This paper presents the integration of a large language model (LLM) into an intelligent information and analytical system for exploratory search support within specific texts. An overview of the capabilities of modern large language models is provided. Special attention is paid to the Retrieval Augmented Generation (RAG) technology used for efficient formation and control of search contexts. The design and development of the system's business logic functions and user interface elements are detailed. Experimental results applying the developed system to texts with specific characteristics are presented. Conclusions are drawn regarding the system's applicability for automating ontology population. Conclusions are drawn regarding the system's applicability for automating the process of populating ontologies, as well as filling other knowledge repositories built using automated monitoring of open big data and intelligent data processing.
The research described in the work is aimed at developing methods for Scheduling. The fundamental disadvantage of the existing methods of Mixed-Integer Linear Programming in application to the problems under consideration is the fact that they are too demanding on the amount of RAM. The difficulty of applying local search procedures to such high-dimensional problems is to develop an effective way to find an acceptable initial approximation and determine the neighboring state transition function, which would allow achieving the optimum fast enough. In the Operations Research Theory, adding additional conditions to a problem can lead to a fundamental change in the problem-solving scheme. The methods proposed in the study are implemented within the framework of the Constraint Programming Paradigm which makes it possible to represent the subject domain dependencies saving RAM, as well as to provide the ability to step-by-step take into account heterogeneous problem conditions without essentially changing the scheme of finding solutions. A significant part of the research deals with methods of logical inference on constraints to reduce the search space and speed up the computational process. The approach to scheduling is illustrated by the Open-Pit Mine Production Scheduling Problem, which was first proposed to be solved as a Constraint Satisfaction Problem. In order to find the first feasible solution, a «greedy» search method is proposed, the result of which can be improved using the developed hybrid method. Both methods rely on original procedures of inference on constraints. The proposed approach has proven its efficiency for block models with sizes of tens and hundreds of thousands of blocks.
The article provides definitions of logistics tasks and their classification. Some mathematical statements of logistics problems and methods of their solution are also given. In particular, the following combinatorial optimization problems are described: the traveling salesman problem, the resource allocation problem, the transportation problem, the maximum flow problem.
The work deals with the search for a special type of regularities in data, called frequent patterns. A frequent pattern is understood as a certain set of attributes that characterizes a sufficiently large number of objects of the training sample. There are many methods for pattern discovery, but they usually do not allow flexible consideration of necessary requirements for their type. Taking into account the new conditions that the desired patterns must meet leads in practice to a time-consuming modification of used algorithms and a decrease in computing performance. This article proposes a new approach based on the constraint programming paradigm, which is free from the listed disadvantages. The approach is based on the original way of presenting the training sample using specialized table constraints – compressed D-type tables, on the author's method of backtracking, as well as on specialized reduction rules for table constraints. Particular attention is paid to solving the closed patterns discovery problem, which is included as part of the solution of all machine learning problems considered in the work, which means taking into account additional requirements for the type of patterns. As additional requirements to the type of pattern, constraints on the frequency of occurrence of a closed pattern, as well as conditions for the occurrence of some element (attribute) into the pattern, are considered. To the basic rules for the reduction of compressed D-type tables, rules are added that take into account the interesting attributes of the analyzed patterns. The advantage of the approach is that the taking into account and analyzing new constraints makes it possible to speed up the calculation process.
To solve machine learning problems, we have developed a method to identify closed sets of common features of objects (patterns) of the training sample. The novelty of the method lies in the fact that it is implemented within the concept of constraint programming and uses a new type of table constraints—compressed tables of the \(D \)-type—for internal representation and processing of the training sample. Search reduction is achieved by applying the proposed method of branching the search tree and using partial order relations on sets of objects (features) to prune unpromising branches. The method has a computational complexity estimate that for some types of input data is better than the estimates obtained for the studied prototypes.