-
公开(公告)号：KR101498944B1
公开(公告)日：2015-03-06
申请号：KR1020120103930
申请日：2012-09-19
Applicant: 세종대학교산학협력단
Abstract: 상품 판매 업체 관련 글 판단 장치가 개시되며, 상기 상품 판매 업체 관련 글 판단 장치는 질의어를 입력하여 검색된 상품 판매 업체 데이터베이스를 기초로 웹 상의 블로그에서 데이터를 수집하는 데이터 수집부; 상기 데이터 수집부에서 수집된 데이터에서 리뷰를 추출하는 리뷰 추출부; 상기 데이터 수집부에서 수집된 데이터에서 이미지를 추출하는 이미지 추출부; 및 상기 리뷰 추출부와 상기 이미지 추출부에서 추출된 정보를 기초로 상품 판매 업체와 관련된 정보 여부를 판단하는 판단부를 포함한다.
-
公开(公告)号：KR1020110044112A
公开(公告)日：2011-04-28
申请号：KR1020090100948
申请日：2009-10-22
Applicant: 세종대학교산학협력단 , 건국대학교 산학협력단
CPC classification number: G06F17/30705 , G06F17/2775 , G06F2216/03
Abstract: PURPOSE: A semi-automatic building of a pattern database for mining review of product attributes is provided to shorten the construction time of a review pattern database. CONSTITUTION: A review for a product is collected in an online shopping mall, and a part of speech is extracted from the review through tagging for part of speech. The part pattern of speech is analyzed for the extracted sentence. The extracted sentence satisfies the 8-structure sentence. An evaluation sentence is included in the corresponding sentence, and the evaluated sentence is inserted into a review pattern database.
Abstract translation: 目的：为了缩短审查模式数据库的建设时间，提供了一个用于挖掘审查产品属性的模式数据库的半自动建立。 规定：在网上购物中心收集产品的评论，并通过对部分讲话进行标注，从评审中抽出部分内容。 对提取的句子分析语音的部分模式。 提取的句子满足8结构句子。 评价句子包含在相应的句子中，评估句子被插入到审阅模式数据库中。
-
公开(公告)号：KR1020140107814A
公开(公告)日：2014-09-05
申请号：KR1020130021844
申请日：2013-02-28
Applicant: 세종대학교산학협력단
CPC classification number: G06F17/3089 , G06F17/30864 , G06F17/30876 , G06Q50/10
Abstract: A server for providing integrated project information according to the present invention includes: a wrapper storage unit which stores a wrapper including the storage location information of specific information among web documents provided from each site and URL information about a plurality of project management institution sites; a collecting unit which collects research project notice data in the project management institution sites; an extracting unit which extracts specific data from the research project notice data collected in the collecting unit based on the wrapper; an integrated information storage unit which inserts the specific information extracted by the extracting unit into integrated information data; and a transmitting unit which transmits the integrated information to a terminal to request the integrated information. The extracting unit can extract the specific information based on the wrapper corresponding to the project management institution site in which the research project notice data is collected.
Abstract translation: 根据本发明的用于提供集成项目信息的服务器包括：包装存储单元，其存储包括每个站点提供的web文档中的特定信息的存储位置信息和关于多个项目管理机构站点的URL信息的包装器; 在项目管理机构网站收集研究项目通知数据的收集单位; 提取单元，其基于所述包装从所述收集单元收集的研究项目通知数据中提取特定数据; 集成信息存储单元，其将由提取单元提取的特定信息插入到综合信息数据中; 以及发送单元，其将所述综合信息发送到终端以请求所述综合信息。 提取单元可以根据与收集研究项目通知数据的项目管理机构站点相对应的包装来提取特定信息。
-
Patent Agency Ranking
公开(公告)号：KR101494655B1
公开(公告)日：2015-02-25
申请号：KR1020120103970
申请日：2012-09-19
Applicant: 세종대학교산학협력단
Abstract: 소셜 네트워크 서비스 데이터 기반 특정 기관의 순위 계산 장치가 개시되며, 상기 소셜 네트워크 서비스 데이터 기반 특정 기관의 순위 계산 장치는 특정 기관의 명칭 및 주소 정보를 기초로 상기 소셜 네트워크 서비스로부터 상기 특정 기관에 대한 정보를 수집하는 데이터 수집부; 상기 소셜 네트워크 서비스를 통해 수집한 정보로부터 상기 특정 기관의 순위 인자를 추출하는 순위 인자 추출부; 및 상기 추출된 순위 인자를 바탕으로 상기 특정 기관의 순위를 계산하는 순위 계산부를 포함한다.
-
公开(公告)号：KR1020140094329A
公开(公告)日：2014-07-30
申请号：KR1020130007030
申请日：2013-01-22
Applicant: 세종대학교산학협력단
CPC classification number: G06F17/2785 , G06F17/18 , G06F17/2735
Abstract: The present invention relates to an apparatus for analyzing the preference of a user on a product, comprising: a sentimental word dictionary for storing sentimental lexicon pattern information; and a preference analysis part for classifying an opinion of the user, described in one or more documents, into a positive opinion class or a negative opinion class based on the sentimental lexicon pattern information defined in the sentimental word dictionary using a statistics based machine learning algorithm.
Abstract translation: 本发明涉及一种用于分析用户对产品的喜好的装置，包括：用于存储感性词典图案信息的感伤词典; 以及偏好分析部件，用于使用基于统计的机器学习算法，将在一个或多个文档中描述的用户的意见分类为基于感性词典词典中定义的感性词典模式信息的积极意见类或负面意见类别 。
-
公开(公告)号：KR1020130059264A
公开(公告)日：2013-06-05
申请号：KR1020120103970
申请日：2012-09-19
Applicant: 세종대학교산학협력단
Abstract: PURPOSE: A specific organization ranking calculating method is provided to increase reliability of a ranking result about an organization based on social networking service data. CONSTITUTION: Information about a specific organization is collected from a social networking service based on the name and address information of the specific organization(S10). The ranking factor of the specific organization is extracted from the collected information through the social networking service(S20). The ranking of the specific organization is calculated based on the extracted ranking factor(S30). [Reference numerals] (S10) Collect information of the specific organization; (S20) Extract the ranking factor of the specific organization; (S30) Calculate the ranking of the specific organization
Abstract translation: 目的：提供一种特定的组织排名计算方法，以提高基于社交网络服务数据的组织排名结果的可靠性。 规定：根据具体组织的名称和地址信息，从社交网络服务收集有关特定组织的信息（S10）。 通过社交网络服务从收集的信息中提取具体组织的排名因素（S20）。 基于提取的排名因子计算特定组织的排名（S30）。 （附图标记）（S10）收集特定组织的信息; （S20）提取具体组织的排名因子; （S30）计算具体组织的排名
-
公开(公告)号：KR1020130059263A
公开(公告)日：2013-06-05
申请号：KR1020120103930
申请日：2012-09-19
Applicant: 세종대학교산학협력단
CPC classification number: G06Q50/10 , G06F17/2705 , G06F17/30719 , G06K9/00456 , G06Q30/0278
Abstract: PURPOSE: A merchandise seller related script decision method is provided to classify an association degree of a merchandise seller related review by dividing a text and an image in a blog review. CONSTITUTION: A database of a merchandise seller which is searched by inputting a query is collected(S10). A review is extracted from a blog on the web based on the database of the searched merchandise seller(S20). The text of the extracted review is classified(S30). The image of the extracted review is classified(S40). A association degree of a merchandise seller related review is classified into many classes based on the classified text and image(S50). [Reference numerals] (S10) Collect a database of a merchandise seller; (S20) Extract a blog review; (S30) Classify the text of the extracted review; (S40) Classify the image of the review; (S50) Classify an association degree of the review
Abstract translation: 目的：提供商品卖家相关的脚本决策方法，通过在博客评论中划分文本和图像来对商品卖家相关评论的关联度进行分类。 构成：收集通过输入查询搜索的商品卖家的数据库（S10）。 基于所搜索的商品卖家的数据库，从网络上的博客中提取评论（S20）。 提取审查的文本分类（S30）。 提取的审查的图像被分类（S40）。 基于分类文本和图像，将商品卖家相关评论的协会程度分为许多类别（S50）。 （附图标记）（S10）收集商品卖家的数据库; （S20）提取博客评论; （S30）对提取审查的案文进行分类; （S40）分类审查的形象; （S50）分类审查的关联程度
-
公开(公告)号：KR1020100020365A
公开(公告)日：2010-02-22
申请号：KR1020080079117
申请日：2008-08-12
Applicant: 세종대학교산학협력단 , 건국대학교 산학협력단
CPC classification number: G06Q30/0243 , G06Q30/0631
Abstract: PURPOSE: A system for recommending products and a method thereof are provided to improve a recommendation performance by estimating product recommendation preference which is not inputted by other. CONSTITUTION: At least one seller terminal(100a-100m) inputs the product information of a new product, and a registration server(200) registers the product information. At least one customer terminal(300a-300n) create a purchase request signal and a purchase decision signal for the product of the registration server. At least one customer terminal inputs the preference for the decided product, and an other person history recommendation unit(620) recommends the product based on the product preference by the other persons, and a user history recommendation unit(610) recommends the product based on the product information of the purchased product.
Abstract translation: 目的：提供一种推荐产品及其方法的系统，以通过估计不由其他人输入的产品推荐偏好来改善推荐性能。 规定：至少一个卖方终端（100a-100m）输入新产品的商品信息，注册服务器（200）登记产品信息。 至少一个客户终端（300a-300n）为注册服务器的产品创建购买请求信号和购买决定信号。 至少一个客户终端输入对所决定的产品的偏好，而另一个人历史推荐单元（620）基于其他人的产品偏好来推荐产品，并且用户历史推荐单元（610）基于 所购产品的产品信息。
-
-
-
-
-
-
-
Search Results
8
records
(took 0.02 seconds)
