Knowledge-Based Intent Engine for Automated Service Resolution

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Managing and optimizing data objects and computing resources in complex application frameworks is challenging due to their scale and complexity, leading to inefficient resource usage and difficulty in processing service tickets and workflows.

Innovation Solution

An intent engine is integrated with the application framework to recognize support intentions through various communication channels, enabling automated resolution actions by correlating intent labels to resolution data objects, thereby optimizing resource usage and improving workflow efficiency.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If traditional manual methods are used to manage service tickets and workflows in complex application frameworks, then human operators can handle nuanced situations, but resource usage becomes inefficient and processing time increases

Engineering Contradiction:

Improveservice ticket processing efficiencyVSAvoidworkflow processing time

Core Design Contradiction:

ProductivityVSLoss of time

Solution Approach 1:

The system enables automated self-service processing of service tickets through machine learning models that independently analyze incoming messages, determine intent, retrieve relevant knowledge, and execute resolution actions without human intervention for routine matters

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

Manual mechanical processing of service tickets is replaced with an automated electronic system comprising machine learning models, knowledge bases, and automated resolution engines that process workflows digitally at scale

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Reliability

If more computing resources are allocated to manage the complexity of application frameworks, then system capabilities improve, but resource usage efficiency deteriorates

Engineering Contradiction:

Improvesystem management capabilityVSAvoidcomputing resource usage efficiency

Core Design Contradiction:

ReliabilityVSUse of energy by moving object

Solution Approach 1:

The system dynamically adjusts processing parameters including model selection, knowledge base query depth, and resolution action complexity based on the specific characteristics of each service ticket, optimizing resource allocation for each case rather than using fixed high-resource configurations

Inventive Principle:

Principle #35Parameter changes

Solution Approach 2:

The system applies partial automation selectively - using full automated processing for straightforward cases and escalating to human operators only when necessary, avoiding excessive resource consumption on simple tickets while maintaining reliability for complex issues

Inventive Principle:

Principle #16Partial or excessive action

3Productivity

If automated resolution actions are implemented using machine learning models, then workflow efficiency improves, but system complexity increases

Engineering Contradiction:

Improveworkflow automation efficiencyVSAvoidsystem architectural complexity

Core Design Contradiction:

ProductivityVSDevice complexity

Solution Approach 1:

The automated resolution system is segmented into distinct modular components including intent recognition models, knowledge base retrieval systems, resolution action engines, and escalation mechanisms, allowing independent development, testing, and maintenance of each module

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

Knowledge bases serve as intermediary layers between machine learning models and resolution actions, providing structured information that bridges the gap between automated intent recognition and appropriate resolution execution, simplifying the overall system architecture

Inventive Principle:

Principle #24Intermediary (Mediator)

4Adaptability or versatility

If multiple communication channels are integrated into the application framework, then service coverage and adaptability improve, but data management complexity increases

Engineering Contradiction:

Improvemulti-channel service coverageVSAvoiddata object management complexity

Core Design Contradiction:

Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The system implements a universal service message object structure that can represent and process communications from multiple different channels (email, chat, phone, etc.) using a standardized format, allowing the same processing logic to handle diverse input sources without channel-specific complexity

Inventive Principle:

Principle #6Universality (Multi-functionality)

Data Source

PatentUS20250321998A1Apparatuses, methods, and computer program products for generating an automated resolution action using a knowledge base system and a trained machine learning model

Publication Date: 2025.10.16 ATLASSIAN PTY LTD

AI summary

Methods, apparatuses, or computer program products provide for generating an automated resolution action using a knowledge base system and a trained machine learning model. In some examples, a service message object is received via a communication channel of a plurality of communication channels and the service message object defines a feature dataset associated with a service request for an application framework, a knowledge base system is queried based on the feature dataset, a knowledge base data structure is received from the knowledge base system in response to the query, the knowledge base data structure is input to a machine learning model trained for reading comprehension to generate a resolution data object associated with a service resolution for the service request, and a resolution action is initiated for the service request based on the resolution data object.