Authors show – implementation of artificial intelligence in combat vehicle shell reduce the time for detection and recognition of air attack object. As result, combat vehicle winning probability against that object is arising thanks to that implementation. Besides that, artificial intelligence helps to assess a rate of threat, determines the time, which has combat vehicle personnel for execution the actions in case of significant threat from side of air attack object and recommend the most effective weapon against target for combat vehicle personnel. The next step stays for native industry for these tasks implementation into specific samples of the combat vehicles

This research presented an approach based on the application of structured prompt instructions to large language models (LLM). Methodological foundations for using an ontology-driven system of structured prompts in interaction with ChatGPT were developed. The ChatGPT system allows expanding the knowledge base by obtaining new information from existing knowledge units based on a set of contexts. Thus, methods for generating meaningful responses in natural language were considered using a large language model using ontological approaches and natural language contexts. Using the proposed methodology, the OntoChatGPT system was developed, which effectively extracts entities from contexts, classifies them and generates appropriate responses. An experiment on the reverse synthesis of natural language sentences based on their ontological representation using large language models allows to clearly demonstrate the effectiveness of using the concept of large language models in dialogue systems. The study highlights the versatility of the methodology, emphasizing its applicability not only to ChatGPT but also to other chatbot systems based on LLMs, such as Google’s Bard utilizing the PaLM 2 LLM. The implementation of this technology is demonstrated using the Ukrainian language

This article explores the case of the usage of artificial intelligence (AI) for optimizing the process of covering distributed systems with consumer-driven contract test, analyzing the pros and cons of this approach. Considering the complexity of development of modern distributed systems, like microservices, and the need to ensure the system components interactions keep reliable as long as the system keeps evolving this study is focused on finding the most effective way to introduce the contact testing into such systems to maximize the contracts tests coverage while minimizing development costs. The contract testing has its challenges: steep learning curve, impact on the delivery lifecycle, spreading the approach consistently across the organization. These challenges often lead to teams sacrificing the benefits of the approach and using more traditional ways of testing, like end-to-end (E2E) testing, which however does not fit well into distrusted system. The described methodology includes generating (by AI platform) the contract between the parties (consumer and provider), generating the consumer test to verify the provider is compatible with the expectations the consumer has of it. It is proposed to use following inputs for AI as the source for generation: request-response pairs, OpenApi specification, consumer codebase. The research employs Pact as a tool that allows to define a contract between a consumer and a provider as well as verify that both sides adhere to this contract. NodeJS is used as a framework for consumer and provider development. PactFlow platform with its HaloAI executes contracts and tests generation. The proposed approach simplifies the road to introduce the contact testing into the distributed systems, increases the development team effectiveness in system implementation and a confidence in its stability

The possibility of cooperative agents usage for the on-board air conditioning system research and diagnosis is considered. A logical model for type I and II faults searching is proposed. This work provides an opportunity to master the practical knowledge and skills the first and second types logical models building to obtaining a minimum test of performance and finding malfunctions and damages the place at complex information systems development, operation and maintenance the stages. An algorithm has been developed that combines the development a generalized I type logical model from the system functional circuit input side and the subsequent construction II type a logical model from its free outputs. The deep learning metod allows to increase the accuracy of the model, the speed of finding faults, predicting and preventing accidents