# US 2025/0165226 A1 · Software-Code-Defined Digital Threads in Digital Engineering Systems with Artificial Intelligence (AI) Assistance

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2025/0165226 A1
- Document ID: US20250165226A1
- Status: Published application
- Kind: A1
- Application number: 18/730,782
- Filed: 2024-03-10
- Published: 2025-05-22
- Earliest claimed: 2023-03-10
- Assignees: Istari Digital, Inc.
- Applicants: Istari Digital, Inc.
- Inventors: William Roper, Jr.; Christopher Lee Benson; Sriram Krishnan; Peter Galvin; Baha aldeen E. A. Abunojaim; Pranav Sumanth Doijode; Najem Aldeen Abu Rmaileh
- Web page: https://patentgrep.com/patent/US20250165226A1

## CPC

- G06F 8/30: Creation or generation of source code
- G06F 8/31: {Programming languages or programming paradigms}
- G06F 8/34: Graphical or visual programming
- G06N 3/045: Combinations of networks
- G06N 3/08: Learning methods
- G06N 3/105: {Shells for specifying net layout}
- G06N 20/00: Machine learning
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

Methods and systems for generating digital threads that connect models and software tools for an interconnected digital engineering and certification ecosystem are provided. In one embodiment, a process for generating a software-code-defined digital thread includes receiving a first model representation of a first engineering model, a second model representation of a second engineering model, and an intent input. Determining, using a machine learning (ML) model, one or more model endpoints in the first and the second model representations. Generating, using a script-generating ML model, a platform orchestration script that accomplishes the intent input by connecting the first model representation and the second model representation, using the one or more model endpoints. Finally, storing the platform orchestration script as the software-code-defined digital thread. The digital threading of digital engineering models, with and without AI assistance, leads to exponential increases in efficiency of designing, testing, certifying, manufacturing, and operating physical products, allowing physical products to be made at digital speeds.

## Claims

### Claim 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 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;
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; and
store the platform orchestration script as the software-code-defined digital thread.

### Claim 2 (depends on 1)

The non-transitory physical storage medium of claim 1, further comprising program code to:
receive a feedback data on the platform orchestration script; and
train and/or fine-tune the script-generating ML model based on the feedback data.

### Claim 3 (depends on 1)

The non-transitory physical storage medium of claim 1, further comprising program code to:
provide a user interface coding environment in an interconnected digital engineering platform (IDEP);
receive a plurality of user selections of the first engineering model and the second engineering model, wherein the first engineering model and the second engineering model were selected by a user;
receive a plurality of corresponding model representations from the first engineering model and the second engineering model;
receive a user-defined code for a user-defined platform orchestration script;
determine and/or receive a corresponding intent input;
determine corresponding model representation endpoints used in the user-defined code from the user-defined platform orchestration script;
record the first and the second engineering models, the first and the second model representations, the corresponding intent input, and the corresponding model representation endpoints, and the user-defined platform orchestration script to generate the training dataset; and
store the training dataset for training the script-generating ML model.

### Claim 4 (depends on 1)

The non-transitory physical storage medium of claim 1, wherein the connecting the first model representation and the second model representation based on the intent input comprises linking a first endpoint of the first model representation and a second endpoint of the second model representation based on the intent input.

### Claim 5 (depends on 4)

The non-transitory physical storage medium of claim 4, further comprising program code to:
evaluate, using a sufficiency machine learning (ML) model, the first engineering model and the second engineering model within an interconnected digital engineering platform (IDEP) for sufficiency for accomplishing the intent input.

### Claim 6 (depends on 5)

The non-transitory physical storage medium of claim 5, further comprising program code to:
determine, using a recommender ML model or the script-generating ML model, a first endpoint in the first model representation that is relevant to the intent input, in response to sufficiency being determined.

### Claim 7 (depends on 6)

The non-transitory physical storage medium of claim 6, further comprising program code to:
determine, using the recommender ML model, a relationship between the first endpoint and the second endpoint based on the intent input.

### Claim 8 (depends on 1)

The non-transitory physical storage medium of claim 1, wherein the platform orchestration script comprises scripting code to read data from the first model representation and/or the second model representation.

### Claim 9 (depends on 1)

The non-transitory physical storage medium of claim 1, wherein the platform orchestration script comprises scripting code to write data to the first model representation and/or the second model representation.

### Claim 10 (depends on 1)

The non-transitory physical storage medium of claim 1, wherein the platform orchestration script comprises an input for the second model representation connected to an output of the first model representation.

### Claim 11 (depends on 10)

The non-transitory physical storage medium of claim 10, further comprising program code to:
execute the platform orchestration script for the second model representation, wherein the output from the first model representation is the input for the second model representation.

### Claim 12 (depends on 1)

The non-transitory physical storage medium of claim 1, wherein the platform orchestration script comprises scripting code to read data from the first model representation, execute a computation on the data, and write a result of the computation to the first model representation and/or the second model representation.

### Claim 13 (depends on 1)

The non-transitory physical storage medium of claim 1, further comprising program code to:
receive a third model representation of a third engineering model,
wherein the platform orchestration script further links the first and/or the second model representation with the third model representation.

### Claim 14 (depends on 1)

The non-transitory physical storage medium of claim 1, further comprising program code to:
execute the platform orchestration script by invoking one or more API or SDK endpoints associated with the first model representation and/or with the second model representation.

### Claim 15 (depends on 1)

The non-transitory physical storage medium of claim 1, further comprising program code to:
determine, using an AI algorithm, a recommended third engineering model based on the first engineering model, the second engineering model, and the training dataset.

### Claim 16 (depends on 1)

The non-transitory physical storage medium of claim 1, wherein the first engineering model and/or the second engineering model is a document file that is human-readable.

### Claim 17 (depends on 16)

The non-transitory physical storage medium of claim 16, further comprising program code to:
receive a document template;
analyze the document template using an interconnected digital engineering platform (IDEP);
determine, using an AI model, output data from the first model representation and/or the second model representation required to generate the document file;
execute appropriate actions on the first model representation and/or the second model representation using a predetermined sequence based on the document template's requirements to generate output required for the document file; and
generate the document file by assembling the document template and the output from the first model representation and/or the second model representation.

### Claim 18 (depends on 1)

The non-transitory physical storage medium of claim 1, further comprising program code to:
predict a change in one or more items selected from the group consisting of the first model representation of the first engineering model and the second model representation of the second engineering model based on a change in one of the items selected from the group consisting of the first model representation of the first engineering model and the second model representation of the second engineering model.

### Claim 19 (depends on 1)

The non-transitory physical storage medium of claim 1, further comprising program code to:
predict a change in the first model representation of the first engineering model based on a change in the second model representation of the second engineering model.

### Claim 20 (depends on 1)

The non-transitory physical storage medium of claim 1, further comprising program code to:
call a second software-code-defined digital thread.

### Claim 21 (depends on 1)

The non-transitory physical storage medium of claim 1, wherein one of the first engineering model and/or the second engineering model comprises a neural network model.

### Claim 22 (depends on 1)

The non-transitory physical storage medium of claim 1, further comprising program code to:
generate, using an AI model, a magic document associated with the software-code-defined digital thread, wherein the magic document comprises API endpoints to human-readable text blocks, and wherein the magic document is updated, using the API endpoints, with an audit log in response to an execution of at least a portion of the platform orchestration script.

### Claim 23 (depends on 1)

The non-transitory physical storage medium of claim 1, wherein the platform orchestration script comprises a code block, wherein the code block is associated with an information security tag, and wherein the information security tag indicates a restriction on executing the code block.

### Claim 24 (depends on 1)

The non-transitory physical storage medium of claim 1, wherein the first model representation is a first model splice, and further comprising program code to generate the first model splice of the first engineering model, utilizing program code to:
receive a first engineering model file of the first engineering model having a DE model type, wherein the first engineering model file is in a native file format;
extract model data from the first engineering model file in the native file format;
store the model data in a model data storage area;
generate one or more external, commonly-accessible splice functions that enable external access to one or more digital artifacts derived from the model data stored in the model data storage area, wherein the one or more external, commonly-accessible splice functions provide addressable Application Programming Interface (API) or Software Development Kit (SDK) endpoints that are accessible by third-party applications and users, and wherein the API or SDK endpoints enable access to the digital artifacts without access to an entirety of the first engineering model file and without requiring direct engagement by the third-party applications and users with a DE tool associated with the DE model type; and
generate the first model splice of the first engineering model, wherein the first model splice comprises access to a selective portion of the one or more digital artifacts, wherein the first model splice comprises access to at least one of the one or more external, commonly-accessible splice functions, wherein the first model splice is accessible via the API or SDK endpoints by the third-party applications and users, and wherein the API or SDK endpoints provide a unified programming interface to sharable model splices generated from DE models having the DE model type.

### Claim 25

A computer-implemented method for generating a software-code-defined digital thread, comprising:
training a script-generating machine learning (ML) model using a training dataset comprising a set of training triplets each 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 the corresponding sample model representation set to accomplish the corresponding sample intent input;
receiving a first model representation of a first engineering model;
receiving a second model representation of a second engineering model;
receiving an intent input;
generating, 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; and
storing the platform orchestration script as the software-code-defined digital thread.
