Intelligent transportation systems
Transportation systems have artificial intelligence including neural networks for recognition and classification of objects and behavior including natural language processing and computer vision systems. The transportation systems involve sets of complex chemical processes, mechanical systems, and interactions with behaviors of operators. System-level interactions and behaviors are classified, predicted and optimized using neural networks and other artificial intelligence systems through selective deployment, as well as hybrids and combinations of the artificial intelligence systems, neural networks, expert systems, cognitive systems, genetic algorithms and deep learning.
1. An artificial intelligence system for voice processing to improve rider satisfaction in a transportation system, comprising:
a rider voice capture system deployed to capture voice output of a specific rider occupying a vehicle;
a voice-analysis circuit trained using machine learning that classifies an emotional state of the specific rider for the captured voice output of the specific rider; and
an expert system trained using machine learning that optimizes at least one operating parameter of the vehicle to change the emotional state of the specific rider to an outcome emotional state classified as an improved emotional state, wherein the emotional state of the specific rider is determined from a combination of emotional state indicative parameters including the captured voice output of the specific rider and at least one other emotional state indicative parameter of the specific rider other than the captured voice output of the specific rider,
wherein the at least one other emotional state indicative parameter of the specific rider includes at least one pattern of physiological data of the specific rider that is detected by an in-vehicle sensor; and
wherein the at least one operating parameter of the vehicle that is optimized includes at least one of: in-vehicle audio content, a speed of the vehicle, an acceleration of the vehicle, or a deceleration of the vehicle, [and] wherein the at least one operating parameter of the vehicle is optimized, at least in part, by the expert system by adjusting a weighting applied to the at least one operating parameter via an expert system configuration interface based on feedback of the outcome emotional state and by eliminating options for configuration from a set of available configurations that are not related to a source of stress for the specific rider.
2. The artificial intelligence system of claim 1 wherein the rider voice capture system comprises an intelligent agent that engages in a dialog with the specific rider to obtain rider feedback for use by the voice-analysis circuit for rider emotional state classification.
3. The artificial intelligence system of claim 1 wherein the voice-analysis circuit uses a first machine learning system and the expert system uses a second machine learning system.
4. The artificial intelligence system of claim 1 further comprising a rule-based rider state model that configures a set of iterations of the at least one operating parameter while continuously monitoring the emotional state of the specific rider via an ongoing dialog with respect to model parameters of the rule-based rider state model.
5. The artificial intelligence system of claim 1 wherein the in-vehicle sensor is a camera.
6. The artificial intelligence system of claim 1 wherein the at least one other emotional state indicative parameter of the specific rider further includes traffic information.
7. The artificial intelligence system of claim 1 wherein the at least one other emotional state indicative parameter of the specific rider further includes weather information.
8. The artificial intelligence system of claim 1 wherein the at least one other emotional state indicative parameter of the specific rider further includes a vehicle state.
9. The artificial intelligence system of claim 1 wherein the at least one other emotional state indicative parameter of the specific rider further includes a route of the vehicle.
10. An artificial intelligence system for voice processing to improve rider satisfaction in a transportation system, comprising:
a rider voice capture system deployed to capture voice output of a specific rider occupying a vehicle;
a voice-analysis circuit trained using machine learning that classifies an emotional state of the specific rider for the captured voice output of the specific rider; and
an expert system trained using machine learning that, in real time, optimizes at least one operating parameter of the vehicle to change the emotional state of the specific rider to an outcome emotional state classified as an improved emotional state, wherein the emotional state of the specific rider is determined from a combination of emotional state indicative parameters including the captured voice output of the specific rider and at least one other emotional state indicative parameter of the specific rider other than the captured voice output of the specific rider,
wherein the at least one other emotional state indicative parameter of the specific rider includes at least one pattern of physiological data of the specific rider in image data that is detected by an in-vehicle camera;
wherein the at least one operating parameter of the vehicle that is optimized includes at least one of: in-vehicle audio content, a speed of the vehicle, an acceleration of the vehicle, or a deceleration of the vehicle, wherein the at least one operating parameter of the vehicle is optimized, at least in part, by the expert system by adjusting a weighting applied to the at least one operating parameter via an expert system configuration interface based on feedback of the outcome emotional state and by eliminating options for configuration from a set of available configurations that are not related to a source of stress for the specific rider.
11. The artificial intelligence system of claim 5 wherein the rider voice capture system comprises an intelligent agent that engages in a dialog with the specific rider to obtain rider feedback for use by the voice-analysis circuit for rider emotional state classification.
12. The artificial intelligence system of claim 5 wherein the voice-analysis circuit uses a first machine learning system and the expert system uses a second machine learning system.
13. The artificial intelligence system of claim 5 wherein the expert system is trained to optimize the at least one operating parameter of the vehicle based, at least in part, on feedback based on the outcome emotional state when adjusting the at least one operating parameter for the specific rider.
14. The artificial intelligence system of claim 10 wherein a rule-based rider state model configures a set of iterations of the at least one operating parameter while continuously monitoring the emotional state of the specific rider via an ongoing dialog with respect to model parameters of the rule-based rider state model.
15. The artificial intelligence system of claim 5 wherein the at least one other emotional state indicative parameter of the specific rider further includes traffic information.
16. The artificial intelligence system of claim 5 wherein the at least one other emotional state indicative parameter of the specific rider further includes weather information.
17. The artificial intelligence system of claim 5 wherein the at least one other emotional state indicative parameter of the specific rider further includes a vehicle state.
18. The artificial intelligence system of claim 5 wherein the at least one other emotional state indicative parameter of the specific rider further includes a route of the vehicle.
19. The artificial intelligence system of claim 10 wherein the real time optimizing by the expert system is to take place within about one second of the emotional state of the specific rider being classified.
20. The artificial intelligence system of claim 1 further comprising a rule-based rider state model, wherein the optimizing of the at least one operating parameter of the vehicle is based, at least in part, on the rule-based rider state model, and wherein a correlation between the weighting applied to the at least one operating parameter and the change to the emotional state of the specific rider is based, at least in part, on another weighting of the emotional state indicative parameters in the combination of emotional state indicative parameters.
21. A voice processing based method of improving satisfaction of a rider of a transportation system, comprising:
capturing, via a rider voice capture system, a voice output of a specific rider occupying a vehicle;
classifying, via a voice-analysis circuit that is trained with machine learning, an emotional state of the specific rider based on the captured voice output of the specific rider, wherein the emotional state of the specific rider is determined from a combination of emotional state indicative parameters including the captured voice output of the specific rider and at least one other emotional state indicative parameter other than the captured voice output of the specific rider, and wherein the at least one other emotional state indicative parameter includes at least one pattern of physiological data of the specific rider that is detected by an in-vehicle sensor; and
optimizing, via an expert system that is trained with machine learning, at least one operating parameter of the vehicle to change the emotional state of the specific rider to an outcome emotional state classified as an improved emotional state, wherein the at least one operating parameter of the vehicle that is optimized includes at least one of: in-vehicle audio content, a speed of the vehicle, an acceleration of the vehicle, or a deceleration of the vehicle;
obtaining feedback regarding the outcome emotional state;
adjusting, via an expert system configuration interface, a weighting applied to the at least one operating parameter that is optimized based on the feedback regarding the outcome emotional state and eliminating options for configuration from a set of available configurations that are not related to a source of stress for the specific rider.
22. The method of claim 21 , further comprising configuring a set of iterations of the at least one operating parameter while continuously monitoring the emotional state of the specific rider.