Structured filtering for a natural language input based on generative artificial intelligence
AssigneeQuorum
InventorsJonathan Marks, Petru Hincu
Life of this patent
Estimating the term…
Abstract
This disclosure provides systems, devices, apparatus, and methods, including computer programs encoded on storage media, for filtering a dataset. The apparatus may receive, via a user interface, a natural language input for a search of the dataset. The natural language input is an unstructured input. The apparatus maps the unstructured input to one or more filters associated with the natural language input based on execution of a generative AI model. The mapping of the unstructured input transforms the unstructured input into a structured input. The apparatus outputs, via the user interface, a result of the search based on an application of the one or more filters to the dataset.
Claims22
A method of filtering a dataset, comprising:
- receiving, via a user interface, a natural language input for a search of the dataset, the natural language input being an unstructured input;
- mapping the unstructured input to one or more filters associated with the natural language input based on execution of a generative artificial intelligence (AI) model, the mapping being to transform the unstructured input into a structured input, wherein to transform the unstructured input into the structured input, the mapping of the unstructured input is made to a reduced number of filters associated with reducing a size of the dataset;
- and
- outputting, via the user interface, a result of the search based on an application of the reduced number of filters to the dataset.
(canceled)
An apparatus for filtering a dataset, comprising:
- a memory;
- and
- at least one processor coupled to the memory and configured to:
- receive, via a user interface, a natural language input for a search of the dataset, the natural language input being an unstructured input;
- map the unstructured input to one or more filters associated with the natural language input based on execution of a generative artificial intelligence (AI) model, the mapping being to transform the unstructured input into a structured input, wherein to transform the unstructured input into the structured input, the mapping of the unstructured input is made to a reduced number of filters associated with reducing a size of the dataset;
- and
- output, via the user interface, a result of the search based on an application of the reduced number of filters to the dataset.
(canceled)
A non-transitory computer-readable medium storing computer executable code, the code when executed by at least one processor causes the at least one processor to:
- receive, via a user interface, a natural language input for a search of a dataset, the natural language input being an unstructured input;
- map the unstructured input to one or more filters associated with the natural language input based on execution of a generative artificial intelligence (AI) model, the mapping being to transform the unstructured input into a structured input, wherein to transform the unstructured input into the structured input, the mapping of the unstructured input is made to a reduced number of filters associated with reducing a size of the dataset;
- and
- output, via the user interface, a result of the search based on an application of the reduced number of filters to the dataset.
Dependencies are inferred from the claim text.