Granted Patent B2

US 12,493,615 · App. 19/092,787 · Granted Dec 9, 2025

Inventors: Daniel Lazarev (Tel Aviv, IL); Barak Sharoni (Tel Aviv, IL); Bar Magnezi (Tel Aviv, IL)

Assignee: Wiz, Inc.

G06F16/243G06F16/212G06F16/2455

Abstract

Claims (59)

1 . A method for generating a database query based on a natural language query, comprising:

receiving an unstructured natural language query directed to a security database, wherein the security database includes a representation of a computing environment;

selecting a group of database queries from a plurality of preexisting database queries based on a similarity to the unstructured natural language query;

generating a context for processing by a language model, the context including the selected group of database queries, an identified technology, and a schema of the computing environment;

processing a prompt and the generated context utilizing the language model to generate a second database query; and

executing the second database query on the security database.

2 . The method of claim 1 , wherein selecting the group of database queries further comprises:

vectorizing each of: the preexisting database queries and the unstructured natural language query;

determining a similarity score between vector of a preexisting database query and a vector of the unstructured natural language query; and

selecting preexisting database queries based on a similarity score exceeding a predetermined threshold.

3 . The method of claim 2 , further comprising:

re-ranking the selected preexisting database queries; and

generating the context based on the re-ranked preexisting database queries.

4 . The method of claim 1 , further comprising:

generating the prompt for a large language model based on the unstructured natural language query and a first database query.

5 . The method of claim 4 , further comprising:

determining a data schema, the data schema utilized to represent an entity of the computing environment; and

generating the prompt further based on the determined data schema.

6 . The method of claim 5 , further comprising:

determining the data schema based on the unstructured natural language query.

7 . The method of claim 4 , further comprising:

generating the prompt further based on a technology identifier, the technology identifier determined based on data extracted from the unstructured natural language query.

8 . The method of claim 1 , further comprising:

parsing the received natural language query to a textual input including a plurality of text elements; and

matching a text element of the plurality of text elements to a data schema.

9 . A non-transitory computer-readable medium storing a set of instructions for generating a database query based on a natural language query, the set of instructions comprising:

one or more instructions that, when executed by one or more processors of a device, cause the device to:

receive an unstructured natural language query directed to a security database, wherein the security database includes a representation of a computing environment;

select a group of database queries from a plurality of preexisting database queries based on a similarity to the unstructured natural language query;

generate a context for processing by a language model, the context including the selected group of database queries, an identified technology, and a schema of the computing environment;

process a prompt and the generated context utilizing the language model to generate a second database query; and

execute the second database query on the security database.

10 . A system for generating a database query based on a natural language query comprising:

a processing circuitry;

a memory, the memory containing instructions that, when executed by the processing circuitry, configure the system to:

receive an unstructured natural language query directed to a security database, wherein the security database includes a representation of a computing environment;

select a group of database queries from a plurality of preexisting database queries based on a similarity to the unstructured natural language query;

generate a context for processing by a language model, the context including the selected group of database queries, an identified technology, and a schema of the computing environment;

process a prompt and the generated context utilizing the language model to generate a second database query; and

execute the second database query on the security database.

11 . The system of claim 10 , wherein the memory contains further instructions that, when executed by the processing circuitry for selecting the group of database queries, further configure the system to:

vectorize each of: the preexisting database queries and the unstructured natural language query;

determine a similarity score between vector of a preexisting database query and a vector of the unstructured natural language query; and

select preexisting database queries based on a similarity score exceeding a predetermined threshold.

12 . The system of claim 11 , wherein the memory contains further instructions which when executed by the processing circuitry further configure the system to:

re-rank the selected preexisting database queries; and

generate the context based on the re-ranked preexisting database queries.

13 . The system of claim 10 , wherein the memory contains further instructions which when executed by the processing circuitry further configure the system to:

generate the prompt for a large language model based on the unstructured natural language query and a first database query.

14 . The system of claim 13 , wherein the memory contains further instructions which when executed by the processing circuitry further configure the system to:

determine a data schema, the data schema utilized to represent an entity of the computing environment; and

generate the prompt further based on the determined data schema.

15 . The system of claim 14 , wherein the memory contains further instructions which when executed by the processing circuitry further configure the system to:

determine the data schema based on the unstructured natural language query.

16 . The system of claim 13 , wherein the memory contains further instructions which when executed by the processing circuitry further configure the system to:

generate the prompt further based on a technology identifier, the technology identifier determined based on data extracted from the unstructured natural language query.

17 . The system of claim 10 , wherein the memory contains further instructions which when executed by the processing circuitry further configure the system to:

parse the received natural language query to a textual input including a plurality of text elements; and

match a text element of the plurality of text elements to a data schema.

Assignments (1)

Continuity (3)

References Cited (141)

Cited By (2)

US 12,626,067 US 12,717,834