Fuzzy Matching Voice Interface for Conversational Entity Recognition

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Conventional voicebots struggle with conversational and real-world caller dialog due to misinterpretation, confusion from extraneous audio, out-of-sequence inputs, and imprecise identifications, lacking effective performance evaluation methods.

Innovation Solution

An intelligent voice interface system that includes audio handling to filter irrelevant audio, handles out-of-sequence dialog, infers user states, and improves entity recognition, combined with a call review tool for manual performance assessment.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If conventional voicebots use strict menu-driven IVR systems, then the structure is simple and easy to control, but the system cannot handle conversational and real-world caller dialog

Engineering Contradiction:

Improveability to handle conversational dialogVSAvoidsystem structure complexity

Core Design Contradiction:

Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The system segments the caller's speech into multiple segments and compares each segment against multiple possible entity identifications. This allows the voicebot to handle conversational dialog by processing speech in manageable units while maintaining a structured evaluation framework, resolving the contradiction between adaptability and complexity.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The system dynamically adjusts its response based on the level of match certainty determined by the fuzzy matching process. When match certainty is high, the system proceeds confidently; when low, it requests clarification. This dynamic adaptation enables the voicebot to handle real-world conversational scenarios while maintaining controlled system behavior.

Inventive Principle:

Principle #15Dynamics

2Adaptability or versatility

If conventional voicebots require highly ordered sequence of inputs, then the interaction is structured and predictable, but the system becomes confused by real-world caller behaviors like pauses and stalling language

Engineering Contradiction:

Improvehandling of real-world caller behaviorsVSAvoidsystem stability under varied input

Core Design Contradiction:

Adaptability or versatilityVSReliability

Solution Approach 1:

The system performs preliminary audio handling to filter out irrelevant audio and identify speaker changes before processing the actual entity identification. This preliminary action prepares the audio stream by removing pauses, stalling language, and background noise, allowing the voicebot to maintain reliability while handling real-world caller behaviors.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system introduces an intermediary fuzzy matching process between the caller's speech and the database entities. This intermediary layer of segment-based fuzzy matching acts as a buffer, absorbing the variability introduced by pauses and stalling language while maintaining accurate entity identification, thus improving both adaptability and reliability.

Inventive Principle:

Principle #24Intermediary (Mediator)

3Adaptability or versatility

If the voicebot uses imprecise entity identification, then the system is more flexible in accepting varied caller responses, but the match accuracy decreases

Engineering Contradiction:

Improveflexibility in accepting varied responsesVSAvoidentity identification accuracy

Core Design Contradiction:

Adaptability or versatilityVSMeasurement precision

Solution Approach 1:

The system applies local quality by evaluating each audio segment individually against multiple possible entity identifications and assigning a match certainty level to each segment. This allows the system to maintain flexibility in accepting varied caller responses while preserving measurement precision through localized, segment-by-segment fuzzy matching that evaluates both similarity and contextual relevance.

Inventive Principle:

Principle #3Local quality

4Measurement precision

If manual evaluation of voicebot performance is used, then the assessment can be comprehensive and nuanced, but the process is very time consuming and subjective

Engineering Contradiction:

Improveperformance assessment accuracyVSAvoidevaluation time

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The system performs self-service by automatically evaluating its own performance using the same fuzzy matching process that handles caller interactions. The automated evaluation system processes recorded calls through the segment-based fuzzy matching algorithm, objectively determining performance metrics without human intervention, thus achieving comprehensive and nuanced assessment while eliminating time consumption and subjectivity.

Inventive Principle:

Principle #25Self-service

Data Source

PatentUS12388927B2Fuzzy matching for intelligent voice interface

Publication Date: 2025.08.12 STATE FARM MUTAL AUTOMOBILE INSURANCE COMPANY

AI summary

A method for identifying entities may include, during a voice communication with a caller via a caller device, sending to the caller device a first voice prompt that asks the caller to identify a particular entity, receiving from the caller device caller input data indicative of a voice response of the caller, and analyzing the caller input data to determine a set of words spoken by the caller. The method may also include, for each segment of two or more segments of the set of words, determining a level of string matching between the segment and a corresponding segment in a record stored in a database, determining, and based upon the levels of string matching, a level of match certainty for the particular entity from among at least three possible levels of match certainty, and/or selecting, based upon the level of match certainty, a pathway of the algorithmic dialog.