表单 AI

Forms AI is part of Document Understanding^TM and can be used for uploading and processing structured forms with standard layouts and fields.

创建 Forms AI

Forms AI is the first extraction method available in Document Understanding. Read more information about how to create a new project in Document Understanding.

创建项目后，您需要按照后续步骤在项目中使用 Forms AI 创建文档类型。

1. 打开项目。
2. Select the New Document Type button.
3. 为您的文档类型添加名称。

If you want to train your document classifiers straight from Document Understanding, than you can use the One Click Classification functionality.

备注：

Fixed layout forms used with Forms AI can each have a maximum length of five pages.

将 Forms AI 转换为半结构化文档类型

您可以将 Forms AI 文档类型转换为半结构化文档类型。

将 Forms AI 文档类型转换为半结构化 (Document Manager) 文档类型时，您可以使用 Document Manager 中的所有可用功能

转换选项非常适合用于训练功能更强大的深度学习机器学习模型的复杂场景。

如何转换 Forms AI 会话

如果您决定将 Forms AI 会话转换为 Document Manager 会话，则可以选择两个选项。

从项目的文档类型列表中

您可以直接从项目的“文档类型”列表中转换文档类型。

Access the Open access menu of the document type you want to convert and click the Convert to Semi-Structured option. A popup window is displayed asking you to confirm the action.

备注：

转换文档类型后，您将无法撤消 Actions。

从打开的 Forms AI 会话

打开已创建的 Forms AI 会话，以将其转换为半结构化会话。

From the opened session click the Access menuthen click the Convert to Semi-Structured option.

备注：

Once a Document Type has been converted, you cannot reverse the action. The Convert to Semi-Structured button is not displayed if the project does not have an AI Center link.

导入文档

创建新的 Forms AI 后，系统将打开一个新窗口，要求您导入数据。您最少可以导入两个文档，最多可以导入二十个文档，每个文档最多包含五页。通过拖放或浏览来上传文件。

导入文档是将表单 AI 转换为半结构化 AI 文档类型的另一种方法。 如果您尝试上传超过 20 个文档，或者任何文档超过 20 页，则会显示一个选项。 屏幕上将显示一个弹出窗口，询问您是否要将 FormsAI 会话转换为半结构化会话。

Automatically extracted fields should also be checked for Content Type accuracy. For example, if a date field was automatically extracted, then the Content Type should be date. Any inaccuracies should be manually corrected.

Management bar

在页面顶部，您可以找到管理栏。您可以使用管理栏执行多项操作：在文档之间导航、删除/还原档、搜索/筛选文档、运行 AI 模型预测以及导入和导出文档。

以下是管理栏中的可用项目：

项目	图标	描述
导航		在与活动筛选器匹配的文档之间导航。在两个箭头之间显示一个计数器。它显示了与活动搜索/筛选器匹配的文档总数和当前文档的编号。
“搜索”和“在文档中搜索”		Search - initiate a search or filter the documents. Filter is also applied when exporting documents. You can filter by words from a document or by document names. Search in document - initiate a text search inside the document by clicking on the or using the shortcut Ctrl + Shift + F
删除/还原	/	删除或还原文档。已删除的文档位于“已删除”筛选器下。
导入		打开“导入数据”对话框。
导出		打开“导出文件”对话框。
文档名称和类型	不适用	当前处于活动状态的文档的名称及其类型。
下载		The option is available in the drop-down next to the document name. Click the icon to download a Zip file containing the original document. Besides the original document, all pages converted internally by Document Manager to .jpeg images are downloaded as well.
永久删除		The option is available in the dropdown next to the document name. Permanently deletes individual files. The .pdf and all its .jpeg images are deleted from the AI Center dataset and all the metadata is deleted from the database. When clicking the button, a pop-up message appears asking you if you are sure you want to permanently delete the document. Click OK to continue or Cancel to revert to the previous screen.
预测		Run AI model predictions and display the results. After configuring Prelabelling, the button is enabled in the management bar. Click it to prelabel the current document. At the moment, using the Predict option with Public Endpoints prelabels only the first 10 pages of a document. This is a known issue and a fix is in the working. Using the Predict option with ML Skills in AI Center, however, does not impose such a limitation.
发布		发布 Forms AI 提取程序并创建关联的链接，该链接可在项目的提取程序列表中找到。
设置		Configure OCR and Prelabelling settings or access the How to... panel. The settings button has two available options: Settings where you can see the OCR configuration which is automatically populated from the Project's Settings. Accessibility mode makes the raw values visible How to... where you can find all the available shortcuts and controls.
会话	不适用	The name of the current session, found at the top of the page, next to the UiPath® Document Understanding TM logo.

Let's go a little bit deeper in understanding the difference between Delete and Permanently Delete options.

• The Delete option deletes the files, without permanently removing them from your project. You can still find the deleted files under the deleted filter from the Search bar, and restore them by using the Restore option.
• The Permanently Delete option deletes the selected files without any possibility of restoring them.

The Settings button has two available options:

• Settings - where you can configure the OCR service
• How to... - which has the purpose of a help menu

列字段

新建列字段

1. Click in the table section at the top of the page to add a new Column field. The Create Column Field window is displayed.
2. 在“输入唯一字段名称”字段中填写字段的唯一名称。该字段不接受大写字母。只能包含小写字母、数字、下划线 _ 和短划线 -。
3. 单击“确定”。

编辑列字段

Click the Edit field button. The available options for column fields can be found in the table below.

选项	描述
字段名称	字段的唯一名称。 The field does not accept uppercase letters. It can only contain lowercase letters, numbers, underscore _ and dash - .
内容类型	字段的内容类型： string : appropriate for company names or addresses, as well as payment terms, or for any other field where the RPA developer prefers to build the parsing or formatting logic manually, in the RPA workflow. number : appropriate for amounts or quantities, with intelligent parsing of the decimal/thousands separators. date : the model parses, formats and unifies the output in a yyyy-mm-dd format. phone : appropriate for phone numbers. Formatting removes letters and parentheses, and replaces spaces with dashes. id-no : appropriate for alphanumeric codes, numbers of IDs, it is similar to the string content type, but includes cleaning of any characters coming before a colon : . If the id number you need to extract might contain colon : characters, please use string as content type instead to avoid data loss.
快捷方式	字段的快捷键。允许使用一个或两个按键。
拆分项目	如果要将此字段用作表格中行项目或行之间的分隔符，请选中此复选框。出现此字段的任何行都会被视为表格中的新行项目或行。这通常用于发票行项目中的“行金额”字段。

单击“保存”以保存您的设置。

Grouping table rows is different than in the AI Center Document Manager. Here, the rows are automatically grouped based on the state of the Split items checkbox on each column fields. This is only relevant for tables with rows that contain multiple lines of text. In this case you must check the Split items checkbox on any of the fields that have only one line for each table row. For instance, on an invoice, the line item amount would be a typical field on which you might check the Split items option. In the context of Forms AI you would do the same thing on forms.

删除列字段

要删除列字段，请执行以下步骤：

1. Click the Edit field button corresponding to the column field you want to delete.
2. 单击“删除”按钮。
3. 单击“确定”。
4. 列字段及其关联的带标签数据将被删除。

字段

Create a new field

1. Click on the right pane in the Fields section. The Create a new regular field window is displayed.
2. 在“输入唯一字段名称”字段中填写字段的唯一名称。该字段不接受大写字母。只能包含小写字母、数字、下划线 _ 和短划线 -。
3. 单击“确定”。

删除所有字段

1. Click in the table section at the top of the page to delete all created fields. Use this function for deleting all fields, including Regular and Column fields, and all the labels on the documents in the current Document Type collection. This action cannot be undone.
2. Click the Delete button from the Delete all fields dialog box.

编辑字段

Click the Edit field button. The available options for regular fields can be found in the table below.

选项	描述
字段名称	字段的唯一名称。 The field does not accept uppercase letters. It can only contain lowercase letters, numbers, underscore _ and dash - .
内容类型	字段的内容类型： string : appropriate for company names or addresses, as well as payment terms, or for any other field where the RPA developer prefers to build the parsing or formatting logic manually, in the RPA workflow. number : appropriate for amounts or quantities, with intelligent parsing of the decimal/thousands separators. date : the model parses, formats and unifies the output in a yyyy-mm-dd format. phone : appropriate for phone numbers. Formatting removes letters and parentheses, and replaces spaces with dashes. id-no : appropriate for alphanumeric codes, numbers of IDs, it is similar to the string content type, but includes cleaning of any characters coming before a colon : . If the id number you need to extract might contain colon : characters, please use string as content type instead to avoid data loss.
快捷方式	字段的快捷键。允许使用一个或两个按键。
多行	常规

单击“保存”以保存您的设置。

删除常规字段

要删除常规字段，请执行以下步骤：

1. Click the Edit field button corresponding to the regular field you want to delete.
2. 单击“删除”按钮。
3. 单击“确定”。
4. 字段及其关联的带标签数据将被删除。

文档视图和标签

对于多页文档，您可以像在任何 PDF 查看器中一样自然地滚动页面。要放大或缩小，请使用 Ctrl 并滚动鼠标滚轮。

您可以通过选择文字框并按下相应的按键，将文档分配给某个字段，从而标记文档。您也可以右键单击文字框并验证提取的信息。

For more details on how to label documents, visit this page.

复选框

应为每个字段手动标记 Forms AI 中可用的复选框。也可以使用“列字段”选项标记表格中的复选框。在 Forms AI 中标记复选框时，应同时考虑选中和未选中的复选框。

Here you can find more detailed information about how to label checkboxes.

You can choose to integrate your Document Understanding project into an RPA workflow by following the steps presented here.