Implementing Automated Testing Strategy for Legal Decision Understanding AI
Nyein, Phoo (2023)
Nyein, Phoo
2023
All rights reserved. This publication is copyrighted. You may download, display and print it for Your own personal use. Commercial use is prohibited.
Julkaisun pysyvä osoite on
https://urn.fi/URN:NBN:fi:amk-2023121336980
https://urn.fi/URN:NBN:fi:amk-2023121336980
Tiivistelmä
This thesis focuses on the automated testing strategies for the data stream pipeline that utilizes Optical Character Recognition (OCR) and Natural language Processing(NLP) for processing legal decisions. The work presents the implementation of an automated testing strategy that validates 23 business rules and evaluates the performance of the system as a whole. The testing approach focuses primarily on end-to-end testing systems for real-time Kafka streams . The strategy aims to ensure the overall quality of processing business rules throughout the pipeline, the reliability, efficiency, and accuracy of the system as a whole for processing legal decisions.
This paper explores the insights of how AI has been used in Legal Decision Making, combined Optical Character Recognition (OCR) and Natural Language Processing (NLP) techniques for processing business rules and automating legal decisions. It also discusses the methodology, tools, and techniques for automated testing and highlights the benefits of automated testing for data stream pipelines.
This paper explores the insights of how AI has been used in Legal Decision Making, combined Optical Character Recognition (OCR) and Natural Language Processing (NLP) techniques for processing business rules and automating legal decisions. It also discusses the methodology, tools, and techniques for automated testing and highlights the benefits of automated testing for data stream pipelines.