Artificial-Text Corpus for Accurate Verbal Feedback Noise Triage

Solution Overview

Problem

Existing customer feedback systems require manual triage to filter out non-actionable 'noise' from verbal feedback, consuming significant time and resources, especially in high-volume scenarios.

Innovation Solution

A machine learning model that classifies free-text content using a combination of free-text and artificial-text generated from parameter values, leveraging supervised learning and transfer learning to automate the triage process.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If manual triage is used to filter noise from verbal feedback, then classification accuracy is improved, but processing time and resource consumption increase significantly

Engineering Contradiction:

Improveclassification accuracyVSAvoidprocessing time

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The patent introduces an artificial-text corpus generated from non-textual parameters as an intermediary component. This artificial text serves as a mediator between the structured parameters and the free-text content, enabling the machine learning model to effectively integrate both data types for automated classification without requiring manual triage intervention

Inventive Principle:

Principle #24Intermediary (Mediator)

Solution Approach 2:

The patent replaces the manual mechanical triage process with an automated machine learning system. The system uses trained models to automatically classify feedback content based on combined features from free-text and artificial-text corpora, eliminating the need for human specialists to manually screen each feedback item

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Measurement precision

If manual triage is used to filter noise from verbal feedback, then classification accuracy is improved, but resource consumption increases significantly

Engineering Contradiction:

Improveclassification accuracyVSAvoidresource consumption

Core Design Contradiction:

Measurement precisionVSUse of energy by moving object

Solution Approach 1:

The system enables self-service automated classification through machine learning models that process feedback independently. The model uses combined feature vectors from free-text and parameter-generated artificial-text to automatically determine actionable vs. non-actionable status without requiring human specialist intervention for each feedback item

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The patent replaces the manual mechanical triage process with an automated machine learning system. The system uses trained models to automatically classify feedback content based on combined features from free-text and artificial-text corpora, eliminating the need for human specialists to manually screen each feedback item

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

3Productivity

If automated classification is implemented without artificial-text generation, then processing speed is improved, but classification accuracy deteriorates

Engineering Contradiction:

Improveprocessing speedVSAvoidclassification accuracy

Core Design Contradiction:

ProductivityVSMeasurement precision

Solution Approach 1:

The patent merges two distinct data sources: the free-text corpus from user feedback and the artificial-text corpus generated from structured parameters. By combining feature vectors from both sources, the system creates a more comprehensive representation of the feedback content, enabling accurate automated classification that leverages both unstructured text and structured parameter information

Inventive Principle:

Principle #5Merging (Combining)

Solution Approach 2:

The patent introduces an artificial-text corpus generated from non-textual parameters as an intermediary component. This artificial text serves as a mediator between the structured parameters and the free-text content, enabling the machine learning model to effectively integrate both data types for automated classification without requiring manual triage intervention

Inventive Principle:

Principle #24Intermediary (Mediator)

Data Source

PatentUS12380356B2Identifying noise in verbal feedback using artificial text from non-textual parameters and transfer learning

Publication Date: 2025.08.05 MICROSOFT TECHNOLOGY LICENSING LLC

AI summary

Methods and systems are provided for classifying free-text content using machine learning. Free-text content (e.g., customer feedback) and parameter values organized according to a schema are received. A free-text corpus is generated, and an artificial-text corpus is generated by applying rules to the parameter values. The artificial-text corpus is generated by converting the parameter values into a finite set of words based on the rules and concatenating the words of the finite set of words into a fixed sequence wordlist. Feature vectors (e.g., sentence embeddings) based on the free-text corpus and the artificial-text corpus are combined and forwarded to a machine learning model for classification. The machine learning model may be trained with a bias towards a specified metric (e.g., precision, recall, F1 score). The model may be trained using transfer learning with training data from a different category of free-text content (e.g., a different category of customer feedback).