Voice Command Resolution for Media Content Search

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

The increasing complexity of searching and selecting media content across various electronic devices, such as television receivers and smartphones, due to different user input controls and vast content options, makes it difficult for consumers to find and consume their preferred media.

Innovation Solution

A voice command resolution system that allows users to submit proposed metadata tags via audio clips, which are weighted, stored, and ranked by popularity, and presented in electronic programming guides, enabling users to easily find content using voice commands, with the system processing and analyzing voice commands to identify media content and perform actions like playback or recording.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If traditional user input controls are used across various electronic devices, then device functionality is maintained, but user complexity and difficulty in searching and selecting media content increases

Engineering Contradiction:
Improveease of searching and selecting media contentVSAvoidcomplexity of user input controls across devices
Core Design Contradiction:
Ease of operationVSDevice complexity

Solution Approach 1:

The patent implements a universal voice command interface that works across multiple electronic devices (television receivers, smartphones, virtual assistant devices) to search and select media content. The voice recognition system provides a single, consistent method for user input that functions across all devices, eliminating the need to learn different controls for each device type.

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

Solution Approach 2:

The patent replaces traditional mechanical input methods (remote control buttons, keyboard typing, touchscreen gestures) with voice-based acoustic input. This substitution eliminates the physical interaction complexity associated with different device interfaces while maintaining full functionality for media content search and selection.

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

2Measurement precision

If voice command resolution system processes all metadata tags equally, then completeness of search is maintained, but search result quality decreases due to incorrect or low-value tags

Engineering Contradiction:
Improveaccuracy of search resultsVSAvoidnumber of metadata tags processed
Core Design Contradiction:
Measurement precisionVSQuantity of substance

Solution Approach 1:

The patent changes the parameter of metadata tag evaluation from binary (present/absent) to weighted (quality-based scoring). Each metadata tag is assigned a weight based on its relevance and accuracy, allowing the system to prioritize high-quality tags while still considering the full set of available tags. This transforms the search mechanism from simple tag matching to weighted tag evaluation.

Inventive Principle:
Principle #35Parameter changes

Solution Approach 2:

The patent applies different quality levels (weights) to different metadata tags based on their relevance and accuracy. Instead of treating all tags uniformly, the system identifies and emphasizes high-quality, relevant tags while downweighting incorrect or less useful tags, thereby improving search result precision without discarding any potential information sources.

Inventive Principle:
Principle #3Local quality

Data Source

PatentEP3906547B1Voice control for media content search and selection
Publication Date: 2023.06.21 DISH NETWORK TECHNOLOGIES INDIA PTE LTD
  • EP3906547B1 patent drawingFigure 1
  • EP3906547B1 patent drawingFigure 2
  • EP3906547B1 patent drawingFigure 3

AI summary

Various techniques are described herein for supporting voice command control of electronic programming guides (EPGs) and other media content selection systems. The voice input hardware and software components of a remote control device, television receiver, smartphone, virtual assistant, and/or other media device may receive voice commands from a user corresponding to a selection of a media content. In response to the received voice input, the media device may perform a speech-to-text conversion of the voice input, and then perform an analysis of the command text to determine one or more content selections of the user. The analysis may include identifying within the command text one or more television channel names, program names, or other media content names, as well as identifying other instructions, preferences, or other meaningful insights from the command text.