本頁面由 Cloud Translation API 翻譯而成。

分析實體

實體分析會檢查指定文字中出現的已知實體 (公眾人物或地標等專有名詞) 並傳回有關這些實體的資訊。實體分析是透過 analyzeEntities 方法執行。如要瞭解 Natural Language 識別的實體類型，請參閱實體說明文件。如需有關 Natural Language API 支援哪些語言的資訊，請參閱語言支援。

本節示範幾種偵測文件中實體的方法。請為每份文件分別提交要求。

分析字串中的實體

以下示範如何針對直接傳送至 Natural Language API 的文字字串執行實體分析：

通訊協定

POST 要求，並提供適當的要求主體，如同下列範例所示。documents:analyzeEntities

範例使用 gcloud auth application-default print-access-token 指令，取得透過 Google Cloud Platform gcloud CLI 建立的專案服務帳戶存取權杖。如需安裝 gcloud CLI、使用服務帳戶建立專案的操作說明，請參閱快速入門導覽課程。

curl -X POST \
     -H "Authorization: Bearer "$(gcloud auth application-default print-access-token) \
     -H "Content-Type: application/json; charset=utf-8" \
     --data "{
  'encodingType': 'UTF8',
  'document': {
    'type': 'PLAIN_TEXT',
    'content': 'President Trump will speak from the White House, located
  at 1600 Pennsylvania Ave NW, Washington, DC, on October 7.'
  }
}" "https://language.googleapis.com/v2/documents:analyzeEntities"

如未指定 document.language_code，系統會自動偵測語言。如需有關 Natural Language API 支援哪些語言的資訊，請參閱語言支援。如需更多有關設定要求主體的資訊，請參閱 Document 參考說明文件。

如果要求成功，伺服器會傳回 200 OK HTTP 狀態碼與 JSON 格式的回應：

{
  "entities": [
    {
      "name": "October 7",
      "type": "DATE",
      "metadata": {
        "month": "10",
        "day": "7"
      },
      "mentions": [
        {
          "text": {
            "content": "October 7",
            "beginOffset": -1
          },
          "type": "TYPE_UNKNOWN",
          "probability": 1
        }
      ]
    },
    {
      "name": "1600",
      "type": "NUMBER",
      "metadata": {
        "value": "1600"
      },
      "mentions": [
        {
          "text": {
            "content": "1600",
            "beginOffset": -1
          },
          "type": "TYPE_UNKNOWN",
          "probability": 1
        }
      ]
    },
    {
      "name": "7",
      "type": "NUMBER",
      "metadata": {
        "value": "7"
      },
      "mentions": [
        {
          "text": {
            "content": "7",
            "beginOffset": -1
          },
          "type": "TYPE_UNKNOWN",
          "probability": 1
        }
      ]
    },
    {
      "name": "1600 Pennsylvania Ave NW, Washington, DC",
      "type": "ADDRESS",
      "metadata": {
        "locality": "Washington",
        "narrow_region": "District of Columbia",
        "street_name": "Pennsylvania Avenue Northwest",
        "street_number": "1600",
        "broad_region": "District of Columbia",
        "country": "US"
      },
      "mentions": [
        {
          "text": {
            "content": "1600 Pennsylvania Ave NW, Washington, DC",
            "beginOffset": -1
          },
          "type": "TYPE_UNKNOWN",
          "probability": 1
        }
      ]
    },
    {
      "name": "1600 Pennsylvania Ave NW",
      "type": "LOCATION",
      "metadata": {},
      "mentions": [
        {
          "text": {
            "content": "1600 Pennsylvania Ave NW",
            "beginOffset": -1
          },
          "type": "PROPER",
          "probability": 0.901
        }
      ]
    },
    {
      "name": "President",
      "type": "PERSON",
      "metadata": {},
      "mentions": [
        {
          "text": {
            "content": "President",
            "beginOffset": -1
          },
          "type": "COMMON",
          "probability": 0.941
        }
      ]
    },
    {
      "name": "Trump",
      "type": "PERSON",
      "metadata": {},
      "mentions": [
        {
          "text": {
            "content": "Trump",
            "beginOffset": -1
          },
          "type": "PROPER",
          "probability": 0.948
        }
      ]
    },
    {
      "name": "Washington, DC",
      "type": "LOCATION",
      "metadata": {},
      "mentions": [
        {
          "text": {
            "content": "Washington, DC",
            "beginOffset": -1
          },
          "type": "PROPER",
          "probability": 0.92
        }
      ]
    },
    {
      "name": "White House",
      "type": "LOCATION",
      "metadata": {},
      "mentions": [
        {
          "text": {
            "content": "White House",
            "beginOffset": -1
          },
          "type": "PROPER",
          "probability": 0.785
        }
      ]
    }
  ],
  "languageCode": "en",
  "languageSupported": true
}

entities 陣列中的 Entity 物件代表偵測到的實體，其中含有實體名稱與類型等資訊。

gcloud

如需完整的詳細資訊，請參閱 analyze-entities 指令。

如要執行實體分析，請使用 gcloud CLI，並使用 --content 標記標示要分析的內容：

gcloud ml language analyze-entities --content="President Trump will speak from the White House, located
  at 1600 Pennsylvania Ave NW, Washington, DC, on October 7."

如果要求成功，伺服器會傳回 JSON 格式的回應：

{
  "entities": [
    {
      "name": "Trump",
      "type": "PERSON",
      "metadata": {
        "mid": "/m/0cqt90",
        "wikipedia_url": "https://en.wikipedia.org/wiki/Donald_Trump"
      },
      "salience": 0.7936003,
      "mentions": [
        {
          "text": {
            "content": "Trump",
            "beginOffset": 10
          },
          "type": "PROPER"
        },
        {
          "text": {
            "content": "President",
            "beginOffset": 0
          },
          "type": "COMMON"
        }
      ]
    },
    {
      "name": "White House",
      "type": "LOCATION",
      "metadata": {
        "mid": "/m/081sq",
        "wikipedia_url": "https://en.wikipedia.org/wiki/White_House"
      },
      "salience": 0.09172433,
      "mentions": [
        {
          "text": {
            "content": "White House",
            "beginOffset": 36
          },
          "type": "PROPER"
        }
      ]
    },
    {
      "name": "Pennsylvania Ave NW",
      "type": "LOCATION",
      "metadata": {
        "mid": "/g/1tgb87cq"
      },
      "salience": 0.085507184,
      "mentions": [
        {
          "text": {
            "content": "Pennsylvania Ave NW",
            "beginOffset": 65
          },
          "type": "PROPER"
        }
      ]
    },
    {
      "name": "Washington, DC",
      "type": "LOCATION",
      "metadata": {
        "mid": "/m/0rh6k",
        "wikipedia_url": "https://en.wikipedia.org/wiki/Washington,_D.C."
      },
      "salience": 0.029168168,
      "mentions": [
        {
          "text": {
            "content": "Washington, DC",
            "beginOffset": 86
          },
          "type": "PROPER"
        }
      ]
    }
    {
      "name": "1600 Pennsylvania Ave NW, Washington, DC",
      "type": "ADDRESS",
      "metadata": {
        "country": "US",
        "sublocality": "Fort Lesley J. McNair",
        "locality": "Washington",
        "street_name": "Pennsylvania Avenue Northwest",
        "broad_region": "District of Columbia",
        "narrow_region": "District of Columbia",
        "street_number": "1600"
      },
      "salience": 0,
      "mentions": [
        {
          "text": {
            "content": "1600 Pennsylvania Ave NW, Washington, DC",
            "beginOffset": 60
          },
          "type": "TYPE_UNKNOWN"
        }
      ]
      }
    }
    {
      "name": "1600",
       "type": "NUMBER",
       "metadata": {
           "value": "1600"
       },
       "salience": 0,
       "mentions": [
         {
          "text": {
              "content": "1600",
              "beginOffset": 60
           },
           "type": "TYPE_UNKNOWN"
        }
     ]
     },
     {
       "name": "October 7",
       "type": "DATE",
       "metadata": {
         "day": "7",
         "month": "10"
       },
       "salience": 0,
       "mentions": [
         {
           "text": {
             "content": "October 7",
             "beginOffset": 105
            },
           "type": "TYPE_UNKNOWN"
         }
       ]
     }
     {
       "name": "7",
       "type": "NUMBER",
       "metadata": {
         "value": "7"
       },
       "salience": 0,
       "mentions": [
         {
           "text": {
             "content": "7",
             "beginOffset": 113
           },
         "type": "TYPE_UNKNOWN"
         }
        ]
     }
  ],
  "language": "en"
}

entities 陣列中的 Entity 物件代表偵測到的實體，其中含有實體名稱與類型等資訊。

Go

如要瞭解如何安裝及使用 Natural Language 的用戶端程式庫，請參閱Natural Language 用戶端程式庫。詳情請參閱 Natural Language Go API 參考說明文件。

如要向 Natural Language 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」。

import (
	"context"
	"fmt"
	"io"

	language "cloud.google.com/go/language/apiv2"
	"cloud.google.com/go/language/apiv2/languagepb"
)

// analyzeEntities sends a string of text to the Cloud Natural Language API to
// detect the entities of the text.
func analyzeEntities(w io.Writer, text string) error {
	ctx := context.Background()

	// Initialize client.
	client, err := language.NewClient(ctx)
	if err != nil {
		return err
	}
	defer client.Close()

	resp, err := client.AnalyzeEntities(ctx, &languagepb.AnalyzeEntitiesRequest{
		Document: &languagepb.Document{
			Source: &languagepb.Document_Content{
				Content: text,
			},
			Type: languagepb.Document_PLAIN_TEXT,
		},
		EncodingType: languagepb.EncodingType_UTF8,
	})

	if err != nil {
		return fmt.Errorf("AnalyzeEntities: %w", err)
	}
	fmt.Fprintf(w, "Response: %q\n", resp)

	return nil
}

Java

如要瞭解如何安裝及使用 Natural Language 的用戶端程式庫，請參閱Natural Language 用戶端程式庫。詳情請參閱 Natural Language Java API 參考說明文件。

如要向 Natural Language 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」。

// Instantiate the Language client com.google.cloud.language.v2.LanguageServiceClient
try (LanguageServiceClient language = LanguageServiceClient.create()) {
  Document doc = Document.newBuilder().setContent(text).setType(Type.PLAIN_TEXT).build();
  AnalyzeEntitiesRequest request =
      AnalyzeEntitiesRequest.newBuilder()
          .setDocument(doc)
          .setEncodingType(EncodingType.UTF16)
          .build();

  AnalyzeEntitiesResponse response = language.analyzeEntities(request);

  // Print the response
  for (Entity entity : response.getEntitiesList()) {
    System.out.printf("Entity: %s", entity.getName());
    System.out.println("Metadata: ");
    for (Map.Entry<String, String> entry : entity.getMetadataMap().entrySet()) {
      System.out.printf("%s : %s", entry.getKey(), entry.getValue());
    }
    for (EntityMention mention : entity.getMentionsList()) {
      System.out.printf("Begin offset: %d\n", mention.getText().getBeginOffset());
      System.out.printf("Content: %s\n", mention.getText().getContent());
      System.out.printf("Type: %s\n\n", mention.getType());
      System.out.printf("Probability: %s\n\n", mention.getProbability());
    }
  }
}

Node.js

如要瞭解如何安裝及使用 Natural Language 的用戶端程式庫，請參閱Natural Language 用戶端程式庫。詳情請參閱 Natural Language Node.js API 參考說明文件。

如要向 Natural Language 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」。

// Imports the Google Cloud client library
const language = require('@google-cloud/language').v2;

// Creates a client
const client = new language.LanguageServiceClient();

/**
 * TODO(developer): Uncomment the following line to run this code.
 */
// const text = 'Your text to analyze, e.g. Hello, world!';

// Prepares a document, representing the provided text
const document = {
  content: text,
  type: 'PLAIN_TEXT',
};

// Detects entities in the document
const [result] = await client.analyzeEntities({document});

const entities = result.entities;

console.log('Entities:');
entities.forEach(entity => {
  console.log(entity.name);
  console.log(` - Type: ${entity.type}`);
  if (entity.metadata) {
    console.log(` - Metadata: ${entity.metadata}`);
  }
});

Python

如要瞭解如何安裝及使用 Natural Language 的用戶端程式庫，請參閱Natural Language 用戶端程式庫。詳情請參閱 Natural Language Python API 參考說明文件。

如要向 Natural Language 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.cloud import language_v2


def sample_analyze_entities(text_content: str = "California is a state.") -> None:
    """
    Analyzes Entities in a string.

    Args:
      text_content: The text content to analyze
    """

    client = language_v2.LanguageServiceClient()

    # Available types: PLAIN_TEXT, HTML
    document_type_in_plain_text = language_v2.Document.Type.PLAIN_TEXT

    # Optional. If not specified, the language is automatically detected.
    # For list of supported languages:
    # https://cloud.google.com/natural-language/docs/languages
    language_code = "en"
    document = {
        "content": text_content,
        "type_": document_type_in_plain_text,
        "language_code": language_code,
    }

    # Available values: NONE, UTF8, UTF16, UTF32.
    # See https://cloud.google.com/natural-language/docs/reference/rest/v2/EncodingType.
    encoding_type = language_v2.EncodingType.UTF8

    response = client.analyze_entities(
        request={"document": document, "encoding_type": encoding_type}
    )

    for entity in response.entities:
        print(f"Representative name for the entity: {entity.name}")

        # Get entity type, e.g. PERSON, LOCATION, ADDRESS, NUMBER, et al.
        # See https://cloud.google.com/natural-language/docs/reference/rest/v2/Entity#type.
        print(f"Entity type: {language_v2.Entity.Type(entity.type_).name}")

        # Loop over the metadata associated with entity.
        # Some entity types may have additional metadata, e.g. ADDRESS entities
        # may have metadata for the address street_name, postal_code, et al.
        for metadata_name, metadata_value in entity.metadata.items():
            print(f"{metadata_name}: {metadata_value}")

        # Loop over the mentions of this entity in the input document.
        # The API currently supports proper noun mentions.
        for mention in entity.mentions:
            print(f"Mention text: {mention.text.content}")

            # Get the mention type, e.g. PROPER for proper noun
            print(f"Mention type: {language_v2.EntityMention.Type(mention.type_).name}")

            # Get the probability score associated with the first mention of the entity in the (0, 1.0] range.
            print(f"Probability score: {mention.probability}")

    # Get the language of the text, which will be the same as
    # the language specified in the request or, if not specified,
    # the automatically-detected language.
    print(f"Language of the text: {response.language_code}")

其他語言

C#：請按照用戶端程式庫頁面的 C# 設定說明操作，然後前往 .NET 適用的 Natural Language 參考說明文件。

PHP：請按照用戶端程式庫頁面的 PHP 設定說明操作，然後前往 PHP 適用的 Natural Language 參考文件。

Ruby：請按照用戶端程式庫頁面的 Ruby 設定說明操作，然後前往 Ruby 適用的 Natural Language 參考說明文件。

分析 Cloud Storage 內容中的實體

為方便起見，Natural Language API 可以直接對 Cloud Storage 中的檔案執行實體分析，您無需在要求內容中傳送檔案的內容。

以下示範如何對位於 Cloud Storage 的檔案執行實體分析。

通訊協定

POST 要求，並提供適當的要求主體及文件路徑，如同下列範例所示。POSTdocuments:analyzeEntities

curl -X POST \
     -H "Authorization: Bearer "$(gcloud auth application-default print-access-token) \
     -H "Content-Type: application/json; charset=utf-8" \
     --data "{
  'document':{
    'type':'PLAIN_TEXT',
    'gcsContentUri':'gs://<bucket-name>/<object-name>'
  }
}" "https://language.googleapis.com/v2/documents:analyzeEntities"

如未指定 document.language_code，系統會自動偵測語言。如需有關 Natural Language API 支援哪些語言的資訊，請參閱語言支援。如要進一步瞭解如何設定要求內容，請參閱 Document 參考說明文件。

如果要求成功，伺服器會傳回 200 OK HTTP 狀態碼與 JSON 格式的回應：

{
  "entities": [
    {
      "name": "October 7",
      "type": "DATE",
      "metadata": {
        "month": "10",
        "day": "7"
      },
      "mentions": [
        {
          "text": {
            "content": "October 7",
            "beginOffset": -1
          },
          "type": "TYPE_UNKNOWN",
          "probability": 1
        }
      ]
    },
    {
      "name": "1600",
      "type": "NUMBER",
      "metadata": {
        "value": "1600"
      },
      "mentions": [
        {
          "text": {
            "content": "1600",
            "beginOffset": -1
          },
          "type": "TYPE_UNKNOWN",
          "probability": 1
        }
      ]
    },
    {
      "name": "7",
      "type": "NUMBER",
      "metadata": {
        "value": "7"
      },
      "mentions": [
        {
          "text": {
            "content": "7",
            "beginOffset": -1
          },
          "type": "TYPE_UNKNOWN",
          "probability": 1
        }
      ]
    },
    {
      "name": "1600 Pennsylvania Ave NW, Washington, DC",
      "type": "ADDRESS",
      "metadata": {
        "locality": "Washington",
        "narrow_region": "District of Columbia",
        "street_name": "Pennsylvania Avenue Northwest",
        "street_number": "1600",
        "broad_region": "District of Columbia",
        "country": "US"
      },
      "mentions": [
        {
          "text": {
            "content": "1600 Pennsylvania Ave NW, Washington, DC",
            "beginOffset": -1
          },
          "type": "TYPE_UNKNOWN",
          "probability": 1
        }
      ]
    },
    {
      "name": "1600 Pennsylvania Ave NW",
      "type": "LOCATION",
      "metadata": {},
      "mentions": [
        {
          "text": {
            "content": "1600 Pennsylvania Ave NW",
            "beginOffset": -1
          },
          "type": "PROPER",
          "probability": 0.901
        }
      ]
    },
    {
      "name": "President",
      "type": "PERSON",
      "metadata": {},
      "mentions": [
        {
          "text": {
            "content": "President",
            "beginOffset": -1
          },
          "type": "COMMON",
          "probability": 0.941
        }
      ]
    },
    {
      "name": "Trump",
      "type": "PERSON",
      "metadata": {},
      "mentions": [
        {
          "text": {
            "content": "Trump",
            "beginOffset": -1
          },
          "type": "PROPER",
          "probability": 0.948
        }
      ]
    },
    {
      "name": "Washington, DC",
      "type": "LOCATION",
      "metadata": {},
      "mentions": [
        {
          "text": {
            "content": "Washington, DC",
            "beginOffset": -1
          },
          "type": "PROPER",
          "probability": 0.92
        }
      ]
    },
    {
      "name": "White House",
      "type": "LOCATION",
      "metadata": {},
      "mentions": [
        {
          "text": {
            "content": "White House",
            "beginOffset": -1
          },
          "type": "PROPER",
          "probability": 0.785
        }
      ]
    }
  ],
  "languageCode": "en",
  "languageSupported": true
}

entities 陣列中的 Entity 物件代表偵測到的實體，其中含有實體名稱與類型等資訊。

gcloud

如需完整的詳細資訊，請參閱 analyze-entities 指令。

如要對 Cloud Storage 的檔案執行實體分析，請使用 gcloud 指令列工具並使用 --content-file 標記標示含有待分析內容的檔案路徑：

gcloud ml language analyze-entities --content-file=gs://YOUR_BUCKET_NAME/YOUR_FILE_NAME

如果要求成功，伺服器會傳回 JSON 格式的回應：

{
  "entities": [
    {
      "name": "October 7",
      "type": "DATE",
      "metadata": {
        "month": "10",
        "day": "7"
      },
      "mentions": [
        {
          "text": {
            "content": "October 7",
            "beginOffset": -1
          },
          "type": "TYPE_UNKNOWN",
          "probability": 1
        }
      ]
    },
    {
      "name": "1600",
      "type": "NUMBER",
      "metadata": {
        "value": "1600"
      },
      "mentions": [
        {
          "text": {
            "content": "1600",
            "beginOffset": -1
          },
          "type": "TYPE_UNKNOWN",
          "probability": 1
        }
      ]
    },
    {
      "name": "7",
      "type": "NUMBER",
      "metadata": {
        "value": "7"
      },
      "mentions": [
        {
          "text": {
            "content": "7",
            "beginOffset": -1
          },
          "type": "TYPE_UNKNOWN",
          "probability": 1
        }
      ]
    },
    {
      "name": "1600 Pennsylvania Ave NW, Washington, DC",
      "type": "ADDRESS",
      "metadata": {
        "locality": "Washington",
        "narrow_region": "District of Columbia",
        "street_name": "Pennsylvania Avenue Northwest",
        "street_number": "1600",
        "broad_region": "District of Columbia",
        "country": "US"
      },
      "mentions": [
        {
          "text": {
            "content": "1600 Pennsylvania Ave NW, Washington, DC",
            "beginOffset": -1
          },
          "type": "TYPE_UNKNOWN",
          "probability": 1
        }
      ]
    },
    {
      "name": "1600 Pennsylvania Ave NW",
      "type": "LOCATION",
      "metadata": {},
      "mentions": [
        {
          "text": {
            "content": "1600 Pennsylvania Ave NW",
            "beginOffset": -1
          },
          "type": "PROPER",
          "probability": 0.901
        }
      ]
    },
    {
      "name": "President",
      "type": "PERSON",
      "metadata": {},
      "mentions": [
        {
          "text": {
            "content": "President",
            "beginOffset": -1
          },
          "type": "COMMON",
          "probability": 0.941
        }
      ]
    },
    {
      "name": "Trump",
      "type": "PERSON",
      "metadata": {},
      "mentions": [
        {
          "text": {
            "content": "Trump",
            "beginOffset": -1
          },
          "type": "PROPER",
          "probability": 0.948
        }
      ]
    },
    {
      "name": "Washington, DC",
      "type": "LOCATION",
      "metadata": {},
      "mentions": [
        {
          "text": {
            "content": "Washington, DC",
            "beginOffset": -1
          },
          "type": "PROPER",
          "probability": 0.92
        }
      ]
    },
    {
      "name": "White House",
      "type": "LOCATION",
      "metadata": {},
      "mentions": [
        {
          "text": {
            "content": "White House",
            "beginOffset": -1
          },
          "type": "PROPER",
          "probability": 0.785
        }
      ]
    }
  ],
  "languageCode": "en",
  "languageSupported": true
}

entities 陣列中的 Entity 物件代表偵測到的實體，其中含有實體名稱與類型等資訊。

Go

如要瞭解如何安裝及使用 Natural Language 的用戶端程式庫，請參閱Natural Language 用戶端程式庫。詳情請參閱 Natural Language Go API 參考說明文件。

如要向 Natural Language 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」。


func analyzeEntitiesFromGCS(ctx context.Context, gcsURI string) (*languagepb.AnalyzeEntitiesResponse, error) {
	return client.AnalyzeEntities(ctx, &languagepb.AnalyzeEntitiesRequest{
		Document: &languagepb.Document{
			Source: &languagepb.Document_GcsContentUri{
				GcsContentUri: gcsURI,
			},
			Type: languagepb.Document_PLAIN_TEXT,
		},
		EncodingType: languagepb.EncodingType_UTF8,
	})
}

Java

如要瞭解如何安裝及使用 Natural Language 的用戶端程式庫，請參閱Natural Language 用戶端程式庫。詳情請參閱 Natural Language Java API 參考說明文件。

如要向 Natural Language 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」。

// Instantiate the Language client com.google.cloud.language.v2.LanguageServiceClient
try (LanguageServiceClient language = LanguageServiceClient.create()) {
  // Set the GCS Content URI path to the file to be analyzed
  Document doc =
      Document.newBuilder().setGcsContentUri(gcsUri).setType(Type.PLAIN_TEXT).build();
  AnalyzeEntitiesRequest request =
      AnalyzeEntitiesRequest.newBuilder()
          .setDocument(doc)
          .setEncodingType(EncodingType.UTF16)
          .build();

  AnalyzeEntitiesResponse response = language.analyzeEntities(request);

  // Print the response
  for (Entity entity : response.getEntitiesList()) {
    System.out.printf("Entity: %s\n", entity.getName());
    System.out.println("Metadata: ");
    for (Map.Entry<String, String> entry : entity.getMetadataMap().entrySet()) {
      System.out.printf("%s : %s", entry.getKey(), entry.getValue());
    }
    for (EntityMention mention : entity.getMentionsList()) {
      System.out.printf("Begin offset: %d\n", mention.getText().getBeginOffset());
      System.out.printf("Content: %s\n", mention.getText().getContent());
      System.out.printf("Type: %s\n\n", mention.getType());
      System.out.printf("Probability: %s\n\n", mention.getProbability());
    }
  }
}

Node.js

如要瞭解如何安裝及使用 Natural Language 的用戶端程式庫，請參閱Natural Language 用戶端程式庫。詳情請參閱 Natural Language Node.js API 參考說明文件。

如要向 Natural Language 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」。

// Imports the Google Cloud client library
const language = require('@google-cloud/language').v2;

// Creates a client
const client = new language.LanguageServiceClient();

/**
 * TODO(developer): Uncomment the following lines to run this code
 */
// const bucketName = 'Your bucket name, e.g. my-bucket';
// const fileName = 'Your file name, e.g. my-file.txt';

// Prepares a document, representing a text file in Cloud Storage
const document = {
  gcsContentUri: `gs://${bucketName}/${fileName}`,
  type: 'PLAIN_TEXT',
};

// Detects entities in the document
const [result] = await client.analyzeEntities({document});
const entities = result.entities;

console.log('Entities:');
entities.forEach(entity => {
  console.log(entity.name);
  console.log(` - Type: ${entity.type}`);
  if (entity.metadata) {
    console.log(` - Metadata: ${entity.metadata}`);
  }
});

Python

如要瞭解如何安裝及使用 Natural Language 的用戶端程式庫，請參閱Natural Language 用戶端程式庫。詳情請參閱 Natural Language Python API 參考說明文件。

如要向 Natural Language 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.cloud import language_v2


def sample_analyze_entities(
    gcs_content_uri: str = "gs://cloud-samples-data/language/entity.txt",
) -> None:
    """
    Analyzes Entities in text file stored in Cloud Storage.

    Args:
      gcs_content_uri: Google Cloud Storage URI where the file content is located.
        e.g. gs://[Your Bucket]/[Path to File]
    """

    client = language_v2.LanguageServiceClient()

    # Available types: PLAIN_TEXT, HTML
    document_type_in_plain_text = language_v2.Document.Type.PLAIN_TEXT

    # Optional. If not specified, the language is automatically detected.
    # For list of supported languages:
    # https://cloud.google.com/natural-language/docs/languages
    language_code = "en"
    document = {
        "gcs_content_uri": gcs_content_uri,
        "type_": document_type_in_plain_text,
        "language_code": language_code,
    }

    # Available values: NONE, UTF8, UTF16, UTF32.
    # See https://cloud.google.com/natural-language/docs/reference/rest/v2/EncodingType.
    encoding_type = language_v2.EncodingType.UTF8

    response = client.analyze_entities(
        request={"document": document, "encoding_type": encoding_type}
    )

    for entity in response.entities:
        print(f"Representative name for the entity: {entity.name}")

        # Get entity type, e.g. PERSON, LOCATION, ADDRESS, NUMBER, et al.
        # See https://cloud.google.com/natural-language/docs/reference/rest/v2/Entity#type.
        print(f"Entity type: {language_v2.Entity.Type(entity.type_).name}")

        # Loop over the metadata associated with entity.
        # Some entity types may have additional metadata, e.g. ADDRESS entities
        # may have metadata for the address street_name, postal_code, et al.
        for metadata_name, metadata_value in entity.metadata.items():
            print(f"{metadata_name}: {metadata_value}")

        # Loop over the mentions of this entity in the input document.
        # The API currently supports proper noun mentions.
        for mention in entity.mentions:
            print(f"Mention text: {mention.text.content}")

            # Get the mention type, e.g. PROPER for proper noun
            print(
                "Mention type:" f" {language_v2.EntityMention.Type(mention.type_).name}"
            )

            # Get the probability score associated with the first mention of the entity in the (0, 1.0] range.
            print(f"Probability score: {mention.probability}")

    # Get the language of the text, which will be the same as
    # the language specified in the request or, if not specified,
    # the automatically-detected language.
    print(f"Language of the text: {response.language_code}")

其他語言

C#：請按照用戶端程式庫頁面的 C# 設定說明操作，然後前往 .NET 適用的 Natural Language 參考說明文件。

PHP：請按照用戶端程式庫頁面的 PHP 設定說明操作，然後前往 PHP 適用的 Natural Language 參考文件。

Ruby：請按照用戶端程式庫頁面的 Ruby 設定說明操作，然後前往 Ruby 適用的 Natural Language 參考說明文件。

分析實體 透過集合功能整理內容 你可以依據偏好儲存及分類內容。

分析字串中的實體

通訊協定

gcloud

Go

Java

Node.js

Python

其他語言

分析 Cloud Storage 內容中的實體

通訊協定

gcloud

Go

Java

Node.js

Python

其他語言

分析實體