Generation of device setting recommendations based on user activeness in configuring multimedia or other user device settings
A method includes obtaining device usage log data associated with multiple user devices. The device usage log data is related to device settings associated with the user devices, where each device setting associated with the user devices is adjustable by users of the user devices. The method also includes obtaining one or more metrics representing each user's activeness in customizing one or more device settings of the user device associated with the user based on the device usage log data. The method further includes clustering the users into multiple groups based on the metric(s) and identifying at least one of the groups as being at least one valid user group. In addition, the method includes providing one or more recommendations of at least one customized device setting to one or more of the user devices based on the device usage log data associated with the valid user group(s).
1. A method comprising:
obtaining, using at least one processing device, device usage log data associated with multiple user devices, the device usage log data related to device settings associated with the user devices, wherein each device setting associated with the user devices is adjustable by users of the user devices;
obtaining, from the device usage log data using the at least one processing device, one or more metrics quantifying each user's history of customizing one or more device settings of the user device associated with the user, wherein the one or more metrics are calculated values from a user feature and extraction function;
clustering, using the at least one processing device, the users into multiple groups based on the one or more metrics;
identifying, using the at least one processing device, at least one of the groups as being at least one valid user group;
generating one or more recommendations of at least one customized device setting for the at least one valid user group based on the device usage log data associated with the at least one valid user group; and
providing, using the at least one processing device, the one or more recommendations to one or more of the user devices associated with the at least one valid user group.
2. The method of claim 1 , wherein each valid user group is identified based on (i) a consistency of the users within that group in making changes to the device settings and (ii) an explainability of the users within that group in making the changes to the device settings.
3. The method of claim 1 , further comprising:
selecting a subset of the device usage log data associated with the at least one valid user group; and
generating the one or more recommendations based on the subset of the device usage log data.
4. The method of claim 3 , wherein selecting the subset of the device usage log data comprises selecting the subset of the device usage log data based on an identified log data quality threshold.
5. The method of claim 3 , wherein selecting the subset of the device usage log data comprises refining a collection of log data that includes the device usage log data into a sub-collection of log data that includes the subset of the device usage log data.
6. The method of claim 1 , wherein the one or more metrics are based on one or more features representing each user's activeness in customizing the one or more device settings of the user device associated with the user.
7. The method of claim 1 , wherein clustering the users into the groups comprises identifying an optimal number of groups in which to cluster the users, the optimal number of groups based on one or more clustering performance metrics.
8. The method of claim 1 , wherein:
the user devices comprise audio/visual devices;
the device settings associated with the user devices comprise at least one of audio/visual modes or individual audio/visual settings of the audio/visual devices; and
the at least one customized device setting comprises at least one of:
a customized audio/visual setting;
a specified one of the audio/visual modes; or
a new audio/visual mode with at least one custom audio/visual setting.
9. An apparatus comprising:
at least one processing device configured to:
obtain device usage log data associated with multiple user devices, the device usage log data related to device settings associated with the user devices, wherein each device setting associated with the user devices is adjustable by users of the user devices;
obtain, from the device usage log data, one or more metrics quantifying each user's history of customizing one or more device settings of the user device associated with the user, wherein the one or more metrics are calculated values from a user feature and extraction function;
cluster the users into multiple groups based on the one or more metrics;
identify at least one of the groups as being at least one valid user group;
generate one or more recommendations of at least one customized device setting for the at least one valid user group based on the device usage log data associated with the at least one valid user group; and
provide the one or more recommendations to one or more of the user devices associated with the at least one valid user group.
10. The apparatus of claim 9 , wherein the at least one processing device is configured to identify each valid user group based on (i) a consistency of the users within that group in making changes to the device settings and (ii) an explainability of the users within that group in making the changes to the device settings.
11. The apparatus of claim 9 , wherein the at least one processing device is further configured to:
select a subset of the device usage log data associated with the at least one valid user group; and
generate the one or more recommendations based on the subset of the device usage log data.
12. The apparatus of claim 11 , wherein the at least one processing device is configured to select the subset of the device usage log data based on an identified log data quality threshold.
13. The apparatus of claim 11 , wherein, to select the subset of the device usage log data, the at least one processing device is configured to refine a collection of log data that includes the device usage log data into a sub-collection of log data that includes the subset of the device usage log data.
14. The apparatus of claim 9 , wherein the one or more metrics are based on one or more features representing each user's activeness in customizing the one or more device settings of the user device associated with the user.
15. The apparatus of claim 9 , wherein, to cluster the users into the groups, the at least one processing device is configured to identify an optimal number of groups in which to cluster the users, the optimal number of groups based on one or more clustering performance metrics.
16. The apparatus of claim 9 , wherein:
the user devices comprise audio/visual devices;
the device settings associated with the user devices comprise at least one of audio/visual modes or individual audio/visual settings of the audio/visual devices; and
the at least one customized device setting comprises at least one of:
a customized audio/visual setting;
a specified one of the audio/visual modes; or
a new audio/visual mode with at least one custom audio/visual setting.
17. A non-transitory machine readable medium containing instructions that when executed cause at least one processor to:
obtain device usage log data associated with multiple user devices, the device usage log data related to device settings associated with the user devices, wherein each device setting associated with the user devices is adjustable by users of the user devices;
obtain, from the device usage log data, one or more metrics quantifying each user's history of customizing one or more device settings of the user device associated with the user, wherein the one or more metrics are calculated values from a user feature and extraction function;
cluster the users into multiple groups based on the one or more metrics;
identify at least one of the groups as being at least one valid user group;
generate one or more recommendations of at least one customized device setting for the at least one valid user group based on the device usage log data associated with the at least one valid user group; and
provide the one or more recommendations to one or more of the user devices associated with the at least one valid user group.
18. The non-transitory machine readable medium of claim 17 , wherein the instructions when executed cause the at least one processor to identify each valid user group based on (i) a consistency of the users within that group in making changes to the device settings and (ii) an explainability of the users within that group in making the changes to the device settings.
19. The non-transitory machine readable medium of claim 17 , wherein the one or more metrics are based on one or more features representing each user's activeness in customizing the one or more device settings of the user device associated with the user.
20. The non-transitory machine readable medium of claim 17 , wherein the instructions that when executed cause the at least one processor to cluster the multiple users into the multiple groups comprise:
instructions that when executed cause the at least one processor to identify an optimal number of groups in which to cluster the users, the optimal number of groups based on one or more clustering performance metrics.