METHODS AND SERVERS FOR STORAGE OF DATA RELATED TO USERS AND DIGITAL ELEMENTS OF RECOMMENDATION SYSTEM Russian patent published in 2023 - IPC G06F16/438 

Abstract RU 2789842 C2

FIELD: computer technology.

SUBSTANCE: model is trained for formation of the first vector representations of users and elements. The first vector representations of users are stored in an undistributed data storage, and the first vector representations of elements are stored in a distributed data storage. The model is retrained for formation of the second vector representations of users and elements. The second vector representations of users are stored in the undistributed data storage in addition to the first vector representations of users, and the second vector representations of elements are stored in the distributed data storage instead of corresponding first vector representations of elements by replacement of the first vector representations of elements. When the second vector representations of elements are stored in each node of the distributed data storage, a server deletes the first vector representations of users, related to the first value, from the undistributed data storage.

EFFECT: reduction in computational load, when determining digital content, which should be provided to users of a recommendation service.

20 cl, 10 dwg

Similar patents RU2789842C2

Title Year Author Number
METHOD AND SYSTEM FOR EVALUATING DATA ON USER-ELEMENT INTERACTIONS 2018
  • Ushanov Dmitry Valerievich
  • Votyakov Roman Alekseevich
  • Parkhomenko Pavel Andreevich
RU2725659C2
METHOD AND SYSTEM FOR GENERATING RECOMMENDATIONS OF DIGITAL CONTENT 2018
  • Lamburt Viktor Grigorievich
  • Ushanov Dmitry Valerievich
  • Ivanychev Sergey Dmitrievich
RU2731335C2
METHOD AND SERVER FOR DETERMINING TRAINING SET FOR MACHINE LEARNING ALGORITHM (MLA) TRAINING 2020
  • Dorogush Anna Veronika Yurevna
  • Alipov Vyacheslav Vyacheslavovich
  • Kruchinin Dmitriy Andreevich
  • Oganesyan Dmitry Alekseevich
RU2817726C2
METHOD AND SYSTEM FOR PROVIDING A LEVEL OF SERVICE WHEN ADVERTISING CONTENT ELEMENT 2019
  • Sokolov Evgeny Andreevich
  • Danilchenko Andrey Petrovich
RU2757406C1
METHOD AND DEVICE FOR CREATING RECOMMENDED LIST OF CONTENT 2015
  • Rojzner Mikhail Aleksandrovich
RU2632131C2
HISTORY LOG OF USERS ACTIVITIES AND ASSOCIATED EMOTIONAL STATES 2012
  • Gerts Lukas Yakobus Fransiskus
  • Timmer Remko
  • Brauver Tyadde Ryutger
  • Rajmakers Teodorus Gerardus Khyugo Kornelius
  • Lopik Vendelina Elize Korinn
RU2610944C2
METHOD AND SYSTEM FOR DETERMINING PARAMETER RELEVANCE FOR CONTENT ITEMS 2018
  • Sokolov Yevgeny Andreevich
  • Lamburt Viktor Grigorievich
  • Sharchilev Boris Dmitrievich
  • Danilchenko Andrey Petrovich
RU2714594C1
FRIENDS RECOMMENDATIONS METHOD AND SERVER AND TERMINAL FOR THIS 2013
  • Cha Sang-Ok
  • I Sang-Kho
  • Shin Dzae-Khiuk
  • Li Joon-Kiong
  • Choj Khiun-Dzin
RU2613724C2
METHOD AND APPARATUS FOR TRAINING MACHINE LEARNING ALGORITHM (MLA) FOR CREATING CONTENT RECOMMENDATIONS IN A RECOMMENDATION SYSTEM AND A METHOD AND APPARATUS FOR CREATING RECOMMENDED CONTENT USING A MACHINE LEARNING ALGORITHM 2016
  • Lifar Igor Igorevich
  • Lamburt Viktor Grigorevich
RU2731659C2
METHOD AND SERVER OF CREATING RECOMMENDED SET OF ELEMENTS FOR USER 2015
  • Rojzner Mikhail Aleksandrovich
  • Lamburt Viktor Grigorevich
RU2629638C2

RU 2 789 842 C2

Authors

Kondrashkin Dmitry Andreevich

Svianadze Zurab Otarievich

Ushanov Dmitry Valerevich

Dates

2023-02-13Published

2020-10-06Filed