• Proceedings of the Korea Information Processing Society Conference
• /
• 2014.11a
• /
• pp.753-756
• /
• 2014

기존의 웹 지도 서비스는 방문 횟수가 많은 장소를 알기 어렵고, 사용자에게 여행 경로를 추천하는 기능 또한 찾기 어려웠다. 따라서 본 논문에서는 사진 촬영 분포를 기반으로 한 여행 경로 추천 시스템을 제안한다. 사진이 많이 촬영된 곳이 여행객이 많이 방문한 곳이며, 유명한 장소일 것이라고 가정하여 사진 촬영 분포를 기반으로 여행 경로를 추천하고자 한다. 여행 경로를 추천하기 위해 사진 데이터의 위치 값을 수집하고, 사진 데이터의 위치 값을 기반으로 사진 촬영 분포를 시각화하여 지도 위에 나타낸다. 또한, 여행 지역 내 사진이 많이 촬영된 장소를 유명한 장소로 선정하여 이를 경유하는 여행 경로를 추천한다. 사용자는 시스템을 통해 유명한 장소를 쉽게 인식할 수 있고, 편리하게 여행 경로를 계획할 수 있다.

• The Journal of the Korea Contents Association
• /
• v.19 no.2
• /
• pp.284-295
• /
• 2019

In the recent times, a personalized travel path recommendation based on both travelogues and community contributed photos and the heterogeneous meta-data (tags, geographical locations, and date taken) which are associated with photos have been studied. The travellers using social media leave their location history, in the form of paths. These paths can be bridged for acquiring information, required, for future recommendation, for the future travellers, who are new to that location, providing all sort of information. In this paper, we propose a personalized travel path recommendation scheme, based on social life log. By taking advantage, of two kinds of social media, such as travelogue and community contributed photos, the proposed scheme, can not only be personalized to user's travel interest, but also be able to recommend, a travel path rather than individual Points of Interest (POIs). The proposed personalized travel route recommendation method consists of two steps, which are: pruning POI pruning step and creating travel path step. In the POI pruning step, candidate paths are created by the POI derived. In the creating travel path step, the proposed scheme creates the paths considering the user's interest, cost, time, season of the topic for more meaningful recommendation.

• Smart Media Journal
• /
• v.9 no.1
• /
• pp.45-50
• /
• 2020

With the development of deep learning, studies using artificial neural networks based on deep learning in recommendation systems are being actively conducted. Especially, the recommendation system based on RNN (Recurrent Neural Network) shows good performance because it considers the sequential characteristics of data. This study proposes a travel route recommendation system using GRU(Gated Recurrent Unit) and Session-based Parallel Mini-batch which are RNN-based algorithm. This study improved the recommendation performance through an ensemble of top1 and bpr(Bayesian personalized ranking) error functions. In addition, it was confirmed that the RNN-based recommendation system considering the sequential characteristics in the data makes a recommendation reflecting the meaning of the travel destination inherent in the travel route.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.5
• /
• pp.117-125
• /
• 2022

Recently, as users' interest for travel increases, research on a travel route recommendation service that replaces the cumbersome task of planning a travel itinerary with automatic scheduling has been actively conducted. The most important and common goal of the itinerary recommendations is to provide the shortest route including popular tour spots near the travel destination. A number of existing studies focused on providing personalized travel schedules, where there was a problem that a survey was required when there were no travel route histories or SNS reviews of users. In addition, implementation issues that need to be considered when calculating the shortest path were not clearly pointed out. Regarding this, this paper presents a quantified method to find out popular tourist destinations using social big data, and discusses problems that may occur when applying the shortest path algorithm and a heuristic algorithm to solve it. To verify the proposed method, 63,000 places information was collected from the Gyeongnam province and big data analysis was performed for the places, and it was confirmed through experiments that the proposed heuristic scheduling algorithm can provide a timely response over the real data.

• KIISE Transactions on Computing Practices
• /
• v.22 no.1
• /
• pp.38-43
• /
• 2016

Recent developments regarding transportation technology have positioned travel as a major leisure activity; however, trip-itinerary planning remains a challenging task for tourists due to the need to select Points of Interest (POI) for visits to unfamiliar cities. Meanwhile, due to the GPS functions on mobile devices such as smartphones and tablet PCs, it is now possible to collect a user's position in real time. Based on these circumstances, our research on an automatic itinerary-planning system to simplify the trip-planning process was conducted briskly. The existing studies that include research on itinerary schedules focus on an identification of the shortest path in consideration of cost and time constraints, or a recommendation of the most-popular travel route in the destination area; therefore, we propose a personalized itinerary-recommendation system for which the stay-time preference of the individual user is considered as part of the personalized service.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.10
• /
• pp.137-146
• /
• 2022

In relation to the travel itinerary recommendation service, which has recently become in high demand, our previous work introduces a method to quantify the popularity of places including tour spots, restaurants, and accommodations through social big data analysis, and to create a travel schedule based on the analysis results. On the other hand, the generated schedule was mainly composed of travel routes that connected tour spots with the shorted distance, and detailed schedule information including restaurants and accommodation information for each travel date was not provided. This paper presents an algorithm for constructing a detailed travel route using a scenario template in a travel schedule created based on social big data, and introduces a prototype system that implements it. The proposed system consists of modules such as place information collection, place-specific popularity score estimation, shortest travel rout generation, daily schedule organization, and UI visualization. Experiments conducted based on social reviews collected from 63,000 places in the Gyeongnam province proved effectiveness of the proposed system.

• Journal of Korea Society of Industrial Information Systems
• /
• v.25 no.1
• /
• pp.31-40
• /
• 2020

In this study, we developed an algorithm for automatic travel itinerary planning based on expert recommendation. The proposed algorithm generates an itinerary by patterning a number of travel routes based on the automatic itinerary generation method based on the routes recommended by travel experts. To evaluate the proposed algorithm, we generated 30 itinerary for Singapore, Bankok, and Da Nang using both algorithms and analyzed the mean difference of trip distances with t-test and interater reliability of those itineraries. The result shows that the itineraries based on the proposed algorithm is not different from that of VRP(Vehicle routing problem) algorithm and interater reliability is high enough to show that the proposed algorithm is effective enough for real-world usage.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2023.01a
• /
• pp.115-118
• /
• 2023

본 논문에서는 지속되던 코로나-19 바이러스로 인한 일상의 제약이 점차 완화되는 추세 속에서 이전에 영위하지 못하던 개개인의 여가생활을 지원하기 위해 개발하였다. 제약이 완화되면서 많은 사람들이 국내 여행의사가 점차 증가된다고 분석된다. 지금 우리의 일상 속에는 인간이 직접 의사결정을 하는 부분들이 많이 줄어들었다. 공공데이터를 이용한 자동화된 경로 추천 시스템을 통해 사용자들은 의사결정의 단계 없이 제공되는 경로를 지도 API를 통해 시각적으로 이용하며 나들이 준비 과정을 간소화 시킬 것으로 예상된다.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2014.10a
• /
• pp.573-576
• /
• 2014

In this paper, it provides social network service using context-aware for tourism. For this the service requires Anthropomorphic natural process. The service object need to provide the function analyzing, storing and processing user action. In this paper, it provides an algorithm to analysis with personalized context aware for users. Providing service is an algorithm providing social network, helped by 'Friend recommendation algorithm' which to make relations and 'Attraction recommendation algorithm' which to recommend somewhere significant. Especially when guide is used, server analysis history and location of users to provide optimal travel path, named 'Travel path recommendation algorithm'. Such as this tourism social network technology can provide more user friendly service. This proposed tour guide system is expected to be applied to a wider vary application services.

• The Journal of the Korean Institute of Forest Recreation
• /
• v.22 no.4
• /
• pp.23-33
• /
• 2018

The purpose of this research is to develop basic materials useful for the visiting management policies' establishment of national parks by analyzing the characteristics of and satisfaction with the visit to Hallyeohaesang National Park according to travel routes. For this, a total of 671 visitors to Hallyeohaesang National Park were recruited and field surveys were conducted three times in spring, summer, and fall from March to November 2017. The Hallyeohaesang national park's visitors were surveyed using a self-administered questionnaire about visitor characteristics (ex: motivation of visiting, travel routes, travel time, and participating activities, etc.) and satisfaction (ex: satisfaction with the visit, intention to revisit, and intention to recommend). SPSS 21.0 program was used for the statistical analysis: frequency analysis and independent-samples t-test analysis. As a result of analysis the motivation of visiting, those who visited only Hallyeohaesang National Park (a single destination) showed a mean value statistically significantly higher level in health improvement and vacation, relaxation, and healing compared to those who had visited or would visit other places along with Hallyeohaesang National Park (multi-destinations). Single destination visitors spent less time traveling from home to national park than multi-destinations visitors. Those who visited only Hallyeohaesang National Park (as a single destination) showed a mean value statistically higher satisfaction and intention to revisit and recommend. The results of this research have significance in providing basic materials to develop efficient park management policies by studying the characteristics of Hallyeohaesang National Park visitors.