TextOre Energy Analytics

download report

Transcript TextOre Energy Analytics

TextOre Energy Analytics
Applying Text Mining Solutions
Toward Extraction of Energy Related
Data from Local Records
Introduction
• TextOre, Inc. offers a suite of highly advanced
text-mining and data analytics software to
search, identify, extract, and mine meaningful
information from large amounts of
unstructured text.
• The Energy arena offers multiple
opportunities for the mining and extraction of
large amounts of energy data to pinpoint
relevant and critical data.
The Opportunity
• Large amounts of data (such as mineral
rights information) exist in currently
unretrievable formats (handwritten
documents, poorly scanned or
photocopied data, etc.) throughout local
repositories.
The Market
• The data analytics market for the petroleum
industry is currently valued at more than $1.7
billion with some research predicting this
sector to be worth more than $4.7 billion by
2018.
(http://www.prweb.com/releases/utilityanalytics-energy/analyticsmarket/prweb10848527.htm)
The Solution
• TextOre, Inc. has a suite of technologies that spun
out of the US intelligence arena and can easily
refine multiple sources of energy data in a wide
array of formats.
• Ability to search, identify, and extract critical data
in real time from multiple sources (static data
such as local records, streaming news and
information from global sources, multi-language
and multi-source.
• Ability to dominate the energy analytics market if
we can gain access to the source data.
The Process
• Gain access to energy related information or
documents that need to be processed for
efficient information extraction.
• Compile the data on servers for processing by
the TextOre suite of analytical products.
• Normalize the data (put into the same format)
for preparation and early processing.
The Process II
• Normalization of documents involves
converting original documents to digital text
files and extracting information from hard to
read court documents and land deeds.
• Use customized OCR (Optical Character
Recognition) software to clean up all files and
produce clean documents for ingestion into
the TextOre Information Refinery.
Document Normalization
Original Scan
Normalized Scan
The Process III
• Ingest cleaned up documents into TextOre for
processing.
• Identify key information elements to be
extracted and enter those concepts into
TextOre for extraction of relevant data from
the ingested documents.
• Apply ingested documents into TextOre for
mining text mining and extraction of key data.
Key Terms
The Process IV
• TextOre will produce a matrix of all possible
and interesting intersections of data. Those
files or records that are of interest are
extracted for additional processing.
• Relevant documents of importance are sorted
and any key data elements are automatically
entered into a customized database for use by
the client.
TextOre Matrix
Pinpointing Data
Pinpointing Data
The Process V
• Data is then entered into customized
databases or sold to the client as is through
the TextOre interface.
• Ability to query additional information sources
to verify legal records, location of mineral
rights owners, recent sales of mineral rights,
etc. or to cross reference important
information.