Machine Learning Data Types

This page describes all the Object types defined and used by Machine Learning Activities.

DateParserInfo

Properties

Property	Type	Description
Date	DateTime	The parsed and modified Date value
Confidence	Double	The confidence of the model in the range 0 to 1

NumberParserInfo

Properties

Property	Type	Description
Number	long	The parsed and modified Numeric value
Confidence	Double	The confidence of the model in the range 0 to 1

DocumentInfo

Properties

Property	Type	Description
DocumentTypes	Dictionary<String, Float>	List of Document Types and the corresponding confidence
Domain	String	The domain to which this document belongs

SentimentInfo

Properties

Property	Type	Description
Sentiment	String	Contains one of the following values: Positive, Negative, or Neutral.
Text	String	The input text.
Confidence	Double	The confidence of the model in the range 0 to 1

LanguageDetectionResult

It represents language detection results obtained from cognitive services.

Properties

Property	Type	Description
Language	String	Language name.
LanguageCode	String	Shortcode of detected Language in ISO 639-1 format. Refer to List of ISO 639-1 codes
ConfidenceScore	Int32	Score between 0 and 100, indicating the confidence for detecting this language.

Entity

It represents an entity identified by cognitive services.

Properties

Property	Type	Description
Text	String	Text of the entity.
ConfidenceScore	Int32	Score between 0 to 100, indicating the confidence for detecting this entity.
Length	Int32	Length of the entity text.
Offset	Int32	Starting position of the entity text within the document text.

NamedEntity

It represents a named entity identified by cognitive services.

Properties

Property	Type	Description
Text	String	Text of the entity.
Category	String	Category of the identified entity.
SubCategory	String	Subcategory of the entity.
ConfidenceScore	Int32	Score between 0 to 100, indicating the confidence for detecting this entity.
Length	Int32	Length of the entity text.
Offset	Int32	Starting position of the entity text within the document text.

BoundingBox

Represents an abstract rectangle that surrounds elements on a document or form. It is used as a reference point for object detection.
Each point coordinate represents a corner of the box. For Image files, coordinates are in pixels. For PDF files, coordinates are in inches

Properties

Property	Type	Description
TopLeft	PointF	Contains top left coordinates of the bounding box.
TopRight	PointF	Contains top right coordinates of the bounding box.
BottomLeft	PointF	Contains bottom left coordinates of the bounding box.
BottomRight	PointF	Contains bottom right coordinates of the bounding box.

CheckMark

Represents a check mark (selection mark) detected in a form

Properties

Property	Type	Description
Text	String	Text associated with the check box (if any)
ConfidenceScore	Float	Confidence score of this detection in the range of 0 to 100
PageNumber	Integer	Page number of detected check mark
CheckState	Boolean	Indicates whether the SelectionMark was selected or unselected
Box	BoundingBox	Box coordinates of the check mark detection

FormText

Represents a word inside a line or cell element inside a table cell

Properties

Property	Type	Description
PageNumber	Integer	Page number of element
ConfidenceScore	Float	Confidence score of the element detection in range 0 to 100
Text	String	Text detected in the element
Box	BoundingBox	Box coordinates of the element

FormTableCell

Represents a detected table cell in the form

Properties

Property	Type	Description
Text	String	Text in the table cell
ConfidenceScore	Float	Confidence score of the table cell detection in range 0 to 100
Box	BoundingBox	Box coordinates of the table cell
PageNumber	Integer	Page number of detected table cell
ColumnIndex	Integer	Index of the column containing the table cell
RowIndex	Integer	Index of the row containing the table cell
ColumnSpan	Integer	Column span of the table cell
RowSpan	Integer	Row span of the table cell
HeaderCell	Boolean	Indicates whether the table cell is in header row
FooterCell	Boolean	Indicates whether the table cell is in footer row
CellElements	FormText	Listing of elements inside the table cell

FormTable

Represents a detected table in a form

Properties

Property	Type	Description
PageNumber	Integer	Page number of detected table
Box	BoundingBox	Box coordinates of the table
ConfidenceScore	Float	Confidence score of the table detection in range 0 to 100
RowCount	Integer	Number of rows in the table
ColumnCount	Integer	Number of columns in the table
Cells	FormTableCell	Listing of all cells inside the table

FormLine

Represents a detected line of text inside a form

Properties

Property	Type	Description
Handwritten	Boolean	Indicates whether the line was handwritten or not
Words	FormText	Listing of words inside the line
PageNumber	Integer	Page number of the detected line
ConfidenceScore	Float	Confidence score of the line detection in the range between 0 to 100
Text	String	Detected text in the line
Box	BoundingBox	Box coordinates of the line

FormPage

Represents a page of a form

Properties

Property	Type	Description
Height	Float	Height of the detected page
Width	Float	Width of the detected page
PageNumber	Integer	Page number of the detected form page
TextAngle	Float	Orientation of detected text in degrees. Value in the range between -180 to 180
Lines	FormLine	Listing of lines detected in the page
Tables	FormTable	Listing of tables detected in the page
CheckMarks	CheckMark	Listing of check marks (selection marks) detected on the page

FormField

Represents a field inside the form

Properties

Property	Type	Description
ConfidenceScore	Float	Confidence score in range 0 to 100 of the detected form field
Label	String	Label text of the detected field
LabelBox	BoundingBox	Box coordinates of the field label
LabelPageNumber	Integer	Page number of the field label
LabelElements	FormText	Elements of the field label
Value	Object	Value of the identified field. Cast to its appropriate type
ValueBox	BoundingBox	Box coordinates of the field value
ValuePageNumber	Integer	Page number of the field value
ValueElements	FormText	Elements of the field value
ValueText	String	Textual value of the identified field
HasValue	Boolean	Indicates whether a value is available for this form field

FormFieldValue

Represents a field inside the form

Properties

Property	Type	Description
ConfidenceScore	Float	Confidence score in range 0 to 100 of the detected form field
Label	String	Label text of the detected field
LabelBox	BoundingBox	Box coordinates of the field label
LabelPageNumber	Integer	Page number of the field label
LabelElements	FormText	Elements of the field label
Value	T	Value of the identified field. Cast to its appropriate type
ValueBox	BoundingBox	Box coordinates of the field value
ValuePageNumber	Integer	Page number of the field value
ValueElements	FormText	Elements of the field value
ValueText	String	Textual value of the identified field

Form

Represents the type of form

Properties

Property	Type	Description
FormType	FormType	Type of the detected form. Can be a BusinessCard, IdentityDocument, Invoice, or Receipt
FormTypeConfidenceScore	Float	Confidence score in the range from 0 to 100 of the detected form type
Pages	FormPage	Listing of pages identified in the form layout
Fields	FormField	Dictionary of fields identified in the form. The field name is used as a key in this dictionary

InvoiceLineItem

Represents a line item inside an invoice

Properties

Property	Type	Description
Text	String	Textual representation of the line item
Amount	FormFieldValue Float	Amount detected in the line item
Description	FormFieldValue String	Description of item detected in the line item
Quantity	FormFieldValue Float	Quantity detected in the line item
UnitPrice	FormFieldValue Float	Price per unit detected in the line item
ProductCode	FormFieldValue String	Product code detected in the line item
Unit	FormFieldValue String	Unit of the item. e.g., hours, nos, etc.
Date	FormFieldValue DateTime	Date detected in the line item
Tax	FormFieldValue Float	Tax amount detected in the line item. It could be represented as the actual amount, percentage, etc.
ValueAddedTax	FormFieldValue Float	VAT amount detected in the line item. The field name in Azure: VAT
Fields	FormField	Dictionary of fields identified in the line item. The field name is used as a key in this dictionary

Invoice

Represents an invoice form

Properties

Property	Type	Description
CustomerName	FormFieldValue String	Invoiced customer name
CustomerId	FormFieldValue String	Customer reference id
PurchaseOrder	FormFieldValue String	Purchase order reference number
InvoiceId	FormFieldValue String	Id of the invoice. Sometimes referred to as InvoiceNumber
InvoiceDate	FormFieldValue DateTime	Date when invoice was issued
DueDate	FormFieldValue DateTime	Date payment of invoice is due
VendorName	FormFieldValue String	Name of vendor associated with invoice
VendorTaxId	FormFieldValue String	Taxpayer Id associated with the vendor
VendorAddress	FormFieldValue String	Vendor mailing address
VendorAddressRecipient	FormFieldValue String	Recipient name associated with vendor address
CustomerTaxId	FormFieldValue String	Taxpayer Id associated with the customer
CustomerAddress	FormFieldValue String	Customer mailing address
CustomerAddressRecipient	FormFieldValue String	Recipient name associated with customer address
BillingAddress	FormFieldValue String	Explicit billing address for customer
BillingAddressRecipient	FormFieldValue String	Recipient name associated with billing address
ShippingAddress	FormFieldValue String	Shipping address of customer specified in invoice
ShippingAddressRecipient	FormFieldValue String	Recipient name associated with shipping address
ServiceAddress	FormFieldValue String	Explicit service address of customer associated with invoice
ServiceAddressRecipient	FormFieldValue String	Recipient name associated with service address
RemittanceAddress	FormFieldValue String	Explicit remittance/payment address associated with customer
RemittanceAddressRecipient	FormFieldValue String	Recipient name associated with remittance address
PaymentTerm	FormFieldValue String	Terms of payment specified in invoice
ServiceStartDate	FormFieldValue DateTime	Starting date of provided service
ServiceEndDate	FormFieldValue DateTime	End date of provided service
AmountDue	FormFieldValue Float	Total amount due
SubTotal	FormFieldValue Float	Subtotal identified in invoice
PreviousUnpaidBalance	FormFieldValue Float	Previous unpaid balance amount identified in invoice
InvoiceTotal	FormFieldValue Float	Total charges associated with the invoice
TotalTax	FormFieldValue Float	Total tax amount identified in invoice
TotalVAT	FormFieldValue Float	Total Value Added Tax amount identified in invoice
LineItems	InvoiceLineItem	Listing of invoice line items identified in invoice
FormType	FormType	Type of detected form. Can be an Invoice, Receipt, BusinessCard, or IdentityCard
FormTypeConfidenceScore	Float	Confidence score in range 0 to 100 of the detected form type
Pages	FormPage	Listing of pages identified in invoice
Fields	FormField	Dictionary of fields identified in the invoice. The form field name is used as a key in the dictionary

BusinessCard

Represents the model of a business card

Properties

Property	Type	Description
ContactNames	FormFieldValue List of String	Contact Name(s)
FirstName	FormFieldValue String	First (given) name of contact.
LastName	FormFieldValue String	Last (family) name of contact
CompanyNames	FormFieldValue List of String	Company Name(s) of contact
DepartmentNames	FormFieldValue List of String	Department Name(s)/Organization Name(s) of contact
JobTitles	FormFieldValue List of String	Job Title(s) of contact
EmailAddresses	FormFieldValue List of String	Email Address(es) of contact
Websites	FormFieldValue List of String	Website(s) of contact
Addresses	FormFieldValue List of String	Address(es) of contact
MobilePhones	FormFieldValue List of String	Mobile Phone Number(s) of contact
WorkPhones	FormFieldValue List of String	Work Phone Number(s) of contact
OtherPhones	FormFieldValue List of String	Other Phone Number(s) of contact
Faxes	FormFieldValue List of String	Fax Number(s) of contact
FormType	FormType	Type of detected form. Can be an Invoice, Receipt, BusinessCard, or IdentityCard
FormTypeConfidenceScore	Float	Confidence score in range 0 to 100 of the detected form type
Pages	FormPage	Listing of pages identified in business card
Fields	FormField	Dictionary of fields identified in the business card. The form field name is used as a key in the dictionary

IdentityDocument

Represents an identity document like a driver's license, passport, etc

Properties

Property	Type	Description
IdentityDocumentType	FormFieldValue String	Type of identity document. Possible values are a driver's license and passport.
FirstName	FormFieldValue String	First (given) name from document.
LastName	FormFieldValue String	Last (family) name from document
MiddleName	FormFieldValue String	Middle name from document
Suffix	FormFieldValue String	Suffix of name from document
DocumentNumber	FormFieldValue String	Identity document number
DateOfBirth	FormFieldValue DateTime	Date of birth extracted from identity document
DateOfIssue	FormFieldValue DateTime	Issue date extracted from identity document
DateOfExpiration	FormFieldValue DateTime	Expiry date extracted from identity document
PlaceOfBirth	FormFieldValue String	Place of birth extracted from document
CountryCode	FormFieldValue String	ISO 3166 country code
NationalityCode	FormFieldValue String	ISO 3166 country code of nationality extracted from passport document
Sex	FormFieldValue String	Person sex extracted from document. Possible values include M, F, and X
MachineReadableZone	FormFieldValue String	MRZ extracted from passport document. Two lines of 44 characters each
Region	FormFieldValue String	Region extracted from identity document. (Driver's license)
Address	FormFieldValue String	Person Address extracted from identity document. (Driver's license)
AddressCity	FormFieldValue String	Person Address city extracted from identity document. (Driver's license)
AddressState	FormFieldValue String	Person Address state code extracted from identity document. (Driver's license)
AddressStateName	FormFieldValue String	Person Address state name extracted from identity document. (Driver's license)
AddressZipCode	FormFieldValue String	Person Address zip code extracted from identity document. (Driver's license)
AddressCounty	FormFieldValue String	Person Address county extracted from identity document. (Driver's license)
LicenseClass	FormFieldValue String	License class extracted from identity document. (Driver's license)
Restrictions	FormFieldValue String	Restrictions extracted from identity document. (Driver's license)
Endorsements	FormFieldValue String	Endorsements extracted from identity document. (Driver's license)
Veteran	FormFieldValue String	Veteran information extracted from identity document. (Driver's license)
FormType	FormType	Type of detected form. Can be an Invoice, Receipt, BusinessCard, or IdentityCard
FormTypeConfidenceScore	Float	Confidence score in range 0 to 100 of the detected form type
Pages	FormPage	Listing of pages identified in identity document
Fields	FormField	Dictionary of fields identified in identity document. The form field name is used as a key in the dictionary

ReceiptLineItem

Represents a line item inside a sales receipt

Properties

Property	Type	Description
ItemName	FormFieldValue String	Item name/Item description
Quantity	FormFieldValue Float	Quantity detected in the line item
UnitPrice	FormFieldValue Float	Price per unit detected in the line item
TotalPrice	FormFieldValue Float	Total price of receipt line item

Receipt

Represents a sales receipt

Properties

Property	Type	Description
ReceiptType	FormFieldValue String	Type of sales receipt. e.g., itemized, hotel, etc.
MerchantName	FormFieldValue String	Merchant name identified in sales receipt
MerchantPhoneNumber	FormFieldValue String	Merchant phone number identified in sales receipt
MerchantAddress	FormFieldValue String	Merchant address identified in sales receipt
TransactionDate	FormFieldValue DateTime	Date when the receipt was issued
TransactionTime	FormFieldValue TimeSpan	Time when the receipt was issued
Total	FormFieldValue Float	Transaction total of the sales receipt
Subtotal	FormFieldValue Float	Subtotal of the sales receipt (normally before tax is applied)
Tax	FormFieldValue Float	Total tax on receipt
Tip	FormFieldValue Float	Tip indicated in the sales receipt
LineItems	ReceiptLineItem	Listing of receipt line items identified in sales receipt
FormType	FormType	Type of detected form. Can be an Invoice, Receipt, BusinessCard, or IdentityCard
FormTypeConfidenceScore	Float	Confidence score in range 0 to 100 of the detected form type
Pages	FormPage	Listing of pages identified in receipt
Fields	FormField	Dictionary of fields identified in receipt. The form field name is used as a key in the dictionary

DetectedObject

It represents the information about the detected object by cognitive services.

Properties

Property	Type	Description
ObjectName	String	Language name.
ConfidenceScore	Double	Score between 0 and 100 indicating the confidence for the detected object.

TranslatedText

It represents translated text information obtained from cognitive services.

Properties

Property	Type	Description
Language	String	Language name.
LanguageCode	String	Shortcode of language in ISO 639-1 format. Refer to List of ISO 639-1 codes
Text	String	Translated text.