Method, apparatus and computer program for estimating driver's personality of route selection

• US 8,798,910 B2
• Filed: 01/02/2013
• Issued: 08/05/2014
• Est. Priority Date: 01/17/2012
• Status: Expired due to Fees

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Osogami, Takayuki
• Primary Examiner(s): Beaulieu, Yonel
• Application Number:
  US13/732,657
• Publication Number:
  US 20130184992A1
• Time in Patent Office: 580 Days
• Field of Search: 701/400, 701/527, 701/533, 701409-411, 701117- 8, 701/23, 701 25- 26, 701/423, 340/988
• US Class Current: 701/400
• CPC Class Codes: G01C 21/3484 Personalized, e.g. from learned user behaviour or user-defined profiles

Abstract

A method for selecting a route from a departure point to an arrival point includes acquiring information concerning a departure point and an arrival point and information concerning a route from the departure point to the arrival point; generating a plurality of basic routes; calculating a parameter of an evaluation function that yields the selected route as an optimum route; generating a new route using the calculated parameter, determining whether or not the generated new route is identical to the selected route; on a condition that the generated new route is not identical to the selected route, adding the generated new route to the basic routes, recalculating the parameter, generating a new route, and comparing the new route with the selected route; and if the new route is identical to the selected route, storing the parameter when the new data becomes identical to the selected route.

Claims

1. A method for estimating a parameter of an evaluation function used for selecting a route from a departure point to an arrival point, the method comprising:

acquiring, with a processing device, information concerning a departure point and an arrival point and information concerning a route from the departure point to the arrival point;

generating a plurality of basic routes on the basis of the acquired information concerning the departure point and the arrival point and the acquired information concerning the route from the departure point to the arrival point;

acquiring information concerning a route actually selected;

calculating a parameter of an evaluation function that yields the actually selected route as an optimum route among the plurality of basic routes and the actually selected route;

generating a new route using the calculated parameter;

determining whether or not the generated new route is identical to the actually selected route;

on a condition that it is determined that the generated new route is not identical to the actually selected route, adding the generated new route to the basic routes, calculating a parameter of the evaluation function anew, repeating generation of a new route, and comparing the generated new route with the actually selected route; and

on a condition that it is determined that the generated new route is identical to the actually selected route, storing the parameter at the time when the new data becomes identical to the actually selected route as a parameter of the evaluation function.

2. The method according to claim 1, wherein:

the information concerning the route from the departure point to the arrival point is acquired as a cost incurred if the route is selected; and

the parameter is calculated as a coefficient by which the cost of each route in the evaluation function is to be multiplied, by optimizing the evaluation function by a linear programming.

3. The method according to claim 1, wherein the basic routes include at least a route with the fewest left and/or right turns, a fastest route, and a shortest route.

4. An apparatus for estimating a parameter of an evaluation function used for selecting a route from a departure point to an arrival point, comprising:

an information acquisition unit configured to acquire information concerning a departure point and an arrival point and information concerning a route from the departure point to the arrival point;

a basic route generation unit configured to generate a plurality of basic routes on the basis of the acquired information concerning the departure point and the arrival point and the acquired information concerning the route from the departure point to the arrival point;

a route selection information acquisition unit configured to acquire information concerning a route actually selected;

a parameter calculation unit configured to calculate a parameter of an evaluation function that yields the actually selected route as an optimum route among the plurality of basic routes and the actually selected route;

a route generation unit configured to generate a new route using the calculated parameter;

a determination unit configured to determine whether or not the generated new route is identical to the actually selected route;

a repetition unit configured to, on a condition that the determination unit determines that the generated new route is not identical to the actually selected route, add the generated new route to the basic routes, calculate a parameter of the evaluation function anew, repeat generation of a new route, and compare the generated new route with the actually selected route; and

a parameter storage unit configured to, on a condition that the determination unit determines that the generated new route is identical to the actually selected route, store the parameter at the time when the new data becomes identical to the actually selected route as a parameter of the evaluation function.

5. The apparatus according to claim 4, wherein:

the information acquisition unit acquires the information concerning the route from the departure point to the arrival point as a cost incurred if the route is selected; and

the parameter calculation unit calculates the parameter as a coefficient by which the cost of each route in the evaluation function is to be multiplied, by optimizing the evaluation function by a linear programming.

6. The apparatus according to claim 4, wherein the basic routes include at least a route with the fewest left and/or right turns, a fastest route, and a shortest route.

7. A computer readable storage medium having computer readable code stored thereon that, when executed by a computer, implement method for estimating a parameter of an evaluation function used for selecting a route from a departure point to an arrival point, the method comprising:

acquiring, with a processing device, information concerning a departure point and an arrival point and information concerning a route from the departure point to the arrival point;

generating a plurality of basic routes on the basis of the acquired information concerning the departure point and the arrival point and the acquired information concerning the route from the departure point to the arrival point;

acquiring information concerning a route actually selected;

calculating a parameter of an evaluation function that yields the actually selected route as an optimum route among the plurality of basic routes and the actually selected route;

generating a new route using the calculated parameter;

determining whether or not the generated new route is identical to the actually selected route;

on a condition that it is determined that the generated new route is not identical to the actually selected route, adding the generated new route to the basic routes, calculating a parameter of the evaluation function anew, repeating generation of a new route, and comparing the generated new route with the actually selected route; and

on a condition that it is determined that the generated new route is identical to the actually selected route, storing the parameter at the time when the new data becomes identical to the actually selected route as a parameter of the evaluation function.

8. The computer readable storage medium according to claim 7, wherein:

the information concerning the route from the departure point to the arrival point is acquired as a cost incurred if the route is selected; and

the parameter is calculated as a coefficient by which the cost of each route in the evaluation function is to be multiplied, by optimizing the evaluation function by a linear programming.

9. The computer program product according to claim 7, wherein the basic routes include at least a route with the fewest left and/or right turns, a fastest route, and a shortest route.

10. A method for estimating a parameter of an evaluation function used for selecting one element or a combination of a plurality of elements, the method comprising:

acquiring, with a processing device, information concerning each of the elements;

generating a basic set including a selectable one element or a selectable combination of a plurality of elements on the basis of the acquired information concerning each of the elements;

acquiring information concerning one actually selected element or an actually selected combination of a plurality of elements; and

calculating a parameter of the evaluation function that yields the actually selected one element or the actually selected combination of a plurality of elements as an optimum one among the basic set.

11. The method according to claim 10, wherein each of the elements is a road between two intersections and the one element or the combination of a plurality of elements is a route that is a combination of the roads.

12. The method according to claim 10, further comprising:

generating one element or a combination of a plurality of elements anew by using a calculated parameter of the evaluation function;

adding the generated new one element or combination of elements to the basic set; and

calculating a parameter of the evaluation function that yields actually selected one element or an actually selected combination of elements as an optimum element or combination in the basic set including the generated new one element or combination of elements.

13. The method according to claim 12, further comprising recursively repeating:

generating one element or a combination of a plurality of elements anew by using a calculated parameter of the evaluation function;

adding the generated new one element or combination of elements to the basic set; and

calculating a parameter of the evaluation function that yields actually selected one element or an actually selected combination of elements as an optimum element or combination in the basic set including the generated new one element or combination of elements.

14. The method according to claim 13, further comprising:

determining whether or not a generated new one element or combination of a plurality or elements is identical to actually selected one element or combination of elements; and

on a condition that the generated new one element or combination of elements are determined to be identical to the actually selected element or combination of elements, storing a parameter at the time when the element or combination of elements becomes identical to the actually selected element or combination of elements as a parameter of the evaluation function.