Artificial intelligence system for processing data from disparate data sources

Inventors: Akash Magoon (New York, NY); Aman Magoon (New York, NY); Daniel Young (New York, NY); Paul Cho (New York, NY); Gerardo Santacruz (New York, NY); Billy Bastardi (New York, NY); Manoj Kintali (New York, NY); Melanie Supple (New York, NY)

Assignee: Adonis Technology, Inc.

G06F16/258 G06F16/212 G06F16/215

View Patent ↗

Loading inventors, assignments & file history…

Monitor This Case

Get email alerts when status or documents change.

Order Certified Copies

Most orders are placed with the USPTO same day — all within 24 business hours.

Order via The Patent Place →

Pre-filled with this patent's details

Quick Facts

Patent No.: US 12670177
App. No.: 19/007,387
Granted: Jun 30, 2026
Kind: B1

External Links

USPTO Patent Center↗ Full Patent PDF↗

Abstract

Processing and transforming data using an artificial intelligence (AI) system is described. A machine-learning-based data profiling tool may be used on first data associated with a first data source and second data associated with a second data source to generate first data profile content identifying first data schema content and second data profile content identifying second data schema content. A schema matching operation may be performed to generate schema matching data identifying a match between a first schema and a second schema. A data transformation operation may be performed to generate transformed data based on converting at least one of the first data or the second data from a source data format to a unified data format.

Claims (37)

1 . A system, comprising:

a memory subsystem storing instructions; and

processing circuitry configured to execute the instructions to cause the system to:

generate first data profile content by performing, using a machine-learning-based data profiling tool, an analysis on first data associated with a first data source, wherein the first data profile content identifies first data schema content associated with the first data;

generate second data profile content by performing, using the machine-learning-based data profiling tool, an analysis on second data associated with a second data source, wherein the second data profile content identifies second data schema content associated with the second data;

perform, using a machine-learning-based schema matching component, a schema matching operation to generate schema matching data identifying a match between a first schema associated with the first data schema content and a second schema associated with the second data schema content;

generate transformed data by performing, using a machine-learning-based data transformation component and based on the schema matching data, a data transformation operation based on converting at least one of the first data or the second data from a source data format to a unified data format associated with a unified data schema; and

store a result of the data transformation operation within a database.

2 . The system of claim 1 , wherein the processing circuitry is configured to execute the instructions to further cause the system to perform, using an a machine-learning-based data cleaning component, a data cleaning operation to correct at least one anomaly in at least one of the first data or the second data.

3 . The system of claim 1 , wherein the processing circuitry is configured to execute the instructions to further cause the system to perform, using a machine-learning-based standardization tool, a standardization operation to map a first medical code format associated with the first data to a second medical code format associated with the second data.

4 . The system of claim 1 , wherein the processing circuitry is configured to execute the instructions to further cause the system to perform, using a machine-learning-based completion tool, a completion operation to complete at least one incomplete field included in the first data or the second data.

5 . The system of claim 4 , wherein, to cause the system to perform the completion operation, the processing circuitry is configured to execute the instructions to cause the system to perform the completion operation based on at least one of an historical trend or a similarity analysis that compares the at least one incomplete field to a complete field included in another data.

6 . The system of claim 1 , wherein the processing circuitry is configured to execute the instructions to further cause the system to generate the unified data schema based on at least one pattern associated with the first schema and the second schema.

7 . The system of claim 1 , wherein the processing circuitry is configured to execute the instructions to further cause the system to perform, using a machine-learning-based entity resolution component, an entity resolution operation to resolve at least one of an entity difference between first entity information associated with the first data schema content and second entity information associated with the second data schema content or a duplicate record difference between the first data schema content and the second data schema content.

8 . The system of claim 7 , wherein the entity resolution operation comprises at least one of a fuzzy matching operation, a clustering operation, or a deep learning operation based on the at least one of the entity difference or the duplicate record difference.

9 . A method, comprising:

generating first data profile content by performing, using a machine-learning-based data profiling tool, an analysis on first data associated with a first data source, wherein the first data profile content identifies first data schema content associated with the first data;

generating second data profile content by performing, using the machine-learning-based data profiling tool, an analysis on second data associated with a second data source, wherein the second data profile content identifies second data schema content associated with the second data;

performing, using an a machine-learning-based schema matching component, a schema matching operation to generate schema matching data identifying a match between a first schema associated with the first data schema content and a second schema associated with the second data schema content;

generating transformed data by performing, using a machine-learning-based data transformation component and based on the schema matching data, a data transformation operation based on converting at least one of the first data or the second data from a source data format to a unified data format associated with a unified data schema; and

storing the transformed data within a database.

10 . The method of claim 9 , wherein the first data profile content further identifies first data type information associated with the first data, and wherein the second data profile content further identifies second data type information associated with the second data.

11 . The method of claim 9 , wherein the first data profile content further identifies at least one discrepancy between the first data schema content and the second data schema content.

12 . The method of claim 9 , wherein the schema matching data is indicative of a match between a first column name associated with the first data schema content and a second column name associated with the second data schema content.

13 . The method of claim 9 , wherein the machine-learning-based schema matching component comprises a natural language processing component configured to use natural language processing to detect at least one of a relationship between a first column name associated with the first data schema content and a second column name associated with the second data schema content, a relationship between a first description associated with the first data schema content and a second description associated with the second data schema content, or a relationship between a first metadata associated with the first data schema content and a second metadata associated with the second data schema content.

14 . The method of claim 9 , wherein the machine-learning-based schema matching component comprises a rule engine configured to apply one or more rules to the first data profile content and the second data profile content to generate an identification of the at least one of first data type information or second data type information.

15 . The method of claim 14 , wherein the machine-learning-based schema matching component is further configured to update the one or more rules based on a machine learning clustering operation.

16 . A non-transitory computer readable medium storing instructions operable to cause one or more processors to perform operations comprising:

performing, using a machine-learning-based schema matching component, a schema matching operation to generate schema matching data identifying a match between a first schema associated with the first data schema content and a second schema associated with the second data schema content;

storing a result of the data transformation operation within a database.

17 . The non-transitory computer readable medium of claim 16 , the operations further comprising performing, using a machine-learning-based data integration component, a data integration operation to establish at least one data flow between a data ingestion pipeline and at least one of the first data source or the second data source.

18 . The non-transitory computer readable medium of claim 17 , wherein the machine-learning-based data integration component comprises a machine-learning-powered application programming interface, and wherein performing the data integration operation comprises invoking the machine-learning-powered application programming interface to perform the at least one data flow.

19 . The non-transitory computer readable medium of claim 17 , the operations further comprising performing, using the machine-learning-based data integration component, an additional data integration operation to synchronize a plurality of databases.

20 . The non-transitory computer readable medium of claim 16 , the operations further comprising managing the database using a machine-learning-based data management component configured to manage at least one of data consistency, data versioning, or data quality.