Patents by Inventor Venkat Yashwanth GUNAPATI
Venkat Yashwanth GUNAPATI 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: 11818010Abstract: Disclosed herein are systems, products, and/or methods for determining a dependency between a task and a hardware component executing the task. The method may include: accessing an execution log storing information related to a plurality of tasks, each task of the plurality of tasks being executed by a respective computing device of a plurality of computing devices distributed across a network architecture; identifying a task of the plurality of tasks to obtain application layer information of the identified task; determining which respective computing device executed the identified task to obtain network layer information of the respective computing device; generating a dependency map illustrating a relationship between the identified task and the respective computing device that executed the identified task, the relationship including the application layer information and the network layer information; and displaying, using an interactive graphical user interface (GUI) on a user device, the dependency map.Type: GrantFiled: June 28, 2021Date of Patent: November 14, 2023Assignee: Capital One Services, LLCInventors: Manideep Kantamneni, Brandon Clodius, Venkat Yashwanth Gunapati, Naveen Bansal, Tariq Bhatti
-
Patent number: 11379659Abstract: A method performed by a device may include identifying a plurality of samples of textual content; performing tokenization of the plurality of samples to generate a respective plurality of tokenized samples; performing embedding of the plurality of tokenized samples to generate a sample matrix; determining groupings of attributes of the sample matrix using a convolutional neural network; determining context relationships between the groupings of attributes using a bidirectional long short term memory (LSTM) technique; selecting predicted labels for the plurality of samples using a model, wherein the model selects, for a particular sample of the plurality of samples, a predicted label of the predicted labels from a plurality of labels based on respective scores of the particular sample with regard to the plurality of labels and based on a nonparametric paired comparison of the respective scores; and providing information identifying the predicted labels.Type: GrantFiled: February 7, 2020Date of Patent: July 5, 2022Assignee: Capital One Services, LLCInventors: Jon Austin Osbourne, Aaron Raymer, Megan Yetman, Venkat Yashwanth Gunapati
-
Publication number: 20210328878Abstract: Disclosed herein are systems, products, and/or methods for determining a dependency between a task and a hardware component executing the task. The method may include: accessing an execution log storing information related to a plurality of tasks, each task of the plurality of tasks being executed by a respective computing device of a plurality of computing devices distributed across a network architecture; identifying a task of the plurality of tasks to obtain application layer information of the identified task; determining which respective computing device executed the identified task to obtain network layer information of the respective computing device; generating a dependency map illustrating a relationship between the identified task and the respective computing device that executed the identified task, the relationship including the application layer information and the network layer information; and displaying, using an interactive graphical user interface (GUI) on a user device, the dependency map.Type: ApplicationFiled: June 28, 2021Publication date: October 21, 2021Applicant: Capital One Services, LLCInventors: Manideep KANTAMNENI, Brandon CLODIUS, Venkat Yashwanth GUNAPATI, Naveen BANSAL, Tariq BHATTI
-
Patent number: 11063833Abstract: Disclosed herein are systems, products, and/or methods for determining a dependency between a task and a hardware component executing the task. The method may include: accessing an execution log storing information related to a plurality of tasks, each task of the plurality of tasks being executed by a respective computing device of a plurality of computing devices distributed across a network architecture; identifying a task of the plurality of tasks to obtain application layer information of the identified task; determining which respective computing device executed the identified task to obtain network layer information of the respective computing device; generating a dependency map illustrating a relationship between the identified task and the respective computing device that executed the identified task, the relationship including the application layer information and the network layer information; and displaying, using an interactive graphical user interface (GUI) on a user device, the dependency map.Type: GrantFiled: September 23, 2019Date of Patent: July 13, 2021Assignee: Capital One Services, LLCInventors: Manideep Kantamneni, Brandon Clodius, Venkat Yashwanth Gunapati, Naveen Bansal, Tariq Bhatti
-
Publication number: 20210092022Abstract: Disclosed herein are systems, products, and/or methods for determining a dependency between a task and a hardware component executing the task. The method may include: accessing an execution log storing information related to a plurality of tasks, each task of the plurality of tasks being executed by a respective computing device of a plurality of computing devices distributed across a network architecture; identifying a task of the plurality of tasks to obtain application layer information of the identified task; determining which respective computing device executed the identified task to obtain network layer information of the respective computing device; generating a dependency map illustrating a relationship between the identified task and the respective computing device that executed the identified task, the relationship including the application layer information and the network layer information; and displaying, using an interactive graphical user interface (GUI) on a user device, the dependency map.Type: ApplicationFiled: September 23, 2019Publication date: March 25, 2021Applicant: Capital One Services, LLCInventors: Manideep Kantamneni, Brandon Clodius, Venkat Yashwanth Gunapati, Naveen Bansal, Tariq Bhatti
-
Publication number: 20200175228Abstract: A method performed by a device may include identifying a plurality of samples of textual content; performing tokenization of the plurality of samples to generate a respective plurality of tokenized samples; performing embedding of the plurality of tokenized samples to generate a sample matrix; determining groupings of attributes of the sample matrix using a convolutional neural network; determining context relationships between the groupings of attributes using a bidirectional long short term memory (LSTM) technique; selecting predicted labels for the plurality of samples using a model, wherein the model selects, for a particular sample of the plurality of samples, a predicted label of the predicted labels from a plurality of labels based on respective scores of the particular sample with regard to the plurality of labels and based on a nonparametric paired comparison of the respective scores; and providing information identifying the predicted labels.Type: ApplicationFiled: February 7, 2020Publication date: June 4, 2020Inventors: Jon Austin Osbourne, Aaron Raymer, Megan Yetman, Venkat Yashwanth Gunapati
-
Patent number: 10599769Abstract: A method performed by a device may include identifying a plurality of samples of textual content; performing tokenization of the plurality of samples to generate a respective plurality of tokenized samples; performing embedding of the plurality of tokenized samples to generate a sample matrix; determining groupings of attributes of the sample matrix using a convolutional neural network; determining context relationships between the groupings of attributes using a bidirectional long short term memory (LSTM) technique; selecting predicted labels for the plurality of samples using a model, wherein the model selects, for a particular sample of the plurality of samples, a predicted label of the predicted labels from a plurality of labels based on respective scores of the particular sample with regard to the plurality of labels and based on a nonparametric paired comparison of the respective scores; and providing information identifying the predicted labels.Type: GrantFiled: June 26, 2018Date of Patent: March 24, 2020Assignee: Capital One Services, LLCInventors: Jon Austin Osbourne, Aaron Raymer, Megan Yetman, Venkat Yashwanth Gunapati
-
Patent number: 10482268Abstract: Systems and methods are provided for access management using machine learning. An exemplary system may include at least one processor and a storage medium storing instructions that, when executed by the processor, cause the processor to perform operations. The operations may include obtaining user access information from an access directory and generating a network comprising nodes and edges. The nodes may include a first type of nodes representing users and a second type of nodes representing access rights. The edges may include a first type of edges indicating that users have access rights, and a second type of edges indicating degrees of similarity between two users. The operations may also include determining a group of nodes of the first type representing a community of users sharing a degree of commonality higher than a degree of commonality shared by other users outside the community.Type: GrantFiled: August 8, 2018Date of Patent: November 19, 2019Inventors: Jon Austin Osborne, Venkat Yashwanth Gunapati, Amanda Juliene Rice
-
Publication number: 20190340235Abstract: A method performed by a device may include identifying a plurality of samples of textual content; performing tokenization of the plurality of samples to generate a respective plurality of tokenized samples; performing embedding of the plurality of tokenized samples to generate a sample matrix; determining groupings of attributes of the sample matrix using a convolutional neural network; determining context relationships between the groupings of attributes using a bidirectional long short term memory (LSTM) technique; selecting predicted labels for the plurality of samples using a model, wherein the model selects, for a particular sample of the plurality of samples, a predicted label of the predicted labels from a plurality of labels based on respective scores of the particular sample with regard to the plurality of labels and based on a nonparametric paired comparison of the respective scores; and providing information identifying the predicted labels.Type: ApplicationFiled: June 26, 2018Publication date: November 7, 2019Inventors: Jon Austin OSBOURNE, Aaron RAYMER, Megan YETMAN, Venkat Yashwanth GUNAPATI