Paper Sheet Handling Apparatus Unrecognized Data Collection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional paper sheet handling apparatuses burden users with the need to retain new or unrecognized paper sheets for data collection and updates, as incorrect recognition results require manual investigation and data collection from these sheets.
Innovation Solution
The apparatus enables users to perform data collection processing for unrecognized paper sheets, allowing for the storage and updating of recognition data within the device, eliminating the need for users to retain the actual sheets until the manufacturer collects them.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If the paper sheet handling apparatus uses existing recognition data to identify paper sheets, then recognition can be performed efficiently, but new or modified paper sheets cannot be correctly recognized
Solution Approach 1:
The system performs preliminary data collection when a paper sheet cannot be recognized, storing the image data and rejection reason in memory before manufacturer intervention. This preliminary action ensures that when new or modified paper sheets appear, the system has already captured their characteristics for future recognition updates.
Solution Approach 2:
The system implements a feedback mechanism where rejection information (both that a sheet was rejected and the reason for rejection) is stored and later used to update recognition data. This feedback loop allows the system to learn from unrecognized sheets and improve its recognition capability for future operations.
2Manufacturing precision
If the manufacturer requests users to retain unrecognized paper sheets for data collection, then recognition data can be updated accurately, but user burden increases
Solution Approach 1:
The system performs self-service data collection by automatically capturing and storing image data and rejection reasons for unrecognized paper sheets without requiring user intervention. The apparatus serves itself by collecting the necessary recognition data, eliminating the need for users to retain physical sheets until manufacturer collection.
Solution Approach 2:
Instead of requiring users to retain original paper sheets, the system creates digital copies (images) of unrecognized sheets and stores them in memory. These digital copies contain all necessary visual information for recognition analysis, replacing the need for physical sheet retention while maintaining data quality for manufacturer updates.
3Reliability
If the system collects and stores data from unrecognized paper sheets, then recognition accuracy improves, but device memory requirements increase
Solution Approach 1:
The system extracts only the essential rejection information (that recognition failed and the specific reason for failure) rather than storing complete detailed analysis of every unrecognized sheet. This extraction approach captures the necessary data for recognition improvement while minimizing memory consumption by storing only critical failure modes.
Solution Approach 2:
The system stores rejection reasons and image data selectively for sheets that cannot be recognized, rather than processing and storing data for all paper sheets. This partial action approach focuses resources on the specific cases where recognition fails, improving accuracy for problematic sheets without the overhead of processing every sheet equally.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
One object is to acquire from a paper sheet circulating in the market data for updating the data for recognition. A paper sheet handling apparatus used for recognizing a paper sheet and the like includes a recognition unit that recognizes a paper sheet, an operation unit for instructing execution of a data collection processing, and a control unit that controls, in the data collection processing that is executed after an instruction operation is performed by using the operation unit, data from a paper sheet that is not correctly recognized by the recognition unit, and a memory that stores therein the data collected by the control unit.