US 12,248,471 B2
Systems and methods for generating and displaying a data pipeline using a natural language query, and describing a data pipeline using natural language
Joseph Rafidi, Washington, DC (US); James Thompson, San Francisco, CA (US); Mohamed Zaki Trache, London (GB); Felix-Gabriel Mance, London (GB); and Martin Copes, London (GB)
Assigned to Palantir Technologies Inc., Denver, CO (US)
Filed by Palantir Technologies Inc., Denver, CO (US)
Filed on Dec. 22, 2022, as Appl. No. 18/087,023.
Claims priority of provisional application 63/425,071, filed on Nov. 14, 2022.
Claims priority of provisional application 63/395,987, filed on Aug. 8, 2022.
Prior Publication US 2024/0045863 A1, Feb. 8, 2024
Int. Cl. G06F 16/2453 (2019.01); G06F 16/242 (2019.01)
CPC G06F 16/24542 (2019.01) [G06F 16/243 (2019.01)] 16 Claims
OG exemplary drawing
 
1. A method for generating a data pipeline, the method comprising:
receiving a natural language (NL) query and a target dataset including one or more target data types;
receiving a model result generated based on the NL query and the target dataset, the model result including a query in a standard query language, the model result being generated using one or more computing models, wherein the model result includes a confidence score associated with the query in the standard query language;
generating the data pipeline based at least in part on the query in the standard query language, the data pipeline comprising one or more data pipeline elements, at least one data pipeline element of the one or more pipeline elements being corresponding to a query component of the query in the standard query language; and
receiving an additional query generated based on the NL query, wherein the additional query is generated if the confidence score is below a predetermined threshold;
wherein the data pipeline is configured to generate data of the one or more target data types;
wherein the method is performed using one or more processors.