Context-based recommendation system

Patent metadata

Field	Value
Publication number	US-10555045-B2
Application number	US-201415021256-A
Country	US
Kind code	B2
Filing date	Sep 11, 2014
Priority date	Sep 11, 2013
Publication date	Feb 4, 2020
Grant date	Feb 4, 2020

Abstract

A content delivery server configured to select from multiple content items a set of content items for display to a user at a user terminal, the content delivery server having access to content identifiers, identifying content items for delivery; a processor operating a content selection program which is arranged to receive the context data for different contexts and to select a set of content items in dependence on the context data, wherein the content items in the set vary with the context data, such that the content of items in a first set for a user in a first context are different from the content of items in a second set for the same user in a second context, and to transmit a recommendation message to the user terminal comprising a set of content identifiers.

First claim

The invention claimed is:

1. A content delivery server configured to select from multiple content items a set of content items for display to a user at a user device, the content delivery server having access to content identifiers and identifying content items for delivery, the content delivery server comprising:
a context collector for receiving context data from a plurality of user devices, the context data from each user device comprising a plurality of context parameters of the user device, where each context parameter defines a characteristic of each user device measured locally at each user device;
a context summarizer for summarizing the context data received from the plurality of user devices into anonymous data sets, each anonymous data set associated with a context, and each anonymous data set comprising a plurality of the context parameters, wherein the context defines a user behavior at a user device;
a context engine for comparing the context data of a given user device to the anonymous data sets summarizing the context data received from the plurality of users and determining at least one probability of a context of the user of the given user device in dependence on comparing its context data to the anonymous data sets summarizing the context data received from the plurality of users, assessing whether the at least one probability exceeds a threshold, determining each context for which the probability exceeds the threshold as being a context of the given user device, determining at least one recommendation for the given user device based on the determined contexts; and transmitting a recommendation message to the given user device, the recommendation message comprising at least one content identifier in dependence on the at least one recommendation, wherein the comparison with the anonymous data sets summarizing the context data received from the plurality of users is used to adjust the determined context.

2. A content delivery server according to claim 1 , wherein the content identifiers identify different types of content selected from video, short form video, social fees, news read.

3. A content delivery server according to claim 1 , wherein the set of content items includes at least one video asset.

4. A content delivery server according to claim 1 , wherein each set of content items includes different types of items.

5. A content delivery server according to claim 1 , wherein the type of content items varies with context.

6. A content delivery server according to claim 1 , wherein the content of content items varies with context.

7. A content delivery server according to claim 1 , wherein the number of content items varies with context.

8. A content delivery server according to claim 1 , wherein the server has access to a user profile holding preferences of a user for use by a content selection program.

9. A content delivery server according to claim 8 , wherein each user profile comprises multiple sub profiles for the user, each sub profile associated with a respective context, wherein the associated sub profile is selectable by context and/or by the user.

10. A content delivery server according to claim 8 , wherein the content selection program comprises a recommendation algorithm which selects the content item based on a first source of content in a first context and on a second source of content in a second context.

11. A content delivery server according to claim 1 , wherein a source of content is social media or a breaking news item.

12. A content delivery server according to claim 1 , wherein a source of content is a live feed updating the user device or a live feed accessible to the server.

13. A content delivery server according to claim 1 , where the user device comprises:
a display for displaying content items to a user;
at least one context sensor configured to sense a characteristic of the user device and generate a context data item;
a context collector configured to:
receive at least one context data item;
perform calculations based on the at least one context data item; and
generate context data, and

an interface for transmitting the generated context data to a content delivery server and for receiving a recommendation message from the content delivery server comprising a set of content item identifiers for content items selected based on at least one inferred probability of a context of the user, wherein a context defines a user behavior at the user device, and each probability of a context is inferred in dependence on the transmitted context data, wherein the display is operable to display the selected content items.

14. A content delivery server as claimed in claim 13 , wherein the context data includes information about live streams supplied to the user device.

15. A content delivery server as claimed in claim 13 , wherein the context sensor comprises one of: a clock; a location module; Bluetooth; WiFi.

16. A content delivery server as claimed in claim 13 , further comprising a context setting component operable to display configurable context settings to a user.

17. A content delivery server as claimed in claim 13 , wherein the user device comprises a connection to a video asset server for accessing video assets identified by the recommendation message and/or a connection to content sources for accessing content identified by the recommendation message.

18. The content delivery server according to claim 1 , in which the context engine is configured to transmit the determined context of the user device to the user device, and receive a confirmation of the determined context.

19. A method for delivering content by selecting from multiple content items a set of content items for display to a user at a user device, the method comprising:
receiving context data from a plurality of user devices, the context data from each user device comprising a plurality of context parameters of the user device, where a context parameter defines a characteristic of each user device measured locally at each user device;
summarizing the context data received from the plurality of user devices into anonymous data sets, each anonymous data set associated with a context, and each anonymous data set comprising a plurality of the context parameters, wherein the context defines a user behavior at a user device;
comparing the context data of a given user device to the anonymous data sets summarizing the context data received from the plurality of users;
determining at least one probability of a context of the user of the given user device in dependence on comparing its context data to the anonymous data sets summarizing the context data received from the plurality of users;
assessing whether the at least one probability exceeds a threshold;
determining each context for which the at least one probability exceeds the threshold as being a context of the user device;
determining at least one recommendation for the given user device based on the determined contexts; and
transmitting a recommendation message to each user device comprising at least one content identifier in dependence on the at least one recommendation, wherein the comparison with the anonymous data sets summarizing the context data received from the plurality of users is used to adjust the determined context.

20. The method of claim 19 further comprising:
transmitting the determined context of the user device to the user device, and
receiving a confirmation of the determined context of the given user.

Assignees

• Piksel Inc

Inventors

• Shaw Philip Antony
• Heiland Peter
• Tillmann Ralf Wilhelm
• Maas Hans-Juergen

Classifications

• H04N21/6582

  Data stored in the client, e.g. viewing habits, hardware capabilities, credit card number (arrangements where receivers interact with the broadcast H04H20/38) · CPC title

• H04N21/2668

  Creating a channel for a dedicated end-user group, e.g. insertion of targeted commercials based on end-user profiles {(information retrieval from the Internet by querying with filtering and personalisation G06F16/9535; arrangements for replacing or switching information during the broadcast H04H20/10; push services over packet-switching network H04L12/1859; adaptation of message content in packet-switching networks H04L51/063)} · CPC title

• H04N21/812

  involving advertisement data (advertising per se G06Q30/02) · CPC title

• H04N21/25891

  being end-user preferences (retrieval of video data in a video database based on user preferences G06F16/739; arrangements for recognizing users' preferences H04H60/46; user profiles in network data switching protocols H04L67/306; processing of user preferences or user profiles in wireless networks H04W8/18) · CPC title

• H04N21/4383

  Accessing a communication channel · CPC title