FR3112634B1 - Procédé de détection d’anomalies - Google Patents

Procédé de détection d’anomalies Download PDF

Info

Publication number
FR3112634B1
FR3112634B1 FR2007444A FR2007444A FR3112634B1 FR 3112634 B1 FR3112634 B1 FR 3112634B1 FR 2007444 A FR2007444 A FR 2007444A FR 2007444 A FR2007444 A FR 2007444A FR 3112634 B1 FR3112634 B1 FR 3112634B1
Authority
FR
France
Prior art keywords
noisy
data set
training data
detection process
anomaly detection
Prior art date
Legal status (The legal status 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 status listed.)
Active
Application number
FR2007444A
Other languages
English (en)
Other versions
FR3112634A1 (fr
Inventor
Roman Moscoviz
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Suez International SAS
Original Assignee
Suez Groupe SAS
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 Suez Groupe SAS filed Critical Suez Groupe SAS
Priority to FR2007444A priority Critical patent/FR3112634B1/fr
Priority to EP21755801.4A priority patent/EP4182859A1/fr
Priority to PCT/FR2021/051321 priority patent/WO2022013503A1/fr
Publication of FR3112634A1 publication Critical patent/FR3112634A1/fr
Priority to ZA2023/01444A priority patent/ZA202301444B/en
Application granted granted Critical
Publication of FR3112634B1 publication Critical patent/FR3112634B1/fr
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N20/00—Machine learning
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/045—Combinations of networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G06N3/088—Non-supervised learning, e.g. competitive learning
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N5/00—Computing arrangements using knowledge-based models
    • G06N5/01—Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Software Systems (AREA)
  • Evolutionary Computation (AREA)
  • Data Mining & Analysis (AREA)
  • Medical Informatics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Physics & Mathematics (AREA)
  • Computing Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Mathematical Physics (AREA)
  • Artificial Intelligence (AREA)
  • Measurement Of Mechanical Vibrations Or Ultrasonic Waves (AREA)
  • Image Analysis (AREA)
  • Testing And Monitoring For Control Systems (AREA)

Abstract

Procédé (1) de détection d’anomalies mis en œuvre par ordinateur dans un ensemble de données mettant en œuvre un module d’apprentissage automatique non-supervisé comprenant une étape de génération (10-10’’) d’une pluralité de copies bruitées de tout ou partie des données de l’ensemble de données d’entraînement, chaque copie bruitée étant obtenue à partir d’au moins un paramètre de génération de bruit, pour chaque copie bruitée, une étape d’entraînement (12-12’’) dudit module d’apprentissage automatique en fonction dudit ensemble de données d’entraînement bruitées associé, et une étape de détermination (14, 14’) de l’ensemble de données d’entraînement bruitées présentant une performance de détection maximale. Figure d’abrégé : Figure 1
FR2007444A 2020-07-16 2020-07-16 Procédé de détection d’anomalies Active FR3112634B1 (fr)

Priority Applications (4)

Application Number Priority Date Filing Date Title
FR2007444A FR3112634B1 (fr) 2020-07-16 2020-07-16 Procédé de détection d’anomalies
EP21755801.4A EP4182859A1 (fr) 2020-07-16 2021-07-15 Génération de copies de données d'entraînement bruitées dans un procédé de détection d'anomalies
PCT/FR2021/051321 WO2022013503A1 (fr) 2020-07-16 2021-07-15 Génération de copies de données d'entraînement bruitées dans un procédé de détection d'anomalies
ZA2023/01444A ZA202301444B (en) 2020-07-16 2023-02-03 Generating noisy copies of training data in a method for detecting anomalies

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
FR2007444 2020-07-16
FR2007444A FR3112634B1 (fr) 2020-07-16 2020-07-16 Procédé de détection d’anomalies

Publications (2)

Publication Number Publication Date
FR3112634A1 FR3112634A1 (fr) 2022-01-21
FR3112634B1 true FR3112634B1 (fr) 2023-04-28

Family

ID=72885727

Family Applications (1)

Application Number Title Priority Date Filing Date
FR2007444A Active FR3112634B1 (fr) 2020-07-16 2020-07-16 Procédé de détection d’anomalies

Country Status (4)

Country Link
EP (1) EP4182859A1 (fr)
FR (1) FR3112634B1 (fr)
WO (1) WO2022013503A1 (fr)
ZA (1) ZA202301444B (fr)

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP6782679B2 (ja) * 2016-12-06 2020-11-11 パナソニック インテレクチュアル プロパティ コーポレーション オブ アメリカＰａｎａｓｏｎｉｃ Ｉｎｔｅｌｌｅｃｔｕａｌ Ｐｒｏｐｅｒｔｙ Ｃｏｒｐｏｒａｔｉｏｎ ｏｆ Ａｍｅｒｉｃａ 情報処理装置、情報処理方法及びプログラム

Also Published As

Publication number Publication date
WO2022013503A1 (fr) 2022-01-20
ZA202301444B (en) 2023-10-25
FR3112634A1 (fr) 2022-01-21
EP4182859A1 (fr) 2023-05-24

Similar Documents

Publication Publication Date Title
US10528878B2 (en) Tailoring question answering system output based on user experience
US10586155B2 (en) Clarification of submitted questions in a question and answer system
US10102254B2 (en) Confidence ranking of answers based on temporal semantics
US9754207B2 (en) Corpus quality analysis
US7870474B2 (en) System and method for smoothing hierarchical data using isotonic regression
US20160026378A1 (en) Answer Confidence Output Mechanism for Question and Answer Systems
US9659259B2 (en) Latency-efficient multi-stage tagging mechanism
US20210240827A1 (en) Apparatus and method for detecting malicious script
US9613093B2 (en) Using question answering (QA) systems to identify answers and evidence of different medium types
US20200327351A1 (en) Optical character recognition error correction based on visual and textual contents
US20210295846A1 (en) Dynamic model selection in speech-to-text processing
CN101218573A (zh) 处理文档中的搭配错误
US20170169355A1 (en) Ground Truth Improvement Via Machine Learned Similar Passage Detection
US20210295845A1 (en) Speech Audio Pre-Processing Segmentation
US20140122069A1 (en) Automatic Speech Recognition Accuracy Improvement Through Utilization of Context Analysis
US20200034465A1 (en) Increasing the accuracy of a statement by analyzing the relationships between entities in a knowledge graph
Liu et al. When and why does a model fail? a human-in-the-loop error detection framework for sentiment analysis
Dojchinovski et al. Crowdsourced corpus with entity salience annotations
US11373655B2 (en) Dual use of acoustic model in speech-to-text framework
US20170124475A1 (en) Cognitive Visual Debugger that Conducts Error Analysis for a Question Answering System
FR3112634B1 (fr) Procédé de détection d’anomalies
US10318885B2 (en) Cognitive system virtual corpus training and utilization
Skitalinskaya et al. To revise or not to revise: Learning to detect improvable claims for argumentative writing support
JP6695835B2 (ja) 機械学習を利用したｆａｑ登録支援方法、及びコンピュータシステム
FR3094506B1 (fr) Système embarqué à bord d'un aéronef de détection et de réponse aux incidents avec enregistrement de logs

Legal Events

Date Code Title Description
PLFP Fee payment

Year of fee payment: 2

EXTE Extension to a french territory

Extension state: PF

PLSC Publication of the preliminary search report

Effective date: 20220121

PLFP Fee payment

Year of fee payment: 3

TP Transmission of property

Owner name: SUEZ INTERNATIONAL, FR

Effective date: 20221129

PLFP Fee payment

Year of fee payment: 4