System and method for selecting and serving content items based on sensor data from mobile devices
Sensor data having values received from several sensors of a mobile device and response data associated with the sensor data may be used in the determination or training of a predictive model. Received sensor data may be input into the predictive model, and the output of the predictive model may be used in the selection and serving of content items to the mobile device. Data to effect presentation of the selected content item may be outputted to the mobile device to effect presentation. In some instances, the predictive model may be updated using the received plurality of values. The updated predictive model may be used in the selection of a subsequent content item for the mobile device. In other implementations, historical sensor data may be used with the set of received sensor data as input for the predictive model.
1. A system, comprising:
a data processing system having one or more data processors and a storage device storing instructions that, when executed by the one or more data processors, cause the data processing system to:
receive i) a first acoustic request for content, and ii) a first plurality of values received from a respective plurality of sensors of a mobile device, the first plurality of values associated with the first acoustic request, the first plurality of values indicating a first ambient condition of the mobile device;
select, in response to the first acoustic request, a first content item based on a predictive model to select content items and based on the first plurality of values, the predictive model selects the first content item from a plurality of candidate content items using associations between i) response data received from a plurality of mobile devices; and ii) values corresponding to sensors of the plurality of mobile devices;
maintain, by the predictive model, for each content item of the plurality of candidate content items, a performance metric based on the response data corresponding to the content item;
output data to effect an acoustic presentation of the first content item by the mobile device;
receive first response data transmitted by the mobile device in response to presentation of the first content item at the mobile device associated with the first acoustic request;
associate the first response data corresponding to the first content item with the values corresponding to the sensors of the plurality of mobile devices;
update the predictive model by associating the first response data corresponding to the first content item with the first plurality of values received from the respective plurality of sensors of the mobile device;
receive i) a second acoustic request for content, and ii) a second plurality of values received from a respective plurality of sensors of the mobile device, the second plurality of values indicating a second ambient condition of the mobile device;
select a second content item based on the updated predictive model and the second plurality of values; and
output data to effect an acoustic presentation of the second content item by the mobile device.
2. The system of claim 1 , wherein the first content item and the second content item each include acoustic content.
3. The system of claim 1 , wherein the first plurality of values received from the respective plurality of sensors of the mobile device comprises a first plurality of acoustic levels received from a plurality of acoustic sensors of the mobile device, and wherein the second plurality of values received from the respective plurality of sensors of the mobile device comprises a second plurality of acoustic levels received from the plurality of acoustic sensors of the mobile device.
4. The system of claim 1 , wherein the first plurality of values combined with the first acoustic request in a first URL string.
5. The system of claim 1 , wherein the first acoustic request comprises speech, and wherein the second acoustic request comprises speech.
6. The system of claim 1 , wherein the first acoustic request is associated with a mobile webpage.
7. The system of claim 1 , wherein the first acoustic request is associated with a mobile application.
8. A method, comprising:
receiving, at one or more data processors, i) a first acoustic request for content and ii) a first plurality of values received from a respective plurality of sensors of a mobile device, the first plurality of values combined with the first acoustic request for the content, the first plurality of values indicating a first ambient condition of the mobile device;
selecting, using one or more data processors and in response to the first acoustic request, a first content item based on a predictive model for selecting content items and the first plurality of values, the predictive model selecting the first content item from a plurality of candidate content items using associations between i) response data received from a plurality of mobile devices; and ii) values corresponding to sensors of the plurality of mobile devices; the predictive model maintaining, for each content item of the plurality of candidate content items, a performance metric based on the response data corresponding to the content item;
outputting data to effect an acoustic presentation of the first content item by the mobile device;
receiving, at one or more data processors, first response data transmitted by the mobile device in response to presentation of the first content item at the mobile device associated with the first acoustic request;
associating, at one or more data processors, the first response data corresponding to the first content item with the values corresponding to the sensors of the plurality of mobile devices;
updating, at one or more data processors, the predictive model by associating the first response data corresponding to the first content item with the first plurality of values received from the respective plurality of sensors of the mobile device;
receiving, at one or more data processors, i) a second acoustic request for content and ii) a second plurality of values received from a respective plurality of sensors of the mobile device, the second plurality of values indicating a second ambient condition of the mobile device; and
selecting, using one or more data processors, a second content item based on the updated predictive model and the second plurality of values.
9. The method of claim 8 , wherein the first content item and the second content item each include acoustic content.
10. The method of claim 8 , wherein the first plurality of values received from the respective plurality of sensors of the mobile device comprises a first plurality of acoustic levels received from a plurality of acoustic sensors of the mobile device, and wherein the second plurality of values received from the respective plurality of sensors of the mobile device comprises a second plurality of acoustic levels received from the plurality of acoustic sensors of the mobile device.
11. The method of claim 8 , wherein the first plurality of values combined with the first acoustic request in a first URL string.
12. The method of claim 8 , wherein the first acoustic request comprises speech, and wherein the second acoustic request speech.
13. The method of claim 8 , wherein the first acoustic request is associated with a mobile webpage.
14. The method of claim 8 , wherein the first acoustic request is associated with a mobile application.
15. The method of claim 8 , wherein the predictive model is associated with an acoustic content item.
16. A computer-readable storage device storing instructions that, when executed by one or more data processors, cause the one or more data processors to perform operations comprising:
receiving i) a first acoustic request for content and ii) a first plurality of values received from a respective plurality of sensors of a mobile device, the first plurality of values indicating a first ambient condition of the mobile device;
selecting, in response to the first acoustic request, a first content item based on a predictive model for selecting content items and the first plurality of values, the predictive model selecting the first content item from a plurality of candidate content items using associations between i) response data received from a plurality of mobile devices; and ii) values corresponding to sensors of the plurality of mobile devices; the predictive model maintaining, for each content item of the plurality of candidate content items, a performance metric based on the response data corresponding to the content item;
outputting data to effect an acoustic presentation of the first content item by the mobile device;
receiving first response data transmitted by the mobile device in response to presentation of the first content item at the mobile device associated with the first acoustic request;
associating, at the one or more data processors, the first response data corresponding to the first content item with the values corresponding to the sensors of the plurality of mobile devices;
updating the predictive model by associating the first response data corresponding to the first content item with the first plurality of values received from the respective plurality of sensors of the mobile device;
receiving i) a second acoustic request for content and ii) a second plurality of values received from a respective plurality of sensors of the mobile device, the second plurality of values indicating a second ambient condition of the mobile device; and
selecting a second content item based on the updated predictive model and the second plurality of values.
17. The computer-readable storage device of claim 16 , wherein the first content item and the second content item each include acoustic content items.
18. The computer-readable storage device of claim 16 , wherein the first plurality of values received from the respective plurality of sensors of the mobile device comprises a first plurality of acoustic levels received from a plurality of acoustic sensors of the mobile device, and wherein the second plurality of values received from the respective plurality of sensors of the mobile device comprises a second plurality of acoustic levels received from the plurality of acoustic sensors of the mobile device.
19. The computer-readable storage device of claim 16 , wherein the first plurality of values combined with the first acoustic request in a first URL string.
20. The computer-readable storage device of claim 16 , wherein the first acoustic request comprises speech, and wherein the second acoustic request comprises speech.