Voice Information Processing for Accurate Time Intent Recognition

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Smart alarm clocks face challenges in accurately setting alarms through voice interaction due to limitations in client data processing capabilities, requiring users to provide precise date and time information, which affects user experience.

Innovation Solution

An information processing method utilizing an information control center device, such as a cloud server, processes complex sound signals through voice recognition and semantic parsing to extract designated times, predicts intended times based on current time, and generates accurate target instructions for task execution, reducing hardware requirements on clients and enabling seamless voice interaction.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If voice interaction is implemented on the client device, then user convenience is improved, but the client's data processing capability is insufficient leading to inaccurate time understanding

Engineering Contradiction:
Improvevoice interaction convenienceVSAvoidtime understanding accuracy
Core Design Contradiction:
Ease of operationVSMeasurement precision

Solution Approach 1:

The patent introduces an information control center as an intermediary between the client device and the voice interaction process. The control center receives sound signals, performs semantic parsing to extract time information, and returns processed results to the client. This mediator handles the complex data processing that the client cannot perform independently, thereby maintaining both voice interaction convenience and time understanding accuracy.

Inventive Principle:
Principle #24Intermediary (Mediator)

Solution Approach 2:

The patent shifts the data processing dimension from the client device to the information control center. Instead of the client processing voice data locally (one-dimensional local processing), the system transitions to cloud-based processing (adding a new dimensional layer), allowing complex semantic analysis to be performed remotely while keeping the client interface simple.

Inventive Principle:
Principle #17Another dimension (Dimensionality change)

2Speed

If the client processes sound signals locally, then response time is reduced, but the processing accuracy and complexity handling capability deteriorate

Engineering Contradiction:
Improveresponse timeVSAvoidtime extraction accuracy
Core Design Contradiction:
SpeedVSManufacturing precision

Solution Approach 1:

The system performs preliminary actions by pre-processing sound signals and extracting time information on the information control center before the client needs the results. The control center prepares the processed time data in advance, so when the client requests alarm setting, the accurate time information is already available, maintaining both speed and accuracy.

Inventive Principle:
Principle #10Preliminary action

3Measurement precision

If keyword recognition is used for time extraction, then time information correctness is improved, but the system cannot handle diverse voice expressions

Engineering Contradiction:
Improvetime information correctnessVSAvoidvoice expression diversity
Core Design Contradiction:
Measurement precisionVSAdaptability or versatility

Solution Approach 1:

The patent implements a universal semantic parsing system on the information control center that can handle multiple types of voice expressions through a single unified processing framework. The system uses templates and rules that can adapt to various speech patterns, making it versatile for different user expressions while maintaining accurate time extraction through structured parsing.

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

Data Source

PatentEP4086895B1Information processing method, information control center device, and computer-readable storage medium
Publication Date: 2025.07.09 AISPEECH CO LTD
  • EP4086895B1 patent drawingFigure 1
  • EP4086895B1 patent drawingFigure 2
  • EP4086895B1 patent drawingFigure 3

AI summary

The present invention discloses an information processing method, an information control center device, and a computer-readable storage medium. The method comprises: obtaining semantic parsing information corresponding to a sound signal, the semantic parsing information including a designated time; performing a time prediction on the designated time based on a current time to determine an intended time; and generating a target instruction corresponding to the sound signal based on the intended time. With this method, the information control center device can process complex and diverse sound signals, and the designated time and target intention in a sound signal can be extracted from the semantic parsing information. Because of the time prediction on the semantic parsing information with the designated time, the designated time provided in the sound signal can be processed more accurately, and the voice interaction process is more accurate.