Case Study

Automatic production of documentation from source code

ABSTRACT
Use of EngGPT to automatically generate from large amounts of code and video tutorials the documentation needed to maintain the systems.

Where: Italy
Challenge
The customer is leader in Europe in the construction and operation of toll motorways. The customer needed to automatically generate documentation of a large amount of code to support internal knowledge of selected processes and the migration to newer technology. The customer also had several hours of video meetings from which to extract context information to the code.
Approach
We analysed the various data formats available; a data processing pipeline was generated to consider the codes in an orderly manner; finally, content information was extracted by associating the context information of the videos with the codes content using EngGPT.
Digital Ecosystem
Solution
Digital Ecosystem
We realised an AI-based solution to automatically generate documentation for large amounts of code of obsolete languages. The programming language with which the application was built, namely COBOL, made AI one of the few alternatives suitable for the purpose. The EngGPT and GenAI algorithms are used to extract relevant information such as operations, tables and reference data from various types of code. At the same time, these algorithms were used to gather contextual information from dozens of hours of videos in which an expert performed a knowledge transfer of the application.
Results
Markets
Ecosystems

Impacts

Technologies

To know more

STARLIGHT: Artificial Intelligence to fight against high priority threats

Better data analysis and management: a project to equip law enforcement agencies with secure and resilient AI technologies and tools.

Use Case

Enable Traceability for AgriFood

How to use digital technologies to improve food chain traceability

Easy and Invisible Payment Experience

How to use “invisible payments” to make the shopping experience easier