Social Media Input Classification via POS Filtering

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Social media inputs from consumers are noisy, unstructured, and difficult to process, leading to increased operational costs and delayed responses for product or service providers due to the lack of efficient workflows.

Innovation Solution

A framework that acquires social media inputs, cleans them to remove redundant elements, extracts features, and classifies them into predefined categories using a trained classifier, enabling automated and efficient processing.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If manual monitoring and ad hoc processing methods are used, then consumer feedback can be captured, but processing time increases and operational costs rise

Engineering Contradiction:
Improvefeedback capture capabilityVSAvoidprocessing efficiency
Core Design Contradiction:
ReliabilityVSProductivity

Solution Approach 1:

The system enables automated self-processing of social media inputs through machine learning classifiers that automatically categorize and route consumer feedback without requiring manual human intervention for each input, thereby maintaining reliable capture while dramatically improving processing efficiency

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The patent replaces the mechanical manual monitoring system with an automated computational system using machine learning algorithms and natural language processing to classify and route social media inputs, substituting human labor with intelligent automated processing

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

2Reliability

If manual monitoring teams are deployed, then social media inputs can be monitored, but additional overhead increases operational costs

Engineering Contradiction:
Improveinput monitoring capabilityVSAvoidoperational cost
Core Design Contradiction:
ReliabilityVSLoss of energy

Solution Approach 1:

The automated classification system processes and routes social media inputs independently without requiring ongoing human team deployment, eliminating the continuous operational overhead of manual monitoring while maintaining reliable input capture

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The system creates intelligent copies of human classification capability through trained machine learning models that replicate and automate the feedback processing function, eliminating the need for continuous human resource allocation

Inventive Principle:
Principle #26Copying

3Quantity of substance

If no efficient workflow is implemented, then all consumer inputs are captured, but responses are delayed or complaints are overlooked

Engineering Contradiction:
Improveinput capture volumeVSAvoidresponse time
Core Design Contradiction:
Quantity of substanceVSLoss of time

Solution Approach 1:

The system performs preliminary automated classification and routing of social media inputs before human review or response is needed, pre-organizing the workload by priority and category to ensure timely responses while maintaining comprehensive input capture

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The automated classification system operates continuously without interruption to process incoming social media inputs in real-time, ensuring no complaints are overlooked and maintaining constant monitoring capability across all input channels

Inventive Principle:
Principle #20Continuity of useful action

Data Source

PatentUS11416680B2Classifying social media inputs via parts-of-speech filtering
Publication Date: 2022.08.16 SAP SE
  • US11416680B2 patent drawing
  • US11416680B2 patent drawing
  • US11416680B2 patent drawing

AI summary

Described herein is a framework for classifying social media inputs. In accordance with one aspect of the framework, one or more social media inputs is acquired from one or more social media platforms. The social media inputs are cleaned to remove redundant elements. One or more features are extracted from the cleaned social media inputs. The social media inputs are classified by a trained classifier into predefined categories using the extracted one or more features.