US 12,461,717 B2
Software-code-defined digital threads in digital engineering systems with artificial intelligence (AI) assistance
William Roper, Jr., Charleston, SC (US); Christopher Lee Benson, Arlington, VA (US); Sriram Krishnan, Cambridge, MA (US); Peter Galvin, Watertown, MA (US); Baha aldeen E. A. Abunojaim, Roslindale, MA (US); Pranav Sumanth Doijode, Rijswijk (NL); and Najem Aldeen Abu Rmaileh, Amman (JO)
Assigned to Istari Digital, Inc., Charleston, SC (US)
Appl. No. 18/730,782
Filed by Istari Digital, Inc., Charleston, SC (US)
PCT Filed Mar. 10, 2024, PCT No. PCT/US2024/019297
§ 371(c)(1), (2) Date Jul. 21, 2024,
PCT Pub. No. WO2024/191882, PCT Pub. Date Sep. 19, 2024.
Claims priority of provisional application 63/451,577, filed on Mar. 11, 2023.
Claims priority of provisional application 63/516,624, filed on Jul. 31, 2023.
Claims priority of provisional application 63/511,583, filed on Jun. 30, 2023.
Claims priority of provisional application 63/451,545, filed on Mar. 10, 2023.
Claims priority of provisional application 63/462,988, filed on Apr. 29, 2023.
Prior Publication US 2025/0165226 A1, May 22, 2025
Int. Cl. G06F 9/44 (2018.01); G06F 8/30 (2018.01); G06F 9/445 (2018.01); G06F 9/455 (2018.01); G06N 20/00 (2019.01)
CPC G06F 8/30 (2013.01) [G06N 20/00 (2019.01)] 22 Claims
OG exemplary drawing
 
1. A non-transitory physical storage medium storing program code, the program code executable by a hardware processor to cause the hardware processor to execute a computer-implemented process for generating a software-code-defined digital thread, the program code comprising code to:
train a script-generating machine learning (ML) model using a training dataset comprising a set of training triplets, each of the training triplets comprising a sample intent input, a corresponding sample model representation set, and a corresponding sample platform orchestration script, wherein the sample platform orchestration script connects models within the corresponding sample model representation set to accomplish the corresponding sample intent input;
receive a first model representation of a first engineering model,
receive a second model representation of a second engineering model:
receive an intent input, wherein the intent input is selected from the group consisting of a user action on an interconnected digital engineering platform, a user prompt, an existing software-code-defined digital thread, and a request from a software agent on the interconnected digital engineering platform;
generate, using the script-generating ML model, a platform orchestration script connecting the first model representation and the second model representation based on the intent input, wherein the platform orchestration script accomplishes the intent input;
store the platform orchestration script as the software-code-defined digital thread; and
wherein the platform orchestration script, when executing, invokes one or more Application Programming Interface (API) or Software Development Kit (SDK) endpoints associated with the first model representation and/or with the second model representation, wherein the API or SDK endpoints provide a unified programming interface to model representations generated from the first and/or the second engineering models.