User profile based on clustering tiered descriptors

Patent metadata

Field	Value
Publication number	US-10140372-B2
Application number	US-201213611740-A
Country	US
Kind code	B2
Filing date	Sep 12, 2012
Priority date	Sep 12, 2012
Publication date	Nov 27, 2018
Grant date	Nov 27, 2018

Abstract

A user of a network-based system may correspond to a user profile that describes the user. The user profile may describe the user using one or more descriptors of items that correspond to the user (e.g., items owned by the user, items liked by the user, or items rated by the user). In some situations, such a user profile may be characterized as a “taste profile” that describes an array or distribution of one or more tastes, preferences, or habits of the user. Accordingly, the user profile machine within the network-based system may generate the user profile by accessing descriptors of items that correspond to the user, clustering one or more of the descriptors, and generating the user profile based on one or more clusters of the descriptors.

First claim

What is claimed is:

1. A method comprising:
accessing, by executing an instruction with a processor, descriptors in metadata that is descriptive of a first item and of a second item, the descriptors and metadata corresponding to a metadata model that organizes the descriptors into multiple tiers of the metadata model, the descriptors including a first descriptor of the first item and a second descriptor of the second item;
accessing, from a database communicatively coupled to the processor, the metadata model that organizes the descriptors into the multiple tiers;
creating, by executing an instruction with the processor, a group of descriptors by grouping the accessed first and second descriptors into the group of descriptors based on the accessed first and second descriptors being both represented in a same tier among the multiple tiers of the accessed metadata model that corresponds to the first and second descriptors;
accessing, via a device of a user communicatively coupled to the processor via a network, biometric data including a heart rate of the user;
determining, by executing an instruction with the processor, a first activity in which the user is engaged based on contextual data that correlates the first item and the second item with multiple locations of the user and the biometric data of the user received from the device of the user via the network;
generating, by executing an instruction with the processor, a user profile based on the first activity of the user and the created group of descriptors into which the first and second descriptors were grouped based on the first and second descriptors being both represented in the same tier among the multiple tiers of the accessed metadata model that corresponds to the first and second descriptors;
storing the group within the user profile as corresponding to the first activity determined based on the multiple locations and the biometric data of the user; and
recommending, by executing an instruction with the processor and in response to a second activity of the user matching the first activity associated with the group within the user profile, a third item based on the user profile, the user profile generated based on the created group of descriptors into which the first and second descriptors were grouped, the grouping performed based on the first and second descriptors being both represented in the same tier among the multiple tiers of the accessed metadata model.

2. The method of claim 1 , wherein:
the first item and the second item are specimens of a collection of items that belong to the user.

3. The method of claim 2 , wherein:
the collection of items is a media library of the user;
the first item is a first media file in the media library of the user; and
the second item is a second media file in the media library of the user.

4. The method of claim 1 , wherein the metadata model organizes the descriptors into a hierarchy of descriptors that includes the multiple tiers of the metadata model.

5. The method of claim 1 , wherein the grouping of the first descriptor and the second descriptor into the group of descriptors includes determining that the first descriptor and the second descriptor match each other.

6. The method of claim 5 , further including determining a name of the group based on the first descriptor being determined to match the second descriptor, and wherein the generating of the user profile includes storing the name of the group within the user profile as a taste descriptor that describes a taste of the user that corresponds to the user profile.

7. The method of claim 1 , wherein the grouping of the first descriptor and the second descriptor into the group of descriptors includes determining that the first descriptor and the second descriptor are similar to each other.

8. The method of claim 7 , further including:
determining a name of the group based on a third descriptor of the first item being determined to match a fourth descriptor of the second item; and wherein
the generating of the user profile includes storing the name of the group within the user profile as a taste descriptor that describes a taste of the user that corresponds to the user profile.

9. The method of claim 1 , wherein:
the metadata model indicates that the tier within which the first descriptor and the second descriptor are represented has a weight that exceeds a further weight of a further tier among the multiple tiers of the metadata model; and
the grouping of the first descriptor and the second descriptor into the group of descriptors is based on the weight of the tier exceeding the further weight of the further tier.

10. The method of claim 9 , wherein the metadata model includes a hierarchy of the multiple tiers in which a top tier is weighted lower than the weight of the tier in which the first descriptor and the second descriptor are represented.

11. The method of claim 1 , further including:
determining the first activity of the user based on contextual data that correlates the first item and the second item with a day of week and a time of day; and wherein
the generating of the user profile includes storing a name of the group within the user profile as corresponding to the first activity determined based on the day of week and the time of day.

12. The method of claim 1 , further including:
determining an anomalous phase of the user based on contextual data that correlates the first item and the second item with a time period that has a duration shorter than a threshold duration; and wherein
the generating of the user profile includes omitting a name of the group from the user profile.

13. A non-transitory machine-readable storage medium comprising instructions that, when executed by one or more processors of a machine, cause the machine to at least:
access descriptors in metadata that is descriptive of a first item and of a second item, the descriptors and metadata corresponding to a metadata model that organizes the descriptors into multiple tiers of the metadata model, the descriptors including a first descriptor of the first item and a second descriptor of the second item;
access, from a database communicatively coupled to the machine, the metadata model that organizes the descriptors into the multiple tiers;
create a group of descriptors by grouping the accessed first and second descriptors into the group of descriptors based on the accessed first and second descriptors being both represented in a same tier among the multiple tiers of the accessed metadata model that corresponds to the first and second descriptors, the grouping being performed by the one or more processors of the machine;
access, via a device of a user communicatively coupled to the machine via a network, biometric data including a heart rate of the user;
determine a first activity in which the user is engaged based on contextual data that correlates the first item and the second item with multiple locations of the user and the biometric data of the user received from the device of the user via the network;
generate a user profile based on the first activity of the user and the created group of descriptors into which the first and second descriptors were grouped based on the first and second descriptors being both represented in the same tier among the multiple tiers of the accessed metadata model that corresponds to the first and second descriptors;
store the group within the user profile as corresponding to the first activity determined based on the multiple locations and the biometric data of the user; and
recommend, in response to a second activity of the user matching the first activity asso

Assignees

• Popp Phillip
• Chen Ching Wei
• Dimaria Peter C
• Cremer Markus K
• Gracenote Inc

Inventors

• Popp Phillip
• Chen Ching-Wei
• Dimaria Peter C
• Cremer Markus K

Classifications

• G06F16/636

  by using biological or physiological data · CPC title

• G06F16/9535 Primary

  Search customisation based on user profiles and personalisation · CPC title

• G06F16/68

  Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually · CPC title

• G06F17/30867 Primary

  Physics · mapped topic

• G06F17/30749

  Physics · mapped topic