Automated Assistant Entry Field Context Analysis

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing human-computer interaction systems using automated assistants struggle to efficiently process spoken utterances, often requiring lengthy verbatim inputs and consuming excessive computational resources.

Innovation Solution

The system processes audio data from spoken utterances to generate recognized text and determines whether to provide the recognized text or alternate content based on contextual parameters, reducing the need for lengthy inputs and conserving resources.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If the system uses verbatim speech-to-text recognition for all spoken utterances, then the user input is accurately captured, but the interaction time and computational resources increase excessively

Engineering Contradiction:
Improvespeech recognition accuracyVSAvoidinteraction time
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The system changes the parameter of speech processing by selectively applying different processing modes (verbatim recognition vs. alternate content generation) based on the entry field context, thereby reducing interaction time while maintaining accuracy where needed

Inventive Principle:
Principle #35Parameter changes

Solution Approach 2:

The system dynamically adjusts the speech processing approach based on real-time context analysis of the entry field, switching between full verbatim recognition and condensed alternate content generation to optimize both accuracy and efficiency

Inventive Principle:
Principle #15Dynamics

2Adaptability or versatility

If the system processes all spoken utterances through automated assistant actions, then the alternate content can be generated, but the computational resources and processing power are consumed excessively

Engineering Contradiction:
Improvecontent adaptation capabilityVSAvoidcomputational resource consumption
Core Design Contradiction:
Adaptability or versatilityVSUse of energy by moving object

Solution Approach 1:

The system applies different processing qualities to different contexts: full automated assistant processing is applied only when the entry field context benefits from alternate content generation, while simple verbatim recognition is used for other cases, thereby reducing overall computational resource consumption

Inventive Principle:
Principle #3Local quality

Solution Approach 2:

The system performs partial processing by analyzing only the necessary properties of the entry field context to determine whether alternate content is needed, avoiding excessive full processing for all utterances

Inventive Principle:
Principle #16Partial or excessive action

3Ease of operation

If the system requires explicit user input to switch between dictation and alternate content modes, then the user has control over the input mode, but the ease of operation decreases

Engineering Contradiction:
Improveinput simplicityVSAvoidsystem control complexity
Core Design Contradiction:
Ease of operationVSDevice complexity

Solution Approach 1:

The system serves itself by automatically determining whether verbatim recognition or alternate content generation is appropriate based on entry field context analysis, eliminating the need for explicit user commands to switch modes while maintaining operational control

Inventive Principle:
Principle #25Self-service

Data Source

PatentEP4553695A1Voice-controlled entry of content into graphical user interfaces
Publication Date: 2025.05.14 GOOGLE LLC
  • EP4553695A1 patent drawingFigure 1A
  • EP4553695A1 patent drawingFigure 1B
  • EP4553695A1 patent drawingFigure 1C

AI summary

Implementations set forth herein relate to an automated assistant that can selectively determine whether to incorporate a verbatim interpretation of portions spoken utterances into an entry field and/or incorporate synonymous content into the entry field. For instance, a user can be accessing an interface that provides an entry field (e.g., address field) for receiving user input. In order to provide input for entry field, the user can select the entry field and/or access a GUI keyboard to initialize an automated assistant for assisting with filling the entry field. Should the user provide a spoken utterance, the user can elect to provide a spoken utterance that embodies the intended input (e.g., an actual address) or a reference to the intended input (e.g., a name). In response to the spoken utterance, the automated assistant can fill the entry field with the intended input without necessitating further input from the user.