Estimating system, estimating method, and information storage medium

1. A system for accurate guidance of a route for a mobile object, the system comprising:

at least one memory configured to store computer program code; and

at least one processor configured to access said at least one memory and operate according to said computer program code, said computer program code including:

via point acquisition code configured to cause the at least one processor to acquire a position of a via point, wherein the via point is a location of a planned interim stay on a route to a destination, wherein the route is a path followed by a mobile object when the mobile object moves toward the destination;

learning code configured to cause the at least one processor to train and adjust a machine learning model based on training data including feature information and staying times for each of a plurality of staying places, each of the plurality of staying places corresponding to a past destination in a history of position data of at least one user terminal, the position data indicating a relationship between a position of the at least one user terminal and a time, the position data having been accumulated from the at least one user terminal for storage in a database, the machine learning model being thereby trained, based on the position data, to describe a relationship between feature information of an input staying place and a staying time of the input staying place;

staying time period code configured to cause the at least one processor to estimate a staying time period for the via point, wherein the staying time period represents an estimate of a time that the mobile object will stay at the position of the via point, wherein the staying time period is estimated at least in part by inputting feature information on the via point to the machine learning model and acquiring the staying time outputted from the machine learning model; and

arrival time code configured to cause the at least one processor to estimate, in real time, an arrival time of the mobile object at the destination, wherein the mobile object is currently in motion and the real-time estimate of the arrival time is based at least in part on the staying time period,

wherein the route is adjusted based at least in part on the estimate of the arrival time, and information including the adjusted route is transmitted to a device associated with the mobile object to be displayed on a display of the device, and

wherein the staying time period for the via point is estimated a plurality of times prior to completion of the route, at least a first estimate of the staying time period being based on the history of position data before receipt of an additional position data point from the at least one user terminal, at least a second estimate of the staying time period being based on the history of position data after receipt of the additional position data point from the at least one user terminal.

2. The system according to claim 1 , wherein the computer program code further includes:

current position acquisition code configured to cause the at least one processor to acquire a current position of the mobile object;

destination acquisition code configured to cause the at least one processor to acquire a position of the destination; and

movement time period code configured to cause the at least one processor to:

estimate a movement time period based on the current position of the mobile object and on the position of the destination, and

estimate the arrival time based on the movement time period and the staying time period.

3. The system according to claim 1 , wherein

the training data is derived by calculating, based on the position data in the history of position data, a plurality of staying time periods, wherein respective ones of the plurality of staying time periods correspond to respective ones of the plurality of staying places.

4. The system according to claim 3 , wherein the computer program code further includes calculation code configured to cause the at least one processor to:

cluster the position data into a plurality of clusters, wherein each cluster corresponds to respective portions of the position data; and

calculate, for each cluster of the plurality of clusters and based on the respective portions of the position data, the plurality of staying time periods.

5. The system according to claim 3 , wherein the computer program code further includes calculation code configured to cause the at least one processor to:

identify a first staying place of the plurality of staying places by determining, based on the position data, whether the at least one user terminal has been within a certain range of the first staying place, wherein the certain range is associated with a movement speed less than a predetermined threshold; and

calculate, for the first staying place, a first staying time period of the first staying place based on the position data.

6. The system according to claim 3 , wherein the computer program code further includes calculation code configured to cause the at least one processor to restrict use, in estimation of the staying time period, of a staying time period having a low probability of becoming one of a destination and a via point, wherein low probability corresponds to a corresponding destination or via point not corresponding to a past delivery destination.

7. The system according to claim 1 ,

wherein the feature information indicates an attribute of one of a region and a building.

8. The system according to claim 1 ,

wherein the feature information indicates one of a time slot and a time of staying at the via point.

9. The system according to claim 1 ,

wherein the feature information indicates a weather condition at the via point.

10. The system according to claim 1 , wherein the staying time period code is further configured to estimate the staying time period based on the position of the via point and on an attribute of the mobile object.

11. The system according to claim 1 , wherein the computer program code further includes notification code configured to cause the at least one processor to notify a user, before the mobile object arrives at the destination and wherein the user is associated with the destination, of the arrival time.

12. The system according to claim 1 ,

wherein the mobile object includes one of a delivery person and a machine for delivering a package to each of a plurality of delivery destinations in order,

wherein the plurality of delivery destinations includes the destination,

wherein the plurality of delivery destinations includes the via point, and

wherein the via point includes a first delivery destination earlier in a delivery order than a second delivery destination, wherein the second delivery destination corresponds to the destination.

13. A method for accurate guidance of a route for a mobile object, the method comprising:

acquiring a position of a via point, wherein the via point is a location of a planned interim stay on a route to a destination, wherein the route is a path followed by a mobile object when the mobile object moves toward the destination;

obtaining a history of position data accumulated from at least one user terminal by referring to a database, the database configured to store the history of position data of the at least one user terminal, the position data indicating a relationship between a position of the at least one user terminal and a time;

training and adjusting a machine learning model based on training data including feature information and staying times for each of a plurality of staying places, each of the plurality of staying places corresponding to a past destination in the history of position data of the at least one user terminal, the machine learning model being thereby trained, based on the position data, to describe a relationship between feature information of an input staying place and a staying time of the input staying place;

estimating a staying time period for the via point, wherein the staying time period represents an estimate of a time that the mobile object will stay at the position of the via point, wherein the staying time period is estimated at least in part by inputting feature information on the via point to the machine learning model and acquiring the staying time outputted from the machine learning model;

estimating, in real time, an arrival time of the mobile object at the destination, wherein the mobile object is currently in motion and the real-time estimate of the arrival time is based at least in part on the staying time period;

adjusting the route based at least in part on the real-time estimate of the arrival time; and

transmitting the adjusted route to a device associated with the mobile object to be displayed on a display of the device,

wherein the staying time period for the via point is estimated a plurality of times prior to completion of the route, at least a first estimate of the staying time period being based on the history of position data before receipt of an additional position data point from the at least one user terminal, at least a second estimate of the staying time period being based on the history of position data after receipt of the additional position data point from the at least one user terminal.

14. A non-transitory information storage medium having stored thereon a program for causing a computer to accurately guide a route for a mobile object by:

acquiring a position of a via point, wherein the via point is a location of a planned interim stay on a route to a destination, wherein the route is a path followed by a mobile object when the mobile object moves toward the destination;

training and adjusting a machine learning model based on training data including feature information and staying times for each of a plurality of staying places, each of the plurality of staying places corresponding to a past destination in a history of position data of at least one user terminal, the position data indicating a relationship between a position of the at least one user terminal and a time, the position data having been accumulated from the at least one user terminal for storage in a database, the machine learning model being thereby trained, based on the position data, to describe a relationship between feature information of an input staying place and a staying time of the input staying place;

estimating a staying time period for the via point, wherein the staying time period represents an estimate of a time that the mobile object will stay at the position of the via point, wherein the staying time period is estimated at least in part by inputting feature information on the via point to the machine learning model and acquiring the staying time outputted from the machine learning model;

estimating, in real time, an arrival time of the mobile object at the destination, wherein the mobile object is currently in motion and the real-time estimate of the arrival time is based at least in part on the staying time period;

adjusting the route based at least in part on the real-time estimate of the arrival time; and

transmitting the adjusted route to a device associated with the mobile object to be displayed on a display of the device,

wherein the staying time period for the via point is estimated a plurality of times prior to completion of the route, at least a first estimate of the staying time period being based on the history of position data before receipt of an additional position data point from the at least one user terminal, at least a second estimate of the staying time period being based on the history of position data after receipt of the additional position data point from the at least one user terminal.