Universal Speech Recognition Service for Cross-Application Command Routing

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current speech recognition systems in smartphones and computing devices often require users to manually switch between applications or use specific commands to initiate voice requests, limiting seamless hands-free operation and efficient handling of spoken user requests across different applications.

Innovation Solution

Implementing a system that allows electronic devices to process spoken user requests, convert them into text, and determine the corresponding action executable by another application, enabling seamless transfer of commands between applications without manual intervention, such as using speech-to-text functionality integrated into music player and web browser applications.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If speech recognition software is integrated into multiple applications, then hands-free operation capability is improved, but system complexity increases

Engineering Contradiction:
Improvehands-free operation capabilityVSAvoidsystem complexity
Core Design Contradiction:
Ease of operationVSDevice complexity

Solution Approach 1:

The patent implements a universal speech recognition service that can be accessed by multiple applications through a common interface. Instead of embedding separate speech recognition systems in each application, the solution creates a shared service layer that provides speech-to-text conversion and command interpretation across different applications, thereby reducing overall system complexity while maintaining hands-free operation capabilities.

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

Solution Approach 2:

The patent introduces an intermediary speech recognition service layer between the user's spoken requests and the various applications. This mediator component receives audio input, converts it to text, interprets the command, and routes it to the appropriate application, simplifying the integration process for individual applications while enabling comprehensive hands-free operation across the system.

Inventive Principle:
Principle #24Intermediary (Mediator)

2Ease of operation

If automatic command transfer between applications is implemented, then user convenience is improved, but reliability of command execution decreases

Engineering Contradiction:
Improveuser convenienceVSAvoidcommand execution reliability
Core Design Contradiction:
Ease of operationVSReliability

Solution Approach 1:

The patent implements a feedback mechanism where the speech recognition service monitors and tracks the execution status of transferred commands. When a command is automatically transferred to another application, the system receives feedback regarding whether the command was successfully executed, allowing for error detection and potential retry mechanisms that maintain reliability while preserving automatic transfer convenience.

Inventive Principle:
Principle #23Feedback

Solution Approach 2:

The patent performs preliminary validation and routing preparation before automatic command transfer. The speech recognition service analyzes the spoken command in advance, determines the appropriate target application, and prepares the command for transfer with necessary context information. This preliminary action ensures that only well-formed, appropriately-routed commands are automatically transferred, maintaining execution reliability while enabling user convenience.

Inventive Principle:
Principle #10Preliminary action

Data Source

PatentEP3149926B1System and method for handling a spoken user request
Publication Date: 2019.06.19 YANDEX EURO
  • EP3149926B1 patent drawingFigure 1
  • EP3149926B1 patent drawingFigure 2
  • EP3149926B1 patent drawingFigure 3

AI summary

Method for handling a spoken user request of a user, executable by each one of at least two applications installed on an electronic device, comprising determining that the spoken user request corresponds to an action executable by an other one of the at least two of the applications; and causing execution of the action by the other one of the at least two of the applications. Method for handling a spoken user request received from a user of an electronic device, comprising detecting reception of a spoken user request by a first application; transferring the spoken user request to the second application by the first application; determining, by the second application, that the spoken user request corresponds to an action executable by a third application; and causing, by the second application, execution of the action by the third application. Electronic devices configured to carry out the methods are also disclosed.