Patents by Inventor R. M. Keelan Downton

R. M. Keelan Downton 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: 20220318681
    Abstract: A topic tracking platform is disclosed that includes a machine-learning model that may be trained to expose topics in a corpus in response to a training table. Because topics are exposed, rather than searched for using existing taxonomies, the sensitivity of a topic tracking platform may be increased, and emerging topic trends may be more quickly flagged. Exposed topics may be automatically labelled, increasing the specificity of the topic tracking platform by overcoming the potential for topic labelling inconsistencies currently experienced in the art. Documents may be scored for each topic using information provided at a token granularity, and the contribution that each token of each document contributes to the topic may be visually represented. In some aspects, mechanisms are provided for reviewing topics of the corpus at varying granularities, including at a topic level, document level or token level granularity.
    Type: Application
    Filed: June 16, 2022
    Publication date: October 6, 2022
    Applicant: Capital One Services, LLC
    Inventors: Mackenzie SWEENEY, R. M. Keelan DOWNTON, Matthew DER, Raymond LUCAS
  • Patent number: 11403557
    Abstract: A topic tracking platform is disclosed that includes a machine-learning model that may be trained to expose topics in a corpus in response to a training table. Because topics are exposed, rather than searched for using existing taxonomies, the sensitivity of a topic tracking platform may be increased, and emerging topic trends may be more quickly flagged. Exposed topics may be automatically labelled, increasing the specificity of the topic tracking platform by overcoming the potential for topic labelling inconsistencies currently experienced in the art. Documents may be scored for each topic using information provided at a token granularity, and the contribution that each token of each document contributes to the topic may be visually represented. In some aspects, mechanisms are provided for reviewing topics of the corpus at varying granularities, including at a topic level, document level or token level granularity.
    Type: Grant
    Filed: May 15, 2019
    Date of Patent: August 2, 2022
    Assignee: Capital One Services, LLC
    Inventors: Mackenzie Sweeney, R. M. Keelan Downton, Matthew Der, Raymond Lucas
  • Publication number: 20200364610
    Abstract: A topic tracking platform is disclosed that includes a machine-learning model that may be trained to expose topics in a corpus in response to a training table. Because topics are exposed, rather than searched for using existing taxonomies, the sensitivity of a topic tracking platform may be increased, and emerging topic trends may be more quickly flagged. Exposed topics may be automatically labelled, increasing the specificity of the topic tracking platform by overcoming the potential for topic labelling inconsistencies currently experienced in the art. Documents may be scored for each topic using information provided at a token granularity, and the contribution that each token of each document contributes to the topic may be visually represented. In some aspects, mechanisms are provided for reviewing topics of the corpus at varying granularities, including at a topic level, document level or token level granularity.
    Type: Application
    Filed: May 15, 2019
    Publication date: November 19, 2020
    Applicant: Capital One Services, LLC
    Inventors: Mackenzie SWEENEY, R. M. Keelan DOWNTON, Matthew DER, Raymond LUCAS
  • Patent number: 10747760
    Abstract: Embodiments disclosed herein generally relate to a system and method for tracking virtual reality experiences. A computing system receives a plurality of location coordinates of a user during a VR simulation. The computing system uploads the plurality of location coordinates to a database. The computing system prompts a client device that an API linking the client device of the user to functionality of the database is available. The computing system receives a query via the API. The computing system translates the received query to a query compatible with the database. The computing system queries the database using the received query for according to criteria set forth in the received query to retrieve a set of location information. The computing system generates a heat map based on the retrieved location information. The computing system prompts the remote client device that the heat map is available for display.
    Type: Grant
    Filed: June 8, 2018
    Date of Patent: August 18, 2020
    Assignee: Capital One Services, LLC
    Inventors: Christopher Lanoue, R. M. Keelan Downton, Paul Buffa
  • Publication number: 20190377812
    Abstract: Embodiments disclosed herein generally relate to a system and method for tracking virtual reality experiences. A computing system receives a plurality of location coordinates of a user during a VR simulation. The computing system uploads the plurality of location coordinates to a database. The computing system prompts a client device that an API linking the client device of the user to functionality of the database is available. The computing system receives a query via the API. The computing system translates the received query to a query compatible with the database. The computing system queries the database using the received query for according to criteria set forth in the received query to retrieve a set of location information. The computing system generates a heat map based on the retrieved location information. The computing system prompts the remote client device that the heat map is available for display.
    Type: Application
    Filed: June 8, 2018
    Publication date: December 12, 2019
    Applicant: Capital One Services, LLC
    Inventors: Christopher Lanoue, R. M. Keelan Downton, Paul Buffa
  • Patent number: 10482130
    Abstract: In one aspect, the present disclosure relates to a method for improved computer-based visualization of a tree structure comprises: receiving a dataset defining the tree structure, the tree structure comprising a plurality of nodes and a plurality of edges; analyzing the dataset to determine constraint information for the tree structure; generating a first plurality of graphical objects corresponding to the node; positioning the first plurality of graphical objects within a three-dimensional coordinate space based on the constraint information, wherein all child nodes of a given node are arranged within a corresponding two-dimensional matrix; generating a second plurality of graphical objects corresponding to the edges; positioning the second plurality of graphical objects based on the positioning of the first plurality of graphical objects; and outputting a three-dimensional tree diagram of the tree structure comprising the first plurality of graphical objects and the second plurality of graphical objects.
    Type: Grant
    Filed: March 19, 2018
    Date of Patent: November 19, 2019
    Assignee: Capital One Services, LLC
    Inventors: Paul Buffa, Christopher Lanoue, R. M. Keelan Downton
  • Publication number: 20190286758
    Abstract: In one aspect, the present disclosure relates to a method for improved computer-based visualization of a tree structure comprises: receiving a dataset defining the tree structure, the tree structure comprising a plurality of nodes and a plurality of edges; analyzing the dataset to determine constraint information for the tree structure; generating a first plurality of graphical objects corresponding to the node; positioning the first plurality of graphical objects within a three-dimensional coordinate space based on the constraint information, wherein all child nodes of a given node are arranged within a corresponding two-dimensional matrix; generating a second plurality of graphical objects corresponding to the edges; positioning the second plurality of graphical objects based on the positioning of the first plurality of graphical objects; and outputting a three-dimensional tree diagram of the tree structure comprising the first plurality of graphical objects and the second plurality of graphical objects.
    Type: Application
    Filed: March 19, 2018
    Publication date: September 19, 2019
    Applicant: Capital One Services, LLC
    Inventors: Paul Buffa, Christopher Lanoue, R.M. Keelan Downton
  • Patent number: D789957
    Type: Grant
    Filed: July 10, 2015
    Date of Patent: June 20, 2017
    Assignee: Capital One Services, LLC
    Inventors: Jingtao Wu, R. M. Keelan Downton, Chi Tak Kwok, Matthew Bryan, Colin Hart, Mark Mendez
  • Patent number: D796548
    Type: Grant
    Filed: December 30, 2016
    Date of Patent: September 5, 2017
    Assignee: CAPITAL ONE SERVICES, LLC
    Inventors: Jingtao Wu, R. M. Keelan Downton, Chi Tak Kwok, Matthew Bryan, Colin Hart, Mark Mendez
  • Patent number: D806127
    Type: Grant
    Filed: December 30, 2016
    Date of Patent: December 26, 2017
    Assignee: CAPITAL ONE SERVICES, LLC
    Inventors: Jingtao Wu, R. M. Keelan Downton, Chi Tak Kwok, Matthew Bryan, Colin Hart, Mark Mendez