System and method for recommending content to a user based on user's interest

Patent metadata

Field	Value
Publication number	US-2016109941-A1
Application number	US-201414559201-A
Country	US
Kind code	A1
Filing date	Dec 3, 2014
Priority date	Oct 15, 2014
Publication date	Apr 21, 2016
Grant date	—

Abstract

Systems and methods for recommending content to a user based on the user's interests are described herein. In one example, the method comprises receiving at least one image of the user, and analyzing the at least one image to determine one or more facial attributes of the user. The method further comprises processing the at least one image to determine the gaze parameters of the user, determining based on the gaze parameters, an object of interest of the user and retrieving the characteristics of the object of interest. The method further comprises ascertaining, based on the facial attributes, an emotional index associated with the user, and generating recommendations of the content for the user based in part on the emotional index and characteristics of the object of interest.

First claim

What is claimed is:

1 . A content recommendation system, comprising a processor and a memory coupled to the processor which is configured to be capable of executing programmed instructions comprising and stored in the memory to:
receive at least one image of a user; analyze the at least one image to determine one or more facial attributes of the user and one or more gaze parameters of the user; determine, based on the gaze parameters, an object of interest of the user; retrieve one or more characteristics of the object of interest; determine, based on the one or more facial attributes, an emotional index associated with the user; and generate one or more content recommendations for the user based at least in part on the emotional index and the one or more characteristics of the object of interest.

2 . The content recommendation system, as claimed in claim 1 , wherein the processor coupled to the memory is further configured to be capable of executing additional programmed instructions comprising and stored in the memory to:
detect one or more emotional transitions of the user based on one or more changes in the emotional index over a pre-defined time interval; and modify the one or more content recommendations based on the one or more emotional transitions.

3 . The content recommendation system, as claimed in claim 2 , wherein the processor coupled to the memory is further configured to be capable of executing additional programmed instructions comprising and stored in the memory to:
determine an interest level of the user in the object of interest based on the emotional index, one or more gaze parameters, or one or more emotional transitions; and modify the one or more content recommendations based on the interest level of the user.

4 . The content recommendation system, as claimed in claim 1 , wherein the processor coupled to the memory is further configured to be capable of executing additional programmed instructions comprising and stored in the memory to:
determine an action in which the object of interest is involved; classify the determined action into one or more genres; detect an emotional transition of the user upon the user consuming the determined action; and modify the one or more content recommendations based on the one or more genres and the detected emotional transition.

5 . The content recommendation system, as claimed in claim 4 , wherein the processor coupled to the memory is further configured to be capable of executing additional programmed instructions comprising and stored in the memory to:
compare the emotional transition of the user upon the user consuming content involving the object of interest, content involving the object of interest involved in one or more actions associated with the one or more genres, content involving one or more actions associated with the one or more genres and not including the object of interest; and modify the one or more content recommendations based on the comparison.

6 . The content recommendation system as claimed in claim 1 , wherein the processor coupled to the memory is further configured to be capable of executing additional programmed instructions comprising and stored in the memory to:
determine at least one image parameter associated with the at least one image; and enhance the at least one image comprising modifying the at least one image parameter associated with the at least one image.

7 . A method for recommending content, the method comprising:
receiving, by a content recommendation system, at least one image of a user; analyzing, by the content recommendation system, the at least one image to determine one or more facial attributes of the user and one or more gaze parameters of the user; determining, by the content recommendation system and based on the gaze parameters, an object of interest of the user; retrieving, by the content recommendation system, one or more characteristics of the object of interest; determining, by the content recommendation system and based on the one or more facial attributes, an emotional index associated with the user; and generating, by the content recommendation system, one or more content recommendations for the user based at least in part on the emotional index and the one or more characteristics of the object of interest.

8 . The method as claimed in claim 7 , further comprising:
detecting, by the content recommendation system, one or more emotional transitions of the user based on one or more changes in the emotional index over a pre-defined time interval; and modifying, by the content recommendation system, the one or more content recommendations based on the one or more emotional transitions.

9 . The method as claimed in claim 8 , further comprising:
determining, by the content recommendation system, an interest level of the user in the object of interest based on the emotional index, one or more gaze parameters, or one or more emotional transitions; and modifying, by the content recommendation system, the one or more content recommendations based on the interest level of the user.

10 . The method as claimed in claim 7 , further comprising:
determining, by the content recommendation system, an action in which the object of interest is involved; classifying, by the content recommendation system, the determined action into one or more genres; detecting, by the content recommendation system, an emotional transition of the user upon the user consuming the determined action; and modifying, by the content recommendation system, the one or more content recommendations based on the one or more genres and the detected emotional transition.

11 . The method as claimed in claim 10 , further comprising:
comparing, by the content recommendation system, the emotional transition of the user upon the user consuming content involving the object of interest, content involving the object of interest involved in one or more actions associated with the one or more genres, content involving one or more actions associated with the one or more genres and not including the object of interest; and modifying, by the content recommendation system, the one or more content recommendations based on the comparison.

12 . The method as claimed in claim 7 , further comprising:
determining, by the content recommendation system, at least one image parameter associated with the at least one image; and enhancing, by the content recommendation system, the at least one image comprising modifying the at least one image parameter associated with the at least one image.

13 . A non-transitory computer readable medium having stored thereon instructions for facilitating n-way high availability storage services comprising executable code which when executed by a processor, causes the processor to perform steps comprising:
receiving at least one image of a user; analyzing the at least one image to determine one or more facial attributes of the user and one or more gaze parameters of the user; determining, based on the gaze parameters, an object of interest of the user; retrieving one or more characteristics of the object of interest; determining, based on the one or more facial attributes, an emotional index associated with the user; and generating one or more content recommendations for the user based at least in part on the emotional index and the one or more characteristics of the object of interest.

14 . The non-transitory computer readable medium as claimed in claim 13 , wherein the executable code when executed by the processor further causes the processor to perform additional step

Assignees

• Wipro Ltd

Inventors

• Govindarajeswaran Maheshwaran
• Jeyaprasad Arjun Jeyarani Arun

Classifications

• G06K9/00315

  Physics · mapped topic

• G06F3/0304

  Detection arrangements using opto-electronic means (constructional details of pointing devices not related to the detection arrangement using opto-electronic means G06F3/033; optical digitisers G06F3/042) · CPC title

• G06T5/00

  Image enhancement or restoration · CPC title

• G06K9/0061

  Physics · mapped topic

• G06F3/012 Primary

  Head tracking input arrangements · CPC title