IP Library › Granted Patent US 12699573

Granted Patent B2

US 12699573 · App. 18/635,106 · Granted Aug 4, 2026

Intelligent apparatus leveraging photonic quantum generative artificial intelligence (AI) to generate crowdsensing device configurations

Inventor: Shailendra Singh (Maharashtra, IN)

Assignee: Bank of America Corporation

G06F9/4411

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 12699573
App. No.: 18/635,106
Granted: Aug 4, 2026
Kind: B2

External Links

USPTO Patent Center↗ Full Patent PDF↗

Abstract

A computing platform may receive, from a user device, a prompt configured for input into a generative AI model. The computing platform may input the prompt into the generative AI model to identify a schemas for use in providing a response to the prompt, where each schema may be a configuration of device clusters, each device may be an IoT enabled device configured to provide crowdsensed information, and the generative AI model may score the schemas, and select, based on identifying that a first schema has a highest score, the first schema. The computing platform may collect, from devices comprising the first schema, crowdsensed information. The computing platform may generate, based on the crowdsensed information, a response to the prompt. The computing platform may send, to the user device, the response to the prompt and may cause the user device to display the response to the prompt.

Claims (75)

1 . A computing platform comprising:

at least one processor;

a communication interface communicatively coupled to the at least one processor; and

memory storing computer-readable instructions that, when executed by the at least one processor, cause the computing platform to:

receive, from a user device, a prompt configured for input into a generative artificial intelligence (AI) model, wherein the prompt includes metadata comprising one or more of: a crowdsensing task description, business rules, security rules, data aggregation rules, data acquisition rules, crowdsensing task temporal and spatial rules, crowdsensing task software payload source information, IoT internet protocol (IP) addresses, or network type information;

generate, based the metadata, one or more smart contracts, each defining a device cluster within the configuration of device clusters;

identify, by inputting the prompt into the generative AI model, plurality of schemas, wherein each schema comprises a configuration of device clusters, wherein each device is an internet of things (IoT) enabled device configured to provide crowdsensed information, wherein the generative AI model identifies the plurality of schemas by scoring the plurality of schemas based on one or more of: latency in request processing, processing power, or computational complexity, and wherein scoring the plurality of schemas comprises assigning a score to each of the plurality of schemes on a scale of 0-100, with 0 being the worst and 100 being the best;

select, based on identifying that a first schema of the plurality of schemas has a highest score, the first schema;

collect, from a first plurality of devices comprising the first schema, crowdsensed information;

generate, based on the crowdsensed information, a response to the prompt and one or more corrective actions;

send, to the user device, the response to the prompt and one or more commands directing the user device to display the response to the prompt, wherein sending the one or more commands directing the user device to display the response to the prompt causes the user device to display the response to the prompt;

execute the one or more corrective actions, wherein executing the one or more corrective actions causes an issue, indicated in the response and detected based on the crowdsensed information, to be automatically remediated;

detect a schema update event, wherein detecting the schema update event comprises detecting one or more of:

more than a threshold number of the devices no longer satisfy the corresponding smart contract,

more than a threshold amount of time has passed since the first schema was selected, or

latency corresponding to the first schema exceeds a predetermined threshold;

update, based on detection of the schema update event, the one or more smart contracts; and

update, using the updated one or more smart contracts, the first schema.

2 . The computing platform of claim 1 , wherein generating the first schema comprises identifying, using the one or more smart contracts, whether each IoT enable device may be added to a corresponding device cluster.

3 . The computing platform of claim 1 , wherein a first device cluster of the configuration of device clusters corresponds to a first device type and a second device cluster of the configuration of device clusters corresponds to a second device type.

4 . The computing platform of claim 1 , wherein collecting the crowdsensed information comprises collecting the crowdsensed information after receiving approval from the corresponding user.

5 . The computing platform of claim 1 , wherein the one or more corrective actions comprise one or more of: deploying a software update, dispatching a technician, or taking a system offline.

6 . The computing platform of claim 1 , wherein the memory stores additional computer-readable instructions that, when executed by the at least one processor, cause the computing platform to:

encrypt, using homomorphic encryption, the metadata of the prompt, wherein identifying the plurality of schemas is performed using the encrypted metadata.

7 . The computing platform of claim 1 , wherein the memory stores additional computer-readable instructions that, when executed by the at least one processor, cause the computing platform to:

identify, by monitoring the first schema in real time, one or more anomalies associated with at least one IoT device; and

isolate, based on the one or more anomalies, one or more sections of the IoT device.

8 . A method comprising:

at a computing platform comprising at least one processor, a communication interface, and memory:

receiving, from a user device, a prompt configured for input into a generative artificial intelligence (AI) model, wherein the prompt includes metadata comprising one or more of: a crowdsensing task description, business rules, security rules, data aggregation rules, data acquisition rules, crowdsensing task temporal and spatial rules, crowdsensing task software payload source information, IoT internet protocol (IP) addresses, or network type information;

generate, based the metadata, one or more smart contracts, each defining a device cluster within the configuration of device clusters;

identifying, by inputting the prompt into the generative AI model, a plurality of schemas, wherein each schema comprises a configuration of device clusters, wherein each device is an internet of things (IoT) enabled device configured to provide crowdsensed information, wherein the generative AI model identifies the plurality of schemas by scoring the plurality of schemas based on one or more of: latency in request processing, processing power, or computational complexity, and wherein scoring the plurality of schemas comprises assigning a score to each of the plurality of schemes on a scale of 0-100, with 0 being the worst and 100 being the best;

selecting, based on identifying that a first schema of the plurality of schemas has a highest score, the first schema;

collecting, from a first plurality of devices comprising the first schema, crowdsensed information;

generating, based on the crowdsensed information, a response to the prompt and one or more corrective actions;

sending, to the user device, the response to the prompt and one or more commands directing the user device to display the response to the prompt, wherein sending the one or more commands directing the user device to display the response to the prompt causes the user device to display the response to the prompt;

executing the one or more corrective actions, wherein executing the one or more corrective actions causes an issue, indicated in the response and detected based on the crowdsensed information, to be automatically remediated;

detecting a schema update event, wherein detecting the schema update event comprises detecting one or more of:

more than a threshold number of the devices no longer satisfy the corresponding smart contract,

more than a threshold amount of time has passed since the first schema was selected, or

latency corresponding to the first schema exceeds a predetermined threshold;

updating, based on detection of the schema update event, the one or more smart contracts; and

updating, using the updated one or more smart contracts, the first schema.

9 . The method of claim 8 , wherein generating the first schema comprises identifying, using the one or more smart contracts, whether each IoT enable device may be added to a corresponding device cluster.

10 . The method of claim 8 , wherein a first device cluster of the configuration of device clusters corresponds to a first device type and a second device cluster of the configuration of device clusters corresponds to a second device type.

11 . The method of claim 8 , wherein collecting the crowdsensed information comprises automatically collecting the crowdsensed information without prompting a corresponding user for approval.

12 . The method of claim 8 , further comprising:

encrypting, using homomorphic encryption, the metadata of the prompt, wherein identifying the plurality of schemas is performed using the encrypted metadata.

13 . Method of claim 8 , further comprising:

identifying, by monitoring the first schema in real time, one or more anomalies associated with at least one IoT device; and

isolating, based on the one or more anomalies, one or more sections of the IoT device.

14 . One or more non-transitory computer-readable media storing instructions that, when executed by a computing platform comprising at least one processor, a communication interface, and memory, cause the computing platform to:

generate, based the metadata, one or more smart contracts, each defining a device cluster within the configuration of device clusters;

identify, by inputting the prompt into the generative AI model, a plurality of schemas, wherein each schema comprises a configuration of device clusters, wherein each device is an internet of things (IoT) enabled device configured to provide crowdsensed information, wherein the generative AI model identifies the plurality of schemas by scoring the plurality of schemas based on one or more of: latency in request processing, processing power, or computational complexity, and wherein scoring the plurality of schemas comprises assigning a score to each of the plurality of schemes on a scale of 0-100, with 0 being the worst and 100 being the best;