Cognitive ride scheduling

1. A method, by a processor, for facilitating ride scheduling, comprising:

executing machine learning logic, by the processor, to generate one or more ride scheduling models by a neural network trained using user data of a user; wherein generating the one or more ride scheduling models includes learning, by the neural network, activities of daily living (ADL) and historical patterns of the user inclusive of using global positioning satellite (GPS) data captured by a wireless communications device associated with the user to track current and historical locations visited by the user and transportation characteristics used by the user to arrive at the current and historical locations, the ADL and historical patterns including factors related to ride scheduling as explicitly specified by the user and factors implicitly related to the ride scheduling not specified by the user;

predicting, by the processor, an occurrence of an event associated with the user based on the ADL and historical patterns referenced in the user data according to the one or more ride scheduling models; wherein predicting the event includes predicting a destination location necessitating arrival by the user at a particular time and predicting sub-events of activities requiring specific hardware necessities to be performed by the user and that will occur during transportation of the user to the destination location;

determining, by the processor, one or more ride scheduling parameters relating to the event and the sub-events; wherein determining the one or more ride scheduling parameters includes determining the current location of the user according to the GPS data of the wireless communications device;

detecting, by the processor, an anomaly in the ADL or historical patterns of the user that will affect the event or the sub-events;

applying the determined one or more ride scheduling parameters to the neural network to generate, by the neural network using the processor, a ride scheduling model of the one or more ride scheduling models satisfying the ride scheduling parameters according to the detected anomaly; wherein the one or more ride scheduling models identify a mode of transportation, a type of vehicle, and characteristics of the vehicle which satisfy the ride scheduling parameters inclusive of characteristics which aid in providing the specific hardware necessities for the activities as contextually related to the anomaly;

automatically facilitating a scheduling of the vehicle for the user, by the processor, according to the ride scheduling model of the one or more ride scheduling models generated by the neural network via a presentation of the one or more ride scheduling models on a user interface associated with the wireless communications device; wherein the ride scheduling models are generated, at least in part, using a Mel-Frequency analysis to extract Mel-Frequency Cepstral Coefficients (MFCC) features of the ride scheduling models, and wherein the MFCC features of the ride scheduling models are used in combination with alternative factors to estimate a departure time at which the user needs to depart the current location in order to arrive at the destination location at the particular time to automatically facilitate the scheduling of the vehicle;

collecting feedback, by the processor, relating to the one or more ride scheduling parameters and the ride scheduling model; and

executing the machine learning logic, by the processor, to automatically update the one or more ride scheduling models using the feedback as new input to the neural network, wherein updating the one or more ride scheduling models includes using the feedback correspondent to an outcome of a trip associated with the ride scheduling model to iteratively re-train the one or more ride scheduling models to increasingly optimize future scheduling of vehicles associated with future trips of the user over time.

2. The method of claim 1 , wherein determining the one or more ride scheduling parameters further includes determining a cognitive state of the user, wherein the cognitive state includes a fatigue level of the user, a level of distraction of the user, a subjective well-being (SWB) of the user, an emotional state of the user, one or more medical conditions, or a combination thereof.

3. The method of claim 1 , wherein determining the one or more ride scheduling parameters further includes collecting the user data from a calendar, social media networks, one or more Internet of Things (IoT) sensor devices, the wireless communication device, crowdsourcing, or a combination thereof.

4. The method of claim 1 , wherein determining the one or more ride scheduling parameters further includes:

learning user preferences, biometric data, and a cognitive state of the user, wherein the user preferences include preferences for one or more modes of transportation, preferences for scheduling the one or more modes of transportation with alternative users, preferences of the one or more ride scheduling models, radio channel preferences, music preferences, temperature preferences, a combination thereof of the user; and

learning one or more contextual factors relating to the user, the event, location, or a combination thereof, wherein the one or more contextual factors include traffic data, weather data, road conditions, time constraints of the user relating to the event, one or more alternative users using the one or more modes of transportation relating to the more ride scheduling models, risk levels of the more ride scheduling models, or a combination thereof.

5. The method of claim 1 , further including ranking the one or more ride scheduling models according to the one or more ride scheduling parameters.

6. The method of claim 1 , further including scheduling one or more modes of transportation relating to the more ride scheduling models based on the one or more ride scheduling parameters.

7. A system for facilitating ride scheduling, comprising:

a processor; and

a memory storing executable instructions that when executed cause the processor to:

execute machine learning logic to generate one or more ride scheduling models by a neural network trained using user data of a user; wherein generating the one or more ride scheduling models includes learning, by the neural network, activities of daily living (ADL) and historical patterns of the user inclusive of using global positioning satellite (GPS) data captured by a wireless communications device associated with the user to track current and historical locations visited by the user and transportation characteristics used by the user to arrive at the current and historical locations, the ADL and historical patterns including factors related to ride scheduling as explicitly specified by the user and factors implicitly related to the ride scheduling not specified by the user;

predict an occurrence of an event associated with the user based on the ADL and historical patterns referenced in the user data according to the one or more ride scheduling models; wherein predicting the event includes predicting a destination location necessitating arrival by the user at a particular time and predicting sub-events of activities requiring specific hardware necessities to be performed by the user and that will occur during transportation of the user to the destination location;

determine one or more ride scheduling parameters relating to the event and the sub-events; wherein determining the one or more ride scheduling parameters includes determining the current location of the user according to the GPS data of the wireless communications device;

detect an anomaly in the ADL or historical patterns of the user that will affect the event or the sub-events;

apply the determined one or more ride scheduling parameters to the neural network to generate a ride scheduling model of the one or more ride scheduling models satisfying the ride scheduling parameters according to the detected anomaly; wherein the one or more ride scheduling models identify a mode of transportation, a type of vehicle, and characteristics of the vehicle which satisfy the ride scheduling parameters inclusive of characteristics which aid in providing the specific hardware necessities for the activities as contextually related to the anomaly;

automatically facilitate a scheduling of the vehicle for the user according to the ride scheduling model of the one or more ride scheduling models generated by the neural network via a presentation of the one or more ride scheduling models on a user interface associated with the wireless communications device; wherein the ride scheduling models are generated, at least in part, using a Mel-Frequency analysis to extract Mel-Frequency Cepstral Coefficients (MFCC) features of the ride scheduling models, and wherein the MFCC features of the ride scheduling models are used in combination with alternative factors to estimate a departure time at which the user needs to depart the current location in order to arrive at the destination location at the particular time to automatically facilitate the scheduling of the vehicle;

collect feedback relating to the one or more ride scheduling parameters and the ride scheduling model; and

execute the machine learning logic, by the processor, to automatically update the one or more ride scheduling models using the feedback as new input to the neural network, wherein updating the one or more ride scheduling models includes using the feedback correspondent to an outcome of a trip associated with the ride scheduling model to iteratively re-train the one or more ride scheduling models to increasingly optimize future scheduling of vehicles associated with future trips of the user over time.

8. The system of claim 7 , wherein the executable instructions, pursuant to determining the one or more ride scheduling parameters, further determine a cognitive state of the user, wherein the cognitive state includes a fatigue level of the user, a level of distraction of the user, a subjective well-being (SWB) of the user, an emotional state of the user, one or more medical conditions, or a combination thereof.

9. The system of claim 7 , wherein the executable instructions, pursuant to determining the one or more ride scheduling parameters, further collect the user data from a calendar, social media networks, one or more Internet of Things (IoT) sensor devices, the wireless communication device, crowdsourcing, or a combination thereof.

10. The system of claim 7 , wherein the executable instructions, pursuant to determining the one or more ride scheduling parameters, further:

learn user preferences, biometric data, and a cognitive state of the user, wherein the user preferences include preferences for one or more modes of transportation, preferences for scheduling the one or more modes of transportation with alternative users, preferences of the one or more ride scheduling models, radio channel preferences, music preferences, temperature preferences, a combination thereof of the user; and

learn one or more contextual factors relating to the user, the event, or a combination thereof, wherein the one or more contextual factors include traffic data, weather data, road conditions, time constraints of the user relating to the event, location, one or more alternative users using the one or more modes of transportation relating to the more ride scheduling models, risk levels of the more ride scheduling models, or a combination thereof.

11. The system of claim 7 , wherein the executable instructions further rank the one or more ride scheduling models according to the one or more ride scheduling parameters.

12. The system of claim 7 , wherein the executable instructions further schedule one or more modes of transportation relating to the more ride scheduling models based on the one or more ride scheduling parameters.

13. A computer program product for facilitating ride scheduling by a processor, the computer program product comprising a non-transitory computer-readable storage medium having computer-readable program code portions stored therein, the computer-readable program code portions comprising:

an executable portion that executes machine learning logic to generate, by the processor, one or more ride scheduling models by a neural network trained using user data of a user; wherein generating the one or more ride scheduling models includes learning, by the neural network, activities of daily living (ADL) and historical patterns of the user inclusive of using global positioning satellite (GPS) data captured by a wireless communications device associated with the user to track current and historical locations visited by the user and transportation characteristics used by the user to arrive at the current and historical locations, the ADL and historical patterns including factors related to ride scheduling as explicitly specified by the user and factors implicitly related to the ride scheduling not specified by the user;

an executable portion that predicts, by the processor, an occurrence of an event associated with the user based on the ADL and historical patterns referenced in the user data according to the one or more ride scheduling models; wherein predicting the event includes predicting a destination location necessitating arrival by the user at a particular time and predicting sub-events of activities requiring specific hardware necessities to be performed by the user and that will occur during transportation of the user to the destination location;

an executable portion that determines, by the processor, one or more ride scheduling parameters relating to the event and the sub-events; wherein determining the one or more ride scheduling parameters includes determining the current location of the user according to the GPS data of the wireless communications device;

an executable portion that detects, by the processor, an anomaly in the ADL or historical patterns of the user that will affect the event or the sub-events;

an executable portion that applies the determined one or more ride scheduling parameters to the neural network to generate, by the neural network using the processor, a ride scheduling model of the one or more ride scheduling models satisfying the ride scheduling parameters according to the detected anomaly; wherein the one or more ride scheduling models identify a mode of transportation, a type of vehicle, and characteristics of the vehicle which satisfy the ride scheduling parameters inclusive of characteristics which aid in providing the specific hardware necessities for the activities as contextually related to the anomaly;

an executable portion that automatically facilitates a scheduling of the vehicle for the user, by the processor, according to the ride scheduling model of the one or more ride scheduling models generated by the neural network via a presentation of the one or more ride scheduling models on a user interface associated with the wireless communications device; wherein the ride scheduling models are generated, at least in part, using a Mel-Frequency analysis to extract Mel-Frequency Cepstral Coefficients (MFCC) features of the ride scheduling models, and wherein the MFCC features of the ride scheduling models are used in combination with alternative factors to estimate a departure time at which the user needs to depart the current location in order to arrive at the destination location at the particular time to automatically facilitate the scheduling of the vehicle;

an executable portion that collects feedback, by the processor, relating to the one or more ride scheduling parameters and the ride scheduling model; and

an executable portion that executes the machine learning logic, by the processor, to automatically update the one or more ride scheduling models using the feedback as new input to the neural network, wherein updating the one or more ride scheduling models includes using the feedback correspondent to an outcome of a trip associated with the ride scheduling model to iteratively re-train the one or more ride scheduling models to increasingly optimize future scheduling of vehicles associated with future trips of the user over time.

14. The computer program product of claim 13 , wherein the executable portion, pursuant to determining the one or more ride scheduling parameters, further collects the user data from a calendar, social media networks, one or more Internet of Things (IoT) sensor devices, the wireless communication device, crowdsourcing, or a combination thereof.

15. The computer program product of claim 13 , wherein the executable portion, pursuant to determining the one or more ride scheduling parameters, further:

learns user preferences, biometric data, and a cognitive state of the user, wherein the user preferences include preferences for one or more modes of transportation, preferences for scheduling the one or more modes of transportation with alternative users, preferences of the one or more ride scheduling models, radio channel preferences, music preferences, temperature preferences, a combination thereof of the user; and

learns one or more contextual factors relating to the user, the event, or a combination thereof, wherein the one or more contextual factors include traffic data, weather data, road conditions, time constraints of the user relating to the event, one or more alternative users using the one or more modes of transportation relating to the more ride scheduling models, risk levels of the more ride scheduling models, or a combination thereof.

16. The computer program product of claim 13 , further including an executable portion that ranks the one or more ride scheduling models according to the one or more ride scheduling parameters.

17. The computer program product of claim 13 , further including an executable portion that schedules one or more modes of transportation relating to the more ride scheduling models based on the one or more ride scheduling parameters.