CN117813846A

CN117813846A - Apparatus, method and computer program

Info

Publication number: CN117813846A
Application number: CN202180101559.1A
Authority: CN
Inventors: T·苏布拉曼亚; H·桑内科; J·阿利-托尔帕; 平静; I·亚当
Original assignee: Nokia Shanghai Bell Co Ltd; Nokia Solutions and Networks Oy
Current assignee: Nokia Shanghai Bell Co Ltd; Nokia Solutions and Networks Oy
Priority date: 2021-08-10
Filing date: 2021-08-10
Publication date: 2024-04-02
Also published as: WO2023015448A1

Abstract

An apparatus comprising means configured to: facilitating cross-domain network service related machine learning or artificial intelligence pipeline reliability functionality, wherein the cross-domain machine learning or artificial intelligence pipeline is used to control a cognitive autonomous network comprising at least two domains.

Description

Apparatus, method and computer program

Technical Field

The present disclosure relates to apparatus, methods and computer programs for providing a framework for cross-domain trusted artificial intelligence applications applicable to, but not exclusively, cognitive autonomous networks.

Background

A communication system may be considered a facility that enables communication sessions between two or more entities, such as communication devices, base stations, and/or other nodes, by providing carriers between the various entities involved in a communication path.

The communication system may be a wireless communication system. Examples of wireless systems include Public Land Mobile Networks (PLMNs) operating based on radio standards such as those provided by 3GPP, satellite-based communication systems, and different wireless local area networks (e.g., wireless Local Area Networks (WLANs)). A wireless system may be generally divided into cells and is therefore generally referred to as a cellular system.

Communication systems and associated devices typically operate in accordance with a given standard or specification which sets out what the various entities associated with the system are permitted to do and how that should be achieved. Communication protocols and/or parameters which should be used for the connection are also typically defined. An example of a standard is the so-called 5G standard.

It is desirable to provide a control system that enables a Communication Service Provider (CSP) to control and optimize a complex network of communication system elements.

One of the current methods employed is closed loop automation and machine learning, which can be built into self-organizing networks (SON), enabling operators to automatically optimize each cell in the radio access network.

Disclosure of Invention

According to a first aspect, there is provided an apparatus comprising means configured to facilitate a cross-domain network service related machine learning or artificial intelligence pipeline reliability function, wherein the cross-domain machine learning or artificial intelligence pipeline is for control of a cognitive autonomous network comprising at least two domains.

The means configured to facilitate cross-domain network service related machine learning or artificial intelligence pipeline reliability functionality may be configured to facilitate at least one of the following, wherein the cross-domain machine learning or artificial intelligence pipeline is for control of a cognitive autonomous network comprising at least two domains: defining machine learning or artificial intelligent pipeline credibility related to the cross-domain network service; configuring machine learning or artificial intelligent pipeline credibility related to the cross-domain network service; measuring the reliability of machine learning or artificial intelligent pipelines related to the cross-domain network service; and reporting machine learning or artificial intelligence pipeline trustworthiness associated with the cross-domain network service.

The cross-domain network service related machine learning or artificial intelligence pipeline reliability function may include at least one of: fairness; an interpretability; and robustness.

The means configured to facilitate cross-domain network service related machine learning or artificial intelligence pipeline reliability functionality may be configured for use in controlling a cognitive autonomous network comprising at least two domains: obtaining cross-domain machine learning or artificial intelligence quality trustworthiness configured to: overlay domain specific machine learning or artificial intelligence quality reliability requirements, and cross-domain network service related machine learning or artificial intelligence pipeline constraints; converting the cross-domain machine learning or artificial intelligence quality trustworthiness to at least one domain-specific machine learning or artificial intelligence quality trustworthiness for at least one of the at least two domains; and providing at least one domain-specific machine learning or artificial intelligence quality confidence for at least one of the at least two domains.

The means configured to translate the cross-domain machine learning or artificial intelligence confidence quality into at least one domain-specific machine learning or artificial intelligence confidence quality for at least one of the at least two domains may be configured to translate the cross-domain machine learning or artificial intelligence confidence quality into the at least one domain-specific machine learning or artificial intelligence confidence quality based on a risk level of the cross-domain network service.

The means configured to translate the cross-domain machine learning or artificial intelligence confidence quality to at least one domain-specific machine learning or artificial intelligence confidence quality for at least one of the at least two domains may be configured to translate the cross-domain machine learning or artificial intelligence confidence quality to at least one domain-specific machine learning or artificial intelligence confidence quality based on at least one service level protocol requirement for the cross-domain network, wherein the at least one service level protocol comprises at least one of: a service type; service priority; and at least one key performance indicator metric.

The means configured to provide at least one domain-specific machine learning or artificial intelligence confidence quality for at least one of the at least two domains may be configured to: generating and communicating a cross-domain confidence machine learning or artificial intelligence configuration or delegation request to at least one domain-specific machine learning or artificial intelligence confidence function, the cross-domain confidence machine learning or artificial intelligence configuration or delegation request configured to control the at least one domain-specific machine learning or artificial intelligence confidence function to configure a machine learning or artificial intelligence pipeline for at least one of the at least two domains; and obtaining a cross-domain confidence machine learning or artificial intelligence configuration or delegated response from the at least one domain specific machine learning or artificial intelligence confidence function based on the implementation of the machine learning or artificial intelligence pipeline configuration for the at least one of the at least two domains.

The means configured to provide at least one domain-specific machine learning or artificial intelligence confidence quality for at least one of the at least two domains may be configured to: generating and communicating a cross-domain trustworthiness machine learning or artificial intelligence configuration or delegation request to at least one domain-specific policy manager, the cross-domain trustworthiness machine learning or artificial intelligence configuration or delegation request configured to control at least one domain-specific machine learning or artificial intelligence trustworthiness function to configure a machine learning or artificial intelligence pipeline for at least one of the at least two domains; and obtaining a cross-domain reliability machine learning or artificial intelligence configuration or delegated response from at least one domain policy manager based on the implementation of the machine learning or artificial intelligence pipeline configuration for at least one of the at least two domains.

The cross-domain trust machine learning or artificial intelligence configuration or delegation request may include: a domain scope parameter configured to identify a domain to which the request is addressing; a pipe identification parameter configured to identify a domain-specific machine learning or artificial intelligence pipe to which the request is addressing; a category identification parameter configured to identify the at least one domain-specific machine learning or artificial intelligence confidence quality.

The cross-domain trust machine learning or artificial intelligence configuration or delegation request may further include at least one of: a desired fairness parameter configured to indicate a relative fairness level for a domain-specific machine learning or artificial intelligence pipeline; a desired interpretive parameter configured to indicate a desired level of interpretive for a domain-specific machine learning or artificial intelligence pipeline; a desired technical robustness parameter configured to indicate a desired technical robustness level for a domain-specific machine learning or artificial intelligence pipeline; and a desired antagonism robustness parameter configured to indicate a desired antagonism robustness level for the domain-specific machine learning or artificial intelligence pipeline.

The means configured to facilitate cross-domain network service related machine learning or artificial intelligence pipeline reliability functionality may be configured for use in controlling a cognitive autonomous network comprising at least two domains: generating and communicating a cross-domain reliability machine learning or artificial intelligence capability information request to at least one domain-specific machine learning or artificial intelligence reliability function, the cross-domain reliability machine learning or artificial intelligence capability information request configured to control the at least one domain-specific machine learning or artificial intelligence reliability function to enable capability discovery of machine learning or artificial intelligence conduits for at least one of the at least two domains; and obtaining a cross-domain reliability machine learning or artificial intelligence capability information response from at least one domain specific machine learning or artificial intelligence reliability function, reporting capability discovery for a machine learning or artificial intelligence pipeline for at least one of the at least two domains.

The cross-domain reliability machine learning or artificial intelligence capability information request may include: a domain scope parameter configured to identify a domain to which the request is addressing; and a scope parameter configured to identify a domain-specific machine learning or artificial intelligence pipeline that the request is addressing.

The cross-domain reliability machine learning or artificial intelligence capability information request may also include pipeline stage parameters configured to identify the stage of the domain-specific machine learning or artificial intelligence pipeline that the request is addressing.

The means configured to facilitate cross-domain network service related machine learning or artificial intelligence pipeline reliability functionality may be further configured for use in a control of a cognitive autonomous network comprising at least two domains: obtaining a cross-domain credibility artificial intelligence report request or subscription from a network operator; generating and communicating domain-specific trust artificial intelligence report requests or subscriptions to at least one domain-specific machine learning or artificial intelligence pipeline trust function based on the cross-domain trust artificial intelligence report requests or subscriptions from network operators, wherein the domain-specific trust artificial intelligence report requests or subscriptions are configured to control the at least one domain-specific machine learning or artificial intelligence pipeline trust function to provide at least one domain-specific machine learning or artificial intelligence pipeline report response or notification; receiving machine learning or artificial intelligence capability information and/or at least one domain-specific machine learning or artificial intelligence pipeline report response or notification from at least one domain-specific machine learning or artificial intelligence pipeline reliability function; storing machine learning or artificial intelligence capability information and/or at least one domain-specific machine learning or artificial intelligence pipeline report received from at least one domain-specific machine learning or artificial intelligence pipeline in a cross-domain trust knowledge database; a cross-domain credibility artificial intelligence report is generated and delivered based on at least one domain specific machine learning or artificial intelligence pipeline report response or notification.

The cross-domain confidence artificial intelligence report request may include: a domain scope parameter configured to identify a domain to which the request is addressing; a scope parameter configured to identify a domain-specific machine learning or artificial intelligence pipeline that the request is addressing; and a pipeline stage parameter configured to identify a stage of domain-specific machine learning or artificial intelligence pipeline that the request is addressing. The cross-domain trust artificial intelligence report request may further comprise at least one of: a list of fairness metric parameters configured to identify a fairness metric to be reported; a list of fairness metric interpretations configured to identify a fairness metric interpretation to be reported; a list of interpretability metrics configured to identify an interpretability metric to be reported; a list of interpretations configured to identify an interpretation to be reported; a list of technical robustness metrics configured to identify technical robustness metrics to be reported; a list of technical robustness metric interpretations configured to identify a technical robustness metric interpretation to be reported; a list of robustness against metrics configured to identify robustness against metrics to be reported; a list of robust metric interpretations configured to identify robust metric interpretations to be reported; a start time parameter configured to identify a start time for reporting; an end time parameter configured to identify an end time for reporting; and a reporting interval parameter configured to identify a periodic interval for reporting.

Cross-domain credibility artificial intelligence report subscription may include: a domain-scope parameter configured to identify a domain to which the subscription is addressing; a scope parameter configured to identify a domain-specific machine learning or artificial intelligence pipeline to which the subscription is addressing; and a pipeline stage parameter configured to identify a stage of domain-specific machine learning or artificial intelligence pipeline that the subscription is addressing.

Cross-domain trust artificial intelligence report subscriptions may also include at least one of: a list of fairness metric parameters configured to identify a fairness metric to be reported; a list of interpretability metrics configured to identify an interpretability metric to be reported; a list of technical robustness metrics configured to identify technical robustness metrics to be reported; a list of robustness against metrics configured to identify robustness against metrics to be reported; and cross-reporting threshold parameters configured to identify thresholds for which metrics or metric interpretations are reported.

According to a second aspect, there is provided a method comprising: facilitating cross-domain network service related machine learning or artificial intelligence pipeline reliability functionality, wherein the cross-domain machine learning or artificial intelligence pipeline is used for control of a cognitive autonomous network comprising at least two domains.

Facilitating cross-domain network service related machine learning or artificial intelligence pipeline reliability functionality may include facilitating at least one of the following, wherein the cross-domain machine learning or artificial intelligence pipeline is for control of a cognitive autonomous network comprising at least two domains: defining machine learning or artificial intelligent pipeline credibility related to the cross-domain network service; configuring machine learning or artificial intelligent pipeline credibility related to the cross-domain network service; measuring the reliability of machine learning or artificial intelligent pipelines related to the cross-domain network service; and reporting machine learning or artificial intelligence pipeline trustworthiness associated with the cross-domain network service.

Facilitating cross-domain network service related machine learning or artificial intelligence pipeline reliability functions may include, among other things, cross-domain machine learning or artificial intelligence pipeline for control of a cognitive autonomous network comprising at least two domains: obtaining cross-domain machine learning or artificial intelligence quality trustworthiness configured to: overlay domain specific machine learning or artificial intelligence quality reliability requirements and cross-domain network service related machine learning or artificial intelligence pipeline constraints; converting the cross-domain machine learning or artificial intelligence quality trustworthiness to at least one domain-specific machine learning or artificial intelligence quality trustworthiness for at least one of the at least two domains; and providing at least one domain-specific machine learning or artificial intelligence quality confidence for at least one of the at least two domains.

Converting the cross-domain machine learning or artificial intelligence confidence quality to at least one domain-specific machine learning or artificial intelligence confidence quality for at least one of the at least two domains may include converting the cross-domain machine learning or artificial intelligence confidence quality to at least one domain-specific machine learning or artificial intelligence confidence quality based on a risk level of the cross-domain network service.

Converting the cross-domain machine learning or artificial intelligence confidence quality to at least one domain-specific machine learning or artificial intelligence confidence quality for at least one of the at least two domains may include converting the cross-domain machine learning or artificial intelligence confidence quality to at least one domain-specific machine learning or artificial intelligence confidence quality based on at least one service level protocol requirement for the cross-domain network, wherein the at least one service level protocol includes at least one of: a service type; service priority; and at least one key performance indicator metric.

Providing at least one domain-specific machine learning or artificial intelligence confidence quality for at least one of the at least two domains may include: generating and communicating a cross-domain confidence machine learning or artificial intelligence configuration or delegation request to at least one domain-specific machine learning or artificial intelligence confidence function, the cross-domain confidence machine learning or artificial intelligence configuration or delegation request configured to control the at least one domain-specific machine learning or artificial intelligence confidence function to configure a machine learning or artificial intelligence pipeline for at least one of the at least two domains; and obtaining a cross-domain confidence machine learning or artificial intelligence configuration or delegated response from the at least one domain specific machine learning or artificial intelligence confidence function based on the implementation of the machine learning or artificial intelligence pipeline configuration for the at least one of the at least two domains.

Providing at least one domain-specific machine learning or artificial intelligence confidence quality for at least one of the at least two domains may include: generating and communicating a cross-domain trustworthiness machine learning or artificial intelligence configuration or delegation request to at least one domain-specific policy manager, the cross-domain trustworthiness machine learning or artificial intelligence configuration or delegation request configured to control at least one domain-specific machine learning or artificial intelligence trustworthiness function to configure a machine learning or artificial intelligence pipeline for at least one of the at least two domains; and obtaining a cross-domain reliability machine learning or artificial intelligence configuration or delegated response from at least one domain policy manager based on the implementation of the machine learning or artificial intelligence pipeline configuration for at least one of the at least two domains.

Facilitating cross-domain network service related machine learning or artificial intelligence pipeline reliability functions may include, among other things, cross-domain machine learning or artificial intelligence pipeline for control of a cognitive autonomous network comprising at least two domains: generating and communicating a cross-domain reliability machine learning or artificial intelligence capability information request to at least one domain-specific machine learning or artificial intelligence reliability function, the cross-domain reliability machine learning or artificial intelligence capability information request configured to control the at least one domain-specific machine learning or artificial intelligence reliability function to enable capability discovery of machine learning or artificial intelligence conduits for at least one of the at least two domains; and obtaining a cross-domain reliability machine learning or artificial intelligence capability information response from at least one domain specific machine learning or artificial intelligence reliability function, reporting capability discovery for a machine learning or artificial intelligence pipeline for at least one of the at least two domains.

Facilitating cross-domain network service related machine learning or artificial intelligence pipeline reliability functions may also include, wherein the cross-domain machine learning or artificial intelligence pipeline is for control of a cognitive autonomous network comprising at least two domains: obtaining a cross-domain credibility artificial intelligence report request or subscription from a network operator; generating and communicating domain-specific trust artificial intelligence report requests or subscriptions to at least one domain-specific machine learning or artificial intelligence pipeline trust function based on the cross-domain trust artificial intelligence report requests or subscriptions from network operators, wherein the domain-specific trust artificial intelligence report requests or subscriptions are configured to control the at least one domain-specific machine learning or artificial intelligence pipeline trust function to provide at least one domain-specific machine learning or artificial intelligence pipeline report response or notification; receiving machine learning or artificial intelligence capability information and/or at least one domain-specific machine learning or artificial intelligence pipeline report response or notification from at least one domain-specific machine learning or artificial intelligence pipeline reliability function; storing machine learning or artificial intelligence capability information and/or at least one domain-specific machine learning or artificial intelligence pipeline report received from at least one domain-specific machine learning or artificial intelligence pipeline in a cross-domain trust knowledge database; a cross-domain credibility artificial intelligence report is generated and delivered based on at least one domain specific machine learning or artificial intelligence pipeline report response or notification.

According to a third aspect, there is provided an apparatus comprising at least one processor and at least one memory including computer code for one or more programs, the at least one memory and the computer code together with the at least one processor configured to cause the apparatus at least to: facilitating cross-domain network service related machine learning or artificial intelligence pipeline reliability functionality, wherein the cross-domain machine learning or artificial intelligence pipeline is used for control of a cognitive autonomous network comprising at least two domains.

The apparatus caused to facilitate cross-domain network service related machine learning or artificial intelligence pipeline reliability functionality may be caused to facilitate at least one of control of a cognitive autonomous network comprising at least two domains: defining machine learning or artificial intelligent pipeline credibility related to the cross-domain network service; configuring machine learning or artificial intelligent pipeline credibility related to the cross-domain network service; measuring the reliability of machine learning or artificial intelligent pipelines related to the cross-domain network service; and reporting machine learning or artificial intelligence pipeline trustworthiness associated with the cross-domain network service.

The apparatus caused to facilitate cross-domain network service related machine learning or artificial intelligence pipeline reliability functionality may be caused to, wherein the cross-domain machine learning or artificial intelligence pipeline is for control of a cognitive autonomous network comprising at least two domains: obtaining cross-domain machine learning or artificial intelligence quality trustworthiness configured to: overlay domain specific machine learning or artificial intelligence quality reliability requirements and cross-domain network service related machine learning or artificial intelligence pipeline constraints; converting the cross-domain machine learning or artificial intelligence quality trustworthiness to at least one domain-specific machine learning or artificial intelligence quality trustworthiness for at least one of the at least two domains; and providing at least one domain-specific machine learning or artificial intelligence quality confidence for at least one of the at least two domains.

The apparatus caused to translate the cross-domain machine learning or artificial intelligence confidence quality into at least one domain-specific machine learning or artificial intelligence confidence quality for at least one of the at least two domains may be caused to translate the cross-domain machine learning or artificial intelligence confidence quality into the at least one domain-specific machine learning or artificial intelligence confidence quality based on a risk level of the cross-domain network service.

The apparatus caused to translate the cross-domain machine learning or artificial intelligence confidence quality to at least one domain-specific machine learning or artificial intelligence confidence quality for at least one of the at least two domains may be caused to translate the cross-domain machine learning or artificial intelligence confidence quality to at least one domain-specific machine learning or artificial intelligence confidence quality based on at least one service level protocol requirement for the cross-domain network, wherein the at least one service level protocol comprises at least one of: a service type; service priority; and at least one key performance indicator metric.

The apparatus caused to provide at least one domain-specific machine learning or artificial intelligence confidence quality for at least one of the at least two domains may be caused to: generating and communicating a cross-domain confidence machine learning or artificial intelligence configuration or delegation request to at least one domain-specific machine learning or artificial intelligence confidence function, the cross-domain confidence machine learning or artificial intelligence configuration or delegation request configured to control the at least one domain-specific machine learning or artificial intelligence confidence function to configure a machine learning or artificial intelligence pipeline for at least one of the at least two domains; and obtaining a cross-domain confidence machine learning or artificial intelligence configuration or delegated response from the at least one domain specific machine learning or artificial intelligence confidence function based on the implementation of the machine learning or artificial intelligence pipeline configuration for the at least one of the at least two domains.

The apparatus caused to provide at least one domain-specific machine learning or artificial intelligence confidence quality for at least one of the at least two domains may be caused to: generating and communicating a cross-domain trustworthiness machine learning or artificial intelligence configuration or delegation request to at least one domain-specific policy manager, the cross-domain trustworthiness machine learning or artificial intelligence configuration or delegation request configured to control at least one domain-specific machine learning or artificial intelligence trustworthiness function to configure a machine learning or artificial intelligence pipeline for at least one of the at least two domains; and obtaining a cross-domain reliability machine learning or artificial intelligence configuration or delegated response from at least one domain policy manager based on the implementation of the machine learning or artificial intelligence pipeline configuration for at least one of the at least two domains.

The apparatus caused to facilitate cross-domain network service related machine learning or artificial intelligence pipeline reliability functionality may be caused to, wherein the cross-domain machine learning or artificial intelligence pipeline is for control of a cognitive autonomous network comprising at least two domains: generating and communicating a cross-domain reliability machine learning or artificial intelligence capability information request to at least one domain-specific machine learning or artificial intelligence reliability function, the cross-domain reliability machine learning or artificial intelligence capability information request configured to control the at least one domain-specific machine learning or artificial intelligence reliability function to enable capability discovery of machine learning or artificial intelligence conduits for at least one of the at least two domains; and obtaining a cross-domain reliability machine learning or artificial intelligence capability information response from at least one domain specific machine learning or artificial intelligence reliability function, reporting capability discovery for a machine learning or artificial intelligence pipeline for at least one of the at least two domains.

The apparatus caused to facilitate cross-domain network service related machine learning or artificial intelligence pipeline reliability functions may also be caused to, wherein the cross-domain machine learning or artificial intelligence pipeline is for control of a cognitive autonomous network comprising at least two domains: obtaining a cross-domain credibility artificial intelligence report request or subscription from a network operator; generating and communicating domain-specific trust artificial intelligence report requests or subscriptions to at least one domain-specific machine learning or artificial intelligence pipeline trust function based on the cross-domain trust artificial intelligence report requests or subscriptions from network operators, wherein the domain-specific trust artificial intelligence report requests or subscriptions are configured to control the at least one domain-specific machine learning or artificial intelligence pipeline trust function to provide at least one domain-specific machine learning or artificial intelligence pipeline report response or notification; receiving machine learning or artificial intelligence capability information and/or at least one domain-specific machine learning or artificial intelligence pipeline report response or notification from at least one domain-specific machine learning or artificial intelligence pipeline reliability function; storing machine learning or artificial intelligence capability information and/or at least one domain-specific machine learning or artificial intelligence pipeline report received from at least one domain-specific machine learning or artificial intelligence pipeline in a cross-domain trust knowledge database; a cross-domain credibility artificial intelligence report is generated and delivered based on at least one domain specific machine learning or artificial intelligence pipeline report response or notification.

The cross-domain confidence artificial intelligence report request may include: a domain scope parameter configured to identify a domain to which the request is addressing; a scope parameter configured to identify a domain-specific machine learning or artificial intelligence pipeline that the request is addressing; and a pipeline stage parameter configured to identify a stage of domain-specific machine learning or artificial intelligence pipeline that the request is addressing.

The cross-domain trust artificial intelligence report request may further comprise at least one of: a list of fairness metric parameters configured to identify a fairness metric to be reported; a list of fairness metric interpretations configured to identify a fairness metric interpretation to be reported; a list of interpretability metrics configured to identify an interpretability metric to be reported; a list of interpretations configured to identify an interpretation to be reported; a list of technical robustness metrics configured to identify technical robustness metrics to be reported; a list of technical robustness metric interpretations configured to identify a technical robustness metric interpretation to be reported; a list of robustness against metrics configured to identify robustness against metrics to be reported; a list of robust metric interpretations configured to identify robust metric interpretations to be reported; a start time parameter configured to identify a start time for reporting; an end time parameter configured to identify an end time for reporting; and a reporting interval parameter configured to identify a periodic interval for reporting.

According to a fourth aspect, an apparatus is provided comprising circuitry configured to facilitate a cross-domain network service related machine learning or artificial intelligence pipeline reliability function, wherein the cross-domain machine learning or artificial intelligence pipeline is for control of a cognitive autonomous network comprising at least two domains.

According to a fifth aspect, there is provided a computer program comprising computer executable code which, when run on at least one processor, is configured to: facilitating cross-domain network service related machine learning or artificial intelligence pipeline reliability functionality, wherein the cross-domain machine learning or artificial intelligence pipeline is used for control of a cognitive autonomous network comprising at least two domains.

According to a sixth aspect, there is provided a computer program [ or a computer readable medium comprising program instructions ] comprising instructions for causing an apparatus to perform at least the following: facilitating cross-domain network service related machine learning or artificial intelligence pipeline reliability functionality, wherein the cross-domain machine learning or artificial intelligence pipeline is used for control of a cognitive autonomous network comprising at least two domains.

According to a seventh aspect, there is provided a non-transitory computer readable medium comprising program instructions for causing an apparatus to perform at least the following: facilitating cross-domain network service related machine learning or artificial intelligence pipeline reliability functionality, wherein the cross-domain machine learning or artificial intelligence pipeline is used for control of a cognitive autonomous network comprising at least two domains.

According to an eighth aspect, there is provided a non-transitory computer readable medium comprising program instructions for causing an apparatus to perform at least the following: facilitating cross-domain network service related machine learning or artificial intelligence pipeline reliability functionality, wherein the cross-domain machine learning or artificial intelligence pipeline is used for control of a cognitive autonomous network comprising at least two domains.

According to a ninth aspect, there is provided a computer readable medium comprising program instructions for causing an apparatus to perform at least the following: facilitating cross-domain network service related machine learning or artificial intelligence pipeline reliability functionality, wherein the cross-domain machine learning or artificial intelligence pipeline is used for control of a cognitive autonomous network comprising at least two domains.

An apparatus comprising means for performing the actions of the method as described above.

An apparatus configured to perform the actions of the method as described above.

A computer program comprising program instructions for causing a computer to perform the method as described above.

A computer program product stored on a medium, capable of causing an apparatus to perform the methods described herein.

An electronic device may comprise an apparatus as described herein.

A chipset may comprise an apparatus as described herein.

Embodiments of the present application aim to address the problems associated with the prior art.

In the foregoing, many different aspects have been described. It will be appreciated that additional aspects may be provided by a combination of any two or more of the above aspects.

Various other aspects are also described in the following detailed description and appended claims.

Abbreviation table

AI: artificial intelligence

CAN: cognitive autonomous network

CD: cross-domain

CN: core network

CNF: cognitive network function

CRUD: creation, reading, updating, deletion

CDSMD: cross-domain service management domain

CU: centralized unit

DU: distributed unit

E2E: end-to-end

E2ESMD: end-to-end service management domain

HLEG: high-level expert group

MANO: management and orchestration

MD: administrative domains

ML: machine learning

QCI: qoS class identifier

QoE: quality of experience

QoS: quality of service

QoT: confidence quality

RAN: radio access network

RRU: remote radio unit

SLA: service level agreement

TAI: trusted artificial intelligence

TAIF: TAI framework

TN: transport network

UMTS: universal mobile telecommunication system

URLLC: ultra-reliable low latency communications

VNF: virtual network function

V2X: all of the vehicles

WI: work item

3GPP: third generation partnership project

5G: fifth generation of

5GC: 5G core network

5GS: 5G system

Drawings

Embodiments will now be described, by way of example only, with reference to the accompanying drawings, in which:

fig. 1 shows a schematic diagram of a 5G communication system;

fig. 2 shows a schematic diagram of a control device;

fig. 3 shows a schematic diagram of a terminal;

FIG. 4 shows a schematic diagram of an artificial intelligence/machine learning pipeline;

FIG. 5 illustrates a schematic diagram of an example of a trusted artificial intelligence framework for a cognitive autonomous network;

FIG. 6 illustrates a workflow diagram for an example trusted artificial intelligence framework for a cognitive autonomous network as shown in FIG. 5;

FIG. 7 illustrates a schematic diagram of an example cross-domain management and orchestration architecture utilizing a domain-specific trusted artificial intelligence framework;

FIG. 8 illustrates a schematic diagram of an example cross-domain management and orchestration architecture utilizing a domain-specific trusted artificial intelligence framework, according to some embodiments;

FIG. 9 illustrates a workflow diagram of an example cross-domain trusted artificial intelligence application programming interface provided by a domain-specific artificial intelligence trust engine to a cross-domain artificial intelligence trust engine; and

Fig. 10 shows a schematic diagram of a non-volatile storage medium storing instructions that, when executed by a processor, allow the processor to perform one or more steps of the methods described herein.

Detailed Description

Certain embodiments are explained below with reference to a mobile communication device capable of communicating via a wireless cellular system and a mobile communication system serving such a mobile communication device. Before explaining the exemplary embodiments in detail, certain general principles of a wireless communication system, its access system, and a mobile communication device are briefly explained with reference to fig. 1, 2, and 3 to help understand the techniques behind the described examples.

Fig. 1 shows a schematic diagram of a 5G system (5 GS). The 5GS may include a terminal, (radio) access network ((R) AN), a 5G core network (5 GC), one or more Application Functions (AFs), and one or more Data Networks (DNs).

The 5G (R) AN may include one or more gNodeB (gNB) Distributed Unit (DU) functions connected to one or more gNodeB (gNB) Centralized Unit (CU) functions.

The 5GC may include an access and mobility management function (AMF), a Session Management Function (SMF), an authentication server function (AUSF), user Data Management (UDM), a User Plane Function (UPF), a Network Exposure Function (NEF), and/or other Network Functions (NF) not shown, such as an Operation Administration and Maintenance (OAM) NF.

Fig. 2 illustrates AN example of a control apparatus 200 for controlling the functions of the (R) AN or 5GC shown in fig. 1. The control means may comprise at least one Random Access Memory (RAM) 211a, at least one Read Only Memory (ROM) 211b, at least one processor 212, 213 and an input/output interface 214. At least one processor 212, 213 may be coupled to the RAM 211a and the ROM 211b. The at least one processor 212, 213 may be configured to execute suitable software code 215. The software code 215 may, for example, allow one or more steps to be performed to perform one or more of the present aspects. The software code 215 may be stored in the ROM 211b. The control device 200 may be interconnected with another control device 200 that controls another function of the 5G (R) AN or 5 GC. In some embodiments, each function of the (R) AN or 5GC includes the control device 200. In alternative embodiments, two or more functions of the (R) AN or 5GC may share the control means.

Fig. 3 shows an example of a terminal 300, such as the terminal shown in fig. 1. The terminal 300 may be provided by any device capable of transmitting and receiving radio signals. Non-limiting examples include user equipment, mobile Stations (MSs) or mobile devices such as mobile phones or so-called "smartphones", computers provided with wireless interface cards or other wireless interface facilities (e.g. USB dongles), personal Data Assistants (PDAs) or tablet computers provided with wireless communication capabilities, machine Type Communication (MTC) devices, cellular internet of things (CIoT) devices or any combination of these devices, etc. The terminal 300 may provide communication, for example, for carrying data for the communication. The communication may be one or more of voice, electronic mail (email), text messages, multimedia, data, machine data, and the like.

The terminal 300 may receive signals over the air or radio interface 307 via suitable means for receiving and may emit signals via suitable means for emitting radio signals. In fig. 3, the transceiver device is schematically designated by block 306. The transceiver means 306 may be provided, for example, by a radio part and an associated antenna arrangement. The antenna arrangement may be arranged inside or outside the mobile device.

The terminal 300 may be provided with at least one processor 301, at least one memory ROM 302a, at least one RAM 302b and possibly other components 303 for use in software and hardware assisted execution of tasks it is designed to perform, including control of access to and communication with access systems and other communication devices. At least one processor 301 is coupled to RAM 302b and ROM 302a. The at least one processor 301 may be configured to execute suitable software code 308. The software code 308 may, for example, allow for execution of one or more of the present aspects. Software code 308 may be stored in ROM 302a.

The processor, memory and other related control means may be provided on a suitable circuit board and/or in a chipset. This feature is indicated by reference numeral 304. The device may optionally have a user interface such as a keypad 305, a touch sensitive screen or pad, combinations thereof, and the like. Optionally, one or more of a display, a speaker and a microphone may be provided depending on the type of device.

As previously described, closed loop automation and Machine Learning (ML) (also known as artificial intelligence or AI) may be built into a self-organizing network (SON) or a Cognitive Autonomous Network (CAN) enabling an operator to automatically optimize each cell in a radio access network.

Artificial Intelligence (AI) or Machine Learning (ML) pipelines help automate AI/ML workflows by splitting the AI/ML workflow into independent, reusable and modular components, and then connecting these components together through the pipeline to create a model. The AI/ML pipeline is iterative, with each step repeated to continually improve the accuracy of the model.

As shown in FIG. 4, the example AI/ML workflow includes the following three components:

the data source manager 403. The data source manager 403 is configured to implement functions such as data collection and data preparation.

Model training manager 405. Model training manager 405 is configured to implement functions such as hyper-parameter adjustment.

The model reasoning manager 407. The model inference manager 407 is configured to implement functions such as model evaluation.

With AI/ML pipelining and recent push to micro-service architecture (e.g., containers), each AI/ML workflow component is abstracted into an independent service that related stakeholders (e.g., data engineers, data scientists) can independently handle. In addition, the AI/ML pipeline orchestrator 401 (an example of which is provided by Kubeflow) may manage the lifecycle of the AI/ML pipeline. For example, manage various phases in the debug, extend, retirement lifecycle.

In order for AI/ML systems to be widely accepted, they should be trusted in addition to their performance (e.g., accuracy). Legal authorities are proposing a framework for AI/ML applications, for example the european commission has proposed the first legal framework for AI since a history. The legal framework exposes new rules that are trusted for AI's, as well as rules that AI-based mission critical systems must follow in the near future. The advanced expert group (HLEG) group on AI has developed Trusted AI (TAI) strategies of the european union committee. In the deliverable effort "Ethics Guidelines for Trustworthy AI" published in 2019, month 4, the group has listed seven key requirements that the AI system should meet to be considered trusted. The following are requirements:

transparency. Transparency requirements include traceability, interpretability, and communication.

Diversity, non-discrimination, and fairness. This requirement includes avoiding unfair bias, accessibility and generic design and stakeholder participation.

Technical robustness and security. The requirements include protection against attacks and security, backup plans, and general security, accuracy, reliability, and reproducibility.

Privacy and data governance. The requirements include respecting privacy, data quality and integrity, and access to the data.

Accountability control. Accountability requirements include auditability, minimization and reporting of negative effects, trade-offs, and remediation.

Human institutions and supervision. Human motility and supervision requirements include basic rights, human motility and human supervision.

Social and environmental welfare. The requirements include sustainability and environmental friendliness, social impact, society and democracy.

In addition, the International organization for standardization and International electrotechnical Commission (ISO/IEC) has also issued technical reports on "Overview of trustworthiness in artificial intelligence". Early efforts of open source communities were also reflected in developing TAI frameworks/tools/libraries, such as IBM AI360, google Expandable AI, and TensorFlow Responsible AI.

In the following, we introduce some key TAI definitions/algorithms/metrics described in the AI/ML research community.

Fairness: fairness is the process of understanding the bias introduced in the data and ensuring that the model provides fair predictions across all population groups. It is important to apply fairness analysis across the entire artificial intelligence/machine learning pipeline, ensuring that the model is continuously reevaluated from a fairness and inclusion perspective. This is especially important when AI/ML is deployed in critical business processes that affect a wide range of end users. There are three broad methods for detecting deviations in the AI/ML model:

1. Pre-processing fairness-algorithms (such as re-weighting and different impact removers) are used to detect deviations in AI/ML training data.

2. In-process fairness—algorithms (such as bias remover and resistance deskew) are used to detect bias in AI/ML model generation.

3. Post-processing fairness—algorithms such as odds equalization and reject option classification are used to detect deviations in AI/ML model decisions.

Quantification of fairness—there are several metrics that measure personal and group fairness. Such as statistical parity differences, average odds differences, difference effects, and tayer's patches.

Interpretability: the interpretability of the AI/ML model refers to the tearing down of the black box model, which only predicts or suggests to the white box, which in fact gives details of the underlying mechanisms and patterns identified by the model for a particular dataset. There are several reasons why it is necessary to know the underlying mechanisms of the AI/ML model, such as human readability, rationality, interpretability, and bias relief. There are three broad approaches to design interpretable ML models:

1. interpretive of pre-modeling—understanding or describing data used to develop the AI/ML model. For example, algorithms such as ProtoDash and unwrap inference a priori variational automatic encoder interpreters are used.

2. Interpretable modeling/interpretable modeling-developing more interpretable AI/ML models, such as ML models with joint prediction and interpretation or alternative interpretable models. For example, algorithms such as generalized linear rule models and pedagogical interpretable decisions (TED) are used.

3. Post modeling interpretability—extract interpretation from a pre-developed AI/ML model. For example, algorithms such as ProtoDash, contrastive Explanations Method, profweight, LIME, and SHAP are used.

Furthermore, the interpretation may be local (i.e., interpreting a single instance/prediction) or global (i.e., interpreting a global AI/ML model structure/prediction, e.g., based on combining many local interpretations of each prediction).

Quantification of interpretability-although the quality of interpretation is ultimately determined by the consumer, the research community has proposed quantitative measures as agents for interpretability. There are several metrics that measure interpretability, such as faithfulness and monotonicity.

Robustness (to resistance): any AI/ML model developer/scientist needs to consider defending against and evaluating the four resistant threats of his AI/ML model and application.

1. Avoidance: evading attacks involves carefully disturbing the input samples at the time of testing so that they are misclassified. For example, techniques such as shadow attacks, threshold attacks are used.

2. Poisoning: poisoning is an antagonistic contamination of training data. The machine learning system may be retrained using data collected during operation. An attacker may poison the data by injecting malicious samples during operation, thereby breaking the retraining. For example, techniques such as back door attacks and resistive back door embedding are used.

3. Extracting: extraction attacks aim to replicate the machine learning model by querying the access target model. For example, techniques such as KnockoffNets and functionally equivalent extraction are used.

4. Reasoning: the inference attack determines whether a sample of data is used in the training dataset for the AI/ML model. For example, techniques such as membership inference black boxes and attribute inference black boxes are used.

In addition to robustness against resistance, AI/ML technology robustness needs to be addressed in other ways, such as handling missing data, erroneous data, data confidence, backup planning, etc.

At each stage of AI/ML design, there are a number of ways in which AI/ML models can be protected from such resistant attacks:

preprocessors-for example, using techniques such as invertersegan and safeagan.

Post-processor-e.g., using techniques such as inverted sigmoid and rounding.

Trainer-e.g., techniques using protocols such as general resistance training and Madry.

Transducers-for example, using techniques such as defensive distillation and nerve purification.

Detectors-for example, using techniques such as detection based on activation analysis and detection based on spectral features.

Quantization of robustness: there are several metrics that measure the robustness of the ML model, such as empirical robustness and loss sensitivity.

One example of a Trusted Artificial Intelligence Framework (TAIF) for Cognitive Autonomous Networks (CAN) to facilitate definition, configuration, monitoring and measurement of AI/ML model trustworthiness (e.g., fairness, interpretability, robustness) in interoperable and multi-vendor environments is shown in fig. 5, and additional details may be found in PCT/EP 2021/062396.

In this example, a network operator 501 is shown that is configured to pass information to a policy manager 533 and an AI trust engine 503.

Policy manager 533 is configured to receive information from network operator 501. Further, policy manager 533 is configured to receive or otherwise obtain service definitions or business/customer intents. In addition to network/AI quality of service (QoS) requirements, service definitions or business/customer intents may also include AI/ML reliability requirements, and TAIF is used to configure the requested AI/ML reliability and monitor and ensure its implementation.

Thus, for example, the system may include a service management and orchestration 527 function configured to receive quality of service (QoS) from policy manager 533. The service management and orchestration 527 is configured to control an element manager or Virtual Network Function (VNF) manager or resource manager 531 based on the output of the service management and orchestration function 527.

In addition, the system may include an AI pipeline orchestrator 525. The AI pipeline orchestrator 525 is configured to obtain or receive AIQoS from the policy manager 533 and, based thereon, and in a similar manner as shown with respect to fig. 4, to control the operation of the data source managers 509, 519, model training managers 511, 521, and model reasoning managers 513, 523 for the AI pipeline 1 505 and the AI pipeline 2 515.

The TAIF introduces two other management functions, an AI trust engine (trust function) 503 (one for each management domain) and AI trust managers 507, 617 (one for each AI/ML pipe 505, 515) and six new interfaces (T1-T6) configured to support interactions in the TAIF. The AI trust engine 503 is configured to act as a hub for managing all AI credibility related components in the network, while the AI trust manager 507, 517 is use case and typically vendor specific, with knowledge of the AI use case and how it is implemented.

In addition, the example TAIF also employs the concept of AI quality of trust (AIQoT) to define AI/ML model trustworthiness in a unified manner, covering three factors, namely fairness, interpretability, and robustness. The AIQoT is passed from the policy manager 533, for example, to the AI trust engine function 503 and is similar to how QoS is used for network performance.

An example QoT may be displayed by the following table

A high level general workflow in an example TAIF is shown in fig. 6.

In this example workflow, it is shown that the customer intent is provided to the policy manager function 533, as shown in step 601 in FIG. 6.

It is additionally shown that the network operator (via the policy manager function 533) specifies the required AIQoT (use case specific based on risk level) to the AI trust engine 503, e.g. over the T1 interface, as shown by step 603 in fig. 6.

The AI trust engine 503 translates the AIQoT into specific AI trust (i.e., fairness, interpretability, and robustness) requirements and identifies the use case specific AI trust manager(s) that are affected. Using the T2 interface, the AI trust engine 503 configures the AI trust manager 507, as shown by step 605 in fig. 6.

The use case specific and perceptually implemented AI trust manager 507 is configured to configure, monitor and measure AI trust requirements for the AI data source manager 509 over the T3 interface, as shown by step 607 in fig. 6.

In addition, the use case specific and perceptually implemented AI trust manager 507 is configured to configure, monitor and measure AI trust requirements for the AI training manager 511 over the T4 interface, as shown by step 609 in fig. 6.

In addition, the use case specific and perceptually implemented AI trust manager 507 is configured to configure, monitor and measure AI trust requirements for the AI inference manager 513 over the T5 interface, as shown by step 611 in fig. 6.

The measured or collected TAI metrics and/or TAI interpretations about the AI pipe from the AI data source manager 509, AI training manager 511, and AI reasoning manager 513 are pushed to the AI trust manager 507 over the T3, T4, and T5 interfaces, respectively, as shown by steps 613, 615, and 617, respectively, in fig. 6.

The AI trust manager 507 pushes TAI metrics and/or TAI interpretations to the AI trust engine 503 over the T2 interface based on reporting mechanisms configured by the AI trust engine (trust function), as shown by step 619 in fig. 6.

Finally, the network operator 501 may request (as shown by step 621 in fig. 6) and receive (as shown by step 623 in fig. 6) TAI metrics/interpretations of the AI pipe from the AI trust engine over the T6 interface.

Based on the obtained information, the network operator may decide to update the policy via the policy/intent manager, as shown by step 625 in fig. 6.

Thus, the example TAI framework enables various telecom stakeholders (e.g., cognitive network function providers, network operators, regulatory authorities, end users) to trust decisions/predictions made by AI/ML models in the network.

An example cross-domain management and orchestration architecture is also shown in fig. 7. This example shows a cross-domain end-to-end (E2E) network service scenario, but other cross-domain non-E2E scenarios (i.e., per domain) are possible. For example, the core domain may be recursively embedded with a 3GPP defined Network Function (NF) domain and a virtualization domain, and the RAN domain may include a Centralized Unit (CU), a Distributed Unit (DU), a Remote Radio Unit (RRU), and a mid-transmission and a forward-transmission domain provided by different providers.

In the example cross-domain E2E network service scenario shown in fig. 7, a cross-domain service management domain (CDSMD) (e.g., E2E service management domain) 705 is located between the cross-domain policy/intent manager 703 and the network operator 701, which is configured to control the cross-domain service MD 705 and the underlying domain management domain. For example, as shown in fig. 7, a (first) domain 1MD (e.g., RAN MD) 712, (second) domain 2MD (e.g., transport MD) 722, and (third) domain 3MD (e.g., core network MD) 732 are shown. The cross-domain service management domain (CDSMD) 705 is configured to decompose a cross-domain E2E network service request (according to a Service Level Agreement (SLA)) received from a network operator 701 or customer (e.g., via a cross-domain policy/intent manager 703) into domain-specific (e.g., RAN, transport, core) network resource/service requirements and to transfer them to corresponding individual Management Domains (MD) 712, 722, 732.

The individual MD 712, 722, 732 are also configured to be responsible for ensuring that domain-specific resource/service requirements are met within their corresponding domains by continuously monitoring and reporting Key Performance Indicators (KPIs) related to the resource/service to the CDSMD 705.

In the example shown in fig. 7, a (first) domain 1MD (e.g., RAN MD) 712 is shown. The (first) domain 1MD (e.g., RAN MD) 712 may also be controlled/monitored by a domain-specific policy/intention manager 711 (which is similar to the policy/intention manager shown in fig. 5 and 6). The (first) domain 1MD (e.g., RAN MD) 712 may include a domain 1AI trust engine 713 (or a trust function) and a domain 1AI pipe orchestrator 714, both of which manage and control domain 1AI pipe 1 715. The 1AI pipe 1 715 can then control or configure domain-specific aspects of the cross-domain network service 717, domain 1 resources (RAN resources 716).

Further, the example shown in fig. 7 shows a (second) domain 2MD (e.g., a transport MD) 722. The (second) domain 2md 722 may also be controlled/monitored by a domain-specific policy/intention manager 721 (which is similar to the policy/intention manager shown in fig. 5 and 6). The (second) domain 2md 722 may include a domain 2AI trust engine 723 (or a trust function) and a domain 2AI pipe orchestrator 724, both of which manage and control domain 2AI pipe 2 725. The domain 2AI pipe 2 725 may then control or configure domain-specific aspects of the cross-domain network service 717, domain 2 resources (transport resources 726).

In addition, as shown in the example of fig. 7, a (third) domain 3MD (e.g., core network MD) 732 may be employed. The (third) domain 3md 732 may also be controlled/monitored by a domain-specific policy/intent manager 731 (similar to the policy/intent manager shown in fig. 5 and 6). The (third) domain 3md 732 may include a domain 3AI trust engine 733 (or trust function) and a domain 3AI pipe orchestrator 734, both of which manage and control domain 3AI pipes 3 735. Domain 3AI pipe 3 735 may then control or configure domain-specific aspects of cross-domain network service 717, domain 3 resources (core network resources 736).

Thus, the requested/instantiated cross-domain E2E network services (e.g., overlay RAN, transport and core domains (represented by block 717)) are managed by their corresponding AI pipes (or CNFs) in the respective MD (represented by blocks 715, 725, 735). It is noted that the AI pipe may be instantiated in a domain-specific MD (e.g., for active resource auto-scaling) or within the domain itself (e.g., for active mobility handover in the RAN domain), depending on the use case. Then, using a domain-specific AI trust engine (trust function) and a specific AI trust manager (as described and referenced above) of the AI pipe, AI pipe trust (i.e., AIQoT including fairness, interpretability, robustness) for that domain-specific AI pipe can be defined, configured, measured, and reported within the corresponding MD.

However, the network as shown in fig. 7 may present problems because there is no management function in the CDSMD 703 that is configured to receive the desired cross-domain AIQoT for the cross-domain E2E network services (i.e., defined by the cross-domain policy/intent manager based on the risk level of the cross-domain E2E network services). Thus, CDSMD has no way to:

converting the cross-domain AIQoT into a domain-specific AIQoT;

discovering TAI capability information from the domain-specific AI trust engine(s);

transmitting the translated domain-specific AIQoT to domain-specific AI trust engine(s); and

cross-domain TAI metrics/interpretations are collected/requested from domain-specific AI trust engine(s).

Furthermore, even if this problem is solved, CDSMD cannot solve (e.g., perform root cause analysis) the TAI-related upgrades (i.e., in terms of TAI metrics/interpretations) received from domain-specific AI trust engine(s) belonging to the cross-domain E2E network service, and cannot delegate the relevant TAI-upgrade-related information received from domain-specific AI trust engine of one MD to another MD so that other MDs can take precautions to avoid cross-domain E2E network service SLA violations (in our case cross-domain AIQoT).

In addition, such a system cannot aggregate TAI-related upgrade metrics/interpretations received from the AI trust engine(s) of the individual MD in a manner to provide CDSMDs to provide a global view of the problem to the network operator or customer. In this example, the upgrade metrics/interpretations related to TAI may include cross-domain AIQoT violations.

The concept further discussed in the following embodiments is the introduction of a cross-domain TAI framework (which extends the domain-specific TAI framework discussed above and introduced for cognitive autonomous networks in PCT/EP2021/062396 to facilitate definition, configuration, measurement and reporting of artificial intelligent pipe trustworthiness (i.e. fairness, interpretability, robustness) related to cross-domain network services in interoperable and multi-provider environments).

In these embodiments, in addition to the cross-domain QoS requirements, the customer intent corresponding to the network service may also include cross-domain AI trust requirements, and a cross-domain TAI framework is used to ensure satisfaction of the desired cross-domain AI trust requirements.

As shown in fig. 8, the cross-domain TAI framework includes novel management functions, a cross-domain AI trust engine (trust function) 801 (trust function). In some embodiments, the cross-domain AI trust engine is employed within a cross-domain service management domain (CDSMD). Additionally, in some embodiments, a new interface (designated as TCD-1 in the example shown in fig. 8) 805 is implemented that is configured to support interactions between the cross-domain AI trust engine 801 and the domain-specific AI trust engines 813, 823, 833 (or trust functionality). Furthermore, in some embodiments, another new interface (designated TCD-2 in the example shown in fig. 8) is implemented between the cross-domain AI trust engine 801 and the domain-specific policy/intent manager 811, 821, 831.

Furthermore, in the embodiments described in detail herein, the concept of cross-domain AIQoT is introduced to define cross-domain AI trustworthiness in a uniform manner, covering domain-specific AIQoT requirements and constraints of AI pipes related to cross-domain network services.

In some embodiments, the cross-domain AI trust engine 801 is configured to support the following operations:

translating the cross-domain AIQoT requirements into domain specific AIQoT requirements (e.g., RAN domain AIQoT, transport domain AIQoT, and core domain AI QoT) depending on the risk level of the cross-domain network service;

the domain-specific AI trust engine is capable of discovery/determination of TAI methods and/or TAI metrics and/or TAI interpretations configured in a domain-specific AI pipeline belonging to a cross-domain network service;

verification of whether cross-domain AIQoT and/or domain-specific AIQoT requirements for cross-domain network services are met;

a configuration/delegation of desired/updated AIQoT (derived from cross-domain AIQoT) that the domain-specific AI trust engine needs to satisfy in a domain-specific AI pipe belonging to a cross-domain network service;

the domain-specific AI trust engines 813, 823, 833 are able to measure/report/upgrade TAI metrics and/or TAI-interpreted requests/subscriptions in domain-specific AI pipes belonging to a cross-domain network service;

Storing all TAI capability information and/or TAI reports received from the domain-specific AI trust engines 813, 823, 833 regarding domain-specific AI pipes 715, 725, 735 belonging to the cross-domain network service in a cross-domain trust knowledge database;

root cause analysis of TAI reports received from the domain-specific AI trust engines 813, 823, 833 is performed. Furthermore, if needed, updating domain-specific AIQoT requirements based on TAI reports;

the network operator is provided with a global view of the issues/upgrades for the cross-domain network services (e.g., aggregated cross-domain network service related TAI reports) -which in this example may be a cross-domain AIQoT violation.

In some embodiments, a cross-domain TAI API (which may be generated by and consumed by the domain-specific AI trust engine (s)) may be implemented. For example, these may be the following:

1. a cross-domain TAI capability discovery API (Req/Resp) -the cross-domain TAI capability discovery API is configured to allow a cross-domain AI trust engine to discover via a TCD-1 interface that a domain-specific AI trust engine is capable of configuring TAI methods and/or TAI metrics and/or TAI interpretations in a domain-specific AI pipe belonging to a cross-domain network service.

2. A cross-domain TAI configuration API or a cross-domain TAI delegation API (Req/Resp). The cross-domain TAI configuration API or cross-domain TAI delegation API is configured to allow the cross-domain AI trust engine to configure/delegate a desired/updated AIQoT (derived from the cross-domain AIQoT) that the domain-specific AI trust engine needs to satisfy in a domain-specific AI pipe belonging to the cross-domain network service via the TCD-1 interface. Alternatively, in some embodiments, the cross-domain TAI configuration API or cross-domain TAI delegation API is configured to allow the cross-domain AI trust engine to inform the domain-specific policy/intent manager (via the domain-specific AI trust engine) via the TCD-2 interface of the desired/updated AIQoT (derived from the cross-domain AIQoT) that is required to be configured in the domain-specific AI pipe belonging to the cross-domain network service.

3. A cross-domain TAI reporting API or a cross-domain TAI upgrading API (request/response and subscription/notification). The cross-domain TAI reporting API or cross-domain TAI upgrading API is configured to allow the cross-domain AI trust engine to request/subscribe to domain-specific AI trust engines via the TCD-1 interface to be able to measure/report/upgrade TAI metrics and/or TAI interpretations in domain-specific AI pipes belonging to the cross-domain network service.

FIG. 9 shows an example workflow diagram illustrating an implementation of a cross-domain AI trust engine 801 in accordance with some embodiments. In addition, the figure shows the application of the above-described APIs and is supplied by the domain-specific AI trust engine(s) over the TCD-1 interface to discover, configure, measure and query/collect TAI methods and/or TAI metrics and/or TAI interpretations from domain-specific AI pipes belonging to the cross-domain network service.

Further, additional example alternative implementations are shown showing interactions between the cross-domain AI trust engine and the domain-specific policy/intent manager through the TCD-2 interface.

As shown by step 901 in fig. 9, the network operator 701 notifies the cross-domain policy/intent manager 703 (within the cross-domain service management domain 705) of an intent for a cross-domain network service, for example, through a T1 interface.

The cross-domain policy/intent manager 703 is then configured to translate the intent for the cross-domain network service into a cross-domain AIQoT and notify the cross-domain AI trust engine 801, as shown in fig. 9, via step 903.

The cross-domain AI trust engine 801 may then be configured to translate the obtained cross-domain AIQoT requirements into domain-specific AIQoT requirements, as shown by step 905 in fig. 9. In other words, the cross-domain AI trust engine 801 is configured to generate parameters RAN domain AIQoT, transport domain AIQoT, and core domain AIQoT depending on the risk level of the cross-domain network service. The generation of parameters RAN domain AIQoT, transport domain AIQoT and core domain AIQoT depending on the risk level of the cross-domain network service may be expressed for example by the following table:

in some embodiments, the translation/mapping logic may consider SLA requirements (e.g., service type, service priority, KPI metrics) for the cross-domain network service, and optionally also domain-specific TAI capability information. In some embodiments, the conversion may be performed after step 911.

The operations of steps 907, 909, and 911 shown in fig. 9 may be implemented as part of a cross-domain TAI capability discovery API, as shown at reference numeral 906 in fig. 9.

For example, the cross-domain AI trust engine 801 may be configured to generate a cross-domain TAI capability information request (cdtaiicireq). As shown in fig. 9, a request may be sent from the cross-domain AI trust engine 801 to the domain-specific AI trust engine(s) via step 907. In this example, the domain-specific AI trust engine is RAN management domain 712AI trust engine 813. The request is for requesting information about the TAI methods and/or TAI metrics and/or TAI interpretations that the AI trust engine(s) 813 can configure in a domain-specific AI pipe belonging to a cross-domain network service.

In some embodiments, the example request (cdtaiicireq) includes the following parameters:

/>

in some embodiments, the domain-specific AI trust engine(s) (in this example, RAN management domain 712AI trust engine 813) is configured to determine all information requested in the received request (cdtaiicireq) by interacting with the domain-specific AI pipe as shown by step 907 in fig. 9. Interactions in this example are with RAN management domain 712, AI pipe 715 (e.g., AI trust manager 902, AI data source manager 903, AI training manager 904, AI reasoning manager 905) belonging to a cross-domain network service. The details of this operation may be implemented according to any suitable manner, for example as described in PCT/EP 2021/071044.

In some embodiments, the domain-specific AI trust engine (in this example, RAN management domain 712AI trust engine 813) sends a cross-domain TAI capability information response (cdtaiiciresp) back to the requesting cross-domain AI trust engine 801 as shown by step 911 in fig. 9. In some embodiments, the cross-domain TAI capability information response (cdtaiiciresp) includes information about supported TAI methods and/or TAI metrics and/or TAI-interpreted domain-specific AI pipes (belonging to a cross-domain network service).

In some embodiments, cdapircresp includes the following parameters:

/>

in some embodiments, the cross-domain AI trust engine is configured to store cross-domain TAI capability information within a cross-domain trust knowledge database. The database may be updated if there is a capability update in one of the domains.

In some embodiments, the cross-domain AI trust engine 801 is configured to determine that cross-domain AIQoT and/or domain-specific AIQoT requirements may be met based on the cross-domain TAI capability information response as shown by step 913 in fig. 9 or the cross-domain TAI capability information stored in the cross-domain trust knowledge database. Additionally, in some embodiments, the cross-domain AI trust engine 801 is configured to translate domain-specific AIQoT into fairness, interpretability, and robustness requirements, as previously shown and described, to determine cross-domain AIQoT and/or domain-specific AIQoT satisfaction results.

The cross-domain AI trust engine 801 may also be configured to generate and send (as shown by step 915 in fig. 9) a negative acknowledgement (cross-domain AIQoT NACK) to the cross-domain policy/intent manager 703 if the requirements cannot be met, as shown by step 915 in fig. 9. This is sent in response to the cross-domain AIQoT received from step 903.

The operations shown as steps 917, 919 and 921 in FIG. 9 illustrate a first alternative as part of a cross-domain TAI configuration API or a cross-domain TAI delegation API, as shown by reference numeral 916 in FIG. 9.

For example, a cross-domain TAI configuration/delegation (CRUD) request (cdtaicon req) is sent from the cross-domain AI trust engine 801 to the domain-specific AI trust engine(s), which in this example is the RAN management domain 712AI trust engine 813, to inform the translated domain-specific AIQoT that needs to be satisfied in the domain-specific AI pipe belonging to the cross-domain network service. This is shown in fig. 9 as step 917.

In some embodiments, the cross-domain AI trust engine 801 is configured to also translate domain-specific AIQoT into fairness, interpretability, and robustness requirements, as shown and described above, and include this information in the cross-domain TAI configuration/delegation (CRUD) request. In some embodiments, cdtaicon req includes the following parameters:

in some embodiments, the domain-specific AI trust engine is configured to configure corresponding (i.e., based on desired domain-specific AIQoT) fairness and/or interpretability and/or robustness methods/metrics/interpretations in domain-specific AI pipes belonging to the cross-domain network service based on the cross-domain TAI configuration/delegated CRUD request. This configuration is shown by step 919 in fig. 9. The implementation may be any suitable implementation, such as described in PCT/EP2021/071044, for example.

Depending on whether the configuration process in the previous step was successful, the domain-specific AI trust engine is configured to respond to the cross-domain AI trust engine with a cross-domain TAI fairness configuration/delegated CRUD response (cdtaicon resp). The response in some embodiments includes an ACK/NACK to satisfy a domain-specific AIQoT in a domain-specific AI pipe belonging to a cross-domain network service. The generation and transmission of this response is shown in fig. 9 by step 921.

The operations shown in fig. 9 as steps 923, 925, 927, 929 and 931 illustrate a second alternative as part of the cross-domain TAI configuration API or cross-domain TAI delegation API shown in fig. 9 as reference numeral 922.

The cross-domain AI trust engine is configured to generate and pass a cross-domain TAI configuration/delegation CRUD request (cdtaicon req) to the domain-specific policy/intention manager 811 to inform the domain-specific policy/intention manager 811 of the translated domain-specific AIQoT that needs to be satisfied in the domain-specific AI pipe belonging to the cross-domain network service. The operation of generating and delivering cdtaicon req is shown by step 923 in fig. 9. In some embodiments, cdtaicon req may include the following parameters:

the domain-specific policy/intent manager 811 is configured to send the desired AIQoT information to the domain-specific AI trust engine 813, as shown by step 925 in fig. 9.

The domain-specific AI trust engine 813 may then translate the AIQoT into fairness, interpretability, and robustness requirements based on the cross-domain TAI configuration/delegation CRUD request, and configure corresponding fairness and/or interpretability and/or robustness methods/metrics/interpretations in the domain-specific AI pipes belonging to the cross-domain network service. This configuration is shown by step 927 in fig. 9. The implementation may be any suitable implementation, such as described in PCT/EP2021/071044, for example.

The domain-specific AI trust engine 813 may then be configured to send an ACK/NACK to the domain-specific policy/intent manager 811 to satisfy the desired AIQoT in the domain-specific AI pipe belonging to the cross-domain network service. The operation of transmitting ACK/NACK is shown by step 929 in fig. 9.

Then, based on whether the domain-specific AIQoT is satisfied, the domain-specific policy/intent manager 811 is configured to respond to the cross-domain AI trust engine with a cross-domain TAI fairness configuration/delegation CRUD response (cdtaiiconrresp) containing an ACK/NACK for satisfying the domain-specific AIQoT in the domain-specific AI pipe belonging to the cross-domain network service. Generating and transmitting a cross-domain TAI fairness configuration/delegation CRUD response (cdtaicon resp) is shown in fig. 9 by step 931.

The operations shown in fig. 9 as steps 933, 935, 937, 939 and 941 illustrate an example cross-domain TAI reporting API or cross-domain TAI upgrading API implementation as shown in fig. 9 as reference numeral 932.

In some embodiments, domain-specific AI trust engine 933 is configured to collect TAI reports (metrics and/or interpretations) configured in step 919 or step 927 from domain-specific AI pipes belonging to cross-domain network services. The collection of reports is shown by step 933 in fig. 9. The implementation may be any suitable implementation, such as described in PCT/EP2021/071044, for example.

In some embodiments, the network operator 701 generates and communicates a request or subscription for cross-domain TAI reports, as shown by step 935 in fig. 9.

As shown by step 937 in fig. 9, a cross-domain TAI report request/subscription (CDTAIRReq/CDTAIRSub) is generated and sent from the cross-domain AI trust engine 801 to the domain-specific AI trust engine 813 of the report/subscription configuration belonging to the domain-specific AI pipe of the cross-domain network service. In some embodiments, CDTAIRReq includes the following parameters:

/>

in some embodiments, CDTAIRSub includes the following parameters:

/>

in some embodiments, the cross-domain AI trust engine may store the cross-domain TAI report within a cross-domain trust knowledge database.

In some embodiments, when one or more reporting characteristics (i.e., periodic or on-demand) are met, then the domain-specific AI trust engine 813 is configured to send a cross-domain TAI report response (TAIRResp) to the cross-domain AI trust engine 801 according to the reporting configuration specified in CDTAIRReq. In some embodiments, when the applicable TAI metrics meet one or more reporting thresholds, then the domain-specific AI trust engine 813 is configured to generate and send a cross-domain TAI report notification (tairno) message to the cross-domain AI trust engine 801 that includes the actual TAI report. The generation of a cross-domain TAI report response (TAIRResp) or cross-domain TAI report notification (tairno) is shown in fig. 9 by step 939.

The cross-domain AI trust engine 801 then performs root cause analysis of TAI reports from the domain-specific AI trust engine(s) and provides a global view of the problem with the cross-domain network service (e.g., aggregated cross-domain network service related TAI reports). For example, as shown by step 941 in fig. 9, a cross-domain AIQoT violation may be sent to the network operator 701. The aggregation logic may consider combining/aggregating data/training/reasoning-related local/global interpretations received from the AI trust engine of the individual domain(s).

Fig. 10 shows a schematic diagram of non-volatile storage media 1000a (e.g., a Computer Disk (CD) or a Digital Versatile Disk (DVD)) and 1000b (e.g., a Universal Serial Bus (USB) memory stick) storing instructions and/or parameters 1002 that, when executed by a processor, allow the processor to perform one or more steps of the methods described above.

Note that while the above describes example embodiments, various changes and modifications may be made to the disclosed solution without departing from the scope of the invention.

It should be appreciated that although the concepts described above have been discussed in the context of 5GS, one or more of these concepts may be applied to other cellular systems.

The embodiments may thus vary within the scope of the attached claims. In general, some embodiments may be implemented in hardware or special purpose circuits, software, logic or any combination thereof. For example, some aspects may be implemented in hardware, while other aspects may be implemented in firmware or software which may be executed by a controller, microprocessor or other computing device, although the embodiments are not limited thereto. While various embodiments may be illustrated and described as block diagrams, flow charts, or using some other pictorial representation, it is well understood that these blocks, apparatus, systems, techniques or methods described herein may be implemented in, as non-limiting examples, hardware, software, firmware, special purpose circuits or logic, general purpose hardware or controller or other computing devices, or some combination thereof.

The embodiments may be implemented by computer software stored in a memory and executable by at least one data processor of the involved entities, either by hardware or by a combination of software and hardware. Further in this regard, it should be noted that any of the processes in, for example, fig. 7 and 8 may represent program steps, or interconnected logic circuits, blocks and functions, or a combination of program steps and logic circuits, blocks and functions. The software may be stored on physical media such as memory chips or blocks of memory implemented within a processor, magnetic media (such as hard or floppy disks), and optical media (such as DVDs and their data variants CDs).

The memory 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 memory, and removable memory. The data processor may be of any type suitable to the local technical environment and may include, as non-limiting examples, one or more of the following: general purpose computers, special purpose computers, microprocessors, digital Signal Processors (DSPs), application Specific Integrated Circuits (ASICs), gate level circuits, and processors based on a multi-core processor architecture.

Alternatively or additionally, some embodiments may be implemented using circuitry. The circuitry may be configured to perform one or more of the functions and/or method steps described previously. The circuitry may be provided in the base station and/or the communication device.

As used in this application, the term "circuitry" may refer to one or more or all of the following:

(a) Hardware-only circuit implementations (such as implementations in analog and/or digital circuitry only);

(b) A combination of hardware circuitry and software, such as:

(i) Combination of analog and/or digital hardware circuit(s) and software/firmware, and

(ii) Any portion of the hardware processor(s) (including digital signal processor (s)) having software, and memory(s) that work together to cause an apparatus (such as a communication device or base station) to perform the various functions previously described; and

(c) Hardware circuit(s) and/or processor(s), such as microprocessor(s) or portion of microprocessor(s), that require software (e.g., firmware) to operate, but may not exist when software is not required for operation.

This definition of circuitry applies to all uses of this term in this application, including in any claims. As a further example, as used in this application, the term "circuitry" also encompasses an implementation of only a hardware circuit or processor (or processors) or a portion of a hardware circuit or processor and its (or their) accompanying software and/or firmware. The term circuitry also encompasses, for example, integrated devices.

The foregoing description has provided by way of exemplary and non-limiting examples a complete and informative description of some embodiments. However, various modifications and adaptations may become apparent to those skilled in the relevant arts in view of the foregoing description, when read in conjunction with the accompanying drawings and the appended claims. However, all such and similar modifications of the present teachings will still fall within the scope defined by the appended claims.

Claims

1. An apparatus comprising means configured to facilitate cross-domain network service related machine learning or artificial intelligence pipeline reliability functionality, wherein the cross-domain machine learning or artificial intelligence pipeline is used to control a cognitive autonomous network comprising at least two domains.

2. The apparatus of claim 1, wherein the means configured to facilitate cross-domain network service related machine learning or artificial intelligence pipeline reliability functionality is configured to facilitate at least one of controlling a cognitive autonomous network comprising at least two domains:

defining machine learning or artificial intelligent pipeline credibility related to the cross-domain network service;

configuring machine learning or artificial intelligent pipeline credibility related to the cross-domain network service;

Measuring the reliability of machine learning or artificial intelligent pipelines related to the cross-domain network service; and

reporting machine learning or artificial intelligence pipeline trustworthiness associated with the cross-domain network service.

3. The apparatus of any of claims 1 or 2, wherein the cross-domain network service related machine learning or artificial intelligence pipeline reliability function comprises at least one of:

fairness;

an interpretability; and

robustness.

4. The apparatus of any of claims 1-3, wherein the means configured to facilitate cross-domain network service related machine learning or artificial intelligence pipeline reliability functionality is configured for controlling a cognitive autonomous network comprising at least two domains:

obtaining cross-domain machine learning or artificial intelligence quality trustworthiness configured to: overlay domain specific machine learning or artificial intelligence quality reliability requirements, and cross-domain network service related machine learning or artificial intelligence pipeline constraints;

converting the cross-domain machine learning or artificial intelligence quality trustworthiness to at least one domain-specific machine learning or artificial intelligence quality trustworthiness for at least one of the at least two domains; and

Providing the at least one domain-specific machine learning or artificial intelligence quality confidence for at least one of the at least two domains.

5. The apparatus of claim 4, wherein the means configured to translate the cross-domain machine learning or artificial intelligence confidence quality to at least one domain specific machine learning or artificial intelligence confidence quality for at least one of the at least two domains is configured to: the cross-domain machine learning or artificial intelligence reliability quality is converted to at least one domain-specific machine learning or artificial intelligence reliability quality based on a risk level of the cross-domain network service.

6. The apparatus of any of claims 4 or 5, wherein the means configured to translate the cross-domain machine learning or artificial intelligence reliability quality to at least one domain-specific machine learning or artificial intelligence reliability quality for at least one of the at least two domains is configured to: converting the cross-domain machine learning or artificial intelligence confidence quality to at least one domain specific machine learning or artificial intelligence confidence quality based on at least one service level agreement requirement for the cross-domain network, wherein the at least one service level agreement comprises at least one of: a service type; service priority; and at least one key performance indicator metric.

7. The apparatus of any of claims 4 to 6, wherein the means configured to provide the at least one domain-specific machine learning or artificial intelligence reliability quality for at least one of the at least two domains is configured to:

a cross-domain confidence machine learning or artificial intelligence configuration or delegation request is generated and passed to at least one domain-specific machine learning or artificial intelligence confidence function, the cross-domain confidence machine learning or artificial intelligence configuration or delegation request configured to: controlling the at least one domain-specific machine learning or artificial intelligence reliability function to configure a machine learning or artificial intelligence pipeline for the at least one of the at least two domains; and

a cross-domain confidence machine learning or artificial intelligence configuration or delegated response is obtained from the at least one domain specific machine learning or artificial intelligence confidence function based on an implementation of the configuration of the machine learning or artificial intelligence pipeline for the at least one of the at least two domains.

8. The apparatus of any of claims 4 to 6, wherein the means configured to provide the at least one domain-specific machine learning or artificial intelligence reliability quality for at least one of the at least two domains is configured to:

Generating and communicating a cross-domain trust machine learning or artificial intelligence configuration or delegation request to at least one domain-specific policy manager, the cross-domain trust machine learning or artificial intelligence configuration or delegation request configured to: controlling at least one domain-specific machine learning or artificial intelligence trust function to configure a machine learning or artificial intelligence pipeline for the at least one of the at least two domains; and

a cross-domain reliability machine learning or artificial intelligence configuration or delegated response is obtained from the at least one domain policy manager based on an implementation of the configuration of the machine learning or artificial intelligence pipeline for the at least one of the at least two domains.

9. The apparatus of any of claims 7 or 8, wherein the cross-domain confidence machine learning or artificial intelligence configuration or delegation request comprises:

a domain scope parameter configured to identify a domain to which the request is addressing;

a pipe identification parameter configured to identify a domain-specific machine learning or artificial intelligence pipe that the request is addressing;

a category identification parameter configured to identify the at least one domain-specific machine learning or artificial intelligence confidence quality.

10. The apparatus of claim 9 when dependent on claim 7, wherein the cross-domain trust machine learning or artificial intelligence configuration or delegation request further comprises at least one of:

a desired fairness parameter configured to indicate a relative fairness level for the domain-specific machine learning or artificial intelligence pipeline;

a desired interpretive parameter configured to indicate a desired level of interpretive for the domain-specific machine learning or artificial intelligence pipeline;

a desired technical robustness parameter configured to indicate a desired technical robustness level for the domain-specific machine learning or artificial intelligence pipeline; and

a desired antagonism robustness parameter configured to indicate a desired antagonism robustness level for the domain-specific machine learning or artificial intelligence pipeline.

11. The apparatus of any of claims 4 to 10, the means configured to facilitate a cross-domain network service related machine learning or artificial intelligence pipeline reliability function configured for controlling a cognitive autonomous network comprising at least two domains:

Generating and communicating a cross-domain reliability machine learning or artificial intelligence capability information request to at least one domain specific machine learning or artificial intelligence reliability function, the cross-domain reliability machine learning or artificial intelligence capability information request configured to: controlling the at least one domain-specific machine learning or artificial intelligence reliability function to enable capability discovery of machine learning or artificial intelligence pipelines for the at least one of the at least two domains; and

a cross-domain reliability machine learning or artificial intelligence capability information response is obtained from the at least one domain specific machine learning or artificial intelligence reliability function reporting the capability discovery for the machine learning or artificial intelligence pipeline for the at least one of the at least two domains.

12. The apparatus of claim 11, wherein the cross-domain reliability machine learning or artificial intelligence capability information request comprises:

a domain scope parameter configured to identify a domain to which the request is addressing; and

a scope parameter configured to identify a domain-specific machine learning or artificial intelligence pipeline that the request is addressing.

13. The apparatus of claim 12, wherein the cross-domain reliability machine learning or artificial intelligence capability information request further comprises a pipeline stage parameter configured to identify a stage of the domain-specific machine learning or artificial intelligence pipeline that the request is addressing.

14. The apparatus of any of claims 4 to 13, wherein the means configured to facilitate cross-domain network service related machine learning or artificial intelligence pipeline reliability functionality is further configured to control a cognitive autonomous network comprising at least two domains:

obtaining a cross-domain credibility artificial intelligence report request or subscription from a network operator;

generating and communicating domain-specific trust artificial intelligence report requests or subscriptions to at least one domain-specific machine learning or artificial intelligence pipeline trust function based on the cross-domain trust artificial intelligence report requests or subscriptions from network operators, wherein the domain-specific trust artificial intelligence report requests or subscriptions are configured to: controlling the at least one domain-specific machine learning or artificial intelligence pipeline reliability function to provide at least one domain-specific machine learning or artificial intelligence pipeline reporting response or notification;

Receiving machine learning or artificial intelligence capability information, and/or the at least one domain-specific machine learning or artificial intelligence pipeline report response or notification from the at least one domain-specific machine learning or artificial intelligence pipeline reliability function;

storing machine learning or artificial intelligence capability information received from the at least one domain-specific machine learning or artificial intelligence pipeline, and/or the at least one domain-specific machine learning or artificial intelligence pipeline report in a cross-domain trust knowledge database;

the cross-domain trustworthiness artificial intelligence report is generated and delivered based on the at least one domain specific machine learning or artificial intelligence pipeline report response or notification.

15. The apparatus of claim 14, wherein the cross-domain confidence artificial intelligence report request comprises:

a scope parameter configured to identify a domain-specific machine learning or artificial intelligence pipeline that the request is addressing; and

pipeline stage parameters configured to identify stages of the domain-specific machine learning or artificial intelligence pipeline that the request is addressing.

16. The apparatus of claim 15, wherein the cross-domain trustworthiness artificial intelligence report request further includes at least one of:

a list of fairness metric parameters configured to identify a fairness metric to be reported;

a list of fairness metric interpretations configured to identify a fairness metric interpretation to be reported;

a list of interpretability metrics configured to identify an interpretability metric to be reported;

a list of interpretations configured to identify an interpretation to be reported;

a list of technical robustness metrics configured to identify technical robustness metrics to be reported;

a list of technical robustness metric interpretations configured to identify a technical robustness metric interpretation to be reported;

a list of robustness against metrics configured to identify robustness against metrics to be reported;

a list of robust metric interpretations configured to identify robust metric interpretations to be reported;

a start time parameter configured to identify a start time for reporting;

an end time parameter configured to identify an end time for reporting; and

a reporting interval parameter configured to identify a periodic interval for reporting.

17. The apparatus of claim 14, wherein the cross-domain trustworthiness artificial intelligence reporting subscription includes:

a domain-scope parameter configured to identify a domain to which the subscription is addressing;

a scope parameter configured to identify a domain-specific machine learning or artificial intelligence pipeline to which the subscription is addressing; and

pipeline stage parameters configured to identify stages of the domain-specific machine learning or artificial intelligence pipeline that the subscription is addressing.

18. The apparatus of claim 17, wherein the cross-domain trustworthiness artificial intelligence reporting subscription further includes at least one of:

a list of robustness against metrics configured to identify robustness against metrics to be reported; and

cross-reporting threshold parameters configured to identify thresholds for which metrics or metric interpretations are reported.

19. A method, comprising:

Facilitating cross-domain network service related machine learning or artificial intelligence pipeline reliability functionality, wherein the cross-domain machine learning or artificial intelligence pipeline is used to control a cognitive autonomous network comprising at least two domains.

20. A computer program comprising computer-executable instructions which, when run on one or more processors, perform the steps of the method of claim 19.