Development of a Program for Automated Data Extraction from Documents of Various Formats on the Structure of Electronic Devices

The purpose of this work is to develop a program for automated data extraction from documents of various formats about the structure of electronic devices. In the course of the work, the research of text processing methods, search of sources and open databases containing information about electronic devices was carried out. In addition, a database containing information about the reliability of elements by their groups and types, based on information from reference books, was developed. An application code has been developed that searches for a match between the series of the element passed to the input and the information from the database, and in its absence makes queries to the Internet to obtain a description of the element. The result of this work is a program that allows you to get their reliability values by the series of the component or a list of components. The volume of the final qualification work is 60 pages, the number of figures – 15, the number of tables – 4 the number of literature sources – 32.