Static Form Structure Extraction for Reflowable Conversion
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for digitizing forms require manual intervention from content authors to convert static forms into reflowable forms, which is time-consuming, expensive, and prone to errors, and existing document structure extraction techniques struggle to accurately disambiguate closely spaced form structures, leading to coarse and poorly reflowable forms.
Innovation Solution
A method that uses a hierarchical, multi-modal approach with two analytics engines to automatically extract form elements and determine logical associations between them, converting static forms into reflowable forms by identifying low-level elements like textruns and widgets, and grouping them into high-level elements such as textblocks, text fields, and choice groups, using prediction models trained end-to-end for accurate grouping and spatial relationship maintenance.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of manufacture
If manual content authoring is used to convert static forms to reflowable forms, then the conversion can be completed with existing tools, but the process is time-consuming and expensive
Solution Approach 1:
The system performs automatic form structure extraction and reflowable form generation without requiring manual content authoring. The extraction system autonomously identifies form elements, determines their hierarchical relationships, and generates reflowable forms, eliminating the need for human intervention in the conversion process.
Solution Approach 2:
The patent replaces the manual mechanical process of content authoring with an automated computational system. The extraction system uses machine learning models and algorithms to automatically extract form structures and generate reflowable forms, substituting human labor with an automated digital system.
2Device complexity
If existing document structure extraction techniques are used, then the extraction process is simple, but the techniques struggle to accurately disambiguate closely spaced form structures
Solution Approach 1:
The extraction system segments the form document into discrete form elements (text blocks, form fields, tables, images) and processes each element individually. This segmentation allows the system to accurately identify and disambiguate closely spaced form structures by treating them as separate, identifiable units with defined spatial relationships.
Solution Approach 2:
The system enhances the extraction process by incorporating spatial dimensionality analysis. It determines the spatial relationships and hierarchical structures of form elements in two-dimensional space, allowing accurate disambiguation of closely spaced elements by analyzing their positional coordinates and spatial arrangements.
3Productivity
If static forms are digitized without reflowable capabilities, then the digitization process is straightforward, but the forms are difficult or impossible to use on devices with various screen sizes
Solution Approach 1:
The system generates dynamic reflowable forms that can adapt their layout and content presentation based on the display characteristics of different devices. The extracted form structures include metadata about spatial relationships and hierarchical organization, enabling the forms to dynamically reflow and reorganize content to suit various screen sizes and device types.
Solution Approach 2:
The extraction system creates universal form structures that can function across multiple device types and platforms. By extracting the underlying logical structure and spatial relationships of form elements, the system generates forms that can be rendered and interacted with uniformly across desktop computers, mobile devices, tablets, and other platforms with varying screen dimensions.
Data Source
AI summary
Techniques described herein extract form structures from a static form to facilitate making that static form reflowable. A method described herein includes accessing low-level form elements extracted from a static form. The method includes determining, using a first set of prediction models, second-level form elements based on the low-level form elements. Each second-level form element includes a respective one or more low-level form elements. The method further includes determining, using a second set of prediction models, high-level form elements based on the second-level form elements and the low-level form elements. Each high-level form element includes a respective one or more second-level form elements or low-level form elements. The method further includes generating a reflowable form based on the static form by, for each high-level form element, linking together the respective one or more second-level form elements or low-level form elements.