AI Information Support System for Intent Recognition

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Traditional decision tree structures for automated information support systems require multiple user inputs, are time-consuming, and intolerant of informational faults, leading to incorrect problem statements and increased processing overhead.

Innovation Solution

A system that processes natural language inputs to determine user intent, compares it with support rules, and returns a dispositioned outcome, reducing the need for multiple inputs by using techniques like TFIDF scoring, lemmatization, and selection algorithms to simplify information support processing.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If traditional decision tree structures are used for automated information support, then the system can provide structured inquiry and information support, but the system requires multiple user inputs, is time-consuming, and demands relatively large processing overhead

Engineering Contradiction:

Improveaccuracy of problem statementVSAvoidtime to define problem

Core Design Contradiction:

ReliabilityVSLoss of time

Solution Approach 1:

The patent replaces the mechanical decision tree structure with an AI-based natural language processing system. Instead of requiring users to navigate through structured branching paths and make sequential selections, the system uses NLP to directly interpret user input, determine intent, and identify problems. This substitution eliminates the need for multiple user inputs and significantly reduces the time required to define problems while maintaining or improving accuracy.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system enables users to define problems through natural language input without requiring them to follow a predetermined decision tree path. The AI automatically interprets the input, determines user intent, and identifies the problem statement, allowing users to complete the process with minimal interaction. This self-service approach reduces both time consumption and processing overhead while maintaining reliability.

Inventive Principle:

Principle #25Self-service

2Ease of operation

If traditional decision tree methods are used, then the system can guide users through structured inquiry, but the system is intolerant of informational faults and may require resetting to the highest level

Engineering Contradiction:

Improveuser input requirementsVSAvoidtolerance of informational faults

Core Design Contradiction:

Ease of operationVSReliability

Solution Approach 1:

The patent replaces the rigid mechanical decision tree with a flexible AI-based NLP system that can interpret natural language input and tolerate informational faults. The system uses intent determination and contextual understanding to handle imperfect or incomplete user input without requiring resets, thereby improving both ease of operation and reliability simultaneously.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system incorporates fault tolerance mechanisms that anticipate and handle informational errors before they cause failure. By using AI-based interpretation rather than strict decision tree matching, the system can recover from imperfect input without requiring users to restart, effectively cushioning against the harmful effects of informational faults.

Inventive Principle:

Principle #11Beforehand cushioning (Prior cushioning)

3Productivity

If traditional decision tree structures are used, then the system can provide automated inquiry support, but the system demands a relatively large number of user inputs and processing overhead

Engineering Contradiction:

Improveinformation support processing efficiencyVSAvoidsystem processing overhead

Core Design Contradiction:

ProductivityVSDevice complexity

Solution Approach 1:

The patent replaces the complex mechanical decision tree structure with a more efficient AI-based NLP system. Although the underlying technology is sophisticated, the system processes user input more efficiently by directly interpreting natural language rather than navigating through multiple decision levels. This substitution improves productivity by reducing the number of user inputs required while managing processing overhead through optimized AI algorithms.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Data Source

PatentUS12124968B2Information support system using artificial intelligence

Publication Date: 2024.10.22 AMERICAN EXPRESS TRAVEL RELATED SERVICES CO INC

AI summary

A system for automated information support processing is disclosed. The system may receive a natural language information support request from a plain text input channel. The system may determine a first user intent based on the information support request. The system may compare the first user intent with a set of support rules. The system may determine a dispositioned outcome based on the set of support rules and the user intent. The system may return the dispositioned outcome.