Methods, circuits, devices, systems and associated computer executable code for driver decision support
The present invention includes methods, circuits, devices, systems and associated computer executable code for providing driver decision making support. According to some embodiments, there may be provided a driver decision support system, which may generate action recommendations to a commercial driver, such as a taxi driver, a cab driver, a limo driver or any other kind of driver who picks up and transports passengers or cargo on an ad hoc (or otherwise flexible/uncertain) basis.
1. A mobile computing device comprising:
a display;
a driver interface adapted to receive a driver input of a driver associated with the mobile computing device, the driver input indicating an operational parameter for optimization; and
processor circuitry communicably coupled to the display and the driver interface, the processor circuit to execute:
a recommendation engine to generate a recommended driver action comprising driving directions for a route, wherein the recommended driver action is optimized according to the operational parameter, wherein the recommendation is at least partially based upon: (1) a location signal indicating a current location of the driver; (2) a live traffic feed indicating current traffic conditions within an area including the current location of the driver; (3) a traffic flow model for the area; and (4) a transportation demand model of at least the area, indicating a current demand for commercial transportation within the area; and
a rendering unit to render upon the display a graphic representation of the recommended driver action;
wherein said traffic flow model and said transportation demand model are dynamic and intermittently updated and said transportation demand module is segmented by location.
2. The mobile computing device according to claim 1 , wherein the recommendation is also at least partially based on a transportation supply model of the area, indicating a current supply of commercial transportation within the area.
3. The mobile computing device according to claim 1 , wherein the operational parameter is profit per shift.
4. The mobile computing device according to claim 1 , wherein the operational parameter is profit of next fare.
5. The mobile computing device according to claim 1 , wherein the operational parameter is optimizing a probability the driver arrives in a specific geographical region at a defined time.
6. The mobile computing device according to claim 1 , wherein the operational parameter is profit of a fleet of commercial drivers.
7. The mobile computing device according to claim 1 , wherein the recommendation engine is to calculate a probability that a commercial driver is e-hailed at a given location.
8. The mobile computing device according to claim 1 , wherein the recommendation engine is further to calculate a probability that a commercial driver is street hailed at a given location or navigating on a given route.
9. The mobile computing device according to claim 7 , wherein the recommendation engine is further to calculate, for each of a set of possible locations, a first probability the driver is hailed on route to each given location, aggregate a second probability of being e-hailed at each given location with a third probability the driver is street hailed on route to each given location into a fourth probability, and recommend an optimal location for the driver to drive to considering both of the first and fourth probabilities.
10. A server computing device comprising:
memory; and
processor circuitry communicably coupled to the memory, the processor circuitry to:
generate a recommended driver action for a driver, wherein the recommended driver action comprises driving directions for a route, and wherein the recommended driver action is optimized according to an operational parameter indicated by the driver and is at least partially based upon: (1) a location signal indicating a current location of the driver; (2) a live traffic feed indicating current traffic conditions within an area including the current location of the driver; (3) a traffic flow model for the area; and (4) a transportation demand vs. supply model of at least the area, indicating a current demand for commercial transportation within the area in relation to a current demand for commercial transportation within the area; and
transmit, to a client computing device, instructions to render a graphic representation of the recommended driver action at the client computing device;
wherein said traffic flow model and said transportation demand model are dynamic and intermittently updated and said transportation demand vs. supply module is segmented by location.
11. The server computing device according to claim 10 , wherein the memory stores the operational parameter indicated by the driver in response to receiving the operational parameter from the client computing device.
12. The server computing device according to claim 11 , wherein the recommendation is also at least partially based on data received from other mobile devices.
13. The server computing device according to claim 11 , wherein the operational parameter comprises at least one of profit per shift or profit of next fare.
14. The server computing device according to claim 10 , wherein the recommendation engine is further to calculate a probability the driver is e-hailed at a given location.
15. The server computing device according to claim 10 , wherein the recommendation engine is further to calculate a probability the driver is street hailed at a given location or cruising a given route.
16. The server computing device according to claim 15 , wherein the recommendation engine is further to calculate a probability the driver is hailed on route to the given location, aggregate a first probability the driver is e-hailed at each given location with a second probability that the driver is hailed on route to the each given location into a fourth probability, and recommend an optimal location for the driver to navigate to considering both the first and the fourth probabilities.
17. A method comprising:
receiving, by a processing device of a mobile computing device, a driver input of a driver associated with the mobile computing device, the driver input indicating an operational parameter for optimization;
generating, by the processing device, a recommended driver action comprising driving directions for a route, wherein generating the recommended driver action further comprises optimizing the recommended driver action according to the operational parameter, wherein the recommended driver action is at least partially based upon: (1) a location signal indicating a current location of the driver; (2) a live traffic feed indicating current traffic conditions within an area including the current location of the driver; (3) a traffic flow model for the area; and (4) a transportation demand model of at least the area, indicating a current demand for commercial transportation within the area; and
providing, via a user interface of the mobile computing device, a graphic representation of the recommended driver action;
wherein said traffic flow model and said transportation demand model are dynamic and intermittently updated and the transportation demand module is segmented by location.
18. The method of claim 17 , wherein the recommended driver action is further optimized at least partially based on a transportation supply model of the area, indicating a current supply of commercial transportation within the area.
19. The method of claim 17 , wherein the operational parameter comprises at least one of profit per shift, profit of next fare, a probability that the driver arrives in a specific geographical region at a defined time, or profit of a fleet of commercial drivers.
20. The method of claim 17 , further comprising:
calculating, for each of a set of possible locations, a first probability the driver is hailed on route to each given location;
aggregating a second probability of being e-hailed at each given location with a third probability the driver is street hailed on route to each given location into a fourth probability; and
recommending an optimal location for the driver to drive to considering both of the first and fourth probabilities.