首页>
外国专利>
METHOD FOR EXTRACTING FORM INFORMATION IN A STRUCTURED MANNER, ELECTRONIC DEVICE, AND COMPUTER-READABLE STORAGE MEDIUM
METHOD FOR EXTRACTING FORM INFORMATION IN A STRUCTURED MANNER, ELECTRONIC DEVICE, AND COMPUTER-READABLE STORAGE MEDIUM
展开▼
机译:在结构化方式,电子设备和计算机可读存储介质中提取表单信息的方法
展开▼
页面导航
摘要
著录项
相似文献
摘要
A method for extracting form information in a structured manner. The method comprises the following steps: acquiring position information and label information about each row of characters in a specified document (such as a PDF document) (S31); according to the position information and label information about each row of characters, recognizing a line wrap situation and a page-crossing situation from a form of the specified document (S32); when a line wrap situation is recognized from the form of the specified document, storing information in the form in rows and in columns according to a first reconstruction rule (S33); and when a page-crossing situation is recognized from the form of the specified document, then storing information in the form in rows and in columns according to a second reconstruction rule (S34). By means of the method, data can be extracted and stored in a structured manner.
展开▼