Audio Search via Trigger Event Time Sequence Matching

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Users face difficulties in searching audio data when they forget the title or lyrics of a song, as existing music applications lack efficient methods to retrieve audio information without explicit song details.

Innovation Solution

A method and apparatus that detect a trigger event, record time points, and match them to pre-stored reference time sequences to determine corresponding audio data, allowing users to search audio based on input time sequences reflecting audio change characteristics, such as tapping or shaking a mobile device.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If users search audio data using traditional methods (title, lyrics), then search accuracy is improved, but usability deteriorates when users forget song information

Engineering Contradiction:
Improvesearch accuracyVSAvoidusability
Core Design Contradiction:
Measurement precisionVSEase of operation

Solution Approach 1:

The patent replaces traditional text-based search mechanisms with acoustic signal-based search. Instead of requiring users to input textual information (title, lyrics), the system captures acoustic signals from user actions (tapping, shaking) and processes them through signal analysis to identify audio content, substituting mechanical/acoustic interaction for text input

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

Solution Approach 2:

The patent introduces an intermediary processing layer between user action and search result. The system uses signal processing components to capture, analyze, and transform physical user actions into searchable acoustic feature data, which then matches against reference time sequences to retrieve audio content

Inventive Principle:
Principle #24Intermediary (Mediator)

2Adaptability or versatility

If the system processes and analyzes audio signals in real-time, then search functionality is improved, but device complexity increases

Engineering Contradiction:
Improvesearch functionalityVSAvoidsystem complexity
Core Design Contradiction:
Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The patent applies preliminary action by pre-processing audio data during the audio creation and storage phase. Reference time sequences and acoustic feature data are extracted and stored in advance, allowing the search function to operate by comparing user-generated signals against these pre-prepared references rather than performing full real-time analysis of entire audio files

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The patent segments audio data into discrete time sequences with specific acoustic features. By dividing continuous audio into manageable temporal segments and extracting key characteristics from each, the system reduces the complexity of processing while maintaining comprehensive search capability across the entire audio content

Inventive Principle:
Principle #1Segmentation

Data Source

PatentUS11574009B2Method, apparatus and computer device for searching audio, and storage medium
Publication Date: 2023.02.07 GUANGZHOU KUGOU COMP TECH CO LTD
  • US11574009B2 patent drawing
  • US11574009B2 patent drawing
  • US11574009B2 patent drawing

AI summary

The present disclosure relates to a method for searching an audio, pertaining to the technical field of electronics. The method includes: detecting a predetermined trigger event in response to receiving a trigger instruction for searching an audio; recording a time point when a detected trigger event occurs each time upon detecting the predetermined trigger event once until a predetermined end event is detected, and acquiring recorded time points to obtain a time point sequence; selecting a target reference time sequence matching the time point sequence from pre-stored reference time sequences; and determining target audio data corresponding to the target reference time sequence based on a pre-stored corresponding relationship between audio data and the reference time sequence.