分析文档

注意：自定义模型的最长使用期限为 18 个月。该时间期限过后，您必须创建并训练新模型，才能继续分析文档。

创建（训练）模型后，您可以请求通过该模型进行预测。向模型提交文档并要求模型根据其目标（分类、实体提取或情感分析）分析文档时，系统就会开始进行预测。

AutoML Natural Language 支持在线预测（您提交单个文档后，模型会同步返回分析结果）和批量预测（您提交一批文档后，模型会异步分析文档）。

在线预测

如需使用 AutoML Natural Language 界面进行预测，请执行以下操作：

1. 点击左侧导航栏中的灯泡图标以显示可用的模型。

   如需查看其他项目的模型，请从标题栏右上角的下拉列表中选择该项目。

2. 点击要用于分析文档的模型所对应的行。

3. 点击标题栏正下方的测试和使用标签页。

4. 在文本框中输入要分析的文本，或单击选择 Cloud Storage 上的文件，然后输入 PDF 或 TIFF 文件的 Cloud Storage 路径。

5. 点击预测。

代码示例

分类

REST

在使用任何请求数据之前，请先进行以下替换：

• project-id：您的项目 ID
• location-id：资源的位置，全球位置为 us-central1，欧盟位置为 eu
• model-id：您的模型 ID

HTTP 方法和网址：

POST https://automl.googleapis.com/v1/projects/project-id/locations/location-id/models/model-id:predict

请求 JSON 正文：

{
  "payload" : {
    "textSnippet": {
      "content": "Google, headquartered in Mountain View, unveiled the new Android phone at the Consumer Electronic Show.  Sundar Pichai said in his keynote that users love their new Android phones.",
        "mime_type": "text/plain"
      },
  }
}

如需发送您的请求，请展开以下选项之一：

curl（Linux、macOS 或 Cloud Shell）

注意：以下命令假定您已使用您的用户账号通过运行 gcloud init 或 gcloud auth login 登录 gcloud CLI，或者使用了 Cloud Shell，这会使您自动登录 gcloud CLI。您可以运行 gcloud auth list 来检查当前活跃的账号。

将请求正文保存在名为 request.json 的文件中，然后执行以下命令：

curl -X POST \
     -H "Authorization: Bearer $(gcloud auth print-access-token)" \
     -H "x-goog-user-project: project-id" \
     -H "Content-Type: application/json; charset=utf-8" \
     -d @request.json \
     "https://automl.googleapis.com/v1/projects/project-id/locations/location-id/models/model-id:predict"

PowerShell (Windows)

注意：以下命令假定您已使用您的用户账号通过运行 gcloud init 或 gcloud auth login 登录 gcloud CLI。您可以运行 gcloud auth list 来检查当前活跃的账号。

将请求正文保存在名为 request.json 的文件中，然后执行以下命令：

$cred = gcloud auth print-access-token
$headers = @{ "Authorization" = "Bearer $cred"; "x-goog-user-project" = "project-id" }

Invoke-WebRequest `
    -Method POST `
    -Headers $headers `
    -ContentType: "application/json; charset=utf-8" `
    -InFile request.json `
    -Uri "https://automl.googleapis.com/v1/projects/project-id/locations/location-id/models/model-id:predict" | Select-Object -Expand Content

您应该收到类似以下内容的 JSON 响应：

{
  "payload": [
    {
      "displayName": "Technology",
      "classification": {
        "score": 0.8989502
      }
    },
    {
      "displayName": "Automobiles",
      "classification": {
        "score": 0.10098731
      }
    }
  ]
}

Python

如需了解如何安装和使用 AutoML Natural Language 的客户端库，请参阅 AutoML Natural Language 客户端库。 如需了解详情，请参阅 AutoML Natural Language Python API 参考文档。

如需向 AutoML Natural Language 进行身份验证，请设置应用默认凭据。如需了解详情，请参阅为本地开发环境设置身份验证。

from google.cloud import automl

# TODO(developer): Uncomment and set the following variables
# project_id = "YOUR_PROJECT_ID"
# model_id = "YOUR_MODEL_ID"
# content = "text to predict"

prediction_client = automl.PredictionServiceClient()

# Get the full path of the model.
model_full_id = automl.AutoMlClient.model_path(project_id, "us-central1", model_id)

# Supported mime_types: 'text/plain', 'text/html'
# https://cloud.google.com/automl/docs/reference/rpc/google.cloud.automl.v1#textsnippet
text_snippet = automl.TextSnippet(content=content, mime_type="text/plain")
payload = automl.ExamplePayload(text_snippet=text_snippet)

response = prediction_client.predict(name=model_full_id, payload=payload)

for annotation_payload in response.payload:
    print(f"Predicted class name: {annotation_payload.display_name}")
    print(f"Predicted class score: {annotation_payload.classification.score}")

Java

如需了解如何安装和使用 AutoML Natural Language 的客户端库，请参阅 AutoML Natural Language 客户端库。 如需了解详情，请参阅 AutoML Natural Language Java API 参考文档。

如需向 AutoML Natural Language 进行身份验证，请设置应用默认凭据。如需了解详情，请参阅为本地开发环境设置身份验证。

import com.google.cloud.automl.v1.AnnotationPayload;
import com.google.cloud.automl.v1.ExamplePayload;
import com.google.cloud.automl.v1.ModelName;
import com.google.cloud.automl.v1.PredictRequest;
import com.google.cloud.automl.v1.PredictResponse;
import com.google.cloud.automl.v1.PredictionServiceClient;
import com.google.cloud.automl.v1.TextSnippet;
import java.io.IOException;

class LanguageTextClassificationPredict {

  public static void main(String[] args) throws IOException {
    // TODO(developer): Replace these variables before running the sample.
    String projectId = "YOUR_PROJECT_ID";
    String modelId = "YOUR_MODEL_ID";
    String content = "text to predict";
    predict(projectId, modelId, content);
  }

  static void predict(String projectId, String modelId, String content) throws IOException {
    // Initialize client that will be used to send requests. This client only needs to be created
    // once, and can be reused for multiple requests. After completing all of your requests, call
    // the "close" method on the client to safely clean up any remaining background resources.
    try (PredictionServiceClient client = PredictionServiceClient.create()) {
      // Get the full path of the model.
      ModelName name = ModelName.of(projectId, "us-central1", modelId);

      // For available mime types, see:
      // https://cloud.google.com/automl/docs/reference/rest/v1/projects.locations.models/predict#textsnippet
      TextSnippet textSnippet =
          TextSnippet.newBuilder()
              .setContent(content)
              .setMimeType("text/plain") // Types: text/plain, text/html
              .build();
      ExamplePayload payload = ExamplePayload.newBuilder().setTextSnippet(textSnippet).build();
      PredictRequest predictRequest =
          PredictRequest.newBuilder().setName(name.toString()).setPayload(payload).build();

      PredictResponse response = client.predict(predictRequest);

      for (AnnotationPayload annotationPayload : response.getPayloadList()) {
        System.out.format("Predicted class name: %s\n", annotationPayload.getDisplayName());
        System.out.format(
            "Predicted sentiment score: %.2f\n\n",
            annotationPayload.getClassification().getScore());
      }
    }
  }
}

Node.js

如需了解如何安装和使用 AutoML Natural Language 的客户端库，请参阅 AutoML Natural Language 客户端库。 如需了解详情，请参阅 AutoML Natural Language Node.js API 参考文档。

如需向 AutoML Natural Language 进行身份验证，请设置应用默认凭据。如需了解详情，请参阅为本地开发环境设置身份验证。

/**
 * TODO(developer): Uncomment these variables before running the sample.
 */
// const projectId = 'YOUR_PROJECT_ID';
// const location = 'us-central1';
// const modelId = 'YOUR_MODEL_ID';
// const content = 'text to predict'

// Imports the Google Cloud AutoML library
const {PredictionServiceClient} = require('@google-cloud/automl').v1;

// Instantiates a client
const client = new PredictionServiceClient();

async function predict() {
  // Construct request
  const request = {
    name: client.modelPath(projectId, location, modelId),
    payload: {
      textSnippet: {
        content: content,
        mimeType: 'text/plain', // Types: 'text/plain', 'text/html'
      },
    },
  };

  const [response] = await client.predict(request);

  for (const annotationPayload of response.payload) {
    console.log(`Predicted class name: ${annotationPayload.displayName}`);
    console.log(
      `Predicted class score: ${annotationPayload.classification.score}`
    );
  }
}

predict();

Go

如需了解如何安装和使用 AutoML Natural Language 的客户端库，请参阅 AutoML Natural Language 客户端库。 如需了解详情，请参阅 AutoML Natural Language Go API 参考文档。

如需向 AutoML Natural Language 进行身份验证，请设置应用默认凭据。如需了解详情，请参阅为本地开发环境设置身份验证。

import (
	"context"
	"fmt"
	"io"

	automl "cloud.google.com/go/automl/apiv1"
	"cloud.google.com/go/automl/apiv1/automlpb"
)

// languageTextClassificationPredict does a prediction for text classification.
func languageTextClassificationPredict(w io.Writer, projectID string, location string, modelID string, content string) error {
	// projectID := "my-project-id"
	// location := "us-central1"
	// modelID := "TCN123456789..."
	// content := "text to classify"

	ctx := context.Background()
	client, err := automl.NewPredictionClient(ctx)
	if err != nil {
		return fmt.Errorf("NewPredictionClient: %w", err)
	}
	defer client.Close()

	req := &automlpb.PredictRequest{
		Name: fmt.Sprintf("projects/%s/locations/%s/models/%s", projectID, location, modelID),
		Payload: &automlpb.ExamplePayload{
			Payload: &automlpb.ExamplePayload_TextSnippet{
				TextSnippet: &automlpb.TextSnippet{
					Content:  content,
					MimeType: "text/plain", // Types: "text/plain", "text/html"
				},
			},
		},
	}

	resp, err := client.Predict(ctx, req)
	if err != nil {
		return fmt.Errorf("Predict: %w", err)
	}

	for _, payload := range resp.GetPayload() {
		fmt.Fprintf(w, "Predicted class name: %v\n", payload.GetDisplayName())
		fmt.Fprintf(w, "Predicted class score: %v\n", payload.GetClassification().GetScore())
	}

	return nil
}

其他语言

C#： 请按照客户端库页面上的 C# 设置说明操作，然后访问 .NET 版 AutoML Natural Language 参考文档。

PHP： 请按照客户端库页面上的 PHP 设置说明操作，然后访问 PHP 版 AutoML Natural Language 参考文档。

Ruby： 请按照客户端库页面上的 Ruby 设置说明操作，然后访问 Ruby 版 AutoML Natural Language 参考文档。

实体提取

REST

在使用任何请求数据之前，请先进行以下替换：

• project-id：您的项目 ID
• location-id：资源的位置，全球位置为 us-central1，欧盟位置为 eu
• model-id：您的模型 ID

HTTP 方法和网址：

POST https://automl.googleapis.com/v1/projects/project-id/locations/location-id/models/model-id:predict

请求 JSON 正文：

{
  "payload" : {
    "textSnippet": {
      "content": "The Wilms tumor-suppressor gene, WT1, plays a key role in urogenital development, and WT1 dysfunction is implicated in both neoplastic and nonneoplastic (glomerulosclerosis) disease. The analysis of diseases linked specifically with WT1 mutations, such as Denys-Drash syndrome (DDS), can provide valuable insight concerning the role of WT1 in development and disease.  We report that heterozygosity for a targeted murine Wt1 allele, Wt1 (tmT396), which truncates ZF3 at codon 396, induces mesangial sclerosis characteristic of DDS in adult heterozygous and chimeric mice. Male genital defects also were evident and there was a single case of Wilms tumor in which the transcript of the nontargeted allele showed an exon 9 skipping event, implying a causal link between Wt1 dysfunction and Wilms tumorigenesis in mice. However, the mutant WT1 (tmT396) protein accounted for only 5% of WT1 in both heterozygous embryonic stem cells and the WT. This has implications regarding the mechanism by which the mutant allele exerts its effect.",
      "mime_type": "text/plain"
      },
   }
}

如需发送您的请求，请展开以下选项之一：

curl（Linux、macOS 或 Cloud Shell）

注意：以下命令假定您已使用您的用户账号通过运行 gcloud init 或 gcloud auth login 登录 gcloud CLI，或者使用了 Cloud Shell，这会使您自动登录 gcloud CLI。您可以运行 gcloud auth list 来检查当前活跃的账号。

将请求正文保存在名为 request.json 的文件中，然后执行以下命令：

curl -X POST \
     -H "Authorization: Bearer $(gcloud auth print-access-token)" \
     -H "x-goog-user-project: project-id" \
     -H "Content-Type: application/json; charset=utf-8" \
     -d @request.json \
     "https://automl.googleapis.com/v1/projects/project-id/locations/location-id/models/model-id:predict"

PowerShell (Windows)

注意：以下命令假定您已使用您的用户账号通过运行 gcloud init 或 gcloud auth login 登录 gcloud CLI。您可以运行 gcloud auth list 来检查当前活跃的账号。

将请求正文保存在名为 request.json 的文件中，然后执行以下命令：

$cred = gcloud auth print-access-token
$headers = @{ "Authorization" = "Bearer $cred"; "x-goog-user-project" = "project-id" }

Invoke-WebRequest `
    -Method POST `
    -Headers $headers `
    -ContentType: "application/json; charset=utf-8" `
    -InFile request.json `
    -Uri "https://automl.googleapis.com/v1/projects/project-id/locations/location-id/models/model-id:predict" | Select-Object -Expand Content

您应该收到类似以下内容的 JSON 响应：

{
  "annotations": [
    {
      "text_extraction": {
        "text_segment": {
          "end_offset": 67,
          "start_offset": 62
        }
      },
      "display_name": "Modifier"
    },
    {
      "text_extraction": {
        "text_segment": {
          "end_offset": 158,
          "start_offset": 141
        }
      },
      "display_name": "SpecificDisease"
    },
    {
      "text_extraction": {
        "text_segment": {
          "end_offset": 330,
          "start_offset": 290
        }
      },
      "display_name": "SpecificDisease"
    },
    {
      "text_extraction": {
        "text_segment": {
          "end_offset": 337,
          "start_offset": 332
        }
      },
      "display_name": "SpecificDisease"
    },
    {
      "text_extraction": {
        "text_segment": {
          "end_offset": 627,
          "start_offset": 610
        }
      },
      "display_name": "Modifier"
    },
    {
      "text_extraction": {
        "text_segment": {
          "end_offset": 754,
          "start_offset": 749
        }
      },
      "display_name": "Modifier"
    },
    {
      "text_extraction": {
        "text_segment": {
          "end_offset": 875,
          "start_offset": 865
        }
      },
      "display_name": "Modifier"
    },
    {
      "text_extraction": {
        "text_segment": {
          "end_offset": 968,
          "start_offset": 951
        }
      },
      "display_name": "Modifier"
    },
    {
      "text_extraction": {
        "text_segment": {
          "end_offset": 1553,
          "start_offset": 1548
        }
      },
      "display_name": "Modifier"
    },
    {
      "text_extraction": {
        "text_segment": {
          "end_offset": 1652,
          "start_offset": 1606
        }
      },
      "display_name": "CompositeMention"
    },
    {
      "text_extraction": {
        "text_segment": {
          "end_offset": 1833,
          "start_offset": 1826
        }
      },
      "display_name": "DiseaseClass"
    },
    {
      "text_extraction": {
        "text_segment": {
          "end_offset": 1860,
          "start_offset": 1843
        }
      },
      "display_name": "SpecificDisease"
    },
    {
      "text_extraction": {
        "text_segment": {
          "end_offset": 1930,
          "start_offset": 1913
        }
      },
      "display_name": "SpecificDisease"
    },
    {
      "text_extraction": {
        "text_segment": {
          "end_offset": 2129,
          "start_offset": 2111
        }
      },
      "display_name": "SpecificDisease"
    },
    {
      "text_extraction": {
        "text_segment": {
          "end_offset": 2188,
          "start_offset": 2160
        }
      },
      "display_name": "SpecificDisease"
    },
    {
      "text_extraction": {
        "text_segment": {
          "end_offset": 2260,
          "start_offset": 2243
        }
      },
      "display_name": "Modifier"
    },
    {
      "text_extraction": {
        "text_segment": {
          "end_offset": 2356,
          "start_offset": 2339
        }
      },
      "display_name": "Modifier"
    }
  ],
}

Python

如需了解如何安装和使用 AutoML Natural Language 的客户端库，请参阅 AutoML Natural Language 客户端库。 如需了解详情，请参阅 AutoML Natural Language Python API 参考文档。

如需向 AutoML Natural Language 进行身份验证，请设置应用默认凭据。如需了解详情，请参阅为本地开发环境设置身份验证。

from google.cloud import automl

# TODO(developer): Uncomment and set the following variables
# project_id = "YOUR_PROJECT_ID"
# model_id = "YOUR_MODEL_ID"
# content = "text to predict"

prediction_client = automl.PredictionServiceClient()

# Get the full path of the model.
model_full_id = automl.AutoMlClient.model_path(project_id, "us-central1", model_id)

# Supported mime_types: 'text/plain', 'text/html'
# https://cloud.google.com/automl/docs/reference/rpc/google.cloud.automl.v1#textsnippet
text_snippet = automl.TextSnippet(content=content, mime_type="text/plain")
payload = automl.ExamplePayload(text_snippet=text_snippet)

response = prediction_client.predict(name=model_full_id, payload=payload)

for annotation_payload in response.payload:
    print(f"Text Extract Entity Types: {annotation_payload.display_name}")
    print(f"Text Score: {annotation_payload.text_extraction.score}")
    text_segment = annotation_payload.text_extraction.text_segment
    print(f"Text Extract Entity Content: {text_segment.content}")
    print(f"Text Start Offset: {text_segment.start_offset}")
    print(f"Text End Offset: {text_segment.end_offset}")

Java

如需了解如何安装和使用 AutoML Natural Language 的客户端库，请参阅 AutoML Natural Language 客户端库。 如需了解详情，请参阅 AutoML Natural Language Java API 参考文档。

如需向 AutoML Natural Language 进行身份验证，请设置应用默认凭据。如需了解详情，请参阅为本地开发环境设置身份验证。

import com.google.cloud.automl.v1.AnnotationPayload;
import com.google.cloud.automl.v1.ExamplePayload;
import com.google.cloud.automl.v1.ModelName;
import com.google.cloud.automl.v1.PredictRequest;
import com.google.cloud.automl.v1.PredictResponse;
import com.google.cloud.automl.v1.PredictionServiceClient;
import com.google.cloud.automl.v1.TextSegment;
import com.google.cloud.automl.v1.TextSnippet;
import java.io.IOException;

class LanguageEntityExtractionPredict {

  static void predict() throws IOException {
    // TODO(developer): Replace these variables before running the sample.
    String projectId = "YOUR_PROJECT_ID";
    String modelId = "YOUR_MODEL_ID";
    String content = "text to predict";
    predict(projectId, modelId, content);
  }

  static void predict(String projectId, String modelId, String content) throws IOException {
    // Initialize client that will be used to send requests. This client only needs to be created
    // once, and can be reused for multiple requests. After completing all of your requests, call
    // the "close" method on the client to safely clean up any remaining background resources.
    try (PredictionServiceClient client = PredictionServiceClient.create()) {
      // Get the full path of the model.
      ModelName name = ModelName.of(projectId, "us-central1", modelId);

      // For available mime types, see:
      // https://cloud.google.com/automl/docs/reference/rest/v1/projects.locations.models/predict#textsnippet
      TextSnippet textSnippet =
          TextSnippet.newBuilder()
              .setContent(content)
              .setMimeType("text/plain") // Types: text/plain, text/html
              .build();
      ExamplePayload payload = ExamplePayload.newBuilder().setTextSnippet(textSnippet).build();
      PredictRequest predictRequest =
          PredictRequest.newBuilder().setName(name.toString()).setPayload(payload).build();

      PredictResponse response = client.predict(predictRequest);

      for (AnnotationPayload annotationPayload : response.getPayloadList()) {
        System.out.format("Text Extract Entity Type: %s\n", annotationPayload.getDisplayName());
        System.out.format("Text score: %.2f\n", annotationPayload.getTextExtraction().getScore());
        TextSegment textSegment = annotationPayload.getTextExtraction().getTextSegment();
        System.out.format("Text Extract Entity Content: %s\n", textSegment.getContent());
        System.out.format("Text Start Offset: %s\n", textSegment.getStartOffset());
        System.out.format("Text End Offset: %s\n\n", textSegment.getEndOffset());
      }
    }
  }
}

Node.js

如需了解如何安装和使用 AutoML Natural Language 的客户端库，请参阅 AutoML Natural Language 客户端库。 如需了解详情，请参阅 AutoML Natural Language Node.js API 参考文档。

如需向 AutoML Natural Language 进行身份验证，请设置应用默认凭据。如需了解详情，请参阅为本地开发环境设置身份验证。

/**
 * TODO(developer): Uncomment these variables before running the sample.
 */
// const projectId = 'YOUR_PROJECT_ID';
// const location = 'us-central1';
// const modelId = 'YOUR_MODEL_ID';
// const content = 'text to predict'

// Imports the Google Cloud AutoML library
const {PredictionServiceClient} = require('@google-cloud/automl').v1;

// Instantiates a client
const client = new PredictionServiceClient();

async function predict() {
  // Construct request
  const request = {
    name: client.modelPath(projectId, location, modelId),
    payload: {
      textSnippet: {
        content: content,
        mimeType: 'text/plain', // Types: 'test/plain', 'text/html'
      },
    },
  };

  const [response] = await client.predict(request);

  for (const annotationPayload of response.payload) {
    console.log(
      `Text Extract Entity Types: ${annotationPayload.displayName}`
    );
    console.log(`Text Score: ${annotationPayload.textExtraction.score}`);
    const textSegment = annotationPayload.textExtraction.textSegment;
    console.log(`Text Extract Entity Content: ${textSegment.content}`);
    console.log(`Text Start Offset: ${textSegment.startOffset}`);
    console.log(`Text End Offset: ${textSegment.endOffset}`);
  }
}

predict();

Go

如需了解如何安装和使用 AutoML Natural Language 的客户端库，请参阅 AutoML Natural Language 客户端库。 如需了解详情，请参阅 AutoML Natural Language Go API 参考文档。

如需向 AutoML Natural Language 进行身份验证，请设置应用默认凭据。如需了解详情，请参阅为本地开发环境设置身份验证。

import (
	"context"
	"fmt"
	"io"

	automl "cloud.google.com/go/automl/apiv1"
	"cloud.google.com/go/automl/apiv1/automlpb"
)

// languageEntityExtractionPredict does a prediction for text entity extraction.
func languageEntityExtractionPredict(w io.Writer, projectID string, location string, modelID string, content string) error {
	// projectID := "my-project-id"
	// location := "us-central1"
	// modelID := "TEN123456789..."
	// content := "text to extract entities"

	ctx := context.Background()
	client, err := automl.NewPredictionClient(ctx)
	if err != nil {
		return fmt.Errorf("NewPredictionClient: %w", err)
	}
	defer client.Close()

	req := &automlpb.PredictRequest{
		Name: fmt.Sprintf("projects/%s/locations/%s/models/%s", projectID, location, modelID),
		Payload: &automlpb.ExamplePayload{
			Payload: &automlpb.ExamplePayload_TextSnippet{
				TextSnippet: &automlpb.TextSnippet{
					Content:  content,
					MimeType: "text/plain", // Types: "text/plain", "text/html"
				},
			},
		},
	}

	resp, err := client.Predict(ctx, req)
	if err != nil {
		return fmt.Errorf("Predict: %w", err)
	}

	for _, payload := range resp.GetPayload() {
		fmt.Fprintf(w, "Text extract entity types: %v\n", payload.GetDisplayName())
		fmt.Fprintf(w, "Text score: %v\n", payload.GetTextExtraction().GetScore())
		textSegment := payload.GetTextExtraction().GetTextSegment()
		fmt.Fprintf(w, "Text extract entity content: %v\n", textSegment.GetContent())
		fmt.Fprintf(w, "Text start offset: %v\n", textSegment.GetStartOffset())
		fmt.Fprintf(w, "Text end offset: %v\n", textSegment.GetEndOffset())
	}

	return nil
}

其他语言

C#： 请按照客户端库页面上的 C# 设置说明操作，然后访问 .NET 版 AutoML Natural Language 参考文档。

PHP： 请按照客户端库页面上的 PHP 设置说明操作，然后访问 PHP 版 AutoML Natural Language 参考文档。

Ruby： 请按照客户端库页面上的 Ruby 设置说明操作，然后访问 Ruby 版 AutoML Natural Language 参考文档。

情感分析

REST

在使用任何请求数据之前，请先进行以下替换：

• project-id：您的项目 ID
• location-id：资源的位置，全球位置为 us-central1，欧盟位置为 eu
• model-id：您的模型 ID

HTTP 方法和网址：

POST https://automl.googleapis.com/v1/projects/project-id/locations/location-id/models/model-id:predict

请求 JSON 正文：

{
  "payload" : {
    "textSnippet": {
      "content": "Enjoy your vacation!",
         "mime_type": "text/plain"
       },
  }
}

如需发送您的请求，请展开以下选项之一：

curl（Linux、macOS 或 Cloud Shell）

注意：以下命令假定您已使用您的用户账号通过运行 gcloud init 或 gcloud auth login 登录 gcloud CLI，或者使用了 Cloud Shell，这会使您自动登录 gcloud CLI。您可以运行 gcloud auth list 来检查当前活跃的账号。

将请求正文保存在名为 request.json 的文件中，然后执行以下命令：

curl -X POST \
     -H "Authorization: Bearer $(gcloud auth print-access-token)" \
     -H "x-goog-user-project: project-id" \
     -H "Content-Type: application/json; charset=utf-8" \
     -d @request.json \
     "https://automl.googleapis.com/v1/projects/project-id/locations/location-id/models/model-id:predict"

PowerShell (Windows)

注意：以下命令假定您已使用您的用户账号通过运行 gcloud init 或 gcloud auth login 登录 gcloud CLI。您可以运行 gcloud auth list 来检查当前活跃的账号。

将请求正文保存在名为 request.json 的文件中，然后执行以下命令：

$cred = gcloud auth print-access-token
$headers = @{ "Authorization" = "Bearer $cred"; "x-goog-user-project" = "project-id" }

Invoke-WebRequest `
    -Method POST `
    -Headers $headers `
    -ContentType: "application/json; charset=utf-8" `
    -InFile request.json `
    -Uri "https://automl.googleapis.com/v1/projects/project-id/locations/location-id/models/model-id:predict" | Select-Object -Expand Content

您应该会收到一个成功的状态代码 (2xx) 和一个空响应。

Python

如需了解如何安装和使用 AutoML Natural Language 的客户端库，请参阅 AutoML Natural Language 客户端库。 如需了解详情，请参阅 AutoML Natural Language Python API 参考文档。

如需向 AutoML Natural Language 进行身份验证，请设置应用默认凭据。如需了解详情，请参阅为本地开发环境设置身份验证。

from google.cloud import automl

# TODO(developer): Uncomment and set the following variables
# project_id = "YOUR_PROJECT_ID"
# model_id = "YOUR_MODEL_ID"
# content = "text to predict"

prediction_client = automl.PredictionServiceClient()

# Get the full path of the model.
model_full_id = automl.AutoMlClient.model_path(project_id, "us-central1", model_id)

# Supported mime_types: 'text/plain', 'text/html'
# https://cloud.google.com/automl/docs/reference/rpc/google.cloud.automl.v1#textsnippet
text_snippet = automl.TextSnippet(content=content, mime_type="text/plain")
payload = automl.ExamplePayload(text_snippet=text_snippet)

response = prediction_client.predict(name=model_full_id, payload=payload)

for annotation_payload in response.payload:
    print(f"Predicted class name: {annotation_payload.display_name}")
    print(
        "Predicted sentiment score: {}".format(
            annotation_payload.text_sentiment.sentiment
        )
    )

Java

如需了解如何安装和使用 AutoML Natural Language 的客户端库，请参阅 AutoML Natural Language 客户端库。 如需了解详情，请参阅 AutoML Natural Language Java API 参考文档。

如需向 AutoML Natural Language 进行身份验证，请设置应用默认凭据。如需了解详情，请参阅为本地开发环境设置身份验证。

import com.google.cloud.automl.v1.AnnotationPayload;
import com.google.cloud.automl.v1.ExamplePayload;
import com.google.cloud.automl.v1.ModelName;
import com.google.cloud.automl.v1.PredictRequest;
import com.google.cloud.automl.v1.PredictResponse;
import com.google.cloud.automl.v1.PredictionServiceClient;
import com.google.cloud.automl.v1.TextSnippet;
import java.io.IOException;

class LanguageSentimentAnalysisPredict {

  static void predict() throws IOException {
    // TODO(developer): Replace these variables before running the sample.
    String projectId = "YOUR_PROJECT_ID";
    String modelId = "YOUR_MODEL_ID";
    String content = "text to predict";
    predict(projectId, modelId, content);
  }

  static void predict(String projectId, String modelId, String content) throws IOException {
    // Initialize client that will be used to send requests. This client only needs to be created
    // once, and can be reused for multiple requests. After completing all of your requests, call
    // the "close" method on the client to safely clean up any remaining background resources.
    try (PredictionServiceClient client = PredictionServiceClient.create()) {
      // Get the full path of the model.
      ModelName name = ModelName.of(projectId, "us-central1", modelId);

      // For available mime types, see:
      // https://cloud.google.com/automl/docs/reference/rest/v1/projects.locations.models/predict#textsnippet
      TextSnippet textSnippet =
          TextSnippet.newBuilder()
              .setContent(content)
              .setMimeType("text/plain") // Types: text/plain, text/html
              .build();
      ExamplePayload payload = ExamplePayload.newBuilder().setTextSnippet(textSnippet).build();
      PredictRequest predictRequest =
          PredictRequest.newBuilder().setName(name.toString()).setPayload(payload).build();

      PredictResponse response = client.predict(predictRequest);

      for (AnnotationPayload annotationPayload : response.getPayloadList()) {
        System.out.format("Predicted class name: %s\n", annotationPayload.getDisplayName());
        System.out.format(
            "Predicted sentiment score: %d\n", annotationPayload.getTextSentiment().getSentiment());
      }
    }
  }
}

Node.js

如需了解如何安装和使用 AutoML Natural Language 的客户端库，请参阅 AutoML Natural Language 客户端库。 如需了解详情，请参阅 AutoML Natural Language Node.js API 参考文档。

如需向 AutoML Natural Language 进行身份验证，请设置应用默认凭据。如需了解详情，请参阅为本地开发环境设置身份验证。

/**
 * TODO(developer): Uncomment these variables before running the sample.
 */
// const projectId = 'YOUR_PROJECT_ID';
// const location = 'us-central1';
// const modelId = 'YOUR_MODEL_ID';
// const content = 'text to predict'

// Imports the Google Cloud AutoML library
const {PredictionServiceClient} = require('@google-cloud/automl').v1;

// Instantiates a client
const client = new PredictionServiceClient();

async function predict() {
  // Construct request
  const request = {
    name: client.modelPath(projectId, location, modelId),
    payload: {
      textSnippet: {
        content: content,
        mimeType: 'text/plain', // Types: 'test/plain', 'text/html'
      },
    },
  };

  const [response] = await client.predict(request);

  for (const annotationPayload of response.payload) {
    console.log(`Predicted class name: ${annotationPayload.displayName}`);
    console.log(
      `Predicted sentiment score: ${annotationPayload.textSentiment.sentiment}`
    );
  }
}

predict();

Go

如需了解如何安装和使用 AutoML Natural Language 的客户端库，请参阅 AutoML Natural Language 客户端库。 如需了解详情，请参阅 AutoML Natural Language Go API 参考文档。

如需向 AutoML Natural Language 进行身份验证，请设置应用默认凭据。如需了解详情，请参阅为本地开发环境设置身份验证。

import (
	"context"
	"fmt"
	"io"

	automl "cloud.google.com/go/automl/apiv1"
	"cloud.google.com/go/automl/apiv1/automlpb"
)

// languageSentimentAnalysisPredict does a prediction for text sentiment analysis.
func languageSentimentAnalysisPredict(w io.Writer, projectID string, location string, modelID string, content string) error {
	// projectID := "my-project-id"
	// location := "us-central1"
	// modelID := "TST123456789..."
	// content := "text to analyze sentiment"

	ctx := context.Background()
	client, err := automl.NewPredictionClient(ctx)
	if err != nil {
		return fmt.Errorf("NewPredictionClient: %w", err)
	}
	defer client.Close()

	req := &automlpb.PredictRequest{
		Name: fmt.Sprintf("projects/%s/locations/%s/models/%s", projectID, location, modelID),
		Payload: &automlpb.ExamplePayload{
			Payload: &automlpb.ExamplePayload_TextSnippet{
				TextSnippet: &automlpb.TextSnippet{
					Content:  content,
					MimeType: "text/plain", // Types: "text/plain", "text/html"
				},
			},
		},
	}

	resp, err := client.Predict(ctx, req)
	if err != nil {
		return fmt.Errorf("Predict: %w", err)
	}

	for _, payload := range resp.GetPayload() {
		fmt.Fprintf(w, "Predicted class name: %v\n", payload.GetDisplayName())
		fmt.Fprintf(w, "Predicted sentiment score: %v\n", payload.GetTextSentiment().GetSentiment())
	}

	return nil
}

其他语言

C#： 请按照客户端库页面上的 C# 设置说明操作，然后访问 .NET 版 AutoML Natural Language 参考文档。

PHP： 请按照客户端库页面上的 PHP 设置说明操作，然后访问 PHP 版 AutoML Natural Language 参考文档。

Ruby： 请按照客户端库页面上的 Ruby 设置说明操作，然后访问 Ruby 版 AutoML Natural Language 参考文档。

批量预测

如果您想利用模型对一批文档进行高吞吐量异步预测，则可以使用 batchPredict 方法。批量预测方法要求您指定指向 Cloud Storage 存储分区中位置的输入和输出 URI。

输入 URI 指向 CSV 或 JSONL 文件，该文件用于指定要分析的内容。针对分类和情感分析使用 CSV 文件。针对实体提取使用 JSONL 文件。输出指定 AutoML Natural Language 保存批量预测结果的位置。

对于分类和情感分析，请创建一个只有一列的 CSV 文件，其中列出要分类的输入文件，每行一个文件。CSV 文件和每个输入文件都需要存储在 Cloud Storage 存储桶中。

gs://folder/text1.txt
gs://folder/text2.pdf

对于实体提取，您需要准备一个 JSONL 文件，其中以内嵌方式或文件链接形式（文件存储在 Cloud Storage 存储桶中）包含要分析的所有内容。以下示例显示了 JSONL 文件中包含的内嵌内容。每项内容都必须包含一个唯一 ID。

{ "id": "0", "text_snippet": { "content": "First item content to be analyzed." } }
{ "id": "1", "text_snippet": { "content": "Second item content to be analyzed." } }
...
{ "id": "n", "text_snippet": { "content": "Last item content to be analyzed." } }

以下示例展示了包含输入文件链接的 JSONL 文件，输入文件必须位于 Cloud Storage 存储分区中。

{ "document": { "input_config": { "gcs_source": { "input_uris": [ "gs://folder/document1.pdf" ] } } } }
{ "document": { "input_config": { "gcs_source": { "input_uris": [ "gs://folder/document2.tif" ] } } } }
...

REST

在使用任何请求数据之前，请先进行以下替换：

• project-id：您的项目 ID
• location-id：资源的位置，全球位置为 us-central1，欧盟位置为 eu
• model-id：您的模型 ID

HTTP 方法和网址：

POST https://automl.googleapis.com/v1/projects/project-id/locations/location-id/models/model-id:batchPredict

请求 JSON 正文：

{
  "input_config": { "gcs_source": { "input_uris": [ "csv-file-URI"] } },
  "output_config": { "gcs_destination": { "output_uri_prefix": "dest-dir-URI" } }
 }

如需发送您的请求，请展开以下选项之一：

curl（Linux、macOS 或 Cloud Shell）

注意：以下命令假定您已使用您的用户账号通过运行 gcloud init 或 gcloud auth login 登录 gcloud CLI，或者使用了 Cloud Shell，这会使您自动登录 gcloud CLI。您可以运行 gcloud auth list 来检查当前活跃的账号。

将请求正文保存在名为 request.json 的文件中，然后执行以下命令：

curl -X POST \
     -H "Authorization: Bearer $(gcloud auth print-access-token)" \
     -H "x-goog-user-project: project-id" \
     -H "Content-Type: application/json; charset=utf-8" \
     -d @request.json \
     "https://automl.googleapis.com/v1/projects/project-id/locations/location-id/models/model-id:batchPredict"

PowerShell (Windows)

注意：以下命令假定您已使用您的用户账号通过运行 gcloud init 或 gcloud auth login 登录 gcloud CLI。您可以运行 gcloud auth list 来检查当前活跃的账号。

将请求正文保存在名为 request.json 的文件中，然后执行以下命令：

$cred = gcloud auth print-access-token
$headers = @{ "Authorization" = "Bearer $cred"; "x-goog-user-project" = "project-id" }

Invoke-WebRequest `
    -Method POST `
    -Headers $headers `
    -ContentType: "application/json; charset=utf-8" `
    -InFile request.json `
    -Uri "https://automl.googleapis.com/v1/projects/project-id/locations/location-id/models/model-id:batchPredict" | Select-Object -Expand Content

您应该会看到类似如下所示的输出。可以使用操作 ID 来获取任务的状态。如需示例，请参阅获取操作状态。

{
  "name": "projects/434039606874/locations/us-central1/operations/TCN8195786061721370625",
  "metadata": {
    "@type": "type.googleapis.com/google.cloud.automl.v1beta1.OperationMetadata",
    "createTime": "2019-03-13T15:37:49.972372Z",
    "updateTime": "2019-03-13T15:37:49.972372Z"
  }
}

Python

如需了解如何安装和使用 AutoML Natural Language 的客户端库，请参阅 AutoML Natural Language 客户端库。 如需了解详情，请参阅 AutoML Natural Language Python API 参考文档。

如需向 AutoML Natural Language 进行身份验证，请设置应用默认凭据。如需了解详情，请参阅为本地开发环境设置身份验证。

from google.cloud import automl

# TODO(developer): Uncomment and set the following variables
# project_id = "YOUR_PROJECT_ID"
# model_id = "YOUR_MODEL_ID"
# input_uri = "gs://YOUR_BUCKET_ID/path/to/your/input/csv_or_jsonl"
# output_uri = "gs://YOUR_BUCKET_ID/path/to/save/results/"

prediction_client = automl.PredictionServiceClient()

# Get the full path of the model.
model_full_id = f"projects/{project_id}/locations/us-central1/models/{model_id}"

gcs_source = automl.GcsSource(input_uris=[input_uri])

input_config = automl.BatchPredictInputConfig(gcs_source=gcs_source)
gcs_destination = automl.GcsDestination(output_uri_prefix=output_uri)
output_config = automl.BatchPredictOutputConfig(gcs_destination=gcs_destination)

response = prediction_client.batch_predict(
    name=model_full_id, input_config=input_config, output_config=output_config
)

print("Waiting for operation to complete...")
print(
    f"Batch Prediction results saved to Cloud Storage bucket. {response.result()}"
)

Java

如需了解如何安装和使用 AutoML Natural Language 的客户端库，请参阅 AutoML Natural Language 客户端库。 如需了解详情，请参阅 AutoML Natural Language Java API 参考文档。

如需向 AutoML Natural Language 进行身份验证，请设置应用默认凭据。如需了解详情，请参阅为本地开发环境设置身份验证。

import com.google.api.gax.longrunning.OperationFuture;
import com.google.cloud.automl.v1.BatchPredictInputConfig;
import com.google.cloud.automl.v1.BatchPredictOutputConfig;
import com.google.cloud.automl.v1.BatchPredictRequest;
import com.google.cloud.automl.v1.BatchPredictResult;
import com.google.cloud.automl.v1.GcsDestination;
import com.google.cloud.automl.v1.GcsSource;
import com.google.cloud.automl.v1.ModelName;
import com.google.cloud.automl.v1.OperationMetadata;
import com.google.cloud.automl.v1.PredictionServiceClient;
import java.io.IOException;
import java.util.concurrent.ExecutionException;

abstract class BatchPredict {

  static void batchPredict() throws IOException, ExecutionException, InterruptedException {
    // TODO(developer): Replace these variables before running the sample.
    String projectId = "YOUR_PROJECT_ID";
    String modelId = "YOUR_MODEL_ID";
    String inputUri = "gs://YOUR_BUCKET_ID/path_to_your_input_csv_or_jsonl";
    String outputUri = "gs://YOUR_BUCKET_ID/path_to_save_results/";
    batchPredict(projectId, modelId, inputUri, outputUri);
  }

  static void batchPredict(String projectId, String modelId, String inputUri, String outputUri)
      throws IOException, ExecutionException, InterruptedException {
    // Initialize client that will be used to send requests. This client only needs to be created
    // once, and can be reused for multiple requests. After completing all of your requests, call
    // the "close" method on the client to safely clean up any remaining background resources.
    try (PredictionServiceClient client = PredictionServiceClient.create()) {
      // Get the full path of the model.
      ModelName name = ModelName.of(projectId, "us-central1", modelId);
      GcsSource gcsSource = GcsSource.newBuilder().addInputUris(inputUri).build();
      BatchPredictInputConfig inputConfig =
          BatchPredictInputConfig.newBuilder().setGcsSource(gcsSource).build();
      GcsDestination gcsDestination =
          GcsDestination.newBuilder().setOutputUriPrefix(outputUri).build();
      BatchPredictOutputConfig outputConfig =
          BatchPredictOutputConfig.newBuilder().setGcsDestination(gcsDestination).build();
      BatchPredictRequest request =
          BatchPredictRequest.newBuilder()
              .setName(name.toString())
              .setInputConfig(inputConfig)
              .setOutputConfig(outputConfig)
              .build();

      OperationFuture<BatchPredictResult, OperationMetadata> future =
          client.batchPredictAsync(request);

      System.out.println("Waiting for operation to complete...");
      future.get();
      System.out.println("Batch Prediction results saved to specified Cloud Storage bucket.");
    }
  }
}

Node.js

如需了解如何安装和使用 AutoML Natural Language 的客户端库，请参阅 AutoML Natural Language 客户端库。 如需了解详情，请参阅 AutoML Natural Language Node.js API 参考文档。

如需向 AutoML Natural Language 进行身份验证，请设置应用默认凭据。如需了解详情，请参阅为本地开发环境设置身份验证。

/**
 * TODO(developer): Uncomment these variables before running the sample.
 */
// const projectId = 'YOUR_PROJECT_ID';
// const location = 'us-central1';
// const modelId = 'YOUR_MODEL_ID';
// const inputUri = 'gs://YOUR_BUCKET_ID/path_to_your_input_csv_or_jsonl';
// const outputUri = 'gs://YOUR_BUCKET_ID/path_to_save_results/';

// Imports the Google Cloud AutoML library
const {PredictionServiceClient} = require('@google-cloud/automl').v1;

// Instantiates a client
const client = new PredictionServiceClient();

async function batchPredict() {
  // Construct request
  const request = {
    name: client.modelPath(projectId, location, modelId),
    inputConfig: {
      gcsSource: {
        inputUris: [inputUri],
      },
    },
    outputConfig: {
      gcsDestination: {
        outputUriPrefix: outputUri,
      },
    },
  };

  const [operation] = await client.batchPredict(request);

  console.log('Waiting for operation to complete...');
  // Wait for operation to complete.
  const [response] = await operation.promise();
  console.log(
    `Batch Prediction results saved to Cloud Storage bucket. ${response}`
  );
}

batchPredict();

Go

如需了解如何安装和使用 AutoML Natural Language 的客户端库，请参阅 AutoML Natural Language 客户端库。 如需了解详情，请参阅 AutoML Natural Language Go API 参考文档。

如需向 AutoML Natural Language 进行身份验证，请设置应用默认凭据。如需了解详情，请参阅为本地开发环境设置身份验证。

import (
	"context"
	"fmt"
	"io"

	automl "cloud.google.com/go/automl/apiv1"
	"cloud.google.com/go/automl/apiv1/automlpb"
)

// batchPredict does a batch prediction.
func batchPredict(w io.Writer, projectID string, location string, modelID string, inputURI string, outputURI string) error {
	// projectID := "my-project-id"
	// location := "us-central1"
	// modelID := "ICN123456789..."
	// inputURI := "gs://BUCKET_ID/path_to_your_input_csv_or_jsonl"
	// outputURI := "gs://BUCKET_ID/path_to_save_results/"

	ctx := context.Background()
	client, err := automl.NewPredictionClient(ctx)
	if err != nil {
		return fmt.Errorf("NewPredictionClient: %w", err)
	}
	defer client.Close()

	req := &automlpb.BatchPredictRequest{
		Name: fmt.Sprintf("projects/%s/locations/%s/models/%s", projectID, location, modelID),
		InputConfig: &automlpb.BatchPredictInputConfig{
			Source: &automlpb.BatchPredictInputConfig_GcsSource{
				GcsSource: &automlpb.GcsSource{
					InputUris: []string{inputURI},
				},
			},
		},
		OutputConfig: &automlpb.BatchPredictOutputConfig{
			Destination: &automlpb.BatchPredictOutputConfig_GcsDestination{
				GcsDestination: &automlpb.GcsDestination{
					OutputUriPrefix: outputURI,
				},
			},
		},
		Params: map[string]string{
			"score_threshold": "0.8", // [0.0-1.0] Only produce results higher than this value
		},
	}

	op, err := client.BatchPredict(ctx, req)
	if err != nil {
		return fmt.Errorf("BatchPredict: %w", err)
	}
	fmt.Fprintf(w, "Processing operation name: %q\n", op.Name())

	resp, err := op.Wait(ctx)
	if err != nil {
		return fmt.Errorf("Wait: %w", err)
	}

	fmt.Fprintf(w, "Batch Prediction results saved to Cloud Storage bucket.\n")
	fmt.Fprintf(w, "%v", resp)

	return nil
}

其他语言

C#： 请按照客户端库页面上的 C# 设置说明操作，然后访问 .NET 版 AutoML Natural Language 参考文档。

PHP： 请按照客户端库页面上的 PHP 设置说明操作，然后访问 PHP 版 AutoML Natural Language 参考文档。

Ruby： 请按照客户端库页面上的 Ruby 设置说明操作，然后访问 Ruby 版 AutoML Natural Language 参考文档。