Methods and systems for data leveraging

Patent metadata

Field	Value
Publication number	US-12182129-B2
Application number	US-202318198863-A
Country	US
Kind code	B2
Filing date	May 18, 2023
Priority date	May 18, 2023
Publication date	Dec 31, 2024
Grant date	Dec 31, 2024

Abstract

A method for facilitating transfer of a new dataset across a network may include the following steps: (a) querying the global dataset via a computer processor to identify an existing dataset having data points corresponding to the new dataset; (b) identifying historical data rules previously used for a set of data transfers relating to the existing dataset; and (c) using the historical data rules to assist a machine learning engine in generating data rules for use with a data transfer relating to the new dataset.

First claim

What is claimed is:

1. A method for facilitating a transfer of a newly received dataset across a data network having access to a searchable global dataset, the method utilizing a computer processor and one or more non-transitory computer-readable media storing computer-executable instructions, wherein the instructions, when executed by the computer processor, automatically generate data rules for said newly received dataset, the method comprising the steps of:
said computer processor querying said global dataset to identify an existing dataset having one or more data patterns similar to said newly received dataset, wherein the existing dataset is a dataset that references a same entity that is contained within the newly received dataset and contains data fields different from the data fields contained within the newly received dataset;
said computer processor identifying historical data rules used for a set of data transfers relating to said existing dataset; and
a machine learning engine using said historical data rules to optimize data rules for use with a data transfer relating to said newly received dataset, thereby facilitating the transfer of said newly received dataset, wherein the machine learning engine is a quantum optimization engine configured to utilize one or more quantum algorithms to process an initial data transfer rule set from the existing dataset to process the newly received data, and further optimize the data rules using the newly received data;
wherein said machine learning engine comprises a modality selected from a group consisting of natural language processing, a trained neural network model, a deep learning model, a supervised machine learning model, and an artificial intelligence model; and
said machine learning engine is a different learning engine from a learning engine used to generate the data rules.

2. The method of claim 1 , wherein said machine learning engine utilizes said historical data rules as an initial set of data rules and subsequently tunes said initial set of data rules using said newly received dataset.

3. The method of claim 1 , wherein said machine learning engine utilizes said newly received dataset to generate an initial set of data rules and subsequently tunes said initial set of data rules using said historical data rules.

4. The method of claim 1 , wherein said computer processor utilizes a machine learning engine.

5. The method of claim 1 , wherein said data rules are used to evaluate quality of said newly received dataset.

6. The method of claim 1 , wherein said data rules are used to prioritize transmission of datapoints of said newly received dataset.

7. A method for facilitating a transfer of a newly received dataset across a data network having access to a searchable global dataset, the method utilizing a computer processor and one or more non-transitory computer-readable media storing computer executable instructions, the instructions when executed by the computer processor, automatically generate data rules for said newly received dataset, the method comprising the steps of:
said computer processor querying said global dataset to identify an existing dataset having data points overlapping with said newly received dataset, wherein the existing dataset is a dataset that references a same entity that is contained within the newly received dataset and contains data fields different from the data fields contained within the newly received dataset;
said computer processor identifying historical data rules used for a set of data transfers relating to said existing dataset; and
a machine learning engine using said historical data rules to optimize data rules for use with a data transfer relating to said newly received dataset, thereby facilitating the transfer of said newly received dataset, wherein the machine learning engine is a quantum optimization engine configured to utilize one or more quantum algorithms to process an initial data transfer rule set from the existing dataset to process the newly received data, and further optimize the data rules using the newly received data;
wherein said machine learning engine comprises a modality selected from a group consisting of natural language processing, a trained neural network model, a deep learning model, a supervised machine learning model, and an artificial intelligence model; and
said machine learning engine is a different learning engine from a learning engine used to generate the data rules.

8. The method of claim 7 , wherein said machine learning engine utilizes said historical data rules as an initial set of data rules and subsequently tunes said initial set of data rules using said newly received dataset.

9. The method of claim 7 , wherein said machine learning engine utilizes said newly received dataset to generate an initial set of data rules and subsequently tunes said initial set of data rules using said historical data rules.

10. The method of claim 7 , wherein said computer processor utilizes a machine learning engine.

11. The method of claim 7 , wherein said data rules are used to evaluate quality of said newly received dataset.

12. The method of claim 7 , wherein said data rules are used to prioritize transmission of datapoints of said newly received dataset.

13. A method for facilitating a transfer of a newly received dataset across a data network having access to a searchable global dataset, the method utilizing a computer processor and one or more non-transitory computer-readable media storing computer executable instructions, the instructions, when executed by the computer processor, automatically generate data rules for said newly received dataset, the method comprising the steps of:
querying said global dataset to identify an existing dataset corresponding with said newly received dataset, wherein the existing dataset is a dataset that references a same entity that is contained within the newly received dataset and contains data fields different from the data fields contained within the newly received dataset;
determining whether said existing dataset comprises at least one existing data point that matches with a corresponding data point in said newly received dataset; and
deprioritizing transfer of said corresponding data point in said newly received dataset, thereby facilitating the transfer of said newly received dataset;
wherein said computer processor utilizes a machine learning engine, and wherein the machine learning engine is a quantum optimization engine configured to utilize one or more quantum algorithms to process an initial data transfer rule set from the existing dataset to process the newly received data, and optimize the data rules using the newly received data; and
wherein said machine learning engine comprises a modality selected from a group consisting of natural language processing, a trained neural network model, a deep learning model, a supervised machine learning model, and an artificial intelligence model; and
said machine learning engine is a different learning engine from a learning engine used to generate the data rules.

14. The method of claim 13 , further comprising the steps of:
identifying novel data points in said newly received dataset, meaning data points that lack corresponding data points in said global dataset; and
merging said novel data points with said existing dataset, thereby generating a merged dataset.

15. The method of claim 14 , further comprising using historical data rules previously used for said existing dataset to assist a machine learning engine in generating updated data rules for use with said merged dataset.

Assignees

• Bank Of America

Inventors

• Gupta Nupur
• Meedinti Bhaskara Reddy Harinath
• Kurian Manu
• Varma Jayachandra
• Perkins Erica

Classifications

• G06F16/24542 Primary

  Plan optimisation · CPC title

• G06N5/022

  Knowledge engineering; Knowledge acquisition · CPC title

• G06N10/60

  Quantum algorithms, e.g. based on quantum optimisation, quantum Fourier or Hadamard transforms · CPC title

• G06N3/08

  Learning methods · CPC title

• G06N20/00

  Machine learning · CPC title