Automatic Media Summary System Using Template Population

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

The manual creation of media program summaries is time-consuming and costly, limiting their availability to only mainstream media programs, as existing methods do not efficiently generate summaries for diverse types of media content.

Innovation Solution

An automatic media summary creation system that analyzes presentation data, including audio and video components, to generate text and image data, which is then used to populate predefined templates, enabling the creation of summaries for various media programs.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If manual summary creation is used, then summary quality and accuracy are improved, but time consumption and cost increase significantly

Engineering Contradiction:
Improvesummary qualityVSAvoidtime consumption
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The patent replaces the manual mechanical process of human summarization with an automated computer system that uses speech recognition, natural language processing, and template-based generation to create media summaries automatically, eliminating the need for human operators to transcribe and write summaries manually

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system performs self-service by automatically analyzing media content, extracting key information, and generating summaries without requiring human intervention. The automated system processes audio tracks, identifies speakers, transcribes dialogue, and assembles summaries independently based on predefined templates and criteria

Inventive Principle:
Principle #25Self-service

2Measurement precision

If manual summary creation is used, then summary accuracy is improved, but production cost increases

Engineering Contradiction:
Improvesummary accuracyVSAvoidproduction cost
Core Design Contradiction:
Measurement precisionVSEase of manufacture

Solution Approach 1:

The patent replaces expensive manual labor with automated computer processing systems that use speech recognition technology, natural language processing algorithms, and template-based generation to create summaries at lower cost, while maintaining acceptable accuracy through systematic analysis of media content

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system uses template-based generation where predefined summary templates are automatically populated with extracted media information, creating consistent and accurate summaries through pattern matching and data insertion rather than manual writing, thereby reducing production costs while maintaining quality standards

Inventive Principle:
Principle #26Copying

3Productivity

If automatic summary creation is implemented, then productivity and cost-effectiveness are improved, but system complexity increases

Engineering Contradiction:
Improvesummary creation efficiencyVSAvoidsystem complexity
Core Design Contradiction:
ProductivityVSDevice complexity

Solution Approach 1:

The patent segments the summary creation process into distinct functional modules: audio track analysis, speaker identification, speech-to-text transcription, key information extraction, and template-based summary generation. This modular segmentation allows each component to be developed and optimized independently, managing overall system complexity while improving productivity

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The system uses predefined summary templates as intermediaries that bridge the gap between raw media data and final summaries. These templates act as structured frameworks that guide the automated extraction and presentation of information, simplifying the transformation process and reducing the complexity of generating varied summary types

Inventive Principle:
Principle #24Intermediary (Mediator)

4Measurement precision

If manual summarization is used, then summary quality is maintained, but availability is limited to mainstream content only

Engineering Contradiction:
Improvesummary qualityVSAvoidsummary availability
Core Design Contradiction:
Measurement precisionVSAdaptability or versatility

Solution Approach 1:

The patent creates a universal automated summary system that can process multiple media types and genres through a single integrated platform. The system uses genre-specific templates and adaptable extraction algorithms that work across diverse content including movies, television programs, and other media, enabling summary generation for niche and non-mainstream content that would be impractical to produce manually

Inventive Principle:
Principle #6Universality (Multi-functionality)

Data Source

PatentUS10290320B2Automatic media summary creation systems and methods
Publication Date: 2019.05.14 VERIZON PATENT & LICENSING INC
  • US10290320B2 patent drawing
  • US10290320B2 patent drawing
  • US10290320B2 patent drawing

AI summary

An exemplary method includes an automatic media summary creation system analyzing presentation data of a media program that includes at least one of an audio component and a video component, generating, based on the analyzing of the presentation data of the media program, a set of text data, selecting, based on an attribute of the media program, a predefined media summary template from a group of predefined media summary templates, and automatically generating a summary of the media program by using the generated set of text data to populate the selected predefined media summary template. Corresponding methods and systems are also described.