Concept Nodes for Virtual Assistant Ontology Adaptability
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current active ontology architectures in virtual assistants face difficulties in adding new knowledge domains, as they require programming to refer to and interact with every existing domain, making it burdensome and complex.
Innovation Solution
The implementation of concept nodes within an active ontology allows for referencing concepts without needing to identify all possible sources or associate logic, simplifying the process of adding new domains by using terminal nodes to identify substrings corresponding to specific concept types, such as time or place, without requiring extensive modifications to existing domains.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If current active ontology architectures are used to represent integration of data modeling and execution environments, then the virtual assistant can quickly and accurately respond to user inputs, but it becomes difficult to add new knowledge domains representing subjects, genres, areas of interest, or groups of similar requests
Solution Approach 1:
The patent segments the ontology into hierarchical levels: generic concepts at the top level and specific knowledge domains at lower levels. This segmentation allows new domains to be added independently without restructuring the entire ontology, resolving the contradiction between maintaining fast response times and enabling easy addition of new knowledge domains.
Solution Approach 2:
The patent introduces concept nodes as intermediaries between generic concepts and specific domain concepts. These concept nodes serve as mediators that connect different knowledge domains to the core ontology structure, enabling new domains to be integrated without modifying existing domain implementations, thus maintaining both response speed and adaptability.
2Reliability
If programming is required to refer to and interact with every existing domain when adding new knowledge domains, then comprehensive domain coverage is achieved, but the process becomes burdensome and complex
Solution Approach 1:
The patent creates a universal concept node structure that can serve multiple knowledge domains simultaneously. A single concept node implementation can be reused across different domains (e.g., time concepts in weather, sports, and news domains), eliminating the need to program separate interactions for each domain and reducing complexity while maintaining comprehensive coverage.
Solution Approach 2:
The patent merges the functionality of domain-specific concept handling into a unified concept node framework. By combining multiple domain interactions through shared concept nodes, the system achieves comprehensive domain coverage without requiring separate programming for each domain, thus reducing the burden of adding new knowledge domains.
Data Source
AI summary
Systems and processes for operating a virtual assistant programmed to refer to shared domain concepts using concept nodes are provided. An example process includes receiving a user speech input, determining a primary domain corresponding to a textual representation of the user speech input, identifying, from the textual representation, a first substring that corresponds to a first concept of the primary domain, parsing the first substring to determine a secondary domain of the plurality of domains, and based on the secondary domain, obtaining a data item corresponding to the first substring. In accordance with determining that the data item is valid for resolving the first concept of the primary domain, extracting, from the data item, a parameter value for the first concept of the primary domain and invoking a service based on the primary domain to produce a result using the parameter value for the first concept.