Knowledge management practice of medical cloud logistics industry: transportation resource semantic discovery based on ontology modelling

PurposeThe booming of the Internet of things (IoT) and artificial intelligence (AI) techniques contributes to knowledge adoption and management innovation for the healthcare industry. It is of great significance to transport the medical resources to required places in an efficient way. However, it is difficult to exactly discover matched transportation resources and deliver to its destination due to the heterogeneity. This paper studies the medical transportation resource discovery mechanism, leading to efficiency improvement and operational innovation.Design/methodology/approachTo solve the transportation resource semantic discovery problem under the novel cloud environment, the ontology modelling approach is used for both transportation resources and tasks information modes. Besides, medical transportation resource discovery mechanism is proposed, and resource matching rules are designed including three stages: filtering reasoning, QoS-based matching and user preferences-based rank to satisfy personalized demands of users. Furthermore, description logic rules are built to express the developed matching rules.FindingsAn organizational transportation case is taken as an example to describe the medical transportation logistics resource semantic discovery process under cloud medical service scenario. Results derived from the proposed semantic discovery mechanism could assist operators to find the most suitable resources.Research limitations/implicationsThe case study validates the effectiveness of the developed transportation resource semantic discovery mechanism, contributing to knowledge management innovation for the medical logistics industry.Originality/valueTo improve task-resource matching accuracy under cloud scenario, this study develops a transportation resource semantic discovery procedure from the viewpoint of knowledge management. The novel knowledge management practice contributes to operational management of the cloud medical logistics service by introducing ontology modelling and creative management.

Evaluating the Spatial Deprivation of Public Transportation Resources in Areas of Rapid Urbanization: Accessibility and Social Equity

To better understand the transportation situation in rapid urbanization areas and to improve social equity, this study constructed an approach to assess the spatial differentiation of public transportation resources based on deprivation theory and an accessibility analysis. Chenggong New District in Kunming, a typical rapid urbanization area in China, was analyzed as a case study. We introduced 6 indexes to establish a public transportation spatial deprivation evaluation system and applied SPSS to screen out two main factors that reflected the spatial deprivation associated with public transportation resources and services. Then, we adopted the accessibility model and spatial cluster model to embody residents’ opportunities to obtain access to public transportation and to judge whether public transportation resource allocation is appropriate. In addition, we used ArcGIS technology to better understand the spatial deprivation characteristics of public transportation. We found that the pattern of public transportation spatial deprivation in Chenggong could be summarized as “multicore and local radiation”: the spatial accessibility characteristics of public transportation take the form of a circular layer along with the metro lines and decline progressively toward the peripheral areas, where public transportation resource allocation is lacking. These findings show that the public transportation situation in rapid urbanization areas is consistent with the local land-use context and the suitability of established methods for extracting spatial public transportation characteristics.

Complete Automation of Metro Stations through Artificial Intelligence

Metro stations have become an invaluable transportation resource and will be spreading out of the metropolitan cities soon. It has reduced travel time and travel cost. We intend to research the possibility of unmanned metro stations through the application of artificial intelligence, one of which is expert systems. Expert systems —that are able to hold the accumulated knowledge of different domain experts can be implemented to guide the commuter about the optimum travel route. In this way the metro stations can be turned into self-sustainable structures.