Personalised channel

Patent metadata

Field	Value
Publication number	US-10523989-B2
Application number	US-201515523050-A
Country	US
Kind code	B2
Filing date	Oct 29, 2015
Priority date	Oct 31, 2014
Publication date	Dec 31, 2019
Grant date	Dec 31, 2019

Abstract

There is disclosed a content delivery system for delivering content to a user, the system comprising a personalised schedule controller configured to receive content recommendations for a user including at least one constrained asset, and for generating a personalised schedule for the user in dependence on the at least one constrained asset included in the content recommendation.

First claim

The invention claimed is:

1. A content delivery system for delivering a personalised channel comprising content recommendations to a user, for a time window having a window predetermined start time and a window predetermined end time, the content delivery system comprising:
a recommendation engine configured to generate a personalised schedule with recommendations for the personalized channel for the user, wherein the recommendations include constrained assets and non-constrained assets; and
a personalised schedule controller configured to:
allocate the recommended constrained assets to a high priority, and allocate the recommended non-constrained assets to a low priority;
retrieve the high priority recommended constrained assets, compare each high priority recommended constrained asset to a constrained relevance threshold, and select one or more of the recommended constrained assets meeting the constrained relevance threshold for the personalised channel, wherein each of the recommended constrained assets has a start time and an end time, and wherein the personalised schedule controller is configured to time shift one or more of the recommended constrained assets to a different asset start time after the window predetermined start time and a different asset end time before the window predetermined end time, wherein recommended constrained assets are selected and if necessary time-shifted until no more can be added to the personalised channel, wherein each constrained asset does not overlap in time with any other constrained asset in the personalised channel as a result of the time-shifting; and
responsive to determining that the personalised channel contains time gaps, retrieve the low priority recommended non-constrained asset, compare each low priority non-constrained asset to a non-constrained relevance threshold, and select one or more of the recommended non-constrained assets meeting the non-constrained relevance threshold for the personalised channel, wherein each of the recommended non-constrained assets has a duration, and wherein the duration of each recommended non-constrained assets is within the personalised channel time window and does not overlap in time with any other selected recommended constrained asset or recommended non-constrained asset.

2. The content delivery system of claim 1 wherein the constrained asset is one of a live asset and a play-out constrained asset.

3. The content delivery system of claim 1 wherein for more than one type of constrained asset, different types of constrained assets are allocated to different priorities.

4. The content delivery system of claim 1 in which the content recommendations for the user are generated dynamically based on a user context, such that as the user context changes at any point the recommendations from the recommendation engine change, and as a consequence the personalised channel schedule changes.

5. The content delivery system of claim 1 wherein the constrained assets include linear assets and time limited assets and the non-constrained assets include persistent assets, wherein the recommendations include linear assets, limited lifetime assets, and persistent assets, and wherein the personalised schedule controller is further configured to:
allocate the recommended linear assets to the high priority, allocate the recommended limited lifetime assets to a medium priority, and allocate the recommended persistent assets to the low priority;
retrieve the high priority recommended linear assets, compare each high priority recommended linear asset to a linear relevance threshold, and select one or more of the recommended linear assets meeting the linear relevance threshold for the personalised channel which does not overlap with any other selected recommended linear asset;
if it is determined that the personalised channel contains gaps in time, retrieve the medium priority recommended limited lifetime assets, compare each medium priority limited lifetime asset to a limited lifetime relevance threshold, and select one or more of the recommended limited lifetime assets meeting the limited lifetime relevance threshold for the personalised channel which does not overlap in time with any other selected recommended linear asset or recommended limited lifetime asset; and
if it is determined that the personalised channel contains gaps in time, retrieve the low priority recommended persistent assets, compare each low priority persistent asset to a persistent relevance threshold, and select one or more of the recommended persistent assets meeting the persistent relevance threshold for the personalised channel, wherein each of the recommended persistent assets has a duration, and wherein the duration of each selected persistent asset is within the personalised channel window, and does not overlap in time with any other selected recommended media asset, recommended limited lifetime asset or recommended persistent asset;

wherein the personalised schedule controller is configured to select the at least one of the recommended linear assets or the recommended limited lifetime assets for the personalised schedule, and if necessary time shift the at least one of the recommended linear assets or the recommended limited lifetime assets to a different asset start time after the window predetermined start time and a different asset end time before the window predetermined end time.

6. The content delivery system of claim 1 wherein if there is a conflict at a given time within the personalised channel, an algorithm is used to select the conflicted assets.

7. The content delivery system of claim 1 wherein the recommendation engine is further configured to generate recommendations for the personalised channel for the user based on the user profile.

8. The content delivery system of claim 1 wherein there is provided a constrained asset which is not a time constrained asset.

9. The content delivery system of claim 1 wherein if a constrained asset is a live asset it is not time shifted.

10. The content delivery system of claim 6 wherein a constrained asset is time-shifted to resolve a conflict in time.

11. A method for delivering a personalised channel comprising content to a user, for a time window having a window predetermined start time and a window predetermined end time, comprising:
receiving content recommendations for the user for the time window from a recommendation engine, wherein the recommendations include at least one constrained asset and at least one non-constrained asset; and
generating a personalised schedule by:
allocating the recommended constrained assets to a high priority, and allocating the recommended non-constrained assets to a low priority;
retrieving the high priority recommended constrained assets, comparing each high priority recommended constrained asset to a constrained relevance threshold, and selecting one or more of the recommended constrained assets meeting the constrained relevance threshold for the personalised channel, wherein each of the recommended constrained assets has a start time and an end time, and time shifting one or more of the recommended constrained assets to a different asset start time after the window predetermined start time and a different asset end time before the window predetermined end time, and selecting recommended constrained assets until no more can be added to the personal channel, wherein each constrained asset does not overlap in time with any other constrained asset in the personal channel as a result of time-shifting; and
responsive to determining that the personalised channel contains gaps in time, retrieve the low priority recommended non-constrained assets, comparing each low pri

Assignees

• Piksel Inc

Inventors

• Shaw Philip
• Maas Hans-Jurgen
• Everett Sean

Classifications

• H04N21/251 Primary

  Learning process for intelligent management, e.g. learning user preferences for recommending movies (details of learning user preferences for the retrieval of video data in a video database G06F16/739; computer systems using learning methods G06N3/08) · 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

• H04N21/26258

  for generating a list of items to be played back in a given order, e.g. playlist, or scheduling item distribution according to such list (retrieval of multimedia data based on playlists G06F16/40) · CPC title

• H04N21/4668

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

• H04N21/26241 Primary

  involving the time of distribution, e.g. the best time of the day for inserting an advertisement or airing a children programme · CPC title