Method and apparatus for service lifecycle management
The AIML service enablement server entity addresses QoS and optimization challenges in AI/ML service management by standardizing lifecycle management and network assistance, enhancing performance across varying network conditions.
Patent Information
- Application Number
- PCT/CN2025/077130
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- Priority Date
- 2024-02-18
- Filing Date
- 2025-02-13
- Publication Date
- 2025-08-21
AI Technical Summary
Current communication networks lack standardized methods for managing the lifecycle of AI/ML services, leading to issues such as inconsistent quality of service (QoS), non-interoperable lifecycle management, and inadequate network assistance for optimization, which affects performance due to varying network conditions and device capabilities.
Implementing an AIML service enablement server entity that receives and sends lifecycle assistance requests and updates, including VAL server identity, service client IDs, operation modes, and optimization assistance, to manage AI/ML service operations across networks.
Ensures consistent QoS and optimized performance of AI/ML services by enabling network assistance for lifecycle management and optimization, addressing issues of interoperability and network conditions.
Smart Images

Figure CN2025077130_21082025_PF_FP_ABST
Abstract
Description
METHOD AND APPARATUS FOR SERVICE LIFECYCLE MANAGEMENTTECHNICAL FIELD
[0001] The non-limiting and exemplary embodiments of the present disclosure generally relate to the technical field of communications, and specifically to methods and apparatuses for service lifecycle management.BACKGROUND
[0002] This section introduces aspects that may facilitate a better understanding of the disclosure. Accordingly, the statements of this section are to be read in this light and are not to be understood as admissions about what is in the prior art or what is not in the prior art.
[0003] In communication networks such as fifth generation system (5GS) as defined by 3rd Generation Partnership Project (3GPP) , service lifecycle management may be supported. For example, the lifecycle of an artificial intelligence / machine learning (AI / ML or AIML) model may include data collection, data processing, model training, model verification, model, instantiation and deployment, model monitoring and termination of AI / ML model components.
[0004] Since 3GPP Release 16, Service Enablement Architecture Layer for Verticals (SEAL) has been introduced to support vertical applications (e. g. vehicle-to-everything (V2X) applications, AI / ML service) . 3GPP Technical Specification (TS) 23.434 V19.0.0, the disclosure of which is incorporated by reference herein in its entirety, specifies generic functional model for SEAL services.SUMMARY
[0005] This summary is provided to introduce a selection of concepts in a simplified form that are further described below in the detailed description. This summary is not intended to identify key features or essential features of the claimed subject matter, nor is it intended to be used to limit the scope of the claimed subject matter.
[0006] For some services such as AI / ML service, the network and device may play an important role. The network conditions like poor conditions and device capabilities like support of Central Processing Unit (CPU) , Graphics Processing Unit (GPU) or accelerator can affect the performance of the service (such as AI / ML) process. For example, there are different types of AI / ML like federated learning, split learning, transfer learning. In these different learning types, the devices can perform different methods like model transfer, or split model or model offload for inference / training. The AI / ML process has a lifecycle from start to finish. For example, the model training starts and when it is trained or the desired accuracy is achieved, the training ends. In between the model training can be paused, for example, the device doing the training is out of power. The devices involve in training require incentives to associate in further rounds of different training of various AI / ML services.
[0007] The service (such as AI / ML) lifecycle may be handled in the application layer (such as application server) . There is no standard way to manage the lifecycle such as start of the training or pause the training. This may lead to issues such as each service managing lifecycle in their manners and the network cannot ensure the quality of service (QoS) for the service (such as AI / ML) because the network is not aware of the service lifecycle.
[0008] The incentive delivery is not standardized which may lead to problems such as each service (such as AI / ML) has its own Application Programming Interface (API) to configure the network for network based incentive.
[0009] The service (such as AI / ML) cannot request network to assist in the optimization like achieving fast convergence or prioritize energy-efficient mode of training.
[0010] Currently, there are no methods for the application servers (such as Vertical Application Layer (VAL) servers, AIML servers) to request a network for the lifecycle management of the service (such as AI / ML) . The application servers manage the lifecycle of its service (such as AI / ML) operation in a non-interoperable method using an application layer service (such as AI / ML) library. Any service (such as AI / ML) operation involves an service (such as AI / ML) server and service (such as AI / ML) clients, and the service (such as AI / ML) server and service (such as AI / ML) clients are connected over a network (such as 5GS) for communication of various tasks such as exchanging model updates, downloading new model transfer, splitting model etc. Such communication is subject to the network conditions. For example, poor network conditions will negatively impact the performance of the AIML service process.
[0011] This creates the need for the application servers to take assistance from the network to ensure the required QoS support for the service (such as AI / ML) operations. Since the network is not aware of any ongoing service (such as AI / ML) operations such as whether the service (such as AI / ML) is started, or stopped, ongoing, it is not possible to ensure the desired QoS for the service (such as AI / ML) .
[0012] The service (such as AI / ML) can be performed on various clients such as servers, robots, user equipments (UEs) , Internet of Things (IoT) devices, etc. as per different use cases. Each use case is subject to its requirements. For example, the service (such as AI / ML) in the IoT domain is subject to the Energy-Efficient (EE) , i. e. IoT devices want to save power while training. For time-critical use cases, it is subject to faster convergence to make sure an updated global model is available for the clients to use. The service (such as AI / ML) server and service (such as AI / ML) clients communicate over the network and the network is dynamic, this creates the need for the enabler layer to assist the service (such as AI / ML) server in achieving its optimization such as EE or fast convergence. However there is no methods to enable service servers (such as AIML servers) to request an enabler layer for its optimization assistance.
[0013] To overcome or mitigate at least one of above mentioned issues or other issues, the embodiments of the present disclosure propose a solution for service lifecycle management.
[0014] In a first aspect of the disclosure, there is provided a method performed by an artificial intelligence / machine learning (AIML) service enablement server entity. The method comprises receiving, from an application server entity, an AIML service lifecycle assistance request or an AIML service lifecycle assistance update request. The method further comprises sending, to the application server entity, an AIML service lifecycle assistance response or an AIML service lifecycle assistance update response. The AIML service lifecycle assistance request and / or the AIML service lifecycle assistance update request comprises at least one of a vertical application layer (VAL) server identity (ID) , a VAL service ID, a service client ID, a service client group ID, a service operation mode, a service model container, an address to fetch a service model, an address to send service model updates, a service optimization assistance mode, or service incentive information.
[0015] In a second aspect of the disclosure, there is provided a method performed by an application server entity. The method comprises sending, to an AIML service enablement server entity, an AIML service lifecycle assistance request or an AIML service lifecycle assistance update request. The method further comprises receiving, from the AIML service enablement server entity, an AIML service lifecycle assistance response or an AIML service lifecycle assistance update response. The AIML service lifecycle assistance request and / or the AIML service lifecycle assistance update request comprises at least one of a VAL server ID, a VAL service identifier, a service client ID, a service client group ID, a service operation mode, a service model container, an address to fetch a service model, an address to send service model updates, a service optimization assistance mode, or service incentive information.
[0016] In a third aspect of the disclosure, there is provided a method performed by an AIML service enablement client entity. The method comprises receiving, from an AIML service enablement server entity, an AIML enablement client service operation request to manage an AIML service operation lifecycle. The method further comprises sending, to the AIML service enablement server entity, an AIML enablement client service operation response. The AIML enablement client service operation request comprises at least one of a service client ID, a service operation mode, a service model, service transport protocol information, an address to send service model updates, or a service application-oriented incentive.
[0017] In a fourth aspect of the disclosure, there is provided an AIML service enablement server entity. The AIML service enablement server entity comprises a processor and a memory coupled to the processor. Said memory contains instructions executable by said processor. Said AIML service enablement server entity is operative to receive, from an application server entity, an AIML service lifecycle assistance request or an AIML service lifecycle assistance update request. Said AIML service enablement server entity is operative to send, to the application server entity, an AIML service lifecycle assistance response or an AIML service lifecycle assistance update response. The AIML service lifecycle assistance request and / or the AIML service lifecycle assistance update request comprises at least one of a vertical application layer (VAL) server identity (ID) , a VAL service ID, a service client ID, a service client group ID, a service operation mode, a service model container, an address to fetch a service model, an address to send service model updates, a service optimization assistance mode, or service incentive information.
[0018] In a fifth aspect of the disclosure, there is provided an application server entity. The application server entity comprises a processor and a memory coupled to the processor. Said memory contains instructions executable by said processor. Said application server entity is operative to send, to an AIML service enablement server entity, an AIML service lifecycle assistance request or an AIML service lifecycle assistance update request. Said application server entity is operative to receive, from the AIML service enablement server entity, an AIML service lifecycle assistance response or an AIML service lifecycle assistance update response. The AIML service lifecycle assistance request and / or the AIML service lifecycle assistance update request comprises at least one of a VAL server ID, a VAL service identifier, a service client ID, a service client group ID, a service operation mode, a service model container, an address to fetch a service model, an address to send service model updates, a service optimization assistance mode, or service incentive information.
[0019] In a sixth aspect of the disclosure, there is provided an AIML service enablement client entity. The AIML service enablement client entity comprises a processor and a memory coupled to the processor. Said memory contains instructions executable by said processor. Said AIML service enablement client entity is operative to receive, from an AIML service enablement server entity, an AIML enablement client service operation request to manage an AIML service operation lifecycle. Said AIML service enablement client entity is operative to send, to the AIML service enablement server entity, an AIML enablement client service operation response. The AIML enablement client service operation request comprises at least one of a service client ID, a service operation mode, a service model, service transport protocol information, an address to send service model updates, or a service application-oriented incentive.
[0020] In a seventh aspect of the disclosure, there is provided a computer program product comprising instructions which when executed by at least one processor, cause the at least one processor to perform the methods according to any one of the first to third aspects.
[0021] In an eighth aspect of the disclosure, there is provided a computer-readable storage medium storing instructions which when executed by at least one processor, cause the at least one processor to perform the methods according to any one of the first to third aspects.
[0022] Embodiments herein may provide many advantages, of which a non-exhaustive list of examples follows. In some embodiments herein, the application server entity such as VAL server can offload the lifecycle of service (such as AI / ML service) to the service (such as AI / ML) enabler layer. In some embodiments herein, the application server entity such as VAL server can use network APIs to assist its service (such as AI / ML) performance optimization. In some embodiments herein, the application server entity such as VAL server can deliver the application oriented incentive and configure the network for network-oriented incentive delivery. In some embodiments herein, the network based on the request can configure the network (such as 5GS) to assist the optimization of the service (such as AI / ML) . The embodiments herein are not limited to the features and advantages mentioned above. A person skilled in the art will recognize additional features and advantages upon reading the following detailed description.BRIEF DESCRIPTION OF THE DRAWINGS
[0023] The above and other aspects, features, and benefits of various embodiments of the present disclosure will become more fully apparent, by way of example, from the following detailed description with reference to the accompanying drawings, in which like reference numerals or letters are used to designate like or equivalent elements. The drawings are illustrated for facilitating better understanding of the embodiments of the disclosure and not necessarily drawn to scale, in which:
[0024] FIG. 1 schematically shows generic on-network functional model of SEAL;
[0025] FIG. 2a schematically shows a high level architecture in a 5G network according to an embodiment of the present disclosure;
[0026] FIG. 2b schematically shows system architecture in a 4G network according to an embodiment of the present disclosure;
[0027] FIG. 3a, 3b, 4, 5 and 6 show flowcharts of methods according to embodiments of the present disclosure;
[0028] FIG. 7 is a block diagram showing an apparatus suitable for practicing some embodiments of the disclosure; and
[0029] FIG. 8 shows a flowchart of AIML service lifecycle assistance procedure.DETAILED DESCRIPTION
[0030] The embodiments of the present disclosure are described in detail with reference to the accompanying drawings. It should be understood that these embodiments are discussed only for the purpose of enabling those skilled persons in the art to better understand and thus implement the present disclosure, rather than suggesting any limitations on the scope of the present disclosure. Reference throughout this specification to features, advantages, or similar language does not imply that all of the features and advantages that may be realized with the present disclosure should be or are in any single embodiment of the disclosure. Rather, language referring to the features and advantages is understood to mean that a specific feature, advantage, or characteristic described in connection with an embodiment is included in at least one embodiment of the present disclosure. Furthermore, the described features, advantages, and characteristics of the disclosure may be combined in any suitable manner in one or more embodiments. One skilled in the relevant art will recognize that the disclosure may be practiced without one or more of the specific features or advantages of a particular embodiment. In other instances, additional features and advantages may be recognized in certain embodiments that may not be present in all embodiments of the disclosure.
[0031] As used herein, the term “network” refers to a network following any suitable communication standards such as new radio (NR) , long term evolution (LTE) , LTE-Advanced, wideband code division multiple access (WCDMA) , high-speed packet access (HSPA) , Code Division Multiple Access (CDMA) , Time Division Multiple Address (TDMA) , Frequency Division Multiple Access (FDMA) , Orthogonal Frequency-Division Multiple Access (OFDMA) , Single carrier frequency division multiple access (SC-FDMA) and other wireless networks. A CDMA network may implement a radio technology such as Universal Terrestrial Radio Access (UTRA) , etc. UTRA includes WCDMA and other variants of CDMA. A TDMA network may implement a radio technology such as Global System for Mobile Communications (GSM) . An OFDMA network may implement a radio technology such as Evolved UTRA (E-UTRA) , Ultra Mobile Broadband (UMB) , IEEE 802.11 (Wi-Fi) , IEEE 802.16 (WiMAX) , IEEE 802.20, Flash-OFDMA, Ad-hoc network, wireless sensor network, etc. In the following description, the terms “network” and “system” can be used interchangeably. Furthermore, the communications between two devices in the network may be performed according to any suitable communication protocols, including, but not limited to, the communication protocols as defined by a standard organization such as 3GPP. For example, the communication protocols may comprise the first generation (1G) , 2G, 3G, 4G, 4.5G, 5G, 6G communication protocols, and / or any other protocols either currently known or to be developed in the future.
[0032] The term “network device” or “network node” or “network function” refers to any suitable function which can be implemented in a network entity (physical or virtual) of a communication network. For example, the network function can be implemented either as a network element on a dedicated hardware, as a software instance running on a dedicated hardware, or as a virtualized function instantiated on an appropriate platform, e. g. on a cloud infrastructure. For example, the 5G system (5GS) may comprise a plurality of NFs such as Access and Mobility Management Function (AMF) , Session Management Function (SMF) , Authentication Service Function (AUSF) , Unified Data Management (UDM) , Policy Control Function (PCF) , Application Function (AF) , Network Exposure Function (NEF) , User plane Function (UPF) and Network Repository Function (NRF) , radio access network (RAN) , service communication proxy (SCP) , network data analytics function (NWDAF) , network slice Selection Function (NSSF) , network slice-Specific Authentication and Authorization Function (NSSAAF) , etc. In other embodiments, the network function may comprise different types of NFs for example depending on a specific network. For example, the 4G system (such as Long Term Evolution (LTE) ) may include Mobile Management Entity (MME) , home subscriber server (HSS) , PCRF (Policy and Charging Rules Function) , PGW (Packet Data Network Gateway) , PGW control plane (PGW-C) , Serving gateway (SGW) , SGW control plane (SGW-C) , E-UTRAN Node B (eNB) , etc. In other embodiments, the network function may comprise different types of NFs for example depending on a specific network.
[0033] Virtualizing means creating virtual versions of apparatuses or devices which may include virtualizing hardware platforms, storage devices and networking resources. As used herein, virtualization can be applied to a provider edge node and relates to an implementation in which at least a portion of the functionality is implemented as one or more virtual components (e.g., via one or more applications, components, functions, virtual machines or containers executing on one or more physical processing nodes in one or more networks) .
[0034] In some embodiments, some or all of the functions described herein may be implemented as virtual components executed by one or more virtual machines implemented in one or more virtual environments hosted by one or more of hardware nodes. Further, in embodiments in which the virtual node is not a radio access node or does not require radio connectivity (e.g., a core network node) , then the provider edge node may be entirely virtualized.
[0035] The functions may be implemented by one or more applications (which may alternatively be called software instances, virtual appliances, network functions, virtual nodes, virtual network functions, etc. ) operative to implement some of the features, functions, and / or benefits of some of the embodiments disclosed herein. Applications are run in virtualization environment which provides hardware comprising processing circuitry and memory. Memory contains instructions executable by processing circuitry whereby application is operative to provide one or more of the features, benefits, and / or functions disclosed herein.
[0036] Virtualization environment, comprises general-purpose or special-purpose network hardware devices comprising a set of one or more processors or processing circuitry, which may be commercial off-the-shelf (COTS) processors, dedicated Application Specific Integrated Circuits (ASICs) , or any other type of processing circuitry including digital or analog hardware components or special purpose processors. Each hardware device may comprise memory which may be non-persistent memory for temporarily storing instructions or software executed by processing circuitry. Each hardware device may comprise one or more network interface controllers (NICs) , also known as network interface cards, which include physical network interface. Each hardware device may also include non-transitory, persistent, machine-readable storage media -having stored therein software and / or instructions executable by processing circuitry. Software may include any type of software including software for instantiating one or more virtualization layers (also referred to as hypervisors) , software to execute virtual machines as well as software allowing it to execute functions, features and / or benefits described in relation with some embodiments described herein.
[0037] Virtual machines, comprise virtual processing, virtual memory, virtual networking or interface and virtual storage, and may be run by a corresponding virtualization layer or hypervisor. Different embodiments of the instance of virtual appliance may be implemented on one or more of virtual machines, and the implementations may be made in different ways.
[0038] During operation, processing circuitry executes software to instantiate the hypervisor or virtualization layer, which may sometimes be referred to as a virtual machine monitor (VMM) . Virtualization layer may present a virtual operating platform that appears like networking hardware to virtual machine.
[0039] The term “terminal device” refers to any end device that can access a communication network and receive services therefrom. By way of example and not limitation, the terminal device refers to a mobile terminal, user equipment (UE) , or other suitable devices. The UE may be, for example, a Subscriber Station (SS) , a Portable Subscriber Station, a Mobile Station (MS) , or an Access Terminal (AT) . The terminal device may include, but not limited to, a portable computer, an image capture terminal device such as a digital camera, a gaming terminal device, a music storage and a playback appliance, a mobile phone, a cellular phone, a smart phone, a voice over IP (VoIP) phone, a wireless local loop phone, a tablet, a wearable device, a personal digital assistant (PDA) , a portable computer, a desktop computer, a wearable terminal device, a vehicle-mounted wireless terminal device, a wireless endpoint, a mobile station, a laptop-embedded equipment (LEE) , a laptop-mounted equipment (LME) , a USB dongle, a smart device, a wireless customer-premises equipment (CPE) and the like. In the following description, the terms “terminal device” , “terminal” , “user equipment” and “UE” may be used interchangeably. As one example, a terminal device may represent a UE configured for communication in accordance with one or more communication standards promulgated by the 3GPP (3rd Generation Partnership Project) , such as 3GPP LTE standard or NR standard. As used herein, a “user equipment” or “UE” may not necessarily have a “user” in the sense of a human user who owns and / or operates the relevant device. In some embodiments, a terminal device may be configured to transmit and / or receive information without direct human interaction. For instance, a terminal device may be designed to transmit information to a network on a predetermined schedule, when triggered by an internal or external event, or in response to requests from the communication network. Instead, a UE may represent a device that is intended for sale to, or operation by, a human user but that may not initially be associated with a specific human user.
[0040] As yet another example, in an Internet of Things (IoT) scenario, a terminal device may represent a machine or other device that performs monitoring and / or measurements, and transmits the results of such monitoring and / or measurements to another terminal device and / or network equipment. The terminal device may in this case be a machine-to-machine (M2M) device, which may in a 3GPP context be referred to as a machine-type communication (MTC) device. As one particular example, the terminal device may be a UE implementing the 3GPP narrow band internet of things (NB-IoT) standard. Particular examples of such machines or devices are sensors, metering devices such as power meters, industrial machinery, or home or personal appliances, for example refrigerators, televisions, personal wearables such as watches etc. In other scenarios, a terminal device may represent a vehicle or other equipment that is capable of monitoring and / or reporting on its operational status or other functions associated with its operation.
[0041] References in the specification to “one embodiment, ” “an embodiment, ” “an example embodiment, ” and the like indicate that the embodiment described may include a particular feature, structure, or characteristic, but it is not necessary that every embodiment includes the particular feature, structure, or characteristic. Moreover, such phrases are not necessarily referring to the same embodiment. Further, when a particular feature, structure, or characteristic is described in connection with an embodiment, it is submitted that it is within the knowledge of one skilled in the art to affect such feature, structure, or characteristic in connection with other embodiments whether or not explicitly described.
[0042] It shall be understood that although the terms “first” and “second” etc. may be used herein to describe various elements, these elements should not be limited by these terms. These terms are only used to distinguish one element from another. For example, a first element could be termed a second element, and similarly, a second element could be termed a first element, without departing from the scope of example embodiments. As used herein, the term “and / or” includes any and all combinations of one or more of the associated listed terms.
[0043] As used herein unless expressly stated to the contrary, the phrase “at least one of A and B” or “at least one of A or B” should be understood to mean any of the following “only A, only B, or both A and B. ” The phrase “A and / or B” should be understood to mean any of the following “only A, only B, or both A and B” .
[0044] As used herein unless expressly stated to the contrary, the phrase “a plurality of” followed by a conjunctive list of enumerated items (e.g., “A and B” , “A, B, and C” ) is intended to mean “multiple items, with each item selected from the list consisting of” the enumerated items. For example, “a plurality of A and B” is intended to mean any of the following: more than one A; more than one B; or at least one A and at least one B.
[0045] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of example embodiments. As used herein, the singular forms “a” , “an” and “the” are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms “comprises” , “comprising” , “has” , “having” , “includes” and / or “including” , when used herein, specify the presence of stated features, elements, and / or components etc., but do not preclude the presence or addition of one or more other features, elements, components and / or combinations thereof.
[0046] It is noted that these terms as used in this document are used only for ease of description and differentiation among nodes, devices or networks etc. With the development of the technology, other terms with the similar / same meanings may also be used.
[0047] In the following description and claims, unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skills in the art to which this disclosure belongs.
[0048] Key issue #1 of 3GPP TR 23.700-82 V0.2.0 is below.
[0049] 5.1 Key issue #1: Support of Architecture Enhancement and Functions for Application Layer AI / ML Services
[0050] SA2 Rel-18 AIMLsys (in 3GPP TS 23.501 and TS 23.502) studied 5G System support for AI / ML-based services in application layer with the assumptions, for example:
[0051] - Application AI / ML operation logic is controlled by an Application Function (AF) .
[0052] - AF request to the 5G System in the context of 5GS assistance to Application AI / ML operation.
[0053] - For application layer Federated Learning, there may one application server (e.g., an AF) controlling the application layer DML / FL training process among multiple application clients (e.g., UEs) .
[0054] SA1 Rel-18 and Rel-19 identified requirements for the support of AI / ML model distribution, transfer, training for various applications, e.g., video / speech recognition, robot control, automotive, in 3GPP TS. 22.874, TS 22.876, and TS 22.261. Such use cases and requirements from SA1 have application layer impacts, e.g., require the support of corresponding architecture and functions to provide assistance in application layer AI / ML operations on model distribution, transfer and training.
[0055] Therefore, to support the AI / ML services in application layer, the following aspects need to be studied:
[0056] - Whether and how to enhance the architecture and related functions to support application layer AI / ML services.
[0057] - Whether and how the above architecture enhancement and related functions supporting the management / execution of AI / ML lifecycle operations.
[0058] Editor's note: How the architecture enhancement and related functions supporting the FL related operations and services is FFS.
[0059] - Whether and how the architecture enhancement and related functions leveraging the existing 5GC capabilities and assistance for the application layer AI / ML services.
[0060] The embodiments of the present disclosure propose a solution for the AIML lifecycle key issue #1 of 3GPP TR 23.700-82 V0.2.0.
[0061] System architecture description
[0062] Although the subject matter described herein may be implemented in any appropriate type of system using any suitable components, the embodiments disclosed herein are described in relation to a communication system complied with the exemplary system architecture illustrated in FIGs. 1, 2a and 2b. For simplicity, the system architecture of FIGs. 1. 2a and 2b only depict some exemplary elements. In practice, a communication system may further include any additional elements suitable to support communication between terminal devices or between a wireless device and another communication device, such as a landline telephone, a service provider, or any other network node or terminal device. The communication system may provide communication and various types of services to one or more terminal devices to facilitate the terminal devices’ access to and / or use of the services provided by, or via, the communication system.
[0063] FIG. 1 schematically shows generic on-network functional model of SEAL, which is same as Figure 6.2-1 of 3GPP TS 23.434 V19.0.0.
[0064] Clause 6.4.2 of 3GPP TS 23.434 V19.0.0 describes the application plane. Entities within the application plane of a VAL system provide application control and media specific functions to support one or more VAL services. For example, the entities within the application plane of the VAL system may comprise VAL client, VAL server, SEAL client, SEAL server and VAL user database, which are examples of “application functional entities” in the present disclosure.
[0065] The VAL client provides the client side functionalities corresponding to the vertical applications (e. g. V2X client) . The VAL client supports interactions with the SEAL client (s) .
[0066] The VAL server provides the server side functionalities corresponding to the vertical applications (e. g. V2X application servers) . The VAL server acts as API invoker of Common API Framework for northbound APIs (CAPIF) as specified in 3GPP TS 23.222 V19.0.0.
[0067] The SEAL client provides the client side functionalities corresponding to the specific SEAL service. The SEAL client (s) supports interactions with the VAL client (s) . The SEAL client also supports interactions with the corresponding SEAL client between the two UEs.
[0068] The SEAL server provides the server side functionalities corresponding to the specific SEAL service. The SEAL server supports interactions with the VAL server (s) . The SEAL server may act as CAPIF's API exposing function as specified in 3GPP TS 23.222 V19.0.0. The SEAL server may also support interactions with the corresponding SEAL server in distributed SEAL deployments.
[0069] The reference points for the generic functional model for SEAL are described in the clause 6.5 of 3GPP TS 23.434 V19.0.0.
[0070] FIG. 2a schematically shows a high level architecture in a 5G network according to an embodiment of the present disclosure. The architecture of FIG. 2a may be similar to Figure 4.2.3-1 of 3GPP TS 23.501 V18.4.0, the disclosure of which is incorporated by reference herein in its entirety. The system architecture of FIG. 2a may comprise a plurality of network functions (NFs) such as Access and Mobility Management Function (AMF) , Session Management Function (SMF) , Authentication Service Function (AUSF) , Unified Data Management (UDM) , Policy Control Function (PCF) , Application Function (AF) , Network Exposure Function (NEF) , User plane Function (UPF) and Network Repository Function (NRF) , (radio) access network ((R) AN) , service communication proxy (SCP) , Network Slice Selection Function (NSSF) , network slice-Specific Authentication and Authorization Function (NSSAAF) , Edge Application Server Discovery Function (EASDF) , NSACF (network slice Admission Control Function) , NWDAF, etc.
[0071] In accordance with an exemplary embodiment, the UE can establish a signaling connection with the AMF over the reference point N1, as illustrated in FIG. 2a. This signaling connection may enable NAS (Non-access stratum) signaling exchange between the UE and the core network, comprising a signaling connection between the UE and the (R) AN and the N2 connection for this UE between the (R) AN and the AMF. The (R) AN can communicate with the UPF over the reference point N3. The UE can establish a protocol data unit (PDU) session to the DN (data network, e. g. an operator network or Internet) through the UPF over the reference point N6.
[0072] As further illustrated in FIG. 2a, the exemplary system architecture also contains the service-based interfaces such as Nnrf, Nnef, Nausf, Nudm, Npcf, Namf, Nnsacf, Neasdf, Nnssf, Nnwdaf and Nsmf exhibited by NFs such as the NRF, the NEF, the AUSF, the UDM, the PCF, the AMF, the NSACF, the EASDF, the NSSF, the NWDAF and the SMF. In addition, FIG. 2a also shows some reference points such as N1, N2, N3, N4, N6 and N9, which can support the interactions between NF services in the NFs. For example, these reference points may be realized through corresponding NF service-based interfaces and by specifying some NF service consumers and providers as well as their interactions in order to perform a particular system procedure.
[0073] Various NFs shown in FIG. 2a may be responsible for functions such as session management, mobility management, authentication, security, etc. The AUSF, AMF, DN, NEF, NRF, NSSF, PCF, SMF, UDM, UPF, AF, UE, (R) AN, SCP, NSACF, NSSAAF, EASDF may include the functionality for example as defined in clause 6.2 of 3GPP TS 23.501 V18.4.0.
[0074] FIG. 2b schematically shows system architecture in a 4G network according to an embodiment of the present disclosure, which is the same as Figure 4.2-1a of 3GPP TS 23.682 V18.0.0, the disclosure of which is incorporated by reference herein in its entirety. The system architecture of FIG. 2b may comprise some exemplary elements such as Services Capability Server (SCS) , Application Server (AS) , SCEF (Service Capability Exposure Function) , HSS, UE, RAN(Radio Access Network) , SGSN (Serving GPRS (General Packet Radio Service) Support Node) , MME, MSC (Mobile Switching Centre) , S-GW (Serving Gateway) , GGSN / P-GW (Gateway GPRS Support Node / PDN (Packet Data Network) Gateway) , MTC-IWF (Machine Type Communications-InterWorking Function) CDF / CGF (Charging Data Function / Charging Gateway Function) , MTC-AAA (Machine Type Communications-authentication, authorization and accounting) , SMS-SC / GMSC / IWMSC (Short Message Service-Service Centre / Gateway MSC / InterWorking MSC) IP-SM-GW (Internet protocol Short Message Gateway) . The network elements and interfaces as shown in FIG. 2b may be same as the corresponding network elements and interfaces as described in 3GPP TS 23.682 V18.0.0.
[0075] The system architecture shows the architecture for a UE used for MTC connecting to the 3GPP network (UTRAN (Universal Terrestrial Radio Access Network) , E-UTRAN (Evolved UTRAN) , GERAN (GSM EDGE (Enhanced Data rates for GSM Evolution) Radio Access Network) , etc. ) via the Um / Uu / LTE-Uu interfaces. The system architecture also shows the 3GPP network service capability exposure to SCS and AS.
[0076] As further illustrated in FIG. 2b, the exemplary system architecture also contains various reference points.
[0077] Tsms: Reference point used by an entity outside the 3GPP network to communicate with UEs used for MTC via SMS (Short Message Service) .
[0078] Tsp: Reference point used by a SCS to communicate with the MTC-IWF related control plane signaling.
[0079] T4: Reference point used between MTC-IWF and the SMS-SC in the HPLMN (home Public Land Mobile Network) .
[0080] T6a: Reference point used between SCEF and serving MME.
[0081] T6b: Reference point used between SCEF and serving SGSN.
[0082] T8: Reference point used between the SCEF and the SCS / AS.
[0083] S6m: Reference point used by MTC-IWF to interrogate HSS / HLR (Home Location Register) .
[0084] S6n: Reference point used by MTC-AAA to interrogate HSS / HLR.
[0085] S6t: Reference point used between SCEF and HSS.
[0086] SGs: Reference point used between MSC and MME.
[0087] Gi / SGi: Reference point used between GGSN / P-GW and application server and between GGSN / P-GW and SCS.
[0088] Rf / Ga: Reference point used between MTC-IWF and CDF / CGF.
[0089] Gd: Reference point used between SMS-SC / GMSC / IWMSC and SGSN.
[0090] SGd: Reference point used between SMS-SC / GMSC / IWMSC and MME.
[0091] E: Reference point used between SMS-SC / GMSC / IWMSC and MSC.
[0092] A non-terrestrial network refers to a network, or segment of networks using RF resources on board a satellite (or Uncrewed Aerial System (UAS) platform) .
[0093] Methods according to embodiments of the present disclosure
[0094] FIG. 3a shows a flowchart of a method according to an embodiment of the present disclosure, which may be performed by an apparatus implemented in or at or as a service enablement server entity (e. g. AIML service enablement server entity) or communicatively coupled to the service enablement server entity (e. g. AIML service enablement server entity) . As such, the apparatus may provide means or modules or circuits for accomplishing various parts of the method 300 as well as means or modules or circuits for accomplishing other processes in conjunction with other components.
[0095] At block 302, the service enablement server entity (e. g. AIML service enablement server entity) receives, from an application server entity, a (e. g. AIML) service lifecycle assistance request or a (e. g. AIML) service lifecycle assistance update request.
[0096] The service enablement server entity may communicate with any suitable network. For example, the service enablement server entity may communicate with the underlying 3GPP network systems using the respective 3GPP interfaces specified by the 3GPP network system. In an embodiment, the service enablement server entity may communicate with Evolved Packet System (EPS) , a 5GS, or a sixth generation system (6GS) as defined by 3GPP.
[0097] The service enablement server entity may be any suitable node, device, function, or entity that can implement service enablement function. For example, the service enablement server entity may be the SEAL server as described in 3GPP TS 23.434 V19.0.0. In an embodiment, the service enablement server entity may comprise an AIML enablement server.
[0098] The application server entity may be any suitable node, device, function, or entity that can provide the application functionalities corresponding to an application or a service. For example, the application server entity can be a VAL server for example as described in 3GPP TS 23.434 V19.0.0. In an embodiment, the application server entity may be an AIML server. The application server entity may support vertical applications, e. g. V2X applications, AI / ML service.
[0099] The service may be any suitable service and the present disclosure has no limit on it. In an embodiment, the service may comprise an AIML service.
[0100] The service lifecycle assistance request may be used for service lifecycle management such as the service lifecycle management of the AIML service. The service lifecycle assistance request may comprise any suitable information regarding the service lifecycle management and the present disclosure has no limit on it.
[0101] The service lifecycle assistance update request may be used for service lifecycle management such as the service lifecycle management of the AIML service. The service lifecycle assistance update request may comprise any suitable information regarding the service lifecycle management and the present disclosure has no limit on it.
[0102] In an embodiment, the (e. g. AIML) service lifecycle assistance request and / or the (e. g. AIML) service lifecycle assistance update request may comprise at least one of: - a vertical application layer (VAL) server identity (ID) , - a VAL service identifier, - a service client ID, such as AIML client ID, - a service client group ID, such as AIML client group ID, - a service operation mode, such as AIML service operation mode, - a service model container, such as AIML service model container, - an address to fetch a service model, such as uniform resource identifier (URI) of the model to fetch the model from a repository, - an address to send service model updates, such as AIML service aggregator URI to send model updates, - a service optimization assistance mode, such as AIML service optimization assistance mode, or - service incentive information, such as AIML service incentive container.
[0103] The VAL server ID may be used to indicate the VAL server identity. The VAL server ID may be similar to the VAL server ID as described in 3GPP TS 23.434 V19.0.0. The VAL service identifier may be used to indicate the identifier of the VAL service. The VAL service identifier may be similar to the VAL service identifier as described in 3GPP TS 23.434 V19.0.0. The service client ID may be used to indicate the service client identity. The service client group ID may be used to identify a client group.
[0104] The service operation mode may comprise any suitable service operation mode and the present disclosure has no limit on it. In an embodiment, the service operation mode may comprise at least one of: - service start, such as AIML service start - service pause, such as AIML service pause - service continue, such as AIML service continue, or - service finish, such as AIML service finish.
[0105] The address to fetch a service model may comprise any suitable address and the present disclosure has no limit on it. In an embodiment, the address to fetch a service model may comprise a URI to fetch the service model.
[0106] The service model may be any suitable service model. For example, the service model may be AIML service model.
[0107] The address to send service model updates may comprise any suitable address and the present disclosure has no limit on it. In an embodiment, the address to send service model updates may comprise a URI to send service model updates.
[0108] The service optimization assistance mode may comprise any suitable service optimization assistance mode and the present disclosure has no limit on it. In an embodiment, the service optimization assistance mode may comprise at least one of energy-efficient (EE) optimization assistance mode and fast convergence optimization assistance mode.
[0109] For example, an AIML service operated on IoT devices may require EE optimization assistance from the AIML enablement layer to train the model and save energy. Another AIML service dealing with time-critical use cases may require faster convergence optimization assistance from the AIML enablement layer so that the global model is updated faster and devices are updated in a short period. The AIML enablement layer can provide network-related implementations by leveraging the network such as 5GS for the VAL server (AIML application layer) to assist the VAL server in achieving its optimization.
[0110] The service incentive information may comprise any suitable service incentive information and the present disclosure has no limit on it. In an embodiment, the service incentive information may comprise at least one of an incentive and an incentive delivery mode.
[0111] The incentive may comprise any suitable incentive and the present disclosure has no limit on it. In an embodiment, the incentive may comprise at least one of an application-oriented incentive and a network-oriented incentive. The application-oriented incentive may be transparent to the service enablement server entity. The network-oriented incentive may be an upgraded subscription plan.
[0112] The incentive delivery mode may comprise any suitable incentive delivery mode and the present disclosure has no limit on it. In an embodiment, the incentive delivery mode may indicate when to deliver the incentive such as the start of the service, the end of the service, or at a defined delivery interval.
[0113] For example, the service enablement server entity such as VAL server sends AIML service lifecycle assistance request to the AIML enablement server. The AIML service lifecycle assistance request may contain VAL server ID, VAL service ID, AIML client ID, AIML clients group ID, AIML service operation mode (such as start, pause, continue, finish) , AIML service model container or URI of the model to fetch the model from a repository, AIML service aggregator URI to send model updates, AIML service optimization assistance mode such as energy-efficient optimization assistance mode, fast convergence optimization assistance mode.
[0114] The request may also contain the AIML service incentive container which may comprise incentive and incentive delivery modes. The incentive may comprise an application-oriented incentive which is transparent to the AIML Enablement server and a network-oriented incentive such as an upgraded subscription plan. The delivery of incentive may define when to deliver the incentive such as the start of the service, end of the service, or at a defined delivery interval.
[0115] The service enablement server entity such as VAL server may send AIML service lifecycle assistance update request to the AIML enablement server with the AIML service operation ID and update container. The AIML service lifecycle assistance update request may contain at least one parameter mentioned in AIML service lifecycle assistance request.
[0116] At block 304, the (e. g. AIML) service enablement server entity sends, to the application server entity, a (e. g. AIML) service lifecycle assistance response or a (e. g. AIML) service lifecycle assistance update response.
[0117] The (e. g. AIML) service lifecycle assistance response may comprise any suitable information. In an embodiment, the (e. g. AIML) service lifecycle assistance response may comprise at least one of a service operation identifier and a status of the service.
[0118] The (e. g. AIML) service lifecycle assistance update response may comprise any suitable information. The (e. g. AIML) service lifecycle assistance update response may comprise at least one of an update result and an associated service operation identifier.
[0119] For example, after receiving the service lifecycle assistance request or the service lifecycle assistance update request, the service enablement server entity may process the service lifecycle assistance request or the service lifecycle assistance update request.
[0120] For example, the service enablement server entity may determine the service optimization assistance mode and / or the service incentive information based on at least one of the VAL server ID, the VAL service ID, a service client ID and / or a service client group ID if the service optimization assistance mode and / or service incentive information are omitted in the lifecycle assistance request and / or the lifecycle assistance update request.
[0121] For example, the service enablement server entity may fetch the service model based on the address to fetch a service model.
[0122] For example, the service enablement server entity may fetch the service model updates based on the address to send service model updates.
[0123] The service enablement server entity may generate the service lifecycle assistance response or the service lifecycle assistance update response based on the processing result.
[0124] FIG. 3b shows a flowchart of a method according to another embodiment of the present disclosure, which may be performed by an apparatus implemented in or at or as a (e. g. AIML) service enablement server entity or communicatively coupled to the (e. g. AIML) service enablement server entity. As such, the apparatus may provide means or modules or circuits for accomplishing various parts of the method 310 as well as means or modules or circuits for accomplishing other processes in conjunction with other components. For some parts which have been described in the above embodiments, the description thereof is omitted here for brevity.
[0125] At block 312, the (e. g. AIML) service enablement server entity may send, to a (e. g. AIML) service enablement client entity, an (e. g. AIML) enablement client service operation request based on a service client ID or a service client group ID.
[0126] The service enablement client entity may communicate with any suitable network. For example, the service enablement client entity may communicate with the underlying 3GPP network systems using the respective 3GPP interfaces specified by the 3GPP network system. In an embodiment, the service enablement client entity may communicate with EPS, 5GS, or 6GS as defined by 3GPP.
[0127] The service enablement client entity may be any suitable node, device, function, or entity that can implement service enablement function. For example, the service enablement client entity may be the SEAL client as described in 3GPP TS 23.434 V19.0.0. In an embodiment, the service enablement client entity may comprise an AIML enablement client.
[0128] The enablement client service operation request may be used for service lifecycle management such as the service lifecycle management of the AIML service. The enablement client service operation request may comprise any suitable information regarding the service lifecycle management and the present disclosure has no limit on it.
[0129] In an embodiment, the (e. g. AIML) enablement client service operation request may comprise at least one of: - a service client ID, such as AIML client ID, - a service operation mode, such as AIML service operation mode, - a service model, such as AIML service model, - service transport protocol information, such as AIML service transport protocol, - an address to send service model updates, such as AIML service aggregator URI to send model updates, or - a service application-oriented incentive.
[0130] At block 314, the (e. g. AIML) service enablement server entity may receive, from the (e.g. AIML) service enablement client entity, an (e. g. AIML) enablement client service operation response.
[0131] The enablement client service operation response may comprise any suitable information. In an embodiment, the (e. g. AIML) enablement client service operation response may comprise information indicating a result of the (e. g. AIML) enablement client service operation.
[0132] For example, after receiving the enablement client service operation request, the service enablement client entity may process the enablement client service operation request.
[0133] For example, the service enablement client entity may determine the service client identified by the service client ID. The service enablement client entity may send at least one of the service operation mode, the service application-oriented incentive and the service model to the service client identified by the service client ID. The service enablement client entity may communicate with the service enablement server entity using the service transport protocol. The service enablement client entity may obtain the service model updates based on the address to send service model updates.
[0134] The service enablement client entity may generate the enablement client service operation response based on the processing result.
[0135] In an embodiment, the (e. g. AIML) enablement client service operation response may comprise information indicating a result (such as success or failure) of the (e. g. AIML) enablement client service operation.
[0136] FIG. 4 shows a flowchart of a method according to another embodiment of the present disclosure, which may be performed by an apparatus implemented in or at or as a (e. g. AIML) service enablement server entity or communicatively coupled to the (e. g. AIML) service enablement server entity. As such, the apparatus may provide means or modules or circuits for accomplishing various parts of the method 400 as well as means or modules or circuits for accomplishing other processes in conjunction with other components. For some parts which have been described in the above embodiments, the description thereof is omitted here for brevity.
[0137] At block 402, the (e. g. AIML) service enablement server entity may interact with a network for configuring a network-oriented incentive.
[0138] In an embodiment, the service enablement server entity may interact with the network for configuring a connection between the service enablement server entity and the service enablement client entity based on the service optimization assistance mode.
[0139] The network may be any suitable network such as EPS, 5GS, or 6GS as defined by 3GPP. For example, the service enablement server entity may interact with a network exposure node such as NEF or SCEF for configuring a network-oriented incentive or the connection between the service enablement server entity and the service enablement client entity.
[0140] In an embodiment, the service enablement server entity may interact with a network for configuring a network-oriented incentive based on an incentive delivery mode.
[0141] FIG. 5 shows a flowchart of a method according to another embodiment of the present disclosure, which may be performed by an apparatus implemented in or at or as an application server entity or communicatively coupled to the application server entity. As such, the apparatus may provide means or modules or circuits for accomplishing various parts of the method 500 as well as means or modules or circuits for accomplishing other processes in conjunction with other components. For some parts which have been described in the above embodiments, the description thereof is omitted here for brevity.
[0142] At block 502, the application server entity sends, to a (e. g. AIML) service enablement server entity, a (e. g. AIML) service lifecycle assistance request or a (e. g. AIML) service lifecycle assistance update request.
[0143] At block 504, the application server entity receives, from the (e. g. AIML) service enablement server entity, a (e. g. AIML) service lifecycle assistance response or a (e. g. AIML) service lifecycle assistance update response.
[0144] In an embodiment, the (e. g. AIML) service lifecycle assistance request and / or the (e. g. AIML) service lifecycle assistance update request may comprise at least one of a VAL server ID, a VAL service identifier, a service client ID, a service client group ID, a service operation mode, a service model container, an address to fetch a service model, an address to send service model updates, a service optimization assistance mode, or service incentive information.
[0145] In an embodiment, the service operation mode may comprise at least one of service start, service pause, service continue, or service finish.
[0146] In an embodiment, the address to fetch a service model may comprise a URI to fetch the service model.
[0147] In an embodiment, the address to send service model updates may comprise a URI to send service model updates.
[0148] In an embodiment, the service optimization assistance mode may comprise at least one of energy-efficient optimization assistance mode and fast convergence optimization assistance mode.
[0149] In an embodiment, the service incentive information may comprise at least one of an incentive and an incentive delivery mode.
[0150] In an embodiment, the incentive may comprise at least one of an application-oriented incentive and a network-oriented incentive.
[0151] In an embodiment, the incentive delivery mode may indicate when to deliver the incentive.
[0152] In an embodiment, the (e. g. AIML) service lifecycle assistance response may comprise at least one of a service operation identifier and a status of the service.
[0153] In an embodiment, the (e. g. AIML) service lifecycle assistance update response comprises at least one of an update result and an associated service operation identifier.
[0154] In an embodiment, the service may comprise an AIML service.
[0155] In an embodiment, the service enablement server entity may comprise an AIML enablement server.
[0156] In an embodiment, the application server entity may comprise a VAL server.
[0157] FIG. 6 shows a flowchart of a method according to another embodiment of the present disclosure, which may be performed by an apparatus implemented in or at or as a (e. g. AIML) service enablement client entity or communicatively coupled to the (e. g. AIML) service enablement client entity. As such, the apparatus may provide means or modules or circuits for accomplishing various parts of the method 600 as well as means or modules or circuits for accomplishing other processes in conjunction with other components. For some parts which have been described in the above embodiments, the description thereof is omitted here for brevity.
[0158] At block 602, the (e. g. AIML) service enablement client entity receives, from a (e. g. AIML) service enablement server entity, an (e. g. AIML) enablement client service operation request e. g. to manage an AIML service operation lifecycle.
[0159] At block 604, the (e. g. AIML) service enablement client entity sends, to the (e. g. AIML) service enablement server entity, an (e. g. AIML) enablement client service operation response.
[0160] In an embodiment, the enablement client service operation request may comprise at least one of a service client ID, a service operation mode, a service model, service transport protocol information, an address to send service model updates, or a service application-oriented incentive.
[0161] In an embodiment, the service operation mode may comprise at least one of service start, service pause, service continue, or service finish.
[0162] In an embodiment, the address to send service model updates may comprise a URI to send service model updates.
[0163] In an embodiment, the (e. g. AIML) enablement client service operation response may comprise information indicating a result of the (e. g. AIML) enablement client service operation.
[0164] In an embodiment, the service may comprise an AIML service.
[0165] In an embodiment, the service enablement client entity may comprise an AIML enablement client.
[0166] In an embodiment, the service enablement server entity may comprise an AIML enablement server.
[0167] In an embodiment, the proposed solution proposes a procedure to manage the lifecycle of the AI / ML service.
[0168] In an embodiment, the procedure also enables network-oriented incentive and application-oriented incentive delivery
[0169] In an embodiment, it also assists the AI / ML service to achieve its optimization request such as faster convergence or energy-efficiency.
[0170] In an embodiment, it also provides update mechanisms to provide changes in the AI / ML ongoing process.
[0171] Currently, there are no methods for the application servers (such as VAL servers, AIML servers) to request a network for the lifecycle management of the AIML service. The application servers manage the lifecycle of its AIML operation in a non-interoperable method using an application layer AIML library. Any AIML service operation involves an AIML server and AIML clients, and the AIML server and AIML clients are connected over a network (such as 5G network) for communication of various tasks such as exchanging model updates, downloading new model transfer, splitting model etc. Such communication is subject to the network conditions. For example, poor network conditions will negatively impact the performance of the AIML service process.
[0172] This creates the need for the application servers to take assistance from the network to ensure the required QoS support for the AIML service operations. Since the network is not aware of any ongoing AIML service operations such as whether the AIML service is started, or stopped, ongoing, it is not possible to ensure the desired QoS for the AIML service. Therefore, the network must provide exposure to the application servers for AIML service lifecycle management. With such exposure the application servers can inform the network about the life cycle of the AIML service and the network can take measures to assist the AIML service operation.
[0173] The proposed method provides a procedure to expose the AIML service lifecycle management to application servers such as VAL servers. The application servers can use the exposure to offload the AIML service lifecycle operation. The exposure enables the application servers to indicate the AIML service lifecycle operation states such as start, stop, pause, and continue. It can further indicate the network-oriented incentive, and application-oriented incentive, and configure the delivery of incentive to the AIML clients. The proposed method enables the application server to use the network in a standardized way for AIML service life cycle management, to configure the incentive and delivery of the incentive. The application server can indicate the network for optimization assistance requests such as faster convergence or achieving energy efficiency for its AIML service operation in the exposure. The network based on the request can configure the 5G network to assist the optimization of the AIML service.
[0174] Embodiments herein may provide many advantages, of which a non-exhaustive list of examples follows. In some embodiments herein, the application server entity such as VAL server can offload the lifecycle of service (such as AI / ML service) to the service (such as AI / ML) enabler layer. In some embodiments herein, the application server entity such as VAL server can use network APIs to assist its service (such as AI / ML) performance optimization. In some embodiments herein, the application server entity such as VAL server can deliver the application oriented incentive and configure the network for network-oriented incentive delivery. In some embodiments herein, the network based on the request can configure the network (such as 5GS) to assist the optimization of the service (such as AI / ML) . The embodiments herein are not limited to the features and advantages mentioned above. A person skilled in the art will recognize additional features and advantages upon reading the following detailed description.
[0175] Apparatuses according to embodiments of the present disclosure
[0176] FIG. 7 is a block diagram showing an apparatus suitable for practicing some embodiments of the disclosure. For example, the (e. g. AIML) service enablement server entity, the (e. g. AIML) service enablement client entity or the application server entity described above may be implemented as or through the apparatus 700.
[0177] The apparatus 700 comprises at least one processor 721, such as a digital processor (DP) , and at least one memory (MEM) 722 coupled to the processor 721. The apparatus 700 may further comprise a transmitter TX and receiver RX 723 coupled to the processor 721. The MEM 722 stores a program (PROG) 724. The PROG 724 may include instructions that, when executed on the associated processor 721, enable the apparatus 700 to operate in accordance with the embodiments of the present disclosure. A combination of the at least one processor 721 and the at least one MEM 722 may form processing means 725 adapted to implement various embodiments of the present disclosure.
[0178] Various embodiments of the present disclosure may be implemented by computer program executable by one or more of the processor 721, software, firmware, hardware or in a combination thereof.
[0179] The MEM 722 may be of any type suitable to the local technical environment and may be implemented using any suitable data storage technology, such as semiconductor based memory devices, magnetic memory devices and systems, optical memory devices and systems, fixed memories and removable memories, as non-limiting examples.
[0180] The processor 721 may be of any type suitable to the local technical environment, and may include one or more of general purpose computers, special purpose computers, microprocessors, digital signal processors (DSPs) and processors based on multicore processor architecture, as non-limiting examples.
[0181] In an embodiment where the apparatus is implemented as or at the (e. g. AIML) service enablement server entity, the memory 722 contains instructions executable by the processor 721, whereby the (e. g. AIML) service enablement server entity operates according to any of the methods performed by the (e. g. AIML) service enablement server entity as described above.
[0182] In an embodiment where the apparatus is implemented as or at the application server entity, the memory 722 contains instructions executable by the processor 721, whereby the application server entity operates according to any of the methods performed by the application server entity as described above.
[0183] In an embodiment where the apparatus is implemented as or at the (e. g. AIML) service enablement client entity, the memory 722 contains instructions executable by the processor 721, whereby the (e. g. AIML) service enablement client entity operates according to any of the methods performed by the (e. g. AIML) service enablement client entity as described above.
[0184] With function units, the (e. g. AIML) service enablement server entity, the (e. g. AIML) service enablement client entity or the application server entity may not need a fixed processor or memory, any computing resource and storage resource may be arranged from the (e.g. AIML) service enablement server entity, the (e. g. AIML) service enablement client entity or the application server entity in the communication system. The introduction of virtualization technology and network computing technology may improve the usage efficiency of the network resources and the flexibility of the network.
[0185] Although the computing devices described herein (e.g., UEs, network nodes, hosts) may include the illustrated combination of hardware components, other embodiments may comprise computing devices with different combinations of components. It is to be understood that these computing devices may comprise any suitable combination of hardware and / or software needed to perform the tasks, features, functions and methods disclosed herein. Determining, calculating, obtaining or similar operations described herein may be performed by processing circuitry, which may process information by, for example, converting the obtained information into other information, comparing the obtained information or converted information to information stored in the network node, and / or performing one or more operations based on the obtained information or converted information, and as a result of said processing making a determination. Moreover, while components are depicted as single boxes located within a larger box, or nested within multiple boxes, in practice, computing devices may comprise multiple different physical components that make up a single illustrated component, and functionality may be partitioned between separate components. For example, a communication interface may be configured to include any of the components described herein, and / or the functionality of the components may be partitioned between the processing circuitry and the communication interface. In another example, non-computationally intensive functions of any of such components may be implemented in software or firmware and computationally intensive functions may be implemented in hardware.
[0186] In certain embodiments, some or all of the functionality described herein may be provided by processing circuitry executing instructions stored on in memory, which in certain embodiments may be a computer program product in the form of a non-transitory computer-readable storage medium. In alternative embodiments, some or all of the functionality may be provided by the processing circuitry without executing instructions stored on a separate or discrete device-readable storage medium, such as in a hard-wired manner. In any of those particular embodiments, whether executing instructions stored on a non-transitory computer-readable storage medium or not, the processing circuitry can be configured to perform the described functionality. The benefits provided by such functionality are not limited to the processing circuitry alone or to other components of the computing device, but are enjoyed by the computing device as a whole, and / or by end users and a wireless network generally.
[0187] The term unit or module may have conventional meaning in the field of electronics, electrical devices and / or electronic devices and may include, for example, electrical and / or electronic circuitry, devices, modules, processors, memories, logic solid state and / or discrete devices, computer programs or instructions for carrying out respective tasks, procedures, computations, outputs, and / or displaying functions, and so on, as such as those that are described herein.
[0188] According to an aspect of the disclosure it is provided a computer program product being tangibly stored on a computer readable storage medium and including instructions which, when executed on at least one processor, cause the at least one processor to carry out any of the methods as described above.
[0189] According to an aspect of the disclosure it is provided a computer-readable storage medium storing instructions which when executed by at least one processor, cause the at least one processor to carry out any of the methods as described above.
[0190] In addition, the present disclosure may also provide a carrier containing the computer program as mentioned above, wherein the carrier is one of an electronic signal, optical signal, radio signal, or computer readable storage medium. The computer readable storage medium can be, for example, an optical compact disk or an electronic memory device like a RAM (random access memory) , a ROM (read only memory) , Flash memory, magnetic tape, CD-ROM, DVD, Blue-ray disc and the like.
[0191] The techniques described herein may be implemented by various means so that an apparatus implementing one or more functions of a corresponding apparatus described with an embodiment comprises not only prior art means, but also means for implementing the one or more functions of the corresponding apparatus described with the embodiment and it may comprise separate means for each separate function, or means that may be configured to perform two or more functions. For example, these techniques may be implemented in hardware (one or more apparatuses) , firmware (one or more apparatuses) , software (one or more modules) , or combinations thereof. For a firmware or software, implementation may be made through modules (e.g., procedures, functions, and so on) that perform the functions described herein.
[0192] Exemplary embodiments herein have been described above with reference to block diagrams and flowchart illustrations of methods and apparatuses. It will be understood that each block of the block diagrams and flowchart illustrations, and combinations of blocks in the block diagrams and flowchart illustrations, respectively, can be implemented by various means including computer program instructions. These computer program instructions may be loaded onto a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions which execute on the computer or other programmable data processing apparatus create means for implementing the functions specified in the flowchart block or blocks.
[0193] Further, while operations are depicted in a particular order, this should not be understood as requiring that such operations be performed in the particular order shown or in sequential order, or that all illustrated operations be performed, to achieve desirable results. In certain circumstances, multitasking and parallel processing may be advantageous. Likewise, while several specific implementation details are contained in the above discussions, these should not be construed as limitations on the scope of the subject matter described herein, but rather as descriptions of features that may be specific to particular embodiments. Certain features that are described in the context of separate embodiments may also be implemented in combination in a single embodiment. Conversely, various features that are described in the context of a single embodiment may also be implemented in multiple embodiments separately or in any suitable sub-combination.
[0194] While this specification contains many specific implementation details, these should not be construed as limitations on the scope of any implementation or of what may be claimed, but rather as descriptions of features that may be specific to particular embodiments of particular implementations. Certain features that are described in this specification in the context of separate embodiments can also be implemented in combination in a single embodiment. Conversely, various features that are described in the context of a single embodiment can also be implemented in multiple embodiments separately or in any suitable sub-combination. Moreover, although features may be described above as acting in certain combinations and even initially claimed as such, one or more features from a claimed combination can in some cases be excised from the combination, and the claimed combination may be directed to a sub-combination or variation of a sub-combination.
[0195] It will be obvious to a person skilled in the art that, as the technology advances, the inventive concept can be implemented in various ways. The above described embodiments are given for describing rather than limiting the disclosure, and it is to be understood that modifications and variations may be resorted to without departing from the spirit and scope of the disclosure as those skilled in the art readily understand. Such modifications and variations are considered to be within the scope of the disclosure and the appended claims. The protection scope of the disclosure is defined by the accompanying claims.
[0196] In an embodiment, 3GPP TR 23.700-82 v0.2.0 may be changed as following. 1. Introduction This pCR proposes a solution for the AIML lifecycle KI#1 2. Reason for Change AIML services require enabler layer support to manage the lifecycle of the AIML services. This includes managing the AIML service with operations like start / pause / continue / finish of the AIML service, initializing the clients with the model, or incentivizing the clients. Using the AIML service operations, the enabler layer can manage the AIML clients like monitoring the QoS, sharing the model with the selected clients, AIML service optimization assistance . The VAL server can offload the lifecycle management of the AI / ML service to the AI / ML enabler layer. Because of this offload, the enabler layer is aware of the lifecycle of the AI / ML process and can ensure the required QoS for the process. The AIML services can be performed on various clients like servers, robots, UEs, IoT devices etc. as per different use cases. Each use case is subject to its requirements. For example, AIML service in the IoT domain is subject to the Energy-Efficient (EE) , ie. IoT devices want to save power while training. For time-critical use cases, it is subject to faster convergence to make sure an updated global model is available for the clients to use. Since the AIML server and AIML clients communicate over the network and the network is dynamic, this creates the need for the enabler layer to assist the AIML server in achieving its optimization like EE or fast convergence. For example, to enable faster convergence service optimization, the enabler layer can configure the network to provide dual connectivity or redundant connectivity links so that the AIML clients can communicate better with the AIML server (e. g. avoid retransmissions and reduce latency) to exchange model updates between the AIML server and client. This can enable the AIML clients to complete more rounds in the AIML service within a given time, train models faster and achieve fast convergence relatively. Therefore exposure is required to enable VAL servers (like AIML servers) to request an enabler layer for its optimization assistance. 3. Conclusions <Conclusion part (optional) > 4. Proposal It is proposed to agree the following changes to 3GPP TR 23.700-82 v0.2.0. 8. x Solution #x: AIML service lifecycle assistance procedure 8.x. 1 General The following clauses specify procedures, information flows and APIs for Key issue 1 to enable the: AIML service lifecycle assistance procedure. The AIML service is a real-time process which involves clients and servers to communicate regarding the operations of the AIML service. There is a need for the AIML Enablement layer to provide the required exposure to facilitate communication. For any AIML service, the VAL servers (like application layer AIML server) need to start the AIML service or stop the AIML service, initialize AIML clients with AIML, and incentivize the AIML clients to take part in the AIML service. The AIML server also required optimization assistance from the AIML Enablement layer for the optimization and to achieve its desired KPIs of the AIML service like faster convergence or AIML service performed in Energy-Efficient (EE) manner. The AIML Enablement layer can help the AIML server to achieve its AIML service optimization and KPIs by providing relevant exposure and implementing the actions to support the optimization. For example, an AIML service operated on IoT devices requires EE optimization assistance from the AIML Enablement layer to train the model and save energy. Another AIML service dealing with time-critical use cases requires faster convergence optimization assistance from the AIML Enablement layer so that the global model is updated faster and devices are updated in a short period. The AIML Enablement layer can provide network-related implementations by leveraging the 5G System for the VAL server (AIML application layer) to assist the VAL server in achieving its optimization. Pre-conditions: 1. The AIML Enablement server has information about the available clients like client IDs, selected clients, and client capabilities. 8.x. 2: AIML service lifecycle assistance procedure FIG. 8 shows a flowchart of AIML service lifecycle assistance procedure. 1. The VAL server sends AIML service lifecycle assistance request to the AIML Enablement server. The request contains VAL server ID, VAL service ID, AIML client ID, AIML clients group ID, AIML service operation mode like start, pause, continue, finish; AIML service model container or URI of the model to fetch the model from a repository, AIML service aggregator URI to send model updates, AIML service optimization assistance mode like Energy-efficient optimization assistance mode, Fast convergence optimization assistance mode. The request also contains the AIML service incentive container consisting of incentive and incentive delivery modes. The incentive contains an application-oriented incentive which is transparent to the AIML Enablement server and a network-oriented incentive like an upgraded subscription plan. The delivery of incentive defines when to deliver the incentive like the start of the service, end of the service, or at a defined delivery interval. 2. The AIML Enablement server receives the request and based on the AIML clients group ID or AIML client ID, it sends the AIML Enablement client service operation request to the AIML Enablement client (s) . The request contains AIML client ID, AIML service operation mode, AIML service model, AIML service transport protocol, AIML service aggregator URI and AIML service application-oriented incentive. Based on the incentive delivery mode, the AIML Enablement server interacts with 5GS for configuring the network-oriented incentive. Editor’s Note 1: other IEs in the request are FFS. Editor’s Note 2: Whether and how the AIML Enablement server interacts with 5GS for configuring the network-oriented incentive is FFS. NOTE 1: How the AIML Enablement server implements different actions to support the AIML service optimization assistance is implementation logic and out of scope. 3. The AIML Enablement client sends a response indicating the success or failure of the AIML Enablement client service operation response. 4. The AIML Enablement server provides the AIML service lifecycle assistance response to the VAL server. The message includes AIML service operation ID and the status of the AIML service. 5. The VAL server sends AIML service lifecycle assistance update request to the AIML Enablement server with the AIML service operation ID and update container. The update container contains parameters mentioned in step 1 clause 8. x. 2. 6. The AIML Enablement server receives the request and performs steps 2 and step 3 described in the procedure defined in clause 8. x. 2. The AIML Enablement server provides the AIML service lifecycle assistance update response to the VAL server. The message includes the result of the update and the associated AIML service operation ID. Editor’s Note 3: other IEs in the response are FFS.
Claims
1.A method (300) performed by an artificial intelligence / machine learning (AIML) service enablement server entity, comprising:receiving (302) , from an application server entity, an AIML service lifecycle assistance request or an AIML service lifecycle assistance update request; andsending (304) , to the application server entity, an AIML service lifecycle assistance response or an AIML service lifecycle assistance update response,wherein the AIML service lifecycle assistance request and / or the AIML service lifecycle assistance update request comprises at least one of:a vertical application layer (VAL) server identity (ID) ,a VAL service ID,a service client ID,a service client group ID,a service operation mode,a service model container,an address to fetch a service model,an address to send service model updates,a service optimization assistance mode, orservice incentive information.2.The method according to claim 1, wherein the service operation mode comprises at least one of:service start,service pause,service continue, orservice finish.3.The method according to claim 1 or 2, wherein the address to fetch a service model comprises a uniform resource identifier (URI) to fetch the service model, and / or wherein the address to send service model updates comprises a URI to send service model updates.4.The method according to any of claims 1-3, wherein the service optimization assistance mode comprises at least one of energy-efficient optimization assistance mode and fast convergence optimization assistance mode.5.The method according to any of claims 1-4, wherein the service incentive information comprises at least one of an incentive and an incentive delivery mode.6.The method according to claim 5, wherein the incentive comprises at least one of an application-oriented incentive and a network-oriented incentive.7.The method according to claim 5 or 6, wherein the incentive delivery mode indicates when to deliver the incentive.8.The method according to any of claims 1-7, further comprising:sending (312) , to an AIML service enablement client entity, an AIML enablement client service operation request based on a service client ID or a service client group ID; andreceiving (314) , from the AIML service enablement client entity, an AIML enablement client service operation response.9.The method according to claim 8, wherein the AIML enablement client service operation request comprises at least one of:a service client ID,a service operation mode,a service model,service transport protocol information,an address to send service model updates, ora service application-oriented incentive.10.The method according to claim 8 or 9, wherein the AIML enablement client service operation response comprises information indicating a result of the AIML enablement client service operation.11.The method according to any of claims 1-10, wherein the AIML service lifecycle assistance response comprises at least one of a service operation identifier and a status of the service and / or wherein the AIML service lifecycle assistance update response comprises at least one of an update result and an associated service operation identifier.12.The method according to any of claims 1-11, further comprising:interacting (402) with a network for configuring a network-oriented incentive.13.The method according to claim 12, wherein interacting with a network for configuring a network-oriented incentive comprises:interacting with a network for configuring a network-oriented incentive based on an incentive delivery mode.14.The method according to any of claims 1-13,wherein the application server entity comprises a VAL server.15.A method (500) performed by an application server entity, comprising:sending (502) , to an artificial intelligence / machine learning (AIML) service enablement server entity, an AIML service lifecycle assistance request or an AIML service lifecycle assistance update request; andreceiving (504) , from the AIML service enablement server entity, an AIML service lifecycle assistance response or an AIML service lifecycle assistance update response,wherein the AIML service lifecycle assistance request and / or the AIML service lifecycle assistance update request comprises at least one of:a vertical application layer (VAL) server identity (ID) ,a VAL service identifier,a service client ID,a service client group ID,a service operation mode,a service model container,an address to fetch a service model,an address to send service model updates,a service optimization assistance mode, orservice incentive information.16.The method according to claim 15, wherein the service operation mode comprises at least one of:service start,service pause,service continue, orservice finish.17.The method according to claim 15 or 16, wherein the address to fetch a service model comprises a uniform resource identifier (URI) to fetch the service model, and / or wherein the address to send service model updates comprises a URI to send service model updates.18.The method according to any of claims 15-17, wherein the service optimization assistance mode comprises at least one of energy-efficient optimization assistance mode and fast convergence optimization assistance mode.19.The method according to any of claims 15-18, wherein the service incentive information comprises at least one of an incentive and an incentive delivery mode.20.The method according to claim 19, wherein the incentive comprises at least one of an application-oriented incentive and a network-oriented incentive.21.The method according to claim 19 or 20, wherein the incentive delivery mode indicates when to deliver the incentive.22.The method according to any of claims 15-21, wherein the AIML service lifecycle assistance response comprises at least one of a service operation identifier and a status of the service and / or wherein the AIML service lifecycle assistance update response comprises at least one of an update result and an associated service operation identifier.23.The method according to any of claims 15-22,wherein the application server entity comprises a VAL server.24.A method (600) performed by an artificial intelligence / machine learning (AIML) service enablement client entity, comprising:receiving (602) , from an AIML service enablement server entity, an AIML enablement client service operation request to manage an AIML service operation lifecycle; andsending (604) , to the AIML service enablement server entity, an AIML enablement client service operation response,wherein the AIML enablement client service operation request comprises at least one of:a service client ID,a service operation mode,a service model,service transport protocol information,an address to send service model updates, ora service application-oriented incentive.25.The method according to claim 24, wherein the service operation mode comprises at least one of:service start,service pause,service continue, orservice finish.26.The method according to claim 24 or 25, wherein the address to send service model updates comprises a URI to send service model updates.27.The method according to any of claims 24-26, wherein the AIML enablement client service operation response comprises information indicating a result of the AIML enablement client service operation.28.An artificial intelligence / machine learning (AIML) service enablement server entity (700) , comprising:a processor (721) ; anda memory (722) coupled to the processor (721) , said memory (722) containing instructions executable by said processor (721) , whereby said AIML service enablement server entity (700) is operative to:receive, from an application server entity, an AIML service lifecycle assistance request or an AIML service lifecycle assistance update request; andsend, to the application server entity, an AIML service lifecycle assistance response or an AIML service lifecycle assistance update response,wherein the AIML lifecycle assistance request and / or the AIML lifecycle assistance update request comprises at least one of:a vertical application layer (VAL) server identity (ID) ,a VAL service ID,a service client ID,a service client group ID,a service operation mode,a service model container,an address to fetch a service model,an address to send service model updates,a service optimization assistance mode, orservice incentive information.29.The AIML service enablement server entity according to claim 28, wherein the AIML service enablement server entity is further operative to perform the method of any one of claims 2 to 14.30.An application server entity (700) , comprising:a processor (721) ; anda memory (722) coupled to the processor (721) , said memory (722) containing instructions executable by said processor (721) , whereby said application server entity (700) is operative to:send, to an artificial intelligence / machine learning (AIML) service enablement server entity, an AIML service lifecycle assistance request or an AIML service lifecycle assistance update request; andreceive, from the AIML service enablement server entity, an AIML service lifecycle assistance response or an AIML service lifecycle assistance update response,wherein the AIML service lifecycle assistance request and / or the AIML service lifecycle assistance update request comprises at least one of:a vertical application layer (VAL) server identity (ID) ,a VAL service identifier,a service client ID,a service client group ID,a service operation mode,a service model container,an address to fetch a service model,an address to send service model updates,a service optimization assistance mode, orservice incentive information.31.The application server entity according to claim 30, wherein the application server entity is further operative to perform the method of any one of claims 16 to 23.32.An artificial intelligence / machine learning (AIML) service enablement client entity (700) , comprising:a processor (721) ; anda memory (722) coupled to the processor (721) , said memory (722) containing instructions executable by said processor (721) , whereby said service enablement client entity (700) is operative to:receive, from an AIML service enablement server entity, an AIML enablement client service operation request to manage an AIML service operation lifecycle; andsend, to the AIML service enablement server entity, an AIML enablement client service operation response,wherein the AIML enablement client service operation request comprises at least one of:a service client ID,a service operation mode,a service model,service transport protocol information,an address to send service model updates, ora service application-oriented incentive.33.The AIML service enablement client entity according to claim 32, wherein the AIML service enablement client entity is further operative to perform the method of any one of claims 25 to 27.34.A computer-readable storage medium storing instructions which when executed by at least one processor, cause the at least one processor to perform the method according to any one of claims 1 to 27.35.A computer program product comprising instructions which when executed by at least one processor, cause the at least one processor to perform the method according to any one of claims 1 to 27.
Citation Information
Patent Citations
Enhancing wireless communication efficiency in 5G / 6G networks through AI / ML model management and deployment
CN117750356A
Management method of machine learning model for network data analytics function device
US20220108214A1
Software Lifecycle Management For A Storage System
US20220391124A1
Methods and apparatus for enhanced lifecycle management in 5g edge computing servers
WO2023018727A1