Patents by Inventor Kishore Kumar Mohan

Kishore Kumar Mohan 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: 11803896
    Abstract: Methods for determining which image of a set of images to present in a search results page for a product are described. Components of a server system may receive a set of images for a set of items associated with a product. Components of the server system may perform image ranking to rank the set of images to identify a representative image of the set of images for the product, based on a user interaction metric of each image of the set of images. The components of the server system may then receive, from a user device, a search query that may be mapped to the product, and the component of the server system may transmit, to the user device, the search results page that includes at least one item of the set of items and the representative image based on the interaction metric of the representative image.
    Type: Grant
    Filed: March 17, 2020
    Date of Patent: October 31, 2023
    Assignee: eBay Inc.
    Inventors: Ramesh Periyathambi, Tomer Lancewicki, Kishore Kumar Mohan, Lakshimi Duraivenkatesh, Selcuk Kopru
  • Publication number: 20230298081
    Abstract: A bundle generation engine provides recommendations for an item and at least one compatible item. Upon receiving an item listing for an item at a listing platform, the bundle generation engine determines that unstructured text of an item description for the item listing includes one or more compatible items. For example, the bundle generation engine may use a classification model to determine the unstructured text includes the one or more compatible items. Based on determining that the unstructured text includes the one or more compatible items, the bundle generation engine identifies one or more identifiers within the unstructured text of the item description. For example, the identifiers may be model identifiers or brand identifiers. In aspects, the identifiers are identified using one or more natural language processing models. A bundle recommendation is provided to a user device based on the one or more identifiers.
    Type: Application
    Filed: March 21, 2022
    Publication date: September 21, 2023
    Inventors: Kishore Kumar MOHAN, Ramesh PERIYATHAMBI, Lakshimi DURAIVENKATESH
  • Publication number: 20230065751
    Abstract: A method of training a machine learning model to promote an item is provided. Acceptance activity of a first entity is monitored and a determination of a first likelihood that the first entity accepts a future offer is made. The acceptance activity and the first likelihood are input as training data for the machine learning model for training purposes. An offer having an acceptance window and a characteristic is received from a second entity for a first item associated with the first entity. A second likelihood that the first entity will accept the offer is determined and an acceptance window is adjusted based on the determination. When the acceptance window closes, the method searches for a second item associated with a third entity based having the characteristic where an offer for the second item is sent to the second entity on behalf of the third entity.
    Type: Application
    Filed: August 24, 2021
    Publication date: March 2, 2023
    Inventors: Kishore Kumar Mohan, Ramesh Periyathambi, Lakshimi Duraivenkatesh, Mohan Patt
  • Publication number: 20210374825
    Abstract: Disclosed are systems, methods, and non-transitory computer-readable media for generating relationship data from listing data. A recommendation system accesses a listing posted to an online marketplace that offers an item for sale. The recommendation system identifies, from listing data included in the listing, a different listing posted to the online marketplace that is offering a recommended item for sale. The listing data is entered by a user that posted the listing to the online marketplace. The recommendation system categorizes the recommended item in a category of items that is related to the item. The recommendation system may generate item recommendation based on the category of items that is related to the item, such as an item recommendation identifying the listing offering the recommended item for sale.
    Type: Application
    Filed: May 27, 2020
    Publication date: December 2, 2021
    Inventors: Ramesh Periyathambi, Kishore Kumar Mohan, Selcuk Kopru, Lakshimi Duraivenkatesh, Tomer Lancewicki
  • Publication number: 20210295422
    Abstract: Methods for determining which image of a set of images to present in a search results page for a product are described. Components of a server system may receive a set of images for a set of items associated with a product. Components of the server system may perform image ranking to rank the set of images to identify a representative image of the set of images for the product, based on a user interaction metric of each image of the set of images. The components of the server system may then receive, from a user device, a search query that may be mapped to the product, and the component of the server system may transmit, to the user device, the search results page that includes at least one item of the set of items and the representative image based on the interaction metric of the representative image.
    Type: Application
    Filed: March 17, 2020
    Publication date: September 23, 2021
    Inventors: Ramesh Periyathambi, Tomer Lancewicki, Kishore Kumar Mohan, Lakshimi Duraivenkatesh, Selcuk Kopru