discover new value from unstructured data

9
Pingar SharePoint NZ Idol For Wave to incorporate into Peter’s presentation

Upload: peter-wren-hilton

Post on 22-Nov-2014

844 views

Category:

Technology


3 download

DESCRIPTION

Presented at Semantic Garage Meetup San Francisco 2011. Unstructured data comes at a high cost - $37,000 per year per person in information industries. By using tools to automatically add metadata enterprises can improve search results, speed e-discovery and risk assessment, summarize content and extract entities from files. Unstructured and semi-structured data represents a large component of big data. By turning unstructured content into business intelligence, enterprise can speed time to information.

TRANSCRIPT

Page 1: Discover New Value from Unstructured Data

Pingar SharePoint NZ Idol

For Wave to incorporate into Peter’s presentation

Page 2: Discover New Value from Unstructured Data

Emails

Creating docs

Analyzing in

fo

Search

ing

Reviewing

Gathering in

fo

Organizing docs

Creating presentations

Creating images

Data entry

Doc approva

l

Publishing

Translating

14.513.3

9.6 9.58.8 8.3

6.8 6.75.6 5.6

4.3 4.2

1

Avg. hours per week

Source: IDC, Hidden Cost of Information (2005)

Time spent on information tasks

= 37K year/person

Page 3: Discover New Value from Unstructured Data

Emails

Creating docs

Analyzing in

fo

Search

ing

Reviewing

Gathering in

fo

Organizing docs

Creating presentations

Creating images

Data entry

Doc approva

l

Publishing

Translating

14.513.3

9.6 9.58.8 8.3

6.8 6.75.6 5.6

4.3 4.2

1

Avg. hours per week

Time spent on information tasks

Source: IDC, Hidden Cost of Information (2005)

…can be rescued!

Page 4: Discover New Value from Unstructured Data

Redaction example is from dysonology.wordpress.com

Page 5: Discover New Value from Unstructured Data

New Pingar API

Rapid DiscoveryRelated searchesDynamic facetsDocument preview

HCIR Workshop20 October 2011

Google, Mountain View

Page 6: Discover New Value from Unstructured Data

Entity ExtractionNamed entity extractionTaxonomy mappingLinked Data connectorsAddress detectionInvoice analysis

New Pingar API

Mining Custom TaxonomiesSept 2010 – Feb 2012

NZ Ministry of Science and InnovationUniversity of Waikato & Pingar

Page 7: Discover New Value from Unstructured Data

Content AnalysisSanitization and redactionOffensive content filteringSummarizationReport generation

New Pingar API

query

Link to downloadan auto-generatedPDF report

Exploring verticalsLegal

BioscienceEducation

Government

Page 8: Discover New Value from Unstructured Data
Page 9: Discover New Value from Unstructured Data

Demo time