Dynamic Voice Interface for Web Form Automation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current voice-enabled systems, such as those using VoiceXML, are limited in their ability to handle dynamic webpages and require users to input information field by field, lacking flexibility and efficiency in interacting with databases and web applications, especially in scenarios like e-CRM and customer service.
Innovation Solution
A method that utilizes automatic speech recognition and dialog management to convert spoken information into text, automatically fill web-based forms, and communicate dynamic webpage content back to users via synthetic speech, enabling natural language dialog and improving interaction with databases and web applications.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If VoiceXML is used for voice-enabled interaction, then users can interact with web applications via voice, but the system requires scripted dialog flows and cannot handle dynamic webpage changes without reprogramming
Solution Approach 1:
The system dynamically generates dialog flows at runtime based on the actual webpage content and user interactions, rather than using fixed pre-scripted dialog trees. This allows the voice interface to adapt automatically to changes in webpage structure and content without requiring reprogramming of the VoiceXML code.
Solution Approach 2:
The system automatically parses webpage HTML content and generates appropriate dialog prompts and form field mappings without human intervention. The dialog manager autonomously handles the conversion of static webpage structures into dynamic voice interaction scripts, enabling the system to self-adapt to webpage changes.
2Manufacturing precision
If users input information field by field in forms, then each field can be accurately filled, but the interaction process becomes time-consuming and inefficient
Solution Approach 1:
The system performs preliminary parsing of the webpage form structure before user interaction begins. It pre-identifies all form fields, their data types, and validation requirements, then uses this preprocessed information to guide efficient data collection and form filling during the voice interaction.
Solution Approach 2:
The system combines multiple form field inputs into a single natural language utterance. Instead of requiring separate voice inputs for each field, users can provide information in conversational form, and the system automatically maps the spoken content to the appropriate form fields based on the pre-parsed structure.
3Adaptability or versatility
If dynamically generated webpages are used to provide customized responses, then user-specific information can be delivered, but the pages cannot be indexed by search engines and are difficult to deal with
Solution Approach 1:
The system acts as an intermediary between the static searchable webpage content and the dynamic customized responses. It parses the HTML structure of dynamically generated pages, extracts relevant information, and uses this structured data to maintain searchability while preserving the ability to deliver customized user-specific content.
Data Source
AI summary
A system and method provides a natural language interface to world-wide web content. Either in advance or dynamically, webpage content is parsed using a parsing algorithm. A person using a telephone interface can provide speech information, which is converted to text and used to automatically fill in input fields on a webpage form. The form is then submitted to a database search and a response is generated. Information contained on the responsive webpage is extracted and converted to speech via a text-to-speech engine and communicated to the person.