Microsoft AI-102 (Designing and Implementing a Microsoft Azure AI Solution) Practice Test 56

Question 550

An invoice includes a line-item table, and the system stores only the total. What field group should be mapped?

  1. Validate the extracted item amounts and total with application-side arithmetic
  2. Extract the recognized invoice items and their structured item fields
  3. Use a separate identity verification and authorization process before granting access
  4. Consume supported selection-mark detection results

Explanation

Correct Answer

B:

Line items convey quantity, description, and amounts that a single total cannot represent. In the shared-services expense document processor, confirm the fix by retesting the affected behavior after extracting the recognized invoice items and their structured item fields.

Incorrect Answers

A:

Although useful elsewhere in the shared-services expense document processor, document extraction returns recognized values; financial consistency checks remain an application responsibility; the present case is different and calls for the team to extract the recognized invoice items and their structured item fields.

C:

That change addresses another failure mode: oCR or field extraction does not establish document authenticity or the user's right to an account; it does not address this case, for which the relevant intervention is to extract the recognized invoice items and their structured item fields.

D:

Selection marks are visual document elements; their state is not reliably recoverable from text lines alone in its own workflow, but that is a different correction from the present requirement to extract the recognized invoice items and their structured item fields. The reported issue would remain.

Question 551

A document has a table whose rows must be loaded into a database with correct cell coordinates. Which result should be consumed?

  1. Use Layout model table cells with row, column, and span metadata
  2. Use the Receipt model and map its receipt-specific output schema
  3. Use the prebuilt ID Document model and validate its typed identity fields
  4. Preserve page identifiers and text spans or polygon coordinates

Explanation

Correct Answer

A:

Layout extraction preserves table structure that plain concatenated OCR text often loses. In the shared-services expense document processor, confirm the fix by retesting the affected behavior after using Layout model table cells with row, column, and span metadata.

Incorrect Answers

B:

Point-of-sale receipts have a different document structure from supplier invoices in its own workflow, but that is a different correction from the present requirement to use Layout model table cells with row, column, and span metadata. The reported issue would remain.

C:

Although useful elsewhere in the shared-services expense document processor, the model extracts relevant fields from supported IDs; its output is data extraction, not independent proof of identity; the present case is different and calls for the team to use Layout model table cells with row, column, and span metadata.

D:

That change addresses another failure mode: read output includes location information on supported inputs, enabling verification against the source page; it does not address this case, for which the relevant intervention is to use Layout model table cells with row, column, and span metadata.

Question 552

A team responsible for a shared-services expense document processor needs to recognize merchant, line item, tax, and total information from purchase receipts; the acceptance check is that receipt fields appear under the relevant receipt schema. Which capability should be selected?

  1. Use the prebuilt Invoice model
  2. Use the prebuilt Receipt model
  3. Use the prebuilt Layout model
  4. Use the prebuilt Read model
  5. Use the prebuilt Identity Document model

Explanation

Correct Answer

B:

The Receipt model is designed for common retail receipt fields without requiring a fresh custom labeled dataset. For this shared-services expense document processor, the intended evidence is that receipt fields appear under the relevant receipt schema. An invoice-specific model is less directly aligned with point-of-sale slips.

Incorrect Answers

A:

The Invoice model recognizes invoice-related fields such as vendor data, dates, and totals from supported formats; it may be used to extract supplier and amount fields from standard invoice documents in a shared-services expense document processor, but the current requirement is instead to recognize merchant, line item, tax, and total information from purchase receipts. That separate capability does not prove that receipt fields appear under the relevant receipt schema; It does not expect to recognize the fields of an identity card instead, so selecting that alternative would not meet the stated acceptance check.

C:

Document Intelligence Layout extracts structural elements of pages such as tables and selection marks where supported; it may be used to retrieve tables, paragraphs, and selection marks with document structure in a shared-services expense document processor, but the current requirement is instead to recognize merchant, line item, tax, and total information from purchase receipts. That separate capability does not prove that receipt fields appear under the relevant receipt schema; It is not chiefly a domain-specific purchase-invoice field classifier, so selecting that alternative would not meet the stated acceptance check.

D:

Document Intelligence Read focuses on OCR and text locations across supported document inputs; it may be used to obtain printed or handwritten text from scanned pages without specialized business-field extraction in a shared-services expense document processor, but the current requirement is instead to recognize merchant, line item, tax, and total information from purchase receipts. That separate capability does not prove that receipt fields appear under the relevant receipt schema; It does not classify invoice totals into a dedicated invoice schema by default, so selecting that alternative would not meet the stated acceptance check.

E:

The ID Document model returns structured fields from supported identity-document layouts; it may be used to extract recognized fields from supported passports or identification documents in a shared-services expense document processor, but the current requirement is instead to recognize merchant, line item, tax, and total information from purchase receipts. That separate capability does not prove that receipt fields appear under the relevant receipt schema; It is not an identity authorization service and does not verify whether someone may access an Azure resource, so selecting that alternative would not meet the stated acceptance check.

Question 553

A PDF contains headings and two columns. A parser produces interleaved lines when using only raw text. What should it inspect?

  1. Preserve the text reading order and page structure returned by the service
  2. Use paragraphs, layout roles, and bounding regions from the Layout analysis
  3. Apply a supported confidence threshold and manual verification for important fields
  4. Confirm the model's supported document types and regional coverage

Explanation

Correct Answer

B:

Page structure helps reconstruct content organization beyond arbitrary token order. In the shared-services expense document processor, confirm the fix by retesting the affected behavior after using paragraphs, layout roles, and bounding regions from the Layout analysis.

Incorrect Answers

A:

Alphabetical sorting destroys source order; OCR results should be reconstructed using reading-order metadata in its own workflow, but that is a different correction from the present requirement to use paragraphs, layout roles, and bounding regions from the Layout analysis. The reported issue would remain.

C:

Although useful elsewhere in the shared-services expense document processor, a recognized numeric value is not guaranteed correct simply because it is present; the present case is different and calls for the team to use paragraphs, layout roles, and bounding regions from the Layout analysis.

D:

That change addresses another failure mode: prebuilt ID extraction has bounded input support; unsupported formats may need another workflow; it does not address this case, for which the relevant intervention is to use paragraphs, layout roles, and bounding regions from the Layout analysis.

Question 554

A form contains checked and unchecked boxes, and OCR text alone cannot distinguish them. What layout feature matters?

  1. Use a field-specific prebuilt or custom extraction model for typed business fields
  2. Validate the extracted item amounts and total with application-side arithmetic
  3. Use a separate identity verification and authorization process before granting access
  4. Consume supported selection-mark detection results

Explanation

Correct Answer

D:

Selection marks are visual document elements; their state is not reliably recoverable from text lines alone. In the shared-services expense document processor, confirm the fix by retesting the affected behavior after consuming supported selection-mark detection results.

Incorrect Answers

A:

Although useful elsewhere in the shared-services expense document processor, read primarily returns text and its structure, not a universal named business schema; the present case is different and calls for the team to consume supported selection-mark detection results.

B:

That change addresses another failure mode: document extraction returns recognized values; financial consistency checks remain an application responsibility; it does not address this case, for which the relevant intervention is to consume supported selection-mark detection results.

C:

OCR or field extraction does not establish document authenticity or the user's right to an account in its own workflow, but that is a different correction from the present requirement to consume supported selection-mark detection results. The reported issue would remain.

Question 555

The solution brief for a shared-services expense document processor requires the system to extract supplier and amount fields from standard invoice documents. A successful test confirms that structured output contains invoice-specific fields. What should the team use?

  1. Use the prebuilt Identity Document model
  2. Use the prebuilt Read model
  3. Use the prebuilt Receipt model
  4. Use the prebuilt Invoice model

Explanation

Correct Answer

D:

The Invoice model recognizes invoice-related fields such as vendor data, dates, and totals from supported formats. For this shared-services expense document processor, the intended evidence is that structured output contains invoice-specific fields. It does not expect to recognize the fields of an identity card instead.

Incorrect Answers

A:

The ID Document model returns structured fields from supported identity-document layouts; it may be used to extract recognized fields from supported passports or identification documents in a shared-services expense document processor, but the current requirement is instead to extract supplier and amount fields from standard invoice documents. That separate capability does not prove that structured output contains invoice-specific fields; It is not an identity authorization service and does not verify whether someone may access an Azure resource, so selecting that alternative would not meet the stated acceptance check.

B:

Document Intelligence Read focuses on OCR and text locations across supported document inputs; it may be used to obtain printed or handwritten text from scanned pages without specialized business-field extraction in a shared-services expense document processor, but the current requirement is instead to extract supplier and amount fields from standard invoice documents. That separate capability does not prove that structured output contains invoice-specific fields; It does not classify invoice totals into a dedicated invoice schema by default, so selecting that alternative would not meet the stated acceptance check.

C:

The Receipt model is designed for common retail receipt fields without requiring a fresh custom labeled dataset; it may be used to recognize merchant, line item, tax, and total information from purchase receipts in a shared-services expense document processor, but the current requirement is instead to extract supplier and amount fields from standard invoice documents. That separate capability does not prove that structured output contains invoice-specific fields; An invoice-specific model is less directly aligned with point-of-sale slips, so selecting that alternative would not meet the stated acceptance check.

Question 556

A supplier field is missing from a stylized invoice. How should the application handle the result?

  1. Preserve the text reading order and page structure returned by the service
  2. Use paragraphs, layout roles, and bounding regions from the Layout analysis
  3. Apply a supported confidence threshold and manual verification for important fields
  4. Validate missing or low-confidence invoice fields and route exceptions for review

Explanation

Correct Answer

D:

Prebuilt models are probabilistic; not every document exposes every recognized field reliably. In the shared-services expense document processor, confirm the fix by retesting the affected behavior after validating missing or low-confidence invoice fields and route exceptions for review.

Incorrect Answers

A:

Although useful elsewhere in the shared-services expense document processor, alphabetical sorting destroys source order; OCR results should be reconstructed using reading-order metadata; the present case is different and calls for the team to validate missing or low-confidence invoice fields and route exceptions for review.

B:

Page structure helps reconstruct content organization beyond arbitrary token order in its own workflow, but that is a different correction from the present requirement to validate missing or low-confidence invoice fields and route exceptions for review. The reported issue would remain.

C:

That change addresses another failure mode: a recognized numeric value is not guaranteed correct simply because it is present; it does not address this case, for which the relevant intervention is to validate missing or low-confidence invoice fields and route exceptions for review.

Question 557

An ID extractor recognizes a passport number, and the application automatically grants account access. What security gap exists?

  1. Validate the extracted item amounts and total with application-side arithmetic
  2. Extract the recognized invoice items and their structured item fields
  3. Consume supported selection-mark detection results
  4. Use a separate identity verification and authorization process before granting access

Explanation

Correct Answer

D:

OCR or field extraction does not establish document authenticity or the user's right to an account. In the shared-services expense document processor, confirm the fix by retesting the affected behavior after using a separate identity verification and authorization process before granting access.

Incorrect Answers

A:

That change addresses another failure mode: document extraction returns recognized values; financial consistency checks remain an application responsibility; it does not address this case, for which the relevant intervention is to use a separate identity verification and authorization process before granting access.

B:

Line items convey quantity, description, and amounts that a single total cannot represent in its own workflow, but that is a different correction from the present requirement to use a separate identity verification and authorization process before granting access. The reported issue would remain.

C:

Although useful elsewhere in the shared-services expense document processor, selection marks are visual document elements; their state is not reliably recoverable from text lines alone; the present case is different and calls for the team to use a separate identity verification and authorization process before granting access.

Question 558

A release for a shared-services expense document processor is blocked until the application can extract recognized fields from supported passports or identification documents. The tester will verify that the extraction response identifies supported ID-document attributes. What should be implemented?

  1. Use the prebuilt Layout model
  2. Use the prebuilt Read model
  3. Use the prebuilt Identity Document model
  4. Use the prebuilt Invoice model

Explanation

Correct Answer

C:

The ID Document model returns structured fields from supported identity-document layouts. For this shared-services expense document processor, the intended evidence is that the extraction response identifies supported ID-document attributes. It is not an identity authorization service and does not verify whether someone may access an Azure resource.

Incorrect Answers

A:

Document Intelligence Layout extracts structural elements of pages such as tables and selection marks where supported; it may be used to retrieve tables, paragraphs, and selection marks with document structure in a shared-services expense document processor, but the current requirement is instead to extract recognized fields from supported passports or identification documents. That separate capability does not prove that the extraction response identifies supported ID-document attributes; It is not chiefly a domain-specific purchase-invoice field classifier, so selecting that alternative would not meet the stated acceptance check.

B:

Document Intelligence Read focuses on OCR and text locations across supported document inputs; it may be used to obtain printed or handwritten text from scanned pages without specialized business-field extraction in a shared-services expense document processor, but the current requirement is instead to extract recognized fields from supported passports or identification documents. That separate capability does not prove that the extraction response identifies supported ID-document attributes; It does not classify invoice totals into a dedicated invoice schema by default, so selecting that alternative would not meet the stated acceptance check.

D:

The Invoice model recognizes invoice-related fields such as vendor data, dates, and totals from supported formats; it may be used to extract supplier and amount fields from standard invoice documents in a shared-services expense document processor, but the current requirement is instead to extract recognized fields from supported passports or identification documents. That separate capability does not prove that the extraction response identifies supported ID-document attributes; It does not expect to recognize the fields of an identity card instead, so selecting that alternative would not meet the stated acceptance check.

Question 559

An OCR result must map a recognized paragraph to its location on scanned page 3. Which returned fields should be retained?

  1. Preserve page identifiers and text spans or polygon coordinates
  2. Use the Invoice model's structured invoice fields and their confidence data
  3. Use the Receipt model and map its receipt-specific output schema
  4. Use Layout model table cells with row, column, and span metadata

Explanation

Correct Answer

A:

Read output includes location information on supported inputs, enabling verification against the source page. In the shared-services expense document processor, confirm the fix by retesting the affected behavior after preserving page identifiers and text spans or polygon coordinates.

Incorrect Answers

B:

Prebuilt invoice extraction identifies domain-specific fields suitable for accounting workflows in its own workflow, but that is a different correction from the present requirement to preserve page identifiers and text spans or polygon coordinates. The reported issue would remain.

C:

Although useful elsewhere in the shared-services expense document processor, point-of-sale receipts have a different document structure from supplier invoices; the present case is different and calls for the team to preserve page identifiers and text spans or polygon coordinates.

D:

That change addresses another failure mode: layout extraction preserves table structure that plain concatenated OCR text often loses; it does not address this case, for which the relevant intervention is to preserve page identifiers and text spans or polygon coordinates.

Question 560

An onboarding system needs to populate name and date of birth from supported identity documents. What field-processing approach fits?

  1. Use the Invoice model's structured invoice fields and their confidence data
  2. Preserve page identifiers and text spans or polygon coordinates
  3. Use the Receipt model and map its receipt-specific output schema
  4. Use the prebuilt ID Document model and validate its typed identity fields

Explanation

Correct Answer

D:

The model extracts relevant fields from supported IDs; its output is data extraction, not independent proof of identity. In the shared-services expense document processor, confirm the fix by retesting the affected behavior after using the prebuilt ID Document model and validate its typed identity fields.

Incorrect Answers

A:

That change addresses another failure mode: prebuilt invoice extraction identifies domain-specific fields suitable for accounting workflows; it does not address this case, for which the relevant intervention is to use the prebuilt ID Document model and validate its typed identity fields.

B:

Read output includes location information on supported inputs, enabling verification against the source page in its own workflow, but that is a different correction from the present requirement to use the prebuilt ID Document model and validate its typed identity fields. The reported issue would remain.

C:

Although useful elsewhere in the shared-services expense document processor, point-of-sale receipts have a different document structure from supplier invoices; the present case is different and calls for the team to use the prebuilt ID Document model and validate its typed identity fields.

Designing and Implementing a Microsoft Azure AI Solution (AI-102) Practice Tests