Voice-Enabled Web Form Interaction via Automatic Task Structure Extraction

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Completing web forms on devices with small displays or for users with physical and visual impairments can be inconvenient, as existing technologies do not effectively enable voice interaction with web pages without modifying or re-authoring the web content.

Innovation Solution

A method and system that automatically process web pages to generate voice-enabled dialog flows, allowing users to interact with web forms using voice input by converting spoken information into text and inserting it into fillable areas, without requiring re-authoring or modification of the web pages, using a processor to extract task structures, generate abstract representations, and provide dialog scripts for voice interaction.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If web forms are used on devices with small displays or without alphabetic input devices, then accessibility is improved, but ease of operation deteriorates

Engineering Contradiction:

ImproveaccessibilityVSAvoidease of operation

Core Design Contradiction:

Adaptability or versatilityVSEase of operation

Solution Approach 1:

The patent replaces mechanical input methods (keyboard typing, manual form filling) with voice-based acoustic input. The speech recognition system converts spoken words into text to populate web forms, eliminating the need for physical alphabetic input devices while maintaining form completion capability.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The patent introduces a speech recognition system as an intermediary between the user and the web form. This mediator captures voice input, processes it through speech-to-text conversion, and automatically fills the form fields, bridging the gap between voice communication and form submission.

Inventive Principle:

Principle #24Intermediary (Mediator)

2Device complexity

If voice interaction is enabled without modifying web pages, then device complexity is reduced, but ease of manufacture deteriorates

Engineering Contradiction:

Improvedevice complexityVSAvoidease of manufacture

Core Design Contradiction:

Device complexityVSEase of manufacture

Solution Approach 1:

The patent implements a self-service mechanism where the speech recognition system automatically analyzes the web page structure, identifies form elements, and generates appropriate voice prompts and interaction flows without requiring manual configuration or modification of the web content itself.

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The patent performs preliminary processing of the web page by analyzing its structure and extracting form information before voice interaction begins. This pre-processing creates a model of the form elements and their relationships, enabling the voice system to interact with the page without subsequent modifications.

Inventive Principle:

Principle #10Preliminary action

Data Source

PatentUS9690854B2Voice-enabled dialog interaction with web pages

Publication Date: 2017.06.27 MICROSOFT TECHNOLOGY LICENSING LLC

AI summary

Voice enabled dialog with web pages is provided. An Internet address of a web page is received including an area with which a user of a client device can specify information. The web page is loaded using the received Internet address of the web page. A task structure of the web page is then extracted. An abstract representation of the web is then generated. A dialog script, based on the abstract representation of the web page is then provided. Spoken information received from the user is converted into text and the converted text is inserted into the area.