.

47. A non-transitory computer-readable medium (1204, 1404) storing computer-executable instructions that, when executed by a processing circuit (1202, 1404) associated with a Network Repository Function (NRF) (420, 520) of a communications network (198, 200, 1002), configures the NRF to perform operations corresponding to any of the methods described in claims 18 to 23.

48. A computer program product (1204a, 1404a) comprising computer-executable instructions that, when executed by a processing circuit (1202, 1404) associated with a Network Repository Function (NRF) (420, 520) of a communication network (198, 200, 1002), configures said NRF to perform operations corresponding to any of the methods set forth in claims 18 to 23.

49. A network device (1008, 1200, 1400) configured to implement an Analytical Data Repository Function (ADRF) (540) of a communications network (198, 200, 1002), wherein the network device comprises: a communication interface circuit (1206, 1404) configured to communicate with network devices implementing other network functions (NFs) of said communication network; a processing circuit (1202, 1404) operably coupled to said communication interface circuit, wherein said processing circuit and said communication interface circuit: receiving a first request from a producer network function (NFp) (430, 530) of said communication network to store a machine learning (ML) model produced, owned and / or maintained by said NFp, wherein said first request comprises: an analysis identifier (ID) associated with the ML model; an interoperability ID containing or associated with a list of vendors that are allowed to access the ML model; a Universal Resource Locator (URL) associated with the NFp from which the ML model can be obtained; and receiving a first request, the first request including: obtaining the ML model from the NFp using the URL associated with the NFp; sending to the NFp a first response including a URL associated with the ADRF from which the ML model may be obtained; a processing circuit (1202, 1404) configured to perform A network device (1008, 1200, 1400) comprising:

50. 50. The network device of claim 49, wherein said processing circuitry and said communications interface circuitry are configured to perform operations corresponding to any of the methods of claims 25 to 30.

51. A network device (1008, 1200, 1400) configured to implement an Analytical Data Repository Function (ADRF) (540) of a communications network (198, 200, 1002), wherein the network device comprises: receiving a first request from a producer network function (NFp) (430, 530) of said communication network to store a machine learning (ML) model generated, owned and / or maintained by said NFp, wherein said first request comprises: an analysis identifier (ID) associated with the ML model; an interoperability ID containing or associated with a list of vendors that are allowed to access the ML model; a Universal Resource Locator (URL) associated with the NFp from which the ML model can be obtained; and receiving a first request, the first request including: obtaining the ML model from the NFp using the URL associated with the NFp; sending to the NFp a first response including a URL associated with the ADRF from which the ML model may be obtained; a network device (1008, 1200, 1400) further configured to:

52. 52. A network device according to claim 51, further configured to perform operations corresponding to any of the methods according to claims 25 to 30.

53. A non-transitory computer-readable medium (1204, 1404) storing computer-executable instructions that, when executed by a processing circuit (1202, 1404) associated with an analytical data repository function (ADRF) (540) of a communications network (198, 200, 1002), configures the ADRF to perform operations corresponding to any of the methods described in claims 24 to 30.

54. 31. A computer program product (1204a, 1404a) comprising computer-executable instructions that, when executed by a processing circuit (1202, 1404) associated with an Analytical Data Repository Facility (ADRF) (540) of a communications network (198, 200, 1002), configures the ADRF to perform operations corresponding to any of the methods set forth in claims 24 to 30.

Images