Patents by Inventor Jaya Prakash Narayana GUTTA
Jaya Prakash Narayana GUTTA 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: 20240028629Abstract: Some embodiments may obtain a natural language question, determine a context of the natural language question, and generate a first vector based on the natural language question using encoder neural network layers. Some embodiments may access a data table comprising column names, generate vectors based on the column names, and determine attention scores based on the vectors. Some embodiments may update the vectors based on the attention scores, generating a second vector based on the natural language question, determine a set of strings comprising a name of the column names and a database language operator based on the vectors. Some embodiments may determine a values based on the determined database language operator, the name, using a transformer neural network model. Some embodiments may generate a query based on the set of strings and the values.Type: ApplicationFiled: September 25, 2023Publication date: January 25, 2024Inventors: Jaya Prakash Narayana Gutta, Sharad Malhautra, Lalit Gupta
-
Patent number: 11860916Abstract: Some embodiments may obtain a natural language question, determine a context of the natural language question, and generate a first vector based on the natural language question using encoder neural network layers. Some embodiments may access a data table comprising column names, generate vectors based on the column names, and determine attention scores based on the vectors. Some embodiments may update the vectors based on the attention scores, generating a second vector based on the natural language question, determine a set of strings comprising a name of the column names and a database language operator based on the vectors. Some embodiments may determine a values based on the determined database language operator, the name, using a transformer neural network model. Some embodiments may generate a query based on the set of strings and the values.Type: GrantFiled: December 2, 2022Date of Patent: January 2, 2024Assignee: DSilo Inc.Inventors: Jaya Prakash Narayana Gutta, Sharad Malhautra, Lalit Gupta
-
Publication number: 20230315770Abstract: A process includes obtaining a document, determining a set of vectors based on a count of n-grams of the document, and determining a first set of information based on the document using a first set of neural networks. The process includes selecting a text section of the natural language document using a second set of neural networks and a code template of a plurality of code templates based on the text section based on the first set of information and the text section. The process includes determining an entity identifier, a value of a conditional statement, a second set of information, and a third set of information based on the text section, the first set of information, and the code template. The process includes generating a first set of program code based on the entity identifier, the value, the second set of information, and the third set of information.Type: ApplicationFiled: June 8, 2023Publication date: October 5, 2023Inventors: Jaya Prakash Narayana Gutta, Sharad Malhautra, Lalit Gupta
-
Patent number: 11720615Abstract: A process includes obtaining a document, determining a set of vectors based on a count of n-grams of the document, and determining a first set of information based on the document using a first set of neural networks. The process includes selecting a text section of the natural language document using a second set of neural networks and a code template of a plurality of code templates based on the text section based on the first set of information and the text section. The process includes determining an entity identifier, a value of a conditional statement, a second set of information, and a third set of information based on the text section, the first set of information, and the code template. The process includes generating a first set of program code based on the entity identifier, the value, the second set of information, and the third set of information.Type: GrantFiled: July 29, 2022Date of Patent: August 8, 2023Assignee: DSilo Inc.Inventors: Jaya Prakash Narayana Gutta, Sharad Malhautra, Lalit Gupta
-
Publication number: 20230195767Abstract: Some embodiments may perform operations of a process that includes obtaining a natural language text document and use a machine learning model to generate a set of attributes based on a set of machine-learning-model-generated classifications in the document. The process may include performing hierarchical data extraction operations to populate the attributes, where different machine learning models may be used in sequence. The process may include using a pre-trained Bidirectional Encoder Representations from Transformers (BERT) model augmented with a pooling operation to determine a BERT output via a multi-channel transformer model to generate vectors on a per-sentence level or other per-text-section level. The process may include using a finer-grain model to extract quantitative or categorical values of interest, where the context of the per-sentence level may be retained for the finer-grain model.Type: ApplicationFiled: February 10, 2023Publication date: June 22, 2023Inventors: Jaya Prakash Narayana Gutta, Sharad Malhautra, Lalit Gupta
-
Publication number: 20230096857Abstract: Some embodiments may obtain a natural language question, determine a context of the natural language question, and generate a first vector based on the natural language question using encoder neural network layers. Some embodiments may access a data table comprising column names, generate vectors based on the column names, and determine attention scores based on the vectors. Some embodiments may update the vectors based on the attention scores, generating a second vector based on the natural language question, determine a set of strings comprising a name of the column names and a database language operator based on the vectors. Some embodiments may determine a values based on the determined database language operator, the name, using a transformer neural network model. Some embodiments may generate a query based on the set of strings and the values.Type: ApplicationFiled: December 2, 2022Publication date: March 30, 2023Inventors: Jaya Prakash Narayana Gutta, Sharad Malhautra, Lalit Gupta
-
Patent number: 11580150Abstract: Some embodiments may perform operations of a process that includes obtaining a natural language text document and use a machine learning model to generate a set of attributes based on a set of machine-learning-model-generated classifications in the document. The process may include performing hierarchical data extraction operations to populate the attributes, where different machine learning models may be used in sequence. The process may include using a pre-trained Bidirectional Encoder Representations from Transformers (BERT) model augmented with a pooling operation to determine a BERT output via a multi-channel transformer model to generate vectors on a per-sentence level or other per-text-section level. The process may include using a finer-grain model to extract quantitative or categorical values of interest, where the context of the per-sentence level may be retained for the finer-grain model.Type: GrantFiled: July 29, 2022Date of Patent: February 14, 2023Assignee: Dsilo, Inc.Inventors: Jaya Prakash Narayana Gutta, Sharad Malhautra, Lalit Gupta
-
Publication number: 20230038529Abstract: A process includes obtaining a document, determining a set of vectors based on a count of n-grams of the document, and determining a first set of information based on the document using a first set of neural networks. The process includes selecting a text section of the natural language document using a second set of neural networks and a code template of a plurality of code templates based on the text section based on the first set of information and the text section. The process includes determining an entity identifier, a value of a conditional statement, a second set of information, and a third set of information based on the text section, the first set of information, and the code template. The process includes generating a first set of program code based on the entity identifier, the value, the second set of information, and the third set of information.Type: ApplicationFiled: July 29, 2022Publication date: February 9, 2023Inventors: Jaya Prakash Narayana Gutta, Sharad Malhautra, Lalit Gupta
-
Publication number: 20230037077Abstract: Some embodiments may perform operations of a process that includes obtaining a natural language text document and use a machine learning model to generate a set of attributes based on a set of machine-learning-model-generated classifications in the document. The process may include performing hierarchical data extraction operations to populate the attributes, where different machine learning models may be used in sequence. The process may include using a pre-trained Bidirectional Encoder Representations from Transformers (BERT) model augmented with a pooling operation to determine a BERT output via a multi-channel transformer model to generate vectors on a per-sentence level or other per-text-section level. The process may include using a finer-grain model to extract quantitative or categorical values of interest, where the context of the per-sentence level may be retained for the finer-grain model.Type: ApplicationFiled: July 29, 2022Publication date: February 2, 2023Inventors: Jaya Prakash Narayana Gutta, Sharad Malhautra, Lalit Gupta
-
Patent number: 11520815Abstract: Some embodiments may obtain a natural language question, determine a context of the natural language question, and generate a first vector based on the natural language question using encoder neural network layers. Some embodiments may access a data table comprising column names, generate vectors based on the column names, and determine attention scores based on the vectors. Some embodiments may update the vectors based on the attention scores, generating a second vector based on the natural language question, determine a set of strings comprising a name of the column names and a database language operator based on the vectors. Some embodiments may determine a values based on the determined database language operator, the name, using a transformer neural network model. Some embodiments may generate a query based on the set of strings and the values.Type: GrantFiled: July 29, 2022Date of Patent: December 6, 2022Assignee: Dsilo, Inc.Inventors: Jaya Prakash Narayana Gutta, Sharad Malhautra, Lalit Gupta
-
METHODS AND SYSTEMS FOR BRIDGING PAIRWISE COMMUNICATION IN A NETWORK OF DISPARATE ENTERPRISE SYSTEMS
Publication number: 20200327473Abstract: Embodiments of the instant disclosure include methods and systems directed at multi-token representation of assets involved in transactions occurring on distributed-ledger based networks that bridge or facilitate such transactions between disparate enterprise resource planning (ERP) systems. The disclose methods and systems improve network performance by at least reducing inefficiencies or errors that occur when disparate systems transact.Type: ApplicationFiled: April 14, 2020Publication date: October 15, 2020Inventors: Chen ZUR, Mathew HARROWING, Tze Wan ANG, Kimmie LUETZHOEFT, Robert John VAN SANT, Jaya Prakash Narayana GUTTA