Verwenden Sie es DetectPiiEntities mit einem oder AWS SDK CLI

    using System;
    using System.Threading.Tasks;
    using Amazon.Comprehend;
    using Amazon.Comprehend.Model;

    /// <summary>
    /// This example shows how to use the Amazon Comprehend service to find
    /// personally identifiable information (PII) within text submitted to the
    /// DetectPiiEntitiesAsync method.
    /// </summary>
    public class DetectingPII
    {
        /// <summary>
        /// This method calls the DetectPiiEntitiesAsync method to locate any
        /// personally dientifiable information within the supplied text.
        /// </summary>
        public static async Task Main()
        {
            var comprehendClient = new AmazonComprehendClient();
            var text = @"Hello Paul Santos. The latest statement for your
                        credit card account 1111-0000-1111-0000 was
                        mailed to 123 Any Street, Seattle, WA 98109.";

            var request = new DetectPiiEntitiesRequest
            {
                Text = text,
                LanguageCode = "EN",
            };

            var response = await comprehendClient.DetectPiiEntitiesAsync(request);

            if (response.Entities.Count > 0)
            {
                foreach (var entity in response.Entities)
                {
                    var entityValue = text.Substring(entity.BeginOffset, entity.EndOffset - entity.BeginOffset);
                    Console.WriteLine($"{entity.Type}: {entityValue}");
                }
            }
        }
    }

Um PII-Entitäten im Eingabetext zu erkennen

Das folgende detect-pii-entities Beispiel analysiert den Eingabetext und identifiziert Entitäten, die personenbezogene Daten enthalten (PII). Der Konfidenzwert des vortrainierten Modells wird ebenfalls für jede Vorhersage ausgegeben.

aws comprehend detect-pii-entities \
    --language-code en \
    --text "Hello Zhang Wei, I am John. Your AnyCompany Financial Services, LLC credit card \
        account 1111-XXXX-1111-XXXX has a minimum payment of $24.53 that is due by July 31st. Based on your autopay settings, \
        we will withdraw your payment on the due date from your bank account number XXXXXX1111 with the routing number XXXXX0000. \
        Customer feedback for Sunshine Spa, 123 Main St, Anywhere. Send comments to Alice at AnySpa@example.com."

Ausgabe:

{
    "Entities": [
        {
            "Score": 0.9998322129249573,
            "Type": "NAME",
            "BeginOffset": 6,
            "EndOffset": 15
        },
        {
            "Score": 0.9998878240585327,
            "Type": "NAME",
            "BeginOffset": 22,
            "EndOffset": 26
        },
        {
            "Score": 0.9994089603424072,
            "Type": "CREDIT_DEBIT_NUMBER",
            "BeginOffset": 88,
            "EndOffset": 107
        },
        {
            "Score": 0.9999760985374451,
            "Type": "DATE_TIME",
            "BeginOffset": 152,
            "EndOffset": 161
        },
        {
            "Score": 0.9999449253082275,
            "Type": "BANK_ACCOUNT_NUMBER",
            "BeginOffset": 271,
            "EndOffset": 281
        },
        {
            "Score": 0.9999847412109375,
            "Type": "BANK_ROUTING",
            "BeginOffset": 306,
            "EndOffset": 315
        },
        {
            "Score": 0.999925434589386,
            "Type": "ADDRESS",
            "BeginOffset": 354,
            "EndOffset": 365
        },
        {
            "Score": 0.9989161491394043,
            "Type": "NAME",
            "BeginOffset": 394,
            "EndOffset": 399
        },
        {
            "Score": 0.9994171857833862,
            "Type": "EMAIL",
            "BeginOffset": 403,
            "EndOffset": 418
        }
    ]
}

Weitere Informationen finden Sie unter Persönlich identifizierbare Informationen (PII) im Amazon Comprehend Developer Guide.

class ComprehendDetect:
    """Encapsulates Comprehend detection functions."""

    def __init__(self, comprehend_client):
        """
        :param comprehend_client: A Boto3 Comprehend client.
        """
        self.comprehend_client = comprehend_client


    def detect_pii(self, text, language_code):
        """
        Detects personally identifiable information (PII) in a document. PII can be
        things like names, account numbers, or addresses.

        :param text: The document to inspect.
        :param language_code: The language of the document.
        :return: The list of PII entities along with their confidence scores.
        """
        try:
            response = self.comprehend_client.detect_pii_entities(
                Text=text, LanguageCode=language_code
            )
            entities = response["Entities"]
            logger.info("Detected %s PII entities.", len(entities))
        except ClientError:
            logger.exception("Couldn't detect PII entities.")
            raise
        else:
            return entities