Conversational Interface Knowledge Graph Query Resolution

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Conversational user interfaces often fail to provide relevant answers to long-tail queries, as they are not mapped to specific nodes in the knowledge graph, leading to unsatisfactory responses such as lists of articles instead of actionable results.

Innovation Solution

The method involves using knowledge graphs to execute functions within conversational user interfaces by iteratively requesting inputs through a conversational user interface based on a graph definition, determining input completeness using a completeness graph, and executing the function once all necessary inputs are provided, allowing for the generation of usable answers to queries of varying complexity.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If traditional automated agents use statistical models to match queries to answers, then commonly encountered queries can be resolved effectively, but long-tail queries cannot be answered and only lists of articles are returned

Engineering Contradiction:

Improvequery resolution accuracyVSAvoidlong-tail query handling

Core Design Contradiction:

ReliabilityVSAdaptability or versatility

Solution Approach 1:

The patent segments the query processing system into multiple components: a natural language understanding module that parses user queries, a knowledge graph traversal module that navigates the graph structure, and a query execution module that performs operations. This segmentation allows the system to handle both common and long-tail queries by routing them through appropriate processing paths.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The patent introduces a knowledge graph as an intermediary between the user query and the data source. The knowledge graph serves as a mediator that translates natural language queries into structured graph traversal operations, enabling the system to resolve long-tail queries that would otherwise be unanswerable through traditional statistical matching alone.

Inventive Principle:

Principle #24Intermediary (Mediator)

2Ease of operation

If conversational user interfaces return lists of articles for long-tail queries, then the system maintains simplicity, but the user experience deteriorates as no direct answer is provided

Engineering Contradiction:

Improvesystem simplicityVSAvoiddirect answer provision

Core Design Contradiction:

Ease of operationVSLoss of information

Solution Approach 1:

The patent implements dynamic query processing where the system adapts its response based on the query type. For long-tail queries, the system dynamically traverses the knowledge graph to construct direct answers, while for common queries it may use pre-computed results. This dynamic approach maintains system simplicity while providing direct answers when possible.

Inventive Principle:

Principle #15Dynamics

Solution Approach 2:

The system incorporates feedback mechanisms where the knowledge graph traversal results inform the generation of direct answers. The system evaluates whether a direct answer can be constructed from graph traversal results, and only falls back to article lists when direct answers cannot be formed, thus reducing information loss.

Inventive Principle:

Principle #23Feedback

3Adaptability or versatility

If the system processes a large universe of operations through knowledge graphs, then query versatility improves, but processing power requirements increase

Engineering Contradiction:

Improvequery operation coverageVSAvoidprocessing power consumption

Core Design Contradiction:

Adaptability or versatilityVSUse of energy by moving object

Solution Approach 1:

The patent applies preliminary action by pre-computing and storing knowledge graph structures, schemas, and relationships before query execution. The knowledge graph is built and organized in advance, allowing queries to traverse pre-established paths rather than computing relationships on-the-fly, significantly reducing processing power requirements during actual query execution.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system applies local quality by optimizing knowledge graph traversal for specific query types and operations. Different parts of the knowledge graph can be traversed with different strategies based on the local structure and query requirements, reducing overall processing power consumption while maintaining versatility across a large universe of operations.

Inventive Principle:

Principle #3Local quality

Data Source

PatentUS20250021301A1Conversational user interfaces based on knowledge graphs

Publication Date: 2025.01.16 INTUIT INC

AI summary

Certain aspects of the present disclosure provide techniques for executing a function in a software application through a conversational user interface based on a knowledge graph associated with the function. An example method generally includes receiving a request to execute a function in a software application through a conversational user interface. A graph definition of the function is retrieved from a knowledge engine. Input is iteratively requested through the conversational user interface for each parameter of the parameters identified in the graph definition of the function based on a traversal of the graph definition of the function. Based on a completeness graph associated with the function, it is determined that the requested inputs corresponding to the parameters identified in the graph definition of the function have been provided through the conversational user interface. The function is executed using the requested inputs as parameters for executing the function.