公开(公告)号：US20240354322A1

公开(公告)日：2024-10-24

申请号：US18632900

申请日：2024-04-11

Applicant: Palantir Technologies Inc.

Inventor： Anirvan Mukherjee ,  Craig De Souza ,  Edgar Gomes de Araujo ,  Johannes Beil ,  Jessica Winssinger ,  Michael Zullo ,  Rushad Heerjee ,  Shubhankar Sachdev

IPC: G06F16/33 ,  G06F18/2415

CPC classification number: G06F16/3344 ,  G06F18/2415

Abstract: 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.

公开(公告)号：US12299022B2

公开(公告)日：2025-05-13

申请号：US18632900

申请日：2024-04-11

Applicant: Palantir Technologies Inc.

Inventor： Anirvan Mukherjee ,  Craig De Souza ,  Edgar Gomes de Araujo ,  Johannes Beil ,  Jessica Winssinger ,  Michael Zullo ,  Rushad Heerjee ,  Shubhankar Sachdev

IPC: G06F16/00 ,  G06F16/334 ,  G06F18/2415 ,  G06N3/0895

Abstract: 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.

公开(公告)号：US20250110753A1

公开(公告)日：2025-04-03

申请号：US18794904

申请日：2024-08-05

Applicant: Palantir Technologies Inc.

Inventor： Johannes Beil ,  Pavlo Tyshevskyi ,  Max-Philipp Schrader ,  Sriram Krishnan ,  Michael Zullo ,  Rushad Heerjee ,  Anirvan Mukherjee

IPC: G06F9/448 ,  G06F40/30

Abstract: Computer-implemented systems and methods are disclosed, including systems and methods for automatically solving problems. A computer-implemented method may include: by an agent service configured to interact with an LLM to complete a run: providing an LLM with access to a state machine, executing an initial state of the state machine with the LLM, determining a subsequent state of the state machine based on at least an initial LLM output, and executing the subsequent state of the state machine.

公开(公告)号：US20240354584A1

公开(公告)日：2024-10-24

申请号：US18632958

申请日：2024-04-11

Applicant: Palantir Technologies Inc.

Inventor： Anirvan Mukherjee ,  Craig De Souza ,  Edgar Gomes de Araujo ,  Johannes Beil ,  Jessica Winssinger ,  Michael Zullo ,  Rushad Heerjee ,  Shubhankar Sachdev

IPC: G06N3/0895

CPC classification number: G06N3/0895

Abstract: 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.

公开(公告)号：US20240354436A1

公开(公告)日：2024-10-24

申请号：US18505912

申请日：2023-11-09

Applicant: Palantir Technologies Inc.

Inventor： Anirvan Mukherjee ,  Craig De Souza ,  Edgar Gomes de Araujo ,  Johannes Beil ,  Jessica Winssinger ,  Michael Zullo ,  Rushad Heerjee ,  Shubhankar Sachdev

IPC: G06F21/62 ,  G06F16/33

CPC classification number: G06F21/6227 ,  G06F16/3344 ,  G06F16/3347

Abstract: 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.