How it Works

OAKLEY - Intelligent Knowledgebase

Intelligent agents enable you to codify and automate your domain expertise so you can use your expertise on the important stuff. We harness that power in a proprietary knowledgebase named OAKLEY. There's no question we can think up that OAKLEY can't answer.

Problem: You need a brilliant idea to present. Your experience tells you it’s a winner. But it could be worded in a variety of ways and is buried among thousands of documents. Although you may know a few keywords, or tags, to help search for documents, you still end up searching then reading through hundreds of irrelevant documents trying to locate that needle in the haystack. You need your own AI, your own agent to do this for you. Smart search is great if you know what to ask for, but you need smart ideas.


Solution: Our core technology for language applications is based on a new form of biologically inspired neural computing that processes information in the same way as the brain.  Unlike other approaches, this core technology enables our machines to learn with or without human supervision. Our technology automatically generates a lightweight ontology that detects all relationships among data elements.  Learning occurs at the time data is ingested — so it is very fast.


Our application leverages this core technology using both static and dynamic fingerprint techniques to deliver a set of tools for the analyst working with unstructured data.  These tools allow the analyst to classify, organize, filter, search and explore in ways not possible with keyword search, natural language processing (NLP), Latent Semantic Indexing (LSI) or other statistical/mathematical tools. Furthermore, the extraction of concepts expressed in documents into a fingerprint graph enables experts with programs such as SAS, SPSS, R and Tableau to include unstructured data in their analytics, programs and any graphics program or BI tool.


We have created a library of thousands of intelligent agents for financial, industry, company, sector and political concepts, building an enriched database for every paragraph in the financial reporting domain. We supplement this with dozens of linguistic attributes including custom tone (sentiment) to extensive analytics.  Additional agents are continually added as topics and industries change. This process saves hours of work searching documents and mitigates the risk of missing new developments – a tremendous value proposition for analysts confronted with ever increasing quantities of information.

It's powerful technology and the attributes we extract are unique and provide a foundation for building proprietary insightful analytics.