Managing messages in vehicles

1. A method comprising:

receiving vehicle data indicating a state of a vehicle, wherein the vehicle data includes one or more of sensor data generated by one or more sensors of the vehicle, or application data generated by one or more vehicle applications, the sensor data being indicative of one or more physical parameters of the vehicle;

determining, based on the vehicle data indicative of the state of the vehicle, a current vehicle context, the current vehicle context being one of a plurality of predetermined vehicle contexts;

receiving message data indicating one or more candidate messages, each candidate message having a respective display context from a plurality of display contexts, wherein each of the plurality of display contexts matches at least one of the predetermined vehicle contexts;

determining whether a particular message of the one or more candidate messages has a display context that matches the current vehicle context; and

responsive to determining that the display context of the particular message matches the current vehicle context:

determining, based on the current vehicle context, a particular vehicle display of a plurality of display devices of the vehicle on which to display the particular message, wherein each of the plurality of the display devices of the vehicle are mounted to the vehicle; and

providing the particular message for output on the particular vehicle display and not one or more of the other vehicle display devices from the plurality of vehicle display devices.

2. The method of claim 1 , wherein the particular message is a first message from the one or more candidate messages, the method further comprising:

responsive to determining that a second message from the one or more candidate messages has a respective display context that does not match the current vehicle context, discarding the second message without providing the second message for display on one of the plurality of display devices of the vehicle.

3. The method of claim 1 , wherein the one or more candidate messages comprises a plurality of candidate messages, the method further comprising:

determining that two or more messages from the plurality of candidate messages have respective display contexts that match the current vehicle context;

clustering the two or more messages into two or more respective groups based on (i) the respective display context associated with each of the two or more messages, or (ii) a respective application that generated each of the two or more messages; and

assigning a priority value to each of the two or more messages based on the respective group into which each of the two or more messages is clustered.

4. The method of claim 3 , further comprising:

ranking each of the two or more messages based on the assigned priority value; and

providing the two or more messages for output on the particular vehicle display based on the ranking.

5. The method of claim 1 , further comprising:

detecting user feedback associated with the particular message after the particular message was output on the particular vehicle display;

determining whether the user feedback includes (i) positive interaction or (ii) negative interaction; and

in response to determining that the user feedback includes positive interaction, increasing a quality score associated with the particular message.

6. The method of claim 5 , further comprising:

in response to determining that the user feedback includes negative interaction, decreasing the quality score associated with the particular message.

7. The method of claim 5 , further comprising:

determining the current vehicle context at the time the user feedback was received; and

updating, based on the user feedback, the quality score for the particular message at the time the user feedback was received.

8. A system comprising:

one or more computers; and

one or more storage devices storing instructions that are operable, when executed by the one or more computers, to cause the one or more computers to perform operations comprising:

receiving vehicle data indicating a state of a vehicle, wherein the vehicle data includes one or more of sensor data generated by one or more sensors of the vehicle, or application data generated by one or more vehicle applications, the sensor data being indicative of one or more physical parameters of the vehicle;

determining, based on the vehicle data indicative of the state of the vehicle, a current vehicle context, the current vehicle context being one of a plurality of predetermined vehicle contexts;

receiving message data indicating one or more candidate messages, each candidate message having a respective display context from a plurality of display contexts, wherein each of the plurality of display contexts matches at least one of the predetermined vehicle contexts;

determining whether a particular message of the one or more candidate messages has a display context that matches the current vehicle context; and

responsive to determining that the display context of the particular message matches the current vehicle context:

determining, based on the current vehicle context, a particular vehicle display of a plurality of display devices of the vehicle on which to display the particular message, wherein each of the plurality of the display devices of the vehicle are mounted to the vehicle; and

providing the particular message for output on the particular vehicle display and not one or more of the other vehicle display devices from the plurality of vehicle display devices.

9. The system of claim 8 , wherein the particular message is a first message from the one or more candidate messages, the operations further comprising:

responsive to determining that a second message from the one or more candidate messages has a respective display context that does not match the current vehicle context, discarding the second message without providing the second message for display on one of the plurality of display devices of the vehicle.

10. The system of claim 8 , wherein the one or more candidate messages comprises a plurality of candidate messages, the operations further comprising:

determining that two or more messages from the plurality of candidate messages have respective display contexts that match the current vehicle context;

clustering the two or more messages into two or more respective groups based on (i) the respective display context associated with each of the two or more messages, or (ii) a respective application that generated each of the two or more messages; and

assigning a priority value to each of the two or more messages based on the respective group into which each of the two or more messages is clustered.

11. The system of claim 8 , the operations further comprising:

detecting user feedback associated with the particular message after the particular message was output on the particular vehicle display;

determining whether the user feedback includes (i) positive interaction or (ii) negative interaction; and

in response to determining that the user feedback includes positive interaction, increasing a quality score associated with the particular message.

12. The system of claim 11 , the operations further comprising:

in response to determining that the user feedback includes negative interaction, decreasing the quality score associated with the particular message.

13. The system of claim 11 , the operations further comprising:

determining the current vehicle context at the time the user feedback was received; and

updating, based on the user feedback, the quality score for the particular message at the time the user feedback was received.

14. A non-transitory computer-readable medium storing software comprising instructions executable by one or more computers which, upon such execution, cause the one or more computers to perform operations comprising:

receiving vehicle data indicating a state of a vehicle, wherein the vehicle data includes one or more of sensor data generated by one or more sensors of the vehicle, or application data generated by one or more vehicle applications, the sensor data being indicative of one or more physical parameters of the vehicle;

determining, based on the vehicle data indicative of the state of the vehicle, a current vehicle context, the current vehicle context being one of a plurality of predetermined vehicle contexts;

receiving message data indicating one or more candidate messages, each candidate message having a respective display context from a plurality of display contexts, wherein each of the plurality of display contexts matches at least one of the predetermined vehicle contexts;

determining whether a particular message of the one or more candidate messages has a display context that matches the current vehicle context; and

responsive to determining that the display context of the particular message matches the current vehicle context:

determining, based on the current vehicle context, a particular vehicle display of a plurality of display devices of the vehicle on which to display the particular message, wherein each of the plurality of the display devices of the vehicle are mounted to the vehicle; and

providing the particular message for output on the particular vehicle display and not one or more of the other vehicle display devices from the plurality of vehicle display devices.

15. The computer-readable medium of claim 14 , wherein the particular message is a first message from the one or more candidate messages, the operations further comprising:

responsive to determining that a second message from the one or more candidate messages has a respective display context that does not match the current vehicle context, discarding the second message without providing the second message for display on one of the plurality of display devices of the vehicle.

16. The computer-readable medium of claim 14 , wherein the one or more candidate messages comprises a plurality of candidate messages, the operations further comprising:

determining that two or more messages from the plurality of candidate messages have respective display contexts that match the current vehicle context;

clustering the two or more messages into two or more respective groups based on (i) the respective display context associated with each of the two or more messages, or (ii) a respective application that generated each of the two or more messages; and

assigning a priority value to each of the two or more messages based on the respective group into which each of the two or more messages is clustered.

17. The computer-readable medium of claim 16 , the operations further comprising:

ranking each of the two or more messages based on the assigned priority value; and

providing the two or more messages for output on the particular vehicle display based on the ranking.

18. The computer-readable medium of claim 14 , the operations further comprising:

detecting user feedback associated with the particular message after the particular message was output on the particular vehicle display;

determining whether the user feedback includes (i) positive interaction or (ii) negative interaction; and

in response to determining that the user feedback includes positive interaction, increasing a quality score associated with the particular message.

19. The computer-readable medium of claim 18 , the operations further comprising:

in response to determining that the user feedback includes negative interaction, decreasing the quality score associated with the particular message.

20. The computer-readable medium of claim 18 , the operations further comprising:

determining the current vehicle context at the time the user feedback was received; and

updating, based on the user feedback, the quality score for the particular message at the time the user feedback was received.