AI Clipboard Transfer for OCR-Based Mobile Data Entry
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods lack an efficient and convenient way to copy real-life documents and photographs of screens from one computing system to another, requiring manual entry, which is time-consuming and inefficient for tasks like uploading expenses or entering data into applications.
Innovation Solution
A system using AI-driven computer vision and OCR to extract content from digital photographs of physical documents or screens, determine the pertinent target application, and automatically enter the information without manual input, utilizing RPA robots or clipboard applications for seamless transfer.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If manual data entry is used to transfer information from physical documents to computing systems, then data accuracy can be maintained through user verification, but time consumption and operational effort increase significantly
Solution Approach 1:
The system performs automatic data extraction and transfer without human intervention. The mobile device captures images of documents, the server automatically extracts text and data using OCR and CV technologies, identifies target applications, and transfers data autonomously, allowing the system to serve itself rather than requiring manual user input for each data transfer task
Solution Approach 2:
The patent replaces the mechanical process of manual typing and data entry with automated optical and computational systems. OCR technology converts optical text from images into digital text, CV algorithms extract structured data, and RPA bots perform automatic data population in target applications, substituting human manual operations with automated technological processes
2Extent of automation
If automated data extraction is implemented using AI models, then data transfer efficiency improves, but system complexity increases due to multiple AI models and processing steps
Solution Approach 1:
The automated data transfer system is divided into distinct functional modules: image capture module on mobile device, OCR processing module for text extraction, CV processing module for data extraction, application identification module for determining target applications, and data transfer module for population. Each module performs a specific function, making the complex system manageable and maintainable through clear separation of concerns
Solution Approach 2:
A server acts as an intermediary between the mobile device and target computing systems. The mobile device captures images and sends them to the server, which performs all AI processing (OCR, CV, application identification) and then transfers the extracted data to the appropriate target applications. This intermediary architecture centralizes complexity in the server while keeping client devices simple
3Measurement precision
If multiple AI models are used for accurate content extraction and application identification, then data processing accuracy improves, but computational resources and processing time increase
Solution Approach 1:
The system performs preliminary actions by first capturing the document image and preprocessing it before applying complex AI models. The OCR model extracts text first, which then informs the CV model's data extraction process. Application identification is performed before actual data transfer, preparing the system in advance. These preliminary steps organize and structure the data beforehand, making subsequent processing more efficient and reducing redundant computations
Solution Approach 2:
The system dynamically selects and applies different AI models based on the specific task requirements. For text extraction, OCR models are used; for structured data extraction from forms or tables, CV models are applied; for determining target applications, categorization models are employed. This dynamic, task-specific model selection optimizes computational resource usage by applying only the necessary processing power for each specific extraction challenge rather than using all models for every task
Data Source
AI summary
Artificial intelligence (AI)-driven, automatic data transfer including semantic associations between a source from a mobile device and a target computing system is disclosed. A digital photograph of the contents of physical documents or a screen of another computing system is obtained with the mobile device, the contents from the digital photograph are extracted, and pertinent target application(s) are determined using AI. The extracted, semantically matched contents are then entered into target application(s) of the target computing system without requiring manual entry by a user.