• Proceedings of the Korea Information Processing Society Conference
• /
• 2012.11a
• /
• pp.961-964
• /
• 2012

NFC(Near Field Communication)는 10cm 이내의 거리에서 무선기기 간의 통신을 가능케 해주는 기술로 13.56 Mhz RF(Radio Frequency) 주파수 대역을 이용한 비접촉식 근거리 무선통신의 한 종류이다. 올해 출시되는 대부분의 스마트 폰에서 NFC 기능을 탑재하며, NFC기반의 모바일 결제 서비스가 가장 유망한 결제 방식으로 주목 받고 있다. 소비자는 NFC 모바일 단말기를 가지고 판매자의 POS(Point of Sale) 단말기와 근접 통신을 통해 결제를 진행하는 방식으로 다른 무선 통신 방식 (RFID, Bluetooth 등)보다 보안 취약성이 높지 않지만, 기존의 RFID 환경에서 일어날 수 있는 기술적 취약점과 비슷한 유형의 위협이 충분히 발생할 수 있으므로 유효한 보안 기술이 필요하다. 본 논문은 안전한 NFC 모바일 결제 환경을 구축하기 위한 공개키 알고리즘인 타원곡선 암호ECC(Elliptic Curve Cryptosystem)를 적용한 Bilinear Pairing을 활용해서 효율적이고 보안성도 강력한 인증 메커니즘을 제안한다.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.15 no.7
• /
• pp.1531-1536
• /
• 2011

We propose an automatic swearword filter system for online game chatting by using Support Vector Machines(SVM). We collected chatting sentences from online games and tagged them as normal sentences or swearword included sentences. We use n-gram syllables and lexical-part of speech (POS) tags of a word as features and select useful features by chi square statistics. Each selected feature is represented as binary weight and used in training SVM. SVM classifies each chatting sentence as swearword included one or not. In experiment, we acquired overall 90.4% of F1 accuracy.

• Annual Conference on Human and Language Technology
• /
• 2004.10d
• /
• pp.73-81
• /
• 2004

한국어에서의 품사 결정 문제는 형태론적 중의성 문제도 있지만, 영어에는 발생하지 않는 동품사 중의성 문제로 더 까다롭다. 이러한 문제들은 어휘 문맥을 고려하지 않고서는 해결하기 어렵다. 통계 자료 부족 문제에 쉽게 대처하는 모델이 필요하며 문맥에 따른 품사를 결정하고자 할 때 서로 다른 형태의 여러 가지 어휘 문맥 정보를 반영할 수 있는 모델이 필요하다. 본 논문에서는 이런 점에 가장 적합한 최대 엔트로피(maximum entropy : ME) 모델을 품사태깅 작업에 이용하는 문제에 대해 다룬다. 어휘 문맥 정보를 이용하기 위한 자질함수가 매우 많아지는 문제에 대처하기 위해 필요에 따라 어휘 문맥 정보를 사전화 한다. 본 시스템의 특징으로는 어절 단위 품사 태깅을 위한 처리 기법. 어절의 형태소 분석열에 대한 어절 내부 확률 계산. ME 모델의 정규화 과정 생략에 의한 성능 향상, 디코딩 경로의 확장과 같은 점들이 있다. 실험을 통하여 본 연구의 기법이 높은 성능의 시스템을 달성할 수 있음을 알게 되었다.

• Annual Conference on Human and Language Technology
• /
• 2019.10a
• /
• pp.246-251
• /
• 2019

품사 부착 말뭉치란 문장에 포함된 각 단어에 품사 표지를 부착한 말뭉치를 말한다. 이런 말뭉치에는 다양한 형태의 오류들이 포함되어 있으며, 오류가 포함된 말뭉치를 학습 자료로 사용하는 자연언어처리 시스템의 좋은 성능을 기대할 수 없다. 따라서 말뭉치의 일관성이나 정확도는 자연언어처리 시스템의 성능에 많은 영향을 준다. 하지만 말뭉치 구축 과정에서 작업자의 실수가 발생하고 여러 작업자가 작업을 수행하다 보니 일관성을 유지하기가 쉽지 않다. 본 논문에서는 이러한 문제를 해결하기 위해서 GMM을 이용한 군집화를 수행하여 오류 후보를 추출한다. 이를 통해서 말뭉치 구축 과정에서 작업자의 실수를 방지하고 일관성을 유지하고자 한다. 세종품사부착 말뭉치를 대상으로 임의로 오류를 유발시켜 실험한 결과, 재현율 84.74%의 성능으로 오류를 탐지하였다. 향후에 좀 더 높은 재현율을 위해서 자질 확장이나 회귀 분석 방법 등을 추진할 계획이다.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.15 no.6
• /
• pp.1031-1036
• /
• 2020

Untact marketing emerged as one of the top 10 marketing in 2018. Since then, the scale of the mobile payment market has expanded, and the ratio of payment through mobile is melting into life even offline. Various mobile apps such as Samsung Pay and Smart Order are already popular systems, and various other mobile payment systems are increasing. For such mobile payments, this paper aims to comprehensively design a general-purpose untouched offline payment system by designing a mobile payment system that applies a short-range wireless communication method along with a study on the currently available mobile payment-linked API. We propose an offline payment system with an untouch method to prevent the spread of infectious diseases and contribute to a healthy society by solving the problem and minimizing contact with others in the current situation like the Corona 19 Incident.

• Journal of Digital Convergence
• /
• v.14 no.8
• /
• pp.115-125
• /
• 2016

Recently, there has been a demand for high quality services as the number of stores that use IT devices increases, and the importance regarding that matter has been emphasized. This study analyzed the factors that influence the effects of Store-IT Management Service. With customers who experienced Store-IT Management Service Quality as targets, it figured out the effects that Store-IT Management Service Quality had on Service Confirmation, Customer Satisfaction, and Continuous Intention. As a result, looking closely at the effects that Store-IT Management Service Quality had on Service Confirmation, it turned out that empathy, reliability, tangibility, and assurance had positive effects. As for the effects that Store-IT Management Service Quality had on Customer Satisfaction, empathy, reliability, and tangibility turned out to be important factors that had positive effects. In addition, Service Confirmation and Customer Satisfaction to Store-IT Management Service Quality turned out to have positive effects on Continuous Intention. With these results, given factors of Store-IT Management Service Quality, via Service Confirmation and Customer Satisfaction, were verified to have positive effect relationships with Continuous Intention. The result of this study is expected to help enhance Store-IT Management Service Quality.

• Journal of KIISE:Software and Applications
• /
• v.37 no.12
• /
• pp.946-950
• /
• 2010

Many sentiment categorization systems based on machine learning methods use morphological analyzers in order to extract linguistic features from sentences. However, the morphological analyzers do not generally perform well in a customer review domain because online customer reviews include many spacing errors and spelling errors. These low performances of the underlying systems lead to performance decreases of the sentiment categorization systems. To resolve this problem, we propose a feature extraction method based on simple longest matching of Eojeol (a Korean spacing unit) and phoneme patterns. The two kinds of patterns are automatically constructed from a large amount of POS (part-of-speech) tagged corpus. Eojeol patterns consist of Eojeols including content words such as nouns and verbs. Phoneme patterns consist of leading consonant and vowel pairs of predicate words such as verbs and adjectives because spelling errors seldom occur in leading consonants and vowels. To evaluate the proposed method, we implemented a sentiment categorization system using a SVM (Support Vector Machine) as a machine learner. In the experiment with Korean customer reviews, the sentiment categorization system using the proposed method outperformed that using a morphological analyzer as a feature extractor.

• The Journal of Information Systems
• /
• v.26 no.3
• /
• pp.295-312
• /
• 2017

Purpose Consumption behaviors of consumers have changed with the widespread use of the Internet and smart phones, and accordingly online marketing activities are becoming ever more prevalent. Yet, the domestic food-service industry has yet to offer an Omni-Channel order system that encompasses a online, offline, and mobile interface. Also, a multilingual menu ordering service for foreign tourists is not yet available. Therefore, if an order service system accessible online and offline which could provide multi-language services were implemented, the satisfaction of the service provider and domestic and foreign customers would be maximized. Design/methodology/approach By designing an electronic menu based on open an OS and providing electronic menus in offline stores, we have completed the design of a linked order system which would be available everywhere (online, offline, and mobile). The CMS was developed to integrate these three mediums and the entire operator was designed to receive basic information and statistical information about the merchants, or store operators. Also, a multilingual term dictionary containing menu information for foreign tourists was made into a database so that foreign tourists who are having difficulty in communication can use it more easily. Findings We have made it possible for customers to use the order service without distinction between online, offline, and mobile platforms, and have proved that it is a more efficient and convenient service for customers as well as operators. Nevertheless, as an initial model, the implemented system has limitations on the execution of the payment support method in the electronic menu board and in the management division of the CMS. In case of commercialization, it is necessary to make an alliance of efforts to attract initial franchises. Through further supplementation, we expect the online and offline connection-types martservice system will maximize the satisfaction of both operators and customers alike.

• Journal of Korea Multimedia Society
• /
• v.18 no.8
• /
• pp.968-979
• /
• 2015

In this paper, we study a vibration bell App which shows waiting sequence numbers by utilizing smartphones to solve an inconveniently long waiting time from ordering to getting foods in restaurants and coffee shops. Unlike existing independently developed hardware and software, the vibration bell App is developed to manage and integrate customer management service, POS service in shops, and group shop management services. The functions of the vibration bell App include two-way communications based on NFC- issuing waiting sequence numbers and electronic coupon, showing event information, and transferring user information. Furthermore, the user's personal information is minimized by recognizing the pre-existing information of the user's smartphone. Replacing the shop's vibration bell system with the vibration bell APP, the shops can reduce the cost of construction and maintenance by up to 1/10, compared to the cost of for existing vibration bell systems. Moreover, the customer's preference and current sales trend can be easily figured out. Thus, it will have a great effect on the future marketing strategies.