Autofill System Using Crowdsourced Learning for Form Accuracy

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Users face inefficiencies and errors when manually filling electronic forms due to the time-consuming and error-prone nature of entering personal and authentication information, and existing autofill solutions struggle with accuracy due to varied form coding.

Innovation Solution

An autofill system that utilizes crowdsourcing and machine learning to improve accuracy by collecting user corrections and using them to train a machine learning classifier, supplementing human supervision in semantic analysis to identify and fill form elements effectively.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Extent of automation

If traditional text recognition and HTML-based autofill solutions are used, then automation is achieved, but accuracy deteriorates due to varied form coding

Engineering Contradiction:

Improveautofill automationVSAvoidform element identification accuracy

Core Design Contradiction:

Extent of automationVSMeasurement precision

Solution Approach 1:

The system implements feedback loops where user corrections of autofilled forms are collected and used to retrain the machine learning model. This continuous feedback mechanism allows the system to learn from errors and improve accuracy over time while maintaining high automation levels.

Inventive Principle:

Principle #23Feedback

Solution Approach 2:

The system performs self-improvement by automatically collecting correction data from users and using it to retrain its own machine learning model. This self-service capability enables the system to adapt to varied form coding without requiring manual reprogramming or external intervention.

Inventive Principle:

Principle #25Self-service

2Measurement precision

If manual form filling is used, then accuracy is maintained, but productivity deteriorates due to time consumption

Engineering Contradiction:

Improveform filling accuracyVSAvoidform filling speed

Core Design Contradiction:

Measurement precisionVSProductivity

Solution Approach 1:

The machine learning model acts as an intermediary between manual form filling and complete automation. It pre-processes and suggests form element mappings based on learned patterns, reducing the cognitive load and time required for manual verification while maintaining high accuracy through user feedback integration.

Inventive Principle:

Principle #24Intermediary (Mediator)

3Adaptability or versatility

If diverse form coding variations are supported, then adaptability is improved, but device complexity increases

Engineering Contradiction:

Improveform coding compatibilityVSAvoidsystem complexity

Core Design Contradiction:

Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The system replaces complex rule-based mechanical processing with a machine learning model that learns patterns from data. This substitution allows the system to handle diverse form coding variations through learned representations rather than explicit rules, reducing maintainability complexity while improving adaptability.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Data Source

PatentUS11080597B2Crowdsourced learning engine for semantic analysis of webpages

Publication Date: 2021.08.03 DASHLANE

AI summary

A method for autofilling an electronic form is provided. Elements of the electronic form are identified. A value for each identified elements of the electronic form is determined. The electronic form is automatically filled with the determined values. During the automatically filling of the electronic form, the determined value is provided in a field corresponding to each of the elements. A user input is received on the provided value. The received user input includes a correction to a first value provided in a first field of the electronic form. An autofill application is trained using the received user input.