Expanding the Capabilities of Ontological Modeling of Legal Knowledge Using Elements of Fuzzy Logic

Introduction. Ontological analysis is a significant area in the field of intelligent information technologies, particularly in the development of legal systems where there is a continuous need for efficient management and exchange of legal knowledge. Due to the complexity of legal systems, the application of semantic technologies allows for formalizing legal concepts, simplifying the development of ontological models for representing legal knowledge, and integrating heterogeneous legal information systems. Additionally, incorporating fuzzy logic is essential for handling uncertainty and incompleteness in legal information. The purpose of the paper is to develop a legal ontology model capable of efficiently processing ambiguous legal terms and concepts while automating the classification and analysis of legal documents. The primary objective is to create a flexible system for formalizing legal knowledge that accounts for the specifics of legal acts, enhances the law enforcement process, and supports informed decision-making. Methods. The study employs semantic ontological modeling methods to create legal ontologies and fuzzy logic methods for processing vague and incomplete data. Modern tools and ontology development languages, such as Protege and OWL (Web Ontology Language), are used alongside machine learning techniques for classifying and analyzing legal texts. The approach also explores integrating fuzzy logic elements for evaluating document similarity and representing complex legal concepts. Results. A legal ontology model was developed to automate the classification and analysis of legal terms, concepts, and their relationships. The proposed methodology enables the system to extract information from various legal sources and analyze legal documents while addressing ambiguous data. Testing demonstrated improved classification accuracy and increased efficiency in retrieving legal norms from large volumes of unstructured data. Conclusions. The proposed legal ontology model, incorporating elements of fuzzy logic, significantly enhances the representation and processing of legal knowledge. The methodology includes grammar analysis and the construction of document ontological models, allowing for more precise comparisons of document similarities and differences. The semantic approach proved more effective than the k-means clustering method for key phrase classification. Integrating fuzzy sets into the ontology model facilitates the description of imprecise information and supports reasoning with varying levels of completeness. Ongoing work aims to expand the Ukrainian-language version of the legal ontology to address practical challenges in knowledge-based legal systems. The obtained results serve as a foundation for further advancements in intelligent information systems within the legal domain.