Expert System Knowledgebase Population via Business Process Translation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing expert systems face challenges in accurately capturing subtle nuances and relationships of real-world business processes due to ad hoc methods of translating business processes into knowledgebases, leading to errors and inconsistencies in natural-language interactions with users.
Innovation Solution
A method is developed to automatically translate business processes into standardized representations that can be stored in a knowledgebase, using triple data structures to infer rules for natural-language interactions, preserving relationships and dependencies among business processes and activities.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If ad hoc methods are used to translate business processes into knowledgebases, then the translation process is flexible and adaptable, but the accuracy and consistency of the knowledgebase deteriorates
Solution Approach 1:
The patent transforms the translation process from ad hoc to systematic by changing the parameters of the methodology. It introduces standardized templates, defined schemas, and structured mapping protocols that convert business process descriptions into knowledgebase rules through consistent transformation rules, thereby improving accuracy while maintaining adaptability through configurable parameters.
Solution Approach 2:
The patent introduces an intermediary translation layer with standardized schemas and mapping templates that mediate between business process descriptions and knowledgebase rules. This intermediary structure ensures consistent transformation while allowing flexibility in the input and output formats, resolving the contradiction between adaptability and reliability.
2Adaptability or versatility
If manual methods are used to create knowledgebases, then customization is possible, but the time and effort required increases
Solution Approach 1:
The patent applies preliminary action by pre-defining schemas, templates, and mapping rules that can be reused across different knowledgebase creation tasks. These pre-prepared structures enable rapid population of knowledgebases while maintaining customization through configuration options, significantly reducing the time and effort required compared to manual creation.
Solution Approach 2:
The patent enables copying and reusing of standardized schemas, templates, and mapping rules across different knowledgebase projects. This replication approach maintains consistency and reduces repetitive work, allowing quick adaptation to different domains while preserving customization through parameter adjustment rather than recreating structures from scratch.
3Measurement precision
If detailed representations of business processes are created, then the precision of the knowledgebase improves, but the complexity of the translation process increases
Solution Approach 1:
The patent applies segmentation by breaking down the translation process into distinct, manageable stages: business process description, schema mapping, rule generation, and validation. Each stage handles specific aspects of the transformation, reducing overall complexity while enabling precise representation through systematic decomposition of the detailed translation tasks.
Data Source
AI summary
A knowledgebase of an expert system is populated with rules inferred from a set of business processes that govern the manner in which the business interacts with users. Each business process contains an input, an output, an action, and a set of dependency relationships that relate pairs of the input, the output, and the action. Each process's input, output, action, and dependency relationships are translated, respectively, into a subject, an object, a predicate, and a set of dependency relationships among the subject, object, and predicate, of a natural-language rule. Each rule is stored in the expert system's knowledgebase as a directed graph, and nodes representing each stored subject, object, and predicate are assigned domain classifications as a function of characteristics of the business rule. These domain classifications are represented within the knowledgebase as a set of domain classifications determined as a further function of characteristics of the business rule.