-
公开(公告)号：US11106979B2
公开(公告)日：2021-08-31
申请号：US16021617
申请日：2018-06-28
Applicant: Microsoft Technology Licensing, LLC
Inventor： Rohan Ramanath , Gungor Polatkan , Qi Guo , Cagri Ozcaglar , Krishnaram Kenthapadi , Sahin Cem Geyik
IPC: G06N3/08 , G06N3/04 , G06F16/248 , G06F16/901
Abstract: Techniques for implementing a learning semantic representations of sparse entities using unsupervised embeddings are disclosed herein. In some embodiments, a computer system accesses corresponding profile data of users indicating at least one entity of a first facet type associated with the user, and generating a graph data structure comprising nodes and edges based on the accessed profile data, with each node corresponding to a different entity indicated by the accessed profile data, and each edge directly connecting a different pair of nodes and indicating a number of users whose profile data indicates both entities of the pair of nodes. The computer system generating a corresponding embedding vector for the entities based on the graph data structure using an unsupervised machine learning algorithm.
-
公开(公告)号：US10902070B2
公开(公告)日：2021-01-26
申请号：US15379676
申请日：2016-12-15
Applicant: Microsoft Technology Licensing, LLC
Inventor： Krishnaram Kenthapadi , Kaushik Rangadurai , Bo Zhao
IPC: G06Q10/10 , G06F16/9535 , H04L29/08 , G06F16/9038 , G06Q50/00 , G06Q50/20
Abstract: Methods, systems, and computer programs are presented for searching job postings for a member of a social network based on transitions from educational institutions to companies. A method includes determining educational-company transition scores indicating a transition probability from educational institution to company. The method identifies jobs based on a search performed for a first member, with a profile including one or more educational institutions, each job associated with a respective company. A server determines a member-company transition score based on the educational-company transition scores of the educational institutions in the profile. For each job, a job affinity score is determined based on data of the job and the profile of the first member. The server ranks the jobs based on the member-company transition score of the company of the job and the job affinity score. Some of the ranked jobs are presented to the first member based on the ranking.
-
公开(公告)号：US10679187B2
公开(公告)日：2020-06-09
申请号：US15419174
申请日：2017-01-30
Applicant: Microsoft Technology Licensing, LLC
Inventor： Krishnaram Kenthapadi , Kaushik Rangadurai
IPC: G06Q10/00 , G06Q10/10 , G06Q50/00 , G06F7/02 , G06F16/9535
Abstract: Methods, systems, and computer programs are presented for grouping job postings for presentation to a user in response to a search. A method includes determining the closest-matching groups of jobs for a user and presenting a display such that the closest-matching jobs are viewable within the groups. For each group, a server determines a group affinity based on a group characteristic and a user characteristic and affinities of jobs for that group based on the job postings and the group characteristic. The server ranks the groups for the user based on the group affinity score for each group, and ranks the job postings within each group based on the jobs affinity to the user. Some of the groups and job postings are presented to the user based on the ranking.
-
公开(公告)号：US10558923B1
公开(公告)日：2020-02-11
申请号：US15371874
申请日：2016-12-07
Applicant: Microsoft Technology Licensing, LLC
Inventor： Krishnaram Kenthapadi , Stuart MacDonald Ambler , Edoardo M. Airoldi
Abstract: In an example, one or more member profiles and corresponding Boolean attributes indicating, for each of the one or more member profiles, whether the corresponding member of a social networking service interacted with a request for confidential data, are obtained. A first set of one or more features are extracted from the one or more member profiles. The first set of one or more features and corresponding Boolean attributes are fed into a machine learning algorithm to train a confidential data response propensity prediction model to output a predicted propensity to interact with a request for confidential data for a candidate member profile. A second set of one or more features are extracted from the candidate member profile. The extracted second set of one or more features are fed to the confidential data response propensity prediction model, outputting the predicted propensity to interact with a request for confidential data.
-
公开(公告)号：US10552741B1
公开(公告)日：2020-02-04
申请号：US15401728
申请日：2017-01-09
Applicant: Microsoft Technology Licensing, LLC
Inventor： Krishnaram Kenthapadi , Stuart MacDonald Ambler , Liang Zhang , Deepak Agarwal
Abstract: In an example, a set of cohort types and an anonymized set of confidential data data values for a plurality of cohorts having cohort types in the set of cohort types are obtained. Then it is determined, from a set of candidate data transformations, a best fitting data transformation for the anonmyized set of confidential data data values. The anonymized set of confidential data data values is transformed using the best fitting data transformation. Optimal smoothing parameters are computed for each cohort type. Then, for each cohort in the set of cohort types having a small sample size, a best parent for the cohort is determined and a posterior distribution for the cohort is determined based on the best parent for the cohort and the optimal smoothing parameters for a cohort type for the cohort.
-
Patent Agency Ranking
公开(公告)号：US20200005134A1
公开(公告)日：2020-01-02
申请号：US16021654
申请日：2018-06-28
Applicant: Microsoft Technology Licensing, LLC
Inventor： Rohan Ramanath , Gungor Polatkan , Qi Guo , Cagri Ozcaglar , Krishnaram Kenthapadi , Sahin Cem Geyik
Abstract: Techniques for generating supervised embedding representations using unsupervised embedding representations and deep semantic structured models for search are disclosed herein. In some embodiments, a computer system generates a graph data structure based on accessed profile data, generates an initial embedding vector using an unsupervised machine learning algorithm, receiving training data comprising query representations, search result representations, and user actions, with each one of the plurality of query representations comprising the initial embedding vector, and generates a final embedding vector using a supervised learning algorithm and the received training data.
-
公开(公告)号：US10318757B1
公开(公告)日：2019-06-11
申请号：US15338768
申请日：2016-10-31
Applicant: Microsoft Technology Licensing, LLC
Inventor： Krishnaram Kenthapadi , Stuart MacDonald Ambler
IPC: G06F21/62 , G06F16/22 , G06F16/2457
Abstract: In an example, a query on a plurality of previously submitted confidential data values for a first cohort having one or more attributes is obtained, and a level in a hierarchy corresponding to an attribute type for the attribute is determined for each attribute. One or more additional cohorts corresponding to different combinations of generalizations of the one or more attributes up one or more levels in each hierarchy corresponding to an attribute type for each attribute are formed. For each cohort, a confidence score and a granularity score are calculated, and then a cohort score is calculated based on a weighted combination of the confidence score and the granularity score. A statistical function is performed on previously submitted confidential data values for a cohort having the highest cohort score, and a response to the query including a result from the statistical function is formed.
-
8.发明授权公开(公告)号：US10262154B1
公开(公告)日：2019-04-16
申请号：US15618554
申请日：2017-06-09
Applicant: Microsoft Technology Licensing, LLC
Inventor： Krishnaram Kenthapadi , Stuart MacDonald Ambler
Abstract: In an example embodiment, an anonymized set of confidential data values is obtained for a plurality of combinations of cohorts having a first attribute type and a second attribute type. A matrix of the confidential data values having the first attribute type as a first axis and the second attribute type as the second axis is constructed. A set of candidate low rank approximations of the matrix is calculated using an objective function evaluated using a set of candidate data transformation functions, the objective function having one or more parameters and an error function. One or more parameters that minimize the error function of the objective function are minimized to select one of the candidate low rank approximations of the matrix. Then one or more cells that are missing data, of the selected one of the candidate low rank approximations of the matrix, are inferred.
-
公开(公告)号：US10261971B2
公开(公告)日：2019-04-16
申请号：US15164626
申请日：2016-05-25
Applicant: Microsoft Technology Licensing, LLC
Inventor： Krishnaram Kenthapadi , Huan Van Hoang
IPC: G06F16/958 , G06F16/9535 , H04L29/08 , G06F16/2457
Abstract: An on-line social network system includes or is in communication with a search engine optimization (SEO) system that is configured to partition a number of available links from authoritative web pages to Job Search Results Rages (JSERPs) in a way that maximizes combined improvement in respective ranks generated by a third party search engine for JSERPs represented by keywords from the set of keywords.
-
公开(公告)号：US20190065612A1
公开(公告)日：2019-02-28
申请号：US15685394
申请日：2017-08-24
Applicant: Microsoft Technology Licensing, LLC
Inventor： Krishnaram Kenthapadi , Fedor Vladimirovich Borisyuk , Parul Jain
Abstract: A machine may be configured to identify top jobs for a member of a social networking service (SNS) based on a universal concept graph. For example, the machine accesses a first record that identifies a universal concept graph. The machine accesses a second record that identifies a first induced concept graph associated with a member profile of a member of the SNS. The machine identifies a numerical value that represents a desired number of job descriptions. The machine generates, for a job description, a similarity value based on the first induced concept graph and a second induced concept graph associated with the job description. The similarity value represents a degree of similarity between the member profile and the job description. The machine causes a presentation of identifiers of job descriptions in a user interface based on the numerical value and the similarity values associated with the identifiers of job descriptions.
-
-
-
-
-
-
-
-
-
Search Results
73
records
(took 0.03 seconds)
