公开(公告)号：US20170046599A1

公开(公告)日：2017-02-16

申请号：US15178119

申请日：2016-06-09

Applicant: National Yunlin University of Science and Technology

Inventor： Chuen-Min HUANG ,  Cheng-Yi WU ,  Po-Hung CHEN

IPC: G06K9/62 ,  G06F17/27 ,  G06K9/52

CPC classification number: G06K9/6267 ,  G06F17/277 ,  G06K9/00671 ,  G06K9/52 ,  G06K2209/27

Abstract: A method for automatically generating an image description includes following steps of: obtaining a first image data; analyzing a text file corresponding to the first image data; calculating occurrences and distribution ratios of terms, each of which contains a target word, from the text file, so as to obtain a plurality of the terms having the distribution ratios greater than a threshold; comparing the distribution ratios of the terms so as to find out at least one key term; finding out one of a plurality of lexical chains containing the key term with a greatest distribution ratio so as to generate a narrative language chain; and setting the narrative language chain as a description of the first image data. A system for automatically generating an image description and a non-volatile computer-readable storage media are also disclosed.

Abstract translation: 一种用于自动生成图像描述的方法包括以下步骤：获得第一图像数据; 分析与第一图像数据相对应的文本文件; 从文本文件中计算每个包含目标字的项的出现次数和分配比例，以便获得具有大于阈值的分配比率的多个项; 比较术语的分配比例，以便找出至少一个关键术语; 发现包含具有最大分配比例的关键词的多个词汇链之一，以产生叙事语言链; 并将叙事语言链设置为第一图像数据的描述。 还公开了一种用于自动生成图像描述和非易失性计算机可读存储介质的系统。

公开(公告)号：US20160239561A1

公开(公告)日：2016-08-18

申请号：US14837692

申请日：2015-08-27

Applicant: NATIONAL YUNLIN UNIVERSITY OF SCIENCE AND TECHNOLOGY

Inventor： Chuen-Min HUANG ,  Ya-Che LI ,  Cheng-Yi WU ,  Po-Hung CHEN ,  Jia-Wun LUO ,  Wei-Ching HSIAO ,  Ching-Che LI

IPC: G06F17/30

Abstract: A method for obtaining information includes the following steps of: retrieving at least a first text file from a first server; analyzing the first text file to generate at least one extracted term; accessing a second server containing a plurality of second text files; comparing the extracted term with the second text files; and when at least one of the second text files contains the extracted term, executing a generalized term extraction procedure, a synonym extraction procedure, or a homonym extraction procedure so as to correspondingly generate generalized term, synonym or homonym information.

Abstract translation: 一种获取信息的方法包括以下步骤：从第一服务器检索至少第一文本文件; 分析所述第一文本文件以生成至少一个提取的项; 访问包含多个第二文本文件的第二服务器; 将提取的术语与第二文本文件进行比较; 并且当所述第二文本文件中的至少一个包含所提取的项时，执行广义术语提取过程，同义词提取过程或同音异义提取过程，以便相应地生成广义术语，同义词或同义词信息。