Enhanced personalization in multi-user devices

Patent metadata

Field	Value
Publication number	US-10929758-B2
Application number	US-201815941813-A
Country	US
Kind code	B2
Filing date	Mar 30, 2018
Priority date	Jul 30, 2014
Publication date	Feb 23, 2021
Grant date	Feb 23, 2021

Abstract

Disclosed herein is an enhanced device personalization that personalizes a user's experience with a device, e.g., a multi-user device. Rather than personalizing based on the specific user(s) that are using, an active entity, which represents a type of consumption, may be generated and used to make recommendations for personalizing an experience using the device. In a case of a multi-user device, each user's experience is personalized by determining an active entity for the user's experience and without knowledge of which user is using the device.

First claim

The invention claimed is:

1. A method comprising:
obtaining, by at least one computing device, data about a plurality of content items consumed using a plurality of devices, at least one of the devices is a multi-user device;
generating, by the at least one computing device and using the obtained data, a plurality of entities, each entity, of the plurality of entities, associated with a type of content item;
generating, by the at least one computing device and using the obtained data, a content item over entity probability distribution, the content item over entity probability distribution comprising, for each entity of the plurality, a plurality of probabilities, each probability, of the plurality of probabilities, indicating a probability that a respective content item of the plurality is of the type of content item associated with the entity;
identifying, by the at least one computing device, a content item currently being presented by the multi-user device;
identifying, by the at least one computing device, an active entity for the content item currently being presented using the content item over entity probability distribution and the identified content item currently being presented by the multi-user device;
identifying, by the at last one computing device and independent of any user of the multi-user device, a number of content items of the plurality of content items using the identified active entity, each of the number of content items associated with the identified active entity; and
making, by the at least one computing device, a recommendation identifying the number of content items of the plurality for consumption using the multi-user device, the recommendation being made independent of information identifying which one or more users of the plurality is using the multi-user device.

2. The method of claim 1 , the content item currently being presented by the multi-user device being identified by a title of the content item.

3. The method of claim 1 , the content item currently being presented by the multi-user device being identified by a description of the content item.

4. The method of claim 1 , the content item currently being presented by the multi-user device being identified using a program identifier.

5. The method of claim 1 , further comprising:
generating, by the at least one computing device and using the obtained data, an entity over device probability distribution, the entity over device probability distribution being generated for the multi-user device and comprising, for each entity of the plurality, a probability of the multi-user device being used to consume the type of content item associated with the entity.

6. The method of claim 5 , the entity over device probability distribution comprising a probability distribution for each device of the plurality of devices, a device identifier of the multi-user device being used in identifying the entity over device probability distribution associated with the multi-user device.

7. The method of claim 6 , identification of the active entity further comprising:
identifying, using the entity over device probability distribution for the multi-user device, a first probability, for each entity of the plurality, that the entity is the active entity; and
identifying, using the content item over entity probability distribution and the identified content item currently being consumed, a second probability, for each entity of the plurality, that the entity is the active entity; and
selecting the active entity using the identified first and second probabilities identified for each entity of the plurality, the first and second probabilities identified for the active entity indicating that it is more likely, relative to each other entity of the plurality, to be the active entity.

8. The method of claim 7 , selection of the active entity further comprising:
combining, for each entity of the plurality, the entity's first and second probabilities in an aggregation, the selecting using the aggregation in selecting the active entity.

9. The method of claim 8 , the aggregation, for an entity of the plurality, comprising a multiplication of the first and second probabilities.

10. The method of claim 8 , the aggregation, for an entity of the plurality, comprising using either the entity's first or second probability as a weighting to weight the other of the entity's first or second probabilities.

11. The method of claim 1 , identification of the active entity further comprising:
identifying, using the content item over entity probability distribution and the identified content item currently being consumed, a probability, for each entity of the plurality, that the entity is the active entity; and
selecting the active entity using the identified probability of each entity of the plurality, the active entity having an associated probability indicating that it is more likely, relative to each other entity of the plurality, to be the active entity.

12. The method of claim 1 , identification of the number of content items further comprising:
ranking the plurality of content items according to each content item's probability of being of the type of content item associated with the identified active entity; and
selecting the number of content items from the plurality using the ranking.

13. A non-transitory computer-readable storage medium tangibly encoded with computer-executable instructions that when executed by a processor associated with a computing device perform a method comprising:
obtaining data about a plurality of content items consumed using a plurality of devices, at least one of the devices is a multi-user device;
generating, using the obtained data, a plurality of entities, each entity, of the plurality of entities, associated with a type of content item;
generating, using the obtained data, a content item over entity probability distribution, the content item over entity probability distribution comprising, for each entity of the plurality, a plurality of probabilities, each probability, of the plurality of probabilities, indicating a probability that a respective content item of the plurality is of the type of content item associated with the entity;
identifying a content item currently being presented by the multi-user device;
identifying an active entity for the content item currently being presented using the content item over entity probability distribution and the identified content item currently being presented by the multi-user device;
identifying, independent of any user of the multi-user device, a number of content items of the plurality of content items using the identified active entity, each of the number of content items associated with the identified active entity; and
making a recommendation identifying the number of content items of the plurality for consumption using the multi-user device, the recommendation being made independent of information identifying which one or more users of the plurality is using the multi-user device.

14. The medium of claim 13 , further comprising:
generating, using the obtained data, an entity over device probability distribution, the entity over device probability distribution being generated for the multi-user device and comprising, for each entity of the plurality, a probability of the multi-user device being used to consume the type of content item associated with the entity.

15. The medium of claim 13 , the entity over device probability distribution comprising a probability distribution for each device of the plurality of devices, a device identifier of the multi-user device being

Assignees

• Verizon Media Inc

Inventors

• Hillel Eshcar
• Aharon Michal
• Golbandi Nadav

Classifications

• G06N5/04 Primary

  Inference or reasoning models · CPC title