公开(公告)号：US20170091692A1

公开(公告)日：2017-03-30

申请号：US14929128

申请日：2015-10-30

申请人： Linkedln Corporation

发明人： Songtao Guo ,  Ke Wang ,  Alex Ching Lai ,  Aarti Kumar ,  Keith Wai Kit Tsang ,  Rekha Thakur ,  Song Lin ,  Christopher Matthew Degiere

IPC分类号： G06Q10/06 ,  G06Q50/00 ,  H04L29/08

摘要： In an example embodiment, a member profile corresponding to a member of a social networking service is obtained. Usage information for the member is then obtained, and one or more member metrics are calculated based on the member profile and usage information for the corresponding member. A plurality of features are extracted from the member profile and the one or more member metrics. The plurality of features is inserted into an organization name confidence score model to obtain a confidence score for an organization name in the member profile.

公开(公告)号：US20170091270A1

公开(公告)日：2017-03-30

申请号：US14929109

申请日：2015-10-30

申请人： Linkedln Corporation

发明人： Songtao Guo ,  Christopher Matthew Degiere ,  Aarti Kumar ,  Alex Ching Lai ,  Xian Li

IPC分类号： G06F17/30 ,  G06N99/00

CPC分类号： G06K9/00456 ,  G06F16/215 ,  G06F16/24534 ,  G06F16/24544 ,  G06F16/285 ,  G06F16/58 ,  G06F16/5838 ,  G06F16/5854 ,  G06F16/9024 ,  G06F16/951 ,  G06K9/00469 ,  G06K9/46 ,  G06K9/6215 ,  G06K9/6256 ,  G06K9/6263 ,  G06K9/6276 ,  G06K2209/25 ,  G06N5/003 ,  G06N7/005 ,  G06N7/02 ,  G06N20/00 ,  G06N20/20 ,  G06Q10/06393 ,  G06Q10/10 ,  G06Q50/01 ,  H04L67/10 ,  H04L67/306 ,  Y04S10/54

摘要： In an example embodiment, an organization name is retrieved from an organization name field of a first record. A web search is performed using the organization name, producing web search results. A second plurality of features is extracted for each web search result in the set of web search results. Each of the extracted second plurality of features for each web search result in the set of web search results is input into a supervised machine learning classifier to classify each of the web search results in the set of web search results as either containing an organization web address or not containing an organization web address. In response to a determination by the supervised machine learning classifier that a first web search result contains an organization web address, the organization web address from the first web search result is injected into an organization web address field of the first record.

公开(公告)号：US20170032324A1

公开(公告)日：2017-02-02

申请号：US14814405

申请日：2015-07-30

申请人： Linkedln Corporation

发明人： Aman Grover ,  Siyu You ,  Krishnaram Kenthapadi ,  Parul Jain ,  Fedor Vladimirovich Borisyuk ,  Christopher Matthew Degiere ,  Songtao Guo

IPC分类号： G06Q10/10 ,  G06Q50/00 ,  G06Q50/20

CPC分类号： G06Q10/1053 ,  G06Q50/01 ,  G06Q50/2057

摘要： In an example embodiment, a method is provided where information regarding a member of a social networking service and a job opening are obtained. Then information about a plurality of courses available for the member to take is obtained, the information including cost, time, and a vector including, for each of a plurality of skills identified in a member profile of the member, an effect of taking the corresponding course. A subset selection algorithm is then used to select an optimal combination of courses selected from the plurality of courses, based on minimizing cost and time while maximizing cumulative increase in odds of the member successfully obtaining the job opening from taking the selected courses.

摘要翻译： 在一个示例性实施例中，提供了一种获得关于社交网络服务和作业打开的成员的信息的方法。 然后，获得关于成员可以使用的多个课程的信息，包括成本，时间和向量的信息，对于在成员的成员简档中识别的多个技能中的每一个，包括采用相应的 课程。 然后，使用子集选择算法来选择从多个课程中选择的课程的最佳组合，其基于最小化成本和时间，同时最大化成员从获取所选课程成功地获得工作开始的可能性的累积增加。