Vehicle content recommendation using cognitive states
Content manipulation uses cognitive states for vehicle content recommendation. Images are obtained of a vehicle occupant using imaging devices within a vehicle. The one or more images include facial data of the vehicle occupant. A content ingestion history of the vehicle occupant is obtained, where the content ingestion history includes one or more audio or video selections. A first computing device is used to analyze the one or more images to determine a cognitive state of the vehicle occupant. The cognitive state is correlated to the content ingestion history using a second computing device. One or more further audio or video selections are recommended to the vehicle occupant, based on the cognitive state, the content ingestion history, and the correlating. The analyzing can be compared with additional analyzing performed on additional vehicle occupants. The additional vehicle occupants can be in the same vehicle as the first occupant or different vehicles.
1. A computer-implemented method for content manipulation comprising:
obtaining one or more images of a vehicle occupant using one or more imaging devices within a vehicle, wherein the one or more images include facial data of the vehicle occupant;
obtaining a content ingestion history of the vehicle occupant, wherein the content ingestion history includes one or more audio or video selections;
analyzing, using a first computing device, the one or more images to determine a cognitive state of the vehicle occupant;
correlating the cognitive state to the content ingestion history using a second computing device; and
recommending to the vehicle occupant one or more further audio or video selections, based on the cognitive state, the content ingestion history, and the correlating.
2. The method of claim 1 wherein the recommending occurs while the vehicle occupant occupies the vehicle.
3. The method of claim 1 wherein the recommending occurs after the vehicle occupant leaves the vehicle.
4. The method of claim 1 further comprising comparing the analyzing with additional analyzing performed on additional vehicle occupants.
5. The method of claim 4 wherein the additional vehicle occupants occupy the vehicle contemporaneously with the vehicle occupant.
6. The method of claim 4 wherein the additional vehicle occupants occupy one or more different vehicles from the vehicle of the vehicle occupant.
7. The method of claim 1 further comprising obtaining additional images of one or more additional occupants of the vehicle, wherein the additional images are analyzed to determine one or more additional cognitive states.
8. The method of claim 7 further comprising adjusting the correlating the cognitive state, wherein the adjusting is performed using the additional cognitive states.
9. The method of claim 8 further comprising changing the recommending based on the adjusting.
10. The method of claim 8 wherein the vehicle occupant and the one or more additional occupants comprise a group of occupants and the adjusting is performed based on a group cognitive state.
11. The method of claim 1 wherein the analyzing is performed without eye region input from the one or more images.
12. The method of claim 1 wherein the vehicle occupant is a driver of the vehicle.
13. The method of claim 12 wherein the driver is a custodial driver.
14. The method of claim 1 further comprising obtaining audio information from the vehicle occupant and augmenting the analyzing based on the audio information.
15. The method of claim 14 wherein the audio information includes speech.
16. The method of claim 14 wherein the audio information includes non-speech vocalizations.
17. The method of claim 16 wherein the non-speech vocalizations include grunts, yelps, squeals, snoring, sighs, laughter, filled pauses, unfilled pauses, or yawns.
18. The method of claim 1 wherein the analyzing is performed using deep learning.
19. The method of claim 1 further comprising tagging the cognitive state with sensor data.
20. The method of claim 19 wherein the sensor data includes one or more of an interior temperature for the vehicle, an exterior temperature for the vehicle, a time of day, a day of week, a season, a level of daylight, weather conditions, road conditions, traffic conditions, a headlight activation, a windshield wiper activation, a setting for the vehicle, an entertainment center selection for the vehicle, or an entertainment center volume for the vehicle.
21. The method of claim 1 wherein at least one of the one or more images includes near infrared content.
22. The method of claim 21 wherein the analyzing is modified, based on the near infrared content of the at least one of the one or more images.
23. The method of claim 1 wherein the cognitive state includes drowsiness, fatigue, distraction, impairment, sadness, stress, happiness, anger, frustration, confusion, disappointment, hesitation, cognitive overload, focusing, engagement, attention, boredom, exploration, confidence, trust, delight, disgust, skepticism, doubt, satisfaction, excitement, laughter, calmness, curiosity, humor, depression, envy, sympathy, embarrassment, poignancy, or mirth.
24. The method of claim 1 wherein the cognitive state that was analyzed is based on intermittent obtaining of the one or more images that include facial data.
25. A computer program product embodied in a non-transitory computer readable medium for content manipulation, the computer program product comprising code which causes one or more processors to perform operations of:
obtaining one or more images of a vehicle occupant using one or more imaging devices within a vehicle, wherein the one or more images include facial data of the vehicle occupant;
obtaining a content ingestion history of the vehicle occupant, wherein the content ingestion history includes one or more audio or video selections;
analyzing, using a first computing device, the one or more images to determine a cognitive state of the vehicle occupant;
correlating the cognitive state to the content ingestion history using a second computing device; and
recommending to the vehicle occupant one or more further audio or video selections, based on the cognitive state, the content ingestion history, and the correlating.
26. A computer system for content manipulation comprising:
a memory which stores instructions;
one or more processors attached to the memory wherein the one or more processors, when executing the instructions which are stored, are configured to:
obtain one or more images of a vehicle occupant using one or more imaging devices within a vehicle, wherein the one or more images include facial data of the vehicle occupant;
obtain a content ingestion history of the vehicle occupant, wherein the content ingestion history includes one or more audio or video selections;
analyze, using a first computing device, the one or more images to determine a cognitive state of the vehicle occupant;
correlate the cognitive state to the content ingestion history using a second computing device; and
recommend to the vehicle occupant one or more further audio or video selections, based on the cognitive state, the content ingestion history, and the correlating.