Patents by Inventor Sepideh Hashtroodi

Sepideh Hashtroodi 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: 10693997
    Abstract: Embodiments of the present disclosure pertain to network based machine learning generated simulations. In one embodiment, the present disclosure includes a computer implemented method comprising sending first code comprising a programmable calculator from a server system to a client system across a network. A data request is sent to a database, the data request configured to retrieve data from the database comprising a plurality of fields and a target field. The retrieved data is processed using a machine learning algorithm to produce a weight for each field of the plurality of fields and a scoring data structure. The fields and the scoring data structure are sent to the client system across the network. A user selects values for the plurality of fields and the programmable calculator is configured based on the scoring data structure to generate a simulated value for the target field based on the user selected values.
    Type: Grant
    Filed: December 15, 2017
    Date of Patent: June 23, 2020
    Assignee: SAP SE
    Inventors: Katherine Wright, Sepideh Hashtroodi, Teresa Hsin Yi Su, Flavia Moser, Sajjad Gholami, Zeyu Ni, Geoffrey Neil Peters
  • Publication number: 20190191009
    Abstract: Embodiments of the present disclosure pertain to network based machine learning generated simulations. In one embodiment, the present disclosure includes a computer implemented method comprising sending first code comprising a programmable calculator from a server system to a client system across a network. A data request is sent to a database, the data request configured to retrieve data from the database comprising a plurality of fields and a target field. The retrieved data is processed using a machine learning algorithm to produce a weight for each field of the plurality of fields and a scoring data structure. The fields and the scoring data structure are sent to the client system across the network. A user selects values for the plurality of fields and the programmable calculator is configured based on the scoring data structure to generate a simulated value for the target field based on the user selected values.
    Type: Application
    Filed: December 15, 2017
    Publication date: June 20, 2019
    Applicant: SAP SE
    Inventors: Katherine Wright, Sepideh Hashtroodi, Teresa Hsin Yi Su, Flavia Moser, Sajjad Gholami, Zeyu Ni, Geoffrey Neil Peters