Azure AI 文档智能 Java SDK

Azure Document Intelligence (Form Recognizer) Java SDK

使用 Azure AI Document Intelligence Java SDK 构建文档分析应用程序。

安装

<dependency>
    <groupId>com.azure</groupId>
    <artifactId>azure-ai-formrecognizer</artifactId>
    <version>4.2.0-beta.1</version>
</dependency>

客户端创建

DocumentAnalysisClient

import com.azure.ai.formrecognizer.documentanalysis.DocumentAnalysisClient;
import com.azure.ai.formrecognizer.documentanalysis.DocumentAnalysisClientBuilder;
import com.azure.core.credential.AzureKeyCredential;
DocumentAnalysisClient client = new DocumentAnalysisClientBuilder()
    .credential(new AzureKeyCredential("{key}"))
    .endpoint("{endpoint}")
    .buildClient();

DocumentModelAdministrationClient

import com.azure.ai.formrecognizer.documentanalysis.administration.DocumentModelAdministrationClient;
import com.azure.ai.formrecognizer.documentanalysis.administration.DocumentModelAdministrationClientBuilder;
DocumentModelAdministrationClient adminClient = new DocumentModelAdministrationClientBuilder()
    .credential(new AzureKeyCredential("{key}"))
    .endpoint("{endpoint}")
    .buildClient();

使用 DefaultAzureCredential

import com.azure.identity.DefaultAzureCredentialBuilder;
DocumentAnalysisClient client = new DocumentAnalysisClientBuilder()
    .endpoint("{endpoint}")
    .credential(new DefaultAzureCredentialBuilder().build())
    .buildClient();

预置模型

| 模型 ID | 用途 |
|----------|---------|
| prebuilt-layout | 提取文本、表格、选择标记 |
| prebuilt-document | 包含键值对的通用文档 |
| prebuilt-receipt | 收据数据提取 |
| prebuilt-invoice | 发票字段提取 |
| prebuilt-businessCard | 名片解析 |
| prebuilt-idDocument | 身份证件（护照、驾照） |
| prebuilt-tax.us.w2 | 美国 W2 税单 |

核心模式

提取布局 (Extract Layout)

import com.azure.ai.formrecognizer.documentanalysis.models.*;
import com.azure.core.util.BinaryData;
import com.azure.core.util.polling.SyncPoller;
import java.io.File;
File document = new File("document.pdf");
BinaryData documentData = BinaryData.fromFile(document.toPath());
SyncPoller<OperationResult, AnalyzeResult> poller = 
    client.beginAnalyzeDocument("prebuilt-layout", documentData);
AnalyzeResult result = poller.getFinalResult();
// 处理页面
for (DocumentPage page : result.getPages()) {
    System.out.printf("Page %d: %.2f x %.2f %s%n",
        page.getPageNumber(),
        page.getWidth(),
        page.getHeight(),
        page.getUnit());
    
    // 行
    for (DocumentLine line : page.getLines()) {
        System.out.println("Line: " + line.getContent());
    }
    
    // 选择标记（复选框）
    for (DocumentSelectionMark mark : page.getSelectionMarks()) {
        System.out.printf("Checkbox: %s (confidence: %.2f)%n",
            mark.getSelectionMarkState(),
            mark.getConfidence());
    }
}
// 表格
for (DocumentTable table : result.getTables()) {
    System.out.printf("Table: %d rows x %d columns%n",
        table.getRowCount(),
        table.getColumnCount());
    
    for (DocumentTableCell cell : table.getCells()) {

### 从 URL 分析

SyncPoller<OperationResult, AnalyzeResult> poller =
client.beginAnalyzeDocumentFromUrl("prebuilt-invoice", documentUrl);

AnalyzeResult result = poller.getFinalResult();

### 分析收据

AnalyzeResult result = poller.getFinalResult();

for (AnalyzedDocument doc : result.getDocuments()) {
Map<String, DocumentField> fields = doc.getFields();

DocumentField merchantName = fields.get("MerchantName");
if (merchantName != null && merchantName.getType() == DocumentFieldType.STRING) {
System.out.printf("Merchant: %s (confidence: %.2f)%n",
merchantName.getValueAsString(),
merchantName.getConfidence());
}

DocumentField transactionDate = fields.get("TransactionDate");
if (transactionDate != null && transactionDate.getType() == DocumentFieldType.DATE) {
System.out.printf("Date: %s%n", transactionDate.getValueAsDate());
}

DocumentField items = fields.get("Items");
if (items != null && items.getType() == DocumentFieldType.LIST) {
for (DocumentField item : items.getValueAsList()) {
Map<String, DocumentField> itemFields = item.getValueAsMap();
System.out.printf("Item: %s, Price: %.2f%n",
itemFields.get("Name").getValueAsString(),
itemFields.get("Price").getValueAsDouble());
}
}
}

### 通用文档分析

AnalyzeResult result = poller.getFinalResult();

// 键值对
for (DocumentKeyValuePair kvp : result.getKeyValuePairs()) {
System.out.printf("Key: %s => Value: %s%n",
kvp.getKey().getContent(),
kvp.getValue() != null ? kvp.getValue().getContent() : "null");
}

## 自定义模型

构建自定义模型

String blobContainerUrl = "{SAS_URL_of_training_data}";
String prefix = "training-docs/";

SyncPoller<OperationResult, DocumentModelDetails> poller = adminClient.beginBuildDocumentModel(
blobContainerUrl,
DocumentModelBuildMode.TEMPLATE,
prefix,
new BuildDocumentModelOptions()
.setModelId("my-custom-model")
.setDescription("Custom invoice model"),
Context.NONE);

DocumentModelDetails model = poller.getFinalResult();

System.out.println("Model ID: " + model.getModelId());
System.out.println("Created: " + model.getCreatedOn());

model.getDocumentTypes().forEach((docType, details) -> {
System.out.println("Document type: " + docType);
details.getFieldSchema().forEach((field, schema) -> {
System.out.printf(" Field: %s (%s)%n", field, schema.getType());
});
});

### 使用自定义模型分析

AnalyzeResult result = poller.getFinalResult();

for (AnalyzedDocument doc : result.getDocuments()) {
System.out.printf("Document type: %s (confidence: %.2f)%n",
doc.getDocType(),
doc.getConfidence());

doc.getFields().forEach((name, field) -> {
System.out.printf("Field '%s': %s (confidence: %.2f)%n",
name,
field.getContent(),
field.getConfidence());
});
}

### 组合模型 (Compose Models)

SyncPoller<OperationResult, DocumentModelDetails> poller =
adminClient.beginComposeDocumentModel(
modelIds,
new ComposeDocumentModelOptions()
.setModelId("composed-model")
.setDescription("Composed from multiple models"));

DocumentModelDetails composedModel = poller.getFinalResult();

### 管理模型 (Manage Models)

// 获取模型详情
DocumentModelDetails model = adminClient.getDocumentModel("model-id");

// 删除模型
adminClient.deleteDocumentModel("model-id");

// 检查资源限制
ResourceDetails resources = adminClient.getResourceDetails();
System.out.printf("Models: %d / %d%n",
resources.getCustomDocumentModelCount(),
resources.getCustomDocumentModelLimit());

## 文档分类 (Document Classification)

构建分类器 (Build Classifier)

SyncPoller<OperationResult, DocumentClassifierDetails> poller =
adminClient.beginBuildDocumentClassifier(docTypes,
new BuildDocumentClassifierOptions().setClassifierId("my-classifier"));

DocumentClassifierDetails classifier = poller.getFinalResult();

### 分类文档 (Classify Document)

AnalyzeResult result = poller.getFinalResult();

for (AnalyzedDocument doc : result.getDocuments()) {
System.out.printf("Classified as: %s (confidence: %.2f)%n",
doc.getDocType(),
doc.getConfidence());
}

## 错误处理 (Error Handling)

try {
client.beginAnalyzeDocumentFromUrl("prebuilt-receipt", "invalid-url");
} catch (HttpResponseException e) {
System.out.println("Status: " + e.getResponse().getStatusCode());
System.out.println("Error: " + e.getMessage());
}

## 环境变量 (Environment Variables)

触发词 (Trigger Phrases)

• "document intelligence Java"

• "form recognizer SDK"

• "extract text from PDF"

• "OCR document Java"

• "analyze invoice receipt"

• "custom document model"

• "document classification"

使用场景 (When to Use)

局限性 (Limitations)

• 仅在任务与上述描述的范围明确匹配时使用此技能。

• 不要将输出视为针对特定环境的验证、测试或专家评审的替代方案。

• 如果所需输入不明确，请停止并请求澄清。