This patent describes an innovative system and method for automatically configuring electronic devices using artificial intelligence (AI). The core idea involves leveraging device usage data (telemetry data) as input for machine learning models to predict future events and proactively configure the device’s operating system, applications, and hardware accordingly. This approach aims to personalize the user experience, optimize device performance (speed, memory, battery), improve resource allocation, and even enable preemptive actions and automatic remediation. A key aspect is the use of cloud-based machine learning models tailored to device metadata, with the potential for local augmentation using device-specific, non-shared information.
Main Themes and Important Ideas/Facts
1. Automated Configuration using AI: The central theme is the automation of electronic device configuration through AI. This moves away from generalized default settings and manual user configuration.
“The devices, systems, and methods described herein enable automatically configuring an electronic device using artificial intelligence (AI).” (Abstract)
2. Telemetry Data as the Foundation: Device usage data, referred to as telemetry data, is crucial for training and informing the AI models. This data captures how the user interacts with the device and its components.
“The devices, systems, and methods enable accessing telemetry data representing device usage data…” (Abstract) “Specifically, the telemetry data gathered by the UTC [Universal Telemetry Client] includes data that represents how the electronic device 100 has been used by the user (e.g., the usage pattern over time)…” (Description, [14])
3. Machine Learning Models for Prediction: Machine learning models, matched to device metadata, analyze the telemetry data to predict future events on the device. These models are primarily generated and potentially updated in the cloud.
“…inputting the accessed telemetry data into machine learning models that are matched to device metadata…” (Abstract) “The machine learning models 118 are generated in the cloud service 116, in one example, and are grouped by device metadata.” (Description, [17])
4. Proactive Notifications and Configuration: Based on the predictions, the system determines and publishes notifications to various components of the electronic device. These notifications trigger the components to configure themselves preemptively.
“…and determining notifications to publish to components of the electronic device. The notifications represent events predicted to occur on the electronic device.” (Abstract) “The notifications are published to the components of the electronic device such that the electronic device is configured according to the published notifications.” (Abstract)
5. Benefits of AI-Powered Configuration: The patent highlights several potential benefits, including personalized settings, improved device performance, increased intelligence of the operating system, automatic remediation, and the possibility of less expensive, user-tailored hardware.
“The determined notifications enable the identification of optimal settings for the electronic device based on the usage pattern of the device and enable components of the electronic device to preemptively take action on events which are predicted to occur in the future.” (Abstract) “Further, the electronic device, when configured to perform the operations described herein, operates in an unconventional manner to increase the speed of the electronic device, conserve memory, reduce processor load, improve operating system resource allocation, improve user efficiency, increase user interaction performance, reduce error rate, and/or the like.” (Description, [10])
6. System Architecture: The patent outlines a system architecture involving an AI client service (responsible for inputting telemetry data into models and determining notifications) and an AI broker (responsible for publishing these notifications to device components). A Universal Telemetry Client (UTC) gathers the usage data.
“Referring to FIG. 1, an exemplary block diagram illustrates an electronic device 100 including an artificial intelligence (AI) client service 102 and an AI broker 104 according to an embodiment.” (Description, [11]) “The electronic device 100 includes a universal telemetry client (UTC) 114 that gathers telemetry data from the electronic device 100 for use by the AI client service 104.” (Description, [14])
7. Broad Range of Applicable Devices and Components: The technology is intended for a wide variety of electronic devices and can configure the operating system, application software, internal hardware, and external hardware.
“The electronic device 100 represents any device executing instructions… The electronic device may include a mobile electronic device or any other portable device… The electronic device may also include less portable devices…” (Description, [12]) “As used herein, ‘components’ of the electronic device 100 may include, but are not limited to, an operating system of the electronic device 100, application software… internal hardware of the electronic device 100, and/or external hardware…” (Description, [12])
8. Prediction of Various Events: The system can predict a diverse set of events, ranging from user preferences and potential contradictions to hardware usage and application activation.
“Events that are predicted to occur by the AI client service 102 include, but are not limited to, the contradiction of a preference and/or action of the user with an expectation of the user, the contradiction of a preference and/or action of the user with a threshold defined and/or expected by the user, a bad deployment of application software and/or hardware, a fault of the electronic device 100 and/or a component thereof, the upcoming use and/or activation of application software 108, an intended use of application software 108, the upcoming use and/or activation of internal hardware 110, an intended use of internal hardware 110, the upcoming use and/or activation of external hardware 112, an intended use of external hardware 112, the upcoming closing and/or de-activation of application software 108, the upcoming powering-down of internal hardware 110, the upcoming powering-down and/or disconnection of external hardware 112, and/or other predictions.” (Description, [25])
9. Customization through Local Augmentation: The AI client service has the capability to augment cloud-based machine learning models with local, device-specific information that is not shared with the cloud. This allows for greater personalization and handling of proprietary or custom device features.
“In some examples, the machine learning models 118 include custom machine learning models 118 from the electronic device 100 and/or a private cloud service… For example, machine learning models 118 generated in the cloud service 116 may be augmented (e.g., updated) using information that is unknown to the cloud service 116 but is known by the electronic device 100 and/or the user.” (Description, [17]) “In this way, the electronic device 100 can update at least some of the machine learning models 118 without sharing proprietary and/or custom information with the cloud service 116.” (Description, [17])
10. Examples of Application: The patent provides examples of how this technology could be used, such as improving virtual personal assistants and tailoring devices for family use.
“In one example scenario, the methods, systems, and electronic devices described herein may be used to increase the functionality of virtual personal assistants… For example, new skills may be added to the virtual personal assistant based on the user’s history of walking into a room, downloading music, setting lights, ordering food, and/or the like.” (Description, [55]) “In another example scenario, the methods, systems, and electronic devices described herein may be used to tailor an electronic device to the uses of a family. For example, the configuration of the electronic device may be automatically changed based on usage patterns indicating that the user is an adult or a child.” (Description, [56])
11. Real-time and Historical Telemetry: The system can utilize both historical usage patterns and real-time data to make predictions and trigger configurations.
“…may, in some examples, include real-time data that represents how the electronic device 100 is currently being used by the user.” (Description, [14]) “wherein the telemetry data input by the AI client service from the memory into the machine learning models is real-time telemetry data from the electronic device.” (Claims, [69])
12. Option for User Confirmation: In some embodiments, notifications might include prompts for user confirmation before automatic configuration changes are implemented.
“In some examples, notifications determined by the AI client service 102 may include a prompt to the user informing the user of the automatic configuration, along with a selection to confirm or reject the automatic configuration.” (Description, [24])
Potential Implications
This patent signifies a move towards more intelligent and adaptive electronic devices that can learn from user behavior and proactively optimize themselves. This could lead to:
- Enhanced User Experience: Devices that are better tailored to individual needs and usage patterns.
- Improved Device Performance: Optimized resource allocation and preemptive actions to avoid slowdowns or issues.
- Reduced Manual Configuration: Less need for users to manually adjust settings.
- New Possibilities for Hardware Design: The ability to configure hardware based on predicted usage could lead to more specialized and potentially less expensive devices.