Patents by Inventor Kenneth Basheer Halaby

Kenneth Basheer Halaby 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).

  • Methods and systems for improved entity recognition and insights
    Patent number: 11327975
    Abstract: Generating and providing match justifications in association with record matching results for improved record matching is provided. An entity resolution system generates a set of deterministic rules based on patterns of attribute comparison outcomes of known matched and unmatched records. Each rule includes matching conditions and an action instruction including a message of a justification for a match/non-match. The system receives a request to determine a match between two records. A matching engine compares various attributes of the records using probabilistic matching technologies to determine a match outcome. A justification engine compares attribute comparison outcomes to the stored rules. When the matching conditions of a rule are satisfied, the rule is activated and a human-readable justification is linked to the match output and provided in a match response. The justification provides insights into the match outcome, and improves the speed and accuracy of a verification process of the match output.
    Type: Grant
    Filed: March 29, 2019
    Date of Patent: May 10, 2022
    Assignee: Experian Health, Inc.
    Inventors: Karly Marie Rowe, Kenneth Basheer Halaby, John T. Dennis, Sean Daniel Reisz, Dimuthu Wijetilleke, Christopher Wavil Moody
  • METHODS AND SYSTEMS FOR IMPROVED ENTITY RECOGNITION AND INSIGHTS
    Publication number: 20190303371
    Abstract: Generating and providing match justifications in association with record matching results for improved record matching is provided. An entity resolution system generates a set of deterministic rules based on patterns of attribute comparison outcomes of known matched and unmatched records. Each rule includes matching conditions and an action instruction including a message of a justification for a match/non-match. The system receives a request to determine a match between two records. A matching engine compares various attributes of the records using probabilistic matching technologies to determine a match outcome. A justification engine compares attribute comparison outcomes to the stored rules. When the matching conditions of a rule are satisfied, the rule is activated and a human-readable justification is linked to the match output and provided in a match response. The justification provides insights into the match outcome, and improves the speed and accuracy of a verification process of the match output.
    Type: Application
    Filed: March 29, 2019
    Publication date: October 3, 2019
    Applicant: Experian Health, Inc.
    Inventors: Karly Marie Rowe, Kenneth Basheer Halaby, John Dennis, Sean Daniel Reisz, Dimuthu Wijetilleke, Christopher Wavil Moody