AI Input Classification for Reusing User Data Across Services

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing computing systems require users to repeatedly input similar information for various Internet services, lacking an efficient method to simplify this process using AI technology.

Innovation Solution

An electronic device equipped with a text classification model using machine learning to identify and classify input information, allowing automatic input into relevant fields of a user interface, utilizing optical character recognition (OCR) and machine learning models to streamline information input across applications.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If users repeatedly input similar information for various Internet services, then information can be provided to multiple services, but user effort and time consumption increase

Engineering Contradiction:
Improveinformation provision to multiple servicesVSAvoiduser input time
Core Design Contradiction:
Adaptability or versatilityVSLoss of time

Solution Approach 1:

The system performs preliminary action by classifying and storing input information in a database during the first service interaction. This pre-processed information is then automatically retrieved and input into subsequent services, eliminating the need for users to repeatedly enter the same information and significantly reducing time consumption.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The system enables self-service by automatically retrieving stored information and inputting it into different service interfaces without requiring user intervention. The machine learning model autonomously determines which stored information to retrieve and how to format it for different services, making the system self-sufficient in handling information reuse across services.

Inventive Principle:
Principle #25Self-service

2Measurement precision

If users manually input information for each service, then information can be accurately provided, but ease of operation decreases

Engineering Contradiction:
Improveinformation accuracyVSAvoidinformation input convenience
Core Design Contradiction:
Measurement precisionVSEase of operation

Solution Approach 1:

The system incorporates feedback mechanisms where the machine learning model continuously learns from user interactions and service responses. This feedback loop allows the system to improve its information classification and retrieval accuracy over time, ensuring that automatically input information maintains high accuracy while increasingly improving ease of operation.

Inventive Principle:
Principle #23Feedback

Solution Approach 2:

The system introduces an intermediary mechanism in the form of a machine learning-based information matching module. This intermediary automatically matches stored information with required service fields, serving as a mediator between the user's initial input and the multiple service interfaces, thereby maintaining accuracy while eliminating manual re-input requirements.

Inventive Principle:
Principle #24Intermediary (Mediator)

3Ease of operation

If a machine learning-based automatic input system is implemented, then ease of operation improves, but device complexity increases

Engineering Contradiction:
Improveinformation input convenienceVSAvoidsystem structure complexity
Core Design Contradiction:
Ease of operationVSDevice complexity

Solution Approach 1:

The system applies universality by implementing a single machine learning-based information classification and retrieval mechanism that serves multiple services simultaneously. This multi-functional approach consolidates what would otherwise require separate information handling systems into one unified framework, improving ease of operation across all services while managing complexity through shared infrastructure.

Inventive Principle:
Principle #6Universality (Multi-functionality)

Solution Approach 2:

The system uses copying by creating a standardized representation of user information in a centralized database structure. Instead of maintaining separate information storage mechanisms for each service, the system creates a universal information copy that can be retrieved and adapted for different service interfaces, simplifying the overall system architecture while enabling automatic information input across multiple services.

Inventive Principle:
Principle #26Copying

Data Source

PatentEP3676760B1Computing apparatus and information input method of the computing apparatus
Publication Date: 2025.11.12 SAMSUNG ELECTRONICS CO LTD
  • EP3676760B1 patent drawingFigure 1
  • EP3676760B1 patent drawingFigure 2
  • EP3676760B1 patent drawingFigure 3

AI summary

Provided are a method and apparatus for classifying and storing input information based on machine learning and artificial intelligence and automatically inputting the stored information. According to an exemplary embodiment, input information is classified and stored using machine learning, an input item to which the stored input information is to be input is identified using machine learning, and the stored input information is input to the input item.