Granted Patent B2

US 12,489,463 · App. 18/628,219 · Granted Dec 2, 2025

Inventors: Raja Arumugam Maharaja (Chennai, IN); Sonali Tiwari (Gurugram, IN)

Assignee: Bank of America Corporation

H03M7/55G06F7/588G06F16/31G06F16/35H03M7/6035

Abstract

Claims (121)

1 . A system, comprising:

a memory operable to store:

a machine learning algorithm configured to evaluate data in accordance with one or more machine learning models:

at least one classical processor communicatively coupled to the memory and configured to:

receive a first request to store first received data;

determine that the first received data comprises first unstructured data:

in response to determining that the first received data comprises the first unstructured data, assort, using a trained machine learning algorithm trained to abbreviate data, contents of the first unstructured data of the first received data into a plurality of clusters, each cluster of the plurality of clusters being representative of a type of content in the first unstructured data;

in response to assorting, using the trained machine learning algorithm, the first unstructured data of the first received data, perform a first analysis operation to identify a first plurality of datapoints representative of the plurality of clusters, the first plurality of datapoints being a first signature representation of the first unstructured data of the first received data; and

generate a first roadmap to store the first plurality of datapoints,

the first roadmap being a plan to store the first plurality of datapoints in the memory in accordance with one or more quantum random number generator (QRNG) operations; and

at least one quantum processor communicatively coupled to the at least one classical processor and configured to:

convert, as part of the one or more QRNG operations, the first plurality of datapoints into a plurality of random intermediate values;

index, as part of the one or more QRNG operations, the plurality of random intermediate values as first indexed data; and

after completion of the first roadmap, store the first plurality of datapoints as the first indexed data.

2 . The system of claim 1 , wherein the first unstructured data comprises textual data.

3 . The system of claim 2 , wherein:

the textual data comprises a first letter and a second letter; and

the first signature representation of the first unstructured data of the first received data comprises a first plurality of numbers indicating instances of the first letter in the textual data and a second plurality of numbers indicating instances of the second letter in the textual data.

4 . The system of claim 1 , wherein:

the at least one classical processor is further configured to:

receive a second request to store second received data;

determine that the second received data comprises first structured data:

in response to determining that the second received data comprises the first structured data, assort, using the trained machine learning algorithm trained to abbreviate data, contents of the first structured data of the second received data into an additional plurality of clusters, each cluster of the additional plurality of clusters being representative of an additional type of content in the first unstructured data;

in response to assorting, using the trained machine learning algorithm, the first structured data of the second received data, perform a second analysis operation to identify a second plurality of datapoints representative of the additional plurality of clusters, the second plurality of datapoints being a second signature representation of the first structured data of the second received data; and

generate a second roadmap to store the second plurality of datapoints,

the second roadmap being a plan to store the second plurality of datapoints in the memory in accordance with one or more containerized cluster operations; and

the at least one quantum processor is further configured to:

cluster the second plurality of datapoints into a plurality of clusters; and

index the additional plurality of clusters as second indexed data; and

after completion of the first roadmap, store the second plurality of datapoints as the second indexed data.

5 . The system of claim 4 , wherein the first structured data comprises image data.

6 . The system of claim 5 , wherein:

the image data comprises a first plurality of pixels associated with a first color and a second plurality of pixels associated with a second color; and

the second signature representation of the first structured data of the second received data comprises a first plurality of numbers indicating a first pixel density of the first color and a second plurality of numbers indicating a second pixel density of the second color.

7 . The system of claim 5 , wherein:

the image data comprises a first object and a second object; and

the second signature representation of the first structured data of the second received data comprises a first plurality of numbers indicating instances of the first object in the image data and a second plurality of numbers indicating instances of the second object in the image data.

8 . The system of claim 1 , wherein the at least one classical processor is further configured to:

receive a second request to store second received data;

determine that the second received data comprises second unstructured data and structured data;

separate the second unstructured data and the structured data;

in response to determining that the second received data comprises the second unstructured data, evaluate the second unstructured data of the second received data in accordance with the machine learning algorithm;

in response to evaluating the second unstructured data of the second received data, perform a second analysis operation to identify a second plurality of datapoints in the second received data, the second plurality of datapoints being a second signature representation of the second unstructured data of the second received data;

generate a second roadmap to store the second plurality of datapoints, wherein:

the second roadmap is a plan to store the second plurality of datapoints in the memory in accordance with one or more containerized cluster operations;

the one or more containerized cluster operations are configured to cluster the second plurality of datapoints into a plurality of clusters; and

the one or more containerized cluster operations are configured to index the plurality of clusters as second indexed data:

cause the quantum processor to store the second plurality of datapoints following the second roadmap;

in response to determining that the second received data comprises the structured data, evaluate the structured data of the second received data in accordance with the machine learning algorithm;

in response to evaluating the structured data of the second received data, perform a third analysis operation to identify a third plurality of datapoints in the second received data, the third plurality of datapoints being a third signature representation of the structured data of the second received data: generate a third roadmap to store the third plurality of datapoints, wherein:

the third roadmap is a plan to store the third plurality of datapoints in the memory in accordance with one or more QRNG operations;

the one or more QRNG operations are configured to convert the third plurality of datapoints into a second plurality of random intermediate values; and

the one or more QRNG operations are configured to index the second plurality of random intermediate values as third indexed data; and

cause the quantum processor to store the third plurality of datapoints following the third roadmap.

9 . The system of claim 1 , wherein the at least one classical processor is further configured to:

receive a second request to store second received data;

determine that the second received data comprises second unstructured data and structured data;

separate the second unstructured data and the structured data;

in response to determining that the second received data comprises unstructured data, evaluate the second unstructured data of the second received data in accordance with the machine learning algorithm;

in response to evaluating the second unstructured data of the second received data, perform a second analysis operation to identify a second plurality of datapoints in the second received data, the second plurality of datapoints being a second signature representation of the second unstructured data of the second received data;

generate a second roadmap to store the second plurality of datapoints, wherein:

the second roadmap is a plan to store the second plurality of datapoints in the memory in accordance with one or more containerized cluster operations;

the one or more containerized cluster operations are configured to cluster the second plurality of datapoints into a plurality of clusters; and

the one or more containerized cluster operations are configured to index the plurality of clusters as second indexed data:

in conjunction with generating the second roadmap to store the second plurality of datapoints, determine that the second plurality of datapoints is not previously stored in the memory;

in response to determining that the second plurality of datapoints is not previously stored in the memory, cause the quantum processor to store the second plurality of datapoints following the second roadmap;

in response to determining that the second received data comprises structured data, evaluate the structured data of the second received data in accordance with the machine learning algorithm;

in response to evaluating the structured data of the second received data, perform a third analysis operation to identify a third plurality of datapoints in the second received data, the third plurality of datapoints being a third signature representation of the structured data of the second received data; in response to performing the third analysis operation to identify the third plurality of datapoints in the second received data, determine that the third plurality of datapoints is previously stored in the memory; and

in response to determining that the third plurality of datapoints is previously stored in the memory, generate a report indicating that the third plurality of datapoints are previously stored in the memory.

10 . A method, comprising:

receiving a first request to store first received data;

determining that the first received data comprises first unstructured data;

in response to determining that the first received data comprises the first unstructured data, assorting, using a trained machine learning algorithm trained to abbreviate data, contents of the first unstructured data of the first received data into a plurality of clusters, each cluster of the plurality of clusters being representative of a type of content in the first unstructured data;

in response to assorting, using the trained machine learning algorithm, the first unstructured data of the first received data, performing a first analysis operation to identify a first plurality of datapoints representative of the plurality of clusters, the first plurality of datapoints being a first signature representation of the first unstructured data of the first received data; and

generate a first roadmap to store the first plurality of datapoints,

the first roadmap being a plan to store the first plurality of datapoints in accordance with one or more quantum random number generator (QRNG) operations:

convert, as part of the one or more QRNG operations, the first plurality of datapoints into a plurality of random intermediate values;

index, as part of the one or more QRNG operations, the plurality of random intermediate values as first indexed data; and

after completion of the first roadmap, storing the first plurality of datapoints as the first indexed data.

11 . The method of claim 10 , wherein the first unstructured data comprises textual data.

12 . The method of claim 11 , wherein:

the textual data comprises a first letter and a second letter; and

the first signature representation of the first unstructured data of the first received data comprises a first plurality of numbers indicating instances of the first letter in the textual data and a second plurality of numbers indicating instances of the second letter in the textual data.

13 . The method of claim 10 , further comprising:

receiving a second request to store second received data;

determining that the second received data comprises first structured data;

in response to determining that the second received data comprises the first structured data, evaluating assorting, using the trained machine learning algorithm trained to abbreviate data, contents of the first structured data of the second received data into an additional plurality of clusters, each cluster of the additional plurality of clusters being representative of an additional type of content in the first unstructured data;

in response to assorting, using the trained machine learning algorithm, the first structured data of the second received data, performing a second analysis operation to identify a second plurality of datapoints representative of the additional plurality of clusters, the second plurality of datapoints being a second signature representation of the first structured data of the second received data;

generate a second roadmap to store the second plurality of datapoints,

the second roadmap being a plan to store the second plurality of datapoints in accordance with one or more containerized cluster operations:

cluster the second plurality of datapoints into a plurality of clusters; and

index the additional plurality of clusters as second indexed data; and

after completion of the second roadmap, storing the second plurality of datapoints as the second indexed data.

14 . The method of claim 13 , wherein the first structured data comprises image data.

15 . The method of claim 14 , wherein:

the image data comprises a first plurality of pixels associated with a first color and a second plurality of pixels associated with a second color; and

the second signature representation of the first structured data of the second received data comprises a first plurality of numbers indicating a first pixel density of the first color and a second plurality of numbers indicating a second pixel density of the second color.

16 . The method of claim 14 , wherein:

the image data comprises a first object and a second object; and

the second signature representation of the first structured data of the second received data comprises a first plurality of numbers indicating instances of the first object in the image data and a second plurality of numbers indicating instances of the second object in the image data.

17 . A non-transitory computer readable medium storing instructions that when executed by a processor cause the processor to:

receive a first request to store first received data;

determine that the first received data comprises first unstructured data;

in response to determining that the first received data comprises the first unstructured data, assort, using a trained machine learning algorithm trained to abbreviate data, contents of the first unstructured data of the first received data into a plurality of clusters, each cluster of the plurality of clusters being representative of a type of content in the first unstructured data;

in response to assorting, using the trained machine learning algorithm, the first unstructured data of the first received data, perform a first analysis operation to identify a first plurality of datapoints representative of the plurality of clusters, the first plurality of datapoints being a first signature representation of the first unstructured data of the first received data: generate a first roadmap to store the first plurality of datapoints, wherein:

the first roadmap being a plan to store the first plurality of datapoints in accordance with one or more quantum random number generator (QRNG) operations:

convert, as part of the one or more QRNG operations, the first plurality of datapoints into a plurality of random intermediate values; and

index, as part of the one or more QRNG operations, the plurality of random intermediate values as first indexed data; and

after completion of the first roadmap, store the first plurality of datapoints as the first indexed data.

18 . The non-transitory computer readable medium of claim 17 , wherein the first unstructured data comprises textual data.

19 . The non-transitory computer readable medium of claim 17 , wherein the instructions further cause the processor to:

receive a second request to store second received data;

determine that the second received data comprises first structured data;

in response to determining that the second received data comprises the first structured data, assort, using the trained machine learning algorithm trained to abbreviate data, contents of the first structured data of the second received data into an additional plurality of clusters, each cluster of the additional plurality of clusters being representative of an additional type of content in the first unstructured data;

in response to assorting, using the trained machine learning algorithm, the first structured data of the second received data, perform a second analysis operation to identify a second plurality of datapoints representative of the additional plurality of clusters, the second plurality of datapoints being a second signature representation of the first structured data of the second received data;

generate a second roadmap to store the second plurality of datapoints,

the second roadmap being a plan to store the second plurality of datapoints in accordance with one or more containerized cluster operations;

cluster the second plurality of datapoints into a plurality of clusters; and

index the plurality of clusters as second indexed data; and

after completion of the second roadmap, store the second plurality of datapoints as the second indexed data.

20 . The non-transitory computer readable medium of claim 19 , wherein the first structured data comprises image data.

Assignments (1)

Continuity (1)

References Cited (22)