Patents by Inventor Viet Thuc Ha

Viet Thuc Ha has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).

  • Patent number: 10380553
    Abstract: In an example, a plurality of member profiles in a social networking service are obtained, each member profile identifying a member and listing one or more skills the corresponding member has explicitly added to the member profile, the one or more skills indicating a proficiency by the member in the corresponding skill. A members-skills matrix is formed, wherein each cell in the matrix is assigned a value based on whether the corresponding member has the corresponding skill. The dot product of the members matrix and the skills matrix is then computed and used to identify one or more latent skills of a first member of the social networking service. Then a first digitally stored member profile is augmented with the one or more latent skills by combining the one or more latent skills with explicit skills for purposes of one or more searches that utilize member skills as an input variable.
    Type: Grant
    Filed: April 14, 2017
    Date of Patent: August 13, 2019
    Assignee: Microsoft Technology Licensing, LLC
    Inventors: Jia Li, Dhruv Arya, Shakti Dhirendraji Sinha, Viet Thuc Ha, Deepak Agarwal
  • Patent number: 10373075
    Abstract: In an example embodiment, a query for search results is received, the query including at least one value for one facet, a facet defining a categorical dimension for the search results. It is then determined that the facet in the query is exclusive. In response to the determination that the facet is exclusive: for each potential facet different from the facet in the query: for each potential value in the potential facet: conditional entropy gain of the value in the query and the potential value is determined. The potential value in the potential facet that has the highest conditional entropy gain is determined, as is the potential facet with the minimum maximum conditional entropy gain. Then the potential facet with the minimum maximum is input into a machine learning model, causing the machine learning model to output one or more suggested facets to add to the query.
    Type: Grant
    Filed: June 21, 2016
    Date of Patent: August 6, 2019
    Assignee: Microsoft Technology Licensing, LLC
    Inventors: Xianren Wu, Satya Pradeep Kanduri, Vijay Dialani, Ye Xu, Yan Yan, Viet Thuc Ha, Abhishek Gupta, Shakti Dhirendraji Sinha
  • Patent number: 9946799
    Abstract: Apparatuses, computer readable medium, and methods are disclosed for federated search page construction based on machine learning. The method may include receiving a search query submitted by a searcher and submitting the search query to a plurality of sources of information to generate a plurality of search results. The method may further include ranking the plurality of search results based on historical search data and selecting a primary search result and a secondary search result of the plurality of search results based on the ranking. The method may further include constructing a federated search results page with a first portion of the first search results positioned first, a cluster of the second search result positioned second, and a second portion of the first search results positioned third. The method may include causing the federated search results page to be displayed to the searcher.
    Type: Grant
    Filed: June 29, 2015
    Date of Patent: April 17, 2018
    Assignee: Microsoft Technology Licensing, LLC
    Inventors: Dhruv Arya, Viet Thuc Ha, Shakti Dhirendraji Sinha
  • Publication number: 20170364596
    Abstract: In an example embodiment, a query for search results is received, the query including at least one value for one facet, a facet defining a categorical dimension for the search results. It is then determined that the facet in the query is exclusive. In response to the determination that the facet is exclusive: for each potential facet different from the facet in the query: for each potential value in the potential facet: conditional entropy gain of the value in the query and the potential value is determined. The potential value in the potential facet that has the highest conditional entropy gain is determined, as is the potential facet with the minimum maximum conditional entropy gain. Then the potential facet with the minimum maximum is input into a machine learning model, causing the machine learning model to output one or more suggested facets to add to the query.
    Type: Application
    Filed: June 21, 2016
    Publication date: December 21, 2017
    Inventors: Xianren Wu, Satya Pradeep Kanduri, Vijay Dialani, Ye Xu, Yan Yan, Viet Thuc Ha, Abhishek Gupta, Shakti Dhirendraji Sinha
  • Publication number: 20170344554
    Abstract: In an example embodiment, one or more ideal candidate member profiles in a social networking service are obtained. Then a search is performed on member profiles in the social networking service using a search query, returning one or more result member profiles. One or more query-based features are produced from the one or more result member profiles using the search query. One or more ideal candidate-based features are produced from the one or more result member profiles using the one or more ideal candidate member profiles. The one or more query-based features and the one or more ideal candidate-based features are input to a combined ranking model trained by a machine learning algorithm to output a ranking score for each of the one or more result member profiles. The one or more result member profiles are then ranked based on the ranking scores.
    Type: Application
    Filed: May 31, 2016
    Publication date: November 30, 2017
    Inventors: Viet Thuc Ha, Yan Yan, Xianren Wu, Satya Pradeep Kanduri, Vijay Dialani, Ye Xu, Abhishek Gupta, Shakti Dhirendraji Sinha
  • Publication number: 20170344556
    Abstract: In an example embodiment, as time goes on and as refinements are received to an online search, weights assigned to each of the one or more query-based features are dynamically trained to increase as more refinements are received and weights assigned to each of the one or more ideal candidate-based features to decrease as more refinements are received.
    Type: Application
    Filed: May 31, 2016
    Publication date: November 30, 2017
    Inventors: Xianren Wu, Ye Xu, Satya Pradeep Kanduri, Vijay Dialani, Yan Yan, Viet Thuc Ha, Abhishek Gupta, Shakti Dhirendraji Sinha
  • Publication number: 20170344954
    Abstract: In an example embodiment, one or more specified ideal candidates are used to perform a search in a database. One or more attributes are extracted from one or more ideal candidate member profiles. A search query is then generated based on the extracted one or more attributes. Then, a search is performed on member profiles in the social networking service using the generated search query, returning one or more result member profiles.
    Type: Application
    Filed: May 31, 2016
    Publication date: November 30, 2017
    Inventors: Ye Xu, Viet Thuc Ha, Xianren Wu, Satya Pradeep Kanduri, Vijay Dialani, Yan Yan, Abhishek Gupta, Shakti Dhirendraji Sinha
  • Publication number: 20170344555
    Abstract: In an example embodiment, one or more sample ideal candidate member profiles in a social networking service are obtained, as well as one or more sample search result member profiles in the social networking service. Then, for each unique pair of sample ideal candidate member profile and sample search result member profile, a label is generated using a score generated from log information of the social networking service, the log information including records of communications between a searcher and members of the social networking service, the score being higher if the searcher communicated with both the member corresponding sample ideal candidate member profile and the member corresponding to the sample search result member profile in a same search session. The generated labels are fed into a machine learning algorithm to train a combined ranking model used to output ranking scores for search result member profiles.
    Type: Application
    Filed: May 31, 2016
    Publication date: November 30, 2017
    Inventors: Yan Yan, Viet Thuc Ha, Xianren Wu, Satya Pradeep Kanduri, Vijay Dialani, Ye Xu, Abhishek Gupta, Shakti Dhirendraji Sinha
  • Patent number: 9760610
    Abstract: A system and method for personalized search user searcher features may include obtaining a search term from a member of a social network at a user device via the network interface. An initial result may be generated based on the search term, including a first group of content items from a social network and stored in a content database, the content items including member profiles of members of the social network. Each of the content items of the first group may be ranked based on information indicative of interactions from an activity database with the content items of the first group, the interactions being by at least a second user of the social network different than the first user. A second group of the content items may be displayed, including at least some of the first group of the content items, based on the rank of the first group of the content items.
    Type: Grant
    Filed: November 12, 2014
    Date of Patent: September 12, 2017
    Assignee: LinkedIn Corporation
    Inventors: Shakti Dhirendraji Sinha, Asif Mansoor Ali Makhani, Viet Thuc Ha, Lin Guo, Senthil Sundaram
  • Patent number: 9734210
    Abstract: A system and method for personalized search based on searcher interest may include obtaining a search term from a member of a social network at a user device via the network interface. An initial result may be generated based on the search term, including a first group of content items from a social network and stored in a content database, the content items including member profiles of members of the social network. Each of the content items of the first group may be ranked based on information from an activity database, the activity database storing the information related to the social network, the activities including interactions with search results that include ones of the member profiles. A second group of the content items may be displayed, including at least some of the first group of the content items, based on the rank of the first group of the content items.
    Type: Grant
    Filed: November 12, 2014
    Date of Patent: August 15, 2017
    Assignee: LinkedIn Corporation
    Inventors: Shakti Dhirendraji Sinha, Asif Mansoor Ali Makhani, Viet Thuc Ha, Lin Guo, Ramesh Dommeti, Senthil Sundaram, Ganesh Venkataraman
  • Publication number: 20170221008
    Abstract: In an example, a plurality of member profiles in a social networking service are obtained, each member profile identifying a member and listing one or more skills the corresponding member has explicitly added to the member profile, the one or more skills indicating a proficiency by the member in the corresponding skill. A members-skills matrix is formed, wherein each cell in the matrix is assigned a value based on whether the corresponding member has the corresponding skill. The dot product of the members matrix and the skills matrix is then computed and used to identify one or more latent skills of a first member of the social networking service. Then a first digitally stored member profile is augmented with the one or more latent skills by combining the one or more latent skills with explicit skills for purposes of one or more searches that utilize member skills as an input variable.
    Type: Application
    Filed: April 14, 2017
    Publication date: August 3, 2017
    Inventors: Jia Li, Dhruv Arya, Shakti Dhirendraji Sinha, Viet Thuc Ha, Deepak Agarwal
  • Publication number: 20170177579
    Abstract: In an example embodiment, usage information is used to calculate one or more individual document historical information-deficient metrics (IDHIDMs) by combining values for the one or more metrics from multiple documents within the document corpus that share an identical combination of entities of the one or more entity types. A search query is segmented into a plurality of segments, wherein at least one of the plurality of segments is tagged as a first entity type and at least one of the plurality of segments is tagged as a second entity type. At least one IDHIDM for a combination of entities matching the tagged segments is used to rank one or more retrieved documents responsive to the query.
    Type: Application
    Filed: December 18, 2015
    Publication date: June 22, 2017
    Applicant: Linkedln Corporation
    Inventors: Jia Li, Dhruv Arya, Shakti Dhirendraji Sinha, Viet Thuc Ha, Deepak Agarwal
  • Patent number: 9639827
    Abstract: In an example embodiment, a plurality of member profiles in a social networking service are obtained, each member profile identifying a member and listing one or more skills the corresponding member has explicitly added to the member profile, the one or more skills indicating a proficiency by the member in the corresponding skill. A members-skills matrix is formed with members on one axis of the matrix and skills on another axis of the matrix, wherein each cell in the matrix is assigned a first value if the corresponding member explicitly lists the corresponding skill in the corresponding member profile and a second value if the corresponding member does not explicitly list the corresponding skill in the corresponding member profile. The members-skills matrix is factorized into a members matrix and a skills matrix in k-dimensional latent space, and then the dot product of the members matrix and the skills matrix is computed.
    Type: Grant
    Filed: December 18, 2015
    Date of Patent: May 2, 2017
    Assignee: LinkedIn Corporation
    Inventors: Jia Li, Dhruv Arya, Shakti Dhirendraji Sinha, Viet Thuc Ha, Deepak Agarwal
  • Publication number: 20160321367
    Abstract: Apparatuses, computer readable medium, and methods are disclosed for federated search page construction based on machine learning. The method may include receiving a search query submitted by a searcher and submitting the search query to a plurality of sources of information to generate a plurality of search results. The method may further include ranking the plurality of search results based on historical search data and selecting a primary search result and a secondary search result of the plurality of search results based on the ranking. The method may further include constructing a federated search results page with a first portion of the first search results positioned first, a cluster of the second search result positioned second, and a second portion of the first search results positioned third. The method may include causing the federated search results page to be displayed to the searcher.
    Type: Application
    Filed: June 29, 2015
    Publication date: November 3, 2016
    Inventors: Dhruv Arya, Viet Thuc Ha, Shakti Dhirendraji Sinha
  • Publication number: 20160314477
    Abstract: A system, method, and apparatus are provided for identifying entities trending within a professional community, such as member of a professional social network. The system collects “share” activity and/or other types of activities conducted by members of the community in which they generate or disseminate (textual) content. From the collected share activity, trending terms are identified and ranked according to scores that reflect the change in frequency of usage of the terms over time. The most relevant shares for each trending term are identified and used to identify names of entities that correspond to (e.g., include) the terms. Reasons indicating why each trending entity is trending are also derived from the share activity. A display or presentation is provided of top trending entities, within one or more segments of the professional community, which includes the reasons and allows a viewer to quickly identify the reason a given entity is trending.
    Type: Application
    Filed: April 27, 2015
    Publication date: October 27, 2016
    Applicant: LinkedIn Corporation
    Inventor: Viet Thuc Ha
  • Patent number: 9330125
    Abstract: The disclosed embodiments provide a reputation system. The reputation system includes a ranking apparatus that obtains a set of reputation scores for one or more dimensions of a set of items in the reputation system and generates a ranking of the items based on the reputation scores and the one or more quantiles. The reputation system also includes a query-processing apparatus that obtains a query comprising the one or more dimensions and one or more quantiles associated with the one or more dimensions and provides the ranking in a response to the query.
    Type: Grant
    Filed: April 23, 2015
    Date of Patent: May 3, 2016
    Assignee: LinkedIn Corporation
    Inventors: Mario S. Rodriguez, Viet Thuc Ha, Jessica V. Zuniga, Mathieu Bastian, Michael Conover
  • Publication number: 20160034464
    Abstract: A system and method for personalized search based on searcher interest may include obtaining a search term from a member of a social network at a user device via the network interface. An initial result may be generated based on the search term, including a first group of content items from a social network and stored in a content database, the content items including member profiles of members of the social network. Each of the content items of the first group may be ranked based on information from an activity database, the activity database storing the information related to the social network, the activities including interactions with search results that include ones of the member profiles. A second group of the content items may be displayed, including at least some of the first group of the content items, based on the rank of the first group of the content items.
    Type: Application
    Filed: November 12, 2014
    Publication date: February 4, 2016
    Inventors: Shakti Dhirendraji Sinha, Asif Mansoor Ali Makhani, Viet Thuc Ha, Lin Guo, Ramesh Dommeti, Senthil Sundaram, Ganesh Venkataraman
  • Publication number: 20160034466
    Abstract: A system and method for personalized search user searcher features may include obtaining a search term from a member of a social network at a user device via the network interface. An initial result may be generated based on the search term, including a first group of content items from a social network and stored in a content database, the content items including member profiles of members of the social network. Each of the content items of the first group may be ranked based on information indicative of interactions from an activity database with the content items of the first group, the interactions being by at least a second user of the social network different than the first user. A second group of the content items may be displayed, including at least some of the first group of the content items, based on the rank of the first group of the content items.
    Type: Application
    Filed: November 12, 2014
    Publication date: February 4, 2016
    Inventors: Shakti Dhirendraji Sinha, Asif Mansoor Ali Makhani, Viet Thuc Ha, Lin Guo, Senthil Sundaram
  • Publication number: 20150347974
    Abstract: A system includes a database, a network interface, and a processor. The database includes, for each multiple users of a social network, profile data and activities, by the user, related to the social network. The network interface is configured to be communicatively coupled to user devices associated with the population of users. The processor is configured to obtain a recruitment search query for a position in an organization, compare the recruitment search query against the profile data of at least some of the users to obtain a comparison, determine, for each of the at least some of the users, a likelihood of interacting with a recruiter associated with the position based on the activities of each of the at least some of the users, and transmit, to at least one of the users, a communication related to the position based, at least in part, on the comparison and the likelihood of interacting.
    Type: Application
    Filed: January 13, 2015
    Publication date: December 3, 2015
    Inventors: Shakti Dhirendraji Sinha, Asif Mansoor Ali Makhani, Anmol Bhasin, Senthil Sundaram, Viet Thuc Ha
  • Publication number: 20150261759
    Abstract: The disclosed embodiments provide a reputation system. The reputation system includes a ranking apparatus that obtains a set of reputation scores for one or more dimensions of a set of items in the reputation system and generates a ranking of the items based on the reputation scores and the one or more quantiles. The reputation system also includes a query-processing apparatus that obtains a query comprising the one or more dimensions and one or more quantiles associated with the one or more dimensions and provides the ranking in a response to the query.
    Type: Application
    Filed: April 23, 2015
    Publication date: September 17, 2015
    Applicant: LinkedIn Corporation
    Inventors: Mario S. Rodriguez, Viet Thuc Ha, Jessica V. Zuniga, Mathieu Bastian, Michael Conover