Back to results
US 10,650,317 B2Granted
Detecting and correcting potential errors in user behavior
AssigneeGoogle Inc.
InventorsJakob Nicolaus Foerster, Frederick Peter Brewin
Life of this patent
Estimating the term…
Abstract
A computing system is described that predicts a future action to be taken by a user of a computing device and determines, based on contextual information associated with the computing device, a current action being taken by the user. The computing system determines, based on the current action, a degree of likelihood of whether the user will be able to take the future action and predicts, based on the degree of likelihood, that the user will not be able to take the future action. The computing system sends information to the computing device indicating that the current action being taken by the user will lead to the user not being able to take the future action.
Claims8
A method comprising:
- predicting, by a computing system, a future action to be taken by a user of a computing device, wherein the future action includes arriving at a first location by a future time;
- determining, by the computing system, based on contextual information associated with the computing device, a current action being taken by the user, wherein the current action includes searching, using the computing device, for navigational directions to a second location that is different than the first location;
- determining, by the computing system, that the first location and the second location are different locations of a transportation service;
- determining, by the computing system, based on the current action, a degree of likelihood of whether the user will be able to take the future action, wherein determining the degree of likelihood of whether the user will be able to take the future action comprises:
- applying, as input across a machine learning model to generate an output, the contextual information associated with the computing device,
- determining the degree of likelihood of whether the user will be able to take the future action based on the output, and
- decreasing, by the computing system, the degree of likelihood in response to both:
- determining the first location and the second location are different locations of the transportation service, and
- determining a current time of the current action is within a threshold amount of time of the future time;
- predicting, by the computing system, based on the degree of likelihood, that the user will not be able to take the future action;
- and
- sending, from the computing system, to the computing device, information that proactively notifies the user that the current action being taken by the user will lead to the user not being able to take the future action and that proactively notifies the user of one or more corrective actions,
- wherein sending the information occurs automatically in response to the searching for navigational directions to the second location, and
- wherein sending the information causes the computing device to automatically present the information to the user in response to the searching for navigational directions to the second location.
11 more elements
A computing system comprising:
- at least one processor;
- and
- at least one module operable by the at least one processor to:
- predict a future action to be taken by a user of a computing device,
- wherein the future action includes arriving at a first location by a future time;
- determine, based on contextual information generated by the computing device, a current action being taken by the user, wherein the current action includes travelling to a second location that is different than the first location;
- determine that the first location and the second location are different locations of a transportation service;
- determine, based on the current action, a degree of likelihood of whether the user will be able to take the future action, wherein in determining the degree of likelihood of whether the user will be able to take the future action the at least one module is further operable by the at least one processor to:
- apply, as input across a machine learning model to generate an output, the contextual information associated with the computing device,
- determine the degree of likelihood of whether the user will be able to take the future action based on the output, and
- decrease the degree of likelihood in response to both:
- determining the first location and the second location are different locations of the transportation service, and
- determining a current time of the current action is within a threshold amount of time of the future time;
- predict, based on the degree of likelihood, that the user will not be able to take the future action;
- and
- send, to the computing device, information that proactively notifies the user that the current action being taken by the user will lead to the user not being able to take the future action and that proactively notifies the user of one or more corrective actions,
- wherein sending the information occurs automatically in response to predicting that the user will not be able to take the future action, and occurs while the user is travelling to the second location that is different than the first location, and
- wherein sending the information causes the computing device to present the information to the user.
15 more elements
A non-transitory computer-readable storage medium comprising instructions that, when executed, cause at least one processor of a computing system to:
- predict a future action to be taken by a user of a computing device, wherein the future action includes arriving at a first location by a future time;
- determine, based on contextual information generated by the computing device, a current action being taken by the user, wherein the current action includes travelling to a second location that is different than the first location;
- determine that the first location and the second location are different respective offices of a single commercial establishment;
- determine, based on the current action, a degree of likelihood of whether the user will be able to take the future action, wherein in determining the degree of likelihood of whether the user will be able to take the future action, the computing system is further operable by the at least one processor to:
- apply, as input across a machine learning model to generate an output, the contextual information associated with the computing device,
- determine the degree of likelihood of whether the user will be able to take the future action based on the output, and
- decrease the degree of likelihood in response to both:
- determining that the first location and the second location are different respective offices of the single commercial establishment, and
- determining a current time of the current action is within a threshold amount of time of the future time;
- predict, based on the degree of likelihood, that the user will not be able to take the future action;
- and
- send, to the computing device, information indicating that the current action being taken by the user will lead to the user not being able to take the future action and that proactively notifies the user of one or more corrective actions,
- wherein sending the information occurs automatically in response to predicting that the user will not be able to take the future action, and occurs while the user is travelling to the second location that is different than the first location, and
- wherein sending the information causes the computing device to present the information to the user.
11 more elements
Dependencies are inferred from the claim text.