Method for Automatic Classification of Full-Text Descriptions of Cores Using Dictionaries

The use of automatic text processing methods, including full-text description classification methods, helps significantly reduce labor costs of experimental data processing. This paper discusses the use of the automatic text classification method in processing and classifying elements of cores and determining lithofacies. Lithofacies are coeval geological bodies (deposits) that differ in composition or structure from adjacent layers. When assessing oil and gas field potential, it is necessary to construct maps and diagrams of lithofacies distribution. This requires classifying a large number of full-text descriptions of core sections pre-pared by specialists. The algorithm proposed here makes it possible, based on the specified rules and dictionaries, to conduct classification taking into account the order and significance of keywords in sentences. The advantages of this approach are the ability to distinguish between similar lithofacies, the ability to use archival data, ease of configuration for new classes, adaptation to Russian-language core descriptions, and the ability to be used locally without the need to send core descriptions to third-party applications.