專利授權區國立清華大學國際產學營運總中心 Operations Center for Industry Collaboration

搜尋專利授權區

關鍵字

» 新增關鍵字

選單

專利授權區

專利授權區
專利名稱(中)	自然語言語料用於機器學習決策模型的訓練方法
專利名稱(英)	Training Method of Natural Language Corpus for the Decision Making Model of Machine Learning
專利家族	中華民國：I798513 美國：US11461558B2
專利權人	國立清華大學 100%
發明人	王道維,李亞倫,林昀嫺
技術領域	資訊工程

專利摘要(英)
A Training Method of Natural Language Corpus for the Decision Making Model of Machine Learning implemented by a computer device, the computer device stores a plurality of natural texts, each of natural text is marked with a target decision result of a plurality of decision results and includes a plurality of reasoning data related to at least one object to be described by the natural text, and includes: For each reasoning data corresponding to each natural text, a segmentation of word algorithm and a document-to-vector algorithm are used to obtain a corresponding reasoning vector group; For each natural text, the reasoning vector groups corresponding to the natural text are combined into an effective vector according to the sequential connection; Obtaining a decision model by using a supervised classification algorithm according to the effective vector corresponding to each natural text and its corresponding target decision result.

專利摘要(英)

A Training Method of Natural Language Corpus for the Decision Making Model of Machine Learning implemented by a computer device, the computer device stores a plurality of natural texts, each of natural text is marked with a target decision result of a plurality of decision results and includes a plurality of reasoning data related to at least one object to be described by the natural text, and includes: For each reasoning data corresponding to each natural text, a segmentation of word algorithm and a document-to-vector algorithm are used to obtain a corresponding reasoning vector group; For each natural text, the reasoning vector groups corresponding to the natural text are combined into an effective vector according to the sequential connection; Obtaining a decision model by using a supervised classification algorithm according to the effective vector corresponding to each natural text and its corresponding target decision result.

聯絡資訊
承辦人姓名	李佳玲
承辦人電話	03-5715131 #62300
承辦人Email	cl.lee@mx.nthu.edu.tw