Application of Vector Language Models in Decision Support Systems

The mathematical model of the decision support system under uncertainty conditions is considered. The model is based on the semiotic model of the situation. Methods for solving the inverse problem for finding formal solutions to achieve the goal are proposed. To interpret the solutions, it is proposed to use vector models of language obtained by training neural networks with a large corpus of text. Examples of interpreting solutions using vector models of language are considered and their capabilities for decision-making are analyzed. A method for assessing the quality of explaining solutions by a deep learning neural network is proposed.