Ontology Workflow Automation for Cross-Application Skill Reuse
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing workflow automation tools require technical expertise for scripting and are application-specific, failing to generalize across similar applications, making them difficult for non-technical users to implement and adapt.
Innovation Solution
An ontology-based approach that records user demonstrations to generate workflow data, selects an ontology tree with similarity, constructs a skill tree, integrates it into an existing application tree, and executes skills using new data, allowing non-technical users to automate workflows across similar applications.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If recording-based tools are used to capture user demonstrations, then workflow automation can be achieved without scripting, but the tools are application-specific and cannot generalize across similar applications
Solution Approach 1:
The patent creates an ontology tree that represents common workflows across multiple applications. By mapping application-specific workflows to this universal ontology tree, the system enables one workflow automation to generalize across similar applications. The ontology tree serves as a universal framework that can accommodate different applications (email clients, document editors, etc.) while maintaining a single generalized workflow definition.
Solution Approach 2:
The ontology tree acts as an intermediary layer between the recording-based automation tool and the various applications. Instead of directly recording application-specific steps, the system records workflows and maps them to the ontology tree, which then serves as a mediator to generalize the workflow across similar applications. This intermediary structure allows the system to capture application-specific details while storing them in a universal format.
2Manufacturing precision
If specialized scripting languages or visual sequencing interfaces are used, then workflow automation precision can be achieved, but technical expertise is required making it difficult for non-technical users
Solution Approach 1:
The system enables non-technical users to create workflow automations through simple recording of their demonstrations. The ontology tree automatically maps these recorded workflows to universal workflow patterns, eliminating the need for users to manually script or configure complex automation logic. Users simply record their natural workflow, and the system handles the precision mapping to the ontology tree automatically.
Solution Approach 2:
Instead of requiring users to create automation logic from scratch using scripting or visual interfaces, the system captures a copy of the user's actual workflow demonstration and maps it to the ontology tree. This copying approach preserves the precision of the user's actual workflow while eliminating the need for technical expertise in automation tooling.
3Reliability
If recording-based tools capture specific input sequences, then accurate workflow reproduction is achieved, but the workflows are fragile and break when user interfaces change
Solution Approach 1:
The ontology tree provides a dynamic framework that can adapt to interface changes. Instead of storing static, rigid sequences of UI interactions, the system maps workflows to the ontology tree which represents the logical structure of the workflow. When interfaces change, the ontology tree can be updated to reflect new interface elements while maintaining the same workflow logic, making the automation robust to UI changes.
Solution Approach 2:
The system extracts the essential logical structure of workflows from the surface-level UI interactions. By mapping recorded workflows to the ontology tree, the system separates the core workflow logic from the specific UI implementation details. This extraction allows the workflow to remain reliable while being independent of specific interface implementations.
4Manufacturing precision
If multiple application-specific automation tools are deployed, then each application can be automated precisely, but information technology infrastructure complexity increases
Solution Approach 1:
The ontology tree serves as a universal framework that can handle multiple applications through a single system. Instead of deploying separate automation tools for each application, the system uses one ontology-based platform that can map and execute workflows across different applications (email clients, document editors, etc.). This universal approach maintains application-specific precision while eliminating the need for multiple specialized tools.
Solution Approach 2:
The patent merges multiple application-specific automation capabilities into a single ontology-based system. By combining the workflow recording, ontology mapping, and execution capabilities into one unified platform, the system reduces infrastructure complexity while maintaining the ability to automate various applications precisely.
Data Source
AI summary
An embodiment records execution of a workflow comprising a skill, the recording generating workflow data. An embodiment selects, using the workflow data, an ontology tree having above a threshold amount of similarity to the workflow. An embodiment constructs, using the ontology tree and the workflow data, a first skill tree corresponding to the workflow. An embodiment integrates, into an existing skill tree of an application, the first skill tree, the integrating resulting in an integrated skill tree of the application. An embodiment executes, responsive to an intent requesting execution of the skill using new data, using the integrated skill tree and the new data, the skill.