User profile and its location in a clustered profile landscape

Patent metadata

Field	Value
Publication number	US-9767221-B2
Application number	US-90107510-A
Country	US
Kind code	B2
Filing date	Oct 8, 2010
Priority date	Oct 8, 2010
Publication date	Sep 19, 2017
Grant date	Sep 19, 2017

Abstract

Delivering targeted content includes collecting, via at least one tangible processor, user activity data for users during a specified time period. questions asked by the users during the specified time period are extracted from the user activity data, via the at least one tangible processor, and stored in user profiles for the users. The user profiles are clustered, via the at least one tangible processor, based on the questions asked. Targeted content is delivered, via the at least one tangible processor, to a subset of the users based on the clustering.

First claim

What is claimed is:

1. A method of delivering targeted content, comprising:
extracting from user activity data, collected for users via a tangible processor during a specified time period determined before the user activity data is collected, quantitative attributes including previous purchase history of the users, the previous purchase history including time between purchases and average cost per item purchased, and qualitative attributes including emotions of the users based on a speech analysis of a portion of the user activity data, and questions asked by the users during the specified time period;
storing the quantitative attributes and the qualitative attributes in user profiles for the users such that the user profiles of the users are searched according to one or more of the quantitative attributes and the qualitative attributes;
plotting values for the quantitative attributes and the qualitative attributes;
determining a distance between the plotted values of the quantitative attributes, and a distance between the plotted values of the qualitative attributes;
contemporaneously clustering a first subset of the user profiles into a first group of users based on the distance between the plotted values of the quantitative attributes, and a second subset of the user profiles into a second group of users based on the distance between the plotted values of the qualitative attributes; and
delivering targeted content to one of the first group of users or second group of users based on the clustering, the targeted content including an advertisement, a recommendation, an answer and content rendered according to display requirements for a user device.

2. The method according to claim 1 ,
wherein one or more of the first subset or the second subset of the user profiles are dynamic user profiles.

3. The method according to claim 1 ,
wherein one or more of the first subset or the second subset of the user profiles are static user profiles.

4. The method according to claim 1 ,
wherein the user activity data includes details of purchasing items via an entity.

5. The method according to claim 1 , further comprising:
extracting, from the user activity data, speech characteristics based on the speech analysis,
wherein the emotions of the users are determined based on the speech characteristics.

6. The method according to claim 5 , further comprising:
storing demographic information as one of the quantitative attributes, the demographic information being obtained from the speech analysis of the portion of the user activity data, in the user profiles.

7. The method according to claim 1 , further comprising:
extracting, from the user activity data, geolocation data for at least one user as one of the quantitative attributes,
wherein the clustering is further based on the geolocation data.

8. The method according to claim 1 , further comprising:
extracting, from the user activity data, user activity data corresponding to similar users,
wherein the clustering is further based on the user activity data corresponding to similar users.

9. The method according to claim 8 ,
wherein the similar users are determined to be similar based on demographic information as one of the quantitative attributes for the users stored in the user profiles.

10. The method according to claim 1 ,
wherein the targeted content is globally accessible by a plurality of entities.

11. The method according to claim 1 ,
wherein a user profile is actively configured by a corresponding user.

12. The method according to claim 1 , further comprising:
determining a generalized prediction of future user activity based on the clustering and a user profile.

13. The method according to claim 1 , further comprising:
determining preferred websites for a user, based on the user activity data.

14. A system for delivering targeted content, comprising:
a memory that stores executable instructions; and
a processor that executes the executable instructions,
wherein, when executed by the processor, the executable instructions cause the system to:
extract, from user activity data collected for users during a specified time period determined before the user activity data is collected, quantitative attributes including previous purchase history of the users, the previous purchase history including time between purchases and average cost per item purchased, and qualitative attributes including emotions of the users based on a speech analysis of a portion of the user activity data, and questions asked by the users during the specified time period;
store the quantitative attributes and the qualitative attributes in user profiles for the users such that the user profiles of the users are searched according to one or more of the quantitative attributes and the qualitative attributes;
plot values for the quantitative attributes and the qualitative attributes;
determine a distance between the plotted values of the quantitative attributes, and a distance between the plotted values of the qualitative attributes;
contemporaneously cluster a first subset of the user profiles into a first group of users based on the distance between the plotted values of the quantitative attributes, and a second subset of user profiles into a second group of users based on the distance between the plotted values of the qualitative attributes; and
deliver targeted content to one of the first group of users or second group of users based on the clustering, the targeted content including an advertisement, a recommendation, an answer and content rendered according to display requirements for a user device.

15. A non-transitory computer readable storage medium that stores a set of executable instructions for delivering targeted content, the set of executable instructions directing a processor to perform acts of:
extracting, from user activity data collected for users during a specified time period determined before the user activity data is collected, quantitative attributes including previous purchase history of the users, the previous purchase history including time between purchases and average cost per item purchased, and qualitative attributes including emotions of the users based on a speech analysis of a portion of the user activity data, and questions asked by the users during the specified time period;
storing the quantitative attributes and the qualitative attributes in user profiles for the users such that the user profiles of the users are searched according to one or more of the quantitative attributes and the qualitative attributes;
plotting values for the quantitative attributes and the qualitative attributes;
determining a distance between the plotted values of the quantitative attributes, and a distance between the plotted values of the qualitative attributes;
contemporaneously clustering a first subset of the user profiles into a first group of users based on the distance between the plotted values of the quantitative attributes, and a second subset of user profiles is clustered into a second group of users based on the distance between the plotted values of the qualitative attributes; and
delivering targeted content to one of the first group of users or second group of users based on the clustering, the targeted content including an advertisement, a recommendation, an answer and content rendered according to display requirements for a user device.

Assignees

• Bangalore Srinivas
• Feng Junlan
• Johnston Michael James Robert
• Mishra Taniya
• At & T Ip I Lp

Inventors

• Bangalore Srinivas
• Feng Junlan
• Johnston Michael James Robert
• Mishra Taniya

Classifications

• G06F17/30976 Primary

  Physics · mapped topic

• G06F17/30997

  Physics · mapped topic

• G06F17/30345

  Physics · mapped topic

• G06F16/907

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

• G06F16/90332 Primary

  Natural language query formulation or dialogue systems · CPC title