Patents by Inventor Roger Hu
Roger Hu 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).
-
Publication number: 20240077331Abstract: A method of predicting one or more road segment attributes corresponding to a road segment in a geographical area, the method including: providing trajectory data and satellite image of the geographical area; calculating one or more image channels based on the trajectory data; and using at least one processor, classi-fying the road segment based on the one or more image channels and the satellite image using a trained classifier into prediction probabil-ities of the road attributes A data processing system including one or more processors configured to carry out a the method of predicting road attributes. A computer executable code including instructions for predicting one or more road segment attributes according to the method.Type: ApplicationFiled: October 19, 2023Publication date: March 7, 2024Inventors: Yifang YIN, Jagannadan VARADARAJAN, Roger ZIMMERMANN, Wenmiao HU, An TRAN, Guanfeng WANG
-
Publication number: 20230297582Abstract: Computer implemented systems and methods are disclosed for automatically clustering and canonically identifying related data in various data structures. Data structures may include a plurality of records, wherein each record is associated with a respective entity. In accordance with some embodiments, the systems and methods further comprise identifying clusters of records associated with a respective entity by grouping the records into pairs, analyzing the respective pairs to determine a probability that both members of the pair relate to a common entity, and identifying a cluster of overlapping pairs to generate a collection of records relating to a common entity. Clusters may further be analyzed to determine canonical names or other properties for the respective entities by analyzing record fields and identifying similarities.Type: ApplicationFiled: May 30, 2023Publication date: September 21, 2023Inventors: Lawrence Manning, Rahul Mehta, Daniel Erenrich, Guillem Palou Visa, Roger Hu, Xavier Falco, Rowan Gilmore, Eli Bingham, Jason Prestinario, Yifei Huang, Daniel Fernandez, Jeremy Elser, Clayton Sader, Rahul Agarwal, Matthew Elkherj, Nicholas Latourette, Aleksandr Zamoshchin
-
Patent number: 11704325Abstract: Computer implemented systems and methods are disclosed for automatically clustering and canonically identifying related data in various data structures. Data structures may include a plurality of records, wherein each record is associated with a respective entity. In accordance with some embodiments, the systems and methods further comprise identifying clusters of records associated with a respective entity by grouping the records into pairs, analyzing the respective pairs to determine a probability that both members of the pair relate to a common entity, and identifying a cluster of overlapping pairs to generate a collection of records relating to a common entity. Clusters may further be analyzed to determine canonical names or other properties for the respective entities by analyzing record fields and identifying similarities.Type: GrantFiled: July 15, 2022Date of Patent: July 18, 2023Assignee: Palantir Technologies Inc.Inventors: Lawrence Manning, Rahul Mehta, Daniel Erenrich, Guillem Palou Visa, Roger Hu, Xavier Falco, Rowan Gilmore, Eli Bingham, Jason Prestinario, Yifei Huang, Daniel Fernandez, Jeremy Elser, Clayton Sader, Rahul Agarwal, Matthew Elkherj, Nicholas Latourette, Aleksandr Zamoshchin
-
Patent number: 11580137Abstract: Systems and techniques for indexing and/or querying a database are described herein. Multiple, large disparate data sources may be processed to cleanse and/or combine item data and/or item metadata. Further, attributes may be extracted from the item data sources. The interactive user interfaces allow a user to select one or more attributes and/or other parameters to present visualizations based on the processed data.Type: GrantFiled: August 27, 2021Date of Patent: February 14, 2023Assignee: Palantir Technologies Inc.Inventors: Boris Valensi, James Ong, Howard Carter, Joy Tao, Mark Schafer, Barry McCardel, Kelsey Falter, Roger Hu
-
Publication number: 20220374454Abstract: Computer implemented systems and methods are disclosed for automatically clustering and canonically identifying related data in various data structures. Data structures may include a plurality of records, wherein each record is associated with a respective entity. In accordance with some embodiments, the systems and methods further comprise identifying clusters of records associated with a respective entity by grouping the records into pairs, analyzing the respective pairs to determine a probability that both members of the pair relate to a common entity, and identifying a cluster of overlapping pairs to generate a collection of records relating to a common entity. Clusters may further be analyzed to determine canonical names or other properties for the respective entities by analyzing record fields and identifying similarities.Type: ApplicationFiled: July 15, 2022Publication date: November 24, 2022Inventors: Lawrence Manning, Rahul Mehta, Daniel Erenrich, Guillem Palou Visa, Roger Hu, Xavier Falco, Rowan Gilmore, Eli Bingham, Jason Prestinario, Yifei Huang, Daniel Fernandez, Jeremy Elser, Clayton Sader, Rahul Agarwal, Matthew Elkherj, Nicholas Latourette, Aleksandr Zamoshchin
-
Patent number: 11392591Abstract: Computer implemented systems and methods are disclosed for automatically clustering and canonically identifying related data in various data structures. Data structures may include a plurality of records, wherein each record is associated with a respective entity. In accordance with some embodiments, the systems and methods further comprise identifying clusters of records associated with a respective entity by grouping the records into pairs, analyzing the respective pairs to determine a probability that both members of the pair relate to a common entity, and identifying a cluster of overlapping pairs to generate a collection of records relating to a common entity. Clusters may further be analyzed to determine canonical names or other properties for the respective entities by analyzing record fields and identifying similarities.Type: GrantFiled: November 13, 2018Date of Patent: July 19, 2022Assignee: Palantir Technologies Inc.Inventors: Lawrence Manning, Rahul Mehta, Daniel Erenrich, Guillem Palou Visa, Roger Hu, Xavier Falco, Rowan Gilmore, Eli Bingham, Jason Prestinario, Yifei Huang, Daniel Fernandez, Jeremy Elser, Clayton Sader, Rahul Agarwal, Matthew Elkherj, Nicholas Latourette, Aleksandr Zamoshchin
-
Publication number: 20220164371Abstract: Systems and techniques for indexing and/or querying a database are described herein. Multiple, large disparate data sources may be processed to cleanse and/or combine item data and/or item metadata. Further, attributes may be extracted from the item data sources. The interactive user interfaces allow a user to select one or more attributes and/or other parameters to present visualizations based on the processed data.Type: ApplicationFiled: August 27, 2021Publication date: May 26, 2022Inventors: Boris Valensi, James Ong, Howard Carter, Joy Tao, Mark Schafer, Barry McCardel, Kelsey Falter, Roger Hu
-
Patent number: 11150629Abstract: A system comprising a computer-readable storage medium storing at least one program and a method for determining, tracking, and anticipating risk in a manufacturing facility are presented. In example embodiments, the method includes generating a risk data model for the manufacturing facility based on correlations between historical staffing conditions of the manufacturing facility and deviations from existing manufacturing procedures. The method further includes receiving projected operational data that includes information related to anticipated future staffing conditions of the manufacturing facility. The method further includes calculating a risk score based on the projected operational data using the risk data model. The method further includes causing presentation of a user interface that includes a display of the risk score.Type: GrantFiled: January 7, 2020Date of Patent: October 19, 2021Assignee: Palantir Technologies Inc.Inventors: Mitchell Beard, Kai Shen, Roger Hu, Sachi Shah, Miklos Danka, Laurynas Pliuskys, Thomas Pearson
-
Patent number: 11106701Abstract: Systems and techniques for indexing and/or querying a database are described herein. Multiple, large disparate data sources may be processed to cleanse and/or combine item data and/or item metadata. Further, attributes may be extracted from the item data sources. The interactive user interfaces allow a user to select one or more attributes and/or other parameters to present visualizations based on the processed data.Type: GrantFiled: October 26, 2018Date of Patent: August 31, 2021Assignee: Palantir Technologies Inc.Inventors: Boris Valensi, James Ong, Howard Carter, Joy Tao, Mark Schafer, Barry McCardel, Kelsey Falter, Roger Hu
-
Publication number: 20200143302Abstract: A system comprising a computer-readable storage medium storing at least one program and a method for determining, tracking, and anticipating risk in a manufacturing facility are presented. In example embodiments, the method includes generating a risk data model for the manufacturing facility based on correlations between historical staffing conditions of the manufacturing facility and deviations from existing manufacturing procedures. The method further includes receiving projected operational data that includes information related to anticipated future staffing conditions of the manufacturing facility. The method further includes calculating a risk score based on the projected operational data using the risk data model. The method further includes causing presentation of a user interface that includes a display of the risk score.Type: ApplicationFiled: January 7, 2020Publication date: May 7, 2020Inventors: Mitchell Beard, Kai Shen, Roger Hu, Sachi Shah, Miklos Danka, Laurynas Pliuskys, Thomas Pearson
-
Patent number: 10579950Abstract: A system comprising a computer-readable storage medium storing at least one program and a method for determining, tracking, and anticipating risk in a manufacturing facility are presented. In example embodiments, the method includes generating a risk data model for the manufacturing facility based on correlations between historical staffing conditions of the manufacturing facility and deviations from existing manufacturing procedures. The method further includes receiving projected operational data that includes information related to anticipated future staffing conditions of the manufacturing facility. The method further includes calculating a risk score based on the projected operational data using the risk data model. The method further includes causing presentation of a user interface that includes a display of the risk score.Type: GrantFiled: April 12, 2017Date of Patent: March 3, 2020Assignee: Palantir Technologies Inc.Inventors: Mitchell Beard, Kai Shen, Roger Hu, Sachi Shah, Miklos Danka, Laurynas Pliuskys, Thomas Pearson
-
Publication number: 20190079937Abstract: Computer implemented systems and methods are disclosed for automatically clustering and canonically identifying related data in various data structures. Data structures may include a plurality of records, wherein each record is associated with a respective entity. In accordance with some embodiments, the systems and methods further comprise identifying clusters of records associated with a respective entity by grouping the records into pairs, analyzing the respective pairs to determine a probability that both members of the pair relate to a common entity, and identifying a cluster of overlapping pairs to generate a collection of records relating to a common entity. Clusters may further be analyzed to determine canonical names or other properties for the respective entities by analyzing record fields and identifying similarities.Type: ApplicationFiled: November 13, 2018Publication date: March 14, 2019Inventors: Lawrence Manning, Rahul Mehta, Daniel Erenrich, Guillem Palou Visa, Roger Hu, Xavier Falco, Rowan Gilmore, Eli Bingham, Jason Prestinario, Yifei Huang, Daniel Fernandez, Jeremy Elser, Clayton Sader, Rahul Agarwal, Matthew Elkherj, Nicholas Latourette, Aleksandr Zamoshchin
-
Publication number: 20190065578Abstract: Systems and techniques for indexing and/or querying a database are described herein. Multiple, large disparate data sources may be processed to cleanse and/or combine item data and/or item metadata. Further, attributes may be extracted from the item data sources. The interactive user interfaces allow a user to select one or more attributes and/or other parameters to present visualizations based on the processed data.Type: ApplicationFiled: October 26, 2018Publication date: February 28, 2019Inventors: Boris Valensi, James Ong, Howard Carter, Joy Tao, Mark Schafer, Barry McCardel, Kelsey Falter, Roger Hu
-
Patent number: 10127289Abstract: Computer implemented systems and methods are disclosed for automatically clustering and canonically identifying related data in various data structures. Data structures may include a plurality of records, wherein each record is associated with a respective entity. In accordance with some embodiments, the systems and methods further comprise identifying clusters of records associated with a respective entity by grouping the records into pairs, analyzing the respective pairs to determine a probability that both members of the pair relate to a common entity, and identifying a cluster of overlapping pairs to generate a collection of records relating to a common entity. Clusters may further be analyzed to determine canonical names or other properties for the respective entities by analyzing record fields and identifying similarities.Type: GrantFiled: August 10, 2016Date of Patent: November 13, 2018Assignee: Palantir Technologies Inc.Inventors: Lawrence Manning, Rahul Mehta, Daniel Erenrich, Guillem Palou Visa, Roger Hu, Xavier Falco, Rowan Gilmore, Eli Bingham, Jason Prestinario, Yifei Huang, Daniel Fernandez, Jeremy Elser, Clayton Sader, Rahul Agarwal, Matthew Elkherj, Nicholas Latourette, Aleksandr Zamoshchin
-
Patent number: 10114884Abstract: Systems and techniques for indexing and/or querying a database are described herein. Multiple, large disparate data sources may be processed to cleanse and/or combine item data and/or item metadata. Further, attributes may be extracted from the item data sources. The interactive user interfaces allow a user to select one or more attributes and/or other parameters to present visualizations based on the processed data.Type: GrantFiled: March 22, 2016Date of Patent: October 30, 2018Assignee: PALANTIR TECHNOLOGIES INC.Inventors: Boris Valensi, James Ong, Howard Carter, Joy Tao, Mark Schafer, Barry McCardel, Kelsey Falter, Roger Hu
-
Patent number: 9671776Abstract: A system comprising a computer-readable storage medium storing at least one program and a method for determining, tracking, and anticipating risk in a manufacturing facility are presented. In example embodiments, the method includes obtaining operational data associated with a manufacturing facility. The method further includes accessing a risk data model corresponding to the manufacturing facility, and calculating a risk score based on the current operational data using the risk data model. The method further includes causing presentation of a user interface that includes a display of the risk score to provide a user with a measure of risk at the manufacturing facility.Type: GrantFiled: August 20, 2015Date of Patent: June 6, 2017Assignee: Palantir Technologies Inc.Inventors: Mitchell Beard, Kai Shen, Roger Hu, Sachi Shah, Miklos Danka, Laurynas Pliuskys, Thomas Pearson
-
Publication number: 20170052958Abstract: Computer implemented systems and methods are disclosed for automatically clustering and canonically identifying related data in various data structures. Data structures may include a plurality of records, wherein each record is associated with a respective entity. In accordance with some embodiments, the systems and methods further comprise identifying clusters of records associated with a respective entity by grouping the records into pairs, analyzing the respective pairs to determine a probability that both members of the pair relate to a common entity, and identifying a cluster of overlapping pairs to generate a collection of records relating to a common entity. Clusters may further be analyzed to determine canonical names or other properties for the respective entities by analyzing record fields and identifying similarities.Type: ApplicationFiled: August 10, 2016Publication date: February 23, 2017Inventors: Lawrence Manning, Rahul Mehta, Daniel Erenrich, Guillem Palou Visa, Roger Hu, Xavier Falco, Rowan Gilmore, Eli Bingham, Jason Prestinario, Yifei Huang, Daniel Fernandez, Jeremy Elser, Clayton Sader, Rahul Agarwal, Matthew Elkherj, Nicholas Latourette, Aleksandr Zamoshchin
-
Patent number: 9311679Abstract: Managing an enterprise social media management platform includes: receiving a request by a user to perform an action on a social media asset that is maintained at an external social media platform; checking whether the user has permission to perform the action on the social media asset, based at least in part on a mapping of the social media asset and a permission level associated with the user; in the event that the user is determined to have permission to perform the action, allowing the user to proceed with the action on the social media asset; and in the event that the user is determined not to have permission to perform the action, disallowing the user to proceed with the action on the social media asset.Type: GrantFiled: October 31, 2011Date of Patent: April 12, 2016Assignee: Hearsay Social, Inc.Inventors: Clara Shih, Robert MacCloy, Roger Hu, Yahui Jin, Steve Garrity
-
Patent number: 9070110Abstract: Identification of rogue social media assets is provided. In some embodiments, identification of rogue social media assets includes identifying a plurality of social media assets; comparing the plurality of social media assets with known social media assets to identify previously unknown social media assets; and displaying the identified previously unknown social media assets.Type: GrantFiled: July 25, 2012Date of Patent: June 30, 2015Assignee: Hearsay Social, Inc.Inventors: Clara Shih, Steve Garrity, Kate Heddleston, Chris Andrew, Roger Hu, Robert MacCloy, Yahui Jin, Diana Freeman-Baer, Jaleh Bisharat
-
Publication number: 20130110922Abstract: Managing an enterprise social media management platform includes: receiving a request by a user to perform an action on a social media asset that is maintained at an external social media platform; checking whether the user has permission to perform the action on the social media asset, based at least in part on a mapping of the social media asset and a permission level associated with the user; in the event that the user is determined to have permission to perform the action, allowing the user to proceed with the action on the social media asset; and in the event that the user is determined not to have permission to perform the action, disallowing the user to proceed with the action on the social media asset.Type: ApplicationFiled: October 31, 2011Publication date: May 2, 2013Applicant: HEARSAY LABS, INC.Inventors: Clara Shih, Robert MacCloy, Roger Hu, Yahui Jin, Steve Garrity