> 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/analytics-dashboard/touchless-intelligence/touchless-change-proposals.md).

# 变更提案和报告

推荐内容可能附带一个**变更提案**，即一项有助于改进的设置变更。管理员分四个步骤处理：

1. **预览**：显示变更内容（当前值 → 提议值）以及 DocBits 的预期结果。不会保存任何内容。只有查看预览后，才能**应用**。
2. **应用**：准确保存预览中的变更。系统会记录此操作。
3. **衡量**：DocBits 会比较同一文档类型在**变更前后**相同时长期间内的无接触率。每个期间至少需要 **20 份文档**，否则结果会显示为\_无法衡量\_。
4. **撤销**：还原此变更。

{% hint style="warning" %}
变更前后的差异只是**观察结果**，并不能证明因果关系。其他因素也可能同时发生变化（例如新增供应商或季节性高峰）。
{% endhint %}

\*\*示例。\*\*你为发票应用\_启用自动 PO 匹配和导出\_。两周后，**变更历史记录**显示：变更前的纯无接触处理率为 52%（210 份文档），变更后为 61%（198 份文档）。提升了 9 个百分点，且文档数量足以进行衡量。

管理员还会在关键指标和图表之间看到两个版块：

* **改进请求**：用户通过验证助手发送的建议，分为 **待处理** 和 **历史记录** 两个标签页。
* **已学习的规则提案**：DocBits 根据团队的更正学到的规则，例如“对于供应商 X，将字段 Y 中的值替换为某个值”。创建规则前，请检查它会替换团队已接受值的文档。**激活后**版块会显示规则生效前后目标字段的手动更正情况。

<figure><img src="https://1870485400-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FlPczlNw8zzYNLfjfispX%2Fuploads%2Fgit-blob-d355597745f9236a3aa8cc0345339052b7cb303a%2Ftouchless-consulting-report.png?alt=media" alt="咨询报告，包含排名前三的提案、排名表和按领域分类的问题"><figcaption><p>咨询报告：排名靠前的提案、按阻碍因素排序的列表（包含文档数量和每月预估影响），以及按领域分类的问题。示例组织使用演示数据；供应商名称均为虚构。</p></figcaption></figure>

管理员可以在标签页底部找到**咨询报告**。点击**创建报告**即可加载报告。报告汇总了组织中的以下内容：

* **影响最大的变更**，按排名列出，并显示各项的领域、问题、推荐操作、文档数量和每月的**预估**影响；
* **每个问题所属的领域**（提取、主数据、PO 匹配、自动记账、设置、流程）；
* **表格配置检查**，例如按文档类型和列列出的\_未使用结构化表格输出\_或\_表格列类型不匹配\_。

影响数值均为**估算值**。如果报告返回\_禁止访问\_，说明你的角色无权查看。

## 相关页面

* [无接触智能](/chinese/guan-li-yu-she-zhi/analytics-dashboard/touchless-intelligence.md)
* [供应商诊断和问题集群](/chinese/guan-li-yu-she-zhi/analytics-dashboard/touchless-intelligence/touchless-supplier-diagnosis.md)
* [PO 匹配诊断](/chinese/guan-li-yu-she-zhi/analytics-dashboard/touchless-intelligence/touchless-po-matching-diagnosis.md)


---

# 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/analytics-dashboard/touchless-intelligence/touchless-change-proposals.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.
