Patents by Inventor Diptarka Saha

Diptarka Saha 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).

  • Relative density-based clustering and anomaly detection system
    Patent number: 10789507
    Abstract: Examples provide a system for detecting anomalies in a dataset. The system includes one or more processors and a memory storing the dataset. The one or more processors are programmed to identify a first set of data points in a cluster, identify a second set of data points outside of the cluster as noisy data points, and determine whether each of the noisy data points is an anomaly by: determining a distance between the noisy data point and other data points in the dataset, ranking the distances between the noisy data point and the other data points, and applying a weight to each of the ranked distances to determine an outlier value for the noisy data point. When the outlier value for the noisy data point exceeds a threshold, the noisy data point is identified as an anomaly, and result is displayed in a user interface.
    Type: Grant
    Filed: May 11, 2018
    Date of Patent: September 29, 2020
    Assignee: Walmart Apollo, LLC
    Inventors: Diptarka Saha, Debanjana Banerjee, Bodhisattwa Prasad Majumder
  • METHOD AND APPARATUS FOR CALCULATING PROMOTION ADJUSTED LOYALTY
    Publication number: 20200294079
    Abstract: Systems and methods for determining promotional adjusted customer loyalty to items sold at a facility are discussed. Embodiments enable the automatic re-ordering of items for a facility based on adjusted loyalty values.
    Type: Application
    Filed: May 8, 2019
    Publication date: September 17, 2020
    Inventor: Diptarka Saha
  • RELATIVE DENSITY-BASED CLUSTERING AND ANOMALY DETECTION SYSTEM
    Publication number: 20190303710
    Abstract: Examples provide a system for detecting anomalies in a dataset. The system includes one or more processors and a memory storing the dataset. The one or more processors are programmed to identify a first set of data points in a cluster, identify a second set of data points outside of the cluster as noisy data points, and determine whether each of the noisy data points is an anomaly by: determining a distance between the noisy data point and other data points in the dataset, ranking the distances between the noisy data point and the other data points, and applying a weight to each of the ranked distances to determine an outlier value for the noisy data point. When the outlier value for the noisy data point exceeds a threshold, the noisy data point is identified as an anomaly, and result is displayed in a user interface.
    Type: Application
    Filed: May 11, 2018
    Publication date: October 3, 2019
    Inventors: Diptarka Saha, Debanjana Banerjee, Bodhisattwa Prasad Majumder