Document Date Extraction Apparatus for Non-Standard Deadline Formats
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing document processing systems fail to accurately convert non-date format character strings into date format for deadline values during character recognition of images, leading to incorrect date extraction from documents like business reports.
Innovation Solution
An information processing apparatus that extracts deadline values from documents, generates a date format character string based on the recognized data, and outputs it, using a combination of character recognition, pattern matching, and calculation formulas to convert non-date format strings into valid date formats.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If character recognition is performed on document images, then text extraction is achieved, but non-date format deadline values cannot be converted to date format
Solution Approach 1:
The system changes the parameter of date representation by detecting non-date format strings (e.g., 'one month after issue') and converting them to standardized date format parameters using calculation formulas, thereby achieving both precision and adaptability
Solution Approach 2:
A date conversion unit is introduced as an intermediary component between the character recognition unit and the output system. This mediator detects non-date formats, applies conversion rules, and outputs standardized date formats, resolving the contradiction between maintaining extraction precision and handling format versatility
2Productivity
If only standard date format extraction is implemented, then extraction speed is maintained, but human-readable date expressions cannot be processed
Solution Approach 1:
The date processing function is segmented into two parallel paths: one for standard date formats (fast extraction) and one for non-date formats (conversion required). This segmentation maintains high processing speed for common cases while adding versatility for human-readable expressions through the conversion unit
3Measurement precision
If date conversion for non-date formats is added, then date accuracy is improved, but system complexity increases
Solution Approach 1:
The system applies partial conversion action by only converting non-date format strings when detected, rather than converting all date expressions. This selective approach improves deadline accuracy for human-readable formats while avoiding unnecessary processing complexity for already-standardized dates
Data Source
AI summary
An information processing apparatus includes a first extraction part that extracts a value corresponding to a first item, which is an item indicative of a deadline, from a result of character recognition with respect to an image acquired by reading a document which includes an item and a value corresponding to the item; a generation part that generates a second character string of a date format indicative of a date of the deadline based on the result of the character recognition in a case where the value extracted by the first extraction part is a first character string other than the date format; and an output part that outputs the generated second character string as the value corresponding to the first item.