Skip to content

Commit 57a233c

Browse files
Merge pull request #225129 from laujan/BemaBonsu/main
Bema bonsu/main
2 parents 384914f + 62d55cf commit 57a233c

File tree

5 files changed

+107
-51
lines changed

5 files changed

+107
-51
lines changed

articles/applied-ai-services/form-recognizer/concept-id-document.md

Lines changed: 8 additions & 6 deletions
Original file line numberDiff line numberDiff line change
@@ -200,7 +200,9 @@ Below are the fields extracted per document type. The Azure Form Recognizer ID m
200200
|:-----|:----:|:----:|:----:|:----:|:----:|:----:|:----:|:----:|
201201
|[prebuilt-idDocument](concept-id-document.md#field-extractions) || | | || | ||
202202

203-
### Document type - `idDocument.driverLicense` fields extracted
203+
### Document types
204+
205+
#### `idDocument.driverLicense` fields extracted
204206

205207
| Field | Type | Description | Example |
206208
|:------|:-----|:------------|:--------|
@@ -223,7 +225,7 @@ Below are the fields extracted per document type. The Azure Form Recognizer ID m
223225
|`Restrictions`|`string`|Restrictions|B|
224226
|`VehicleClassifications`|`string`|Vehicle classification|D|
225227

226-
### Document type - `idDocument.passport` fields extracted
228+
#### `idDocument.passport` fields extracted
227229

228230
| Field | Type | Description | Example |
229231
|:------|:-----|:------------|:--------|
@@ -254,7 +256,7 @@ Below are the fields extracted per document type. The Azure Form Recognizer ID m
254256
|`MachineReadableZone.DateOfExpiration`|`date`|Date of expiration|2019-05-05|
255257
|`MachineReadableZone.Sex`|`string`|Sex|F|
256258

257-
### Document type - `idDocument.nationalIdentityCard` fields extracted
259+
#### `idDocument.nationalIdentityCard` fields extracted
258260

259261
| Field | Type | Description | Example |
260262
|:------|:-----|:------------|:--------|
@@ -274,7 +276,7 @@ Below are the fields extracted per document type. The Azure Form Recognizer ID m
274276
|`Weight`|`string`|Weight|185LB|
275277
|`Sex`|`string`|Sex|M|
276278

277-
### Document type - `idDocument.residencePermit` fields extracted
279+
#### `idDocument.residencePermit` fields extracted
278280

279281
| Field | Type | Description | Example |
280282
|:------|:-----|:------------|:--------|
@@ -289,7 +291,7 @@ Below are the fields extracted per document type. The Azure Form Recognizer ID m
289291
|`PlaceOfBirth`|`string`|Place of birth|Germany|
290292
|`Category`|`string`|Permit category|DV2|
291293

292-
### Document type - `idDocument.usSocialSecurityCard` fields extracted
294+
#### `idDocument.usSocialSecurityCard` fields extracted
293295

294296
| Field | Type | Description | Example |
295297
|:------|:-----|:------------|:--------|
@@ -298,7 +300,7 @@ Below are the fields extracted per document type. The Azure Form Recognizer ID m
298300
|`LastName`|`string`|Surname|TALBOT|
299301
|`DateOfIssue`|`date`|Date of issue|08/12/2012|
300302

301-
### Document type - `idDocument` field extracted
303+
#### `idDocument` field extracted
302304

303305
|Name| Type | Description | Standardized output|
304306
|:-----|:----|:----|:----|

articles/applied-ai-services/form-recognizer/concept-invoice.md

Lines changed: 31 additions & 19 deletions
Original file line numberDiff line numberDiff line change
@@ -7,7 +7,7 @@ manager: nitinme
77
ms.service: applied-ai-services
88
ms.subservice: forms-recognizer
99
ms.topic: conceptual
10-
ms.date: 11/14/2022
10+
ms.date: 01/25/2023
1111
ms.author: lajanuar
1212
recommendations: false
1313
---
@@ -23,7 +23,14 @@ recommendations: false
2323
[!INCLUDE [applies to v2.1](includes/applies-to-v2-1.md)]
2424
::: moniker-end
2525

26-
The Form Recognizer invoice model combines powerful Optical Character Recognition (OCR) capabilities with invoice understanding models to analyze and extract key fields and line items from sales invoices. Invoices can be of various formats and quality including phone-captured images, scanned documents, and digital PDFs. The API analyzes invoice text; extracts key information such as customer name, billing address, due date, and amount due; and returns a structured JSON data representation. The model currently supports both English and Spanish invoices.
26+
The Form Recognizer invoice model uses powerful Optical Character Recognition (OCR) capabilities to analyze and extract key fields and line items from sales invoices, utility bills, and purchase orders. Invoices can be of various formats and quality including phone-captured images, scanned documents, and digital PDFs. The API analyzes invoice text; extracts key information such as customer name, billing address, due date, and amount due; and returns a structured JSON data representation. The model currently supports both English and Spanish invoices.
27+
28+
**Supported document types:**
29+
30+
* Invoices
31+
* Utility bills
32+
* Sales orders
33+
* Purchase orders
2734

2835
## Automated invoice processing
2936

@@ -41,7 +48,7 @@ Automated invoice processing is the process of extracting key accounts payable f
4148

4249
**Sample invoice processed with [Form Recognizer Sample Labeling tool](https://fott-2-1.azurewebsites.net)**:
4350

44-
:::image type="content" source="media/invoice-example-new.jpg" alt-text="Screenshot of a sample invoice.":::
51+
:::image type="content" source="media/invoice-example-new.jpg" alt-text="Screenshot of a sample invoice.":::
4552

4653
::: moniker-end
4754

@@ -155,17 +162,17 @@ See how data, including customer information, vendor details, and line items, is
155162
## Supported languages and locales
156163

157164
>[!NOTE]
158-
> It's not necessary to specify a locale. This is an optional parameter. The Form Recognizer deep-learning technology will auto-detect the language of the text in your image.
159-
160-
| Model | Language—Locale code | Default |
161-
|--------|:----------------------|:---------|
162-
|Invoice| <ul><li>English (United States)—en-US</li></ul>| English (United States)—en-US|
163-
|Invoice| <ul><li>Spanish—es</li></ul>| Spanish (United States)—es|
164-
|Invoice | <ul><li>German—de</li></ul>| German (Germany)-de|
165-
|Invoice | <ul><li>French—fr</li></ul>| French (France)—fr|
166-
|Invoice | <ul><li>Italian—it</li></ul>| Italian (Italy)—it|
167-
|Invoice | <ul><li>Portuguese—pt</li></ul>| Portuguese (Portugal)—pt|
168-
|Invoice | <ul><li>Dutch—nl</li></ul>| Dutch (Netherlands)—nl|
165+
> Form Recognizer auto-detects language and locale data.
166+
167+
| Supported languages | Details |
168+
|:----------------------|:---------|
169+
| &bullet; English | United States (us), Australia (-au), Canada (-ca), Great Britain (-gb), India (-in)|
170+
| &bullet; Spanish |Spain (es)|
171+
| &bullet; German | Germany (de)|
172+
| &bullet; French | France (fr) |
173+
| &bullet; Italian | Italy (it)|
174+
| &bullet; Portuguese | Portugal (-pt), Brazil (-br)|
175+
| &bullet; Dutch | Netherlands (de)|
169176

170177
## Field extraction
171178

@@ -200,10 +207,14 @@ See how data, including customer information, vendor details, and line items, is
200207
| ServiceStartDate | Date | First date for the service period (for example, a utility bill service period) | yyyy-mm-dd |
201208
| ServiceEndDate | Date | End date for the service period (for example, a utility bill service period) | yyyy-mm-dd|
202209
| PreviousUnpaidBalance | Number | Explicit previously unpaid balance | Integer |
210+
| CurrencyCode | String | The Currency Code associated with an extracted amount | |
211+
| PaymentOptions | Array | An array that holds Payment Option details such as `IBAN`and `SWIFT` | |
212+
| TotalDiscount | Number | The total discount applied to an invoice | Integer |
213+
| TaxItems (en-IN only) | Array | AN array that holds added tax information such as `CGST`, `IGST`, and `SGST`. This line item is currently only available for the en-in locale | |
203214

204215
### Line items
205216

206-
Following are the line items extracted from an invoice in the JSON output response (the output below uses this [sample invoice](media/sample-invoice.jpg))
217+
Following are the line items extracted from an invoice in the JSON output response (the following output uses this [sample invoice](media/sample-invoice.jpg))
207218

208219
|Name| Type | Description | Text (line item #1) | Value (standardized output) |
209220
|:-----|:----|:----|:----| :----|
@@ -215,7 +226,8 @@ Following are the line items extracted from an invoice in the JSON output respon
215226
| ProductCode | String| Product code, product number, or SKU associated with the specific line item | A123 | |
216227
| Unit | String| The unit of the line item, e.g, kg, lb etc. | Hours | |
217228
| Date | Date| Date corresponding to each line item. Often it's a date the line item was shipped | 3/4/2021| 2021-03-04 |
218-
| Tax | Number | Tax associated with each line item. Possible values include tax amount, tax %, and tax Y/N | 10% | |
229+
| Tax | Number | Tax associated with each line item. Possible values include tax amount and tax Y/N | 10.00 | |
230+
| TaxRate | Number | Tax Rate associated with each line item. | 10% | |
219231

220232
The invoice key-value pairs and line items extracted are in the `documentResults` section of the JSON output.
221233

@@ -235,7 +247,7 @@ Keys can also exist in isolation when the model detects that a key exists, with
235247

236248
## Fields extracted
237249

238-
The Invoice service will extract the text, tables, and 26 invoice fields. Following are the fields extracted from an invoice in the JSON output response (the output below uses this [sample invoice](media/sample-invoice.jpg)).
250+
The Invoice service will extract the text, tables, and 26 invoice fields. Following are the fields extracted from an invoice in the JSON output response (the following output uses this [sample invoice](media/sample-invoice.jpg)).
239251

240252
|Name| Type | Description | Text | Value (standardized output) |
241253
|:-----|:----|:----|:----| :----|
@@ -266,7 +278,7 @@ The Invoice service will extract the text, tables, and 26 invoice fields. Follow
266278
| ServiceEndDate | date | End date for the service period (for example, a utility bill service period) | 11/14/2019 | 2019-11-14 |
267279
| PreviousUnpaidBalance | number | Explicit previously unpaid balance | $500.00 | 500 |
268280

269-
Following are the line items extracted from an invoice in the JSON output response (the output below uses this [sample invoice](./media/sample-invoice.jpg))
281+
Following are the line items extracted from an invoice in the JSON output response (the following output uses this [sample invoice](./media/sample-invoice.jpg))
270282

271283
|Name| Type | Description | Text (line item #1) | Value (standardized output) |
272284
|:-----|:----|:----|:----| :----|
@@ -310,4 +322,4 @@ The JSON output has three parts:
310322

311323
* Complete a [Form Recognizer quickstart](quickstarts/get-started-sdks-rest-api.md?view=form-recog-2.1.0&preserve-view=true) and get started creating a document processing app in the development language of your choice.
312324

313-
::: moniker-end
325+
::: moniker-end

articles/applied-ai-services/form-recognizer/concept-receipt.md

Lines changed: 10 additions & 12 deletions
Original file line numberDiff line numberDiff line change
@@ -7,7 +7,7 @@ manager: nitinme
77
ms.service: applied-ai-services
88
ms.subservice: forms-recognizer
99
ms.topic: conceptual
10-
ms.date: 11/14/2022
10+
ms.date: 01/25/2023
1111
ms.author: lajanuar
1212
recommendations: false
1313
---
@@ -157,20 +157,18 @@ See how data, including time and date of transactions, merchant information, and
157157
## Supported languages and locales v3.0
158158

159159
>[!NOTE]
160-
> It's not necessary to specify a locale. This is an optional parameter. The Form Recognizer deep-learning technology will auto-detect the language of the text in your image.
160+
> Form Recognizer auto-detects language and locale data.
161161
162162
The receipt model supports all English receipts and the following locales:
163163

164-
|Language| Locale code |
164+
|Supported Languages| Details |
165165
|:-----|:----:|
166-
|English (Australia)|`en-au`|
167-
|English (Canada)|`en-ca`|
168-
|English (United Kingdom)|`en-gb`|
169-
|English (India|`en-in`|
170-
|English (United States)| `en-us`|
171-
|French | 'fr' |
172-
|Spanish | `es` |
173-
166+
|&bullet; English| United States (-us), Australia (-au), Great Britain (-gb), India (-in), United Arab Emirates (-ae)|
167+
|&bullet; Dutch| Netherlands (nl)|
168+
|&bullet; French | France (fr) |
169+
|&bullet; Japanese | Japan (ja)|
170+
|&bullet; Portuguese| Portugal (-pt), Brazil (-br)|
171+
|&bullet; Spanish | Spain (es) |
174172
::: moniker-end
175173

176174
::: moniker range="form-recog-2.1.0"
@@ -262,4 +260,4 @@ The receipt model supports all English receipts and the following locales:
262260

263261
* Complete a [Form Recognizer quickstart](quickstarts/get-started-sdks-rest-api.md?view=form-recog-2.1.0&preserve-view=true) and get started creating a document processing app in the development language of your choice.
264262

265-
::: moniker-end
263+
::: moniker-end

articles/applied-ai-services/form-recognizer/language-support.md

Lines changed: 20 additions & 13 deletions
Original file line numberDiff line numberDiff line change
@@ -7,7 +7,7 @@ manager: nitinme
77
ms.service: applied-ai-services
88
ms.subservice: forms-recognizer
99
ms.topic: reference
10-
ms.date: 01/06/2023
10+
ms.date: 01/25/2023
1111
ms.author: lajanuar
1212
---
1313

@@ -260,7 +260,7 @@ The **2022-06-30** and later releases include Japanese language support:
260260

261261
Language| Locale code |
262262
|:-----|:----:|
263-
|English (United States) |en-US|
263+
|English |en-US, en-IN, en-GB, en-CA, en-AU|
264264
|Spanish| es|
265265
|German (**2022-06-30** and later)| de|
266266
|French (**2022-06-30** and later)| fr|
@@ -505,23 +505,30 @@ This table lists the written languages supported by each Form Recognizer service
505505
## Prebuilt receipt and business card
506506

507507
>[!NOTE]
508-
> It's not necessary to specify a locale. This is an optional parameter. The Form Recognizer deep-learning technology will auto-detect the language of the text in your image.
508+
>The Form Recognizer deep-learning technology will auto-detect the language of the text in your image.
509509
510510
Prebuilt Receipt and Business Cards support all English receipts and business cards with the following locales:
511511

512-
|Language| Locale code |
512+
|Supported Languages| Details |
513513
|:-----|:----:|
514-
|English (Australia)|`en-au`|
515-
|English (Canada)|`en-ca`|
516-
|English (United Kingdom)|`en-gb`|
517-
|English (India|`en-in`|
518-
|English (United States)| `en-us`|
514+
|English| United States (-us), Australia (-au), Great Britain (-gb), India (-in|
515+
|French | France (FR) |
516+
|Spanish | Spain (ES) |
519517

520518
## Prebuilt invoice
521519

522-
Language| Locale code |
523-
|:-----|:----:|
524-
|English (United States)|en-us|
520+
>[!NOTE]
521+
>The Form Recognizer deep-learning technology will auto-detect the language of the text in your image.
522+
523+
| Supported languages | Details |
524+
|:----------------------|:---------|
525+
| <ul><li>English</li></ul>| United States (-us), Australia (-au), Canada (-ca), Great Britain (-gb), India (-in)|
526+
| <ul><li>Spanish</li></ul>|Spain (ES)|
527+
| <ul><li>German</li></ul>| Germany (DE)|
528+
| <ul><li>French</li></ul>| France (FR) |
529+
| <ul><li>Italian</li></ul>| Italy (IT)|
530+
| <ul><li>Portuguese</li></ul>| Portugal (-pt), Brazil (-br)|
531+
| <ul><li>Dutch</li></ul>| Netherlands (DE)|
525532

526533
## Prebuilt identity documents
527534

@@ -540,4 +547,4 @@ This technology is currently available for US driver licenses and the biographic
540547
::: moniker range="form-recog-2.1.0"
541548
> [!div class="nextstepaction"]
542549
> [Try Form Recognizer Sample Labeling tool](https://aka.ms/fott-2.1-ga)
543-
::: moniker-end
550+
::: moniker-end

articles/applied-ai-services/form-recognizer/whats-new.md

Lines changed: 38 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -7,7 +7,7 @@ manager: nitinme
77
ms.service: applied-ai-services
88
ms.subservice: forms-recognizer
99
ms.topic: conceptual
10-
ms.date: 12/15/2022
10+
ms.date: 01/30/2023
1111
ms.author: lajanuar
1212
monikerRange: '>=form-recog-2.1.0'
1313
recommendations: false
@@ -27,6 +27,43 @@ Form Recognizer service is updated on an ongoing basis. Bookmark this page to st
2727
>[!NOTE]
2828
> With the release of the 2022-08-31 GA API, the associated preview APIs are being deprecated. If you are using the 2021-09-30-preview or the 2022-01-30-preview API versions, please update your applications to target the 2022-08-31 API version. There are a few minor changes involved, for more information, _see_ the [migration guide](v3-migration-guide.md).
2929
30+
## January 2023
31+
32+
* **[Prebuilt receipt model](concept-receipt.md#supported-languages-and-locales-v30) —additional language support**:
33+
34+
The **prebuilt receipt model** now has added support for the following languages:
35+
36+
* English - United Arab Emirates (en-ae)
37+
* Dutch - Netherlands (nl-nl)
38+
* French - Canada (fr-ca)
39+
* Japanese - Japan (ja-jp)
40+
* Portuguese - Brazil (pt-br)
41+
42+
* **[Prebuilt invoice model](concept-invoice.md)—additional language support and field extractions**
43+
44+
The **prebuilt invoice model** now has added support for the following languages:
45+
46+
* English - Australia (en-au), Canada (en-ca), Great Britain (en-gb), India (en-in)
47+
* Portuguese - Brazil (pt-br)
48+
49+
The **prebuilt invoice model** now has added support for the following field extractions:
50+
51+
* Currency code
52+
* Payment options
53+
* Total discount
54+
* Tax items (en-in only)
55+
56+
* **[Prebuilt ID document model](concept-id-document.md#document-types)—additional document types support**
57+
58+
The **prebuilt ID document model** now has added support for the following document types:
59+
60+
* Passport, driver's license, and residence permit ID expansion.
61+
* US military ID
62+
* India ID
63+
* Australia ID
64+
* Canada ID
65+
* United Kingdom ID
66+
3067
## December 2022
3168

3269
* [**Form Recognizer Studio updates**](https://formrecognizer.appliedai.azure.com/studio)

0 commit comments

Comments
 (0)