IDENTIFICATION OF IDLE NETWORK CONNECTIONS BASED ON MACHINE LEARNING Russian patent published in 2020 - IPC H04L12/26 

Abstract RU 2715802 C1

FIELD: physics.

SUBSTANCE: invention relates to means of navigation, to resources in network connections. Invention discloses a system and a method, including computer programs encoded on a computer storage medium for identifying idle network connections. In one aspect, the system includes an external server(s) which receives data indicating, for a plurality of different user interactions with one or more application links, presentation duration. Internal server(s), which communicates with the external server(s), can classify each application link as idle or operating on the basis of application of the machine training model to presentation duration for the application link. Machine learning model can be generated using marked training data. Internal server(s) may generate and output a warning identifying an application link as a broken link, based on the fact that the application link is classified as disabled by the machine learning model.

EFFECT: technical result is wider range of means.

20 cl, 6 dwg

Similar patents RU2715802C1

Title Year Author Number
LISTS AND FEATURES OF SOURCES/ADDRESSEES FOR PREVENTING SPAM MESSAGES 2004
  • Gudman Dzhoshua T.
  • Rauntvejt Robert L.
  • Gvozdz Dehniel
  • Mer Dzhon D.
  • Khauehll Natan D.
  • Rupersburg Mika S.
  • Starbuk Brajan T.
RU2378692C2
DETECTING TEXT FIELDS USING NEURAL NETWORKS 2018
  • Zuev, Konstantin Alekseevich
  • Senkevich, Oleg Evgenyevich
  • Golubev, Sergei Vladimirovich
RU2699687C1
DETECTING SECTIONS OF TABLES IN DOCUMENTS BY NEURAL NETWORKS USING GLOBAL DOCUMENT CONTEXT 2019
  • Stanislav Semenov
RU2721189C1
IDENTIFICATION OF FIELDS AND TABLES IN DOCUMENTS USING NEURAL NETWORKS USING GLOBAL DOCUMENT CONTEXT 2019
  • Stanislav Semenov
RU2723293C1
RETRIEVING FIELDS USING NEURAL NETWORKS WITHOUT USING TEMPLATES 2019
  • Stanislav Semenov
RU2737720C1
SYSTEM AND METHOD FOR GENERATING CLASSIFIER FOR DETECTING PHISHING SITES USING DOM OBJECT HASHES 2023
  • Tushkanov Vladislav Nikolaevich
RU2811375C1
METHOD AND SERVER OF FORECASTING POPULARITY OF ELEMENT CONTENT 2015
  • Gusev Gleb Gennadevich
  • Drutsa Aleksej Valerevich
  • Serdyukov Pavel Viktorovich
RU2635905C2
IDENTIFICATION OF FIELDS ON AN IMAGE USING ARTIFICIAL INTELLIGENCE 2018
  • Kalenkov Maksim Petrovich
RU2695489C1
IDENTIFICATION OF BLOCKS OF RELATED WORDS IN DOCUMENTS OF COMPLEX STRUCTURE 2019
  • Stanislav Semenov
RU2765884C2
METHOD FOR DETECTING PHISHING SITES AND SYSTEM THAT IMPLEMENTS IT 2023
  • Tushkanov Vladislav Nikolaevich
RU2813242C1

RU 2 715 802 C1

Authors

Li, Xin

Yang, Fang

Dates

2020-03-03Published

2016-10-17Filed