AI/ML configuration feedback

1 . A user equipment comprising:

one or more processors, and memory storing instructions that, when executed by the one or more processors, cause the user equipment to:

monitor, while a regular radio operation prioritized over an artificial intelligence/machine learning operation is ongoing, whether the user equipment suffers a performance issue due to the artificial intelligence/machine learning operation; and

in response to detecting the performance issue, perform measurement configuration adaptation for data collection for the artificial intelligence/machine learning operation to remove or reduce the performance issue.

2 . The apparatus according to claim 1 , wherein the artificial intelligence/machine learning operation comprises at least one of the following:

data collection for the training of an artificial intelligence/machine learning model;

performing training of the artificial intelligence/machine learning model; or

transmitting the data collected for training of the artificial intelligence/machine learning model.

3 . The apparatus according to claim 1 , wherein the instructions, when executed by the one or more processors, further cause the apparatus to:

supervise whether the user equipment receives, from the network, in addition to a configured measurement configuration, a fallback measurement configuration for a case that the user equipment suffers the performance issue due to the artificial intelligence/machine learning operation; wherein

the performing measurement configuration adaptation by the user equipment comprises adopting the fallback measurement configuration in the user equipment if the user equipment receives the fallback measurement configuration.

4 . The apparatus according to claim 1 , wherein the instructions, when executed by the one or more processors, cause the user equipment to monitor whether the user equipment suffers the performance issue due to the artificial intelligence/machine learning operation by at least one of the following criteria:

monitoring whether the performance issue occurs more frequently than a frequency threshold; or

performing an activity for resolving the performance issue and then monitoring whether the performance issue is not solved due to the activity, wherein the activity is not related to the artificial intelligence/machine learning operation; or

monitoring whether the training of the artificial intelligence/machine learning model takes longer than expected if the training of the artificial intelligence/machine learning training is performed by the user equipment; or

monitoring whether the user equipment uses too many resources.

5 . The apparatus according to claim 1 , wherein a status of the artificial intelligence/machine learning operation is reflected in a state machine, wherein the state machine has a status that is any of active, impaired, or inactive.

6 . The apparatus of claim 1 , wherein the measurement configuration adaptation is performed by at least one of the following: adjusting volume of data, adjusting resolution of the data, postpone measurements, prolong measurement reporting cycle, or setting longer time for training of a model in association with the artificial intelligence/machine learning operation.

7 . A method comprising:

monitoring, by a user equipment while a regular radio operation prioritized over an artificial intelligence/machine learning operation is ongoing, whether the user equipment suffers a performance issue due to the artificial intelligence/machine learning operation; and

in response to detecting the performance issue, performing, by the user equipment, measurement configuration adaptation for data collection for the artificial intelligence/machine learning operation to remove or reduce the performance issue.

8 . The method according to claim 7 , wherein the artificial intelligence/machine learning operation comprises at least one of the following:

data collection for the training of an artificial intelligence/machine learning model;

performing training of the artificial intelligence/machine learning model; or

transmitting the data collected for training of the artificial intelligence/machine learning model.

9 . The method according to claim 7 , further comprising:

supervising whether the user equipment receives, from the network, in addition to a configured measurement configuration, a fallback measurement configuration for a case that the user equipment suffers the performance issue due to the artificial intelligence/machine learning operation; wherein

the performing measurement configuration adaptation by the user equipment comprises adopting the fallback measurement configuration in the user equipment if the user equipment receives the fallback measurement configuration.

10 . The method according to claim 7 , wherein a status of the artificial intelligence/machine learning operation is reflected in a state machine, wherein the state machine has a status that is any of active, impaired, or inactive.

11 . The method of claim 7 , wherein the measurement configuration adaptation is performed by at least one of the following: adjusting volume of data, adjusting resolution of the data, postpone measurements, prolong measurement reporting cycle, or setting longer time for training of a model in association with the artificial intelligence/machine learning operation.