Conversational Agent Semantic Graph Matching for Ungrammatical Queries

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Traditional search technologies on company websites often fail to handle complex user queries effectively, leading to frustration and inefficient use of resources, as they require personalized information and struggle with messy or ungrammatical user inputs.

Innovation Solution

Implementing conversational agents that use linguistic analysis and semantic graph patterns to match user utterances with intended user intents, allowing for robust handling of misspelled, incomplete, or ungrammatical inputs and providing automated assistance through natural language dialog.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If traditional search technologies are used on company websites, then implementation is simple and cost-effective, but they fail to handle complex user queries effectively and require personalized information

Engineering Contradiction:

Improvequery handling effectivenessVSAvoidsystem complexity

Core Design Contradiction:

ReliabilityVSDevice complexity

Solution Approach 1:

The patent introduces a conversational agent as an intermediary between users and company information systems. This agent uses natural language processing to understand user queries and matches them against graph patterns representing company knowledge, thereby handling complex queries effectively while maintaining a user-friendly interface that doesn't require users to navigate complex search systems

Inventive Principle:

Principle #24Intermediary (Mediator)

Solution Approach 2:

The patent replaces traditional keyword-based search mechanisms with a semantic understanding system that uses linguistic analysis and graph pattern matching. This substitution enables the system to comprehend the intent behind queries rather than merely matching keywords, significantly improving query handling effectiveness for complex scenarios

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Ease of operation

If traditional search technologies are used, then system implementation is straightforward, but user experience deteriorates when queries become increasingly complex

Engineering Contradiction:

Improveuser experienceVSAvoidquery complexity handling

Core Design Contradiction:

Ease of operationVSAdaptability or versatility

Solution Approach 1:

The conversational agent dynamically adapts to varying query complexities by adjusting its linguistic analysis depth and graph pattern matching strategies. For simple queries, it provides quick responses, while for complex queries, it engages in multi-turn dialog to clarify intent and provide comprehensive answers, thereby maintaining ease of operation across all query types

Inventive Principle:

Principle #15Dynamics

Solution Approach 2:

The system changes parameters such as linguistic analysis granularity and graph pattern matching depth based on query characteristics. This allows the system to optimize its response strategy for each query, providing simple answers for straightforward questions and engaging in detailed dialog for complex scenarios, thereby improving both user experience and adaptability

Inventive Principle:

Principle #35Parameter changes

3Reliability

If conversational agents with linguistic analysis are implemented, then handling of misspelled and ungrammatical inputs improves, but computational resources increase

Engineering Contradiction:

Improveinput robustnessVSAvoidcomputational resource usage

Core Design Contradiction:

ReliabilityVSUse of energy by moving object

Solution Approach 1:

The linguistic analysis system performs partial analysis on inputs that appear straightforward and reserves full analysis for queries that show signs of complexity or potential issues. This selective approach maintains robust handling of misspelled and ungrammatical inputs while reducing unnecessary computational resource consumption on simple, clear queries

Inventive Principle:

Principle #16Partial or excessive action

4Extent of automation

If graph pattern matching is used to match user utterances with user intents, then automated assistance capability improves, but system complexity increases

Engineering Contradiction:

Improveautomated assistance capabilityVSAvoidsystem architecture complexity

Core Design Contradiction:

Extent of automationVSDevice complexity

Solution Approach 1:

The patent segments the automated assistance system into distinct modules: a linguistic analysis module that processes user input, a graph pattern matching module that identifies user intent, and a response generation module that formulates answers. This segmentation allows each component to be optimized independently and simplifies the overall system architecture by creating clear interfaces between modules

Inventive Principle:

Principle #1Segmentation

Data Source

PatentUS9524291B2Visual display of semantic information

Publication Date: 2016.12.20 VIRTUOZ

AI summary

Techniques involving visual display of information related to matching user utterances against graph patterns are described. In one or more implementations, an utterance of a user is obtained that has been indicated as corresponding to a graph pattern through linguistic analysis. The utterance is displayed in a user interface as a representation of the graph pattern.