Slide 1

MICROSOFT SEMANTIC ENGINE

Unified Search, Discovery and Insight

Significant Content is Outside Structured Storage (RDBMS, OLAP, BI)

Integration of this Content is Prohibitively Expensive (Time, Money, Resources)

Extracting Insight, Analytics, and Recommendations is even harder

Situation is a Confluence of Search | Predictive Analytics | Large-Scale Collaborative Filtering

Having all forms of digital information on a single platform allows people to blend unstructured and structured content and to drive insight and decision making

Microsoft Semantic Engine provides a combination of technologies to form a contextual understanding of all digital content

Cri

tica

l B

usi

ness

Need Analysts gather

documents, medi

a and web

content about

“Business

Analytics”, “Data

Integration” and

“Search and

Discovery” Co

re M

ach

ine L

earn

ing

Unsupervised

learning infers

“Unified

Information

Access” concept

cluster based on

automated

analysis of

content Eff

icie

nt

Data

Ag

gre

gati

on

Cluster gains in

relevance from

mining across

unstructured and

structured

sources added

from ERP and BI

systems Use

r R

ele

van

ce B

oo

st Users (BDM) re-

label cluster as

“Unified Search,

Discovery and

Insight” and

engine adopts it

further boosting

that cluster

relevance Co

llab

ora

tive B

oo

st Analysts collate

this content

requiring multi-

resolution super-

clusters with

embedded sub-

clusters

Bu

sin

ess

Deci

sio

n M

akin

g

The CxO explores

super-cluster and

drafts business

plan for her new

division

|

|

Search and Collaboration | Personalized search, discovery and organization

Legal | Precedent and subject based search over large scale textual corpuses

Life Sciences | Systems biology with large volume data correlation and search

Government Services | Intelligence, real-time analytics, visualization, clustering

Social Networking | Social graph relevance mining, ranking criteria auto tuning

|

Unified Search, Discovery and Insight

Automatic Clustering and Organization

Meaning-Driven Indexing, Classification and Storage

Scalable Content Processing over all Content Types

Instant On Experience for Out of Box Value

|

Search, Discover and Organize features exposed via sample UX gallery

Seamless installation and indexing of desktop, email and web content

Fully documented Managed APIs used in UX gallery and JavaScript / C# samples

|

Streams | Descriptors (Properties) | Kinds (Concepts)

Streams processed into contextualized and indexed concepts for search | discovery | organization

KR_CLIENT_225.docxSTREAM

LEGAL DOCUMENTCONCEPT

BILLABLE WORKCONCEPT

EVIDENCECONCEPT

DEPOSITIONCONCEPT

EXTRACTED PROPERTIESPROPERTY

LEGAL CASE [xxx]CONCEPT CLUSTER

SEARCH AND SHAREMDP

|

Engine consists of self-contained set of pluggable services

Text Processing

Image Processing

Video Processing

Audio ProcessingSupervised Machine

Learning

Clustering MDI (RBV)

Conceptual Search

InferenceSequence Store

(Suffix Tree)Distributed Content Store Ontology and Taxonomy

Management

Semantic Engine

Search and MarkupTrend and Predictive

AnalysisAutomatic Organization

Recommendation and Discovery

|

The logical architecture partitions analysis, indexing and storage

API1 API2 API3 Analysis3Analysis2Analysis1

Staging Core Index Stream

Store(<content>) Annotate(<kind>)

Index(<content>) Organize(<kinds>)

Search(<query>) …

Text

Image

Audio Video Video

|

Designed to be hassle free out of the box

Several programming languages and frameworks supported

CLR/.NET, JavaScript, TSQL, C++

|

Sample of storing a stream in the system

Initiates the content processing, classification, and indexing

|

Sample of search and recommendations

Returns contextual results from the store and the web

|

Seamless Integration in Windows Desktop Federated Search

Expose Meaning-Driven Indexing and Semantic Actions

Zero Learning Curve

|

Importers

Files

PlugInsPlugInsPlug-Ins

Semantic

Engine

Database

Kind Descriptor Stream KindLink

ListKind

|

KindID SourceUri

00000000-1111 C:\My Documents\Saint Germain Des Pres Cafe (Finest electro-jazz compilation)\05 Track

5.wma

StreamID KindID StreamUri Format Stream

11111111-2222 00000000-1111 audio/x-

ms-wma

0xFFD8FFE000104A4649460001…

DescriptorID KindID Type Attribute ValueDescriptorID KindID Type Attribute Value

10000000-0000 00000000-

1111

Classificat

ion

Audio 1.0

20000000-0000 00000000-

1111

Metadata Name 05 Track 5.wma

30000000-0000 00000000-

1111

Metadata Item Type Windows Media Audio File

DescriptorID KindID Type Attribute Value

10000000-0000 00000000-

1111

Classificat

ion

Audio 1.0

20000000-0000 00000000-

1111


30000000-0000 00000000-

1111


40000000-0000 00000000-

1111

Metadata Length 00:05:22

50000000-0000 00000000-

1111

Metadata WM/ProviderStyl

e

Electronica


10000000-0000 00000000-

1111

Classificat

ion

Audio 1.0

20000000-0000 00000000-

1111


30000000-0000 00000000-

1111


40000000-0000 00000000-

1111


50000000-0000 00000000-

1111


e

Electronica

60000000-0000 00000000-

1111

Audio Tonality/Major 0.78

70000000-0000 00000000-

1111

Audio Tempo/Moderato 0.79


10000000-0000 00000000-

1111

Classificat

ion

Audio 1.0

20000000-0000 00000000-

1111


30000000-0000 00000000-

1111


40000000-0000 00000000-

1111


50000000-0000 00000000-

1111


e

Electronica

60000000-0000 00000000-

1111

Audio Tonality/Major 0.78

70000000-0000 00000000-

1111

Audio Tempo/Moderato 0.79

80000000-0000 00000000-

1111

Classificat

ion

Music .8

|

|

All Change data is

returned to MSE as one

XML block

MSE data is exposed

through custom views

keyed to the Users’

Primary Keys

|

Seamless Integration of Meaning-Driven Indexing in ALL SQL Tables

Expose Meaning-Driven Indexing via T-SQL

PARTING THOUGHTS

Unified Search, Discovery and Insight over Every Digital Artifact

Extensible and Scalable Semantic Platform

Zero Learning Curve

>

>

channel9.msdn.com/learnBuilt by Developers for Developers….

http://www.microsoft.com/

http://channel9.msdn.com/learn

© 2009 Microsoft Corporation. All rights reserved. Microsoft, Windows, Windows Vista and other product names are or may be registered trademarks and/or trademarks in the U.S. and/or other countries.

The information herein is for informational purposes only and represents the current view of Microsoft Corporation as of the date of this presentation. Because Microsoft must respond to changing market

conditions, it should not be interpreted to be a commitment on the part of Microsoft, and Microsoft cannot guarantee the accuracy of any information provided after the date of this presentation. MICROSOFT

MAKES NO WARRANTIES, EXPRESS, IMPLIED OR STATUTORY, AS TO THE INFORMATION IN THIS PRESENTATION.