Interfaces for assuring ai / ML capabilities in a wireless communication system

Abstract

Various aspects of the present disclosure relate to a first network entity for wireless communication. The first network entity may be configured to, capable of, or operable to receive, from a second network entity, a network service request including at least one intelligence service requirement related to a network service; establish, with the second entity, a service level agreement in accordance with the at least one intelligent service requirement related to a network service; translate the at least one intelligence service requirement into a respective at least one intelligence service capability; select a service interface of a third network entity to control the at least one intelligent service capability; and transmit, to the selected service interface, a network intelligence request comprising the at least one intelligence service capability.

Description

INTERFACES FOR ASSURING AI / ML CAPABILITIES IN A WIRELESS COMMUNICATION SYSTEMTECHNICAL FIELD

[0001] The present disclosure relates generally to wireless communication, including interfaces for assuring Artificial Intelligence (Al) and / or Machine Learning (ML) capabilities in a wireless communication system.BACKGROUND

[0002] A wireless communications system may include one or multiple network communication devices, which may be otherwise knowns as network equipment (NE) supporting wireless communications for one or multiple user communication devices, which may be otherwise known as user equipment (UE), or other suitable terminology. The wireless communications system may support wireless communications with one or multiple user communication devices by utilizing resources of the wireless communication system (e.g., time resources (e.g., symbols, slots, subframes, frames, or the like) or frequency resources (e.g., subcarriers, carriers, or the like). Additionally, the wireless communications system may support wireless communications across various radio access technologies including third generation (3G) radio access technology, fourth generation (4G) radio access technology, fifth generation (5G) radio access technology, among other suitable radio access technologies beyond 5G (e.g., sixth generation (6G)).SUMMARY

[0003] An article “a” before an element is unrestricted and understood to refer to “at least one” of those elements or “one or more” of those elements. The terms “a,” “at least one,” “one or more,” and “at least one of one or more” may be interchangeable. As used herein, including in the claims, “or” as used in a list of items (e.g., a list of items prefaced by a phrase such as “at least one of’ or “one or more of’ or “one or both of’) indicates an inclusive list such that, for example, a list of at least one of A, B, or C means A or B or C or AB or AC or BC or ABC (i.e., A and B and C). Also, as used herein, the phrase “based on” shall not be construed as a reference to a closed set of conditions. For example, an examplestep that is described as “based on condition A” may be based on both a condition A and a condition B without departing from the scope of the present disclosure. In other words, as used herein, the phrase “based on” shall be construed in the same manner as the phrase “based at least in part on. Further, as used herein, including in the claims, a “set” may include one or more elements.

[0004] A first network entity for wireless communication is described. The first network entity may be configured to, capable of, or operable to perform one or more operations as described herein. For example, the first network entity may include at least one memory; and at least one processor coupled with the at least one memory and configured to cause the first network entity to: receive, from a second network entity, a network service request including at least one intelligence service requirement related to a network service; establish, with the second entity, a service level agreement in accordance with the at least one intelligent service requirement related to a network service; translate the at least one intelligence service requirement into a respective at least one intelligence service capability; select a service interface of a third network entity to control the at least one intelligent service capability; and transmit, to the selected service interface, a network intelligence request comprising the at least one intelligence service capability.

[0005] A processor for wireless communication is described. The processor may be configured to, capable of, or operable to perform one or more operations as described herein. For example, the processor may comprise at least one controller coupled with at least one memory and configured to cause the processor to: receive, from a second network entity, a network service request including at least one intelligence service requirement related to a network service; establish, with the second entity, a service level agreement in accordance with the at least one intelligent service requirement related to the network service; translate the at least one intelligence service requirement into a respective at least one intelligence service capability; select a service interface of a third network entity to control the at least one intelligent service capability; and transmit, to the selected service interface, a network intelligence request comprising the at least one intelligence service capability.

[0006] A method performed by a first network entity is described. The method may comprise: receiving, from a second network entity, a network service request including at least one intelligence service requirement related to a network service; establishing, with the second entity, a service level agreement in accordance with the at least one intelligent service requirement related to the network service; translating the at least one intelligence service requirement into a respective at least one intelligence service capability; select a service interface of a third network entity to control the at least one intelligent service capability; and transmitting, to the selected service interface, a network intelligence request comprising the at least one intelligence service capability.BRIEF DESCRIPTION OF THE DRAWINGS

[0007] Figure 1 illustrates an example of a wireless communications system in accordance with aspects of the present disclosure.

[0008] Figure 2 illustrates an overview of an ML-pipeline architecture including the main operations and components of the ML-pipeline and their respective interfaces.

[0009] Figure 3 illustrates an overview of the Network Intelligence Plane or network intelligent provider including their related services.

[0010] Figure 4 illustrates a network architecture showing the different network domains or network planes highlighting the distinct Al Service interfaces and components.

[0011] Figure 5 illustrates an example of a process flow 500 related to network service that requires the assistance of intelligence in accordance with aspects of the present disclosure.

[0012] Figure 6 illustrates an example of a UE in accordance with aspects of the present disclosure.

[0013] Figure 7 illustrates an example of a processor in accordance with aspects of the present disclosure.

[0014] Figure 8 illustrates an example of a NE in accordance with aspects of the present disclosure.

[0015] Figure 9 illustrates a flowchart of a method performed by a NE in accordance with aspects of the present disclosure.DETAILED DESCRIPTION

[0016] A wireless communication system, including one or more UE and NE may be subject to network intelligence by one or more network intelligence services. Such network intelligence may encompass any combination of analytics, decision and execution. Known arrangements assume that a network intelligence service is enabled by a single mobile network operator, which operates the radio and core network, network management, resource, and network intelligence component. When different parties operate the network management, mobile network, network resources, and network intelligence capabilities then there is a need to develop a ML Application Programming Interfaces (APIs) before introducing service APIs to allow control of offered services

[0017] The first network node described herein may obtain and control an intelligence service capability from a Network Intelligence Provider. The intelligence service capability may include network intelligence monitoring, analytics, decision and / or execution or any combination thereof. The intelligence service capability may require the application of AI / ML. The first network node may thus obtain the benefits of an intelligence service capability that uses AI / ML without needing to perform AI / ML processing itself. This allows for dedicated hardware and / or software for AI / ML to be provisioned at the Network Intelligence Provider, improving the operational efficiency of the intelligence service capability. The first network node may thus obtain the benefits of an intelligence service capability that uses AI / ML without needing to develop and maintain AI / ML logic itself or have the logic on how to form an AI / ML service chain or pipeline. This allows for dedicated software for AI / ML to be provisioned by the assistance of the Network Intelligence Provider, simplifying the operations and the efficiency of the intelligence service capability.

[0018] Aspects of the present disclosure are described in the context of a wireless communications system.

[0019] Figure 1 illustrates an example of a wireless communications system 100 in accordance with aspects of the present disclosure. The wireless communications system 100 may include one or more NE 102, one or more UE 104, and a core network (CN) 106. The wireless communications system 100 may support various radio access technologies. In some implementations, the wireless communications system 100 may be a 4G network, such as an LTE network or an LTE- Advanced (LTE-A) network. In some other implementations, the wireless communications system 100 may be a NR network, such as a 5G network, a 5G- Advanced (5G-A) network, or a 5G ultrawideband (5G-UWB) network. In other implementations, the wireless communications system 100 may be a combination of a 4G network and a 5G network, or other suitable radio access technology including Institute of Electrical and Electronics Engineers (IEEE) 802.11 (Wi-Fi), IEEE 802.16 (WiMAX), IEEE 802.20. The wireless communications system 100 may support radio access technologies beyond 5G, for example, 6G. Additionally, the wireless communications system 100 may support technologies, such as time division multiple access (TDMA), frequency division multiple access (FDMA), or code division multiple access (CDMA), etc.

[0020] The one or more NE 102 may be dispersed throughout a geographic region to form the wireless communications system 100. One or more of the NE 102 described herein may be or include or may be referred to as a network node, a base station, a network element, a network function, a network entity, a radio access network (RAN), a NodeB, an eNodeB (eNB), a next-generation NodeB (gNB), or other suitable terminology. An NE 102 and a UE 104 may communicate via a communication link, which may be a wireless or wired connection. For example, an NE 102 and a UE 104 may perform wireless communication (e.g., receive signalling, transmit signalling) over a Uu interface.

[0021] An NE 102 may provide a geographic coverage area for which the NE 102 may support services for one or more UEs 104 within the geographic coverage area. For example, an NE 102 and a UE 104 may support wireless communication of signals related to services (e.g., voice, video, packet data, messaging, broadcast, etc.) according to one or multiple radio access technologies. In some implementations, an NE 102 may be moveable, for example, a satellite associated with a non-terrestrial network (NTN). Insome implementations, different geographic coverage areas associated with the same or different radio access technologies may overlap, but the different geographic coverage areas may be associated with different NE 102.

[0022] The one or more UE 104 may be dispersed throughout a geographic region of the wireless communications system 100. A UE 104 may include or may be referred to as a remote unit, a mobile device, a wireless device, a remote device, a subscriber device, a transmitter device, a receiver device, or some other suitable terminology. In some implementations, the UE 104 may be referred to as a unit, a station, a terminal, or a client, among other examples. Additionally, or alternatively, the UE 104 may be referred to as an Internet-of-Things (loT) device, an Internet-of-Everything (loE) device, or machine-type communication (MTC) device, among other examples.

[0023] A UE 104 may be able to support wireless communication directly with other UEs 104 over a communication link. For example, a UE 104 may support wireless communication directly with another UE 104 over a device-to-device (D2D) communication link. In some implementations, such as vehicle-to-vehicle (V2V) deployments, vehicle-to-everything (V2X) deployments, or cellular- V2X deployments, the communication link may be referred to as a sidelink. For example, a UE 104 may support wireless communication directly with another UE 104 over a PC5 interface.

[0024] An NE 102 may support communications with the CN 106, or with another NE 102, or both. For example, an NE 102 may interface with other NE 102 or the CN 106 through one or more backhaul links (e.g., SI, N2, N2, or network interface). In some implementations, the NE 102 may communicate with each other directly. In some other implementations, the NE 102 may communicate with each other or indirectly (e.g., via the CN 106. In some implementations, one or more NE 102 may include subcomponents, such as an access network entity, which may be an example of an access node controller (ANC). An ANC may communicate with the one or more UEs 104 through one or more other access network transmission entities, which may be referred to as a radio heads, smart radio heads, or transmission-reception points (TRPs).

[0025] The CN 106 may support user authentication, access authorization, tracking, connectivity, and other access, routing, or mobility functions. The CN 106 may be anevolved packet core (EPC), or a 5G core (5GC), which may include a control plane entity that manages access and mobility (e.g., a mobility management entity (MME), an access and mobility management functions (AMF)) and a user plane entity that routes packets or interconnects to external networks (e.g., a serving gateway (S-GW), a Packet Data Network (PDN) gateway (P-GW), or a user plane function (UPF)). In some implementations, the control plane entity may manage non-access stratum (NAS) functions, such as mobility, authentication, and bearer management (e.g., data bearers, signal bearers, etc.) for the one or more UEs 104 served by the one or more NE 102 associated with the CN 106.

[0026] The CN 106 may communicate with a packet data network over one or more backhaul links (e.g., via an SI, N2, N2, or another network interface). The packet data network may include an application server. In some implementations, one or more UEs 104 may communicate with the application server. A UE 104 may establish a session (e.g., a protocol data unit (PDU) session, or the like) with the CN 106 via an NE 102. The CN 106 may route traffic (e.g., control information, data, and the like) between the UE 104 and the application server using the established session (e.g., the established PDU session). The PDU session may be an example of a logical connection between the UE 104 and the CN 106 (e.g., one or more network functions of the CN 106).

[0027] In the wireless communications system 100, the NEs 102 and the UEs 104 may use resources of the wireless communications system 100 (e.g., time resources (e.g., symbols, slots, subframes, frames, or the like) or frequency resources (e.g., subcarriers, carriers)) to perform various operations (e.g., wireless communications). In some implementations, the NEs 102 and the UEs 104 may support different resource structures. For example, the NEs 102 and the UEs 104 may support different frame structures. In some implementations, such as in 4G, the NEs 102 and the UEs 104 may support a single frame structure. In some other implementations, such as in 5G and among other suitable radio access technologies, the NEs 102 and the UEs 104 may support various frame structures (i.e., multiple frame structures). The NEs 102 and the UEs 104 may support various frame structures based on one or more numerologies.

[0028] One or more numerologies may be supported in the wireless communications system 100, and a numerology may include a subcarrier spacing and a cyclic prefix. A firstnumerology (e.g., / r=0) may be associated with a first subcarrier spacing (e.g., 15 kHz) and a normal cyclic prefix. In some implementations, the first numerology (e.g., / r=0) associated with the first subcarrier spacing (e.g., 15 kHz) may utilize one slot per subframe. A second numerology (e.g., / r=l) may be associated with a second subcarrier spacing (e.g., 30 kHz) and a normal cyclic prefix. A third numerology (e.g., / r=2) may be associated with a third subcarrier spacing (e.g., 60 kHz) and a normal cyclic prefix or an extended cyclic prefix. A fourth numerology (e.g., / r=3) may be associated with a fourth subcarrier spacing (e.g., 120 kHz) and a normal cyclic prefix. A fifth numerology (e.g., / r=4) may be associated with a fifth subcarrier spacing (e.g., 240 kHz) and a normal cyclic prefix.

[0029] A time interval of a resource (e.g., a communication resource) may be organized according to frames (also referred to as radio frames). Each frame may have a duration, for example, a 10 millisecond (ms) duration. In some implementations, each frame may include multiple subframes. For example, each frame may include 10 subframes, and each subframe may have a duration, for example, a 1 ms duration. In some implementations, each frame may have the same duration. In some implementations, each subframe of a frame may have the same duration.

[0030] Additionally, or alternatively, a time interval of a resource (e.g., a communication resource) may be organized according to slots. For example, a subframe may include a number (e.g., quantity) of slots. The number of slots in each subframe may also depend on the one or more numerologies supported in the wireless communications system 100. For instance, the first, second, third, fourth, and fifth numerologies (i.e., / r=0, jU=l, / r=2, jU=3, / r=4) associated with respective subcarrier spacings of 15 kHz, 30 kHz, 60 kHz, 120 kHz, and 240 kHz may utilize a single slot per subframe, two slots per subframe, four slots per subframe, eight slots per subframe, and 16 slots per subframe, respectively. Each slot may include a number (e.g., quantity) of symbols (e.g., OFDM symbols). In some implementations, the number (e.g., quantity) of slots for a subframe may depend on a numerology. For a normal cyclic prefix, a slot may include 14 symbols. For an extended cyclic prefix (e.g., applicable for 60 kHz subcarrier spacing), a slot may include 12 symbols. The relationship between the number of symbols per slot, the number of slots per subframe, and the number of slots per frame for a normal cyclic prefix and an extendedcyclic prefix may depend on a numerology. It should be understood that reference to a first numerology (e.g., fi=O) associated with a first subcarrier spacing (e.g., 15 kHz) may be used interchangeably between subframes and slots.

[0031] In the wireless communications system 100, an electromagnetic (EM) spectrum may be split, based on frequency or wavelength, into various classes, frequency bands, frequency channels, etc. By way of example, the wireless communications system 100 may support one or multiple operating frequency bands, such as frequency range designations FR1 (410 MHz - 7.125 GHz), FR2 (24.25 GHz - 52.6 GHz), FR3 (7.125 GHz - 24.25 GHz), FR4 (52.6 GHz - 114.25 GHz), FR4a or FR4-1 (52.6 GHz - 71 GHz), and FR5 (114.25 GHz - 300 GHz). In some implementations, the NEs 102 and the UEs 104 may perform wireless communications over one or more of the operating frequency bands. In some implementations, FR1 may be used by the NEs 102 and the UEs 104, among other equipment or devices for cellular communications traffic (e.g., control information, data). In some implementations, FR2 may be used by the NEs 102 and the UEs 104, among other equipment or devices for short-range, high data rate capabilities.

[0032] FR1 may be associated with one or multiple numerologies (e.g., at least three numerologies). For example, FR1 may be associated with a first numerology (e.g., / r=0), which includes 15 kHz subcarrier spacing; a second numerology (e.g., / z=l), which includes 30 kHz subcarrier spacing; and a third numerology (e.g., / r=2), which includes 60 kHz subcarrier spacing. FR2 may be associated with one or multiple numerologies (e.g., at least 2 numerologies). For example, FR2 may be associated with a third numerology (e.g., / r=2), which includes 60 kHz subcarrier spacing; and a fourth numerology (e.g., / z=3), which includes 120 kHz subcarrier spacing.

[0033] AI / ML may be employed in network analytics applied to a 5G core network. Such network analytics may include analytics functions or services inside the mobile network in fixed pre-configured locations. Such pre-configured locations may not change during the service life cycle. Where machine learning or ML is mentioned in this document, this should be understood to include what is currently referred to as Artificial Intelligence or Al.

[0034] AI / ML has already been introduced in the mobile core network with the Network Data Analytics Function (NWDAF) supporting various analytics types as elaborated in TS 23.288 vl9.1.0 (December 2024) titled “Architecture enhancements for 5G System (5GS) to support network data analytics services”. Each NWDAF may support one or more analytics, each analytic having an Analytics ID. Each NWDAF may have the role of inference, training, or both. An NWDAF having an inference role is called an NWDAF Analytics Logical Function (AnLF). An NWDAF having a training role is called an NWDAF Model Training Logical Function (MTLF). An AnLF that supports a specific Analytics ID inference subscribes to a MTLF that is responsible for training the specific Analytics ID.

[0035] Similarly, the use of Application Data Analytics Enablement Service (AD AES) to launch AI / ML services in the application layer also relies on analytics identifiers (such as the Analytics ID) for selecting a specific analytics service. The AD AES distinguishes the roles of ML analytics into inference and training as detailed in TS 23.436 vl9.3.0 (January 2025) titled “Functional architecture and information flows for Application Data Analytics Enablement Service”. AI / ML and analytics in the management plane, i.e., Management Data Analytics (MDA), also follow the same paradigm. MDA are preconfigured, invoked based on analytics identifier and perform inference as documented in TS 28.104 vl 9.0.0 (January 2025) titled “Management and orchestration; Management Data Analytics (MDA)”. The MDA is supported by another training service entity as per TS 28.105 V19.1.0 (January 2025) titled “Management and orchestration; Artificial Intelligence / Machine Learning (AI / ML) management”.

[0036] Different AI / ML models can be supported in the 5G core, application and management planes including supervised or semi-supervised learning based on data labels, federated learning, transfer learning and Reinforcement Learning (RL) models. One or more AI / ML models may be selected based on the needs and service paradigms for the analytics.

[0037] Current AI / ML schemes may use at least one data collection and distribution framework, e.g., based on Data Collection Coordination Function (DCCF) in 5G core or Application-DCCF (A-DCCF) in the application plane, to efficiently subscribe to datasources, collect, and distribute raw data and analytics. Optionally, AI / ML may also adopt data preparation mechanisms, e.g., to clean and check data from random errors and format it for the respective AI / ML model.

[0038] Each AI / ML or analytics entity may collect various input data, which may include data from 5G core Network Functions (NFs), Application Functions (AFs), 5G core repositories, e.g., Network Repository Function (NRF), Unified Data Management (UDM) / Unified Data Repository (UDR), and the Operations, Administration and Maintenance (0AM) system, i.e., via a Management Service (MnS) Consumer or Management Function (MF). Typically, this data is collected from fixed input data sources per analytics service identifier, i.e., input data sources that are pre-determined as required input to enable the calculation of the respective analytics data, with respect to the geographical area in where the analytics service operates.

[0039] It should be noted that the 3 GPP standards support pre-configured AI / ML functions that support a service indicated by an identifier and may perform inference or training or both, based on input data received from pre-determined data sources. 3 GPP paradigms do not support dynamic configuration of AI / ML functions considering customization requests.

[0040] As well as the 3GPP paradigm, ITU-T FG-ML5G, introduces the notion of a ML pipeline where an ML orchestrator, a.k.a., ML Function Orchestrator (MLFO), creates a service chain of AI / ML logical processes or components based on a consumer request. The ML pipeline allows a consumer to issue an intent that is analysed by the ML orchestrator, which may determine AI / ML components and their respective location assuming that distinct components may reside across different technology domains, e.g., radio, core, or transport networks, which are operated by the single 0AM entity. The different AI / ML components may include:• a source (SRC) that generates raw data to feed into the AI / ML Model;• a collector (C), which collects data from various sources;• a pre-processor (PP), which is responsible for preparing the data to fit the AI / ML model by performing data processing operations, cleansing, formatting and / or aggregation;• an AI / ML Model (M) representing an AI / ML logic or algorithm;• a policy (P) that leverages the output of the Model and apply a suitable set of rules depending on the corresponding use case;• a distributor (D), which is in charge of identifying the Sinks and the distributing Policy to forward the output of the Model towards the corresponding Sinks; and• a sink (SINK), which is the target node of the Distributor.

[0041] Figure 2 illustrates an arrangement 200 in accordance with aspects of the present disclosure. The arrangement 200 may implement or be implemented by aspects of the wireless communication system 100. For example, the arrangement 200 may include a management subsystem 210, an ML sandbox subsystem 220, an ML pipeline subsystem 230, a plurality of ML underlay networks 240, any of which may be implemented by one or more examples of devices described herein with reference to Figure 1. The plurality of ML underlay networks 240 may include a first underlay network 241 and a second underlay network 242.

[0042] The arrangement 200 may be referred to as a procedure, including one or more operations performed by one or more of the management subsystem 210, the ML sandbox subsystem 220, the ML pipeline subsystem 230, and the plurality of ML underlay networks 240. In the example of Figure 2, the arrangement 200 may include overview of the ML- pipeline architecture.

[0043] In the following description of the arrangement 200, the operations or signalling performed between one or more of the management subsystem 210, the ML sandbox subsystem 220, the ML pipeline subsystem 230, and the plurality of ML underlay networks 240 may be performed or signalled (e.g., transmitted, received) in a different order than the example order shown, or the operations or signalling performed by one or more of the management subsystem 210, the ML sandbox subsystem 220, the ML pipeline subsystem 230, and the plurality of ML underlay networks 240 may be performed or signalled (e.g., transmitted, received) in different orders or at different times. Some operations or signalling may also be omitted from the arrangement 200. Additionally, although some operations or signalling may be shown to occur at different times, these operations or signalling may occur at the same time or in overlapping time periods.

[0044] The ML-pipeline architecture of Figure 2 may be used to provide an intelligence service as described herein. The intelligence service may comprise one or more intelligence service capabilities. In some cases, an intelligence service capability may be referred to as an intelligence service requirement. An intelligence service capability and / or requirement may include network intelligence monitoring, analytics, decision and / or execution or any combination thereof. The intelligence service capability may require the application of AI / ML. The first network node may thus obtain the benefits of an intelligence service capability that uses AI / ML without needing to perform AI / ML processing itself. This allows for dedicated hardware and / or software for AI / ML to be provisioned at the Network Intelligence Provider, improving the operational efficiency of the intelligence service capability. The first network node may thus obtain the benefits of an intelligence service capability that uses AI / ML without needing to develop and maintain AI / ML logic itself or have the logic on how to form an AI / ML service chain or pipeline.

[0045] The life-cycle management of an AI / ML-pipeline relies on the MLFO, which resides on the 0AM system and takes care of the configuration, scale-up / down and relocation of AI / ML-pipeline components. An AI / ML-pipeline can serve as input to a sandbox for simulation or can be applied in a real network environment directly or both. An overview of the ML-pipeline architecture including the main operations and components of the ML-pipeline and the respective interfaces is illustrated in Figure 2.

[0046] A plurality of interfaces are illustrated in Figure 2.• 271, 272 are data handling interfaces between simulated ML underlay networks and an ML pipeline in an ML sandbox subsystem.• 273 is the interface between an ML sandbox subsystem and an ML pipeline subsystem.• 274 is the interface between an ML pipeline subsystem and ML underlay networks.• 275, 276 are the interfaces between the management subsystem and the ML pipeline subsystem and ML sandbox subsystem, respectively.• 277 is the interface between the MLFO and other management and orchestration functions of the management subsystem.• 278, 279 are the interfaces between ML pipeline nodes located in different levels or network domains.

[0047] It should be noted that ITU-T FG-ML5G (March 2019) “Unified Architecture for Machine Learning in 5G and Future Networks” supports the on-demand creation and configuration of an ML pipeline that can serve an incoming intent. ITU-T FG-ML5G supports such creation and configuration without specifying the format of such intent, by an ML orchestrator. The ML orchestrator may be the MLFO, which resides in the 0AM system. Hence, there is no definition of a service interface that can be modelled using intent, and which can enable a consumer to request, modify and terminate an ML-pipeline. In addition, there is currently no definition of any notion of automation in the process of the lifecycle management related with the ML-pipeline.

[0048] A Network Intelligence Plane is described herein within the context of the EU- funded DAEMON project, (e.g., M. Camelo, et.al., DAEMON: A Network Intelligence Plane for 6G Networks, IEEE Globecom Workshops, 2022). The DAEMON project aims to manage the lifecycle management of AI / ML operation and assist the control plane and user plane empowering them with intelligence. The role of the NIP is to orchestrate network intelligence by introducing the following capabilities:• decompose complex Network Intelligence (NI) instances and represent them as a combination of atomic NI elements forming closed control loops across different network domains;• provide NI Interfaces to enable communication between NI instances;• support NI lifecycle management, services and functions and shall provide coordination among NI instances; and / or• support NI catalogue to enable to choose NI instance to onboard at a given time considering available computing resources, inference latency requirements, or accuracy constraints.

[0049] The DAEMON project aims to support NI service composition considering the mobile operator computing and network capabilities, while it also sheds light into the life cycle management of an NI service. The DEAMON project focuses on how an AI / ML service can be composed and configured, but it does not consider how a service can berequested or how to form a request as an intent to enable consumers to receive an AI / ML service. Further, it would be advantageous if the consumer could do so without dealing with the details related to the technical requirements. So far there has been no effort to develop an agent-based approach for offering intelligent services that can be self-tuned by considering the alternating conditions within the mobile network.

[0050] The solution presented herein introduces a means to enable and control an intelligent service once a Service Level Agreement (SLA) between a consumer and an intelligence capabilities provider is established. Such an SLA may be established through a Business Support Systems (BSS). An intelligent capabilities provider may be a part of the mobile network operator (MNO) or an independent business entity. The intelligence capabilities provider can offer AI / ML services or micro-services from which a consumer may request, resembling a notion of a network intelligence plane or an intelligence toolset.

[0051] Intelligence can be introduced by providing an AI / ML service chain or pipeline and respective AI / ML service capabilities, which can be configured in the network by the corresponding network orchestrator with respect to a network service and / or application. To introduce self-tuning capabilities and assure that the configured AI / ML service chain or pipeline performs as expected despite of alternating network conditions, there is defined herein an Al agent. The Al agent may be responsible for facilitating flexibility by adjusting the provisioned one or more AI / ML pipelines, i.e., by adding and / or modifying selected intelligent services, to reflect evolving network conditions The Al agent may also be responsible for selecting the Al capabilities, assembling the AI / ML service chain or AI / ML pipeline and taking care of its life cycle management considering the feedback from the respective consumer.

[0052] Figure 3 illustrates an example of a Network Intelligence Plane 300 in accordance with aspects of the present disclosure. The Network Intelligence Plane 300 may implement or be implemented by aspects of the wireless communication system 100. For example, the Network Intelligence Plane 300 may include a data service 303, an AI / ML model database 306, an AI / ML inference service 309, an AI / ML model training service 312, an AI / ML model performance monitoring service 315, an AI / ML maintenance service 318, a data processing service 321, an at least one data collection & distribution service324, an at least one storage service 327, a network digital twin service 330, an AI / ML online learning service 333, and an AI / ML orchestrator 336, which may be implemented by one or more examples of devices described herein with reference to Figure 1.

[0053] The Network Intelligence Plane 300 may be referred to as a procedure, including one or more operations performed by one or more of the data service 303, the AI / ML model database 306, the AI / ML inference service 309, the AI / ML model training service 312, the AI / ML model performance monitoring service 315, the AI / ML maintenance service 318, the data processing service 321, the at least one data collection & distribution service 324, the at least one storage service 327, the network digital twin service 330, the AI / ML online learning service 333, and the AI / ML orchestrator 336. In the example of Figure 3, the Network Intelligence Plane 300 may include a plurality of services.

[0054] In the following description of the Network Intelligence Plane 300, the operations or signalling performed between one or more of the data service 303, the AI / ML model database 306, the AI / ML inference service 309, the AI / ML model training service 312, the AI / ML model performance monitoring service 315, the AI / ML maintenance service 318, the data processing service 321, the at least one data collection & distribution service 324, the at least one storage service 327, the network digital twin service 330, the AI / ML online learning service 333, and the AI / ML orchestrator 336 may be performed or signalled (e.g., transmitted, received) in a different order than the example order shown, or the operations or signalling performed by one or more of the data service 303, the AI / ML model database 306, the AI / ML inference service 309, the AI / ML model training service 312, the AI / ML model performance monitoring service 315, the AI / ML maintenance service 318, the data processing service 321, the at least one data collection & distribution service 324, the at least one storage service 327, the network digital twin service 330, the AI / ML online learning service 333, and the AI / ML orchestrator 336 may be performed or signalled (e.g., transmitted, received) in different orders or at different times. Some operations or signalling may also be omitted from the Network Intelligence Plane 300. Additionally, although some operations or signalling may be shown to occur at differenttimes, these operations or signalling may occur at the same time or in overlapping time periods.

[0055] The Network Intelligence Plane and network intelligent provider of Figure 3 may be used to provide an intelligence service as described herein. The intelligence service may comprise one or more intelligence service capabilities. In some cases, an intelligence service capability may be referred to as an intelligence service requirement. An intelligence service capability and / or requirement may include network intelligence monitoring, analytics, decision and / or execution or any combination thereof. The intelligence service capability may require the application of AI / ML. The first network node may thus obtain the benefits of an intelligence service capability that uses AI / ML without needing to perform AI / ML processing itself. This allows for dedicated hardware and / or software for AI / ML to be provisioned at the Network Intelligence Provider, improving the operational efficiency of the intelligence service capability. The first network node may thus obtain the benefits of an intelligence service capability that uses AI / ML without needing to develop and maintain AI / ML logic itself or have the logic on how to form an AI / ML service chain or pipeline.

[0056] An overview of the Network Intelligence Plane or network intelligent provider including the related services is illustrated in Figure 3. The terminology “Network Intelligence Plane” and “network intelligent provider” can be used interchangeably in this disclosure. The Network Intelligence Plane is not obliged to follow a service-based architecture paradigm and can also be deployed using point to point interfaces. However, a service-based architecture paradigm offers benefits in terms of flexibility in composing and provisioning an AI / ML pipeline service. The Network Intelligence Plane may reside at the same business entity as the MNO, i.e., it can be a part of the same PLMN or can also belong to a different business entity. Such a Network Intelligence Plane can be seen as a library of software services, microservices, or capabilities that can be offered to different consumers (which in this case may also be offered by different parties and / or different business entities). Such a library of software services, microservices, or capabilities may include any of the following non-limiting list of examples from Figure 3.

[0057] AI / ML orchestrator 336, which is responsible for authentication and authorization procedures as well as for provisioning an Al agent to assist the consumer with the selection, arrangement and life-cycle management of the offered an intelligent service. An Al agent can be associated with a single consumer request carrying out several tasks, i.e., several ML pipelines, or alternative being responsible for a specific ML pipeline depending on the agreed level of granularity.

[0058] Data service capabilities 303 related to data sets for AI / ML Model training with respect to specific AI / ML task ID, network environment, (e.g., type of network), and described with a DataTag that contains data statics (e.g., range, max-min, distribution, etc.)

[0059] Data Processing service capabilities 321 introduce (i) data analysis to determine the central data tendency, anomalies, missing values and outliers, (ii) data processing to augment missing data and perform data cleaning, (iii) data labelling introducing data tag to interpret raw data, (v) data formatting to prepare data sets for AI / ML Model processing.

[0060] Data Collection / Distribution service capabilities 324 that assist data collection and distribution of raw data from data sources and Al related data, e.g., analytics.

[0061] Storage service capabilities 327 introduce to enable storage of raw data, AI / ML Models and knowledge based on previous experience for building historical record.

[0062] AI / ML Inference service capabilities 309, includes the AI / ML logic to perform inference based on a selected AI / ML Model type.

[0063] AI / ML model training service 312, includes the AI / ML logic and APIs configured to perform AI / ML model training for specific AI / ML task and inference service that adopts a certain AI / ML Model type and optionally it includes the logic for providing AI / ML Model validation and testing.

[0064] AL / ML Model Data Base service capabilities 306, provides different types ofAI / ML Models, which can be selected to be trained and used in the AI / ML inference services.

[0065] AL / ML Online Learning service capabilities 333 to assist the feedback in online learning, e.g., the network state and / or the consumer feedback.

[0066] AI / ML Model Performance Monitoring service capabilities 315 related to accuracy considering: (i) feedback from the consumer, (ii) correlation of ground truth data with predictions, (iii) deviations in collected training data.

[0067] AI / ML Model Maintenance service capabilities 318 include updates once a new version is available.

[0068] Network Digital Twin service capabilities 330 support AI / ML Model training services by providing: (i) missing data or (ii) AI / ML model training for RL Models.

[0069] It should be noted certain combinations of the AI / ML capabilities may be influenced by the AI / ML Model selection, e.g., a selection of an RL Model that does not need an AI / ML Training service capabilities but needs AI / ML Model Interpreter service capabilities.

[0070] The Network Intelligence Plane may be operated by the MNO that is responsible for provisioning the 0AM based network management and orchestration services. The Network Intelligence Plane may be operated by a different business entity, i.e., operated by a computing or application provider such as Amazon or an AI / ML provider, e.g., NVIDIA.

[0071] Once authentication and authorization are completed and the respective interactions are set having established a SLA among the MNO and the Network Intelligent Plane provider a service interaction is initiated. The goal of the service interaction is to:• introduce and manage AI / ML related service requirements if the Network Intelligent Plane resides in the MNO;• translate an established business SLA into operational service requirements, i.e., from BSS to Operation Support Subsystem (OSS); and / or• discover and select the appropriate service API that would assist the consumer of the network intelligent service to manage and control it.

[0072] There are two different scenarios when requesting the Network Intelligence Plane and specifically the AI / ML orchestrator to provide AI / ML service capabilities, these are described in the following paragraphs.

[0073] A Management Function (MF) that belongs to MNO requests the Network Intelligence Plane to provide AI / ML service capabilities for network management and orchestration purposes, e.g., resource management, coordination and conflict resolution, root cause analysis, fault and alarms management, etc., which may span among different network services. The MF may also request the Network Intelligence Plane to provide AI / ML service capabilities for network services related to third parties that request intelligence related to a specific network service, which can be configured by the 0AM.

[0074] A network resource orchestrator, i.e., responsible for collecting and trading virtual network and cloud resources, e.g., Network Function Virtualization (NFV) Orchestrator within the ETSI NFV Architecture Framework ETSI GS NFV 002 vl.2.1 (2014-12), may request that the Network Intelligence Plane provide AI / ML service capabilities for resource optimization, feasibility check, etc., which may span among different network services offered by a network management system.

[0075] Figure 4 illustrates an example of an arrangement 400 in accordance with aspects of the present disclosure. The arrangement 400 may implement or be implemented by aspects of the wireless communication system 100. For example, the arrangement 400 may include a network service customer 402, a mobile network operator 410, an intelligence plane provider 420, and an underlying network resource provider 430, which may be embodied by one or more examples of devices described herein with reference to Figure 1. The mobile network operator 410 may include at least one network slice 412 and a management plane 416. Each network slice 412 may include a user plane 413 and a control plane 414.

[0076] The arrangement 400 may be referred to as a procedure, including one or more operations performed by one or more of the network service customer 402, the mobile network operator 410, the intelligence plane provider 420, and the underlying network resource provider 430. In the example of Figure 4, the arrangement 400 provides an overview of the network architecture indicating the different network planes and involved parties.

[0077] In the following description of the arrangement 400, the operations or signalling performed between one or more of the network service customer 402, the mobile networkoperator 410, the intelligence plane provider 420, and the underlying network resource provider 430 may be performed or signalled (e.g., transmitted, received) in a different order than the example order shown, or the operations or signalling performed by one or more of the network service customer 402, the mobile network operator 410, the intelligence plane provider 420, and the underlying network resource provider 430 may be performed or signalled (e.g., transmitted, received) in different orders or at different times. Some operations or signalling may also be omitted from the arrangement 400. Additionally, although some operations or signalling may be shown to occur at different times, these operations or signalling may occur at the same time or in overlapping time periods.

[0078] The Al Service interfaces and components of Figure 4 may be used to provide an intelligence service as described herein. The intelligence service may comprise one or more intelligence service capabilities. In some cases, an intelligence service capability may be referred to as an intelligence service requirement. An intelligence service capability and / or requirement may include network intelligence monitoring, analytics, decision and / or execution or any combination thereof. The intelligence service capability may require the application of AI / ML. The first network node may thus obtain the benefits of an intelligence service capability that uses AI / ML without needing to perform AI / ML processing itself. This allows for dedicated hardware and / or software for AI / ML to be provisioned at the Network Intelligence Provider, improving the operational efficiency of the intelligence service capability. The first network node may thus obtain the benefits of an intelligence service capability that uses AI / ML without needing to develop and maintain AI / ML logic itself or have the logic on how to form an AI / ML service chain or pipeline.

[0079] Figure 4 illustrates the network architecture showing the different network domains or network planes highlighting the distinct Al Service interfaces and components. The Al service interfaces may include:• Al-Serv API 415, 425 that enables the instantiation and life-cycle management of an Al service in the: (a) management plane, i.e., 0AM, (b) NS configured by the 0AM and (c) in the network resource plane or domain, and / or• NS-API 405, which can: (a) be based on the “Generic Slice Template (GST)”, as per GSMA NG.116, in where Al is included as enhanced features or (b) be introduced a new Al NS API focusing on the Al service aspects.

[0080] The Network Intelligent Plane may reside into the premisses of a different provider. The MNO may use the Network Intelligent Plane and the underlying network resources, which may also be operated by a different provider.

[0081] In case a network service customer issues a request to the MNO and an agreement is established with an SLA then the request can be analyzed and translated, i.e., from BSS to OSS, to derive AI / ML service requirements. Equally when the management plane or the network resource provider are independent entities and have established an agreement with the intelligent plane provider then a BSS to OSS translation is performed to derive the respective AI / ML service requirements.

[0082] The following AI / ML service requirements can be derived from BSS to OSS translation:• Prom a business service or network service task (a network service task can relate to a management service or a resource optimization service) and related goal objectives that requires intelligence it can be derived the: o Type of intelligent service that is needed, e.g., Analytics ID; more than one Analytics ID can be derived depending on the business task for example levels of automation in a vehicular scenario may require network load predictions and user mobility predictions. o Domain of intelligence, i.e., RAN, core network, application, network management, and / or a combination of thereof. o Scenario for applying intelligence including: (i) network and service planning, (ii) network and service deployment, (iii) network and service maintenance, (iv) network and service optimization and / or a combination of thereof.• From the indicated desired level of intelligence, as per TS 28.100 related to levels of automation it can be derived:o In which part of the lifecycle of AI / ML shall intelligence be introduced, i.e., awareness, analytics, decision, execution, or interaction with consumer, i.e., intent and / or a combination of thereof. o Scope of intelligence including: (i) embedded in a network element, e.g., NF or base station, (ii) domain level, e.g., RAN, core, (iii) cross-domain level, (iv) communication service and / or a combination of thereof.• From the AI / ML Model performance, it can be derived: o The need to include AI / ML Model performance monitoring. o A reputation of AI / ML models with respect to the indicated accuracy o Decide how fast is expected to provide a result, i.e., immediate, near-real time, non-real time, that influences: (i) if an AI / ML Model is embedded on, e.g., NF or base station, or be an external network entity, e.g., NF, domain level or cross-domain level, (ii) if AI / ML Model shall be trained offline or online, (iii) when a certain upper bound limit is provided for the desired computing resources.• From the expected AI / ML service cost, i.e., an indicated upper bound cost, it can be derived: o The sophistication level or complexity considering inference, training and preparation of the adopted AI / ML Model• From AI / ML models or hardware restrictions, it can be derived: o An indication of AI / ML Models related to specific vendors or application providers o An indication of AI / ML Model data format, or alternatively the data format needed.• From AI / ML pipeline maintenance, it can be derived: o An indication of requiring AI / ML component software updates and troubleshooting including security.• Indication of the spatial validity information in terms of geographical coordinates that can be translated into one or more Tracking Area or cells in where the AI / ML Model shall be applied.• Indication of the temporal validity that shapes the time schedule for applying the AI / ML Model.

[0083] The translated AI / ML service requirements can then be communicated to the intelligent plane provider on the service level, i.e., among the OSSs of the different business entities, assuming that a pre-determined API is in place.

[0084] Such API may include at least one of the documented AI / ML service requirements derived from the BSS to OSS translation. Once the AI / ML service requirements are received by the AI / ML orchestrator or Al agent provisioned, it determines: (i) AI / ML Model type that can assist the selected AI / ML tasks, (ii) the applicability conditions related to AI / ML Model type (i.e., how and where it can be applied), and / or (iii) accompanied operations and restrictions.

[0085] Alternatively, once the business agreement is established and provided that the consumer is already authorized then the intelligent plane provider can:• allow the consumer to discover and access the respective API, so it can request and control a specific AI / ML service job from the Intelligent plane provider; and / or• publish the available APIs so the consumer can select the one it needs.

[0086] The use of existing methods can be adopted for the AI / ML service API usage such as the Common API Framework (CAPIF) as per 3GPP TS 23.222 vl9.4.0 (January 2025) titled “Common API Framework for 3GPP Northbound APIs”.

[0087] The process of discovering or publishing available APIs can also take place following an initial AI / ML service request provided that the intelligent plane provider, i.e., the AI / ML orchestrator or Al agent, has determined that a certain AI / ML Model type exist with the respective AI / ML pipeline components that can assist towards fulfilling this AI / ML service request providing a kind of feasibility check before enabling the consumer to use other APIs.

[0088] Several service APIs which can be either offered or published may exist including the following:• AI / ML pipeline service API allows a consumer to control a specified AI / ML lifecycle and to request modifications related to one or more intelligent servicecomponents that can be separated or inter-related. The AI / ML pipeline as a service API may include information related to at least: o AI / ML pipeline ID for initial deployment and further modifications activities. o Data related requirements including lack of data or data restrictions in specific locations, data preparation components. o Need of specific AI / ML Model preparation services, i.e., pre-training, using Network Digital Twin. o Need of specific AI / ML pipeline components, e.g., inference, training, data collection and distribution, storage. o Preference for AI / ML Model type including indication of AI / ML Model transfer or knowledge transfer related parameters. o Indication of the spatial and temporal validity for applying the AI / ML pipeline. o Indication of AI / ML service target and consumer entities.Note: These parameters may be initially selected and modified by the consumer to reflect certain network conditions that may change and are not visible into the Intelligent Plane Provider, since it cannot collect network data to make decision in terms of the deployment, but only takes care of the service chain as a logical sequence of AI / ML related services that needs to be executed.• AI / ML pipeline performance monitoring service API may include information related to at least: o AI / ML Model performance ID for initial deployment and further modifications activities. o Performance of pre-trained AI / ML Models and / or evaluation of the data provided for the AI / ML Model training. o AI / ML Model performance accuracy:■ mechanisms, based on, e.g., (i) consumer feedback API, (ii) corelation of predictions and ground truth data in the inference components, (iii) correlation of newly with old collected data in the training component, and respective■ fulfilling targets that can be indicated as threshold value and a time duration when a threshold is violated before triggering a corrective action. o AI / ML Model performance speed or responding targets including:■ how fast an AI / ML Model shall (i) provide an inference result, and / or (ii) learn considering different options: (a) AI / ML training process, e.g., based on labelled or unlabelled data, or (b) online training.■ the required and / or available computing resources with respect to inference and / or training speed targets. o The amount of input data and / or data statistics, e.g., data distribution, mixmax, etc., that used to feed AI / ML Model training with respect to achieved accuracy target. o Performance of the data collection and distribution component, which can be measured by e.g., speed and / or efficiency or amount of data that can be collected within a specified time duration. o AI / ML pipeline performance based on: (i) positioning of inference with respect to the AI / ML Model targets, i.e., for collecting input data, and consumers, i.e., for providing the analytics result, (ii) positioning of training with respect to inference to reduce the response time when training is needed. o Indication of the spatial and temporal validity for applying AI / ML Model performance monitoring.This API can assist the consumer to inform the Intelligent plane provider regarding the performance related to the components of the AI / ML pipeline, which provide recommendation and suggestion related to the use of specific AI / ML components.• AI / ML pipeline cost service API may include information related to at least: o AI / ML pipeline cost ID for accounting correspondence. o Processing cost, i.e., assisting an AI / ML pipeline lifecycle management, related to the AI / ML orchestration or Al Agent, or alternative per Al Agent associated with an AI / ML pipeline.o Cost of AI / ML pipeline and / or individual components used in the AI / ML pipeline for the duration of the AI / ML pipeline service. o Cost of monitoring service including suggestions for performance improvement as events, i.e., upon a report, and / or for a duration of time. o Cost of maintenance including updates to the AI / ML pipeline or individual components, as events, i.e., upon a report, and / or for a duration of time.This API can assist the intelligent plane provider keep a charging record related to the provided services and inform the consumer when an update is recorded.• AI / ML pipeline maintenance may include information related to at least: o AI / ML pipeline maintenance ID for future correspondence. o AI / ML pipeline component ID and version, vendor and data format if applicable. o AI / ML maintenance events or time duration. o Preference AI / ML pipeline component for maintenance.This API can assist the intelligent plane provider to get information related to AI / ML pipeline maintenance needs from consumers.

[0089] In case the management plane or the network resource provider reside at the same business entity as the intelligent plane provider then these service APIs can be used directly without the need to establish a business SLA, however authorization and authentication may still be needed for enabling consumers to access them.

[0090] It shall be note that the described AI / ML APIs as separate entities is one embodiment. Alternatively, these APIs may be combined, for instance the AI / ML pipeline service API can be combined with the AI / ML pipeline performance monitoring service API to form a single AI / ML pipeline lifecycle management API or all these APIs can be combined to form a single API related to AI / ML pipeline service adopting any combination of the API parameters described.

[0091] Figure 5 illustrates an example of a process flow 500 in accordance with aspects of the present disclosure. The process flow 500 may implement or be implemented by aspects of the wireless communication system 100. For example, the process flow 500 may include a network service customer 502, a mobile network operator 510, a networkresource provider 530, and a network intelligence provider 520, which may be one or more examples of devices described herein with reference to Figure 1. The mobile network operator 510 may be BSS enabled for AI / ML requests. The network resource provider 530 may include a BSS: resource and Al SLA. The network intelligence provider 520 may be BSS enabled for AI / ML requests.

[0092] The process flow 500 may be referred to as a procedure, including one or more operations performed by one or more of the network service customer 502, the mobile network operator 510, the network resource provider 530, and the network intelligence provider 520. In the example of Figure 5, the process flow 500 may include a business request including AI / ML services being issued from a Network service customer to the Mobile Network Operator.

[0093] In the following description of the process flow 500, the operations or signalling performed between one or more of the network service customer 502, the mobile network operator 510, the network resource provider 530, and the network intelligence provider 520 may be performed or signalled (e.g., transmitted, received) in a different order than the example order shown, or the operations or signalling performed by one or more of the network service customer 502, the mobile network operator 510, the network resource provider 530, and the network intelligence provider 520 may be performed or signalled (e.g., transmitted, received) in different orders or at different times. Some operations or signalling may also be omitted from the process flow 500. Additionally, although some operations or signalling may be shown to occur at different times, these operations or signalling may occur at the same time or in overlapping time periods.

[0094] The process flow of Figure 5 may be used to provide an intelligence service as described herein. The intelligence service may comprise one or more intelligence service capabilities. In some cases, an intelligence service capability may be referred to as an intelligence service requirement. An intelligence service capability and / or requirement may include network intelligence monitoring, analytics, decision and / or execution or any combination thereof. The intelligence service capability may require the application of AI / ML. The first network node may thus obtain the benefits of an intelligence service capability that uses AI / ML without needing to perform AI / ML processing itself. Thisallows for dedicated hardware and / or software for AI / ML to be provisioned at the Network Intelligence Provider, improving the operational efficiency of the intelligence service capability. The first network node may thus obtain the benefits of an intelligence service capability that uses AI / ML without needing to develop and maintain AI / ML logic itself or have the logic on how to form an AI / ML service chain or pipeline.

[0095] An overview of the process related to network service that requires the assistance of intelligence is illustrated in figure 5. The Network Service Customer 502 issues a request to the MNO 510, which handles this request via the 0AM. Specifically, the request is handled initially vi the BSS system of the 0AM and once an SLA is established then the service requirements are derived, and service-related APIs can be used to control the respective network and AI / ML services.

[0096] The Mobile Network Operator 510 and the Network Resource Provider 530 are different entities that consume intelligence or AI / ML service from an independent Network Intelligence Provider 520, the following steps are executed once an SLA is established via the BSS.

[0097] At 571, The network service customer 502 may issue (e.g. sends, transmits, outputs), and the MNO 510 may receive (e.g., acquire, obtain), a request for establishing a network service. The MNO 510 may be chosen by the network service customer 502. The network service request includes AI / ML requirements.

[0098] At 572, once the MNO 510 receives the network service request and establishes an SLA with the network, the business or SLA requirements may then be translated into service requirements, i.e., deriving network service requirements related to network resources and AI / ML service requirements.

[0099] At 573, the MNO 510 may negotiate with the Network Resource Provider 530 and establishes an SLA for the underlying network resources.

[0100] At 574, once a feasibility check is performed and the network service can be established using the underlying network resources, the MNO 510 issues (e.g. sends, transmits, outputs), and the Network Intelligence Provider 520 may receive (e.g., acquire,obtain), an AI / ML service request using a respective API to communicate the AI / ML service requirements (i.e., the outcome of the translated network service SLA).

[0101] At 575, after it receives the request, the Network Intelligent Provider 520 performs the authentication / authorization (if not performed already in previous step) and checks its feasibility, i.e., if it can offer AI / ML service components that can form an AI / ML pipeline that fulfils the desired service requirements, it instantiates an Al Agent to be responsible for the AI / ML pipeline. An Al Agent can be associated with one or more AI / ML pipeline related to a certain consumer. Alternative the AI / ML orchestrator can handle the instantiation of the AI / ML pipeline.

[0102] At 576, if the authentication / authorization is successful and the AI / ML pipeline instantiation is feasible then the Network Intelligence Provider 520, i.e., the Al Agent, notifies the MNO management system, BSS / OSS, that certain AI / ML APIs are available to be discovered, which can assist the consumer to control the AI / ML pipeline, its components and manage its lifecycle or alternative it pushes the available APIs so the consumer can choose the appropriate one depending on its needs.

[0103] At 577, the MNO 510 notifies (e.g. sends, transmits, outputs), and the network service customer may receive (e.g., acquire, obtain), the status of accepting its network service request and provides suggestions to adjust the provided service requirements in a negotiation phase if needed. The Network Service Customer 502 provides preferences on the deployment of the network service also including information regarding the selection of AI / ML service APIs.

[0104] At 578, once the Network Service Customer 502 provides an indication of the preferred AI / ML service APIs that shall be used for controlling the AI / ML pipeline lifecycle the MNO BSS / OSS can reflect it and use it. It should be noted that the MNO 510 can derive the customer preference from the AI / ML requirements of original network service request or after the translation phase.

[0105] At 579, selecting the AI / ML pipeline service API may include the following steps:• At 579a, the MNO 510, i.e., its OSS, can indicate to the Al Agent of the Network Intelligent Provider its preference of the AI / ML pipeline components, which is used from the Al Agent to form an AI / ML pipeline.• At 579b, the Network Intelligence Provider 520 can then provision the AI / ML pipeline that best suits the received requirements.• At 579c, the MNO 510 configures this AI / ML pipeline for the respective network service and provides a notification to inform the Network Service Customer 502 including billing information.

[0106] At 580, in case the Network Service Customer 502 indicated the preference to monitor the performance of the intelligent service the following steps may be performed:• At 580a, the MNO 510 configures an AI / ML pipeline for a network service, and then it provides reports related to its performance either regularly and / or upon a certain event, e.g., threshold crossing, related to metric.• At 580b, the Network Intelligence Provider 520 receives this report and then it analyses whether providing a modification either in an AI / ML service components and / or configuration option may improve the desired performance and provides this as a suggestion to the MNO including billing information.• At 580c, the MNO 510 informs the Network Service Customer 502 regarding the AI / ML pipeline modification including billing information and if the modification is acknowledged, it is configured by the MNO 510 0AM in the allocated network service.

[0107] At 581, in case the Network Service Customer 502 indicated the preference for receiving AI / ML pipeline maintenance the following steps may be performed:• At 581a, the MNO 510 subscribes to the Network Intelligence Provider 520 to receive updates related to an AI / ML pipeline component.• At 581b, the Network Intelligence Provider 520 receives this subscription and then it provides suggestion for updating the selected AI / ML pipeline components including billing information.• At 581c, the MNO 510 informs the Network Service Customer 502 regarding AI / ML pipeline component updates including and acknowledged positively, it is configured by the MNO 510 0AM in the allocated network service.• At 582, the Network Intelligence Provider 520 regularly or upon certain events updates 582a the billing information towards the MNO 510 related to the AI / ML pipeline service. The MNO 510 may inform the Network Service Customer 502 regarding AI / ML pipeline billing.

[0108] It should be noted that steps 574 to 576 can also be generalized to express AI / ML requirements also including the cases in where the intelligent service consumer is either the MNO 510 0AM or the Network Resource Provider 530 and the producer is the Network Intelligence Provider 520. This generalization can also hold for using all AI / ML service APIs considering steps 578 to 582.

[0109] Figure 6 illustrates an example of a UE 600 in accordance with aspects of the present disclosure. The UE 600 may include a processor 602, a memory 604, a controller 606, and a transceiver 608. The processor 602, the memory 604, the controller 606, or the transceiver 608, or various combinations thereof or various components thereof may be examples of means for performing various aspects of the present disclosure as described herein. These components may be coupled (e.g., operatively, communicatively, functionally, electronically, electrically) via one or more interfaces.

[0110] The processor 602, the memory 604, the controller 606, or the transceiver 608, or various combinations or components thereof may be implemented in hardware (e.g., circuitry). The hardware may include a processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), or other programmable logic device, or any combination thereof configured as or otherwise supporting a means for performing the functions described in the present disclosure.

[0111] The processor 602 may include an intelligent hardware device (e.g., a general- purpose processor, a DSP, a CPU, an ASIC, an FPGA, or any combination thereof). In some implementations, the processor 602 may be configured to operate the memory 604. In some other implementations, the memory 604 may be integrated into the processor 602.The processor 602 may be configured to execute computer-readable instructions stored in the memory 604 to cause the UE 600 to perform various functions of the present disclosure.

[0112] The memory 604 may include volatile or non-volatile memory. The memory 604 may store computer-readable, computer-executable code including instructions when executed by the processor 602 cause the UE 600 to perform various functions described herein. The code may be stored in a non-transitory computer-readable medium such the memory 604 or another type of memory. Computer-readable media includes both non- transitory computer storage media and communication media including any medium that facilitates transfer of a computer program from one place to another. A non-transitory storage medium may be any available medium that may be accessed by a general-purpose or special-purpose computer.

[0113] In some implementations, the processor 602 and the memory 604 coupled with the processor 602 may be configured to cause the UE 600 to perform one or more of the functions described herein (e.g., executing, by the processor 602, instructions stored in the memory 604). For example, the processor 602 may support wireless communication at the UE 600 in accordance with examples as disclosed herein. The UE 600 may be configured to support the arrangements described herein.

[0114] The controller 606 may manage input and output signals for the UE 600. The controller 606 may also manage peripherals not integrated into the UE 600. In some implementations, the controller 606 may utilize an operating system such as iOS®, ANDROID®, WINDOWS®, or other operating systems. In some implementations, the controller 606 may be implemented as part of the processor 602.

[0115] In some implementations, the UE 600 may include at least one transceiver 608. In some other implementations, the UE 600 may have more than one transceiver 608. The transceiver 608 may represent a wireless transceiver. The transceiver 608 may include one or more receiver chains 610, one or more transmitter chains 612, or a combination thereof.

[0116] A receiver chain 610 may be configured to receive signals (e.g., control information, data, packets) over a wireless medium. For example, the receiver chain 610 may include one or more antennas for receive the signal over the air or wireless medium.The receiver chain 610 may include at least one amplifier (e.g., a low- noise amplifier (LNA)) configured to amplify the received signal. The receiver chain 610 may include at least one demodulator configured to demodulate the receive signal and obtain the transmitted data by reversing the modulation technique applied during transmission of the signal. The receiver chain 610 may include at least one decoder for decoding the processing the demodulated signal to receive the transmitted data.

[0117] A transmitter chain 612 may be configured to generate and transmit signals (e.g., control information, data, packets). The transmitter chain 612 may include at least one modulator for modulating data onto a carrier signal, preparing the signal for transmission over a wireless medium. The at least one modulator may be configured to support one or more techniques such as amplitude modulation (AM), frequency modulation (FM), or digital modulation schemes like phase-shift keying (PSK) or quadrature amplitude modulation (QAM). The transmitter chain 612 may also include at least one power amplifier configured to amplify the modulated signal to an appropriate power level suitable for transmission over the wireless medium. The transmitter chain 612 may also include one or more antennas for transmitting the amplified signal into the air or wireless medium.

[0118] Figure 7 illustrates an example of a processor 700 in accordance with aspects of the present disclosure. The processor 700 may be an example of a processor configured to perform various operations in accordance with examples as described herein. The processor 700 may include a controller 702 configured to perform various operations in accordance with examples as described herein. The processor 700 may optionally include at least one memory 704, which may be, for example, an L1 / L2 / L3 cache. Additionally, or alternatively, the processor 700 may optionally include one or more arithmetic-logic units (ALUs) 706. One or more of these components may be in electronic communication or otherwise coupled (e.g., operatively, communicatively, functionally, electronically, electrically) via one or more interfaces (e.g., buses).

[0119] The processor of Figure 7 may be used to provide an intelligence service as described herein. The intelligence service may comprise one or more intelligence service capabilities. In some cases, an intelligence service capability may be referred to as an intelligence service requirement. An intelligence service capability and / or requirementmay include network intelligence monitoring, analytics, decision and / or execution or any combination thereof. The intelligence service capability may require the application of AI / ML. The first network node may thus obtain the benefits of an intelligence service capability that uses AI / ML without needing to perform AI / ML processing itself. This allows for dedicated hardware and / or software for AI / ML to be provisioned at the Network Intelligence Provider, improving the operational efficiency of the intelligence service capability. The first network node may thus obtain the benefits of an intelligence service capability that uses AI / ML without needing to develop and maintain AI / ML logic itself or have the logic on how to form an AI / ML service chain or pipeline.

[0120] The processor 700 may be a processor chipset and include a protocol stack (e.g., a software stack) executed by the processor chipset to perform various operations (e.g., receiving, obtaining, retrieving, transmitting, outputting, forwarding, storing, determining, identifying, accessing, writing, reading) in accordance with examples as described herein. The processor chipset may include one or more cores, one or more caches (e.g., memory local to or included in the processor chipset (e.g., the processor 700) or other memory (e.g., random access memory (RAM), read-only memory (ROM), dynamic RAM (DRAM), synchronous dynamic RAM (SDRAM), static RAM (SRAM), ferroelectric RAM (FeRAM), magnetic RAM (MRAM), resistive RAM (RRAM), flash memory, phase change memory (PCM), and others).

[0121] The controller 702 may be configured to manage and coordinate various operations (e.g., signalling, receiving, obtaining, retrieving, transmitting, outputting, forwarding, storing, determining, identifying, accessing, writing, reading) of the processor 700 to cause the processor 700 to support various operations in accordance with examples as described herein. For example, the controller 702 may operate as a control unit of the processor 700, generating control signals that manage the operation of various components of the processor 700. These control signals include enabling or disabling functional units, selecting data paths, initiating memory access, and coordinating timing of operations.

[0122] The controller 702 may be configured to fetch (e.g., obtain, retrieve, receive) instructions from the memory 704 and determine subsequent instruct! on(s) to be executed to cause the processor 700 to support various operations in accordance with examples asdescribed herein. The controller 702 may be configured to track memory address of instructions associated with the memory 704. The controller 702 may be configured to decode instructions to determine the operation to be performed and the operands involved. For example, the controller 702 may be configured to interpret the instruction and determine control signals to be output to other components of the processor 700 to cause the processor 700 to support various operations in accordance with examples as described herein. Additionally, or alternatively, the controller 702 may be configured to manage flow of data within the processor 700. The controller 702 may be configured to control transfer of data between registers, arithmetic logic units (ALUs), and other functional units of the processor 700.

[0123] The memory 704 may include one or more caches (e.g., memory local to or included in the processor 700 or other memory, such RAM, ROM, DRAM, SDRAM, SRAM, MRAM, flash memory, etc. In some implementations, the memory 704 may reside within or on a processor chipset (e.g., local to the processor 700). In some other implementations, the memory 704 may reside external to the processor chipset (e.g., remote to the processor 700).

[0124] The memory 704 may store computer-readable, computer-executable code including instructions that, when executed by the processor 700, cause the processor 700 to perform various functions described herein. The code may be stored in a non-transitory computer-readable medium such as system memory or another type of memory. The controller 702 and / or the processor 700 may be configured to execute computer-readable instructions stored in the memory 704 to cause the processor 700 to perform various functions. For example, the processor 700 and / or the controller 702 may be coupled with or to the memory 704, the processor 700, the controller 702, and the memory 704 may be configured to perform various functions described herein. In some examples, the processor 700 may include multiple processors and the memory 704 may include multiple memories. One or more of the multiple processors may be coupled with one or more of the multiple memories, which may, individually or collectively, be configured to perform various functions herein.

[0125] The one or more ALUs 706 may be configured to support various operations in accordance with examples as described herein. In some implementations, the one or more ALUs 706 may reside within or on a processor chipset (e.g., the processor 700). In some other implementations, the one or more ALUs 706 may reside external to the processor chipset (e.g., the processor 700). One or more ALUs 706 may perform one or more computations such as addition, subtraction, multiplication, and division on data. For example, one or more ALUs 706 may receive input operands and an operation code, which determines an operation to be executed. One or more ALUs 706 be configured with a variety of logical and arithmetic circuits, including adders, subtractors, shifters, and logic gates, to process and manipulate the data according to the operation. Additionally, or alternatively, the one or more ALUs 706 may support logical operations such as AND, OR, exclusive-OR (XOR), not-OR (NOR), and not- AND (NAND), enabling the one or more ALUs 706 to handle conditional operations, comparisons, and bitwise operations.

[0126] The processor 700 may support wireless communication in accordance with examples as disclosed herein. The processor 700 may be configured to or operable to support a means for receiving, from a second network entity, a network service request including at least one intelligence service requirement related to a network service; establishing, with the second entity, a service level agreement in accordance with the at least one intelligent service requirement related to the network service; translating the at least one intelligence service requirement into a respective at least one intelligence service capability; selecting a service interface of a third network entity to control the at least one intelligent service capability; and transmitting, to the selected service interface, a network intelligence request comprising the at least one intelligence service capability.

[0127] Figure 8 illustrates an example of a NE 800 in accordance with aspects of the present disclosure. The NE 800 may include a processor 802, a memory 804, a controller 806, and a transceiver 808. The processor 802, the memory 804, the controller 806, or the transceiver 808, or various combinations thereof or various components thereof may be examples of means for performing various aspects of the present disclosure as described herein. These components may be coupled (e.g., operatively, communicatively, functionally, electronically, electrically) via one or more interfaces.

[0128] The processor 802, the memory 804, the controller 806, or the transceiver 808, or various combinations or components thereof may be implemented in hardware (e.g., circuitry). The hardware may include a processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), or other programmable logic device, or any combination thereof configured as or otherwise supporting a means for performing the functions described in the present disclosure.

[0129] The processor 802 may include an intelligent hardware device (e.g., a general- purpose processor, a DSP, a CPU, an ASIC, an FPGA, or any combination thereof). In some implementations, the processor 802 may be configured to operate the memory 804. In some other implementations, the memory 804 may be integrated into the processor 802. The processor 802 may be configured to execute computer-readable instructions stored in the memory 804 to cause the NE 800 to perform various functions of the present disclosure.

[0130] The memory 804 may include volatile or non-volatile memory. The memory 804 may store computer-readable, computer-executable code including instructions when executed by the processor 802 cause the NE 800 to perform various functions described herein. The code may be stored in a non-transitory computer-readable medium such the memory 804 or another type of memory. Computer-readable media includes both non- transitory computer storage media and communication media including any medium that facilitates transfer of a computer program from one place to another. A non-transitory storage medium may be any available medium that may be accessed by a general-purpose or special-purpose computer.

[0131] In some implementations, the processor 802 and the memory 804 coupled with the processor 802 may be configured to cause the NE 800 to perform one or more of the functions described herein (e.g., executing, by the processor 802, instructions stored in the memory 804). For example, the processor 802 may support wireless communication at the NE 800 in accordance with examples as disclosed herein. The NE 800 may be configured to support a means for receiving, from a second network entity, a network service request including at least one intelligence service requirement related to a network service; establishing, with the second entity, a service level agreement in accordance with the at least one intelligent service requirement related to the network service; translating the atleast one intelligence service requirement into a respective at least one intelligence service capability; selecting a service interface of a third network entity to control the at least one intelligent service capability; and transmitting, to the selected service interface, a network intelligence request comprising the at least one intelligence service capability.

[0132] The controller 806 may manage input and output signals for the NE 800. The controller 806 may also manage peripherals not integrated into the NE 800. In some implementations, the controller 806 may utilize an operating system such as iOS®, ANDROID®, WINDOWS®, or other operating systems. In some implementations, the controller 806 may be implemented as part of the processor 802.

[0133] In some implementations, the NE 800 may include at least one transceiver 808. In some other implementations, the NE 800 may have more than one transceiver 808. The transceiver 808 may represent a wireless transceiver. The transceiver 808 may include one or more receiver chains 810, one or more transmitter chains 812, or a combination thereof.

[0134] A receiver chain 810 may be configured to receive signals (e.g., control information, data, packets) over a wireless medium. For example, the receiver chain 810 may include one or more antennas for receive the signal over the air or wireless medium. The receiver chain 810 may include at least one amplifier (e.g., a low- noise amplifier (LNA)) configured to amplify the received signal. The receiver chain 810 may include at least one demodulator configured to demodulate the receive signal and obtain the transmitted data by reversing the modulation technique applied during transmission of the signal. The receiver chain 810 may include at least one decoder for decoding the processing the demodulated signal to receive the transmitted data.

[0135] A transmitter chain 812 may be configured to generate and transmit signals (e.g., control information, data, packets). The transmitter chain 812 may include at least one modulator for modulating data onto a carrier signal, preparing the signal for transmission over a wireless medium. The at least one modulator may be configured to support one or more techniques such as amplitude modulation (AM), frequency modulation (FM), or digital modulation schemes like phase-shift keying (PSK) or quadrature amplitude modulation (QAM). The transmitter chain 812 may also include at least one power amplifier configured to amplify the modulated signal to an appropriate power level suitablefor transmission over the wireless medium. The transmitter chain 812 may also include one or more antennas for transmitting the amplified signal into the air or wireless medium.

[0136] Figure 9 illustrates a flowchart of a method 900 in accordance with aspects of the present disclosure. The operations of the method 900 may be implemented by a NE as described herein. In some implementations, the NE may execute a set of instructions to control the function elements of the NE to perform the described functions.

[0137] At 902, the method 900 may include receiving, from a second network entity, a network service request including at least one intelligence service requirement related to a network service. The operations of 902 may be performed in accordance with examples as described herein. In some implementations, aspects of the operations of 902 may be performed by a NE as described with reference to Figure 8.

[0138] At 904, the method 900 may include establishing, with the second entity, a service level agreement in accordance with the at least one intelligent service requirement related to the network service. The operations of 904 may be performed in accordance with examples as described herein. In some implementations, aspects of the operations of 904 may be performed by a NE as described with reference to Figure 8.

[0139] At 906, the method 900 may include translating the at least one intelligence service requirement into a respective at least one intelligence service capability. The operations of 906 may be performed in accordance with examples as described herein. In some implementations, aspects of the operations of 906 may be performed a NE as described with reference to Figure 8.

[0140] At 908, the method 900 may include select a service interface of a third network entity to control the at least one intelligent service capability. The operations of 908 may be performed in accordance with examples as described herein. In some implementations, aspects of the operations of 908 may be performed by a NE as described with reference to Figure 8.

[0141] At 910, the method 900 may include transmitting, to the selected service interface, a network intelligence request comprising the at least one intelligence service capability. The operations of 910 may be performed in accordance with examples asdescribed herein. In some implementations, aspects of the operations of 910 may be performed by a NE as described with reference to Figure 8.

[0142] A first network entity for wireless communication is described. The first network entity may be configured to, capable of, or operable to perform one or more operations as described herein. For example, the first network entity may include at least one memory; and at least one processor coupled with the at least one memory and configured to cause the first network entity to: receive, from a second network entity, a network service request including at least one intelligence service requirement related to a network service; establish, with the second entity, a service level agreement in accordance with the at least one intelligent service requirement related to a network service; translate the at least one intelligence service requirement into a respective at least one intelligence service capability; select a service interface of a third network entity to control the at least one intelligent service capability; and transmit, to the selected service interface, a network intelligence request comprising the at least one intelligence service capability.

[0143] The first network entity may be an 0AM of an MNO. The second network entity may include a network service customer. The third network entity may include a Network intelligence provider. The service interface may be able to reconfigure, modify, or delete the at least one intelligent service capabilities. The service interface may be able to request to reconfigure, request to modify, or request to delete the at least one intelligent service capabilities.

[0144] When different parties operate the network management, mobile network, network resources, and intelligent service capabilities then there is a need to develop a ML Application Programming Interfaces (APIs) to allow control of offered AI / ML services.

[0145] The first network node described herein may obtain and control an intelligence service capability from a Network Intelligence Provider. The first network node may thus obtain the benefits of an intelligence service capability that uses AI / ML without needing to own an AI / ML service and / or perform AI / ML maintenance itself, or have / operate the logic on how to form an AI / ML service chain or pipeline. This allows for dedicated hardware and / or software for AI / ML to be provisioned by the assistance of the Network Intelligence Provider, improving the operational efficiency of the network intelligence service. It ispossible that the first network node will run the AI / ML process itself, but the ownership and responsibility for maintenance and the life-cycle tools related with the AI / ML service chain may be provided by a third party.

[0146] The at least one processor being arranged to establish a service level agreement with the second network entity may include the at least one processor being further configured to cause the first network entity to instantiate an agent responsible for allowing correspondence and control of the intelligent service offered by the third network entity.

[0147] The correspondence may include message exchange. The agent may reside in the third network entity. The correspondence may include the capability of discovering and selecting an interface for controlling the offered intelligent service.

[0148] The agent responsible for allowing correspondence and control of the intelligent service offered by the third network entity may reside at the third network entity and may use an interface that enables the at least one processor to be further configured to cause the first network entity to: communicate intelligent service requirements related to a network service; control an intelligent service chain or pipeline by selecting and modifying the contained intelligent service components; provide performance monitoring information related to an intelligent service chain or pipeline configured; receive updates related to the components of the intelligent service chain or pipeline configured; and / or exchange billing information related to the provisioned intelligent service.

[0149] The at least one processor may be further configured to cause the first network entity to discover at least one service interface related to an intelligent service from the third network entity.

[0150] The first network entity may discover one or more service interfaces related to an intelligent service from the third network entity. The third network entity may offer at least one service interface to the first network entity. The first network entity may select a service interface after discovering the offered service interfaces. The selection may be made from the discovered / offered at least one service interface. If only one service interface is discovered the selection is trivial. Otherwise, the selection is based on the AI / ML operations objectives and / or the intelligent service capability that the first networknode needs to control. The first network entity may send, to the third network entity, a request for an intelligent service provision. The first network entity may receive, from the third network entity, a request for an intelligent service provision.

[0151] The third network entity may include an agent responsible for authorizing and / or authenticating a request for an intelligent service provision. The third network entity may allow the first network entity to discover service interfaces related to an intelligent service. The third network entity may publish the available service interfaces related to an intelligent service to the first network entity.

[0152] The at least one processor may be further configured to cause the first network entity to use a service request interface to communicate with the agent responsible for allowing correspondence and control of the intelligent service offered by the third network entity, wherein the service request interface is used to convey at least one of: an identity of an at least one intelligent task; a domain identifier related to the at least one intelligent task; a lifecycle process indicator related to the applicability of the at least one intelligent task; a network scope indicator related to the applicability of the at least one intelligent task; a model performance indicator related to the at least one intelligent task; a service cost indicator related to the at least one intelligent task; a service maintenance indicator related to the at least one intelligent task; a vendor or model restriction indicator of a model related to the at least one intelligent task; a spatial validity information related to the at least one intelligent task; and / or a temporal validity information related to the at least one intelligent task.

[0153] The at least one processor may be further configured to cause the first network entity to use the service interface of the third network entity to select and control a pipeline or chain of intelligent service components with the at least one of the following pieces of information: a pipeline or service chain identifier related to an intelligent task; data information related to an intelligent task; model information related to an intelligent task; target information and consumer information related to an intelligent task; a spatial validity information related to an intelligent task; and / or a temporal validity information related to an intelligent task. The target information may be an input. The consumer information may be an output.

[0154] The at least one processor may be further configured to cause the first network entity to use the service interface of a third network entity to provide performance monitoring information for a configured pipeline or chain of intelligent service components to the corresponding agent residing in a third network entity, the performance monitoring information comprising at least one of: a performance monitoring correspondence identifier; a model performance accuracy mechanism indication; a model performance accuracy fulfilling target; a model performance speed information; a computing resource indication related to a target speed; a data related information to achieve a target speed; a positioning information related to the components of an intelligent service pipeline or chain; a spatial validity information related to an intelligent task; and / or a temporal validity information related to an intelligent task.

[0155] The at least one processor may be further configured to cause the first network entity to use the service interface to provide maintenance information for a configured pipeline or chain of intelligent service components to a corresponding agent residing in the third network entity, the maintenance information comprising at least one of: a maintenance correspondence identifier; an intelligent service component identifier and / or a vendor identifier and / or a model related format identifier related to a component that is to be replaced or updated; an event identifier and / or a time related indicator associated with an intelligent service component maintenance; and / or a preference for maintenance among a list of intelligent service components.

[0156] The at least one processor may be further configured to cause the first network entity to use the service interface to provide billing information for a configured pipeline or chain of intelligent service components to a corresponding agent residing in the third network entity, the billing information comprising at least one of: a pipeline or service chain identifier related to an intelligent service; a processing cost for assisting lifecycle management, including agent provision; a cost related to the components of a pipeline or service chain related to an intelligent service provision; a cost of a monitoring service of a pipeline or service chain related to an intelligent service provision including modification suggestion events and / or for a duration of time; and / or a maintenance cost including the updates related to the components of an intelligent service.

[0157] A processor for wireless communication is described. The processor may be configured to, capable of, or operable to perform one or more operations as described herein. For example, the processor may include at least one controller coupled with at least one memory and configured to cause the processor to: receive, from a second network entity, a network service request including at least one intelligence service requirement related to a network service; establish, with the second entity, a service level agreement in accordance with the at least one intelligent service requirement related to the network service; translate the at least one intelligence service requirement into a respective at least one intelligence service capability; select a service interface of a third network entity to control the at least one intelligent service capability; and transmit, to the selected service interface, a network intelligence request comprising the at least one intelligence service capability.

[0158] A method performed by a first network entity is described. The method may include: receiving, from a second network entity, a network service request including at least one intelligence service requirement related to a network service; establishing, with the second entity, a service level agreement in accordance with the at least one intelligent service requirement related to the network service; translating the at least one intelligence service requirement into a respective at least one intelligence service capability; select a service interface of a third network entity to control the at least one intelligent service capability; and transmitting, to the selected service interface, a network intelligence request comprising the at least one intelligence service capability.

[0159] The first network entity may be an 0AM of an MNO. The second network entity may include a network service customer. The third network entity may include a Network intelligence provider. The service interface may be able to reconfigure, modify, or delete the at least one intelligent service capabilities. The service interface may be able to request to reconfigure, request to modify, or request to delete the at least one intelligent service capabilities.

[0160] When different parties operate the network management, mobile network, network resources, and intelligent service capabilities then there is a need to develop a ML Application Programming Interfaces (APIs) to allow control of offered AI / ML services.

[0161] The first network node described herein may obtain and control an intelligence service capability from a Network Intelligence Provider. The first network node may thus obtain the benefits of an intelligence service capability that uses AI / ML without needing to own an AI / ML service and / or perform AI / ML maintenance itself, or have / operate the logic on how to form an AI / ML service chain or pipeline. This allows for dedicated hardware and / or software for AI / ML to be provisioned by the assistance of the Network Intelligence Provider, improving the operational efficiency of the network intelligence service. It is possible that the first network node will run the AI / ML process itself, but the ownership and responsibility for maintenance and the life-cycle tools related with the AI / ML service chain may be provided by a third party.

[0162] Establishing a service level agreement with the second network entity may include instantiating an agent responsible for allowing correspondence and control of the intelligent service offered by the third network entity. The correspondence may include message exchange. The agent may reside in the third network entity. The correspondence may include the capability of discovering and selecting an interface for controlling the offered intelligent service.

[0163] The agent responsible for allowing correspondence and control of the intelligent service offered by the third network entity may reside at the third network entity and may use an interface that enables the first network entity to: communicate intelligent service requirements related to a network service; control an intelligent service chain or pipeline by selecting and modifying the contained intelligent service components; provide performance monitoring information related to an intelligent service chain or pipeline configured; receive updates related to the components of the intelligent service chain or pipeline configured; and / or exchange billing information related to the provisioned intelligent service.

[0164] The method may further include discovering at least one service interface related to an intelligent service from the third network entity. The first network entity may discover one or more service interfaces related to an intelligent service from the third network entity. The third network entity may offer at least one service interface to the first network entity. The first network entity may select a service interface after discovering theoffered service interfaces. The selection may be made from the disco ver ed / offered at least one service interface. If only one service interface is discovered the selection is trivial. Otherwise, the selection is based on the AI / ML operations objectives and / or the intelligent service capability that the first network node needs to control. The first network entity may send, to the third network entity, a request for an intelligent service provision. The first network entity may receive, from the third network entity, a request for an intelligent service provision. The third network entity may include an agent responsible for authorizing and / or authenticating a request for an intelligent service provision. The third network entity may allow the first network entity to discover service interfaces related to an intelligent service. The third network entity may publish the available service interfaces related to an intelligent service to the first network entity.

[0165] The method may further include using a service request interface to communicate with the agent responsible for allowing correspondence and control of the intelligent service offered by the third network entity, wherein the service request interface is used to convey at least one of: an identity of an at least one intelligent task; a domain identifier related to the at least one intelligent task; a lifecycle process indicator related to the applicability of the at least one intelligent task; a network scope indicator related to the applicability of the at least one intelligent task; a model performance indicator related to the at least one intelligent task; a service cost indicator related to the at least one intelligent task; a service maintenance indicator related to the at least one intelligent task; a vendor or model restriction indicator of a model related to the at least one intelligent task; a spatial validity information related to the at least one intelligent task; and / or a temporal validity information related to the at least one intelligent task.

[0166] The method may further include using the service interface of the third network entity to select and control a pipeline or chain of intelligent service components with the at least one of the following pieces of information: a pipeline or service chain identifier related to an intelligent task; data information related to an intelligent task; model information related to an intelligent task; target information and consumer information related to an intelligent task; a spatial validity information related to an intelligent task;and / or a temporal validity information related to an intelligent task. The target information may be an input. The consumer information may be an output.

[0167] The method may further include using the service interface of a third network entity to provide performance monitoring information for a configured pipeline or chain of intelligent service components to the corresponding agent residing in a third network entity, the performance monitoring information comprising at least one of: a performance monitoring correspondence identifier; a model performance accuracy mechanism indication; a model performance accuracy fulfilling target; a model performance speed information; a computing resource indication related to a target speed; a data related information to achieve a target speed; a positioning information related to the components of an intelligent service pipeline or chain; a spatial validity information related to an intelligent task; and / or a temporal validity information related to an intelligent task.

[0168] The method may further include using the service interface to provide maintenance information for a configured pipeline or chain of intelligent service components to a corresponding agent residing in the third network entity, the maintenance information comprising at least one of: a maintenance correspondence identifier; an intelligent service component identifier and / or a vendor identifier and / or a model related format identifier related to a component that is to be replaced or updated; an event identifier and / or a time related indicator associated with an intelligent service component maintenance; and / or a preference for maintenance among a list of intelligent service components.

[0169] The method may further include using the service interface to provide billing information for a configured pipeline or chain of intelligent service components to a corresponding agent residing in the third network entity, the billing information comprising at least one of: a pipeline or service chain identifier related to an intelligent service; a processing cost for assisting lifecycle management, including agent provision; a cost related to the components of a pipeline or service chain related to an intelligent service provision; a cost of a monitoring service of a pipeline or service chain related to an intelligent service provision including modification suggestion events and / or for a duration of time; and / or a maintenance cost including the updates related to the components of an intelligent service.

[0170] When network intelligence capabilities are offered by an independent provider that is responsible to enable AI / ML services for i) the 0AM of a mobile network operator, ii) a separate network resource provider or for iii) a network service related to a customer of the mobile network operator then there is a need to be able to control the AI / ML pipeline service and its respective components after establishing a relationship for the duration of the service life cycle but current there is no mechanisms and APIs to enable this objective.

[0171] There is described herein an apparatus and method that tend to facilitate an Al Agent that is responsible for feasibility and for the provision of a series of service APIs towards a network intelligence provider, to offer AI / ML service capabilities for: i) a network service customer when it has established an SLA with a mobile network operator ii) the 0AM purposes of the management plane related to a Mobile Network Operator, iii) the network resource orchestrator related to a Network resource provider. This invention introduces four APIs to provide: (i) AI / ML requirements, (ii) AI / ML pipeline lifecycle management, (iii) AI / ML performance monitoring and maintenance and (iv) billing.

[0172] Known approaches do not consider the scenario where network intelligence capabilities are offered by an independent provider and hence there was no need to develop service APIs to facilitate AI / ML capabilities.

[0173] Network Intelligent Service APIs that enable a network service customer through the management system of an MNO to provide the service requirements of the desired AI / ML service and additionally allow control of the AI / ML pipeline lifecycle management, and may enable AI / ML performance monitoring and maintenance as well as billing.

[0174] Network Service APIs that enable a network service customer to directly interact and provide the service requirements of the desired AI / ML service and additionally allow to control the AI / ML pipeline lifecycle management, enable AI / ML performance monitoring and maintenance as well as billing.

[0175] There is described herein a first network entity [0AM of MNO] for wireless communication, comprising: at least one memory; and at least one processor coupled with the at least one memory and configured to cause the network entity to: establish a servicelevel agreement with a second entity [network service customer] that contains at least one intelligent service requirement related to a network service, translate at least one requirement related with a service level agreement into an intelligent service capability, use a service interface to control at least one intelligent service capability that is offered by a third network entity [Network intelligent provider],

[0176] The establishment of a service level agreement with a second entity [network service customer] may consist of: instantiating an agent responsible for allowing correspondence [i.e., message exchange] and control of the intelligent service offered by a third network entity [Network intelligent provider],

[0177] The interaction with an agent residing at a third network entity may be performed using at least an interface that enables said first network entity to: communicate intelligent service requirements related to a network service, control an intelligent service chain or pipeline by selecting and modifying the contained intelligent service components, provide performance monitoring information related to an intelligent service chain or pipeline configured, receive updates related to the components of the intelligent service chain or pipeline configured, exchange of billing information related to the provisioned intelligent service.

[0178] There is further provide a third network entity where an agent is responsible for authorizing and / or authenticating a request for an intelligent service provision before it: allows a first network entity to discover service interfaces related to an intelligent service or publishes the available service interfaces related to an intelligent service to a first network entity.

[0179] The first network entity may use a service request interface to communicate with the corresponding agent residing in a third network entity, which include at least one of the following pieces of information: an identity of at least one intelligent task, a domain identifier related to an intelligent task, a lifecycle process indicator related to the applicability of an intelligent task, a network scope indicator related to the applicability of an intelligent task, a model performance indicator related to an intelligent task, a service cost indicator related to an intelligent task, a service maintenance indicator related to anintelligent task, a vendor or model restriction indicator of a model related to an intelligent task, a spatial and / or temporal validity information related to an intelligent task.

[0180] The first network entity may use a service interface to select and control a pipeline or chain of intelligent service components with the corresponding agent residing in a third network entity, which includes at least one of the following pieces of information: a pipeline or service chain identifier related to an intelligent task, Data information related to an intelligent task, Model information related to an intelligent task, Target [input] and consumer [output] information related to an intelligent task, a spatial and / or temporal validity information related to an intelligent task.

[0181] The first network entity may use a service interface to provide performance monitoring related with a configured pipeline or chain of intelligent service components with the corresponding agent residing in a third network entity, which include at least one of the following pieces of information: a performance monitoring correspondence identifier, a model performance accuracy mechanism indication, a model performance accuracy fulfilling target, a model performance speed information, a computing resource indication related to a target speed, a data related information to achieve a target speed, a positioning information related to the components of an intelligent service pipeline or chain, a spatial and / or temporal validity information related to an intelligent task.

[0182] The first network entity may use a service interface to provide maintenance related with a configured pipeline or chain of intelligent service components with the corresponding agent residing in the third network entity, which include at least one of the following pieces of information: a maintenance correspondence identifier, an intelligent service component identifier and / a vendor identifier and / or a model related format identifier related to a component that is to be replaced or updated, an evet identifier and / or a time related indicator associated with an intelligent service component maintenance, a preference for maintenance among a list of intelligent service components,

[0183] An agent that resides in the third network entity may use a service interface to provide billing information related to the support of a configured pipeline or chain of intelligent service, which include at least one of the following pieces of information: a pipeline or service chain identifier related to an intelligent service; a processing cost forassisting lifecycle management, including agent provision; a cost related to the components of a pipeline or service chain related to an intelligent service provision; a cost of a monitoring service of a pipeline or service chain related to an intelligent service provision including modification suggestion events and / or for a duration of time; a maintenance cost including the updates related to the components of an intelligent service.

[0184] It should be noted that the method described herein describes a possible implementation, and that the operations and the steps may be rearranged or otherwise modified and that other implementations are possible.

[0185] The description herein is provided to enable a person having ordinary skill in the art to make or use the disclosure. Various modifications to the disclosure will be apparent to a person having ordinary skill in the art, and the generic principles defined herein may be applied to other variations without departing from the scope of the disclosure. Thus, the disclosure is not limited to the examples and designs described herein but is to be accorded the broadest scope consistent with the principles and novel features disclosed herein.

[0186] The following abbreviations are relevant in the field addressed by this document: AD AES, Application Data Analytics Enablement Service; AF, Application Function; AI / ML, Artificial Intelligence / Machine Learning ; AnLF, Analytics Logical Function; API, Application Programming Interface; BSS, Business Support Systems ; CAPIF, Common API Framework; DCCF, Data Collection Coordination Functionality; GSMA, Global System for Mobile Communications; GST, Generic Slice Template ; MDA, Management Data Analytics; MF, Management Function; MLFO, ML Function Orchestrator; MNO, Mobile Network Operator; MnS, Management Service; MTLF, Model Training Logical Function; NF, Network Function; NFV, Network Function Virtualization ; NI, Network Intelligence ; NIP, Network Intelligence Plane ; NRF, Network Repository Function ; NS, Network Service; NWDAF, Network Data Analytics Function; 0AM, Operations, Administration and Maintenance; OSS, Operations Support Subsystem;PLMN, Public Land Mobile Network; RAN, Radio Access Network; RL, Reinforcement Learning; SLA, Service Level Agreement ; UDM, User Data Manager ; UDR, User Data Repository; and VNF, Virtualized Network function.

Claims

CLAIMSWhat is claimed is:

1. A first network entity for wireless communication, comprising: at least one memory; and at least one processor coupled with the at least one memory and configured to cause the first network entity to: receive, from a second network entity, a network service request including at least one intelligence service requirement related to a network service; establish, with the second entity, a service level agreement in accordance with the at least one intelligent service requirement related to a network service; translate the at least one intelligence service requirement into a respective at least one intelligence service capability; select a service interface of a third network entity to control the at least one intelligent service capability; and transmit, to the selected service interface, a network intelligence request comprising the at least one intelligence service capability.

2. The first network entity of claim 1, wherein the at least one processor being arranged to establish a service level agreement with the second network entity comprises the at least one processor being further configured to cause the first network entity to instantiate an agent responsible for allowing correspondence and control of the intelligent service offered by the third network entity.

3. The first network entity of claim 2, wherein the agent responsible for allowing correspondence and control of the intelligent service offered by the third network entity resides at the third network entity and uses an interface that enables the at least one processor to be further configured to cause the first network entity to: communicate intelligent service requirements related to a network service; control an intelligent service chain or pipeline by selecting and modifying the contained intelligent service components;provide performance monitoring information related to an intelligent service chain or pipeline configured; receive updates related to the components of the intelligent service chain or pipeline configured; and / or exchange billing information related to the provisioned intelligent service.

4. The first network entity of any of claims 1 to 3, wherein the at least one processor is further configured to cause the first network entity to discover at least one service interface related to an intelligent service from the third network entity.

5. The first network entity of claims 2 or 4, wherein the at least one processor is further configured to cause the first network entity to use a service request interface to communicate with the agent responsible for allowing correspondence and control of the intelligent service offered by the third network entity, wherein the service request interface is used to convey at least one of: an identity of an at least one intelligent task; a domain identifier related to the at least one intelligent task; a lifecycle process indicator related to the applicability of the at least one intelligent task; a network scope indicator related to the applicability of the at least one intelligent task; a model performance indicator related to the at least one intelligent task; a service cost indicator related to the at least one intelligent task; a service maintenance indicator related to the at least one intelligent task; a vendor or model restriction indicator of a model related to the at least one intelligent task; a spatial validity information related to the at least one intelligent task; and / or a temporal validity information related to the at least one intelligent task.

6. The first network entity of any of claims 1 to 5, wherein the at least one processor is further configured to cause the first network entity to use the service interface of the thirdnetwork entity to select and control a pipeline or chain of intelligent service components with the at least one of the following pieces of information: a pipeline or service chain identifier related to an intelligent task; data information related to an intelligent task; model information related to an intelligent task; target information and consumer information related to an intelligent task; a spatial validity information related to an intelligent task; and / or a temporal validity information related to an intelligent task.

7. The first network entity of any of claims 2 to 6, wherein the at least one processor is further configured to cause the first network entity to use the service interface of a third network entity to provide performance monitoring information for a configured pipeline or chain of intelligent service components to the corresponding agent residing in a third network entity, the performance monitoring information comprising at least one of: a performance monitoring correspondence identifier; a model performance accuracy mechanism indication; a model performance accuracy fulfilling target; a model performance speed information; a computing resource indication related to a target speed; a data related information to achieve a target speed; a positioning information related to the components of an intelligent service pipeline or chain; a spatial validity information related to an intelligent task; and / or a temporal validity information related to an intelligent task.

8. The first network entity of any of claims 1 to 7, wherein the at least one processor is further configured to cause the first network entity to use the service interface to provide maintenance information for a configured pipeline or chain of intelligent service components to a corresponding agent residing in the third network entity, the maintenance information comprising at least one of: a maintenance correspondence identifier;an intelligent service component identifier and / or a vendor identifier and / or a model related format identifier related to a component that is to be replaced or updated; an event identifier and / or a time related indicator associated with an intelligent service component maintenance; and / or a preference for maintenance among a list of intelligent service components.

9. The first network entity of any of claims 1 to 8, wherein the at least one processor is further configured to cause the first network entity to use the service interface to provide billing information for a configured pipeline or chain of intelligent service components to a corresponding agent residing in the third network entity, the billing information comprising at least one of: a pipeline or service chain identifier related to an intelligent service; a processing cost for assisting lifecycle management, including agent provision; a cost related to the components of a pipeline or service chain related to an intelligent service provision; a cost of a monitoring service of a pipeline or service chain related to an intelligent service provision including modification suggestion events and / or for a duration of time; and / or a maintenance cost including the updates related to the components of an intelligent service.

10. A processor for wireless communication, comprising: at least one controller coupled with at least one memory and configured to cause the processor to: receive, from a second network entity, a network service request including at least one intelligence service requirement related to a network service; establish, with the second entity, a service level agreement in accordance with the at least one intelligent service requirement related to the network service; translate the at least one intelligence service requirement into a respective at least one intelligence service capability;select a service interface of a third network entity to control the at least one intelligent service capability; and transmit, to the selected service interface, a network intelligence request comprising the at least one intelligence service capability.

11. A method performed or performable by a first network entity for wireless communication, the method comprising: receiving, from a second network entity, a network service request including at least one intelligence service requirement related to a network service; establishing, with the second entity, a service level agreement in accordance with the at least one intelligent service requirement related to the network service; translating the at least one intelligence service requirement into a respective at least one intelligence service capability; selecting a service interface of a third network entity to control the at least one intelligent service capability; and transmitting, to the selected service interface, a network intelligence request comprising the at least one intelligence service capability.

12. The method of claim 11, wherein establishing a service level agreement with the second network entity comprises instantiating an agent responsible for allowing correspondence and control of the intelligent service offered by the third network entity.

13. The method of claim 12, wherein the agent responsible for allowing correspondence and control of the intelligent service offered by the third network entity resides at the third network entity and uses an interface that enables the first network entity to: communicate intelligent service requirements related to a network service; control an intelligent service chain or pipeline by selecting and modifying the contained intelligent service components; provide performance monitoring information related to an intelligent service chain or pipeline configured;receive updates related to the components of the intelligent service chain or pipeline configured; and / or exchange billing information related to the provisioned intelligent service.

14. The method of any of claims 11 to 13, further comprising discovering at least one service interface related to an intelligent service from the third network entity.

15. The method of claims 12 or 14, further comprising using a service request interface to communicate with the agent responsible for allowing correspondence and control of the intelligent service offered by the third network entity, wherein the service request interface is used to convey at least one of: an identity of an at least one intelligent task; a domain identifier related to the at least one intelligent task; a lifecycle process indicator related to the applicability of the at least one intelligent task; a network scope indicator related to the applicability of the at least one intelligent task; a model performance indicator related to the at least one intelligent task; a service cost indicator related to the at least one intelligent task; a service maintenance indicator related to the at least one intelligent task; a vendor or model restriction indicator of a model related to the at least one intelligent task; a spatial validity information related to the at least one intelligent task; and / or a temporal validity information related to the at least one intelligent task.

16. The method of any of claims 11 to 15, further comprising using the service interface of the third network entity to select and control a pipeline or chain of intelligent service components with the at least one of the following pieces of information: a pipeline or service chain identifier related to an intelligent task; data information related to an intelligent task; model information related to an intelligent task;target information and consumer information related to an intelligent task; a spatial validity information related to an intelligent task; and / or a temporal validity information related to an intelligent task.

17. The method of any of claims 12 to 16, further comprising using the service interface of a third network entity to provide performance monitoring information for a configured pipeline or chain of intelligent service components to the corresponding agent residing in a third network entity, the performance monitoring information comprising at least one of: a performance monitoring correspondence identifier; a model performance accuracy mechanism indication; a model performance accuracy fulfilling target; a model performance speed information; a computing resource indication related to a target speed; a data related information to achieve a target speed; a positioning information related to the components of an intelligent service pipeline or chain; a spatial validity information related to an intelligent task; and / or a temporal validity information related to an intelligent task.

18. The method of any of claims 11 to 17, further comprising using the service interface to provide maintenance information for a configured pipeline or chain of intelligent service components to a corresponding agent residing in the third network entity, the maintenance information comprising at least one of: a maintenance correspondence identifier; an intelligent service component identifier and / or a vendor identifier and / or a model related format identifier related to a component that is to be replaced or updated; an event identifier and / or a time related indicator associated with an intelligent service component maintenance; and / or a preference for maintenance among a list of intelligent service components.

19. The method of any of claims 11 to 18, further comprising using the service interface to provide billing information for a configured pipeline or chain of intelligent service components to a corresponding agent residing in the third network entity, the billing information comprising at least one of: a pipeline or service chain identifier related to an intelligent service; a processing cost for assisting lifecycle management, including agent provision; a cost related to the components of a pipeline or service chain related to an intelligent service provision; a cost of a monitoring service of a pipeline or service chain related to an intelligent service provision including modification suggestion events and / or for a duration of time; and / or a maintenance cost including the updates related to the components of an intelligent service.

Images