要求人工審查文件

設定 Google Cloud 帳戶、建立處理器並啟用人工審查後，即可將審查要求傳送至處理器。本頁說明如何為文件申請臨時人工審查。

申請人工審查

網路使用者介面

  1. 在 Google Cloud 控制台中開啟「Human-in-the-Loop」(人工參與) 頁面。

    前往人機迴圈資訊主頁

  2. 按一下要用於人工審查的處理器。

  3. 選取「上傳文件」，然後上傳要送審的本機檔案。文件可能需要 1 至 2 分鐘才會顯示在審查佇列中。

REST

使用任何要求資料之前，請先替換以下項目：

  • PROJECT_ID：您的 Google Cloud 專案 ID。
  • LOCATION：處理器的位置，例如：
    • us - 美國
    • eu - 歐盟
  • PROCESSOR_ID：自訂處理器的 ID。
  • ENABLE_SCHEMA_VALIDATION：是否應對臨時審查要求執行結構定義驗證。
    • true - 啟用臨時審查要求的結構定義驗證。
    • false - 停用臨時審查要求的結構定義驗證。
  • PRIORITY：人工審查工作的優先順序。
    • DEFAULT：預設優先程度。
    • URGENT - 緊急優先等級。標籤管理員應將標籤員資源分配給緊急工作佇列，以符合這個優先順序等級。
  • DOCUMENT：已由設定為審查的處理器處理的 Document 物件。

HTTP 方法和網址：

POST https://LOCATION-documentai.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION/processors/PROCESSOR_ID/humanReviewConfig:reviewDocument

JSON 要求主體：

{
  "enableSchemaValidation": ENABLE_SCHEMA_VALIDATION,
  "priority": "PRIORITY",
  "inlineDocument": "DOCUMENT"
}

如要傳送要求，請選擇以下其中一個選項：

curl

將要求主體儲存在名為 request.json 的檔案中，然後執行下列指令：

curl -X POST \
     -H "Authorization: Bearer $(gcloud auth print-access-token)" \
     -H "Content-Type: application/json; charset=utf-8" \
     -d @request.json \
     "https://LOCATION-documentai.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION/processors/PROCESSOR_ID/humanReviewConfig:reviewDocument"

PowerShell

將要求主體儲存在名為 request.json 的檔案中，然後執行下列指令：

$cred = gcloud auth print-access-token
$headers = @{ "Authorization" = "Bearer $cred" }

Invoke-WebRequest `
    -Method POST `
    -Headers $headers `
    -ContentType: "application/json; charset=utf-8" `
    -InFile request.json `
    -Uri "https://LOCATION-documentai.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION/processors/PROCESSOR_ID/humanReviewConfig:reviewDocument" | Select-Object -Expand Content

如果要求成功，回應會包含 Operation 的例項。如要進一步瞭解長時間執行的作業，請參閱說明文件。 

{
  "name": "projects/PROJECT_ID/locations/LOCATION/operations/OPERATION_ID",
  "metadata": {
    "@type": "type.googleapis.com/google.cloud.documentai.v1.ReviewDocumentOperationMetadata",
    "commonMetadata": {
      "state": "RUNNING",
      "createTime": "TIMESTAMP",
      "updateTime": "TIMESTAMP",
      "resource": "projects/PROJECT_ID/locations/LOCATION/processors/PROCESSOR_ID/humanReviewConfig"
    }
  }
}

Python

詳情請參閱 Document AI Python API 參考說明文件。

如要向 Document AI 進行驗證，請設定應用程式預設憑證。 詳情請參閱「為本機開發環境設定驗證」。


from google.api_core.client_options import ClientOptions
from google.cloud import documentai  # type: ignore

# TODO(developer): Uncomment these variables before running the sample.
# project_id = 'YOUR_PROJECT_ID'
# location = 'YOUR_PROCESSOR_LOCATION' # Format is 'us' or 'eu'
# processor_id = 'YOUR_PROCESSOR_ID' # Create processor before running sample
# file_path = '/path/to/local/pdf'
# mime_type = 'application/pdf'  # https://cloud.google.com/document-ai/docs/file-types


def review_document_sample(
    project_id: str, location: str, processor_id: str, file_path: str, mime_type: str
) -> None:
    # You must set the api_endpoint if you use a location other than 'us'.
    opts = ClientOptions(api_endpoint=f"{location}-documentai.googleapis.com")

    # Create a client
    client = documentai.DocumentProcessorServiceClient(client_options=opts)

    # Make Processing Request
    inline_document = process_document(
        project_id, location, processor_id, file_path, mime_type
    )

    # Get the full resource name of the human review config, e.g.:
    # projects/project_id/locations/location/processor/processor_id/humanReviewConfig
    human_review_config = client.human_review_config_path(
        project_id, location, processor_id
    )

    # Options are DEFAULT, URGENT
    priority = documentai.ReviewDocumentRequest.Priority.DEFAULT

    # Configure the human review request
    request = documentai.ReviewDocumentRequest(
        inline_document=inline_document,
        human_review_config=human_review_config,
        enable_schema_validation=False,
        priority=priority,
    )

    # Make a request for human review of the processed document
    operation = client.review_document(request=request)

    # Print operation name, can be used to check status of the request
    print(operation.operation.name)


def process_document(
    project_id: str, location: str, processor_id: str, file_path: str, mime_type: str
) -> documentai.Document:
    # You must set the api_endpoint if you use a location other than 'us'.
    opts = ClientOptions(api_endpoint=f"{location}-documentai.googleapis.com")

    client = documentai.DocumentProcessorServiceClient(client_options=opts)

    # The full resource name of the processor, e.g.:
    # projects/project_id/locations/location/processor/processor_id
    name = client.processor_path(project_id, location, processor_id)

    # Read the file into memory
    with open(file_path, "rb") as image:
        image_content = image.read()

    # Load Binary Data into Document AI RawDocument Object
    raw_document = documentai.RawDocument(content=image_content, mime_type=mime_type)

    # Configure the process request
    request = documentai.ProcessRequest(name=name, raw_document=raw_document)

    result = client.process_document(request=request)

    return result.document