Modern businesses increasingly rely on chatbots to enhance customer communication and automate routine tasks. The research aimed to determine the optimal configurations of a telecommunications chatbot on the Rasa Pro platform, including the selection of large language models (LLMs), prompt formats, and command structures. The impact of various LLMs, prompt formats, and command precision on response quality was analyzed. Smaller models, like Gemini-1.5-Flash-8B and Gemma2-9B-IT, can achieve results comparable to larger models, offering a cost-effective solution. Specifically, the Gemini-1.5-Flash-8B model achieved an accuracy improvement of 21.62 points when using the JSON prompt format. This emphasizes the importance of prompt engineering techniques, like using structured formats (YAML, JSON) and precise commands. The study utilized a dataset of 400 sample test phrases created based on real customer service conversations with a mobile phone operator’s customers. Results suggest optimizing chatbot performance does not always require the most powerful models. Proper prompt preparation and data format choice are crucial. The theoretical framework focuses on the interaction between model size, prompt format, and command precision. Findings provide insights for chatbot designers to optimize performance through LLM selection and prompt construction. These findings have practical implications for businesses seeking cost-effective and efficient chatbot solutions.

Phishing remains a persistent and evolving cyber threat, constantly adapting its tactics to bypass traditional security measures. The advent of Machine Learning (ML) and Neural Networks (NN) has significantly enhanced the capabilities of automated phishing detection systems. This comprehensive review systematically examines the landscape of ML- and NN-based approaches for identifying and mitigating phishing attacks. Our analysis, based on a rigorous search methodology, focuses on articles published between 2017 and 2024 across relevant subject areas in computer science and mathematics. We categorize existing research by phishing delivery channels, including websites, electronic mail, social networking, and malware. Furthermore, we delve into the specific machine learning models and techniques employed, such as various algorithms, classification and ensemble methods, neural network architectures (including deep learning), and feature engineering strategies. This review provides insights into the prevailing research trends, identifies key challenges, and highlights promising future directions in the application of machine learning and neural networks for robust phishing detection.

The role played by information and communication technologies in human life is growing by the year. During the current pandemic, communication systems have become an essential part of operations of many industries around the world. This has also brought a dynamic development of solutions implemented in Contact Center systems, which ensure quick contact with customers. This paper presents how the pace of the development of Contact Center systems affects optimization of selected Key Performance Indicators (KPIs). It contains a detailed analysis of how successive technologies deployed in the industry, including IVR, chat, WebRTC, Visual IVR, Social Media, MultiChannel, OmniChannel and bots, have affected KPIs. The authors selected essential indicators that are critical to customer service, namely Service Level, Cost per Contact, Customer Satisfaction, Average Handle Time, First Call Resolution, Abandon Rate, Average Waiting Time, and Occupancy Rate. The authors also presented possible trends in the development of the solutions discussed in this paper, including in particular broad possibilities of employing artificial intelligence. AI methods will soon enable equipping Contact Centers with mechanisms for multi-criteria content classification and smart emotion recognition and behavioral profiling methods, and will optimize the process of predicting both inbound and outbound traffic.

Today, there is a marked increase in interest in the share of renewable energy sources in the energy mix, which benefits the environment. This also applies to the energy of sea (wave) current, as, without a doubt, the offshore area is becoming one of the leading areas of renewable energy, which translates into changes in energy production. This can be exemplified by the latest research in the context of theory, design, modeling, as well as application, control, and monitoring of wave turbines to enhance their performance. This article reviews the research in this context, systematizes information, identifies literature gaps, and presents future directions in this area. For this purpose, 3240 English-language publications from 2015 to 2024 were identified in the Scopus database. The data are analyzed according to the selected research domains. Some of them are review or conceptual in nature, while others are empirical in nature (experimental attempts and case studies). From this point of view, it becomes possible not only to systematize the state-of-the-art but also to identify future research prospects.

This review paper analyzes the recent applications of computational mechanics methods in combination with machine learning (ML) and neural network (NN) techniques, as found in the literature published between 2015 and 2024. We present how ML and NNs are enhancing traditional computational methods, such as the finite element method, enabling the solution of complex problems in material modeling, surrogate modeling, inverse analysis, and uncertainty quantification. We categorize current research by considering the specific computational mechanics tasks and the employed ML/NN architectures. Furthermore, we discuss the current challenges, development opportunities, and future directions of this dynamically evolving interdisciplinary field, highlighting the potential of data-driven approaches to transform the modeling and simulation of mechanical systems. The review has been updated to include pivotal publications from 2025, reflecting the rapid evolution of the field in multiscale modeling, data-driven mechanics, and physics-informed/operator learning. Accordingly, the timespan is now 2015–2025, with a focused inclusion of high-impact contributions from 2024 to 2025.