Information processing device and method
The present technology relates to an information processing device, an information processing method, that facilitate comparisons between insurances. The information processing device includes an acquisition unit that acquires an output from one sensor or outputs from a plurality of sensors different from each other as behavior-monitoring data items of a user, and a diagnosis-result prediction unit that predicts a diagnosis result about one insurance or diagnosis results about a plurality of insurances for the user on the basis of a prediction model calculated in advance by learning for the one insurance or each of the plurality of insurances and on the basis of the behavior-monitoring data items. The present technology is applicable to comparison systems.
1. An information processing device, comprising:
a plurality of sensors configured to acquire user position information and user action recognition information, wherein
the user position information indicates a user position on a driving path of an automobile, and
the user action recognition information indicates a user action;
an action recognition unit configured to recognize a user state based on the acquired user action recognition information, wherein the user state is one of a user walking state, a user driving state, a user cycling state, a user running state, or a user pausing state;
an acquisition unit configured to:
determine each of a first time period and a second time period based on the acquired user position information and the recognized user state, wherein
the recognized user state is the user driving state, and
the second time period is subsequent to the first time period;
acquire, between a start of the first time period and an end of the first time period, a plurality of first outputs from the plurality of sensors; and
acquire, between a start of the second time period and an end of the second time period, a plurality of second outputs from the plurality of sensors, wherein
the plurality of first outputs from the plurality of sensors corresponds to a plurality of first user behavior-monitoring data items in the first time period,
the plurality of second outputs from the plurality of sensors corresponds to a plurality of second user behavior-monitoring data items in the second time period,
each of the plurality of first user behavior-monitoring data items and the plurality of second user behavior-monitoring data items is different from the acquired user position information and the acquired user action recognition information, and
each sensor of the plurality of sensors is different;
a diagnosis-result prediction unit configured to predict a plurality of diagnosis results about a plurality of insurances, wherein
each diagnosis result of the plurality of diagnosis results includes a score that indicates user driving information,
the user driving information corresponds to a degree of safe driving for the automobile,
the prediction is based on a prediction model, the plurality of first user behavior-monitoring data items, and the plurality of second user behavior-monitoring data items, and
the prediction model is calculated based on machine learning for each insurance of the plurality of insurances;
a prediction-error prediction unit configured to:
store prediction-error prediction models; and
predict, based on the stored prediction-error prediction models, the plurality of first user behavior-monitoring data items, the plurality of second user behavior-monitoring data items, the first time period, and the second time period, a plurality of errors corresponding to a plurality of results of the prediction of the plurality of diagnosis results about the plurality of insurances, wherein
the plurality of errors includes a plurality of first errors in the first time period and a plurality of second errors in the second time period,
the first time period is greater than the second time period, and
each first error of the plurality of first errors is smaller than each second error of the plurality of second errors; and
a display-data generation unit configured to control a display unit to display an insurance comparison screen to compare the plurality of insurances, wherein
the insurance comparison screen includes a set of display data items to compare the plurality of insurances,
the set of display data items includes a first display data item and a second display data item,
the first display data item indicates the plurality of results of the prediction of the plurality of diagnosis results about the plurality of insurances, and
the second display data item indicates one of a plurality of discounts or a plurality of premiums of the plurality of insurances.
2. The information processing device according to claim 1 , wherein
the display-data generation unit is further configured to calculate
the plurality of discounts or the plurality of premiums of the plurality of insurances based on the plurality of results of the prediction.
3. The information processing device according to claim 1 , wherein each of the plurality of insurances is a telematics insurance.
4. The information processing device according to claim 1 , wherein
the prediction-error prediction unit is further configured to calculate
a plurality of confidence factors, based on a result of the plurality of errors, of the plurality of results of the prediction of the plurality of diagnosis results about the plurality of insurances,
the display-data generation unit is further configured to generate the first display data item based on at least one of
the plurality of confidence factors or the plurality of errors of the plurality of results of the prediction.
5. The information processing device according to claim 4 , wherein the first display data item includes a third display data item to present
the plurality of results of the prediction with the plurality of confidence factors or the plurality of errors.
6. The information processing device according to claim 4 , wherein the first display data item includes a third display data item to
present, based on a determination that one of each of the plurality of confidence factors is equal to or greater than a first value or the plurality of errors is equal to or less than a second value, the plurality of results of the prediction of the plurality of diagnosis results about the plurality of insurances.
7. The information processing device according to claim 1 , wherein the acquisition unit is further configured to:
determine the end of the first time period based on the recognized user state; and
acquire the plurality of first user behavior-monitoring data items based on the end of the first time period.
8. The information processing device according to claim 1 , wherein the acquisition unit is further configured to determine the start of the first time period and the end of the first time period based on the user position information and the user state.
9. The information processing device according to claim 1 , wherein the plurality of first user behavior-monitoring data items includes:
a plurality of third user behavior-monitoring data items in a third time period, and
a plurality of fourth user behavior-monitoring data items in each interval is different from an interval in the second time period,
the plurality of results of the prediction of the plurality of diagnosis results about the plurality of insurances includes:
a plurality of first prediction results obtained from the plurality of third user behavior-monitoring data items in the third time period, and
a plurality of second prediction results obtained from the plurality of fourth user behavior-monitoring data items in each interval different from the interval in the third time period,
the diagnosis-result prediction unit is further configured to specify
the interval in which differences between the plurality of first prediction results and the plurality of second prediction results are each equal to or more than a specific value, and
the information processing device further comprises a driving-behavior specifying unit configured to specify a plurality of user driving behaviors in the interval based on the plurality of third user behavior-monitoring data items in the third time period.
10. The information processing device according to claim 9 , wherein the plurality of user driving behaviors include at least one of sudden braking, sudden acceleration, or sudden steering.
11. The information processing device according to claim 9 , wherein the display-data generation unit is further configured to display a third display data item to present the plurality of user driving behaviors in the interval.
12. The information processing device according to claim 11 , wherein
the third display data item includes a display data item to present a specific user driving behavior of the plurality of user driving behaviors,
the specific user driving behavior is exhibited a specific number of times in the interval,
each user driving behavior of a set of user driving behaviors is exhibited less than the specific number of times,
the plurality of user driving behaviors includes the set of user driving behaviors, and
each user driving behavior of the set of user driving behaviors is different from the specific user driving behavior.
13. The information processing device according to claim 1 , wherein
the plurality of sensors includes at least one of an acceleration sensor, a gyroscopic sensor, a barometric sensor, or a geomagnetic sensor.
14. The information processing device according to claim 1 , wherein
the diagnosis-result prediction unit is further configured to generate, for each of the plurality of insurances, a learning data item for at least one error of the plurality of errors, and
the learning data item includes a pair of a length of a corresponding driving time period of a user and the at least one error.
15. The information processing device according to claim 1 , wherein each error of the plurality of errors comprises an absolute value of a difference between an actual drive diagnosis result and the prediction of a corresponding diagnosis result of the plurality of diagnosis results.
16. An information processing method, comprising:
acquiring, by a plurality of sensors, user position information and user action recognition information, wherein
the user position information indicates a user position on a driving path of an automobile, and
the user action recognition information indicates a user action;
recognizing a user state based on the acquired user action recognition information, wherein the user state is one of a user walking state, a user driving state, a user cycling state, a user running state, or a user pausing state;
determining each of a first time period and a second time period based on the acquired user position information and the recognized user state, wherein
the recognized user state is the user driving state, and
the second time period is subsequent to the first time period;
acquiring, between a start of the first time period and an end of the first time period, a plurality of first outputs from the plurality of sensors;
acquiring, between a start of the second time period and an end of the second time period, a plurality of second outputs from the plurality of sensors, wherein
the plurality of first outputs from the plurality of sensors corresponds to a plurality of first user behavior-monitoring data items in the first time period,
the plurality of second outputs from the plurality of sensors corresponds to a plurality of second user behavior-monitoring data items in the second time period,
each of the plurality of first user behavior-monitoring data items and the plurality of second user behavior-monitoring data items is different from the acquired user position information and the acquired user action recognition information, and
each sensor of the plurality of sensors is different;
predicting a plurality of diagnosis results about a plurality of insurances, wherein
each diagnosis result of the plurality of diagnosis results includes a score that indicates user driving information,
the user driving information corresponds to a degree of safe driving for the automobile,
the prediction is based on a prediction model, the plurality of first user behavior-monitoring data items, and the plurality of second user behavior-monitoring data items, and
the prediction model is calculated based on machine learning for each insurance of the plurality of insurances;
storing prediction-error prediction models;
predicting, based on the stored prediction-error prediction models, the plurality of first user behavior-monitoring data items, the plurality of second user behavior-monitoring data items, the first time period, and the second time period, a plurality of errors corresponding to a plurality of results of the prediction of the plurality of diagnosis results about the plurality of insurances, wherein
the plurality of errors includes a plurality of first errors in the first time period and a plurality of second errors in the second time period,
the first time period is greater than the second time period, and
each first error of the plurality of first errors is smaller than each second error of the plurality of second errors; and
controlling a display unit to display an insurance comparison screen to compare the plurality of insurances, wherein
the insurance comparison screen includes a set of display data items to compare the plurality of insurances,
the set of display data items includes a first display data item and a second display data item,
the first display data item indicates the plurality of results of the prediction of the plurality of diagnosis results about the plurality of insurances, and
the second display data item indicates one of a plurality of discounts or a plurality of premiums of the plurality of insurances.
17. A non-transitory computer-readable medium having stored thereon, computer-executable instructions which, when executed by a processor, cause the processor to execute operations, the operations comprising:
acquiring, by a plurality of sensors, user position information and user action recognition information, wherein
the user position information indicates a user position on a driving path of an automobile, and
the user action recognition information indicates a user action;
recognizing a user state based on the acquired user action recognition information, wherein the user state is one of a user walking state, a user driving state, a user cycling state, a user running state, or a user pausing state;
determining each of a first time period and a second time period based on the acquired user position information and the recognized user state, wherein
the recognized user state is the user driving state, and
the second time period is subsequent to the first time period;
acquiring, between a start of the first time period and an end of the first time period, a plurality of first outputs from the plurality of sensors;
acquiring, between a start of the second time period and an end of the second time period, a plurality of second outputs from the plurality of sensors, wherein
the plurality of first outputs from the plurality of sensors corresponds to a plurality of first user behavior-monitoring data items in the first time period,
the plurality of second outputs from the plurality of sensors corresponds to a plurality of second user behavior-monitoring data items in the second time period,
each of the plurality of first user behavior-monitoring data items and the plurality of second user behavior-monitoring data items is different from the acquired user position information and the acquired user action recognition information, and
each sensor of the plurality of sensors is different;
predicting a plurality of diagnosis results about a plurality of insurances, wherein
each diagnosis result of the plurality of diagnosis results includes a score that indicates user driving information,
the user driving information corresponds to a degree of safe driving for the automobile,
the prediction is based on a prediction model, the plurality of first user behavior-monitoring data items, and the plurality of second user behavior-monitoring data items, and
the prediction model is calculated based on machine learning for each insurance of the plurality of insurances;
storing prediction-error prediction models;
predicting, based on the stored prediction-error prediction models, the plurality of first user behavior-monitoring data items, the plurality of second user behavior-monitoring data items, the first time period, and the second time period, a plurality of errors corresponding to a plurality of results of the prediction of the plurality of diagnosis results about the plurality of insurances, wherein
the plurality of errors includes a plurality of first errors in the first time period and a plurality of second errors in the second time period,
the first time period is greater than the second time period, and
each first error of the plurality of first errors is smaller than each second error of the plurality of second errors; and
controlling a display unit to display an insurance comparison screen to compare the plurality of insurances, wherein
the insurance comparison screen includes a set of display data items to compare the plurality of insurances,
the set of display data items includes a first display data item and a second display data item,
the first display data item indicates the plurality of results of the prediction of the plurality of diagnosis results about the plurality of insurances, and
the second display data item indicates one of a plurality of discounts or a plurality of premiums of the plurality of insurances.