Search

US-20260127494-A1 - ARTIFICIAL INTELLIGENCE SELECTION AND CONFIGURATION

US20260127494A1US 20260127494 A1US20260127494 A1US 20260127494A1US-20260127494-A1

Abstract

In embodiments, a method for configuring an intelligent agent to do a task based on spatial-temporal magnetic imaging data of the brain of a worker is disclosed. The method includes generating a brain region parameter indicating an active neocortex region associated with visual processing during performance of the task based on the spatial-temporal magnetic imaging data. The method further includes selecting a convolutional neural network (CNN) component type in response to a match between the brain region parameter and an associated CNN component type. The method includes configuring the intelligent agent based on the selected CNN component and a neocortical processing flow parameter derived using the spatial-temporal magnetic imaging data, wherein the intelligent agent is configured to process image data using the CNN component and provide an output of the CNN to another AI component via a data connection created based on the neocortical processing flow parameter.

Inventors

  • Charles Howard Cella
  • Jenna Lynn Parenti
  • Taylor D. Charon

Assignees

  • Strong Force TX Portfolio 2018, LLC

Dates

Publication Date
20260507
Application Date
20250902

Claims (20)

  1. 1 . A computer-implemented method for automatically configuring and executing an intelligent agent, the method comprising: obtaining, by one or more processors, spatial-temporal magnetic imaging data of a brain of a worker performing a task from one or more magnetic imaging machines; generating, by the one or more processors, a brain region parameter indicating an active neocortex region associated with visual processing during performance of the task based on the spatial-temporal magnetic imaging data; querying, by the one or more processors, a data store comprising a plurality of records using the brain region parameter as a query input, wherein each of the plurality of records associates one of a plurality of different artificial intelligence (AI) component types with a corresponding neocortex region based on functional suitability; automatically selecting, by the one or more processors, a convolutional neural network (CNN) component type in response to a match between the brain region parameter and a record associating the CNN component type with visual processing; automatically configuring, by the one or more processors, the intelligent agent, wherein the automatic configuring comprises: configuring the intelligent agent to receive image data from a visual sensor and to provide the image data as an input to a CNN component based on the record associating the CNN component type with visual processing; generating, by the one or more processors, a processing flow parameter indicating a neocortical processing flow based on the spatial-temporal magnetic imaging data; and creating a data connection from an output of the CNN component to an additional AI component using one of a serial or a parallel connection to match the neocortical processing flow based on the processing flow parameter; and executing, by the one or more processors, the configured intelligent agent, wherein the executing comprises: receiving the image data from the visual sensor; processing the image data using the CNN component to generate an output; and providing the output of the CNN component to the additional AI component via the data connection.
  2. 2 . The method of claim 1 , further comprising: generating, by the one or more processors, a second brain region parameter indicating an active neocortex region P4 based on the spatial-temporal magnetic imaging data; and automatically selecting a gated recurrent neural network (GRNN) component type in response to a match between the second brain region parameter and a record in the data store associating the GRNN component type with the active neocortex region P4, wherein automatically configuring the intelligent agent further comprises incorporating a GRNN component of the selected GRNN component type into the intelligent agent.
  3. 3 . The method of claim 2 , wherein the GRNN component is the additional AI component.
  4. 4 . The method of claim 1 , further comprising: generating, by the one or more processors, a third brain region parameter indicating an active neocortex region associated with auditory processing based on the spatial-temporal magnetic imaging data, wherein automatically configuring the intelligent agent further comprises configuring the intelligent agent to receive audio data from a microphone based on the third brain region parameter.
  5. 5 . The method of claim 1 , further comprising: generating, by the one or more processors, a fourth brain region parameter indicating an active neocortex region C3 associated with data storage or retrieval based on the spatial-temporal magnetic imaging data; and automatically selecting an AI component type optimized for data storage or retrieval in response to a match between the fourth brain region parameter and a record in the data store associating the AI component type with the active neocortex region C3.
  6. 6 . The method of claim 5 , wherein the AI component type optimized for data storage or retrieval comprises a blockchain-based distributed ledger, wherein automatically configuring the intelligent agent further comprises incorporating the blockchain-based distributed ledger into the intelligent agent.
  7. 7 . The method of claim 1 , further comprising: obtaining a second temporal biometric measurement of the worker, wherein the second temporal biometric measurement comprises at least one of heartbeat data, galvanic skin response data, or eye-tracking data, and wherein generating the brain region parameter indicating the active neocortex region associated with visual processing is further based on the second temporal biometric measurement.
  8. 8 . The method of claim 1 , wherein automatically configuring the intelligent agent further comprises at least one of: setting a weighting factor for the image data provided as the input to the CNN component; or tuning a learning parameter of the CNN component.
  9. 9 . The method of claim 1 , wherein the magnetic imaging machine is a functional magnetic resonance imaging (fMRI) machine.
  10. 10 . The method of claim 1 , wherein the data store further comprises metadata associated with each of the plurality of different AI component types, the metadata indicating at least one of a user rating, a performance review, or a licensing mechanism for the AI component type.
  11. 11 . A system for automatically configuring and executing an intelligent agent, the system comprising: one or more processors; and a non-transitory computer-readable medium storing instructions that, when executed by the one or more processors, cause the system to: obtain spatial-temporal magnetic imaging data of a brain of a worker performing a task from one or more magnetic imaging machines; generate a brain region parameter indicating an active neocortex region associated with visual processing during performance of the task based on the spatial-temporal magnetic imaging data; query a data store comprising a plurality of records using the brain region parameter as a query input, wherein each of the plurality of records associates one of a plurality of different artificial intelligence (AI) component types with a corresponding neocortex region based on functional suitability; automatically select a convolutional neural network (CNN) component type in response to a match between the brain region parameter and a record associating the CNN component type with visual processing; automatically configure the intelligent agent, wherein the instructions to automatically configure comprise instructions to: configure the intelligent agent to receive image data from a visual sensor and to provide the image data as an input to a CNN component based on the record associating the CNN component type with visual processing; generate a processing flow parameter indicating a neocortical processing flow based on the spatial-temporal magnetic imaging data; and create a data connection from an output of the CNN component to an additional AI component using one of a serial or a parallel connection to match the neocortical processing flow based on the processing flow parameter; and execute the configured intelligent agent, wherein the instructions to execute comprise instructions to: receive the image data from the visual sensor; process the image data using the CNN component to generate an output; and provide the output of the CNN component to the additional AI component via the data connection.
  12. 12 . The system of claim 11 , wherein the instructions, when executed, further cause the one or more processors to: generate a second brain region parameter indicating an active neocortex region P4 based on the spatial-temporal magnetic imaging data; and automatically select a gated recurrent neural network (GRNN) component type in response to a match between the second brain region parameter and a record in the data store associating the GRNN component type with the active neocortex region P4, wherein the instructions to automatically configure the intelligent agent further comprise instructions to incorporate a GRNN component of the selected GRNN component type into the intelligent agent.
  13. 13 . The system of claim 12 , wherein the GRNN component is the additional AI component.
  14. 14 . The system of claim 11 , wherein the instructions, when executed, further cause the one or more processors to: generate a third brain region parameter indicating an active neocortex region associated with auditory processing based on the spatial-temporal magnetic imaging data, wherein the instructions to automatically configure the intelligent agent further comprise instructions to configure the intelligent agent to receive audio data from a microphone based on the third brain region parameter.
  15. 15 . The system of claim 11 , wherein the instructions, when executed, further cause the one or more processors to: generate a fourth brain region parameter indicating an active neocortex region C3 associated with data storage or retrieval based on the spatial-temporal magnetic imaging data; and automatically select an AI component type optimized for data storage or retrieval in response to a match between the fourth brain region parameter and a record in the data store associating the AI component type with the active neocortex region C3.
  16. 16 . The system of claim 15 , wherein the AI component type optimized for data storage or retrieval comprises a blockchain-based distributed ledger, and wherein the instructions to automatically configure the intelligent agent further comprise instructions to incorporate the blockchain-based distributed ledger into the intelligent agent.
  17. 17 . The system of claim 11 , wherein the instructions, when executed, further cause the one or more processors to: obtain a second temporal biometric measurement of the worker, wherein the second temporal biometric measurement comprises at least one of heartbeat data, galvanic skin response data, or eye-tracking data, and wherein the instructions to generate the brain region parameter indicating the active neocortex region O1 are further based on the second temporal biometric measurement.
  18. 18 . The system of claim 11 , wherein the instructions to automatically configure the intelligent agent further comprise instructions to perform at least one of: setting a weighting factor for the image data provided as the input to the CNN component; or tuning a learning parameter of the CNN component.
  19. 19 . The system of claim 11 , further comprising a network component in communication with the magnetic imaging machine, wherein the magnetic imaging machine is a functional magnetic resonance imaging (fMRI) machine.
  20. 20 . The system of claim 11 , further comprising the data store communicatively coupled to the one or more processors, wherein the data store further comprises metadata associated with each of the plurality of different AI component types, the metadata indicating at least one of a user rating, a performance review, or a licensing mechanism for the AI component type.

Description

CROSS REFERENCE TO RELATED APPLICATIONS The present application is a continuation of U.S. patent application Ser. No. 17/243,145 (SFTX-0017-U01), filed Apr. 28, 2021, entitled “ARTIFICIAL INTELLIGENCE SELECTION AND CONFIGURATION” which claims the benefit of priority to and is a continuation-in-part of PCT Application PCT/US2021/016473 (SFTX-0013-WO), filed Feb. 3, 2021, entitled “ARTIFICIAL INTELLIGENCE SELECTION AND CONFIGURATION.” PCT Application PCT/US2021/016473 (SFTX-0013-WO) claims the benefit of priority to and is a continuation-in-part of U.S. patent application Ser. No. 16/780,519 (SFTX-0012-U01), filed Feb. 3, 2020, entitled “ADAPTIVE INTELLIGENCE AND SHARED INFRASTRUCTURE LENDING TRANSACTION ENABLEMENT PLATFORM RESPONSIVE TO CROWD SOURCED INFORMATION”, issued Jun. 6, 2023 as U.S. Pat. No. 11,669,914. U.S. patent application Ser. No. 16/780,519 (SFTX-0012-U01) claims the benefit of priority to and is a continuation-in-part of PCT Application PCT/US19/58647 (SFTX-0009-WO), filed Oct. 29, 2019, entitled “ADAPTIVE INTELLIGENCE AND SHARED INFRASTRUCTURE LENDING TRANSACTION ENABLEMENT PLATFORM.” PCT Application PCT/US19/58647 (SFTX-0009-WO) claims the benefit of priority to the following U.S. Provisional Patent Applications: Ser. No. 62/751,713 (SFTX-0003-P01), filed Oct. 29, 2018, entitled “METHODS AND SYSTEMS FOR IMPROVING MACHINES AND SYSTEMS THAT AUTOMATE EXECUTION OF DISTRIBUTED LEDGER AND OTHER TRANSACTIONS IN SPOT AND FORWARD MARKETS FOR ENERGY, COMPUTE, STORAGE AND OTHER RESOURCES”, Ser. No. 62/843,992 (SFTX-0005-P01), filed May 6, 2019, entitled “ADAPTIVE INTELLIGENCE AND SHARED INFRASTRUCTURE LENDING TRANSACTION ENABLEMENT PLATFORM WITH ROBOTIC PROCESS ARCHITECTURE”; Ser. No. 62/818,100 (SFTX-0006-P01), filed Mar. 13, 2019, entitled “ROBOTIC PROCESS AUTOMATION ARCHITECTURE, SYSTEMS AND METHODS IN TRANSACTION ENVIRONMENTS”; Ser. No. 62/843,455 (SFTX-0007-P01), filed May 5, 2019, entitled “ADAPTIVE INTELLIGENCE AND SHARED INFRASTRUCTURE LENDING TRANSACTION ENABLEMENT PLATFORM WITH ROBOTIC PROCESS ARCHITECTURE”; and Ser. No. 62/843,456 (SFTX-0008-P01), filed May 5, 2019, entitled ADAPTIVE INTELLIGENCE AND SHARED INFRASTRUCTURE LENDING TRANSACTION ENABLEMENT PLATFORM WITH ROBOTIC PROCESS ARCHITECTURE.” PCT Application PCT/US19/58647 also claims the benefit of priority to and is a continuation-in-part of PCT Application PCT/US2019/030934 (SFTX-0004-WO), filed May 6, 2019, entitled, “METHODS AND SYSTEMS FOR IMPROVING MACHINES AND SYSTEMS THAT AUTOMATE EXECUTION OF DISTRIBUTED LEDGER AND OTHER TRANSACTIONS IN SPOT AND FORWARD MARKETS FOR ENERGY, COMPUTE, STORAGE AND OTHER RESOURCES.” U.S. patent application Ser. No. 16/780,519 (SFTX-0012-U01) also claims the benefit of priority to and is a continuation-in-part of PCT Application PCT/US2019/030934 (SFTX-0004-WO), filed May 6, 2019, entitled, “METHODS AND SYSTEMS FOR IMPROVING MACHINES AND SYSTEMS THAT AUTOMATE EXECUTION OF DISTRIBUTED LEDGER AND OTHER TRANSACTIONS IN SPOT AND FORWARD MARKETS FOR ENERGY, COMPUTE, STORAGE AND OTHER RESOURCES.” PCT Application PCT/US2019/030934 (SFTX-0004-WO) claims the benefit of priority to the following U.S. Provisional Patent Applications: Ser. No. 62/787,206 (SFTX-0001-P01), filed Dec. 31, 2018, entitled “METHODS AND SYSTEMS FOR IMPROVING MACHINES AND SYSTEMS THAT AUTOMATE EXECUTION OF DISTRIBUTED LEDGER AND OTHER TRANSACTIONS IN SPOT AND FORWARD MARKETS FOR ENERGY, COMPUTE, STORAGE AND OTHER RESOURCES”; Ser. No. 62/667,550 (SFTX-0002-P01), filed May 6, 2018, entitled “METHODS AND SYSTEMS FOR IMPROVING MACHINES AND SYSTEMS THAT AUTOMATE EXECUTION OF DISTRIBUTED LEDGER AND OTHER TRANSACTIONS IN SPOT AND FORWARD MARKETS FOR ENERGY, COMPUTE, STORAGE AND OTHER RESOURCES”; and Ser. No. 62/751,713 (SFTX-0003-P01), filed Oct. 29, 2018, entitled “METHODS AND SYSTEMS FOR IMPROVING MACHINES AND SYSTEMS THAT AUTOMATE EXECUTION OF DISTRIBUTED LEDGER AND OTHER TRANSACTIONS IN SPOT AND FORWARD MARKETS FOR ENERGY, COMPUTE, STORAGE AND OTHER RESOURCES.” PCT Application PCT/US2021/016473 (SFTX-0013-WO) also claims priority to the following U.S. Provisional Patent Applications: Ser. No. 63/127,980 (SFTX-0016-P01), filed Dec. 18, 2020, entitled “MARKET ORCHESTRATION SYSTEM FOR FACILITATING ELECTRONIC MARKETPLACE TRANSACTIONS“; Ser. No. 63/069,542 (SFTX-0015-P01), filed Aug. 24, 2020, entitled”INFORMATION TECHNOLOGY SYSTEMS AND METHODS FOR TRANSACTION ARTIFICIAL INTELLIGENCE LEVERAGING DIGITAL TWINS”; and Ser. No. 62/994,581 (SFTX-0014-P01), filed Mar. 25, 2020, entitled “COMPLIANCE SYSTEM FOR FACILITATING LICENSING OF PERSONALITY RIGHTS”. U.S. patent application Ser. No. 17/243,145 (SFTX-0017-U01) also claims the benefit of priority to and is a continuation-in-part of PCT Application No.: PCT/US19/58671 (SFTX-0010-WO), filed Oct. 29, 2019, entitled “METHODS AND SYSTEMS FOR IMPROVING MACHINES AND SYSTEMS THAT AUTOMATE EXECUTION OF DISTRIBUTED LEDGER AND OTHER TRANSACTIONS IN SPOT AND FORWARD MARKETS FOR ENERGY, COMPUTE, STORAGE AND OT