Patents by Inventor Dmitry Martyanov

Dmitry Martyanov 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: 12014372
    Abstract: Event data of a first entity is accessed. The first entity has been flagged as having a predefined status. The event data corresponds to a plurality of events involving the first entity that occurred within a predefined first time period. Based on the accessing of the event data, behavioral data of the first entity is generated. The behavioral data is formatted as a data sequence. A machine learning model is trained using the behavioral data of the first entity as training data. Using the trained machine learning model, a determination is made as to whether a second entity has the predefined status.
    Type: Grant
    Filed: June 16, 2020
    Date of Patent: June 18, 2024
    Inventors: Rongsheng Zhu, Dmitry Martyanov, Xiuyi Ling
  • Patent number: 11941623
    Abstract: There are provided systems and methods for a device manager to control data tracking with client devices. A device may implement a manager process or application that allows a user to set preferences and/or a schedule of rates for allowing other online service providers to track user data. This may include placement of device-side data, such as a cookie or pixel, or tracking of device data through an application. The manager process may detect when a website, online platform, application, or other entity attempts to track data on the device and may utilize the schedule of rates to request a payment from the tracking entity. If the entity agrees to the payment, the manager may allow the entity to begin tracking data. However, if the tracking entity does not agree to the payment, then the manager may prevent the tracking entity from collecting data from the device.
    Type: Grant
    Filed: June 25, 2019
    Date of Patent: March 26, 2024
    Assignee: PAYPAL, INC.
    Inventors: David Williams, Dmitry Martyanov
  • Publication number: 20230111652
    Abstract: Event data of a first entity is accessed. The first entity has been flagged as having a predefined status. The event data corresponds to a plurality of events involving the first entity that occurred within a predefined first time period. Based on the accessing of the event data, behavioral data of the first entity is generated. The behavioral data is formatted as a data sequence. A machine learning model is trained using the behavioral data of the first entity as training data. Using the trained machine learning model, a determination is made as to whether a second entity has the predefined status.
    Type: Application
    Filed: June 16, 2020
    Publication date: April 13, 2023
    Inventors: Rongsheng Zhu, Dmitry Martyanov, Xiuyi Ling
  • Patent number: 11615332
    Abstract: Techniques are described relating to automatically classifying telephone calls into a particular category using machine learning and artificial intelligence technology. As one example, calls to a customer service phone number can be classified as related to prohibited activity, or as legitimate. In particular, a number of different telephony variables as well as additional variables can be used to make such a classification, after training an appropriate machine learning model. The training process may use an externally provided call classification score that is provide by an outside entity as an input, and can be calibrated so that the output score of the trained classifier provides a score that corresponds to a real-world percentage chance of an unclassified call falling into a particular category. Thus, a classifier score of “95” can indicate that a call is in fact believed to be 95% likely to correspond to prohibited activity, for example.
    Type: Grant
    Filed: June 25, 2019
    Date of Patent: March 28, 2023
    Assignee: PAYPAL, INC.
    Inventors: David Williams, Dmitry Martyanov
  • Patent number: 11442804
    Abstract: Systems and methods are disclosed for detecting anomalies in text content of data objects even when a format of the data and/or data object is unknown. These may include receiving a first data object that corresponds to a first application service and that includes first text content. An anomaly classifier may be trained based on an artificial neural network by using a natural language processing algorithm on respective text content of at least a portion of each of a plurality of data objects corresponding to the first computing service. Each of the plurality of data objects may be labeled as belonging a category. The trained anomaly classifier may identify one or more text character sequences in the first text content of the first data object as anomalous and output identifying information indicating the one or more anomalous text character sequences in the first text content of the first data object.
    Type: Grant
    Filed: December 27, 2019
    Date of Patent: September 13, 2022
    Assignee: PAYPAL, INC.
    Inventor: Dmitry Martyanov
  • Patent number: 11360944
    Abstract: Methods and systems are presented for providing data consistency in a distributed data storage system using an eventual consistency model. The distributed data storage system may store data across multiple data servers. To process a request for writing a first data value for a data field, a first data server may generate, for the first data value, a first causality chain representing a data replacement history for the data field leading to the first data value. The first data server may insert the first data value without deleting pre-existing data values from the data field. To process a data read request, multiple data values corresponding to the data field may be retrieved. The first data server may then select one data value based on the causality chains associated with the multiple data values for responding to the data read request.
    Type: Grant
    Filed: October 20, 2020
    Date of Patent: June 14, 2022
    Assignee: PayPal, Inc.
    Inventors: Junaid Zaheer Jaswal, Dmitry Martyanov
  • Publication number: 20210200612
    Abstract: Systems and methods are disclosed for detecting anomalies in text content of data objects even when a format of the data and/or data object is unknown. These may include receiving a first data object that corresponds to a first application service and that includes first text content. An anomaly classifier may be trained based on an artificial neural network by using a natural language processing algorithm on respective text content of at least a portion of each of a plurality of data objects corresponding to the first computing service. Each of the plurality of data objects may be labeled as belonging a category. The trained anomaly classifier may identify one or more text character sequences in the first text content of the first data object as anomalous and output identifying information indicating the one or more anomalous text character sequences in the first text content of the first data object.
    Type: Application
    Filed: December 27, 2019
    Publication date: July 1, 2021
    Inventor: Dmitry Martyanov
  • Publication number: 20210103560
    Abstract: Methods and systems are presented for providing data consistency in a distributed data storage system using an eventual consistency model. The distributed data storage system may store data across multiple data servers. To process a request for writing a first data value for a data field, a first data server may generate, for the first data value, a first causality chain representing a data replacement history for the data field leading to the first data value. The first data server may insert the first data value without deleting pre-existing data values from the data field. To process a data read request, multiple data values corresponding to the data field may be retrieved. The first data server may then select one data value based on the causality chains associated with the multiple data values for responding to the data read request.
    Type: Application
    Filed: October 20, 2020
    Publication date: April 8, 2021
    Inventors: Junaid Zaheer Jaswal, Dmitry Martyanov
  • Publication number: 20200410489
    Abstract: There are provided systems and methods for a device manager to control data tracking with client devices. A device may implement a manager process or application that allows a user to set preferences and/or a schedule of rates for allowing other online service providers to track user data. This may include placement of device-side data, such as a cookie or pixel, or tracking of device data through an application. The manager process may detect when a website, online platform, application, or other entity attempts to track data on the device and may utilize the schedule of rates to request a payment from the tracking entity. If the entity agrees to the payment, the manager may allow the entity to begin tracking data. However, if the tracking entity does not agree to the payment, then the manager may prevent the tracking entity from collecting data from the device.
    Type: Application
    Filed: June 25, 2019
    Publication date: December 31, 2020
    Inventors: David Williams, Dmitry Martyanov
  • Publication number: 20200410378
    Abstract: Techniques are described relating to automatically classifying telephone calls into a particular category using machine learning and artificial intelligence technology. As one example, calls to a customer service phone number can be classified as related to prohibited activity, or as legitimate. In particular, a number of different telephony variables as well as additional variables can be used to make such a classification, after training an appropriate machine learning model. The training process may use an externally provided call classification score that is provide by an outside entity as an input, and can be calibrated so that the output score of the trained classifier provides a score that corresponds to a real-world percentage chance of an unclassified call falling into a particular category. Thus, a classifier score of “95” can indicate that a call is in fact believed to be 95% likely to correspond to prohibited activity, for example.
    Type: Application
    Filed: June 25, 2019
    Publication date: December 31, 2020
    Inventors: David Williams, Dmitry Martyanov
  • Patent number: 10810166
    Abstract: Methods and systems are presented for providing data consistency in a distributed data storage system using an eventual consistency model. The distributed data storage system may store data across multiple data servers. To process a request for writing a first data value for a data field, a first data server may generate, for the first data value, a first causality chain representing a data replacement history for the data field leading to the first data value. The first data server may insert the first data value without deleting pre-existing data values from the data field. To process a data read request, multiple data values corresponding to the data field may be retrieved. The first data server may then select one data value based on the causality chains associated with the multiple data values for responding to the data read request.
    Type: Grant
    Filed: September 20, 2018
    Date of Patent: October 20, 2020
    Assignee: PayPal, Inc.
    Inventors: Junaid Zaheer Jaswal, Dmitry Martyanov
  • Publication number: 20200097567
    Abstract: Methods and systems are presented for providing data consistency in a distributed data storage system using an eventual consistency model. The distributed data storage system may store data across multiple data servers. To process a request for writing a first data value for a data field, a first data server may generate, for the first data value, a first causality chain representing a data replacement history for the data field leading to the first data value. The first data server may insert the first data value without deleting pre-existing data values from the data field. To process a data read request, multiple data values corresponding to the data field may be retrieved. The first data server may then select one data value based on the causality chains associated with the multiple data values for responding to the data read request.
    Type: Application
    Filed: September 20, 2018
    Publication date: March 26, 2020
    Inventors: Junaid Zaheer Jaswal, Dmitry Martyanov