Form Definition Generation via Interactive Recognition Feedback
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional methods for form recognition require expert knowledge to generate new form definition information, making it difficult for general users to create or modify form layouts, as they need to interview experts to obtain form layout information.
Innovation Solution
An information processing apparatus and method that acquires first form definition information, recognizes and extracts specific items and values from form images, and displays the recognition results, while also allowing users to input and generate second form definition information, thereby simplifying the process for general users.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If conventional form recognition methods are used, then form layout information can be recognized, but expert knowledge is required to generate new form definition information making it difficult for general users
Solution Approach 1:
The system enables general users to generate form definition information themselves through an interactive interface where they can input corrections and modifications to recognition results. The system automatically processes these inputs to create form definition information without requiring expert intervention, allowing users to serve themselves in the form definition generation process.
Solution Approach 2:
The system displays recognition results to users and accepts their feedback in the form of corrections and modifications. This feedback loop allows users to guide the form definition generation process by indicating what should be recognized differently, and the system uses this feedback to generate appropriate form definition information.
2Measurement precision
If expert engineers interview general users to obtain form layout information, then accurate form definition can be generated, but this process is time-consuming and requires expert intervention
Solution Approach 1:
The system performs preliminary form image recognition automatically before user review, pre-processing the form image to extract candidate form definition information. This preliminary action provides a starting point that users can then refine, eliminating the need for experts to conduct time-consuming interviews from scratch while maintaining accuracy through user feedback.
Solution Approach 2:
The system acts as an intermediary between the form image and the final form definition, automatically generating candidate definitions that users can then refine. This intermediary processing reduces the time required compared to direct expert interviews while maintaining accuracy through the user feedback loop.
3Adaptability or versatility
If form definition information is changed or created by general users, then user autonomy is improved, but the complexity of the process makes it too difficult for general users to perform
Solution Approach 1:
The system empowers general users to independently generate and modify form definition information through a simplified interface. Users can input corrections and modifications without needing to understand the underlying complex processes, and the system automatically handles the generation of form definition information based on their inputs.
Solution Approach 2:
The system replaces the complex manual process of form definition creation with an automated recognition system that users can guide through simple feedback. Instead of requiring users to manually create form definitions from scratch, the system uses automatic recognition combined with user feedback to generate definitions, substituting complex mechanical processes with automated intelligence.
Data Source
AI summary
An information processing apparatus includes circuitry configured to acquire first form definition information defining a positional relationship between one or more items and a respective value of the one or more items stored in a memory, recognize and extract a specific item set with a specific character string and a specific value of the specific item from data of a form image based on the first form definition information as a recognition result, and display, on a display, the recognition result and an input reception section used for receiving an input of second form definition information.