Adapting playback settings based on change history
Techniques discussed herein improve a user's playback experience of a multimedia file by automatically adjusting playback settings based on change history data stored in one or more profiles. A system is configured to detect and collect information regarding changes to playback settings made by one or more users, and/or made in response to input from one or more users, during presentation of a media title, such as a song and/or movie, on one or more computers. This information is processed by a backend process on one or more server computers to determine predicted preferred playback settings for a particular user using a particular computer or playback device, requesting a particular multimedia file.
1. A method comprising:
during playback of each of a plurality of multimedia files, detecting changes to playback settings;
for each respective multimedia file of the plurality of multimedia files, maintaining a respective profile that includes change history data that is based on the changes to the playback settings that were detected to have occurred during playback of the respective multimedia file;
receiving, from a particular client device, a request for a particular multimedia file of the plurality of multimedia files, wherein the request includes a set of one or more attributes associated with the request;
based on change history data from one or more profiles of the plurality of multimedia files, determining one or more changes to apply to playback settings for playback of the particular multimedia file, wherein:
the one or more changes to apply to playback settings include applying machine learning algorithm to the set of one or more attributes associated with the request for the particular multimedia file, and
the one or more changes are generated based on the machine learning algorithm; and
responding to the request by causing the multimedia file to play, using a particular application on said particular client device, with said one or more changes to the playback settings automatically applied during playback;
wherein the method is performed by one or more computing devices.
2. The method of claim 1 , wherein the one or more profiles includes at least a particular profile of changes, by viewers, to playback settings of the particular multimedia file; wherein determining the one or more changes to the playback settings based on the one or more profiles of the plurality of multimedia files, includes:
grouping the changes of the particular profile by:
a time at which each change occurred while playing the particular multimedia file, and
a client device type of a plurality of client device types on which each change to the playback settings occurred;
wherein determining the one or more changes to the playback settings includes applying a set of one or more threshold conditions to the groupings.
3. The method of claim 2 , wherein the one or more changes to playback settings includes a change to volume while playing a particular multimedia file at a particular time on a particular client device type that is the client device type of the particular client device.
4. The method of claim 1 , further comprising:
for each client computer of a plurality of client computers, receiving attributes associated with each change to the playback settings;
wherein determining the one or more changes to the playback settings based on the one or more profiles of the plurality of multimedia files, includes:
generating, for the particular multimedia file, a respective score for each possible change to playback settings described in the one or more profiles; and
based on one or more scores generated, selecting the one or more changes to the playback settings.
5. The method of claim 4 , wherein the one or more profiles includes at least a particular profile of changes, by viewers, to playback settings of the particular multimedia file; wherein the method further comprises: increasing a weight of attributes associated with changes, by viewers, to playback settings of the particular multimedia file.
6. The method of claim 4 , wherein the attributes include time of day and geolocation.
7. The method of claim 6 , wherein the one or more changes to playback settings includes a change to contrast during a particular time of day at a particular geolocation.
8. One or more non-transitory computer-readable media storing one or more sequences of instructions which, when executed by one or more processors, cause performance of:
during playback of each of a plurality of multimedia files, detecting changes to playback settings;
for each respective multimedia file of the plurality of multimedia files, maintaining a respective profile that includes change history data that is based on the changes to the playback settings that were detected to have occurred during playback of the respective multimedia file;
receiving, from a particular client device, a request for a particular multimedia file of the plurality of multimedia files, wherein the request includes a set of one or more attributes associated with the request;
based on change history data from one or more profiles of the plurality of multimedia files, determining one or more changes to apply to playback settings for playback of the particular multimedia file, wherein:
the one or more changes to apply to playback settings include applying machine learning algorithm to the set of one or more attributes associated with the request for the particular multimedia file, and
the one or more changes are generated based on the machine learning algorithm; and
responding to the request by causing the multimedia file to play, using a particular application on said particular client device, with said one or more changes to the playback settings automatically applied during playback.
9. The one or more non-transitory computer-readable media of claim 8 , wherein the one or more profiles includes at least a particular profile of changes, by viewers, to playback settings of the particular multimedia file; wherein determining the one or more changes to the playback settings based on the one or more profiles of the plurality of multimedia files, includes:
grouping the changes of the particular profile by:
a time at which each change occurred while playing the particular multimedia file, and
a client device type of a plurality of client device types on which each change to the playback settings occurred;
wherein determining the one or more changes to the playback settings includes applying a set of one or more threshold conditions to the groupings.
10. The one or more non-transitory computer-readable media of claim 9 , wherein the one or more changes to playback settings includes a change to volume while playing a particular multimedia file at a particular time on a particular client device type that is the client device type of the particular client device.
11. The one or more non-transitory computer-readable media of claim 8 , wherein the one or more non-transitory computer-readable media store instructions which, when executed by one or more processors, further cause:
for each client computer of a plurality of client computers, receiving attributes associated with each change to the playback settings;
wherein determining the one or more changes to the playback settings based on the one or more profiles of the plurality of multimedia files, includes:
generating, for the particular multimedia file, a respective score for each possible change to playback settings described in the one or more profiles; and
based on one or more scores generated, selecting the one or more changes to the playback settings.
12. The one or more non-transitory computer-readable media of claim 11 , wherein the one or more profiles includes at least a particular profile of changes, by viewers, to playback settings of the particular multimedia file; wherein the one or more non-transitory computer-readable media store instructions which, when executed by the one or more processors, further cause: increasing a weight of attributes associated with changes, by viewers, to playback settings of the particular multimedia file.
13. The one or more non-transitory computer-readable media of claim 11 , wherein the attributes include time of day and geolocation.
14. The one or more non-transitory computer-readable media of claim 13 , wherein the one or more changes to playback settings includes a change to contrast during a particular time of day at a particular geolocation.
15. An adaptive playback management system comprising one or more computing devices configured to:
during playback of each of a plurality of multimedia files, detect, by a monitoring agent, changes to playback settings;
for each respective multimedia file of the plurality of multimedia files, maintain, by a configuration manager, a respective profile that includes change history data that is based on the changes to the playback settings that were detected to have occurred during playback of the respective multimedia file;
receive, from a particular client device, a request for a particular multimedia file of the plurality of multimedia files, wherein the request includes a set of one or more attributes associated with the request;
based on change history data from one or more profiles of the plurality of multimedia files, determine one or more changes to apply to playback settings for playback of the particular multimedia file, wherein:
the one or more changes to apply to playback settings include applying machine learning algorithm to the set of one or more attributes associated with the request for the particular multimedia file, and
the one or more changes are generated based on the machine learning algorithm; and
respond to the request by causing the multimedia file to play, using a particular application on said particular client device, with said one or more changes to the playback settings automatically applied during playback.
16. The adaptive playback management system of claim 15 , wherein the one or more profiles includes at least a particular profile of changes, by viewers, to playback settings of the particular multimedia file; wherein in order to determine the one or more changes to the playback settings based on the one or more profiles of the plurality of multimedia files, the one or more computing devices are further configured to:
grouping the changes of the particular profile by:
a time at which each change occurred while playing the particular multimedia file, and
a client device type of a plurality of client device types on which each change to the playback settings occurred;
wherein determining the one or more changes to the playback settings includes applying a set of one or more threshold conditions to the groupings.
17. The adaptive playback management system of claim 16 , wherein the one or more changes to playback settings includes a change to volume while playing a particular multimedia file at a particular time on a particular client device type that is the client device type of the particular client device.
18. The adaptive playback management system of claim 15 , wherein the one or more computing devices are further configured to:
for each client computer of a plurality of client computers, receive attributes associated with each change to the playback settings;
wherein the configuration to determine the one or more changes to the playback settings based on the one or more profiles of the plurality of multimedia files, includes:
generate, for the particular multimedia file, a respective score for each possible change to playback settings described in the one or more profiles; and
based on one or more scores generated, selecting the one or more changes to the playback settings.
19. The adaptive playback management system of claim 18 , wherein the one or more profiles includes at least a particular profile of changes, by viewers, to playback settings of the particular multimedia file; wherein the one or more computing devices are further configured to: increase a weight of attributes associated with changes, by viewers, to playback settings of the particular multimedia file.
20. The adaptive playback management system of claim 18 , wherein the attributes include time of day and geolocation.