Granted Patent B2

US 12,488,155 · App. 19/197,754 · Granted Dec 2, 2025

Inventors: William Roper, Jr. (Charleston, SC); Christopher Lee Benson (Arlington, VA); Sriram Krishnan (Cambridge, MA); Peter Galvin (Watertown, MA); Pranav Sumanth Doijode (Rijswijk, NL); Bayan Abedal-Muttaleb Afif Hashem (Amman, JO)

Assignee: Istari Digital, Inc

G06F30/10G06F2111/20

Abstract

Claims (73)

1 . A non-transitory physical storage medium storing instructions, the instructions executable by a processor of a digital documentation system to cause the processor to perform operations comprising:

retrieve one or more digital engineering (DE) document templates from a DE document template library comprising DE document templates for one or more phases of a DE product lifecycle, wherein the DE document templates comprise first DE data fields;

receive a first user input from a user, wherein the first user input comprises a first DE model file of a DE model type, wherein the first DE model file resides in a customer environment distinct from the digital documentation system, and wherein the first user input comprises a selected DE document template selected from the one or more DE document templates;

crawl the first DE model file to extract a plurality of model data from the first DE model file to generate a data schema describing a structure and a format of the plurality of model data;

generate a plurality of splice function scripts to access the plurality of model data based on an access permission of the user, wherein the plurality of splice function scripts are written in a computer-executable scripting language, wherein at least one of the plurality of splice function scripts invokes a native API function of a third-party DE tool, and wherein the plurality of splice function scripts provide a plurality of API endpoints to access and manipulate the plurality of model data based on the data schema;

generate an externally-accessible API from the plurality of splice function scripts, wherein the externally-accessible API allows access to the plurality of model data without directly invoking the native API function of the third-party DE tool, and wherein the externally-accessible API is associated with the DE model type;

wrap the DE model file with the externally-accessible API to generate a model splice of the first DE model file of the DE model type, wherein the model splice provides access to limited portions of the plurality of model data of the first DE model file, and wherein the model splice provides access control to the plurality of model data based on the access permission of the user;

generate a first model data using a first splice function of the model splice of the first DE model file, via the externally-accessible API, based on the selected DE document template;

train a generator machine learning (ML) model on one or more example DE document files and a platform documentation from the digital documentation system, wherein the platform documentation comprises a reference guide of the externally-accessible API;

fine-tune the generator ML model using a fine-tuning database to generate a fine-tuned generator ML model, wherein the fine-tuning database comprises at least a sample prompt-response pair, wherein the sample prompt-response pair comprises a sample user input and a corresponding response of the digital documentation system; and

execute the fine-tuned generator ML model to generate a DE document file from the selected DE document template and the first model data.

2 . The non-transitory physical storage medium of claim 1 , wherein the first model data is stored within a customer-controlled storage bucket with a zero-trust access control.

3 . The non-transitory physical storage medium of claim 1 , wherein the first DE model file is accessible through the externally-accessible API along with a second DE model file of a second DE model type that is not already interoperable with the first DE model file of the DE model type.

4 . The non-transitory physical storage medium of claim 1 , wherein the generation of the first model data is executed upon invocation by an orchestration script of the externally-accessible API.

5 . The non-transitory physical storage medium of claim 1 , further comprising instructions to:

receive one or more modifications to the first model data upon an update of the first DE model file via the model splice; and

update one or more portions of the DE document file based on the one or more modifications to the first model data.

6 . The non-transitory physical storage medium of claim 1 ,

wherein the DE document file is part of an interconnected digital engineering platform (IDEP),

wherein the generator ML model has access to the first model data via the model splice, and the one or more DE document templates, to generate the DE document file, and

wherein the non-transitory physical storage medium further comprises instructions to dynamically update the DE document file using at least one software-defined digital thread in the IDEP having instructions to:

receive user interactions dynamically from the user;

responsive to the user interacting with the IDEP and performing a first modification to the first model data via the DE model and/or a second modification to a parameter setting in the IDEP, propagate the first modification and/or the second modification through the at least one software-defined digital thread to an associated DE documentation comprising the DE document file; and

execute the generator ML model to generate and/or update the DE document file.

7 . The non-transitory physical storage medium of claim 1 ,

wherein the DE document file is a live DE document file associated with a digital twin configuration of a physical twin, and

wherein the non-transitory physical storage medium further comprises instructions to:

receive a predetermined timestamp; and

generate a printed DE document file corresponding to a static, time-stamped version of the DE document file at the predetermined timestamp.

8 . The non-transitory physical storage medium of claim 7 , further comprising instructions to:

detect a first modification of the first DE model file or a second modification of a software-defined digital thread associated with the first DE model file;

update the first DE data fields of the DE document file based on the first modification or the second modification responsive to the first modification or the second modification; and

generate an updated printed DE document file with the updated first DE data fields updated based on the DE document file.

9 . The non-transitory physical storage medium of claim 1 , further comprising instructions to:

execute a recommender engine to recommend one or more recommended DE document templates from the one or more DE document templates, wherein the one or more recommended DE document templates comprise template data and/or metadata that match the first user input within a predetermined confidence level, and wherein the selected DE document template is selected from the one or more recommended DE document templates based on the first user input.

10 . The non-transitory physical storage medium of claim 9 , wherein the recommender engine comprises a recommender ML model that is trained on user profile data and template metadata, and wherein the recommender ML model recommends the one or more recommended DE document templates from the one or more DE document templates based on the training of the recommender ML.

11 . The non-transitory physical storage medium of claim 9 , wherein the recommender engine comprises a Large Language Model (LLM), wherein the LLM is fine-tuned with an ontology of documentation requirements, and wherein the LLM recommends the one or more recommended DE document templates based on the first user input.

12 . The non-transitory physical storage medium of claim 1 , wherein the generator ML model further comprises predictive modeling and decision-tree algorithms, and wherein the instructions to generate the DE document file comprise instructions to generate suggestions for the first DE data fields and values based on the first user input and an overall context of the DE document file.

13 . The non-transitory physical storage medium of claim 1 , wherein the generator ML model further comprises an LLM fine-tuned on an ontology of documentation requirements.

14 . The non-transitory physical storage medium of claim 1 , wherein the generator ML model further comprises an LLM fine-tuned on system metadata.

15 . The non-transitory physical storage medium of claim 1 , wherein the generator ML model further comprises a rule-based algorithm, and wherein the rule-based algorithm uses a domain-specific language (DSL) that updates the DE document file, using examples of prior, related DE documents.

16 . The non-transitory physical storage medium of claim 1 , further comprising instructions to:

receive user feedback data related to the DE document file generated by the generator ML model from the user;

generate feedback metrics related to a quality of the DE document file generated by the generator ML model; and

train and/or fine-tune the generator ML model utilizing the feedback metrics to improve future DE document files generated by the generator ML model.

17 . The non-transitory physical storage medium of claim 1 , further comprising instructions to:

generate training data comprising a plurality of DE document files from the generator ML model and document edits made to the plurality of DE document files by the user; and

train and/or fine-tune the generator ML model on the training data.

18 . A digital documentation system, comprising:

at least one processor; and

at least one non-transitory storage medium storing instructions, the instructions executable by the processor to cause the processor to perform operations comprising:

retrieve one or more digital engineering (DE) document templates from a DE document template library comprising DE document templates for one or more phases of a DE product lifecycle, wherein the DE document templates comprise first DE data fields;

receive a first user input from a user, wherein the first user input comprises a first DE model file of a DE model type, wherein the first DE model file resides in a customer environment distinct from the digital documentation system, and wherein the first user input comprises a selected DE document template selected from the one or more DE document templates;

crawl the first DE model file to extract a plurality of model data from the first DE model file to generate a data schema describing a structure and a format of the plurality of model data;

generate a plurality of splice function scripts to access the plurality of model data based on an access permission of the user, wherein the plurality of splice function scripts are written in a computer-executable scripting language, wherein at least one of the plurality of splice function scripts invokes a native API function of a third-party DE tool, and wherein the plurality of splice function scripts provide a plurality of API endpoints to access and manipulate the plurality of model data based on the data schema;

generate an externally-accessible API from the plurality of splice function scripts, wherein the externally-accessible API allows access to the plurality of model data without directly invoking the native API function of the third-party DE tool, and wherein the externally-accessible API is associated with the DE model type;

wrap the DE model file with the externally-accessible API to generate a model splice of the first DE model file of the DE model type, wherein the model splice provides access to limited portions of the plurality of model data of the first DE model file, and wherein the model splice provides access control to the plurality of model data based on the access permission of the user;

generate a first model data using a first splice function of the model splice of the first DE model file, via the externally-accessible API, based on the selected DE document template;

train a generator machine learning (ML) model on one or more example DE document files and a platform documentation from the digital documentation system, wherein the platform documentation comprises a reference guide of the externally-accessible API;

fine-tune the generator ML model using a fine-tuning database to generate a fine-tuned generator ML model, wherein the fine-tuning database comprises at least a sample prompt-response pair, wherein the sample prompt-response pair comprises a sample user input and a corresponding response of the digital documentation system; and

execute the fine-tuned generator ML model to generate a DE document file from the selected DE document template and the first model data.

19 . A computer-implemented method for generating a digital engineering (DE) document file in a digital documentation system, comprising:

retrieving one or more digital engineering (DE) document templates from a DE document template library comprising DE document templates for one or more phases of a DE product lifecycle, wherein the DE document templates comprise first DE data fields;

receiving a first user input from a user, wherein the first user input comprises a first DE model file of a DE model type, wherein the first DE model file resides in a customer environment distinct from the digital documentation system, and wherein the first user input comprises a selected DE document template selected from the one or more DE document templates;

crawling the first DE model file to extract a plurality of model data from the first DE model file to generate a data schema describing a structure and a format of the plurality of model data;

generating a plurality of splice function scripts to access the plurality of model data based on an access permission of the user, wherein the plurality of splice function scripts are written in a computer-executable scripting language, wherein at least one of the plurality of splice function scripts invokes a native API function of a third-party DE tool, and wherein the plurality of splice function scripts provide a plurality of API endpoints to access and manipulate the plurality of model data based on the data schema;

generating an externally-accessible API from the plurality of splice function scripts, wherein the externally-accessible API allows access to the plurality of model data without directly invoking the native API function of the third-party DE tool, and wherein the externally-accessible API is associated with the DE model type;

wrapping the DE model file with the externally-accessible API to generate a model splice of the first DE model file of the DE model type, wherein the model splice provides access to limited portions of the plurality of model data of the first DE model file, and wherein the model splice provides access control to the plurality of model data based on the access permission of the user;

generating a first model data using a first splice function of the model splice of the first DE model file, via the externally-accessible API, based on the selected DE document template;

training a generator machine learning (ML) model on one or more example DE document files and a platform documentation from the digital documentation system, wherein the platform documentation comprises a reference guide of the externally-accessible API;

fine-tuning the generator ML model using a fine-tuning database to generate a fine-tuned generator ML model, wherein the fine-tuning database comprises at least a sample prompt-response pair, wherein the sample prompt-response pair comprises a sample user input and a corresponding response of the digital documentation system; and

executing the fine-tuned generator ML model to generate the DE document file from the selected DE document template and the first model data.

20 . The computer-implemented method of claim 19 , wherein the first model data is stored within a customer-controlled storage bucket with a zero-trust access control.

Assignments (1)

Continuity (6)

References Cited (28)