Assistive Digital Form Authoring Using Embedding Vectors
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional digital form authoring systems are inefficient as users must manually navigate through multiple menus and submenus to identify and add form elements, making the process time-consuming and labor-intensive.
Innovation Solution
An authoring system that uses machine learning models, such as Bidirectional Encoder Representations from Transformers, and collaborative filtering models to generate embedding vectors and identify candidate form elements and search outputs, allowing users to interact with intuitive user interface components to add elements to digital forms without extensive manual navigation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If users manually navigate through multiple menus and submenus to add form elements, then they can identify and add form elements to digital forms, but the process becomes time-consuming and labor-intensive
Solution Approach 1:
The system automatically identifies candidate form elements and search outputs by analyzing user interactions and embedding vectors, eliminating the need for users to manually navigate through menus. The authoring system serves itself by generating suggestions based on collaborative filtering models and embedding distance calculations, allowing users to simply select from presented options rather than actively searching through multiple interface levels.
Solution Approach 2:
The patent replaces the mechanical navigation process (manual menu browsing) with an automated information retrieval system using machine learning models. Instead of users physically navigating through interface hierarchies, the system computes embedding vectors, calculates distances in latent space, and retrieves relevant form elements automatically, substituting manual mechanical interaction with automated computational processes.
2Productivity
If the system uses machine learning models to generate embedding vectors and identify candidate elements, then identification speed improves, but computational costs increase
Solution Approach 1:
The system computes embedding vectors and distances for only the necessary candidate elements rather than processing all possible form elements. By calculating distances in the latent space and selecting top candidates based on distance thresholds, the system performs partial computation sufficient for identifying relevant elements without exhaustively processing the entire form element database, thus reducing unnecessary computational overhead.
Solution Approach 2:
The system pre-computes and stores embedding vectors for form elements in a database before they are needed during authoring operations. When users interact with the system, the pre-computed embeddings are readily available for distance calculations, eliminating the need to generate embeddings from scratch during real-time interactions. This preliminary preparation significantly reduces computational costs during actual form authoring while maintaining high identification speed.
Data Source
AI summary
In implementations of systems for assistive digital form authoring, a computing device implements an authoring system to receive input data describing a search input associated with a digital form. The authoring system generates an input embedding vector that represents the search input in a latent space using a machine learning model trained on training data to generate embedding vectors in the latent space. A candidate embedding vector included in a group of candidate embedding vectors is identified based on a distance between the input embedding vector and the candidate embedding vector in the latent space. The authoring system generates an indication of a search output associated with the digital form for display in a user interface based on the candidate embedding vector.