Back to results
US 2025/0031068 A1Published application
Mechanism for functionality based life cycle management
AssigneeNokia Technologies Oy
InventorsAmir Mehdi AHMADIAN TEHRANI, Andrea BONFANTE, Keeth Saliya Jayasinghe LADDU, Frederick VOOK, Tachporn SANGUANPUAK
Life of this patent
Estimating the term…
Abstract
The present disclosure relates to a solution for functionality-based performance monitoring. In particular, a solution is proposed to enable functionality-based performance monitoring via sending updates on the configured/identified functionalities using applicable conditions framework. In this way, it can improve performance of the AI/ML entity.
Claims21
-29. (canceled)
An apparatus comprising:
- at least one processor;
- and
- at least one memory storing instructions that, when executed by the at least one processor, cause the apparatus to:
- transmit, to a network device, first information indicating a first artificial intelligence and machine learning (AI/ML) entity supported by the apparatus and a first delay associated with the first AI/ML entity, wherein the first delay comprises a first activation delay of the first AI/ML entity and a first switching delay between another AI/ML entity and the first AI/ML entity;
- in accordance with a determination that an indication to activate or switch to the first AI/ML entity is received from the network device, determine a first updated delay associated with the first AI/ML entity, wherein the first updated delay comprises a first updated activation delay of first AI/ML entity and a first updated switching delay between the other AI/ML entity and the first AI/ML entity;
- determine whether there is a change between the first delay and the first updated delay based on a predefined criterion;
- in accordance with a determination that the first updated activation delay is smaller than or equal to a first activation threshold delay and that the first updated switching delay is smaller than or equal to a first switching threshold delay, determine that there is a change between the first delay and the first updated delay based on the predefined criterion, wherein the first activation threshold delay is the first activation delay multiplying a first activation scaling factor, and wherein the first switching threshold delay is the first switching delay multiplying a first switching scaling factor;
- based on the determination that the first updated activation delay is smaller than or equal to the first activation threshold delay and that the first updated switching delay is smaller than or equal to the first switching threshold delay, transmit, to the network device, the first updated activation delay and the first updated switching delay;
- transmit, to a network device, second information indicating a second AI/ML entity supported by the apparatus and a second delay associated with the second AI/ML entity, wherein the second delay comprises a second activation delay of the second AI/ML entity and a second switching delay between another AI/ML entity and the second AI/ML entity;
- in accordance with a determination that an indication to activate or switch to the second AI/ML entity is received from the network device, determine a second updated delay associated with the first AI/ML entity, wherein the second updated delay comprises a second updated activation delay of second AI/ML entity and a second updated switching delay between the other AI/ML entity and the second AI/ML entity;
- determine whether there is a change between the second delay and the second updated delay based on a predefined criterion;
- in accordance with a determination that the second updated activation delay is larger than a second activation threshold delay and that the second updated switching delay is larger than a second switching threshold delay, determine that the second updated activation delay and the second updated switching delay are out of range based on the predefined criterion, wherein the second activation threshold delay is the second activation delay multiplying a second activation scaling factor, and wherein the second switching threshold delay is the second switching delay multiplying a second switching scaling factor;
- and
- based on the determination that the second updated activation delay is larger than the second activation threshold delay and that the second updated switching delay is larger than the second switching threshold delay, transmit, to the network device, third information indicating no support of the second AI/ML entity.
11 more elements
A system comprising:
- an apparatus:
- at least one processor;
- and
- at least one memory storing instructions that, when executed by the at least one processor, cause the apparatus to:
- transmit, to a network device, first information indicating a first artificial intelligence and machine learning (AI/ML) entity supported by the apparatus and a first delay associated with the first AI/ML entity, wherein the first delay comprises a first activation delay of the first AI/ML entity and a first switching delay between another AI/ML entity and the first AI/ML entity;
- in accordance with a determination that an indication to activate or switch to the first AI/ML entity is received from the network device, determine a first updated delay associated with the first AI/ML entity, wherein the first updated delay comprises a first updated activation delay of first AI/ML entity and a first updated switching delay between the other AI/ML entity and the first AI/ML entity;
- determine whether there is a change between the first delay and the first updated delay based on a predefined criterion;
- in accordance with a determination that the first updated activation delay is smaller than or equal to a first activation threshold delay and that the first updated switching delay is smaller than or equal to a first switching threshold delay, determine that there is a change between the first delay and the first updated delay based on the predefined criterion, wherein the first activation threshold delay is the first activation delay multiplying a first activation scaling factor, and wherein the first switching threshold delay is the first switching delay multiplying a first switching scaling factor;
- based on the determination that the first updated activation delay is smaller than or equal to the first activation threshold delay and that the first updated switching delay is smaller than or equal to the first switching threshold delay, transmit, to the network device, the first updated activation delay and the first updated switching delay;
- transmit, to a network device, second information indicating a second AI/ML entity supported by the apparatus and a second delay associated with the second AI/ML entity, wherein the second delay comprises a second activation delay of the second AI/ML entity and a second switching delay between another AI/ML entity and the second AI/ML entity;
- in accordance with a determination that an indication to activate or switch to the second AI/ML entity is received from the network device, determine a second updated delay associated with the first AI/ML entity, wherein the second updated delay comprises a second updated activation delay of second AI/ML entity and a second updated switching delay between the other AI/ML entity and the second AI/ML entity;
- determine whether there is a change between the second delay and the second updated delay based on a predefined criterion;
- in accordance with a determination that the second updated activation delay is larger than a second activation threshold delay and that the second updated switching delay is larger than a second switching threshold delay, determine that the second updated activation delay and the second updated switching delay are out of range based on the predefined criterion, wherein the second activation threshold delay is the second activation delay multiplying a second activation scaling factor, and wherein the second switching threshold delay is the second switching delay multiplying a second switching scaling factor;
- and
- based on the determination that the second updated activation delay is larger than the second activation threshold delay and that the second updated switching delay is larger than the second switching threshold delay, transmit, to the network device, third information indicating no support of the second AI/ML entity.
12 more elements
A method comprising:
- transmitting, to a network device, first information indicating a first artificial intelligence and machine learning (AI/ML) entity supported by the apparatus and a first delay associated with the first AI/ML entity, wherein the first delay comprises a first activation delay of the first AI/ML entity and a first switching delay between another AI/ML entity and the first AI/ML entity;
- in accordance with a determination that an indication to activate or switch to the first AI/ML entity is received from the network device, determining a first updated delay associated with the first AI/ML entity, wherein the first updated delay comprises a first updated activation delay of first AI/ML entity and a first updated switching delay between the other AI/ML entity and the first AI/ML entity;
- determining whether there is a change between the first delay and the first updated delay based on a predefined criterion;
- in accordance with a determination that the first updated activation delay is smaller than or equal to a first activation threshold delay and that the first updated switching delay is smaller than or equal to a first switching threshold delay, determining that there is a change between the first delay and the first updated delay based on the predefined criterion, wherein the first activation threshold delay is the first activation delay multiplying a first activation scaling factor, and wherein the first switching threshold delay is the first switching delay multiplying a first switching scaling factor;
- based on the determination that the first updated activation delay is smaller than or equal to the first activation threshold delay and that the first updated switching delay is smaller than or equal to the first switching threshold delay, transmitting, to the network device, the first updated activation delay and the first updated switching delay;
- transmitting, to a network device, second information indicating a second AI/ML entity supported by the apparatus and a second delay associated with the second AI/ML entity, wherein the second delay comprises a second activation delay of the second AI/ML entity and a second switching delay between another AI/ML entity and the second AI/ML entity;
- in accordance with a determination that an indication to activate or switch to the second AI/ML entity is received from the network device, determining a second updated delay associated with the first AI/ML entity, wherein the second updated delay comprises a second updated activation delay of second AI/ML entity and a second updated switching delay between the other AI/ML entity and the second AI/ML entity;
- determining whether there is a change between the second delay and the second updated delay based on a predefined criterion;
- in accordance with a determination that the second updated activation delay is larger than a second activation threshold delay and that the second updated switching delay is larger than a second switching threshold delay, determining that the second updated activation delay and the second updated switching delay are out of range based on the predefined criterion, wherein the second activation threshold delay is the second activation delay multiplying a second activation scaling factor, and wherein the second switching threshold delay is the second switching delay multiplying a second switching scaling factor;
- and
- based on the determination that the second updated activation delay is larger than the second activation threshold delay and that the second updated switching delay is larger than the second switching threshold delay, transmitting, to the network device, third information indicating no support of the second AI/ML entity.
8 more elements
Dependencies are inferred from the claim text.