AI Planning Problem Translation System for Domain Experts
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional approaches to artificial intelligence planning require specialized knowledge of AI description languages, making it difficult for domain experts without AI training to encode and utilize domain knowledge effectively, especially in plan recognition problems.
Innovation Solution
A method that translates graphical representations of domain knowledge, such as mind maps, into AI planning problems expressed in AI description languages, allowing domain experts to encode knowledge without needing AI training, and automatically validates the planning problems to ensure validity.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If conventional AI planning approaches are used, then planning problems can be solved, but domain experts without AI training cannot effectively encode domain knowledge
Solution Approach 1:
The patent introduces an intermediary translation system that converts graphical representations (mind maps, flowcharts) into AI planning problem formats. This mediator eliminates the need for domain experts to directly learn and use complex AI description languages, while still enabling effective encoding of domain knowledge through intuitive graphical interfaces
Solution Approach 2:
The patent replaces the mechanical requirement of learning and manually writing complex AI description languages with an automated translation mechanism. The system automatically generates planning problems from graphical representations, substituting the manual encoding process with an automated conversion that preserves domain knowledge while eliminating language complexity barriers
2Manufacturing precision
If specialized AI description languages are required, then planning problems can be accurately formulated, but the barrier to entry for domain experts increases
Solution Approach 1:
The patent creates a copy of domain knowledge in a simplified graphical format (mind maps, flowcharts) that domain experts can easily create without AI training. This graphical copy is then automatically translated into the formal AI planning problem representation, preserving accuracy while eliminating the need for experts to directly manipulate complex languages
3Adaptability or versatility
If manual encoding of domain knowledge is required, then flexibility in expressing domain concepts is maintained, but the time and effort needed increases
Solution Approach 1:
The patent performs preliminary translation of graphical representations into AI planning problem formats before the actual planning execution. This preliminary conversion step automates the encoding process, reducing the time and effort domain experts need to invest while maintaining the flexibility to express complex domain concepts through intuitive graphical structures
Data Source
AI summary
Techniques for translating graphical representations of domain knowledge are provided. In one example, a computer-implemented method comprises receiving, by a device operatively coupled to a processor, a graphical representation of domain knowledge. The graphical representation comprises information indicative of a central concept and at least one chain of events associated with the central concept. The computer-implemented method further comprises translating, by the device, the graphical representation into an artificial intelligence planning problem. The artificial intelligence planning problem is expressed in an artificial intelligence description language. The translating comprises parsing the graphical representation into groupings of terms. A first grouping of terms of the grouping of terms comprises an event from the at least one chain of events and a second grouping of terms of the grouping of terms comprises the information indicative of the central concept. The computer-implemented method also comprises validating, by the device, the artificial intelligence planning problem.