专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明申请

US20120283956A1 METHOD AND SYSTEM FOR PREDICTING SELECTIVE CANCER DRUG TARGETS 审中-公开
标题翻译：用于预测选择性癌症药物目标的方法和系统
公开(公告)号：US20120283956A1
公开(公告)日：2012-11-08
申请号：US13410950
申请日：2012-03-02
申请人： Eytan RUPPIN , Tomer Shlomi , Ori Folger , Eyal Gottlieb , Christian Frezza
发明人： Eytan RUPPIN , Tomer Shlomi , Ori Folger , Eyal Gottlieb , Christian Frezza
IPC分类号： G06F19/26
CPC分类号： G16B5/00 , G06F17/11 , G16B20/00
摘要： A method for creating a metabolic map of metabolic reactions by selecting metabolic reactions active in cancer cells. A core set of metabolic reactions occurring in the cancer cells is designated. For each permutation, whether inhibition of the k-th non-core reaction together with inhibition of all previously deleted non-core reactions results in inhibition of any of the core reactions or results in inhibition of the flux of biomass metabolites to biomass is determined. If inhibition of the k-th non-core reaction and inhibition of all previously deleted non-core reactions does not result in inhibition of any core reactions and does not result in inhibition of the flux of biomass metabolites to biomass, then the k-th non-core reaction is deleted from the set of non-core reactions. The number of permutations for which the k-th non-core reaction is not deleted is determined and a metabolic map is then created based on that number.
摘要翻译：通过选择在癌细胞中活跃的代谢反应来产生代谢反应代谢图的方法。指定在癌细胞中发生的核心代谢反应。对于每个排列，确定第k个非核心反应的抑制以及所有先前删除的非核心反应的抑制是否导致抑制任何核心反应或导致生物质代谢物对生物量的通量的抑制。如果第k次非核心反应的抑制和所有先前删除的非核心反应的抑制不会导致任何核心反应的抑制，并且不会导致生物质代谢物的通量对生物量的抑制，则第k 非核心反应从一组非核心反应中删除。确定不删除第k个非核心反应的排列数，然后基于该数量创建代谢图。

2. 发明申请

US20170024765A1 ADAPTIVE USER SUGGESTIONS IN A SOCIAL NETWORKING SERVICE 审中-公开
标题翻译：社区网络服务中的自适应用户建议
公开(公告)号：US20170024765A1
公开(公告)日：2017-01-26
申请号：US13610748
申请日：2012-09-11
申请人： Tzvi Itzhak BARENHOLZ , Oded Poncz , Ari Leichtberg , Ori Folger , Roman Gershman , Eyal Molad , Hilly Meerovitch
发明人： Tzvi Itzhak BARENHOLZ , Oded Poncz , Ari Leichtberg , Ori Folger , Roman Gershman , Eyal Molad , Hilly Meerovitch
IPC分类号： G06F15/16
CPC分类号： G06Q30/0255
摘要： In one aspect, the present disclosure can be embodied in a method that includes providing item recommendations for display to a user of a social networking service based on the user's responses (or lack thereof) to recommendations that were previously displayed or viewed by the user. A score is calculated for each item recommendation based on whether the item recommendation was displayed during a predetermined time period but implicitly rejected by the user. The scores assigned to the respective item recommendations are used to select additional item recommendations for display.
摘要翻译：在一个方面，本公开可以体现在一种方法中，所述方法包括根据用户对先前由用户显示或观看的推荐的响应（或缺少）向社交网络服务的用户提供用于显示的项目建议。基于项目建议是否在预定时间段期间显示而被用户隐含地拒绝，针对每个项目推荐计算分数。分配给各个项目建议的分数用于选择附加项目建议进行显示。

3. 发明授权

US09208155B2 Adaptive recommendation system 有权
标题翻译：自适应推荐系统
公开(公告)号：US09208155B2
公开(公告)日：2015-12-08
申请号：US13229482
申请日：2011-09-09
申请人： Nir Nice , Dror Kremer , Daniel Sitton , Michael Feldman , Shimon Shlevich , Ori Folger
发明人： Nir Nice , Dror Kremer , Daniel Sitton , Michael Feldman , Shimon Shlevich , Ori Folger
IPC分类号： G06N5/04 , G06F17/30 , G06Q30/02 , G06Q30/06
CPC分类号： G06F17/30029 , G06N5/04 , G06Q30/0255 , G06Q30/0631
摘要： A recommendation system for optimizing content recommendation lists is disclosed. The system dynamically tracks a list interaction history of a user, which details that user's interactions with a plurality of different lists presenting different recommended items to that user. The system automatically correlates one or more list preferences with that user based on the list interaction history, and builds a recommendation list with a plurality of candidate items having different recommendation confidences. The recommendation list is built such that each candidate item with a higher recommendation confidence is prioritized over each candidate item with a lower recommendation confidence according to the one or more list preferences correlated to that user.
摘要翻译：公开了一种优化内容推荐列表的推荐系统。系统动态地跟踪用户的列表交互历史，其详细描述了用户与向该用户呈现不同推荐项目的多个不同列表的交互。该系统基于列表交互历史自动地将一个或多个列表偏好与该用户相关联，并且建立具有不同推荐信息的多个候选项目的推荐列表。构建推荐列表，使得根据与该用户相关联的一个或多个列表偏好，具有较高建议置信度的每个候选项优先于具有较低建议置信度的每个候选项。

4. 发明申请

US20130218907A1 RECOMMENDER SYSTEM 审中-公开
标题翻译：推荐系统
公开(公告)号：US20130218907A1
公开(公告)日：2013-08-22
申请号：US13400581
申请日：2012-02-21
申请人： Nir Nice , Shahar Keren , Ori Folger , Ulrich Paquet , Shimon Shlevich , Noam Koenigstein , Eylon Yogev
发明人： Nir Nice , Shahar Keren , Ori Folger , Ulrich Paquet , Shimon Shlevich , Noam Koenigstein , Eylon Yogev
IPC分类号： G06F17/30
CPC分类号： G06F16/435
摘要： Embodiments of the invention provide methods and apparatus for recommending items from a catalog of items to users in a population of users by generating trait vectors that represent items in the catalog responsive to explicit and/or implicit preference data for a group of less than all the users and using the trait vectors to recommend items to users in the population that are not in the group.
摘要翻译：本发明的实施例提供方法和装置，用于通过产生表示目录中的项目的特征向量来响应于对于少于所有这些的一组的显式和/或隐性偏好数据来从项目目录向用户的目录推荐项目用户并使用特征向量向不在组中的群体中的用户推荐项目。

5. 发明申请

US20130066819A1 ADAPTIVE RECOMMENDATION SYSTEM 有权
标题翻译：自适应推荐系统
公开(公告)号：US20130066819A1
公开(公告)日：2013-03-14
申请号：US13229482
申请日：2011-09-09
申请人： Nir Nice , Dror Kremer , Daniel Sitton , Michael Feldman , Shimon Shlevich , Ori Folger
发明人： Nir Nice , Dror Kremer , Daniel Sitton , Michael Feldman , Shimon Shlevich , Ori Folger
IPC分类号： G06F15/18
CPC分类号： G06F17/30029 , G06N5/04 , G06Q30/0255 , G06Q30/0631
摘要： A recommendation system for optimizing content recommendation lists is disclosed. The system dynamically tracks a list interaction history of a user, which details that user's interactions with a plurality of different lists presenting different recommended items to that user. The system automatically correlates one or more list preferences with that user based on the list interaction history, and builds a recommendation list with a plurality of candidate items having different recommendation confidences. The recommendation list is built such that each candidate item with a higher recommendation confidence is prioritized over each candidate item with a lower recommendation confidence according to the one or more list preferences correlated to that user.
摘要翻译：公开了一种优化内容推荐列表的推荐系统。系统动态地跟踪用户的列表交互历史，其详细描述了用户与向该用户呈现不同推荐项目的多个不同列表的交互。该系统基于列表交互历史自动地将一个或多个列表偏好与该用户相关联，并且建立具有不同推荐信息的多个候选项目的推荐列表。构建推荐列表，使得根据与该用户相关联的一个或多个列表偏好，具有较高建议置信度的每个候选项优先于具有较低建议置信度的每个候选项。

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式