> For the complete documentation index, see [llms.txt](https://docs.docbits.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.docbits.com/chinese/guan-li-yu-she-zhi/settings/global-settings/document-types/model-training/import-data-model-training.md).

# 导入用于模型训练的示例文档

使用此页面为文档类型添加示例 PDF，然后训练或测试其分类模型。你需要有权访问 **Settings** 和 **Document Types**。有关训练功能的用途，请参阅[用途：模型训练](/chinese/guan-li-yu-she-zhi/settings/global-settings/document-types/model-training/purpose-and-use-model-training.md)。

## 打开文档类型

1. 前往 **Settings → Document Types**。
2. 找到要训练的文档类型，然后在其所在行中选择 **Model Training**。以下示例使用 **Invoice**。

<figure><img src="https://1870485400-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FlPczlNw8zzYNLfjfispX%2Fuploads%2Fgit-blob-3e76059dd61059889727d6498fec408edb41d216%2Fdbdc163-document-types-en.png?alt=media" alt="Document Types 页面上的 Invoice 行，其中包含 Model Training 链接"><figcaption><p>从所选文档类型打开 Model Training。</p></figcaption></figure>

此卡片上的其他控件用途不同：**Activate** 用于启用文档类型，**Extraction** 用于切换其提取模式，齿轮图标用于打开其设置，其余链接用于打开其他配置区域。仅打开 Model Training 时，无需更改这些控件。

**Train Model** 页面会显示示例数量以及已上传训练文档的列表。在示例组织中，该列表为空；你的组织中显示的文档和数量可能不同。

<figure><img src="https://1870485400-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FlPczlNw8zzYNLfjfispX%2Fuploads%2Fgit-blob-038fd96223074c98c69f58bbbec559cb5022121e%2Fdbdc163-model-training-en.png?alt=media" alt="Invoice Train Model 页面，显示示例数量、Import、Train model、Test classification 以及文档列表"><figcaption><p>训练列表右上方有三个操作。</p></figcaption></figure>

## 导入示例 PDF

1. 选择 **Import**。
2. 选择与示例文档相符的 **Amount & Date Format**。例如，若使用美国的数字和日期格式，请选择 **United States**。此选项用于告知 DocBits 如何解析上传文档中的值；它不会更改应用语言。
3. 将 PDF 文件拖入对话框，或使用 **Upload** 选择文件。当前的示例文档导入器只接受 **PDF 文件**，其他文件类型会被拒绝。选择文件后即开始上传。
4. 关闭对话框，并检查文档是否出现在训练列表中。如果 DocBits 报告上传错误或提示文档已存在，请修正文件，或选择其他示例后再继续。

<figure><img src="https://1870485400-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FlPczlNw8zzYNLfjfispX%2Fuploads%2Fgit-blob-d5ee548ef6723d2dccbd8b63f600160027c6d0f3%2Fdbdc163-import-dialog-en.png?alt=media" alt="Import 对话框，包含 Amount and Date Format 选择器、拖放区域和 Upload 字段"><figcaption><p>选择格式后，再选择示例 PDF。</p></figcaption></figure>

<figure><img src="https://1870485400-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FlPczlNw8zzYNLfjfispX%2Fuploads%2Fgit-blob-fde3e22be6c8fa838060d39e7b5221580c6adb64%2Fdbdc163-format-menu-en.png?alt=media" alt="Amount and Date Format 菜单，包含国家和地区选项，如 United States 和 Great Britain"><figcaption><p>选择文档中使用的格式，而不是你偏好的界面语言。</p></figcaption></figure>

有关导入示例的操作，请参阅[管理训练数据](/chinese/guan-li-yu-she-zhi/settings/global-settings/document-types/model-training/manage-training-data.md)。

## 训练和检查模型

所需的示例 PDF 出现在列表中后，选择 **Train model**。DocBits 可能会在后台处理训练；请等待完成提示后，再将新模型视为已就绪。此页面显示的示例数量和任何计划限制均适用于你的组织。

如需检查分类结果，请选择 **Test classification**，然后在对话框中上传另一个示例文件。处理完成后，DocBits 会显示预测的文档类型是否与此页面对应的类型一致，并提供分类详情。下方显示的是尚未提交文件的空测试对话框。

<figure><img src="https://1870485400-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FlPczlNw8zzYNLfjfispX%2Fuploads%2Fgit-blob-93afa6e8c17a954be40c5d3bb36e8cb579afc1c7%2Fdbdc163-test-dialog-en.png?alt=media" alt="Test classification 对话框，包含拖放区域和 Upload 字段"><figcaption><p>使用 Test classification，通过另一份文档检查模型。</p></figcaption></figure>

有关如何解读结果，请参阅[测试模型](/chinese/guan-li-yu-she-zhi/settings/global-settings/document-types/model-training/testing-the-model.md)。如果结果不理想，请先查看[训练数据](/chinese/guan-li-yu-she-zhi/settings/global-settings/document-types/model-training/manage-training-data.md)和[故障排除指南](/chinese/guan-li-yu-she-zhi/settings/global-settings/document-types/model-training/troubleshooting.md)，再添加更多示例。


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.docbits.com/chinese/guan-li-yu-she-zhi/settings/global-settings/document-types/model-training/import-data-model-training.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.