公开(公告)号：US08484209B2

公开(公告)日：2013-07-09

申请号：US13299294

申请日：2011-11-17

Applicant: Tae Hoon Kim ,  Min Je Park ,  Se Uk Cheon

Inventor： Tae Hoon Kim ,  Min Je Park ,  Se Uk Cheon

IPC: G06F17/00

CPC classification number: G06Q30/02

Abstract: The present invention relates to a method for recommending other users who have similar preference with a user. The method includes the steps of: acquiring information on objects selected by a user and other users; acquiring information on topics; determining to which topic the user and the other users respectively correspond; evaluating a degree of user similarity by each other user, the degree of user similarity being relevant to sum of probabilities of the specific object appearing in the state of a topic while k-th other user and the user have the topic as a probability of the k-th other user and the user having selected the specific object, by referring to correspondence relationships; and recommending specific other users who have a high degree of user similarity, wherein the degree of user similarity is evaluated by multiplying the sum by a probability of the specific object appearing independently.

Abstract translation: 本发明涉及一种用于推荐与用户具有相似偏好的其他用户的方法。 该方法包括以下步骤：获取由用户和其他用户选择的对象的信息; 获取主题信息; 确定用户和其他用户分别对应的主题; 评估每个其他用户的用户相似度，用户相似度与在主题状态下出现的特定对象的概率之和相关，而第k个其他用户和用户将主题作为主题的概率相关 通过参考对应关系，选择第k个其他用户和用户已经选择了特定对象; 并推荐具有高度的用户相似性的特定的其他用户，其中通过将该和乘以独立出现的特定对象的概率来评估用户相似度的程度。

公开(公告)号：US20120173561A1

公开(公告)日：2012-07-05

申请号：US13299294

申请日：2011-11-17

Applicant: Tae Hoon Kim ,  Min Je Park ,  Se Uk Cheon

Inventor： Tae Hoon Kim ,  Min Je Park ,  Se Uk Cheon

IPC: G06F17/30

CPC classification number: G06Q30/02

Abstract: The present invention relates to a method for recommending other users who have similar preference with a user. The method includes the steps of: acquiring information on objects selected by a user and other users; acquiring information on topics; determining to which topic the user and the other users respectively correspond; evaluating a degree of user similarity by each other user, the degree of user similarity being relevant to sum of probabilities of the specific object appearing in the state of a topic while k-th other user and the user have the topic as a probability of the k-th other user and the user having selected the specific object, by referring to correspondence relationships; and recommending specific other users who have a high degree of user similarity, wherein the degree of user similarity is evaluated by multiplying the sum by a probability of the specific object appearing independently.

Abstract translation: 本发明涉及一种用于推荐与用户具有相似偏好的其他用户的方法。 该方法包括以下步骤：获取由用户和其他用户选择的对象的信息; 获取主题信息; 确定用户和其他用户分别对应的主题; 评估每个其他用户的用户相似度，用户相似度与在主题状态下出现的特定对象的概率之和相关，而第k个其他用户和用户将主题作为主题的概率相关 通过参考对应关系，选择第k个其他用户和用户已经选择了特定对象; 并推荐具有高度的用户相似性的特定的其他用户，其中通过将该和乘以独立出现的特定对象的概率来评估用户相似度的程度。

公开(公告)号：US08477152B2

公开(公告)日：2013-07-02

申请号：US12805543

申请日：2010-08-05

Applicant: Kye Hyun Kim ,  Se Uk Cheon ,  Hyuk Lee ,  Chol Young Lee ,  Yong Gil Park

Inventor： Kye Hyun Kim ,  Se Uk Cheon ,  Hyuk Lee ,  Chol Young Lee ,  Yong Gil Park

IPC: G09G5/00

CPC classification number: G09B11/00 ,  G09B29/106

Abstract: Disclosed herein is a system and method for drawing a stream and road centerline for GIS-based linear map production, which performs a series of processes of automatically detecting accurate positions of points of a centerline using contour line data of a stream map or a road map having a digital map form, which is extracted from a digital map produced through remote sensing or construction of national geographic information systems, and connecting the detected points of the centerline so as to update stream and road centerline data generated by an inaccurate method and algorithm and to enable an accurate centerline to be used in various application fields.

Abstract translation: 本文公开了一种用于绘制基于GIS的线性地图生成的流和道路中心线的系统和方法，其执行使用流图或路线图的轮廓线数据自动检测中心线的点的精确位置的一系列处理 具有从通过遥感或构建国家地理信息系统产生的数字地图提取的数字地图形式，并连接中心线的检测点，以更新由不准确的方法和算法产生的流和道路中心线数据，以及 以便在各种应用领域中使用准确的中心线。