Patents by Inventor Nafiseh SABERIAN
Nafiseh SABERIAN 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).
-
Publication number: 20240155054Abstract: A method includes selecting a customer of a company; constructing a digital footprint of the selected customer. The method includes inputting the digital footprint to an artificial intelligence (AI) engine. The method includes obtaining one or more probability values from the AI engine based on the input digital footprint. The method includes selecting a call driver, from among a plurality of call drivers, as a predicted call driver. The method includes providing the predicted call driver to a call center associated with the company.Type: ApplicationFiled: January 18, 2024Publication date: May 9, 2024Applicant: Charles Schwab & Co., IncInventors: Nafiseh SABERIAN, Ravindra Reddy TAPPETA VENKATA, Stephen FILIOS, Logan Sommers AHLSTROM, Abhilash Krishnankutty NAIR
-
Patent number: 11924380Abstract: A method includes selecting a customer of a company; constructing a digital footprint of the selected customer. The method includes inputting the digital footprint to an artificial intelligence (AI) engine. The method includes obtaining one or more probability values from the AI engine based on the input digital footprint. The method includes selecting a call driver, from among a plurality of call drivers, as a predicted call driver. The method includes providing the predicted call driver to a call center associated with the company.Type: GrantFiled: August 16, 2022Date of Patent: March 5, 2024Assignee: CHARLES SCHWAB & CO., INC.Inventors: Nafiseh Saberian, Ravindra Reddy Tappeta Venkata, Stephen Filios, Logan Sommers Ahlstrom, Abhilash Krishnankutty Nair
-
Publication number: 20230215426Abstract: A method of operating a customer utterance analysis system includes obtaining a subset of utterances from among a first set of utterances. The method includes encoding, by a sentence encoder, the subset of utterances into multi-dimensional vectors. The method includes generating reduced-dimensionality vectors by reducing a dimensionality of the multi-dimensional vectors. Each vector of the reduced-dimensionality vectors corresponds to an utterance from among the subset of utterances. The method includes performing clustering on the reduced-dimensionality vectors. The method includes, based on the clustering performed on the reduced-dimensionality vectors, arranging the subset of utterances into clusters. The method includes obtaining labels for a least two clusters from among the clusters. The method includes generating training data based on the obtained labels. The method includes training a neural network model to predict an intent of an utterance based on the training data.Type: ApplicationFiled: March 14, 2023Publication date: July 6, 2023Applicant: TD Ameritrade IP Company, Inc.Inventors: Abhilash Krishnankutty NAIR, Amaris Yuseon Sim, Dayanand Narregudem, Drew David Riassetto, Logan Sommers Ahlstrom, Nafiseh Saberian, Stephen Filios, Ravindra Reddy Tappeta Venkata
-
Patent number: 11626108Abstract: A method of operating a customer utterance analysis system includes obtaining a subset of utterances from among a first set of utterances. The method includes encoding, by a sentence encoder, the subset of utterances into multi-dimensional vectors. The method includes generating reduced-dimensionality vectors by reducing a dimensionality of the multi-dimensional vectors. Each vector of the reduced-dimensionality vectors corresponds to an utterance from among the subset of utterances. The method includes performing clustering on the reduced-dimensionality vectors. The method includes, based on the clustering performed on the reduced-dimensionality vectors, arranging the subset of utterances into clusters. The method includes obtaining labels for a least two clusters from among the clusters. The method includes generating training data based on the obtained labels. The method includes training a neural network model to predict an intent of an utterance based on the training data.Type: GrantFiled: September 25, 2020Date of Patent: April 11, 2023Assignee: TD Ameritrade IP Company, Inc.Inventors: Abhilash Krishnankutty Nair, Amaris Yuseon Sim, Dayanand Narregudem, Drew David Riassetto, Logan Sommers Ahlstrom, Nafiseh Saberian, Stephen Filios, Ravindra Reddy Tappeta Venkata
-
Publication number: 20220394131Abstract: A method includes selecting a customer of a company; constructing a digital footprint of the selected customer. The method includes inputting the digital footprint to an artificial intelligence (AI) engine. The method includes obtaining one or more probability values from the AI engine based on the input digital footprint. The method includes selecting a call driver, from among a plurality of call drivers, as a predicted call driver.Type: ApplicationFiled: August 16, 2022Publication date: December 8, 2022Applicant: TD Ameritrade IP Company, Inc.Inventors: Nafiseh SABERIAN, Ravindra Reddy TAPPETA VENKATA, Stephen FILIOS, Logan Sommers AHLSTROM, Abhilash Krishnankutty NAIR
-
Patent number: 11431848Abstract: A method includes selecting a customer of a company; constructing a digital footprint of the selected customer. The method includes inputting the digital footprint to an artificial intelligence (AI) engine. The method includes obtaining one or more probability values from the AI engine based on the input digital footprint. The method includes selecting a call driver, from among a plurality of call drivers, as a predicted call driver. The method includes providing the predicted call driver to a call center associated with the company.Type: GrantFiled: June 30, 2020Date of Patent: August 30, 2022Assignee: TD Ameritrade IP Company, Inc.Inventors: Nafiseh Saberian, Ravindra Reddy Tappeta Venkata, Stephen Filios, Logan Sommers Ahlstrom, Abhilash Krishnankutty Nair
-
Publication number: 20220101837Abstract: A method of operating a customer utterance analysis system includes obtaining a subset of utterances from among a first set of utterances. The method includes encoding, by a sentence encoder, the subset of utterances into multi-dimensional vectors. The method includes generating reduced-dimensionality vectors by reducing a dimensionality of the multi-dimensional vectors. Each vector of the reduced-dimensionality vectors corresponds to an utterance from among the subset of utterances. The method includes performing clustering on the reduced-dimensionality vectors. The method includes, based on the clustering performed on the reduced-dimensionality vectors, arranging the subset of utterances into clusters. The method includes obtaining labels for a least two clusters from among the clusters. The method includes generating training data based on the obtained labels. The method includes training a neural network model to predict an intent of an utterance based on the training data.Type: ApplicationFiled: September 25, 2020Publication date: March 31, 2022Inventors: Abhilash Krishnankutty NAIR, Amaris Yuseon SIM, Dayanand NARREGUDEM, Drew David RIASSETTO, Logan Sommers AHLSTROM, Nafiseh SABERIAN, Stephen FILIOS, Ravindra Reddy TAPPETA VENKATA
-
Publication number: 20210409545Abstract: A method includes selecting a customer of a company; constructing a digital footprint of the selected customer. The method includes inputting the digital footprint to an artificial intelligence (AI) engine. The method includes obtaining one or more probability values from the AI engine based on the input digital footprint. The method includes selecting a call driver, from among a plurality of call drivers, as a predicted call driver. The method includes providing the predicted call driver to a call center associated with the company.Type: ApplicationFiled: June 30, 2020Publication date: December 30, 2021Inventors: Nafiseh SABERIAN, Ravindra Reddy TAPPETA VENKATA, Stephen FILIOS, Logan Sommers AHLSTROM, Abhilash Krishnankutty NAIR
-
Publication number: 20210374851Abstract: An equity system receives input from multiple data subsystem module. The data is filtered and weighted. The filtered and weighted data is received by a visualization subsystem that generates a visual representation of the weighted, filtered data. The visualization is rendered to a user and may be a cluster web. The visualization includes connections defining the relatedness of the nodes in the visualization. A client device is configured to view the displayed visualized representation to a user, wherein the client device is configured to receive input from a user requesting execution of one of a trade or research based upon the displayed visualized representation.Type: ApplicationFiled: May 28, 2020Publication date: December 2, 2021Inventors: Nafiseh SABERIAN, Ravindra Reddy TAPPETA VENKATA, Abhilash Krishnankutty NAIR