Recommending content based on user profiles clustered by subscription data

Patent metadata

Field	Value
Publication number	US-10311478-B2
Application number	US-201514744378-A
Country	US
Kind code	B2
Filing date	Jun 19, 2015
Priority date	Dec 31, 2014
Publication date	Jun 4, 2019
Grant date	Jun 4, 2019

Abstract

A method for recommending content based on user profiles clustered by subscription data includes receiving usage data of users. The usage data for each user includes device usage data and subscription data associated with the one or more applications installed on the user device. The method further includes receiving a recommendation request from a first user device of a first user for new subscription data and determining first usage data of the first user. The method also includes identifying a second user having second usage data that has a threshold similarity to the first usage data amongst the users. The method includes determining the new subscription data as being at least some of the subscription data of the second usage data that is different than the subscription data of the first usage data and outputting the new subscription data to the user device of the first user.

First claim

What is claimed is:

1. A method comprising:
receiving, at a computing device, usage data of users,
wherein the usage data for each of the users comprises device usage data associated with a user device of a corresponding user and subscription data associated with one or more applications installed on the user device, and
wherein user devices include a first user device of a first user and a second user device of a second user;
receiving, at the computing device, a recommendation request from the first user device of the first user for new subscription data;
determining, using the computing device, first usage data of the first user;
determining a total distance between first usage data elements of the first usage data and second usage data elements of second usage data, wherein when the total distance equals zero, the first usage data and the second usage data include same data elements;
identifying, using the computing device, the second user having the second usage data that has a threshold similarity to the first usage data from among the users based on a value of the total distance;
selecting the second user having the second usage data when the total distance is greater than zero, the second user data having the threshold similarity to the first usage data,
wherein the usage data of the users includes the first usage data and the second usage data;
determining, at the computing device, the new subscription data as being at least some of the subscription data of the second usage data that is different than the subscription data of the first usage data; and
outputting, from the computing device, the new subscription data to the first user device of the first user.

2. The method of claim 1 , wherein the device usage data comprises device data defining at least one of a device location, a device operating system, or a list of the one or more applications installed on the corresponding user device.

3. The method of claim 1 , wherein the subscription data of the first usage data comprises one or more subscription tags to content access mechanisms, each subscription tag associated with one of the one or more applications installed on the user device, and each subscription tag associated with one or more entities or categories.

4. The method of claim 3 , wherein the categories comprise at least one of a book category, a business category, an education category, an entertainment category, a food and dining category, a games category, a health and fitness category, a lifestyle category, a music and videos category, a news category, a weather category, a photo category, a productivity category, a social media category, or a sports category.

5. The method of claim 1 , wherein the identifying of the second user having the second usage data that has the threshold similarity to the first usage data further comprises:
determining the total distance by calculating
D P1,P2 =√{square root over ( d s1 2 +d s2 2 + . . . +d sn 2 )}

where D P1,P2 is the total distance, P 1 is the first usage data, P 2 is the second usage data,d sn is a distance between a corresponding one of the first usage data elements and a corresponding one of the second usage data elements with respect to a 1−n th known data element
D P1,P2 .

6. The method of claim 1 ,
wherein the new subscription data comprises:
a content access mechanism having a reference to a corresponding application installed on the user device and indicating a content performable operation for the corresponding application, and
an application access mechanism having a reference to the corresponding application installed on the user device and indicating a general performable operation for the corresponding application,

wherein the general performable operation is different from the content performable operation,
wherein the content access mechanism is associated with the subscription data, and
wherein the content access mechanism is different than the application access mechanism.

7. The method of claim 6 , further comprising:
receiving, at the computing device from the user device, an indication of a user selectable link; and
executing, using the computing device, the access mechanism associated with the user selectable link.

8. The method of claim 1 , further comprising:
grouping, using the computing device, a plurality of the users having the threshold similarity between the usage data corresponding to the plurality of users.

9. The method of claim 1 , further comprising, at the computing device, if a distance between the second usage data and the first usage data is less than a predetermined threshold, then including the at least some of the subscription data of the second usage data in the new subscription data,
wherein while using the computing device and while identifying the second user as having the second usage data that has the threshold similarity to the first usage data, determining whether the distance between the second usage data and the first usage data is less than the predetermined threshold.

10. A method comprising:
sending, from a user device to a recommendation system, usage data of a first user,
wherein the usage data comprises device usage data associated with the user device and subscription data associated with one or more applications installed on the user device,
wherein the subscription data defines one or more subscriptions to content feeds, and
wherein each subscription associated with an application is installed on the user device;
sending a subscription recommendation request from the user device to the recommendation system;
receiving, at the user device, one or more recommendation results transmitted from the recommendation system,
wherein each of the one or more recommendation results comprises a content access mechanism having a reference to one of the one or more applications installed on the user device,
wherein each of the content access mechanisms indicates a content performable operation for a corresponding one of the one or more applications,
wherein the one or more recommendation results are based on subscription data of a second user having usage data that has a threshold similarity to the usage data of the first user when a total distance is greater than zero, wherein when the total distance equals zero, the usage data of the first user and the usage data of the second user include same data elements, and
wherein the one or more recommendation results comprises at least some of the subscription data of the usage data of the second user that is different than the subscription data of the usage data of the first user; and
displaying, on a display, a graphical user interface including the one or more recommendation results,
wherein each of the one or more recommendation results comprises a content user selectable link associated with a corresponding content access mechanism.

11. The method of claim 10 , further comprising:
receiving, at the user device, an indication to execute one of the content access mechanisms; and
executing, at the user device, the one of the content access mechanisms to cause a corresponding one of the one or more applications to enter a corresponding content application state associated with the one or more content access mechanisms.

12. The method of claim 11 ,
wherein each of the one or more recommendation results further comprises application access mechanisms having a reference to the corresponding one of the one or more applications that is installed on the user device, and
wherein each of the application access mechanisms indicates an application performable operation for the corresponding one

Assignees

• Samsung Electronics Co Ltd

Inventors

• Dai Xueying
• Glover Eric J

Classifications

• G06Q30/0255 Primary

  based on user history · CPC title

• H04L67/306

  User profiles · CPC title

• H04L67/22

  Electricity · mapped topic

• G06Q30/0267

  Wireless devices · CPC title

• H04L67/535

  Tracking the activity of the user (network monitoring arrangements H04L43/00; recording of computer activity G06F11/34) · CPC title