公开(公告)号：US20170060997A1

公开(公告)日：2017-03-02

申请号：US15307058

申请日：2014-07-29

Applicant: FOUNDATION OF SOONGSIL UNIVERSITY INDUSTRY COOPERATION

Inventor： Soo Won LEE ,  Joon Ho NOH

IPC: G06F17/30

CPC classification number: G06F16/3344 ,  G06F15/16 ,  G06F16/355 ,  G06F16/93 ,  G06F17/277

Abstract: A method and a server for extracting a topic and evaluating suitability of the extracted topic are disclosed. The topic extraction server includes a text preprocessing unit configured to extract noun from a document group and remove stopword from the extracted noun, a keyword extraction unit configured to calculate a weight of a noun and extracting a keyword representing the document group, a seed selection unit configured to calculate a weight of the extracted keyword and select a seed, an initial clustering unit configured to generate one cluster including the selected seed and a keyword shown by several times in a sentence including the selected seed, and a cluster combination unit configured to extract a topic group.

Abstract translation: 公开了一种用于提取主题并评估提取的主题的适用性的方法和服务器。 主题提取服务器包括：文本预处理单元，被配置为从文档组中提取名词并从提取的名词中删除句子;关键词提取单元，被配置为计算名词的权重并提取表示文档组的关键词;种子选择单元 被配置为计算所提取的关键字的权重并选择种子，初始聚类单元，被配置为在包括所选择的种子的句子中生成包括所选择的种子和多个关键字的一个群组，以及群组合单元，被配置为提取 主题组。

公开(公告)号：US20170018033A1

公开(公告)日：2017-01-19

申请号：US15210900

申请日：2016-07-15

Applicant: FOUNDATION OF SOONGSIL UNIVERSITY INDUSTRY COOPERATION

Inventor： Soo Won LEE ,  Jang Yun UM

IPC: G06Q40/06 ,  G06N7/00

CPC classification number: G06Q40/06 ,  G06N7/005

Abstract: Provided are a method and a system for predicting stock fluctuation prediction. A system for predicting stock fluctuation according to an embodiment of the present invention includes: a data collector and a preprocessor collecting news and KOSPI data and extracting words from the collected news through stopword removal and morphologic analysis, a sentiment dictionary constructor selecting sentiment words and calculating sentiment values of the sentiment words to construct a sentiment dictionary of a stock domain required for stock prediction, and a stock fluctuation prediction model constructor predicting fluctuation of a closing price of a next day to a closing price of a current day by combining a prediction model using the constructed sentiment dictionary and an ARIMA prediction model using the KOSPI data.

Abstract translation: 提供了一种用于预测股票波动预测的方法和系统。 根据本发明的实施例的用于预测股票波动的系统包括：数据收集器和预处理器收集消息和KOSPI数据，并通过字词移除和形态分析从收集的消息中提取词，情感词典构造器选择情绪词和计算 情绪词的情感值构成股票预测所需的股票领域的情绪词典，以及股票波动预测模型构造者，通过组合预测模型来预测第二天的收盘价波动到当天的收盘价 使用构建的情绪词典和使用KOSPI数据的ARIMA预测模型。