Content source driven recommendation for given context of content delivery and display system

Patent metadata

Field	Value
Publication number	US-10810249-B2
Application number	US-201515502164-A
Country	US
Kind code	B2
Filing date	Aug 5, 2015
Priority date	Aug 5, 2014
Publication date	Oct 20, 2020
Grant date	Oct 20, 2020

Abstract

There is provided a computer device for providing recommendations to a user device associated with a user, the computer device including a processor configured to: determine a set of recommendations for the user based on a current user context; transmit a recommendation message to the user device based on the determined set of recommendations; monitor the information from which the set of recommendations are derived; in dependence on identifying a change in the information, transmitting a modified recommendation to the user device.

First claim

The invention claimed is:

1. A computer device for providing recommendations to a user device associated with a user, the computer device including a processor configured to:
determine a current user context;
determine a set of information from a set of content sources;
determine an initial set of recommendations for the user from the determined set of information based on the determined current user context, wherein the initial set of recommendations are derived from information provided by a first sub-set of the set of content sources, such that only the first sub-set of content sources are used for deriving the initial set of recommendations, the remaining content sources forming a second sub-set of content sources;
transmit a recommendation message to the user device based on the determined set of initial recommendations from the first sub-set of content sources;
monitor the whole set of information from which the initial set of recommendations are derived, including monitoring the first sub-set of content sources and the second sub-set of content sources, and watching for new items that are relevant to the user in their current context in either the first sub-set of content sources or the second sub-set of content sources;
monitor the user context for which the initial set of recommendations are determined;
in dependence on the user context changing, determining a new set of recommendations for the user; and
in dependence on identifying a change in the first sub-set of content sources or the in the first sub-set of content sources or the second sub-set of content sources, without the user context changing, transmitting a modified recommendation to the user device comprising recommendations derived from one or both of the first sub-set of content sources and the second sub-set of content sources.

2. The computer device of claim 1 , in which the processor is configured to transmit the recommendation message with identifiers associated with the recommendations.

3. The computer device of claim 1 wherein the context is one of multiple contexts of the user.

4. A recommendation engine including the computer device of claim 1 .

5. A content delivery system including a recommendation engine including the computer device of claim 1 and at least one user device, wherein the user device has a display and a processor configured to execute a consumer application which controls the display to display the recommendations based on receipt of the recommendation message.

6. The content delivery system of claim 5 wherein the processor of the user device is configured to display the current user context.

7. The content delivery system of claim 6 wherein the processor of the user device is configured to receive an input from the user to confirm or reject the displayed context.

8. The content delivery system of claim 5 further comprising multiple user devices, each user device supplying context data which is used to determine a context for the multiple user devices, and each of the multiple user devices receiving a respective recommendation message.

9. The computer device of claim 1 wherein the content sources include external data sources and information that is derived from external data sources reflects at least one of: ratings, Facebook entries, data from YouTube, and news feeds.

10. A recommendation system comprising:
a context engine for receiving context data, and generating a context for a user;
a filter for receiving user input data for a recommendation engine and for outputting a context dependent user input data; and
a recommendation engine, for receiving the context dependent user data, and for generating a recommendation message for the user, the recommendation engine including the computer device of claim 1 .

11. The recommendation system of claim 10 wherein the user input data comprises a user profile and a user viewing history data, wherein the filter outputs a context dependent user profile and a context dependent user viewing history to the recommendation engine, the recommendation engine the context dependent user profile and the context dependent user viewing history, the computer device being configured to generate the recommendation in dependence on such.

12. A method for providing recommendations to a user device associated with a user, comprising:
determining a current user context;
determining a set of information from a set of content sources;
determining an initial set of recommendations for the user from the determined set of information based on the determined current user context, wherein the initial set of recommendations are derived from information provided by a first sub-set of the set of content sources, such that only the first sub-set of content sources are used for deriving the initial set of recommendations, the remaining content sources forming a second sub-set of content sources;
transmitting a recommendation message to the user device based on the determined set of initial recommendations from the first sub-set of content sources;
monitoring the whole set of information from which the set of recommendations are derived, including monitoring the first sub-set of content sources and the second sub-set of content sources, and watching for new items that are relevant to the user in their current context in either the first sub-set or the second sub-set of content sources;
monitoring the user context for which the initial set of recommendations are determined;
in dependence on the user context changing, determining a new set of recommendations for the user; and
in dependence on identifying a change in the first sub-set of content sources or the second sub-set of content sources, without the user context changing, transmitting a modified recommendation to the user device comprising recommendations derived from one or both of the first sub-set of content sources and the second sub-set of content sources.

13. The method of claim 12 further comprising, in dependence on a change in the current user context, determining a new set of recommendations for the user based on the changed context, and transmitting a new recommendation message.

14. The method of claim 12 , further comprising transmitting a notification of the identified change.

15. The method of claim 12 , further comprising revising the recommendation message based on the change in information, and transmitting the revised recommendation message.

16. The method of claim 12 , further comprising transmitting the recommendation message with identifiers associated with the recommendations.

17. The method of claim 12 further comprising accessing a memory holding user profiles.

18. The method of claim 12 further comprising receiving context data for determining a context for the user.

19. The method of claim 12 wherein the content sources include external data sources and information that is derived from external data sources reflects at least one of: ratings, Facebook entries, data from YouTube, and news feeds.

Assignees

• Piksel Inc

Inventors

• Shaw Philip
• Brett Leigh
• Bullett Kristan
• Carvajal Jose
• Stekolshchik Felix
• Johar Puneet
• Maas Hans-Jurgen
• Heiland Peter
• Tillmann Ralf Wilhelm
• Christie Mark

Classifications

• G06Q10/40

  Business processes related to social networking or social networking services · CPC title

• H04N21/4668

  for recommending content, e.g. movies · CPC title

• G06F16/24578

  using ranking · CPC title

• G06F16/68

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

• G06F16/435 Primary

  Filtering based on additional data, e.g. user or group profiles · CPC title