The prevalence of smartphones and wireless broadband networks have been progressing as a new Railway infomration environment. According to the spread of such devices and information technology, various types of information can be obtained from databases connected to the Internet. One scenario of obtaining such a wide variety of information resources is in the phase of user's transportation. This paper proposes an information provision system, named the Station Concierge System that matches the situation and intention of passengers. The purpose of this system is to estimate the needs of passengers like station staff or hotel concierge and to provide information resources that satisfy user's expectations dynamically. The most important module of the system is constructed based on a new information ranking method for passenger intention prediction and service recommendation. This method has three main features, which are (1) projecting a user to semantic vector space by using her current context, (2) predicting the intention of a user based on selecting a semantic vector subspace, and (3) ranking the services by a descending order of relevant scores to the user' intention. By comparing the predicted results of our method with those of two straightforward computation methods, the experimental studies show the effectiveness and efficiency of the proposed method. Using this system, users can obtain transit information and service map that dynamically matches their context. INTRODUCTIONThe prevalence of smartphones and wireless broadband networks have been progressing as a new Railway infomration environment. According to the spread of such devices and information technology, various types of information can be obtained from databases connected to the Internet. One scenario of obtaining such a wide variety of information is when the users use transportation [1]. In general, information that passengers need are transfer guides, facility information, and tourist information, etc. but they are separately provided and managed by each service provider. Thus, passengers must look for information from each service provider contents and summarize/merge them. Obviously, this is a challenge in enhancing the convenience of transportation service [2]. One additional aspect to the challenge is the wide spreading diversity of passengers with increasing number of them needed special care such as tourists, baby carriage users, handicapped people, etc. and their respective demands. To address these challenges, JR East has provided smartphone users with the smartphone app "JR East App" [3] and has studied information services that reflect the needs of individual passengers by interactive communication [4]. With the available of information providing systems such as the JR East app, passengers can more easily obtain the information. Since the display of these systems is restricted to the displayable area, their screens are created for each category of information. Thus, the passengers struggle to find the information that they n...

No abstract

In recent years, with the development of information technology, many cyber-physical systems, in which real space and the information space are linked for data acquisition and analysis, have been constructed. The purpose of constructing a cyber-physical system is to solve and improve social and environmental problems. An important target is the railway space, which aims to provide safe and stable transportation services as part of the social infrastructure. In this paper, we propose a new data model, the “Context Cube Semantic Network”, for the railway space and a metric method that employs an integrated scale based on heterogeneous correlations of purpose, sensibility, and distance for the railway space. Furthermore, we constructed a station guidance system that implements the proposed method and evaluates subjects at the station. As a result, we clarified the effectiveness and applicability of the system.