公开(公告)号：US09984184B2

公开(公告)日：2018-05-29

申请号：US14404089

申请日：2014-09-03

Applicant: KOREA INSTITUTE OF SCIENCE AND TECHNOLOGY INFORMATION

Inventor： Seok Jong Yu

IPC: G06G7/58 ,  G06F17/50 ,  G06F19/12 ,  G06F17/30

CPC classification number: G06F17/5022 ,  G06F17/30477 ,  G06F19/12

Abstract: The present invention relates to a biological network analysis device and a method therefor. The biological network analysis method includes receiving biological data from an external server, extracting biological information from the received biological data to generate a biological interaction database, storing the generated biological interaction database, receiving input of a plurality of biological objects for a simulation, and performing a simulation by setting each of the biological objects to a node and automatically and generating a Boolean role based on the generated biological interaction database. Accordingly, the biological network analysis method conveniently designs a biological network and simulates the biological network based on biological interaction information by generating the biological interaction database.

公开(公告)号：US20180309772A1

公开(公告)日：2018-10-25

申请号：US15768002

申请日：2016-02-15

Applicant: KOREA INSTITUTE OF SCIENCE AND TECHNOLOGY INFORMATION

Inventor： Jungsuk SONG ,  Jangwon CHOI ,  Sangsoo CHOI ,  Heeseok KIM ,  Jiyeon CHOI ,  Younsu LEE

IPC: H04L29/06

CPC classification number: H04L63/1416 ,  H04L63/0236 ,  H04L63/10 ,  H04L63/101 ,  H04L63/12 ,  H04L63/1433 ,  H04L63/1441 ,  H04L69/22

Abstract: The present invention relates to a method and a device for automatically verifying a security event. The method for automatically verifying a security event, according to one embodiment of the present invention, comprises the steps of: receiving a security event and information related to the security event; extracting a feature of the security event; classifying the security event; and verifying the security event.

公开(公告)号：US20160110645A1

公开(公告)日：2016-04-21

申请号：US14571738

申请日：2014-12-16

Applicant: Korea Institute of Science and Technology Information

Inventor： Taehong Kim ,  Chang Hoo Jeong ,  Jung Ho Um ,  Seungwoo Lee ,  Hanmin Jung ,  Won Kyung Sung

IPC: G06N5/02 ,  G06F9/54

CPC classification number: G06F9/542

Abstract: A system and method dynamically updates an event configuration rule for processing a complex event. The system for dynamically updating an event configuration rule for processing a complex event includes an analysis unit configured to analyze an event configuration rule, change a redundant factor to a new virtual rule node, and generate an event rule by combining the new virtual rule node with a non-redundant factor and an update unit configured to sequentially compare the new virtual rule node with a set of previously stored virtual rule nodes and segment and reconfigure the new virtual rule node or the set of virtual rule nodes based on a result of the comparison.

Abstract translation: 系统和方法动态地更新用于处理复杂事件的事件配置规则。 用于动态更新用于处理复杂事件的事件配置规则的系统包括：分析单元，被配置为分析事件配置规则，将冗余因子改变为新的虚拟规则节点，并且通过将新的虚拟规则节点与 非冗余因子和更新单元，被配置为顺序地将新的虚拟规则节点与一组先前存储的虚拟规则节点进行比较，并且基于比较的结果来分段和重新配置新的虚拟规则节点或虚拟规则节点集合 。

公开(公告)号：US20150220623A1

公开(公告)日：2015-08-06

申请号：US14419336

申请日：2013-08-01

Applicant: KOREA INSTITUTE OF SCIENCE AND TECHNOLOGY INFORMATION

Inventor： Chang Hoo Jeong ,  Sung Pil Choi ,  Hong Woo Chun ,  Mi Nyeong Hwang ,  Sung Jae Jung ,  Han Min Jung

IPC: G06F17/30

CPC classification number: G06F16/338 ,  G06F16/951 ,  G16B5/00 ,  G16B40/00

Abstract: The present invention relates to a system and method for pathway construction, including an advance information database for storing an entity name of protein, diseases, compounds, symptoms, enzymes, medicines, diseases, place and/or pathway; an entity recognition unit for recognizing entities from an input document using the advance information database; a relation recognition unit for extracting context between the recognized entities based on the pre-stored context pattern information, and recognizing a relation between the entities by normalizing the extracted context; a relation event generating unit for performing a web search for the recognized entities to collect a document including the entities and information on the points in cells of the entities, and generating a relation event based on the collected information; and a pathway generating unit for displaying relevant entities at the relevant points in the cells based on the recognized relation event to generate a pathway.

Abstract translation: 本发明涉及一种用于途径建设的系统和方法，包括用于存储蛋白质，疾病，化合物，症状，酶，药物，疾病，地点和/或途径的实体名称的预先信息数据库; 实体识别单元，用于使用所述预先信息数据库从输入文档识别实体; 关系识别单元，用于基于所述预先存储的上下文模式信息来提取所识别的实体之间的上下文，并通过归一化所提取的上下文来识别所述实体之间的关系; 关系事件发生单元，用于对所识别的实体进行网络搜索以收集包括所述实体的文档和关于所述实体的单元中的点的信息，以及基于所收集的信息生成关系事件; 以及路径产生单元，用于基于所识别的关系事件在单元格中的相关点处显示相关实体以生成路径。

公开(公告)号：US20140101087A1

公开(公告)日：2014-04-10

申请号：US13726221

申请日：2012-12-24

Applicant: Korea Institute of Science and Technology Information

Inventor： Young Ho MOON ,  Kang Hoe KIM ,  Seon Ho KIM ,  Woon Dong YEO ,  Jae Woo KANG

IPC: G06N5/02

CPC classification number: G06N5/02 ,  G06F17/2235 ,  G06F17/30014 ,  G06K9/6269 ,  G06N3/08 ,  G06N99/005

Abstract: A method of evaluating a value of reference information and an apparatus for evaluating a value of reference information are disclosed. According to an embodiment of the present invention, the method includes calculating similarity values of reference relationships between the subject document and each of neighbor documents, respectively, and summing the calculated similarity values to calculate a first sum, multiplying each of the similarity values of reference relationships between the subject document and each of the neighbor documents by a corresponding value of reference information of the first reference document for each of the neighbor documents, and summing the multiplied values to calculate a second sum, and evaluating a value of reference information using a ratio of the first and second sums.

Abstract translation: 公开了一种评估参考信息的值的方法和用于评估参考信息的值的装置。 根据本发明的一个实施例，该方法包括分别计算主题文档和每个相邻文档之间的参考关系的相似度值，并将所计算的相似度值相加以计算第一和，将每个参考的相似度值相乘 通过对于每个相邻文档的第一参考文档的参考信息的对应值，对主题文档和每个相邻文档之间的关系，并且对相乘的值求和以计算第二和，并且使用 第一和第二和的比率。

公开(公告)号：US20160283626A1

公开(公告)日：2016-09-29

申请号：US14404089

申请日：2014-09-03

Applicant: KOREA INSTITUTE OF SCIENCE AND TECHNOLOGY INFORMATION

Inventor： Seok Jong YU

IPC: G06F17/50 ,  G06F17/30

CPC classification number: G06F17/5022 ,  G06F17/30477 ,  G06F19/12

Abstract: The present invention relates to a biological network analysis device and a method therefor. The biological network analysis method includes receiving biological data from an external server, extracting biological information from the received biological data to generate a biological interaction database, storing the generated biological interaction database, receiving input of a plurality of biological objects for a simulation, and performing a simulation by setting each of the biological objects to a node and automatically and generating a Boolean role based on the generated biological interaction database. Accordingly, the biological network analysis method conveniently designs a biological network and simulates the biological network based on biological interaction information by generating the biological interaction database.

Abstract translation: 本发明涉及一种生物网络分析装置及其方法。 所述生物网络分析方法包括从外部服务器接收生物数据，从接收到的生物数据中提取生物信息以产生生物相互作用数据库，存储生成的生物交互数据库，接收用于模拟的多个生物体的输入，以及执行 通过将每个生物对象设置为节点并自动生成并基于生成的生物交互数据库生成布尔角色来进行模拟。 因此，生物网络分析方法方便地设计生物网络，并通过生成生物相互作用数据库，基于生物相互作用信息模拟生物网络。

公开(公告)号：US20160132779A1

公开(公告)日：2016-05-12

申请号：US14572192

申请日：2014-12-16

Applicant: Korea Institute of Science and Technology Information

Inventor： Seungwoo Lee ,  Chang Hoo Jeong ,  Jung Ho Um ,  Taehong Kim ,  Hanmin Jung ,  Won Kyung Sung

IPC: G06N5/04

CPC classification number: G06N5/046

Abstract: A hybrid rule reasoning apparatus and a method thereof includes: a reasoning rule classification unit for classifying an input reasoning rule into at least one of a schema rule, an instance rule, and a mixed rule; a memory-based reasoning unit for performing reasoning by applying a schema rule to a previously stored schema triple and specifying a mixed rule into an instance rule by applying the mixed rule to the schema triple; and a disk-based distributed/parallel reasoning unit for performing reasoning by applying the instance rule specified by the memory-based reasoning unit or the instance rule classified by the reasoning rule classification unit to a previously stored instance triple.

Abstract translation: 混合规则推理装置及其方法包括：推理规则分类单元，用于将输入推理规则分类为模式规则，实例规则和混合规则中的至少一个; 基于存储器的推理单元，用于通过将模式规则应用于先前存储的模式三元组并通过将混合规则应用于模式三元框来将混合规则指定到实例规则中来执行推理; 以及基于磁盘的分布式/并行推理单元，用于通过将由基于存储器的推理单元指定的实例规则或由推理规则分类单元分类的实例规则应用于先前存储的实例三元来执行推理。

公开(公告)号：US09224093B2

公开(公告)日：2015-12-29

申请号：US13726221

申请日：2012-12-24

Applicant: KOREA INSTITUTE OF SCIENCE AND TECHNOLOGY INFORMATION

Inventor： Young Ho Moon ,  Kang Hoe Kim ,  Seon Ho Kim ,  Woon Dong Yeo ,  Jae Woo Kang

IPC: G06N3/08 ,  G06N5/02 ,  G06K9/62 ,  G06N99/00 ,  G06F17/30

CPC classification number: G06N5/02 ,  G06F17/2235 ,  G06F17/30014 ,  G06K9/6269 ,  G06N3/08 ,  G06N99/005

Abstract: A method of evaluating a value of reference information and an apparatus for evaluating a value of reference information are disclosed. According to an embodiment of the present invention, the method includes calculating similarity values of reference relationships between the subject document and each of neighbor documents, respectively, and summing the calculated similarity values to calculate a first sum, multiplying each of the similarity values of reference relationships between the subject document and each of the neighbor documents by a corresponding value of reference information of the first reference document for each of the neighbor documents, and summing the multiplied values to calculate a second sum, and evaluating a value of reference information using a ratio of the first and second sums.

Abstract translation: 公开了一种评估参考信息的值的方法和用于评估参考信息的值的装置。 根据本发明的一个实施例，该方法包括分别计算主题文档和每个相邻文档之间的参考关系的相似度值，并将所计算的相似度值相加以计算第一和，将每个参考的相似度值相乘 通过对于每个相邻文档的第一参考文档的参考信息的对应值，对主题文档和每个相邻文档之间的关系，并且对相乘的值求和以计算第二和，并且使用 第一和第二和的比率。

公开(公告)号：US20140101173A1

公开(公告)日：2014-04-10

申请号：US13726220

申请日：2012-12-24

Applicant: Korea Institute of Science and Technology Information

Inventor： Young Ho MOON ,  Kang Hoe KIM ,  Seon Ho KIM ,  Woon Dong YEO ,  Jae Woo KANG ,  Jae Min LEE

IPC: G06F17/30

CPC classification number: G06F17/30 ,  G06F17/2235 ,  G06F17/30014

Abstract: A method for providing information about a main knowledge stream is disclosed. According to an embodiment of the present invention, the method includes obtaining reference links representing reference relationships among reference documents in each of a plurality of documents stored in a database, determining one or more basic paths connecting the reference links, calculating probability values of the reference links by overlapping the determined basic paths, determining a first document among the documents and an input reference link associated with the first document, and performing a Markov chain model using a probability value of the input reference link, and calculating information about the main knowledge stream associated with the first document using the result obtained by performing the Markov chain model.

Abstract translation: 公开了一种用于提供关于主要知识流的信息的方法。 根据本发明的实施例，所述方法包括：获取表示存储在数据库中的多个文档中的每一个中的参考文档之间的参考关系的参考链接，确定连接所述参考链接的一个或多个基本路径，计算参考的概率值 通过重叠确定的基本路径，确定文档中的第一文档和与第一文档相关联的输入参考链接，以及使用输入参考链接的概率值来执行马尔科夫链模型，以及计算关于主知识流的信息 使用通过执行马尔可夫链模型获得的结果与第一文档相关联。