Composite Viewer Profile Generation for Group Media Recommendation

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Conventional media playback systems struggle to recommend content effectively to groups of viewers, as existing recommendation approaches often rely on single user profiles, failing to account for group settings and dynamic changes in viewer composition, leading to inappropriate content suggestions.

Innovation Solution

A media recommendation and consumption compositor (MRCC) system that detects individual viewers within a predefined viewing region, generates a composite viewer profile, computes content recommendations based on this profile, and dynamically adapts content playback in response to changes in viewer presence, ensuring appropriate content is displayed.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If conventional recommendation systems use single user profiles, then recommendations are personalized to individual users, but recommendations become inappropriate when multiple viewers are present

Engineering Contradiction:

Improveadaptability to group viewing contextVSAvoidappropriateness of content recommendations

Core Design Contradiction:

Adaptability or versatilityVSReliability

Solution Approach 1:

The system merges multiple individual viewer profiles into a composite group profile by combining profile data from all detected viewers. This composite profile serves as the basis for generating content recommendations that are appropriate for the entire group, resolving the contradiction between individual personalization and group appropriateness.

Inventive Principle:

Principle #5Merging (Combining)

Solution Approach 2:

The system dynamically updates the composite viewer profile as viewers are detected or leave the viewing area. When a new viewer is detected, their profile is added to the composite; when a viewer leaves, their profile is removed. This dynamic adaptation ensures recommendations remain appropriate as the group composition changes.

Inventive Principle:

Principle #15Dynamics

2Loss of information

If electronic programming guides list all available content options, then users have complete information about content availability, but users become overwhelmed and cannot identify desirable content

Engineering Contradiction:

Improvecompleteness of content informationVSAvoidease of identifying desirable content

Core Design Contradiction:

Loss of informationVSEase of operation

Solution Approach 1:

The system extracts and highlights only the most relevant content options from the complete available content space. By computing a content recommendation space based on the composite viewer profile, the system extracts a subset of recommended content that is most likely to be enjoyable for the group, removing the overwhelming aspect while preserving the ability to access complete information if needed.

Inventive Principle:

Principle #2Taking out (Extraction)

Solution Approach 2:

The system applies different quality levels of recommendation to different content options. Highly recommended content is prominently displayed with strong visual indicators, while other content receives less emphasis. This local differentiation in presentation quality helps users quickly identify desirable content without hiding the complete information.

Inventive Principle:

Principle #3Local quality

3Device complexity

If recommendation systems analyze single user profiles, then computational complexity is low, but the system fails to account for group settings and dynamic changes in viewer composition

Engineering Contradiction:

Improvecomplexity of profile analysisVSAvoidability to handle group viewing dynamics

Core Design Contradiction:

Device complexityVSAdaptability or versatility

Solution Approach 1:

The system segments the profile analysis task into two distinct phases: first, individual viewer profiles are analyzed separately (maintaining low computational complexity for each), and second, these individual profiles are combined to form a composite group profile. This segmentation allows the system to handle group dynamics while keeping the computational burden manageable through divide-and-conquer processing.

Inventive Principle:

Principle #1Segmentation

Data Source

PatentUS11109104B2Viewer compositing for enhanced media recommendation and consumption

Publication Date: 2021.08.31 DISH NETWORK LLC

AI summary

Novel techniques are described for viewer compositing using media playback systems for enhanced media recommendation and consumption. For example, a display device can be in communication with a media recommendation and consumption compositor (MRCC) system. When a group of viewers desires a shared media consumption experience, the MRCC system can detect the group of viewers and can obtain respective viewer profiles, which can be used to generate a composite profile representing a composite of the group of viewers. The MRCC system can determine an available content space indicating the content available for consumption and can compute a content recommendation space as a function of the composite viewer profile and the available content space that defines recommended content options for the composited group of viewers. A recommendation interface can be output to indicate recommended content options for selecting and viewing.