Palantir Technologies Inc. patent applications on December 5th, 2024
Patent Applications by Palantir Technologies Inc. on December 5th, 2024
Palantir Technologies Inc.: 13 patent applications
Palantir Technologies Inc. has applied for patents in the areas of G06F9/455 (2), G06F9/48 (2), G06F16/242 (2), G06T7/292 (1), G06F11/14 (1) G06F16/243 (2), G06F9/45558 (1), G06F9/4881 (1), G06F11/3656 (1), G06F16/212 (1)
With keywords such as: data, receiving, security, user, llm, level, response, language, prompt, and determining in patent application abstracts.
Patent Applications by Palantir Technologies Inc.
Inventor(s): Jakob Frick of London (GB) for palantir technologies inc., Sriram Krishnan of Jersey City NJ (US) for palantir technologies inc., Thomas Powell of London (GB) for palantir technologies inc., David Lisuk of Brooklyn NY (US) for palantir technologies inc., Mayada Gonimah of New York NY (US) for palantir technologies inc.
IPC Code(s): G06F9/455, G06F3/0484
CPC Code(s): G06F9/45558
Abstract: computer-implemented systems and methods are disclosed, including for integration and management of computer-based models in a model management. a computer-implemented method may include, for example, receiving one or more inputs including requesting to add a first model to a defined modeling objective, specifying a first model location, and/or providing a first model adapter configuration. in response to the one or more user inputs, the method may further include storing or providing access to information associated with the first model, associating the first model with a defined modeling objective, and/or implementing the first model adapter configuration to provide communication with the first model.
Inventor(s): Yishak Tofik Mohammed of Jersey City NJ (US) for palantir technologies inc., Bruno Rahle of London (GB) for palantir technologies inc., Clara Lebbos of Neuilly-sur-Seine (FR) for palantir technologies inc., Charles Sese of Geneve (CH) for palantir technologies inc., Jaafar Rammal of London (GB) for palantir technologies inc., Naga Sri Subhash Nalluru of London (GB) for palantir technologies inc., Wiem Gharbi of Zurich (CH) for palantir technologies inc.
IPC Code(s): G06F9/48
CPC Code(s): G06F9/4881
Abstract: methods, apparatuses and computer programs are for executing complex computing tasks in a computing platform are provided. according to one aspect, a method comprises receiving, by a planning agent, a use case input indicating an objective for completion in the computing platform. the planning agent decomposes, by the planning agent, the use case input into a plurality of tasks for achieving the objective. the planning agent provides each of the plurality of tasks to a respective task agent for execution. for each task of the plurality of tasks, the respective task agent identifies a tool suitable for performing the task from a plurality of tools. the task agent uses the identified tool to execute an operation corresponding to the respective task in the computing platform.
Inventor(s): Matthew Hawes of Denver CO (US) for palantir technologies inc., Ankit Shankar of San Francisco CA (US) for palantir technologies inc., Morten Telling of Copenhagen (DK) for palantir technologies inc., Jack Dobson of New York NY (US) for palantir technologies inc., Adil Majid of New York NY (US) for palantir technologies inc.
IPC Code(s): G06F11/36
CPC Code(s): G06F11/3656
Abstract: the disclosure is directed to methods and systems for improving interactions with a large language model (llm). an artificial intelligence system (ais) can receive user inputs via a graphical user interface indicating a task to be performed by the llm, one or more tools which may be accessed by the ais in response to tool calls from the llm, and an output schema for structuring a format of a response from the llm. the ais can generate a prompt for the llm based on the user input. the prompt can include indications of the one or more tools, one or more example tool operations, the task to be performed, and an indication of the output schema. the ais can include a debugging application or module enabling rich debugging of language model interactions in a single view.
Inventor(s): Daniel Zangri of Austin TX (US) for palantir technologies inc., Nicholas Morgan of Salt Lake City UT (US) for palantir technologies inc., Hunter Herman of Palo Alto CA (US) for palantir technologies inc.
IPC Code(s): G06F16/21
CPC Code(s): G06F16/212
Abstract: systems and methods for managing and/or using observation schemas are provided. in some embodiments, a method includes receiving a data stream from one or more data sources; accessing a first observation schema including one or more built-in fields and one or more custom fields associated with the received data stream; receiving a configuration associated with at least one of the one or more custom fields; and generating a second observation schema based on the configuration and the first observation schema.
Inventor(s): Matthew Hawes of Denver CO (US) for palantir technologies inc., Ankit Shankar of San Francisco CA (US) for palantir technologies inc., Morten Telling of Copenhagen (DK) for palantir technologies inc., Jack Dobson of New York NY (US) for palantir technologies inc., Adil Majid of New York NY (US) for palantir technologies inc.
IPC Code(s): G06F16/242, G06F16/2455
CPC Code(s): G06F16/243
Abstract: a system may receive a natural language query. a system may receive indications of one or more data object types, wherein each of the one or more data object types is associated with a respective one or more properties. a system may receive references to one or more data sets, wherein the one or more data sets are each associated with at least a respective data object type. a system may transmit a prompt to a large language model (“llm”), the prompt comprising at least: the natural language query, the indications of the one or more data object types, and the references to the one or more data sets. a system may receive, from the llm, a response to the prompt, wherein the response includes indications of: at least a first reference to a first data set and a query to be applied to the first data set.
Inventor(s): Matthew Hawes of Denver CO (US) for palantir technologies inc., Ankit Shankar of San Francisco CA (US) for palantir technologies inc., Matthew Bayer of Brooklyn NY (US) for palantir technologies inc.
IPC Code(s): G06F16/242
CPC Code(s): G06F16/243
Abstract: a system may receive a natural language query and receive an indication of a format of a first computer language as well as an indication of one or more computer-based tools stored in and/or accessible by the system. the system can transmit a prompt to a large language model (“llm”). the prompt may include the natural language query, the indication of the format, and the indication of the one or more computer-based tools. the system can receive, from the llm, a response to the prompt in the format of the first computer language. the system can parse the response in the first computer language to identify at least: a computer-based tool of the one or more computer-based tools. the system can generate a second query in a second computer language and provide the second query in the second computer language to the computer-based tool.
Inventor(s): Katherine Brainard of East Orange NJ (US) for palantir technologies inc., Ernest Zeidman of Palo Alto CA (US) for palantir technologies inc., Ilya Nepomnyashchiy of Mountain View CA (US) for palantir technologies inc.
IPC Code(s): G06F16/248, G06F7/14, G06F16/27, G06F16/28, G06F16/9535
CPC Code(s): G06F16/248
Abstract: a method of contextual modification of data sharing constraints is disclosed. the method comprises receiving a data sharing request to share a first data model with a database associated with a second data model; generating a shareable version of the first data model in response to the data sharing request; determining a parameter value used to perform a data model merging operation to merge the shareable version of the first data model with the second data model, the parameter value indicating whether to execute or skip a particular process during the data model merging operation; determining context data for the data model merging operation based on the generating; modifying the parameter value based on the context data; performing the data model merging operation using the modified parameter value.
Inventor(s): Matthew Hawes of Denver CO (US) for palantir technologies inc., Ankit Shankar of San Francisco CA (US) for palantir technologies inc., Morten Telling of Copenhagen (DK) for palantir technologies inc., Jack Dobson of New York NY (US) for palantir technologies inc., Adil Majid of New York NY (US) for palantir technologies inc.
IPC Code(s): G06F21/31, G06F16/903
CPC Code(s): G06F21/31
Abstract: computer-implemented systems and methods are disclosed, including for determining permissions for nondeterministic model output. a computer-implemented method may include, for example, receiving one or more user inputs including a first user input providing at least a portion of a first prompt for a query for a first nondeterministic model. a computer-implemented method may in response to receiving the one or more user inputs include: executing the query, by the first nondeterministic model, to generate an output, determining a first one or more data inputs used by the first nondeterministic model during execution of the query, determining a first set of permissions associated with the first one or more data inputs; and applying a second set of permissions to at least a first portion of the output based on the first set of permissions.
Inventor(s): Daniel Zangri of Austin TX (US) for palantir technologies inc., Nicholas Morgan of Salt Lake City UT (US) for palantir technologies inc., Hunter Herman of Palo Alto CA (US) for palantir technologies inc., Matthew Meacham of Washington DC (US) for palantir technologies inc.
IPC Code(s): G06F21/60, G06F16/9032
CPC Code(s): G06F21/604
Abstract: systems and methods for generating and/or managing maps are provided. in some embodiments, a method includes receiving a map request from a first user to generate a map with a map security level, in response to determining that the map security level satisfies the first security level threshold, generating the map with the map security level, receiving a query from the first user, identifying a data feed associated with the query, receiving the data feed from a data source, the data feed including a plurality of data items and each data item corresponding to a corresponding data security level, for each data item of the plurality of data items, determining whether the data item satisfies a second security condition, and adding one or more data items of the plurality of data items that satisfy the second security condition on the map.
Inventor(s): Daniel Zangri of Austin TX (US) for palantir technologies inc., Nicholas Morgan of Salt Lake City UT (US) for palantir technologies inc., Joshua Dufault of Alexandria VA (US) for palantir technologies inc., Matthew Meacham of Washington DC (US) for palantir technologies inc.
IPC Code(s): G06F21/62
CPC Code(s): G06F21/6218
Abstract: systems and methods for generating, managing, and/or providing notifications are provided. in some embodiments, a method includes displaying a map corresponding to a map security level to a user, receiving an indication of a geospatial area on the map, receiving a data stream, the data stream corresponds to a data security level, determining if the data security level satisfies a first security level threshold, in response to determining that the data security level satisfies the first security level threshold, in response to detecting the entity that satisfies the notification condition, generating a geospatial notification including information representing the geospatial area and the entity, determining if a user security level for the user satisfies a second security level threshold, and in response to determining that the user security level satisfies the second security level threshold, presenting the geospatial notification to the user.
Inventor(s): Matthew Hawes of Denver CO (US) for palantir technologies inc., Ankit Shankar of San Francisco CA (US) for palantir technologies inc., Morten Telling of Copenhagen (DK) for palantir technologies inc., Adil Majid of New York NY (US) for palantir technologies inc., Jack Dobson of New York NY (US) for palantir technologies inc.
IPC Code(s): G06N3/08
CPC Code(s): G06N3/08
Abstract: an artificial intelligence system can be used to respond to natural language inputs. the ai system may, for example, receive a first user input for a llm, generate a first prompt based on the first user input, transmit the first prompt to an llm, receive an output from the llm, and evaluate the output from the llm with reference to one or more validation tests. responsive to determining that the output from the llm is not validated, generate a second prompt for the llm, where the second prompt indicates at least an aspect of the output that caused the output to not be evaluated (e.g., a portion of the output that may need to be updated or corrected), transmit the second prompt to the llm, and receive an updated output from the llm. the ai system can include an application for testing functions that utilize interactions with language models.
Inventor(s): Daniel Zangri of Austin TX (US) for palantir technologies inc.
IPC Code(s): G06T7/292, G01S13/66, G01S15/06, G01S17/06, G01S19/03
CPC Code(s): G06T7/292
Abstract: systems and methods for correlating data (e.g., sensor data) with entities and/or tracking entities are provided. in some embodiments, a method includes displaying one or more indications of one or more entities, receiving a first input to select the target entity from the one or more entities, in response to receiving the first input, displaying an interactive element for associating one or more sensors to the target entity, displaying the one or more sensors that are active, receiving a second input associated with the interactive element, in response to receiving the second input, creating a link between the target entity and at least one sensor of the one or more sensors, and updating one or more entity properties of the target entity based on sensor data of the at least one sensor and the created link.
Inventor(s): Greg DeArment of Seattle WA (US) for palantir technologies inc., Mark Elliot of New York NY (US) for palantir technologies inc., Jonathan Yu of Palo Alto CA (US) for palantir technologies inc., Jon Paek of Sunnyvale CA (US) for palantir technologies inc., Phillip Chen of New York NY (US) for palantir technologies inc., Brian Toth of Palo Alto CA (US) for palantir technologies inc., David Tolnay of Menlo Park CA (US) for palantir technologies inc., Daniel Rothfus of Fort Worth TX (US) for palantir technologies inc., Bradley Moylan of Palo Alto CA (US) for palantir technologies inc.
IPC Code(s): H04L67/1095, G06F8/71, G06F9/44, G06F9/445, G06F9/455, G06F9/46, G06F9/48, G06F9/50, G06F11/07, G06F11/14, H04L41/5054
CPC Code(s): H04L67/1095
Abstract: a method comprises receiving, at a host, a request to set new service configuration information for a target service in a distributed computing environment; retrieving a current revision identifier of a current revision of service configuration information for the target service from a revision index key in a local replica of a configuration store, the revision index key storing one or more key-value pairs, a key in a specific key-value pair identifying the target service; assigning a new revision identifier based on the current revision identifier; writing the new service configuration information into a new revision of the service configuration information in the local replica; updating the revision index key in an atomic compare-and-swap operation, the compare comprising verifying that the current revision identifier in the revision index key has remained the same since the retrieving, the swap comprising updating the specific key-value pair with the new revision identifier.
Palantir Technologies Inc. patent applications on December 5th, 2024
- Palantir Technologies Inc.
- G06F9/455
- G06F3/0484
- CPC G06F9/45558
- Palantir technologies inc.
- G06F9/48
- CPC G06F9/4881
- G06F11/36
- CPC G06F11/3656
- G06F16/21
- CPC G06F16/212
- G06F16/242
- G06F16/2455
- CPC G06F16/243
- G06F16/248
- G06F7/14
- G06F16/27
- G06F16/28
- G06F16/9535
- CPC G06F16/248
- G06F21/31
- G06F16/903
- CPC G06F21/31
- G06F21/60
- G06F16/9032
- CPC G06F21/604
- G06F21/62
- CPC G06F21/6218
- G06N3/08
- CPC G06N3/08
- G06T7/292
- G01S13/66
- G01S15/06
- G01S17/06
- G01S19/03
- CPC G06T7/292
- H04L67/1095
- G06F8/71
- G06F9/44
- G06F9/445
- G06F9/46
- G06F9/50
- G06F11/07
- G06F11/14
- H04L41/5054
- CPC H04L67/1095
