Granted Patent B2

US 12,411,667 · App. 18/143,397 · Granted Sep 9, 2025

Inventors: Shubham Gupta (Bhopal, IN); Sparsh Dutta (Jaipur, IN); Rishika Khandelwal (Jaipur, IN); Paras Gupta (Agra, IN); Vibhuti Agrawal (Bangaluru, IN)

Assignee: INNOVACCER INC.

G06F8/36G06F8/51

Abstract

Claims (27)

1. A method for generating a required feature output by providing a FaaS (Function-as-a-Service) based feature library using a DAG (Directed Acyclic Graph), the method comprising:

configuring a processing unit, the processing unit executing a plurality of computer instructions stored in a memory for:

configuring a feature library to store logic codes generated for a plurality of features;

deploying the feature library on a FaaS engine;

receiving, by the FaaS engine, at least one feature selection configuration from a user;

extracting, by the FaaS engine, raw data from at least one resource adapter connected to the FaaS engine;

using the DAG for implementing at least one transformation based on the at least one feature selection configuration; and

generating the required feature output based on the at least one transformation.

2. The method of claim 1 , wherein each of the plurality of features is derived from at least one set of data available in at least one raw data source.

3. The method of claim 2 , wherein the FaaS engine has access to the at least one raw data source to extract the at least one set of data for deriving the plurality of features.

4. The method of claim 1 , wherein the plurality of features includes at least one of: raw data or developed features.

5. The method of claim 1 , wherein a new tag for stored features is released for facilitating new runs of the stored features.

6. The method of claim 5 , wherein the stored features are selected using a configurable input for future runs.

7. A system for generating a required feature output by providing a FaaS (Function-as-a-Service) based feature library using a DAG (Directed Acyclic Graph), the system comprising:

a memory and

a processing unit, the processing unit configured to execute a plurality of computer instructions stored in the memory for:

configuring a feature library to store logic codes generated for a plurality of features;

deploying the feature library on a FaaS engine;

receiving, by the FaaS engine, at least one feature selection configuration from a user;

extracting, by the FaaS engine, raw data from at least of the connected resource adapters;

using the DAG for implementing at least one transformation based on the at least one feature selection configuration; and

generating the required feature output based on the at least one transformation.

8. The system of claim 7 , wherein each of the plurality of features is derived from at least one set of data available in at least one raw data source.

9. The system of claim 8 , wherein the FaaS engine has access to the at least one raw data source to extract the at least one set of data for deriving the plurality of features.

10. The system of claim 7 , wherein the plurality of features includes at least one of: raw data or developed features.

11. The system of claim 7 , wherein a new tag for stored features is released for facilitating new runs of the stored features.

12. The system of claim 11 , wherein the stored features are selected using a configurable input for future runs.

Assignments (2)

Priority Claims (1)

Continuity (1)

References Cited (223)