Ontology-Based Conversational Agent Specification
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional conversational agents suffer from a lack of modularity and difficulty in navigating and updating their specifications, leading to inefficient user interactions and limited scalability in providing accurate and timely information.
Innovation Solution
An ontological conversational agent is developed with a structured specification that organizes domain knowledge into classes, attributes, and relationships, enabling easier navigation and updates, and includes language-related descriptions to recognize multiple descriptions and vernaculars, allowing for goal-directed reasoning and flexible interaction.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If conventional conversational agent specifications use a fixed set of variables and tree-based dialogue states, then the agent can be simple in principle, but it does not scale well to realistic conversational agents and suffers from lack of modularity
Solution Approach 1:
The patent segments the conversational agent specification into modular components: ontology modules (defining domain concepts, relationships, and hierarchy), dialogue state modules (tracking conversation state), and policy modules (guiding agent behavior). This segmentation allows each module to be independently developed, updated, and scaled, resolving the contradiction between simple structure and scalability.
2Ease of manufacture
If domain knowledge is implicit and scattered through conversational agent definitions, then the agent can be easier to define initially, but it becomes difficult to navigate and modify
Solution Approach 1:
The patent introduces an explicit ontology as an intermediary layer between the agent's internal representation and the external domain knowledge. This ontology serves as a structured mediator that organizes domain concepts, relationships, and constraints in a navigable format, making it easier to define, navigate, and modify domain knowledge without scattering it throughout the agent definitions.
3Productivity
If the conversational agent uses traditional specification methods, then the agent can be developed quickly, but it provides information slower and less accurately to users
Solution Approach 1:
The patent applies preliminary action by pre-organizing domain knowledge into a structured ontology before the conversational agent begins processing user queries. This pre-structured knowledge base enables faster and more accurate information retrieval during conversations, reducing the time to provide accurate information to users while maintaining rapid development through modular ontology creation.
Data Source
AI summary
According to a first aspect of the present invention, a computer implemented method, a computer system and a computer program product for creating an ontological conversational agent, the method including creating an ontological specification of a domain of discourse of the ontological conversational agent, and creating a description of one or more goals of the ontological conversational agent. In an embodiment, the ontological description includes classes of entities, their associated attributes and relationships between the classes of entities. In an embodiment, the ontological description includes language-related descriptions. In an embodiment, the method, computer system and computer program product further includes creating a description of services of the ontological conversational agent. An embodiment including receiving a first utterance from a user during a conversation, identifying a first intent based on the first utterance, and recognizing a first goal of the one or more goals, based on the first intent.