首页> 外国专利> PROCEDURE EXTRACTION AND ENRICHMENT FROM UNSTRUCTURED TEXT USING NATURAL LANGUAGE PROCESSING (NLP) TECHNIQUES

PROCEDURE EXTRACTION AND ENRICHMENT FROM UNSTRUCTURED TEXT USING NATURAL LANGUAGE PROCESSING (NLP) TECHNIQUES

机译:使用自然语言处理(NLP)技术从非结构化文本中提取和丰富程序

摘要

A method for extraction and enrichment of a procedure from a document is provided. The method may include identifying a potential location of a procedure in the document. The method may also include detecting a beginning boundary and an end boundary associated with the identified potential location of the procedure. The method may further include validating a text associated with the identified potential location of the procedure in the document. Additionally, the method may include determining an intent from the identified potential location of the procedure based on at least one of the beginning boundary, the end boundary, a surrounding text associated with the identified potential location of the procedure, a context associated with the document, and a title of the document. The method may also include enriching the procedure based on the determined intent.
机译:提供了一种用于从文档中提取和丰富程序的方法。该方法可以包括识别过程在文档中的潜在位置。该方法还可以包括检测与所识别的过程的潜在位置相关联的开始边界和结束边界。该方法可以进一步包括验证与该过程在文档中的所标识的潜在位置相关联的文本。另外,该方法可以包括基于以下至少一项来从所标识的过程的潜在位置中确定意图:开始边界,结束边界,与所标识的过程的潜在位置相关联的周围文本,与文档相关联的上下文。 ,以及文件标题。该方法还可以包括基于所确定的意图来丰富该过程。

著录项

  • 公开/公告号US2015212994A1

    专利类型

  • 公开/公告日2015-07-30

    原文格式PDF

  • 申请/专利权人 INTERNATIONAL BUSINESS MACHINES CORPORATION;

    申请/专利号US201414168356

  • 发明设计人 AMIT P. BOHRA;

    申请日2014-01-30

  • 分类号G06F17/24;

  • 国家 US

  • 入库时间 2022-08-21 15:23:49

相似文献

  • 专利
  • 外文文献
  • 中文文献
获取专利

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号