Semantic Feedback Ontology for Accurate Client Experience Scoring

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing techniques for analyzing user experience feedback across multiple channels struggle to detect commonalities in underlying causes and compute a client experience score accurately due to varying terminology and organizational obstacles, leading to incomplete insights and inaccurate satisfaction assessments.

Innovation Solution

An AI system processes structured and unstructured feedback data using natural language processing and machine learning to identify commonalities, supplemented with weighting factors and logistic regression to compute a unique client experience score.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Quantity of substance

If unstructured feedback from multiple sources is collected, then the quantity and diversity of feedback data increases, but the difficulty of detecting commonalities and computing accurate client experience scores increases due to varying terminology

Engineering Contradiction:

Improvefeedback data volumeVSAvoiddifficulty of detecting commonalities

Core Design Contradiction:

Quantity of substanceVSDifficulty of detecting and measuring

Solution Approach 1:

The patent introduces a semantic knowledge database as an intermediary layer between raw feedback data and analysis results. This database contains ontology mappings that serve as a mediator to translate and standardize varying terminology from different feedback sources into unified concepts, enabling accurate detection of commonalities across diverse unstructured feedback data

Inventive Principle:

Principle #24Intermediary (Mediator)

Solution Approach 2:

The system transforms feedback data from multiple formats (text, audio, video) into a standardized parameter representation using ontology mappings. By changing the representation parameters of feedback data into a unified semantic framework, the system enables consistent measurement and comparison across different feedback channels and terminology

Inventive Principle:

Principle #35Parameter changes

2Ease of operation

If structured feedback surveys are used, then the ease of obtaining feedback increases, but the ability to detect new or emerging trends decreases due to pre-conceived problem detection limitations

Engineering Contradiction:

Improveease of obtaining feedbackVSAvoidability to detect new trends

Core Design Contradiction:

Ease of operationVSAdaptability or versatility

Solution Approach 1:

The patent creates a universal feedback processing system that handles multiple feedback types (structured surveys, unstructured calls, emails, social media) through a single ontology-based framework. This multi-functional approach allows the system to detect both pre-conceived problems from structured data and emerging trends from unstructured data sources

Inventive Principle:

Principle #6Universality (Multi-functionality)

Solution Approach 2:

The system performs preliminary action by pre-building a comprehensive semantic knowledge base with ontology mappings before feedback analysis. This pre-prepared semantic framework enables the system to automatically recognize and categorize both expected and emerging feedback patterns without requiring pre-conceived survey questions

Inventive Principle:

Principle #10Preliminary action

3Measurement precision

If manual review of feedback data is performed, then the accuracy of trend detection may improve, but the loss of time and productivity decreases due to organizational obstacles and processing delays

Engineering Contradiction:

Improveaccuracy of trend detectionVSAvoidprocessing time

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The patent replaces manual mechanical review processes with an automated AI-based system that uses natural language processing and semantic ontology matching. This substitution eliminates human processing delays while maintaining or improving detection accuracy through computational analysis of feedback patterns across multiple channels

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Data Source

PatentUS20260017683A1Computing metrics from unstructured datatypes of a semantic knowledge database ontology

Publication Date: 2026.01.15 TRUIST BANK

AI summary

A system for use by a business to process user feedback data. User experience feedback data is provided via multiple channels—including structured feedback in the form of surveys, and unstructured and unsolicited feedback from provided people in an ad hoc manner. The unstructured feedback may be from social media posts, calls to a service center, emails, and other sources. The feedback is aggregated as text data in a data pool. A natural language processing system analyzes the feedback, and to identify commonalities in the feedback data. Data from the feedback channels are supplemented with other sources of data and used to compute a client experience score. The client experience score computation includes weighting factors applied to the data sources. Logistic regression is used to adjust the weighting factors so that the client experience score matches client behavior as established by client events.