Dynamic Workflow Knowledge Graph Technical Support
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing computerized technical support systems rely on predefined workflows, which become outdated when applications change, leading to duplicated data and increased storage and maintenance challenges.
Innovation Solution
A computer-implemented method using a knowledge graph to dynamically generate an automated technical support workflow by processing user queries to extract action identifiers, identifying relevant nodes and edges, and creating custom clarification statements to narrow down the most relevant information, decoupling workflow information from application data.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If predefined workflows are used for technical support, then initial support can be provided to users, but the workflows become outdated when applications change, requiring manual updates and causing data duplication
Solution Approach 1:
The patent transforms static predefined workflows into dynamic workflows that automatically adapt to application changes. The system continuously monitors application data and dynamically generates updated workflows without manual intervention, making the workflow system flexible and adaptive while reducing maintenance complexity
Solution Approach 2:
The system implements self-service by automatically detecting application changes and generating updated workflows autonomously. The workflow system serves itself by using application data to create and update its own workflow structures, eliminating the need for manual updates and reducing maintenance burden
2Extent of automation
If predefined workflows are used for technical support, then support automation is achieved, but data duplication increases storage requirements
Solution Approach 1:
The patent merges the workflow definition data with application data into a unified structure. Instead of storing workflows and application data separately (causing duplication), the system combines them so that workflows are derived from application data, eliminating redundant storage while maintaining automation
3Loss of information
If multiple nodes are identified in the knowledge graph, then comprehensive information is retrieved, but clarification is needed to determine the most relevant node
Solution Approach 1:
The system uses feedback mechanisms by analyzing the relationships between multiple identified nodes and using this information to generate clarification questions. The clarification process provides feedback to the user to narrow down the query, and the system uses the returned information to select the most relevant node, balancing completeness with efficiency
Data Source
AI summary
Disclosed embodiments provide techniques for computerized technical support. A knowledge graph for a computer application is established. An input query from a user is processed to extract entities used as action identifiers. One or more nodes within the knowledge graph are identified, along with corresponding relationship edges leading to the nodes. When multiple candidate nodes are found that contain information relevant to the input query, a custom clarification statement is created based on the one or more identified relationship edges. The user provides answers to the clarification statement to narrow down which nodes contain the most relevant information. This process may continue, eliminating nodes based on user responses, until a single node remains, corresponding to an action identifier. The action identifier includes action description information that provides technical assistance to a user.