Patents by Inventor Aleksandr Alekseevich Sidorov

Aleksandr Alekseevich Sidorov has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).

  • Recommender system for staff recruitment using machine learning with multivariate data dimension reduction and staff recruitment method using machine learning with multivariate data dimension reduction
    Patent number: 11941584
    Abstract: The provided invention relates to search engines and may be used to search for vacancies and resumes in databases. Further, the invention may be used to sort out vacancies and resumes by professional area and other predetermined similarity criteria. The technical result is to reduce labor costs for the preparation of materials required for machine learning, reduce the amount of machine computing, accelerate the receipt of results, and reduce the time for analyzing search results. To achieve the technical result, the recommender system uses learning and working databases, wherein the learning sequences are formed by sorting and processing the learning database matrices based on user feedback with regard to the degree of correspondence of the results presented to them to the query subject.
    Type: Grant
    Filed: March 17, 2020
    Date of Patent: March 26, 2024
    Assignee: OOO “HEADHUNTER”
    Inventors: Georgiy Andreevich Danshchin, Viktor Viktorovich Reushkin, Aleksandr Alekseevich Sidorov
  • RECOMMENDER SYSTEM FOR STAFF RECRUITMENT USING MACHINE LEARNING WITH MULTIVARIATE DATA DIMENSION REDUCTION AND STAFF RECRUITMENT METHOD USING MACHINE LEARNING WITH MULTIVARIATE DATA DIMENSION REDUCTION
    Publication number: 20220172173
    Abstract: The provided invention relates to search engines and may be used to search for vacancies and resumes in databases. Further, the invention may be used to sort out vacancies and resumes by professional area and other predetermined similarity criteria. The technical result is to reduce labor costs for the preparation of materials required for machine learning, reduce the amount of machine computing, accelerate the receipt of results, and reduce the time for analyzing search results. To achieve the technical result, the recommender system uses learning and working databases, wherein the learning sequences are formed by sorting and processing the learning database matrices based on user feedback with regard to the degree of correspondence of the results presented to them to the query subject.
    Type: Application
    Filed: March 17, 2020
    Publication date: June 2, 2022
    Inventors: Georgiy Andreevich Danshchin, Viktor Viktorovich Reushkin, Aleksandr Alekseevich Sidorov