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。

公开(公告)号：US20190050750A1

公开(公告)日：2019-02-14

申请号：US15674968

申请日：2017-08-11

申请人： Linkedln Corporation

发明人： Benjamin Hoan Le ,  Saurabh Kataria ,  Nadia Fawaz ,  Aman Grover ,  Guoyin Wang

IPC分类号： G06N99/00 ,  G06N3/08 ,  G06F17/30 ,  H04L29/08 ,  G06Q10/10 ,  G06F3/0482

摘要： In an example, features in a boosting decision tree model are initialized to zero, the boosting decision tree model located in a GLMM and connected to a deep neural network collaborative filtering model via a prediction layer. While the features in the boosting decision tree model remain zero, the deep neural network collaborative filtering model is trained. One or more trees in the boosting decision tree model are boosted using logits produced by the training of the deep neural network collaborative filtering model as a margin. The prediction layer is trained using features from the deep neural network collaborative filtering model and features from the boosting decision tree model. It is then determined whether a set of convergence criteria is met. If not, then the deep neural network collaborative filtering model is retrained using the features and the process is repeated until the set of convergence criteria is met.

公开(公告)号：US20180173803A1

公开(公告)日：2018-06-21

申请号：US15379656

申请日：2016-12-15

申请人： Linkedln Corporation

发明人： Aman Grover ,  Dhruv Arya ,  Ganesh Venkataraman ,  Kimberly McManus ,  Liang Zhang

IPC分类号： G06F17/30 ,  H04L29/08 ,  G06Q10/10 ,  G06N99/00 ,  G06N7/00

CPC分类号： G06F16/9535 ,  G06F16/24578 ,  G06F16/248 ,  G06N20/00 ,  G06Q10/1053 ,  G06Q50/01 ,  H04L67/306

摘要： Methods, systems, and computer programs are presented for expanding a job search that includes an industry by adding other similar industries. A method accesses, by a social networking server, a plurality of job applications, with each job application being submitted by a member for a job in a company, the member and the job having a respective industry from a plurality of industries. Semantic analysis of the job applications is performed by a machine-learning program to identify similarity coefficients among the plurality of industries. A job search query is received from a first member, the job search query including a query industry, and the job search query is expanded with industries that are similar to the query industry. The social networking server executes the expanded job search query to generate a plurality of job results. Presentation is provided on a display of one or more of the top job results.

公开(公告)号：US20170315676A1

公开(公告)日：2017-11-02

申请号：US15141090

申请日：2016-04-28

申请人： Linkedln Corporation

发明人： Siyu You ,  Aman Grover ,  Christos Koufogiannakis ,  Manoj Rameshchandra Thakur

IPC分类号： G06F3/0481 ,  H04L12/26 ,  H04L29/08

CPC分类号： G06F16/35 ,  G06F16/958 ,  G06F16/972 ,  G06F17/2247 ,  G06F17/248 ,  G06Q30/0241 ,  G06Q30/0251 ,  G06Q30/0277 ,  G06Q50/01 ,  H04L67/02 ,  H04L67/306

摘要： Methods and systems for selecting candidate content for insertion into a content presentation to generate tailored user interface screens are described. According to various embodiments, the system receives a set of publication data including a plurality of content pages with content elements. The system determines a set of content divisions among the content pages and one or more insertion points corresponding to one or more content divisions. The system determines a set of candidate insertion content based on the set of content elements and the insertion points. The system causes presentation of the set of publication data including the plurality of content pages. Upon presentation of a content page proximate to an insertion point, the system selects a candidate insertion content item for insertion into the insertion point and causes presentation of the candidate insertion content during presentation of the set of publication data.