Wyniki wyszukiwania - BazTech

1

Discovering relationships between data in enterprise system using log analysis

Korzeniowski Łukasz, Goczyła Krzysztof

Annals of Computer Science and Information Systems

|

2023

|

Vol. 35

141--150

EN

Enterprise systems are inherently complex and maintaining their full, up-to-date overview poses a serious challenge to the enterprise architects' teams. This problem encourages the search for automated means of discovering knowledge about such systems. An important aspect of this knowledge is understanding the data that are processed by applications and their relationships. In our previous work, we used application logs of an enterprise system to derive knowledge about the interactions taking place between applications. In this paper, we further explore logs to discover correspondence between data processed by different applications. Our contribution is the following: we propose a method for discovering relationships between data using log analysis, we validate our method against a benchmark system AcmeAir and we validate our method against a real-life system running at Nordea Bank.

2

Discovering interactions between applications with log analysis

Korzeniowski Łukasz, Goczyła Krzysztof

Annals of Computer Science and Information Systems

|

2022

|

Vol. 30

861--869

EN

Application logs record the behavior of a system during its runtime and their analysis can provide useful information. In this article, we propose a method of automated log analysis to discover interactions taking place between applications in an enterprise. We believe that such an automated approach can greatly support enterprise architects in building an up-to-date view of a governed system in a modern, fast-paced development environment. Our contribution is the following: we propose a new method for log template generation called SLT (Simple Log Template), we propose a method of extracting knowledge about application interactions from logs, and we validate the proposed methods on a real system running at Nordea Bank. Additionally, we collect statistical information about application logs from the real-life system, based on which we formulate some observations that support our method.

3

Artificial intelligence for software development : the present and the challenges for the future

Korzeniowski Łukasz, Goczyła Krzysztof

Biuletyn Wojskowej Akademii Technicznej

|

2019

|

Vol. 68, nr 1

15--32

EN

Since the time when first CASE (Computer-Aided Software Engineering) methods and tools were developed, little has been done in the area of automated creation of code. CASE tools support a software engineer in creation the system structure, in defining interfaces and relationships between software modules and, after the code has been written, in performing testing tasks on different levels of detail. Writing code is still the task of a skilled human, which makes the whole software development a costly and error-prone process. It seems that recent advances in AI area, particularly in deep learning methods, may considerably improve the matters. The paper presents an extensive survey of recent work and achievements in this area reported in the literature, both from the theoretical branch of research and from engineer-oriented approaches. Then, some challenges for the future work are proposed, classified into Full AI, Assisted AI and Supplementary AI research fields.

PL

Od czasu pojawienia się pierwszych metod i narzędzi CASE niewiele zrobiono w zakresie automatycznego wytwarzania oprogramowania. Narzędzia CASE wspierają deweloperów w tworzeniu struktury systemu, definiowaniu interfejsów i relacji między modułami oprogramowania oraz, po powstaniu kodu, w wykonywaniu zadań testowych na różnych poziomach szczegółowości. Pisanie kodu jest jednak nadal zadaniem wykwalifikowanego specjalisty, co powoduje, że cały proces wytwarzania oprogramowania jest kosztowny i podatny na błędy. Ostatnie postępy w obszarze sztucznej inteligencji, szczególnie w zakresie metod głębokiego uczenia maszynowego, mogą i powinny znacznie poprawić tę sytuację. W artykule przedstawiono przegląd dotychczasowych osiągnięć w tej dziedzinie, znanych z literatury przedmiotu, szczególnie w zakresie czysto teoretycznym, gdyż efekty inżynierskie znajdujące zastosowanie praktyczne są jak dotąd bardzo ograniczone. Następnie zaproponowano i opisano kilka kierunków przyszłych prac w tej dziedzinie, które zaklasyfikowano jako Full AI, Assisted AI i Supplementary AI, w kolejności wynikającej z oczekiwanego stopnia zautomatyzowania procesów wytwarzania oprogramowania.