Document Field Image Extraction for Form Automation

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing software programs require manual entry of information, which is time-consuming, laborious, and prone to errors, affecting user experience, customer satisfaction, and sales.

Innovation Solution

An electronic device that receives a document description from a user, prompts for information associated with a field, captures an image of the field, extracts information using OCR and radial image analysis, and populates the form, reducing the need for manual data entry.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If manual entry of information is used, then users can provide data from forms, but the process is time-consuming and laborious

Engineering Contradiction:
Improveform completion speedVSAvoidtime for manual data entry
Core Design Contradiction:
ProductivityVSLoss of time

Solution Approach 1:

The patent replaces the mechanical manual typing process with an optical image recognition system. The electronic device captures an image of the form field and automatically extracts the information through optical character recognition, eliminating the need for manual mechanical entry of data.

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

Solution Approach 2:

The form completion system performs self-service by automatically extracting information from captured images. The electronic device autonomously processes the form data without requiring user intervention for typing, validating the core data entry function itself.

Inventive Principle:
Principle #25Self-service

2Reliability

If manual entry of information is used, then users can input data, but errors occur in the provided information

Engineering Contradiction:
Improveaccuracy of form dataVSAvoiderrors in manual data entry
Core Design Contradiction:
ReliabilityVSObject-generated harmful factors

Solution Approach 1:

The patent replaces error-prone manual typing with automated optical recognition. The system captures an image of the form field and uses character recognition algorithms to extract data, eliminating human transcription errors and improving data accuracy.

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

Solution Approach 2:

The system incorporates validation feedback mechanisms that check the extracted information against expected formats and ranges. The electronic device can identify and prompt users to correct potential errors in the automatically extracted data, ensuring higher reliability.

Inventive Principle:
Principle #23Feedback

3Reliability

If users validate all provided data, then errors can be detected, but the validation process is time-consuming and laborious

Engineering Contradiction:
Improvedata validation completenessVSAvoidtime for data validation
Core Design Contradiction:
ReliabilityVSLoss of time

Solution Approach 1:

The validation process performs self-service through automated algorithms that check the extracted data against predefined criteria. The electronic device automatically validates the information without requiring manual user verification of each field, significantly reducing validation time.

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The system provides automated feedback on data validity, immediately identifying and flagging errors in the extracted information. This real-time feedback mechanism eliminates the need for time-consuming manual validation while maintaining high reliability.

Inventive Principle:
Principle #23Feedback

4Loss of information

If users provide all information on a form, then complete data is captured, but wasted effort occurs on irrelevant data

Engineering Contradiction:
Improvecompleteness of form dataVSAvoideffort on irrelevant data
Core Design Contradiction:
Loss of informationVSLoss of time

Solution Approach 1:

The patent extracts only the specific information needed for the form by capturing an image of the relevant field and using targeted optical character recognition. The system extracts only the necessary data points rather than requiring users to provide or validate all form information.

Inventive Principle:
Principle #2Taking out (Extraction)

Solution Approach 2:

The system applies local quality by focusing the image capture and recognition process on specific form fields rather than the entire document. The electronic device prompts users to capture images of particular fields, extracting information locally where needed rather than processing the whole form uniformly.

Inventive Principle:
Principle #3Local quality

Applied Scientific Principles

This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.

Function Achieved in This Case

Facilitates efficient and accurate form completion, reducing errors and improving user experience, leading to increased customer satisfaction and sales.

Implementation Method 1

the image may include a digital photograph. Alternatively, the image may include a real-time video stream provided by an imaging device

Methodology Applied
Scientific EffectLight reflection: Reflection

Implementation Method 2

extracting the information may involve optical character recognition. For example, the optical character recognition may include a radial image analysis technique that identifies a boundary of the field in the region

Methodology Applied
Scientific EffectOptical character recognition: Image Processing

Data Source

PatentUS12026639B2Interactive technique for using a user-provided image of a document to collect information
Publication Date: 2024.07.02 INTUIT INC
  • US12026639B2 patent drawing
  • US12026639B2 patent drawing
  • US12026639B2 patent drawing

AI summary

In a collection technique, a user (such as a taxpayer) provides information (such as income-tax information) by submitting an image of a document, such as an income-tax summary or form. In particular, the user may provide a description of the document. In response, the user is prompted for the information associated with the field in the document. Then, the user provides the image of a region in the document that includes the field. Based on the image, the information is extracted, and the field in the form is populated using the extracted information. The prompting, receiving, extracting and populating operations may be repeated for one or more additional fields in the document.