Topic based user profiles

• US 9,355,168 B1
• Filed: 03/05/2014
• Issued: 05/31/2016
• Est. Priority Date: 12/01/2010
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Liebald, Benjamin, Nandy, Palash, Davidson, Jamie, Ilvento, Christina
• Primary Examiner(s): Dang, Thanh-Ha
• Application Number:
  US14/198,495
• Time in Patent Office: 818 Days
• Field of Search: 707/727, 707/738
• US Class Current: 1/1
• CPC Class Codes: G06F 15/16 Combinations of two or more digital computers each having at least an arithmetic unit, a program unit and a register, e.g. for a simultaneous processing of several programs coordinating program control therefor G06F9/52; in regulating and control system G05B
• CPC Class Codes: G06F 16/285 Clustering or classification
• CPC Class Codes: G06F 16/337 Profile generation, learning or modification
• CPC Class Codes: G06F 16/435 Filtering based on additional data, e.g. user or group profiles
• CPC Class Codes: G06F 16/635 Filtering based on additional data, e.g. user or group profiles
• CPC Class Codes: G06F 16/735 Filtering based on additional data, e.g. user or group profiles
• CPC Class Codes: G06F 16/7867 using information manually generated, e.g. tags, keywords, comments, title and artist information, manually generated time, location and usage information, user ratings
• CPC Class Codes: G06F 3/0482 Interaction with lists of selectable items, e.g. menus
• CPC Class Codes: H04L 65/60 Network streaming of media packets
• CPC Class Codes: H04L 65/80 Responding to QoS

Abstract

A system and method for developing a user'"'"'s profile based on the user'"'"'s interaction with content items. A module on the client rendering the content items or the service including the content items tracks the user'"'"'s interactions with the content items and transmits the tracked data to a user analysis module. The user analysis module determines the topics associated with the interacted upon content items. The user analysis module then selects the topics for the user'"'"'s profiles based on the received tracked data and the associated topics. The selected topics are stored in association with the user profile.

Claims

1. A computer-implemented method for developing user profiles within a profile corpus, the method comprising:

determining topics associated with digital content items;

organizing user profiles of users into a plurality of demographic groups based on demographics of the users;

retrieving access data indicating interactions of users in a demographic group from one of the plurality of demographic groups with a plurality of the digital content items;

identifying the topics associated with the plurality of digital content items interacted with by the users from the demographic group as candidate topics to include in user profiles of the users in the demographic group based on the access data;

for each candidate topic, identifying, topics included in the user profiles of the users in the demographic group that co-occur in the user profiles with that candidate topic;

selecting, by a computer, a candidate topic from the candidate topics to include in a target user profile of a target user from the demographic group based on co-occurrence of the candidate topic with one or more topics included in the target user profile that were identified from the user profiles of the users in the demographic group as co-occurring with the candidate topic; and

adding the selected candidate topic to the target user profile of the target user from the demographic group.

2. The computer-implemented method of claim 1, wherein adding the selected candidate topic comprises:

adding the selected candidate topic to the target user profile of the target user from the demographic group responsive to the target user profile not including the selected candidate topic.

3. The computer-implemented method of claim 1, further comprising:

selecting a second candidate topic from the candidate topics to include in the target user profile of the target user from the demographic group based on co-occurrence of the second candidate topic with a second group of one or more topics included in the target user profile that were identified from the user profiles of the users in the demographic group as co-occurring with the second candidate topic;

or

increasing a topic strength between the second candidate topic and the target user profile responsive to the target user profile of the target user from the demographic group already including the second candidate topic.

4. The computer-implemented method of claim 1, further comprising:

calculating, for each of the candidate topics, a count at which the candidate topic co-occurs with the topics identified from the user profiles of the users in the demographic group;

ranking, by the computer, the candidate topics for the target user profile based on the count at which each of the candidate topics co-occurs with topics included in the target user profile; and

wherein selecting the candidate topic to add to the target user profile of the target user from the demographic group is based on a rank of the candidate topic in the ranking of candidate topics for the target user profile.

5. The computer-implemented method of claim 4, wherein ranking the candidate topics for the target user profile comprises calculating, for each candidate topic, a second count at which the candidate topic occurs across all user profiles in the profile corpus, the count at which the candidate topic co-occurs with the topics included in the user profiles of the users in the demographic group normalized based on the second count.

6. The computer implemented method of claim 4, wherein the ranking of the candidate topics is based in part on a topic strength between the candidate topic and the user profiles of the users from the demographic group in which the candidate topic co-occurs with the identified topics, the topic strength between the candidate topic and a user profile of a user based on at least one of:

a frequency of the user interacting with a digital content item associated with the candidate topic;

a duration of at least one interaction of the user with a digital content item associated with the candidate topic; and

an amount of time elapsed since a last user interaction of the user with a digital content item associated with the candidate topic.

7. The computer implemented method of claim 1, wherein the demographics of the users indicate one of more of a same age range and a gender classification for the user profiles of the users in the demographic group.

8. A computer system for developing user profiles within a profile corpus, the system comprising a non-transitory computer readable medium storing instructions to:

determine topics associated with digital content items;

organize user profiles of users into a plurality of demographic groups based on demographics of the users;

retrieve access data indicating interactions of users in a demographic group from one of the plurality of demographic groups with a plurality of the digital content items;

identify the topics associated with the plurality of digital content items interacted with by the users from the demographic group as candidate topics to include in user profiles of the users in the demographic group based on the access data;

for each candidate topic, identify topics included in the user profiles of the users in the demographic group that co-occur in the user profiles with that candidate topic;

select, by a computer, a candidate topic from the candidate topics to include in a target user profile of a target user from the demographic group based on co-occurrence of the candidate topic with one or more topics included in the target user profile that were identified from the user profiles of the users in the demographic group as co-occurring with the candidate topic; and

add the selected candidate topic to the target user profile of the target user from the demographic group.

9. The computer system of claim 8, wherein adding the selected candidate topic comprises:

adding the selected candidate topic to the target user profile of the target user from the demographic group responsive to the target user profile not including the selected candidate topic.

10. The computer system of claim 8, further comprising instructions to:

select a second candidate topic from the candidate topics to include in the target user profile of the target user from the demographic group based on co-occurrence of the second candidate topic with a second group of one or more topics included in the target user profile that were identified from the user profiles of the users in the demographic group as co-occurring with the second candidate topic;

or

increase a topic strength between the second candidate topic and the target user profile responsive to the target user profile of the target user from the demographic group already including the second candidate topic.

11. The computer system of claim 8, further comprising instructions to:

calculate, for each of the candidate topics, a count at which the candidate topic co-occurs with the topics identified from the user profiles of the users in the demographic group;

rank, by the computer, the candidate topics for the target user profile based on the count at which each of the candidate topics co-occurs with topics included in the target user profile; and

wherein select the candidate topic to add to the target user profile of the target user from the demographic group is based on a rank of the candidate topic in the ranking of candidate topics for the target user profile.

12. The computer system of claim 11, wherein the ranking of the candidate topics is based in part on a topic strength between the candidate topic and the user profiles of the users from the demographic group in which the candidate topic co-occurs with the identified topics, the topic strength between the candidate topic and a user profile of a user based on at least one of:

a frequency of the user interacting with a digital content item associated with the candidate topic;

a duration of at least one interaction of the user with a digital content item associated with the candidate topic; and

an amount of time elapsed since a last user interaction of the user with a digital content item associated with the candidate topic.

13. The computer system of claim 8, wherein the demographics of the users indicate one of more of a same age range and a gender classification for the user profiles of the users in the demographic group.

14. A non-transitory computer readable medium storing instructions for developing user profiles within a profile corpus, the instructions comprising:

determining topics associated with digital content items;

organizing user profiles of users into a plurality of demographic groups based on demographics of the users;

retrieving access data indicating interactions of users in a demographic group from one of the plurality of demographic groups with a plurality of the digital content items;

identifying the topics associated with the plurality of digital content items interacted with by the users from the demographic group as candidate topics to include in user profiles of the users in the demographic group based on the access data;

for each candidate topic, identifying topics included in the user profiles of the users in the demographic group that co-occur in the user profiles with that candidate topic;

selecting, by a computer, a candidate topic from the candidate topics to include in a target user profile of a target user from the demographic group based on co-occurrence of the candidate topic with one or more topics included in the target user profile that were identified from the user profiles of the users in the demographic group as co-occurring with the candidate topic; and

adding the selected candidate topic to the target user profile of the target user from the demographic group.

15. The non-transitory computer readable medium of claim 14, wherein adding the selected candidate topic comprises:

adding the selected candidate topic to the target user profile of the target user from the demographic group responsive to the target user profile not including the selected candidate topic.

16. The non-transitory computer readable medium of claim 14, further comprising:

selecting a second candidate topic from the candidate topics to include in the target user profile of the target user from the demographic group based on co-occurrence of the second candidate topic with a second group of one or more topics included in the target user profile that were identified from the user profiles of the users in the demographic group as co-occurring with the second candidate topic;

or

increasing a topic strength between the second candidate topic and the target user profile responsive to the target user profile of the target user from the demographic group already including the second candidate topic.

17. The non-transitory computer readable medium of claim 14, further comprising:

calculating, for each of the candidate topics, a count at which the candidate topic co-occurs with the topics identified from the user profiles of the users in the demographic group;

ranking, by the computer, the candidate topics for the target user profile based on the count at which each of the candidate topics co-occurs with topics included in the target user profile; and

wherein selecting the candidate topic to add to the target user profile of the target user from the demographic group is based on a rank of the candidate topic in the ranking of candidate topics for the target user profile.

18. The non-transitory computer readable medium of claim 17, wherein ranking the candidate topics for the target user profile comprises calculating, for each candidate topic, a second count at which the candidate topic occurs across all user profiles in the profile corpus, the count at which the candidate topic co-occurs with the topics included in the user profiles of the users in the demographic group normalized based on the second count.

19. The non-transitory computer readable medium of claim 17, wherein the ranking of the candidate topics is based in part on a topic strength between the candidate topic and the user profiles of the users from the demographic group in which the candidate topic co-occurs with the identified topics, the topic strength between the candidate topic and a user profile of a user based on at least one of:

a frequency of the user interacting with a digital content item associated with the candidate topic;

a duration of at least one interaction of the user with a digital content item associated with the candidate topic; and

an amount of time elapsed since a last user interaction of the user with a digital content item associated with the candidate topic.

20. The non-transitory computer readable medium of claim 14, wherein the demographics of the users indicate one of more of a same age range and a gender classification for the user profiles of the users in the demographic group.