AI Geospatial Search Using Knowledge Graphs for Relevant Results
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing geospatial search tools return voluminous results, making it difficult for analysts to draw meaningful conclusions, and there is a need for more robust systems that provide relevant and tailored datasets in an easy-to-digest format, allowing users to enter simple queries in natural language and obtain accurate information.
Innovation Solution
A geospatial online search system utilizing artificial intelligence techniques, including a spider engine, query preprocessing, and a knowledge graph, to process natural language queries, enrich indexes with semantic data, and provide tailored results, while considering user credentials and security clearances.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If traditional geospatial search tools are used to search for geospatial data, then a large volume of results is returned, but the results are often irrelevant and difficult to analyze
Solution Approach 1:
The patent introduces an AI-based language model as an intermediary between the user query and the geospatial search system. The language model first processes the natural language query to extract key entities, locations, and temporal information, then formulates a structured search query. This intermediary processing step filters and refines the search parameters before querying the geospatial database, ensuring that only highly relevant results are returned rather than a voluminous but irrelevant dataset.
2Quantity of substance
If traditional geospatial search tools return all available results, then completeness is achieved, but analysts spend substantial time reviewing voluminous results
Solution Approach 1:
The patent applies preliminary action by pre-processing and enriching geospatial data before it needs to be searched. The system pre-generates metadata, extracts key features, and organizes data with contextual information in advance. When a search query is executed, the AI language model can quickly filter and retrieve relevant pre-processed results without requiring analysts to manually review raw voluminous data, significantly reducing review time while maintaining completeness.
Solution Approach 2:
The patent replaces the mechanical manual review process with an AI-based language model that automatically analyzes and ranks search results. Instead of analysts manually reviewing voluminous results, the language model semantically understands the query intent and automatically filters, ranks, and presents the most relevant results, substituting human mechanical review with intelligent automated processing.
3Ease of operation
If simple natural language queries are accepted, then ease of use is improved, but processing complexity increases
Solution Approach 1:
The AI-based language model serves as an intermediary that handles the complexity of processing natural language queries. It accepts simple user input and automatically performs semantic analysis, entity extraction, and query formulation. This intermediary layer shields the user from processing complexity while the system handles the sophisticated NLP tasks required to convert natural language into effective geospatial search queries.
Data Source
AI summary
An artificial intelligence (AI) search system can build or include one or more knowledge graphs and databases of indexes. The knowledge graphs can encode information and relationships from a variety of domains. The databases of indexes can store pointers to public and/or private data and raw content in those domains. An example of a domain includes fields requiring or handling geospatial data. The AI search system can receive a user query and process the query with AI models, including language models and knowledge graphs to identify data matching the intention and context of the user query. The AI search system can present relevant results in an assortment of user interfaces.