Patents by Inventor Shubhankar Sachdev
Shubhankar Sachdev 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: 20260330055Abstract: Computer-implemented systems and methods are disclosed, including systems and methods utilizing language models for searching a large corpus of data. A computer-implemented method may include: receiving a first user input comprising a natural language query; vectorizing the first user input into a query vector; executing, using the query vector, a similarity search in a document search model to identify one or more similar document portions, where the document search model includes a plurality of vectors corresponding to a plurality of portions of a set of documents; generating a first prompt for a large language model (“LLM”), the first prompt including at least the first user input, and the one or more similar document portions; transmitting the first prompt to the LLM; receiving a first output from the LLM in response to the first prompt; and providing, via a user interface, the first output from the LLM.Type: ApplicationFiled: January 29, 2026Publication date: October 22, 2026Inventors: Anirvan Mukherjee, Craig De Souza, Edgar Gomes de Araujo, Johannes Beil, Jessica Winssinger, Michael Zullo, Rushad Heerjee, Shubhankar Sachdev
-
Publication number: 20260329910Abstract: Computer-implemented systems and methods are disclosed, including systems and methods utilizing language models for generating data objects and/or updating an ontology. A computer-implemented method may include: employing one or more large language models (“LLMs”) to generate at least a data triple and a classified triple; executing, using the classified triple, a similarity search with reference to an ontology to determine that the classified triple at least partially matches one or more data object types defined in the ontology; in response to the determination, adding into a first database at least a first data object of a first data object type that represents a first entity in the data triple and a second data object of a second data object type that represents a second entity in the data triple.Type: ApplicationFiled: June 24, 2026Publication date: October 22, 2026Inventors: Anirvan Mukherjee, Craig De Souza, Edgar Gomes de Araujo, Johannes Beil, Jessica Winssinger, Michael Zullo, Rushad Heerjee, Shubhankar Sachdev
-
Publication number: 20260330054Abstract: Computer-implemented systems and methods are disclosed, including systems and methods utilizing language models for searching a large corpus of data. A computer-implemented method may include: receiving a first user input comprising a natural language query; vectorizing the first user input into a query vector; executing, using the query vector, a similarity search in a document search model to identify one or more similar document portions, where the document search model includes a plurality of vectors corresponding to a plurality of portions of a set of documents; generating a first prompt for a large language model (“LLM”), the first prompt including at least the first user input, and the one or more similar document portions; transmitting the first prompt to the LLM; receiving a first output from the LLM in response to the first prompt; and providing, via a user interface, the first output from the LLM.Type: ApplicationFiled: January 29, 2026Publication date: October 22, 2026Inventors: Anirvan Mukherjee, Craig De Souza, Edgar Gomes de Araujo, Johannes Beil, Jessica Winssinger, Michael Zullo, Rushad Heerjee, Shubhankar Sachdev
-
Publication number: 20260320221Abstract: Computer-implemented systems and methods are disclosed, including systems and methods utilizing language models for searching a large corpus of data. A computer-implemented method may include: receiving a first user input comprising a natural language query; vectorizing the first user input into a query vector; executing, using the query vector, a similarity search in a document search model to identify one or more similar document portions, where the document search model includes a plurality of vectors corresponding to a plurality of portions of a set of documents; generating a first prompt for a large language model (“LLM”), the first prompt including at least the first user input, and the one or more similar document portions; transmitting the first prompt to the LLM; receiving a first output from the LLM in response to the first prompt; and providing, via a user interface, the first output from the LLM.Type: ApplicationFiled: January 29, 2026Publication date: October 15, 2026Inventors: Anirvan Mukherjee, Craig De Souza, Edgar Gomes de Araujo, Johannes Beil, Jessica Winssinger, Michael Zullo, Rushad Heerjee, Shubhankar Sachdev
-
Publication number: 20260320220Abstract: Computer-implemented systems and methods are disclosed, including systems and methods utilizing language models for searching a large corpus of data. A computer-implemented method may include: receiving a first user input comprising a natural language query; vectorizing the first user input into a query vector; executing, using the query vector, a similarity search in a document search model to identify one or more similar document portions, where the document search model includes a plurality of vectors corresponding to a plurality of portions of a set of documents; generating a first prompt for a large language model (“LLM”), the first prompt including at least the first user input, and the one or more similar document portions; transmitting the first prompt to the LLM; receiving a first output from the LLM in response to the first prompt; and providing, via a user interface, the first output from the LLM.Type: ApplicationFiled: January 29, 2026Publication date: October 15, 2026Inventors: Anirvan Mukherjee, Craig De Souza, Edgar Gomes de Araujo, Johannes Beil, Jessica Winssinger, Michael Zullo, Rushad Heerjee, Shubhankar Sachdev
-
Publication number: 20260288999Abstract: Computer-implemented systems and methods are disclosed, including systems and methods utilizing language models for searching a large corpus of data. A computer-implemented method may include: receiving a first user input comprising a natural language query; vectorizing the first user input into a query vector; executing, using the query vector, a similarity search in a document search model to identify one or more similar document portions, where the document search model includes a plurality of vectors corresponding to a plurality of portions of a set of documents; generating a first prompt for a large language model (“LLM”), the first prompt including at least the first user input, and the one or more similar document portions; transmitting the first prompt to the LLM; receiving a first output from the LLM in response to the first prompt; and providing, via a user interface, the first output from the LLM.Type: ApplicationFiled: January 29, 2026Publication date: September 24, 2026Inventors: Anirvan Mukherjee, Craig De Souza, Edgar Gomes de Araujo, Johannes Beil, Jessica Winssinger, Michael Zullo, Rushad Heerjee, Shubhankar Sachdev
-
Publication number: 20260260013Abstract: Computer-implemented systems and methods are disclosed, including systems and methods utilizing language models for searching a large corpus of data. A computer-implemented method may include: receiving a first user input comprising a natural language query; vectorizing the first user input into a query vector; executing, using the query vector, a similarity search in a document search model to identify one or more similar document portions, where the document search model includes a plurality of vectors corresponding to a plurality of portions of a set of documents; generating a first prompt for a large language model (“LLM”), the first prompt including at least the first user input, and the one or more similar document portions; transmitting the first prompt to the LLM; receiving a first output from the LLM in response to the first prompt; and providing, via a user interface, the first output from the LLM.Type: ApplicationFiled: January 28, 2026Publication date: September 3, 2026Inventors: Anirvan Mukherjee, Craig De Souza, Edgar Gomes de Araujo, Johannes Beil, Jessica Winssinger, Michael Zullo, Rushad Heerjee, Shubhankar Sachdev
-
Patent number: 12717828Abstract: Computer-implemented systems and methods are disclosed, including systems and methods utilizing language models for generating data objects and/or updating an ontology. A computer-implemented method may include: employing one or more large language models (“LLMs”) to generate at least a data triple and a classified triple; executing, using the classified triple, a similarity search with reference to an ontology to determine that the classified triple at least partially matches one or more data object types defined in the ontology; in response to the determination, adding into a first database at least a first data object of a first data object type that represents a first entity in the data triple and a second data object of a second data object type that represents a second entity in the data triple.Type: GrantFiled: April 14, 2025Date of Patent: August 25, 2026Assignee: Palantir Technologies Inc.Inventors: Anirvan Mukherjee, Craig De Souza, Edgar Gomes de Araujo, Johannes Beil, Jessica Winssinger, Michael Zullo, Rushad Heerjee, Shubhankar Sachdev
-
Patent number: 12566881Abstract: Computer-implemented systems and methods are disclosed, including systems and methods utilizing language models for searching a large corpus of data. A computer-implemented method may include: receiving a first user input comprising a natural language query; vectorizing the first user input into a query vector; executing, using the query vector, a similarity search in a document search model to identify one or more similar document portions, where the document search model includes a plurality of vectors corresponding to a plurality of portions of a set of documents; generating a first prompt for a large language model (“LLM”), the first prompt including at least the first user input, and the one or more similar document portions; transmitting the first prompt to the LLM; receiving a first output from the LLM in response to the first prompt; and providing, via a user interface, the first output from the LLM.Type: GrantFiled: November 9, 2023Date of Patent: March 3, 2026Assignee: Palantir Technologies Inc.Inventors: Anirvan Mukherjee, Craig De Souza, Edgar Gomes de Araujo, Johannes Beil, Jessica Winssinger, Michael Zullo, Rushad Heerjee, Shubhankar Sachdev
-
Publication number: 20250252127Abstract: Computer-implemented systems and methods are disclosed, including systems and methods utilizing language models for generating data objects and/or updating an ontology. A computer-implemented method may include: employing one or more large language models (“LLMs”) to generate at least a data triple and a classified triple; executing, using the classified triple, a similarity search with reference to an ontology to determine that the classified triple at least partially matches one or more data object types defined in the ontology; in response to the determination, adding into a first database at least a first data object of a first data object type that represents a first entity in the data triple and a second data object of a second data object type that represents a second entity in the data triple.Type: ApplicationFiled: April 14, 2025Publication date: August 7, 2025Inventors: Anirvan Mukherjee, Craig De Souza, Edgar Gomes de Araujo, Johannes Beil, Jessica Winssinger, Michael Zullo, Rushad Heerjee, Shubhankar Sachdev
-
Patent number: 12299022Abstract: Computer-implemented systems and methods are disclosed, including systems and methods utilizing language models for generating data objects and/or updating an ontology. A computer-implemented method may include: employing one or more large language models (“LLMs”) to generate at least a data triple and a classified triple; executing, using the classified triple, a similarity search with reference to an ontology to determine that the classified triple at least partially matches one or more data object types defined in the ontology; in response to the determination, adding into a first database at least a first data object of a first data object type that represents a first entity in the data triple and a second data object of a second data object type that represents a second entity in the data triple.Type: GrantFiled: April 11, 2024Date of Patent: May 13, 2025Assignee: Palantir Technologies Inc.Inventors: Anirvan Mukherjee, Craig De Souza, Edgar Gomes de Araujo, Johannes Beil, Jessica Winssinger, Michael Zullo, Rushad Heerjee, Shubhankar Sachdev
-
Publication number: 20240354584Abstract: Computer-implemented systems and methods are disclosed, including systems and methods utilizing language models for creating and/or updating an ontology. A computer-implemented method may include: receiving tabular data from one or more data sources; generating an interactive graphical representation of at least a portion of the tabular data and connections between the portion of the tabular data; providing, via a user interface, the interactive graphical representation; receiving a user operation via the user interface, updating an ontology and/or generating transformations for adding data objects into a database.Type: ApplicationFiled: April 11, 2024Publication date: October 24, 2024Inventors: Anirvan Mukherjee, Craig De Souza, Edgar Gomes de Araujo, Johannes Beil, Jessica Winssinger, Michael Zullo, Rushad Heerjee, Shubhankar Sachdev
-
Publication number: 20240354436Abstract: Computer-implemented systems and methods are disclosed, including systems and methods utilizing language models for searching a large corpus of data. A computer-implemented method may include: receiving a first user input comprising a natural language query; vectorizing the first user input into a query vector; executing, using the query vector, a similarity search in a document search model to identify one or more similar document portions, where the document search model includes a plurality of vectors corresponding to a plurality of portions of a set of documents; generating a first prompt for a large language model (“LLM”), the first prompt including at least the first user input, and the one or more similar document portions; transmitting the first prompt to the LLM; receiving a first output from the LLM in response to the first prompt; and providing, via a user interface, the first output from the LLM.Type: ApplicationFiled: November 9, 2023Publication date: October 24, 2024Inventors: Anirvan Mukherjee, Craig De Souza, Edgar Gomes de Araujo, Johannes Beil, Jessica Winssinger, Michael Zullo, Rushad Heerjee, Shubhankar Sachdev
-
Publication number: 20240354322Abstract: Computer-implemented systems and methods are disclosed, including systems and methods utilizing language models for generating data objects and/or updating an ontology. A computer-implemented method may include: employing one or more large language models (“LLMs”) to generate at least a data triple and a classified triple; executing, using the classified triple, a similarity search with reference to an ontology to determine that the classified triple at least partially matches one or more data object types defined in the ontology; in response to the determination, adding into a first database at least a first data object of a first data object type that represents a first entity in the data triple and a second data object of a second data object type that represents a second entity in the data triple.Type: ApplicationFiled: April 11, 2024Publication date: October 24, 2024Inventors: Anirvan Mukherjee, Craig De Souza, Edgar Gomes de Araujo, Johannes Beil, Jessica Winssinger, Michael Zullo, Rushad Heerjee, Shubhankar Sachdev