Data Source Mapper for Natural Language Query Retrieval
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing techniques for responding to natural language queries in software applications are limited by their inability to determine relevant data sources and often lack contextual information, leading to computationally expensive processes and inaccurate responses.
Innovation Solution
Utilizing a named entity recognition (NER) machine learning model and a knowledge graph to identify and expand on data sources indicated in a query, retrieving data from multiple relevant sources to generate a more accurate and contextual response.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If large language models with large numbers of parameters are used to analyze natural language queries, then the ability to understand and respond to queries improves, but computational cost and processing time increase significantly
Solution Approach 1:
The system divides the query processing task into separate functional components: a lightweight NER model for identifying data sources, a knowledge graph for semantic expansion, and a template-based response generator. This segmentation allows each component to be optimized independently, using smaller, more efficient models rather than one large monolithic model, thereby reducing overall computational cost while maintaining accuracy.
Solution Approach 2:
The knowledge graph acts as an intermediary between the NER model and the response generation process. It enriches the query by adding contextual information about data sources and their relationships, enabling more accurate responses without requiring the NER model or response generator to be computationally expensive. The intermediary handles the complex semantic reasoning separately.
2Ease of operation
If existing techniques request data only from data sources specifically identified in the natural language query, then the process is simple, but the response lacks appropriate context and useful information
Solution Approach 1:
The system performs preliminary actions by using the NER model to identify all potentially relevant data sources before retrieving data. It then uses the knowledge graph to expand this list with additional related data sources that may not be explicitly mentioned in the query but are contextually relevant. This preliminary identification and expansion ensures comprehensive data retrieval while maintaining a systematic approach.
Solution Approach 2:
The knowledge graph serves multiple functions: it stores relationships among data sources, expands the list of relevant data sources based on query context, and provides contextual information for response generation. This multi-functionality allows the system to handle complex query understanding and data retrieval without adding separate specialized components for each function.
3Reliability
If the system determines which data sources contain information most relevant to a natural language query, then response accuracy improves, but the system complexity increases
Solution Approach 1:
The system creates a simplified representation of data source relationships through the knowledge graph, which copies and organizes the essential connectivity information between data sources. This structured copy allows the system to efficiently determine relevant data sources by traversing the pre-organized knowledge graph rather than analyzing raw relationships between all data sources, reducing computational complexity while maintaining selection accuracy.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
Aspects of the present disclosure provide techniques for enhanced electronic data retrieval. Embodiments include receiving a natural language query and identifying one or more electronic data sources indicated in the natural language query using a named entity recognition (NER) machine learning model trained through a supervised learning process based on training natural language strings associated with labels indicating entity names. Embodiments include determining one or more additional electronic data sources related to the one or more electronic data sources using a knowledge graph that maps relationships among electronic data sources. Embodiments include retrieving data related to the natural language query by transmitting requests to the one or more electronic data sources and the one or more additional electronic data sources and providing a response to the natural language query based on the data related to the natural language query.