Natural Language Grammar System for Interactive Voice Response

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing automated systems for processing transactions are less flexible than human agents and are costly to create, necessitating a method for economically feasible and flexible automated systems that can handle interactions in a more intuitive manner.

Innovation Solution

A system comprising a computer with executable instructions that uses a hierarchy of grammars to process natural language inputs, determining user goals, missing information, and providing prompts to complete transactions, allowing for flexible and intuitive interactions without requiring users to follow a predetermined menu structure.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of manufacture

If existing automated systems are used to process transactions, then cost reduction is achieved, but flexibility and intuitive interaction capabilities deteriorate

Engineering Contradiction:

Improvesystem development costVSAvoidflexibility in handling interactions

Core Design Contradiction:

Ease of manufactureVSAdaptability or versatility

Solution Approach 1:

The grammar system is segmented into multiple hierarchical levels (sentence level, phrase level, word level) that can independently process different aspects of user input. This segmentation allows the system to handle complex interactions by breaking them down into manageable grammatical components, providing flexibility without requiring a complete system redesign for each interaction type.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The grammar-based automated system is designed to be universal by using natural language processing capabilities that can handle multiple types of transactions and interactions through a single interface. The system can adapt to different transaction types by interpreting user intent through grammatical analysis rather than requiring separate processing paths for each transaction category.

Inventive Principle:

Principle #6Universality (Multi-functionality)

2Adaptability or versatility

If more flexibility is built into automated systems to handle interactions closer to human agents, then interaction quality improves, but system creation cost increases

Engineering Contradiction:

Improveflexibility in handling interactionsVSAvoidsystem creation cost

Core Design Contradiction:

Adaptability or versatilityVSEase of manufacture

Solution Approach 1:

The system uses self-service grammar development where grammars can be automatically generated from website content and interaction data without requiring extensive manual programming. The grammar development process is automated through algorithms that analyze existing text and interaction patterns, significantly reducing the manual effort and cost associated with creating flexible automated systems.

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The system achieves flexibility by changing the parameter of grammar representation from rigid predefined structures to dynamic natural language-based structures. By using natural language grammars that can adapt to different input patterns, the system gains human-agent-like flexibility while avoiding the need for complex programming at each interaction level.

Inventive Principle:

Principle #35Parameter changes

3Device complexity

If predetermined menu structures are required for transaction processing, then system complexity is reduced, but user interaction intuitiveness deteriorates

Engineering Contradiction:

Improvesystem structure simplicityVSAvoiduser interaction intuitiveness

Core Design Contradiction:

Device complexityVSEase of operation

Solution Approach 1:

The patent replaces the mechanical menu-driven interaction system with a natural language processing system. Instead of requiring users to navigate through predetermined menu options, the system uses grammatical analysis to interpret user intent directly from natural language input, making interactions more intuitive while maintaining manageable system complexity through structured grammar rules.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Data Source

PatentUS8738384B1Method and system for creating natural language understanding grammars

Publication Date: 2014.05.27 CONCENTRIX CVG CUSTOMER MANAGEMENT DELAWARE LLC

AI summary

Grammars for interactive voice response systems using natural language understanding can be created using information which is available on websites. These grammars can be created in automated manners and can have various tuning measures applied to obtain optimal results when deployed in a customer contact environment. These grammars can allow a variety of statements to be appropriately handled by the system.