Loren Data's SAM Daily™

fbodaily.com
Home Today's SAM Search Archives Numbered Notes CBD Archives Subscribe
FBO DAILY ISSUE OF AUGUST 20, 2010 FBO #3191
SPECIAL NOTICE

A -- X-Man - Data Extraction System Software

Notice Date
8/18/2010
 
Notice Type
Special Notice
 
NAICS
238990 — All Other Specialty Trade Contractors
 
Contracting Office
Department of Energy, Lawrence Livermore National Laboratory (DOE Contractor), Industrial Partnerships & Commercialization, 7000 East Avenue, L-795, Livermore, California, 94550
 
ZIP Code
94550
 
Solicitation Number
FBO226-10
 
Archive Date
9/21/2010
 
Point of Contact
Connie L Pitcock, Phone: 925-422-1072
 
E-Mail Address
pitcock1@llnl.gov
(pitcock1@llnl.gov)
 
Small Business Set-Aside
N/A
 
Description
TECHNOLOGY/BUSINESS OPPORTUNITY X-Man - Data Extraction System Software Opportunity : Lawrence Livermore National Laboratory (LLNL), operated by the Lawrence Livermore National Security (LLNS), LLC under contract with the U.S. Department of Energy (DOE), is offering the opportunity to license (both patents and copyrights) and commercialize Data Extraction System Software, which we call X-Man (Extraction Manager). Background : Data extraction (aka entity extraction) software is utilized broadly for commercial applications, and many different types of tools exist. However, most of these tools are limited in their effectiveness and often have significant error rates within their range of application. Specifically, these existing tools are marginally useful because of their propensity to generate misses and/or false alarms, produce fragmented and/or partial extractions and in general, operate with unknown error rates. Description : This Data Extraction System Software (X-Man) provides a system that can accept new (unknown) data and produce probabilistically ranked output. X-Man accomplishes this via a novel system design, novel analytical tools, and multiple existing (off the shelf) data extraction tools. X-Man analyzes and aggregates (via probabilitistic methods) the output of the existing tools to produce output with significantly reduced error rates relative to its constituent (off the shelf) tools. X-Man provides a mathematical basis for ascertaining the certainty of the output. This approach has demonstrated the ability to reconstruct the truth even when all of its constituent (off the shelf) data extraction tools fail. X-Man's unique system architecture operates in two modes. The system first uses existing data with known truth to analyze and characterize the operation of the existing (off the shelf) data extraction tools (Training Mode). The analysis and characterization of these data extraction tools is then "fed into" the production side of X-Man (Production Mode). In the Production Mode, X-Man takes in new data (truth unknown) and uses the commercial data extractors, analytical tools, and the analysis from the Training Mode to produce probabilistically ranked output. Advantages : X-Man offers the following advantages over existing data extraction tools: •· Decreases catastrophic errors (e.g., false alarms and/or missed data). •· Increases detection. •· Extends the range of application. •· Provides a measure of certainty for the data extracted. Potential Applications : This technology enables a variety of data mining, content extraction, semantic technologies, search and discovery needs from news articles, blog posts, research reports, social media sites, resumes, etc. These include the following: •· Detection and tracking of topic trends for commercial and government needs (e.g., clipping services, key word tracing). •· Detection of anomalies for commercial and government needs (e.g., for summarization / insight of books, articles, reports, etc.). •· Detection of patterns and linkages addressing commercial and government needs, such as customer relationship management, and predictive analytics for customer attrition. •· Homeland security and intelligence analysis. •· Web / network search and retrieval. Development Status: X-Man is currently operational at LLNL. This software is prototyped and can be demonstrated. LLNL has filed a Provisional patent application that covers the novel aspects of the software. In addition, LLNL can license copyrighted software which embodies the technology. LLNL is seeking industry partners with a demonstrated ability to bring such inventions to the market. Moving critical technology beyond the Laboratory to the commercial world helps our licensees gain a competitive edge in the marketplace. All licensing activities are conducted under policies relating to the strict nondisclosure of company proprietary information. Please visit the IPO website at http://ipo.llnl.gov/workwithus/partneringprocess.php for more information on working with LLNL and the industrial partnering and technology transfer process. Note: THIS IS NOT A PROCUREMENT. Companies interested in commercializing LLNL's X-Man ( Data Extraction System Software) should provide a written statement of interest, which includes the following: 1. Company Name and address. 2. The name, address, and telephone number of a point of contact. •3. A description of corporate expertise and facilities relevant to commercializing this technology. Written responses should be directed to: Lawrence Livermore National Laboratory Industrial Partnerships Office P.O. Box 808, L-795 Livermore, CA 94551-0808 Attention: FBO 226-10 Please provide your written statement within thirty (30) days from the date this announcement is published to ensure consideration of your interest in LLNL's X-Man ( Data Extraction System Software).
 
Web Link
FBO.gov Permalink
(https://www.fbo.gov/spg/DOE/LLNL/LL/FBO226-10/listing.html)
 
Record
SN02244871-W 20100820/100818234933-461e4e5a7fdbcd54f1ca0387709efc5e (fbodaily.com)
 
Source
FedBizOpps Link to This Notice
(may not be valid after Archive Date)

FSG Index  |  This Issue's Index  |  Today's FBO Daily Index Page |
ECGrid: EDI VAN Interconnect ECGridOS: EDI Web Services Interconnect API Government Data Publications CBDDisk Subscribers
 Privacy Policy  Jenny in Wanderland!  © 1994-2024, Loren Data Corp.