Machine Learning System for Synthetic Conversation Detection

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Conventional technologies fail to detect and predict synthetic driven conversations and impending events from electronic media messages across digital broadcasting and social media platforms, lacking the capability to identify anomalous patterns and memetic relationships.

Innovation Solution

A machine-learning based electronic media analysis system that uses feature extraction and semi-supervised learning to identify keywords, determine memetic relationships, and detect chains of messages forming synthetic driven conversations by analyzing data feeds from various electronic media sources.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Loss of information

If conventional sentiment analysis and property identification technologies are used, then basic information about opinions and group properties can be obtained, but the capability to detect synthetic driven conversations and predict impending events is lost

Engineering Contradiction:

Improvedetection capabilityVSAvoidsystem complexity

Core Design Contradiction:

Loss of informationVSDevice complexity

Solution Approach 1:

The patent combines sentiment analysis, property identification, and event detection into a unified machine learning framework that processes electronic media messages comprehensively. The system merges multiple analytical functions (sentiment detection, keyword identification, memetic relationship analysis) into an integrated model that simultaneously performs these tasks, thereby improving detection capability without proportionally increasing system complexity.

Inventive Principle:

Principle #5Merging (Combining)

Solution Approach 2:

The machine learning model is designed with multi-functionality to perform diverse analytical tasks including sentiment analysis, keyword extraction, event prediction, and synthetic conversation detection. This universal approach allows a single system to handle multiple detection functions, reducing the need for separate specialized systems and thereby improving overall detection capability while managing complexity.

Inventive Principle:

Principle #6Universality (Multi-functionality)

2Measurement precision

If machine-learning based analysis with feature extraction is implemented, then detection of anomalous patterns and predictive intelligence is improved, but processing complexity and computational requirements increase

Engineering Contradiction:

Improvepattern detection accuracyVSAvoidprocessing complexity

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The patent segments the analysis process into distinct feature extraction stages, where specific features (sentiment, keywords, temporal metadata, referential relationships) are extracted and analyzed separately before being integrated. This segmentation allows the system to apply specialized processing to each feature type, improving pattern detection accuracy while managing computational complexity through modular processing.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The system performs preliminary feature extraction and preprocessing of electronic media messages before applying the main machine learning detection algorithms. By pre-processing the data to extract relevant features (keywords, sentiment scores, temporal patterns) in advance, the system reduces the computational burden during the main detection phase, thereby improving accuracy without proportionally increasing overall processing complexity.

Inventive Principle:

Principle #10Preliminary action

3Productivity

If real-time analysis of electronic media messages across multiple platforms is performed, then actionable insights into information operations are provided, but data processing volume and source diversity increase system complexity

Engineering Contradiction:

Improveinformation analysis throughputVSAvoidplatform integration complexity

Core Design Contradiction:

ProductivityVSDevice complexity

Solution Approach 1:

The machine learning model is designed to handle multiple data sources and message formats universally, accommodating electronic media messages from diverse platforms (social media, news outlets, blogs) through a unified processing framework. This multi-functional design enables real-time analysis across platforms without requiring separate processing pipelines for each source, thereby maintaining high information analysis throughput while managing platform integration complexity.

Inventive Principle:

Principle #6Universality (Multi-functionality)

Data Source

PatentUS11790251B1Systems and methods for semantically detecting synthetic driven conversations in electronic media messages

Publication Date: 2023.10.17 ARCHITECTURE TECH CORP

AI summary

Various embodiments described herein relate to a machine-learning based electronic media analysis software system. The system is configured to detect anomalous and predictive patterns associated with an event. The system is configured to use feature extraction techniques and semi-supervised machine-learning to detect the patterns associated with the event in the electronic media messages, which may indicate a synthetic driven behavior and conversation corresponding to the event.