Processing

Please wait...

Settings

Settings

Goto Application

1. WO2022041406 - OCR AND TRANSFER LEARNING-BASED APP VIOLATION MONITORING METHOD

Publication Number WO/2022/041406
Publication Date 03.03.2022
International Application No. PCT/CN2020/120724
International Filing Date 14.10.2020
IPC
G06K 9/20 2006.1
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
KRECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
9Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
20Image acquisition
CPC
G06F 16/951
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
FELECTRIC DIGITAL DATA PROCESSING
16Information retrieval; Database structures therefor; File system structures therefor
90Details of database functions independent of the retrieved data types
95Retrieval from the web
951Indexing; Web crawling techniques
G06F 16/955
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
FELECTRIC DIGITAL DATA PROCESSING
16Information retrieval; Database structures therefor; File system structures therefor
90Details of database functions independent of the retrieved data types
95Retrieval from the web
955using information identifiers, e.g. uniform resource locators [URL]
G06K 9/6268
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
KRECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
9Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
62Methods or arrangements for recognition using electronic means
6267Classification techniques
6268relating to the classification paradigm, e.g. parametric or non-parametric approaches
G06N 3/0445
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
3Computer systems based on biological models
02using neural network models
04Architectures, e.g. interconnection topology
0445Feedback networks, e.g. hopfield nets, associative networks
G06N 3/0454
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
3Computer systems based on biological models
02using neural network models
04Architectures, e.g. interconnection topology
0454using a combination of multiple neural nets
G06N 3/049
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
3Computer systems based on biological models
02using neural network models
04Architectures, e.g. interconnection topology
049Temporal neural nets, e.g. delay elements, oscillating neurons, pulsed inputs
Applicants
  • 深圳大学 SHENZHEN UNIVERSITY [CN]/[CN]
Inventors
  • 蔡树彬 CAI, Shubin
  • 明仲 MING, Zhong
  • 林旭恒 LIN, Xuheng
  • 吴东阳 WU, Dongyang
Agents
  • 深圳市君胜知识产权代理事务所(普通合伙) JOHNSON INTELLECTUAL PROPERTY AGENCY (SHENZHEN)
Priority Data
202010862575.X25.08.2020CN
Publication Language Chinese (zh)
Filing Language Chinese (ZH)
Designated States
Title
(EN) OCR AND TRANSFER LEARNING-BASED APP VIOLATION MONITORING METHOD
(FR) PROCÉDÉ DE SURVEILLANCE DE VIOLATIONS D'APPLICATIONS BASÉ SUR UNE RECONNAISSANCE OPTIQUE DE CARACTÈRES ET SUR UN APPRENTISSAGE PAR TRANSFERT
(ZH) 一种基于OCR和迁移学习的APP违规监测方法
Abstract
(EN) Disclosed in the present invention is an OCR and transfer learning-based app violation monitoring method. Said method comprises: periodically updating an APK, and performing data acquisition on a corresponding app according to the updated APK, the data acquisition comprising the capture of data packets and the acquisition of page screenshots; performing text recognition and extraction on the screenshots on the basis of an OCR algorithm; for the recognized text content, constructing a sample set by means of keywords and regular expressions, and performing manual annotation on same; inputting the manually annotated sample set into a pre-trained deep learning model for model adjustment, and implementing violation determination of text in different scenarios by means of division of service scenarios; and collecting statistics of scores of different apps according to the determination results outputted by the deep learning model, so as to obtain violation scores of the apps. By acquiring and analyzing data of apps, the present invention effectively and quickly detects the violation usage situations of the apps.
(FR) Est divulgué dans la présente invention un procédé de surveillance de violations d'applications basé sur une reconnaissance optique de caractères (OCR) et sur un apprentissage par transfert. Ledit procédé consiste à : mettre à jour périodiquement un APK et réaliser une acquisition de données sur une application correspondante en fonction de l'APK mis à jour, l'acquisition de données comprenant la capture de paquets de données et l'acquisition de captures d'écrans de pages ; réaliser une reconnaissance et une extraction de textes sur les captures d'écrans sur la base d'un algorithme d'OCR ; pour le contenu de texte reconnu, construire un ensemble d'échantillons au moyen de mots-clés et d'expressions régulières et effectuer une annotation manuelle sur celui-ci ; entrer l'ensemble d'échantillons annotés manuellement dans un modèle d'apprentissage profond pré-appris pour un ajustement de modèle, et implémenter une détermination de violations de textes dans différents scénarios au moyen d'une division de scénarios de services ; et collecter des statistiques de scores de différentes applications en fonction des résultats de détermination délivrés par le modèle d'apprentissage profond, de sorte à obtenir des scores de violations des applications. Par l'acquisition et l'analyse de données d'applications, la présente invention détecte efficacement et rapidement les situations d'usages de violations des applications.
(ZH) 本发明公开了一种基于OCR和迁移学习的APP违规监测方法,所述方法包括:定期更新APK,根据更新后的APK进行对应APP的数据采集,所述数据采集包括数据抓包和页面截图;基于OCR算法对截图进行文字识别及提取;对识别后的文字内容,通过关键字及正则表达式进行样本集构建,并进行人工标注;将人工标注后的样本集输入预训练的深度学习模型进行模型调整,通过划分业务场景实现不同场景下文本的违规判别;根据所述深度学习模型输出的判别结果,对不同APP的得分进行统计,得出APP的违规得分。本发明通过对APP的数据进行采集和分析,有效、快速检测出APP的违规使用情况。
Related patent documents
Latest bibliographic data on file with the International Bureau