Machine learning-based user-customized automatic patent document classification method, device, and system

A web server for classifying patent documents based on a classification input of a user, comprising:

• a memory unit configured to store data;
• a communication unit configured to perform communication using at least one protocol;
• and
• a processor configured to control the memory unit and the communication unit,
• wherein the processor is further configured to:
• learn patent documents stored in a patent database by machine learning technology, establish a first classification standard based on similarity between the patent documents, and generate a basic classification model of classifying the patent documents based on the first classification standard;
• generate a patent pool including a plurality of patent documents based on a search and/or selection input of the user;
• receive the classification input of the user and classify the plurality of patent documents included in the patent pool according to the classification input;
• predict a second classification standard classifying the plurality of patent documents by the user based on the similarity between the classified patent documents;
• and
• classify remaining patent documents which are not yet classified in the patent pool based on the basic classification model and the second classification standard.