Toshiba Digital Solutions and JUNPUZI Launch Trials for AI-based Demand Responsive Rideshare Transportation

- System can alleviate transport access difficulties and contribute to community revitalization through demand forecasting enabled by deep learning -

July 12, 2018
Toshiba Digital Solutions Corporation

KAWASAKI and TOKYO–Toshiba Digital Solutions Corporation (TDSL) and JUNPUZI.CO.,LTD. (JUNPUZI) today announced they commenced trials for AI-based demand responsive rideshare transportation (including taxis and buses).

In recent years Japan has seen the discontinuation of local bus routes due to declining populations and an increasing number of drivers voluntarily surrendering their licenses. This has resulted in a dramatic increase of people experiencing transport access difficulties, particularly the elderly. Furthermore, with heightened expectations for community revitalization programs, including tourism and resident exchange promotion, there is a need for affordable and convenient transport options.

JUNPUZI and The University of Tokyo jointly developed a demand responsive rideshare transport system “Convenicle“ (meaning “convenient and smart vehicle”) that has been in operation since 2009. Convenicle is a system that automatically configures operation plans (including routes, schedules and the number of passengers) in response to requested embarkation and disembarkation points and riding times, which can be entered at random by customers using smartphone apps or through phone calls. As a convenient transportation method that is more affordable than taxis or buses, rideshare taxis and buses operated by Convenicle are used by approximately 65,000 people per month in 42 locations nationwide.

Both companies aim to set up efficient operation plans through demand forecasting. This will be done by employing JUNPUZI’s big data, which has been acquired by integrating approximately nine years of operational data and external environmental data such as weather and traffic data, and Toshiba "SATLYS™" analytics AI, which is based on TDSL’s abundant know-how in deep learning and other technologies developed through its experience in a wide range of business fields. The system can be utilized for advance vehicle dispatch coordination and other applications by forecasting demand for pick up and drop off points as well as passenger numbers several weeks ahead of time and visualizing this data on maps. In addition, both companies will verify how the system can be used for events where demand is expected and for other town development initiatives.

TDSL and JUNPUZI will conduct demand forecasting demonstrations and use the results to improve the functionality of Convenicle and deploy them for community revitalization purposes. Furthermore, as a pilot case approved within Chiba Prefecture to lead regional economic business planning, this trial will be deployed to the 42 locations nationwide where JUNPUZI currently operates and later to transport operators to lead regional economies.

About JUNPUZI’s "Convenicle"

As of June 2018, the rideshare demand responsive transport system "Convenicle" is used at 42 locations nationwide with about 150 vehicles every day, and has a ridership of approximately 65,000 passengers every month. For more information, please see the following website (in Japanese):

About Toshiba "SATLYS™" Analytics AI

Toshiba "SATLYS™" analytics AI is a service that applies Toshiba’s 140 years of insights and achievements in manufacturing to AI design to realize high-precision recognition, forecasting, cause prediction, anomaly detection, malfunction prediction and behavior prediction. By offering solutions that use SATLYS to analyze inspection data, sensor data, work data and behavioral data, Toshiba is accelerating the digital transformation of its customers. For more information, please see the following website (in Japanese):


  • * Convenicle is a registered trademark of JUNPUZI.CO.,LTD. in Japan.
  • * SATLYS is a registered trademark or trademark of Toshiba Digital Solutions Corporation in Japan and other countries.
  • * Other company names and product names in this document may be trademarks or registered trademarks of the respective companies.