Document Image File Naming via Preview Selection

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing document management methods require users to manually set item names and location information before scanning, making it cumbersome to extract specific information from scanned paper documents.

Innovation Solution

An information processing apparatus that displays a preview image, detects character areas selected by the user, extracts item name candidates based on the selected areas, and sets these as file names, allowing users to select and edit the item names easily.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If manual setting of item names and location information is required before scanning, then extraction accuracy is improved, but user workload and operation time increase

Engineering Contradiction:
Improveextraction accuracyVSAvoiduser workload
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The system automatically extracts item names and location information from the scanned document image without requiring manual user input. The extraction unit analyzes the document structure and automatically identifies field names and their corresponding values, allowing the system to serve itself rather than requiring user configuration for each extraction task

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The system performs preliminary extraction of item names and location information from the document image before the user needs to use this data. By pre-processing the document to automatically identify and extract these elements, the system prepares the data in advance, eliminating the need for users to manually set these parameters before scanning

Inventive Principle:
Principle #10Preliminary action

2Measurement precision

If manual setting of item names and location information is required before scanning, then extraction accuracy is improved, but ease of operation deteriorates

Engineering Contradiction:
Improveextraction accuracyVSAvoidease of operation
Core Design Contradiction:
Measurement precisionVSEase of operation

Solution Approach 1:

The extraction unit automatically analyzes the document image to identify item names and their locations without requiring user intervention. The system self-configures the extraction parameters by detecting document structures, field labels, and data positions, making the operation simple while maintaining accuracy

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The manual mechanical process of users setting item names and locations is replaced by an automated image analysis system. The extraction unit uses optical character recognition and pattern matching to automatically identify document elements, substituting human manual configuration with automated computational analysis

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

3Ease of operation

If automatic extraction is implemented without manual setting, then ease of operation is improved, but extraction accuracy may deteriorate

Engineering Contradiction:
Improveease of operationVSAvoidextraction accuracy
Core Design Contradiction:
Ease of operationVSMeasurement precision

Solution Approach 1:

The system replaces manual configuration with automated image analysis that maintains high accuracy. The extraction unit uses sophisticated algorithms to detect document structures, recognize field labels, and extract values with precision comparable to or exceeding manual setting, while significantly improving ease of operation

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system creates an accurate digital representation of the document structure by analyzing the image data. It copies the logical structure of the document (fields, labels, relationships) from the visual image into structured data format, maintaining the accuracy of the original document while enabling automated processing

Inventive Principle:
Principle #26Copying

Data Source

PatentUS11765292B2Information processing apparatus used for converting image to file, image processing system, method of controlling information processing apparatus, and storage medium
Publication Date: 2023.09.19 CANON KK
  • US11765292B2 patent drawing
  • US11765292B2 patent drawing
  • US11765292B2 patent drawing

AI summary

An information processing apparatus capable of reducing troublesome work of a user when converting an image obtained by newly scanning a business form to a file. An information processing apparatus that sets, when converting the image to a file, a file name of the image. A preview image of the scanned original is displayed, and user selection of a character area on the preview image is detected. An item name candidate area is extracted based on location information of the character area selected by the user on the preview image, and a character string included in the item name candidate area is set as an item name of a character string included in the character area selected by the user. The set item name is displayed as a file name rule such that the set item name is selectable by the user.