Methods and system for managing predictive models

• US 10,380,488 B2
• Filed: 09/29/2014
• Issued: 08/13/2019
• Est. Priority Date: 05/30/2014
• Status: Active Grant

• Current Assignee: Apple Inc.
• Original Assignee: Apple Inc.
• Inventors: Mathew, Binu K., Wan, Kit-Man, Kapoor, Gaurav
• Primary Examiner(s): Zhen, Li B.
• Assistant Examiner(s): Pellett, Daniel T
• Application Number:
  US14/500,985
• Publication Number:
  US 20150347907A1
• Time in Patent Office: 1,779 Days
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06N 5/04 Inference or reasoning models
• CPC Class Codes: G06N 5/043 Distributed expert systems; Blackboards
• CPC Class Codes: H04L 67/10 in which an application is distributed across nodes in the network software deployment G06F8/60; multiprogramming arrangements G06F9/46

Abstract

Disclosed herein is a technique for implementing a framework that enables application developers to enhance their applications with dynamic adjustment capabilities. Specifically, the framework, when utilized by an application on a mobile computing device that implements the framework, can enable the application to establish predictive models that can be used to identify meaningful behavioral patterns of an individual who uses the application. In turn, the predictive models can be used to preempt the individual'"'"'s actions and provide an enhanced overall user experience. The framework is configured to interface with other software entities on the mobile computing device that conduct various analyses to identify appropriate times for the application to manage and update its predictive models. Such appropriate times can include, for example, identified periods of time where the individual is not operating the mobile computing device, as well as recognized conditions where power consumption is not a concern.

Claims

1. A method for generating and deploying predictive models to computing devices, the method comprising steps that include:

at a source computing device;

receiving a request, to generate a raw predictive model based on a set of training data;

generating, at the source computing device, the raw predictive model using the set of training data to facilitate improving a load time of the raw predictive model by a respective destination computing device which is to receive the raw predictive model, wherein the raw predictive model is generated in a binary form that is specifically tailored to one or more destination computing devices such that each destination computing device of the one or more destination computing devices is not required to parse the raw predictive model;

identifying the one or more destination computing devices to which a respective deployment predictive model associated with the raw predictive model is to be established; and

for each destination computing device of the one or more destination computing devices;

providing the raw predictive model to the destination computing device, wherein the destination computing device generates the respective deployment predictive model based on the raw predictive model.

2. The method of claim 1, wherein, for a given destination computing device of the one or more destination computing devices, the respective deployment predictive model is optimized based on a hardware architecture that is implemented by the destination computing device.

3. The method of claim 1, wherein, for a given destination computing device of the one or more destination computing devices, the respective deployment predictive model is optimized based on at least one performance requirement instituted by an application that is configured to:

execute on the destination computing device, and

utilize the respective deployment predictive model.

4. The method of claim 1, wherein the raw predictive model is generated in a platform-independent form that the one or more destination computing devices are capable of parsing.

5. The method of claim 1, wherein each destination computing device of the one or more destination computing devices periodically updates the respective deployment predictive model as updated training data is gathered over time by the destination computing device.

6. A method for managing a predictive model on a mobile computing device, the method comprising:

at the mobile computing device;

receiving a raw predictive model from a source computing device, wherein the raw predictive model is generated by the source computing device and is based on an original set of data;

generating the predictive model based on the raw predictive model;

identifying a condition to perform an update to the predictive model, wherein identifying the condition facilitates avoiding interfering with functionality of the mobile computing device while being utilized;

accessing an updated set of training data on which to base the update to the predictive model, wherein the updated set of training data supplements the original set of training data previously used to establish the predictive model;

updating the predictive model based on the updated set of training data; and

subsequent to updating the predictive model;

implementing the predictive model for usage on the mobile computing device, and

updating a configuration to reflect that the updated set of training data has been processed.

7. The method of claim 6, wherein identifying the condition comprises receiving a notification from a power management module implemented on the mobile computing device.

8. The method of claim 7, wherein the power management module is configured to provide the notification when the mobile computing device is connected to an external power source or when the mobile computing device is not being operated by a user.

9. The method of claim 6, wherein each of the original set of training data and the updated set of training data is stored locally on the mobile computing device.

10. The method of claim 6, wherein the predictive model, subsequent to being updated, is provided to an application that utilizes the predictive model and executes on the mobile computing device.

11. A method for managing a predictive model on a mobile computing device, the method comprising:

at the mobile computing device;

receiving a raw predictive model from a source computing device, wherein the raw predictive model is generated by the source computing device and is based on an original set of data;

generating the predictive model based on the raw predictive model;

identifying that a threshold amount of additional training data has been added to a set of training data, on which the predictive model is based;

determining, based on parameters associated with the predictive model, an appropriate time to update the predictive model, wherein determining the appropriate time to update the predictive model facilitates avoiding interfering with functionality of the mobile computing device while being utilized;

at the appropriate time, updating the predictive model based on the additional training data; and

subsequent to updating the predictive model, implementing the predictive model for usage.

12. The method of claim 11, wherein the set of training data is stored locally on the mobile computing device.

13. The method of claim 11, wherein the predictive model, subsequent to being updated, is provided to an application that utilizes the predictive model and executes on the mobile computing device.

14. The method of claim 11, wherein the parameters indicate one or more of:

a historical average amount of time required to update to the predictive model, a historical average amount of processing resources that are required to update the predictive model, and a historical average amount of memory resources that are required to update the predictive model.

15. The method of claim 11, wherein the mobile computing device is configured to update at least one other predictive model while the predictive model is being updated.

16. The method of claim 11, further comprising:

receiving, via an over the air update, a replacement predictive model that is associated with the predictive model; and

replacing the predictive model with the replacement predictive model.

17. At least one non-transitory computer readable storage medium configured to store instructions that, when executed by at least one processor included in a mobile computing device, cause the mobile computing device to carry out steps that include:

receiving a raw predictive model from a source computing device, wherein the raw predictive model is generated by the source computing device and is based on an original set of data;

generating the predictive model based on the raw predictive model;

identifying a condition to perform an update to a predictive model, wherein identifying the condition facilitates avoiding interfering with functionality of the mobile computing device while being utilized;

accessing an updated set of training data on which to base the update to the predictive model, wherein the updated set of training data supplements the original set of training data previously used to establish the predictive model;

updating the predictive model based on the updated set of training data; and

subsequent to updating the predictive model;

implementing the predictive model for usage on the mobile computing device, and

updating a configuration to reflect that the updated set of training data has been processed.

18. The at least one non-transitory computer readable storage medium of claim 17, wherein identifying the condition comprises receiving a notification from a power management module implemented on the mobile computing device.

19. A mobile device, comprising:

at least one processor; and

at least one memory storing instructions that, when executed by the at least one processor, cause the mobile

device to;

receive a raw predictive model from a source computing device, wherein the raw predictive model is generated by the source computing device and is based on an original set of data;

generate a predictive model based on the raw predictive model;

identify that a threshold amount of additional training data has been added to a set of training data on which the predictive model is based;

determine, based on parameters associated with the predictive model, an appropriate time to update the predictive model, wherein to determine the appropriate time to update the predictive model facilitates avoiding interfering with functionality of the mobile computing device while being utilized;

at the appropriate time, update the predictive model based on the additional training data; and

subsequent to updating the predictive model, implement the predictive model for usage.

20. The mobile device of claim 19, wherein the set of training data is stored locally on the mobile device.