Self-Learning Semantic Layer for Dynamic Keyword Mapping
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing big-data analytics tools rely on static models defined by data experts, making modifications expensive and complicated, and often result in inconsistent calculations due to outdated data, with users needing to rely on technical knowledge for data manipulation.
Innovation Solution
A system with a self-learning and context-sensitive semantic layer that allows users to interact with data using natural language queries, dynamically mapping keywords and learning new mappings through user feedback, enabling interactive data exploration and visualization without requiring technical expertise.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If a static model defined by data experts is used, then data consistency and reliability are improved, but device complexity and ease of operation deteriorate
Solution Approach 1:
The semantic layer automatically learns and adapts to user queries without requiring manual reconfiguration by data experts. The system self-adjusts keyword mappings and data relationships based on user interactions, eliminating the need for complex manual model updates while maintaining data consistency.
Solution Approach 2:
The semantic layer transitions from a static to a dynamic model that continuously evolves based on user queries and feedback. Keyword mappings are updated in real-time as users interact with the system, allowing the model to adapt to changing data structures and user needs without requiring manual redefinition.
2Reliability
If pre-defined reports are used, then reliability is improved, but ease of operation and adaptability deteriorate
Solution Approach 1:
Users can independently create and modify reports through natural language queries without requiring technical expertise. The semantic layer automatically interprets user intentions and translates them into appropriate data queries, making report generation accessible to end-users while maintaining accuracy.
Solution Approach 2:
The system incorporates feedback mechanisms where users can refine their queries and provide feedback on results. This feedback loop enables the semantic layer to improve its understanding of user needs and data relationships, enhancing both accessibility and report accuracy over time.
3Ease of operation
If data is imported into spreadsheet applications, then ease of operation is improved, but reliability deteriorates due to inconsistent calculations
Solution Approach 1:
The semantic layer acts as an intermediary between users and the underlying data sources. It provides a consistent abstraction layer that standardizes data access and calculation methods, ensuring reliable results while maintaining ease of operation through user-friendly interfaces and natural language queries.
4Device complexity
If a static semantic layer is used, then device complexity is reduced, but adaptability deteriorates
Solution Approach 1:
The semantic layer dynamically adapts to new keywords and data structures through automated learning from user queries. This allows the system to maintain simplicity while gaining flexibility, as the semantic layer automatically expands its knowledge base without requiring manual reconfiguration.
Solution Approach 2:
The system automatically learns and incorporates new keywords and data relationships through user interactions. This self-learning capability enables the semantic layer to adapt to changing requirements while maintaining a simple and intuitive interface, eliminating the need for manual updates.
Data Source
AI summary
According to a general aspect, a system includes a query engine configured to receive a query from a user via a user interface layer for obtaining data from one or more databases, determine if a keyword of the query can be mapped to at least one of a plurality of keyword mappings stored in a semantic layer, and if the keyword cannot be mapped, provide an interactive object, via the user interface layer, to learn a new keyword mapping for the keyword such that the semantics layer is updated with the new keyword mapping for future queries. The system includes a prediction engine configured to check for previous queries of the user or other users that map the query to predict a next query, and the query engine is configured to provide query results of the query and the next query as a suggestion via the user interface layer.