NL2Query in Sales
Cisco’s sales team needed a way for non-technical users to effectively retrieve technical product information from graph databases.
The product information they wanted was listed in structured and unstructured technical product tables or plain text. Questions included compatibility concerns and features across products.
The Lymba Solution
Use specific ontologies to process research reports to create a natural language question-answering interface.
Process
Lymba used Jaguar to automatically bolster ontologies. This allowed our users control over what knowledge was extracted.
We then processed documents via semantics to RDF, stored them to an RDF Triple Store, and used NL2Query to retrieve data.
We converted natural language questions into SPARQL queries using ontology driven NLP and query semantics extractions. NLP queries were able to retrieve relevant information from RDF triple stores populated with structured and unstructured data..
Outcome
The result allowed Cisco’s sales team to save time responding to customer’s Request for Proposals and improve productivity.