Scanned Document AI Prompt Automation via One-Touch Buttons
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Users need to repeatedly input instruction sentences for generative AI services when processing images from scanned documents, which is cumbersome.
Innovation Solution
An image processing apparatus that includes a receiving unit for user input, an acquisition unit for document scanning, and a transmission unit to automatically transmit pre-registered instruction sentences to the AI service, allowing for one-touch button operation to process scanned documents.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If users input instruction sentences manually each time for AI service processing, then the AI service can process images accurately according to user requirements, but the operation becomes troublesome and time-consuming
Solution Approach 1:
The system performs preliminary action by automatically generating and transmitting instruction sentences based on pre-configured templates and current image data, eliminating the need for users to manually input instruction sentences each time while maintaining processing accuracy
Solution Approach 2:
The system enables self-service by automatically creating instruction sentences from image metadata and transmitting them to the AI service without requiring user intervention, allowing the system to serve itself in the instruction generation process
2Loss of time
If the same instruction sentence is transmitted for multiple images, then user input time is reduced, but the system cannot adapt to different processing requirements for different images
Solution Approach 1:
The system applies dynamics by making instruction sentences adaptive and changeable based on image-specific characteristics such as file format, dimensions, and content type, allowing the same template to generate different instruction sentences for different images while reducing user input time
Solution Approach 2:
The system changes parameters by dynamically adjusting instruction sentence content based on image metadata parameters such as resolution, format, and content type, enabling adaptable processing for different images without requiring manual user input for each image
Data Source
AI summary
An image processing apparatus includes a receiving unit configured to receive selection of a button from a user, an acquisition unit configured to acquire image data by reading an original document according to reception of the selection by the receiving unit, and a transmission unit configured to transmit an instruction sentence registered in association with the button by the user and to be used for processing that is performed using the image data by an artificial intelligence (AI) service and the image data to the AI service.