Automated Content Interruption Point Identification

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Manual processes for identifying content interruption points for advertisements in content distribution are inefficient and inflexible, requiring substantial human resources and not adaptable to individual user preferences.

Innovation Solution

Automated content interruption point identification using metadata, sound, lighting, and visual transitions to dynamically select when and how often primary content is interrupted for auxiliary content, such as advertisements, based on user preferences and detected user information.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If manual processes are used to identify content interruption points, then human decision-making can select appropriate advertisement insertion points, but the process requires substantial human resources and is inefficient

Engineering Contradiction:

Improveaccuracy of interruption point identificationVSAvoidefficiency of content interruption point identification

Core Design Contradiction:

Measurement precisionVSProductivity

Solution Approach 1:

The system enables automated identification of content interruption points using machine learning models that analyze content features independently, eliminating the need for manual human review while maintaining accurate identification of suitable advertisement insertion points

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

Manual human decision-making processes are replaced with automated machine learning algorithms that analyze content characteristics, sound levels, lighting changes, and scene transitions to identify interruption points, substituting mechanical human labor with computational systems

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Stability of the object's composition

If manual processes are used to identify content interruption points, then each identified interruption point is consistently utilized, but the process is inflexible and cannot adapt to user preferences

Engineering Contradiction:

Improveconsistency of interruption point utilizationVSAvoidflexibility to user preferences

Core Design Contradiction:

Stability of the object's compositionVSAdaptability or versatility

Solution Approach 1:

The system transforms static, fixed interruption point selection into a dynamic process where machine learning models continuously analyze content features and user preferences to adaptively determine interruption points, enabling both consistency through systematic analysis and flexibility through preference-based customization

Inventive Principle:

Principle #15Dynamics

Solution Approach 2:

The system incorporates user feedback mechanisms where user preferences and viewing behavior are analyzed to refine and adjust interruption point selection, creating a feedback loop that maintains consistency in systematic analysis while adapting to individual user preferences over time

Inventive Principle:

Principle #23Feedback

3Quantity of substance

If advertising revenue is used to offset content costs, then content can be provided at reduced cost or free to consumers, but consumers must tolerate or consume advertising

Engineering Contradiction:

Improvecost of content to consumerVSAvoidadvertising tolerance burden on consumer

Core Design Contradiction:

Quantity of substanceVSObject-affected harmful factors

Solution Approach 1:

The system applies localized quality control by selecting specific interruption points where advertisements are inserted based on content analysis, ensuring advertisements appear at appropriate locations rather than uniformly throughout, thereby reducing consumer burden while maintaining revenue models

Inventive Principle:

Principle #3Local quality

Solution Approach 2:

The system changes the parameters of advertisement delivery by using machine learning to optimize interruption point selection based on content characteristics and user preferences, transforming the advertisement delivery from a fixed, intrusive model to a dynamic, context-aware model that reduces consumer burden

Inventive Principle:

Principle #35Parameter changes

Data Source

PatentUS9633262B2Content interruption point identification accuracy and efficiency

Publication Date: 2017.04.25 MICROSOFT TECHNOLOGY LICENSING LLC

AI summary

Automated content interruption point identification improves the accuracy with which potential content interruption points are identified, and increases the efficiency of content interruption point identification and content distribution. Potential interruption points are automatically identified based on transitions occurring within the content, including changes in the sound level, changes in the light, or brightness, level, changes in people visible in a scene of the content, transitions that are identified by content metadata, and other types of transitions. In providing content to a content consumer, a determination is made whether to interrupt the provision of the content, at one or more of the identified potential content interruption points, based on factors including interruption point metadata, metadata associated with auxiliary content that would be inserted, and user information, which includes explicitly specified user settings, as well as detected user information.