Professional Documents
Culture Documents
Azure Search
2.5 quintillion
bytes per day
80%
of business relevant information is
unstructured
management free
keyword search
faceting
language analyzers
geospatial support
suggestions/auto-complete
customizable scoring
proximity search
synonyms
etc.
TIFF HTML
…
JPG
TIFF
Scott Guthrie
Title:
Executive Vice President,
C+E
Company: Microsoft
JPG
Cognitive skills
Annotations
Customer Annotated Search
Data Documents Index
Your custom
skill goes here!
handwritten
text recognition
face
detection cryptonym
extraction
face
detection redaction
classifier
{
{
"values": [ "values": [
{ {
"recordId": "7cad2", "recordId": "7cad2",
"data": "data":
{ {
"value1": "myOuput1":
"I owe you 5 grand" "Te debo cinco mil"
} }
}, },
{ Custom {
"recordId": "7cad3", translation "recordId": "7cad3",
skill
"data": "data":
{ https {
"value1": "myOutput1":
"Just my 2 cents", "Solo mis 2 centavos"
} }
}, },
…
] …
} ]
}
JFK and Wolters Kluwer
Demo
OCR (text
recognition)
handwritten
text recognition
face
detection cryptonym
extraction
face
detection redaction
classifier
/document
/content
/normalized_images
/1
/2
/…
/n
"skills": [
{
"@odata.type": "#Microsoft.Skills.Text.LanguageDetectionSkill",
"inputs":
[
{ "name": "text", "source": "/document/content" }
],
"outputs":
[
{ "name": "languageCode", "targetName": "myLanguageCode" },
{ "name": "languageName", "targetName": "myLanguageName" }
]
},
/document
/content
/normalized_images
/1
/2
/…
/n
/myLanguageCode
…,
{
"@odata.type": "#Microsoft.Skills.Text.NamedEntityRecognitionSkill",
"categories": [ "Organization" ],
"defaultLanguageCode": "en",
"inputs":
[
{ "name": "text", "source": "/document/content" },
"name" "languageCode" "source" "/document/myLanguageCode"
],
"outputs":
[
{ "name": "organizations", "targetName": "organizations" }
]
},
/document
/content /organizations
/normalized_images /1
/1
/2
/2
/…
/…
/n
/n
/mylanguagecode
…,
{
"@odata.type": "#Microsoft.Skills.Custom.WebApiSkill",
"uri" "https://myskill.azurewebsites.net/api/OrgId"
"context": "/document/organizations/*" ,
"httpHeaders": {"Api-Key": "mySecret" },
"inputs":
[
{ "name": “organizationName", "source": "/document/organizations/*" },
],
"outputs":
[
{ "name": "organizationId", "targetName": "organizationId" }
]
},
/document
/content /organizations
/normalized_images /1 organizationId
/1
/2 organizationId
/2
/… organizationId
/…
/n organizationId
/n
/mylanguagecode
Customer Annotated Search
Data Documents Index
/1 /1 organizationId /1 tags
/… /… organizationId
/… tags
/n /n organizationId
/n tags
Use Case: Icertis
Trusted by the world’s top companies
AUTOMOTIVE PHARMA/HEALTH CARE SOFTWARE/TECHNOLOGY CONSULTING/SERVICES
Scenario
Architecture Icertis contract
management
1 2 3 4 5
Receive PDF Extract text Search for Spot risks, enrich Prep for
contract in email GDPR clauses data and search searchability
across languages
Customer Annotated Search
Data Documents Index