WO2023068503A1 - Procédé de conversion de méta-description pour analyse de données de réseau, et dispositif d'analyse de réseau l'utilisant - Google Patents

Procédé de conversion de méta-description pour analyse de données de réseau, et dispositif d'analyse de réseau l'utilisant Download PDF

Info

Publication number
WO2023068503A1
WO2023068503A1 PCT/KR2022/011580 KR2022011580W WO2023068503A1 WO 2023068503 A1 WO2023068503 A1 WO 2023068503A1 KR 2022011580 W KR2022011580 W KR 2022011580W WO 2023068503 A1 WO2023068503 A1 WO 2023068503A1
Authority
WO
WIPO (PCT)
Prior art keywords
data
meta description
meta
network
description
Prior art date
Application number
PCT/KR2022/011580
Other languages
English (en)
Korean (ko)
Inventor
박형곤
정다은
Original Assignee
이화여자대학교 산학협력단
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 이화여자대학교 산학협력단 filed Critical 이화여자대학교 산학협력단
Publication of WO2023068503A1 publication Critical patent/WO2023068503A1/fr

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
    • H04L41/14—Network analysis or design
    • H04L41/142—Network analysis or design using statistical or mathematical methods
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N20/00—Machine learning
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L43/00—Arrangements for monitoring or testing data switching networks
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L43/00—Arrangements for monitoring or testing data switching networks
    • H04L43/02—Capturing of monitoring data
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L43/00—Arrangements for monitoring or testing data switching networks
    • H04L43/06—Generation of reports
    • H04L43/067—Generation of reports using time frame reporting
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L65/00—Network arrangements, protocols or services for supporting real-time applications in data packet communication
    • H04L65/40—Support for services or applications
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L67/00—Network arrangements or protocols for supporting network services or applications
    • H04L67/50—Network services
    • H04L67/56—Provisioning of proxy services
    • H04L67/561—Adding application-functional data or data for application control, e.g. adding metadata

Definitions

  • the present invention relates to a meta description conversion method and a network analysis apparatus using the meta description conversion method, and more specifically, to a method of extracting time data and length data from raw data and converting the meta description, and converting the meta description converted data into an AI / It is about the device used as the input data of ML.
  • NWDAF Network Data Analytics Function
  • the present invention provides a method and apparatus for minimizing redundancy occurring in the network data analysis process by extracting time data and length data from raw data and using meta description converted data as input data of AI/ML. .
  • the present invention provides a method and apparatus for reflecting time-varying network characteristics by defining data for each characteristic of time data and length data and data between characteristics as a meta description for each characteristic and a meta description between characteristics.
  • the present invention provides a method and apparatus for reducing NWDAF data processing time by performing network analysis using a meta description that has a smaller capacity than raw data but includes network characteristics.
  • a meta description conversion method includes extracting time data and length data from raw data; generating a meta description for each characteristic by converting information for each time interval of the time data and the length data; converting information indicating a relationship between the time data and the length data to generate a meta description between characteristics; and generating a final meta description by using the meta description for each characteristic and the meta description between the characteristics.
  • the time data of the meta description conversion method according to an embodiment of the present invention may be data representing the input time of the raw data, and the length data may be data representing the length of a packet including the raw data. .
  • the step of generating the meta description for each characteristic of the meta description transformation method includes generating first frequency data by transforming statistical data about the time data into frequency data of fast Fourier transform coefficients. ; generating second frequency data by converting statistical data of the length data into frequency data of fast Fourier transform coefficients; and generating a meta description for each characteristic by combining the first frequency data and the second frequency data.
  • the meta description between the characteristics of the meta description conversion method according to an embodiment of the present invention may include at least one of a dot product between the time data and the length data, a correlation, a P value of Pearson's correlation coefficient, and a mutual data value. there is.
  • the raw data of the meta description conversion method is data generated in the process of the user requesting a service from the network, and the final meta description is AI/ML (Artificial Intelligence) of the network analysis device. / Machine Learning) to classify the service being used by the user and to determine a NWDAF (Network Data Analytics Function) policy according to the classification result.
  • AI/ML Artificial Intelligence
  • NWDAF Network Data Analytics Function
  • a network data analysis method includes receiving raw data generated in a process in which a user requests a service from a network; Time data and length data are extracted from the raw data to generate a meta description for each characteristic and a meta description between the characteristics, and a final meta description is generated using the meta description for each characteristic and the meta description between the characteristics. doing; and classifying the service being used by the user based on the final meta description, and determining an NWDAF policy according to a result of the classification.
  • the meta description for each characteristic of the network data analysis apparatus includes first frequency data obtained by converting statistical data of the time data into frequency data of fast Fourier transform coefficients and statistical data of the length data. It may be generated by combining second frequency data obtained by converting ? to frequency data of fast Fourier transform coefficients.
  • the meta description between the characteristics of the apparatus for analyzing network data may include data representing statistical and entropic relationships between the time data and the length data.
  • time-varying network characteristics may be reflected by defining data for each characteristic of time data and length data and data between characteristics as a meta description for each characteristic and a meta description between characteristics.
  • the meta description conversion unit 120 may extract time data and length data from raw data received by the communicator 110 .
  • the time data may be data indicating a time when raw data is input to the network from a user or a time when raw data is generated according to a user's input.
  • the length data may be data representing the length of a packet including raw data.
  • the meta description conversion unit 120 may extract some data 321 from the original data 310 .
  • the data extracted from the raw data 310 by the meta description conversion unit 120 is time data. and length data can be
  • the second frequency data 621 may be generated by transforming the statistical data of 620 into frequency data of fast Fourier transform coefficients.
  • statistical data is length data. It may include at least one of Skewness, Kurtosis, and Standard Error of (620).
  • the present invention can reduce NWDAF data processing time by performing network analysis using a meta description that has a smaller capacity than raw data but includes network characteristics.

Landscapes

  • Engineering & Computer Science (AREA)
  • Signal Processing (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Mathematical Physics (AREA)
  • General Physics & Mathematics (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Software Systems (AREA)
  • Mathematical Analysis (AREA)
  • Medical Informatics (AREA)
  • Algebra (AREA)
  • Artificial Intelligence (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Computation (AREA)
  • Mathematical Optimization (AREA)
  • Pure & Applied Mathematics (AREA)
  • Computing Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Probability & Statistics with Applications (AREA)
  • Library & Information Science (AREA)
  • Multimedia (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

Le procédé de conversion de méta-description peut comprendre les étapes consistant à : extraire des données de temps et des données de longueur à partir de données sources; convertir des informations spécifiques de segment de temps concernant chacune des données de temps et des données de longueur de façon à générer une méta-description spécifique de caractéristique; convertir des informations indiquant une relation entre les données de temps et les données de longueur, de façon à générer une méta-description entre les caractéristiques; et générer la méta-description finale en utilisant la méta-description spécifique de caractéristique et la méta-description entre les caractéristiques.
PCT/KR2022/011580 2021-10-21 2022-08-04 Procédé de conversion de méta-description pour analyse de données de réseau, et dispositif d'analyse de réseau l'utilisant WO2023068503A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
KR1020210141124A KR102561335B1 (ko) 2021-10-21 2021-10-21 네트워크 데이터 분석을 위한 메타 디스크립션 변환 방법 및 그를 이용한 네트워크 분석 장치
KR10-2021-0141124 2021-10-21

Publications (1)

Publication Number Publication Date
WO2023068503A1 true WO2023068503A1 (fr) 2023-04-27

Family

ID=86059324

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/KR2022/011580 WO2023068503A1 (fr) 2021-10-21 2022-08-04 Procédé de conversion de méta-description pour analyse de données de réseau, et dispositif d'analyse de réseau l'utilisant

Country Status (2)

Country Link
KR (1) KR102561335B1 (fr)
WO (1) WO2023068503A1 (fr)

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2018505456A (ja) * 2014-12-22 2018-02-22 ロヴィ ガイズ， インコーポレイテッド メタデータおよび使用データ解析を用いるフィルタリング技術のためのシステムおよび方法
KR20180102804A (ko) * 2017-03-08 2018-09-18 한국전자통신연구원 네트워크 패킷 검색 장치 및 방법
KR20190091488A (ko) * 2016-12-02 2019-08-06 레알레예스 오위 미디어 컨텐츠 성과 예측을 위한 데이터 프로세싱 방법
KR20210037416A (ko) * 2019-09-27 2021-04-06 삼성전자주식회사 이동 통신 시스템에서 nwdaf를 활용한 서비스의 탐지 및 서비스의 특성 분석을 위한 방법 및 장치

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2018505456A (ja) * 2014-12-22 2018-02-22 ロヴィ ガイズ， インコーポレイテッド メタデータおよび使用データ解析を用いるフィルタリング技術のためのシステムおよび方法
KR20190091488A (ko) * 2016-12-02 2019-08-06 레알레예스 오위 미디어 컨텐츠 성과 예측을 위한 데이터 프로세싱 방법
KR20180102804A (ko) * 2017-03-08 2018-09-18 한국전자통신연구원 네트워크 패킷 검색 장치 및 방법
KR20210037416A (ko) * 2019-09-27 2021-04-06 삼성전자주식회사 이동 통신 시스템에서 nwdaf를 활용한 서비스의 탐지 및 서비스의 특성 분석을 위한 방법 및 장치

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
DAEUN JUNG: "Meta Description Transform for Network Data Analytics/ 저작자표시-비영리-변경금지 2.0 대한민국 이용자는 아래의 조건을 따르는 경우에 한하여 자유롭게", MASTER'S THESIS, DEPARTMENT OF ELECTRONIC AND ELECTRICAL ENGINEERING, THE GRADUATE SCHOOL OF EWHA WOMANS UNIVERSITY., 1 June 2021 (2021-06-01), The Graduate School of Ewha Womans University., XP093058584, Retrieved from the Internet <URL:https://dspace.ewha.ac.kr/handle/2015.oak/258023> [retrieved on 20230628] *

Also Published As

Publication number Publication date
KR102561335B1 (ko) 2023-07-28
KR20230057105A (ko) 2023-04-28

Similar Documents

Publication Publication Date Title
EP2019360A1 (fr) Appareil de traitement de données et procédé de transfert de données
US5915127A (en) System for fast data transfer utilizing separation of transfer data header and substantially continuously reading and processing transfer data based on read header
WO2022059969A1 (fr) Procédé de pré-apprentissage de réseau neuronal profond permettant une classification de données d&#39;électrocardiogramme
WO2019164074A1 (fr) Procédé d&#39;analyse de poussière fine et appareil permettant la mise en œuvre dudit procédé
CN112364829B (zh) 一种人脸识别方法、装置、设备及存储介质
CN114745451A (zh) 数据传输方法及装置、电子设备和计算机可读介质
WO2023068503A1 (fr) Procédé de conversion de méta-description pour analyse de données de réseau, et dispositif d&#39;analyse de réseau l&#39;utilisant
WO2019112385A1 (fr) Procédé de codage d&#39;informations temporelles de caractéristiques spécifiques à une trame de segment d&#39;image en vue d&#39;une reconnaissance de vidéo
WO2016148516A1 (fr) Procédé de compression d&#39;image et appareil de compression d&#39;image
CN113407665A (zh) 文本比对方法、装置、介质及电子设备
WO2017122845A1 (fr) Système et procédé d&#39;acquisition/reproduction d&#39;image à ultra-haute résolution multicanal pour fonctions hétérogènes de chaque canal
WO2020213757A1 (fr) Procédé de détermination de similarité de mots
WO2011007970A1 (fr) Procédé et appareil pour traiter une image
WO2021251600A1 (fr) Procédé et dispositif de prédiction de succès au box-office de contenu grâce à l&#39;intelligence artificielle
WO2022045519A1 (fr) Dispositif et procédé de sélection de modèle d&#39;optimisation
WO2022114272A1 (fr) Procédé de traitement de transactions adaptatif et dispositif associé
JP2757668B2 (ja) 画像解析装置
CN110378378A (zh) 事件检索方法、装置、计算机设备及存储介质
WO2023214633A1 (fr) Procédé et dispositif d&#39;amélioration d&#39;une qualité d&#39;image sur la base d&#39;un réseau neuronal à super-résolution
WO2024043406A1 (fr) Système et procédé de compression de nuage de points pour diffusion en continu
WO2024111730A1 (fr) Appareil de ré-identification d&#39;objets basée sur l&#39;ia et procédé associé
WO2021137357A1 (fr) Appareil et procédé d&#39;acquisition de données d&#39;apprentissage basées sur un mélange par trajets multiples
WO2023058842A1 (fr) Appareil électronique et procédé de génération de domaine cible
WO2023096309A1 (fr) Dispositif électronique et procédé d&#39;élimination de mot préjudiciable par filtrage
WO2023204399A1 (fr) Dispositif et procédé de planification de réseau

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 22883731

Country of ref document: EP

Kind code of ref document: A1