Knowledge model "Tags about batches and containers" of the ERP system "PlasmIS" with the possibility of self-improvement using local llm models

The main requirements, capabilities and functionality of the "Tags about batch and containers" module of the "PlasmIS" information system are recearched in the article. Mathematical models of the intelligent module including offered database and knowledge base are suggested. The principles of printing actual tags were considered and the method of printing tags from the information system was developed. An approach to automated standardization of technical names of hardware using local large language models (LLM) is considered, which allows to significantly increase the accuracy of processing specialized data. The architecture of interaction of Python scripts with the local Lm studio server is described in detail, including the organization of API requests, the structure of input and output data in JSON format, as well as mechanisms for saving results in the SQLite database.