表单识别器(带标签的自定义模型)未获取正确的数据

Form recognizer(custom model with labels) is not fetching proper data

目前,我正在使用 Form Recognizer 2.1 预览版 从包含扫描图像的 PDF 文件中提取数据。文本已正确提取,但值与标签的映射不符合预期。我正在使用自定义模型 Train with labels to extract data from the file and using FOTT website to label data which is giving the functionality to label data manually. I have trained model with manually labeled data for 5 pages which is not giving proper response. And also tried Train without labels is not giving proper result. However, the model is not giving exact result. Some labels are not fetched and some labels are having incomplete values in the result. I have read documentation from Microsoft Docs 来了解此认知服务。它没有按预期给出正确的结果,我也不知道这是什么问题。所以,我想知道没有得到正确结果的可能原因是什么。

训练模型时,您是否使用来自同一结构的 5 个文档?要改进模型,您还可以添加一些额外的文档,以便您的训练数据代表您尝试从中提取数据的文档。在分析文档时,如果缺少键值对,您可以将该文档添加到训练数据中并训练模型,以便它也可以改进该文档。