ML-Based Improper Reference Identification in Content

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Current content creation applications lack the ability to efficiently detect and correct improper references, such as ambiguous or incorrect pronouns, which can lead to misunderstandings and embarrassment, and require time-consuming manual review.

Innovation Solution

A data processing system utilizing machine-learning models to identify improper references in content, providing suggestions for replacement, and allowing users to easily select and implement these suggestions through a user interface, with feedback mechanisms to improve model accuracy.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If manual review of content is performed to detect improper references, then detection accuracy can be achieved, but time consumption and operational complexity increase significantly

Engineering Contradiction:

Improvedetection accuracyVSAvoidtime consumption

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The patent replaces the mechanical manual review system with an automated machine learning-based natural language processing system. The ML model analyzes content segments to identify improper references, pronouns, and potential issues automatically, eliminating the need for manual examination while maintaining high detection accuracy through trained algorithms and pattern recognition.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system enables self-service by allowing the content creation application to automatically detect and flag improper references without requiring user intervention. The ML model independently processes content segments, identifies issues, and provides suggestions for correction, making the detection process autonomous and eliminating time-consuming manual review.

Inventive Principle:

Principle #25Self-service

2Reliability

If detailed examination of content is performed to detect inappropriate references, then detection reliability improves, but ease of operation deteriorates

Engineering Contradiction:

Improvedetection reliabilityVSAvoidease of operation

Core Design Contradiction:

ReliabilityVSEase of operation

Solution Approach 1:

The patent replaces complex manual examination processes with an automated ML-based system that performs detailed content analysis. The system reliably detects improper references, pronouns, and contextual issues through algorithmic processing, eliminating the need for users to perform difficult manual reviews while maintaining high detection reliability through trained models.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The ML model acts as an intermediary between the user and the content, automatically performing the detailed examination that would otherwise require manual effort. The system analyzes content segments, identifies improper references, and presents findings to the user, bridging the gap between simple operation and reliable detection.

Inventive Principle:

Principle #24Intermediary (Mediator)

3Productivity

If automated systems are used to detect improper references, then productivity increases, but measurement precision may deteriorate

Engineering Contradiction:

Improvecontent review efficiencyVSAvoiddetection accuracy

Core Design Contradiction:

ProductivityVSMeasurement precision

Solution Approach 1:

The patent implements an automated ML-based system that substitutes manual content review processes. The system processes content segments rapidly and accurately by analyzing pronouns, references, and contextual information using natural language processing algorithms, achieving both high productivity through automation and maintained precision through trained detection models.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system incorporates feedback mechanisms where the ML model learns from detected patterns and user interactions. The automated detection provides feedback on improper references found in content, and the system can be trained on this feedback to continuously improve detection accuracy while maintaining high processing speed and productivity.

Inventive Principle:

Principle #23Feedback

Data Source

PatentUS11397846B1Intelligent identification and modification of references in content

Publication Date: 2022.07.26 MICROSOFT TECHNOLOGY LICENSING LLC

AI summary

A method and system for providing improper reference identification for a content segment may include receiving a request to identify an improper reference in the content segment, inputting the content segment into a machine-learning (ML) model to identify the improper reference in the content segment, obtaining the identified improper reference as a first output from the ML model, obtaining one or more suggested replacement references as a second output from the ML model, and providing at least one of the identified improper reference or the at least one of the one or more suggested replacements for display.