Image-based detection of modem crashes in mobile telephonic devices
AssigneeT-Mobile USA, Inc.
InventorPei Zheng
Life of this patent
Estimating the term…
Abstract
To detect “silent” crashes of communications processors in a mobile device, the mobile device analyzes signal strength icon images using a trained image processing model. During operation of a mobile device, the device captures images of a signal strength icon that is displayed by the device and that visually represents a telecommunications signal strength detected by the mobile device. The mobile device applies the captured images to the trained image processing model, which is configured to output a prediction of whether the communications processor in the mobile device crashed.
Claims20
A mobile telephonic device comprising:
- at least one display device;
- at least one modem;
- at least one application processor;
- and
- at least one non-transitory memory storing instructions, which, when executed by the at least one application processor, cause the mobile telephonic device to:
- capture a sequence of images of a signal strength icon displayed on the at least one display device, the signal strength icon visually representing a signal strength of a cellular network signal at the mobile telephonic device at a time each image in the sequence of images is captured;
- analyze the sequence of images of the signal strength icon using an image processing machine learning model that is trained to output a prediction of a crash of the at least one modem based on the sequence of images;
- and
- in response to the image processing machine learning model predicting the crash of the at least one modem, recording state data associated with a context of the crash of the at least one modem.
At least one computer-readable storage medium, excluding transitory signals and carrying instructions, which, when executed by at least one data processor of a system, cause the system to:
- capture a sequence of images of a signal strength icon displayed on a display device of the system, the signal strength icon visually representing a signal strength of a telecommunications network signal at the system at a time each image in the sequence of images is captured;
- analyze the sequence of images of the signal strength icon using an image processing model that is trained to output a prediction of a crash of a communications processor in the system based on the sequence of images;
- and
- in response to the image processing model predicting the crash of the communications processor, recording state data associated with a context of the crash of the communications processor.
At least one computer-readable storage medium, excluding transitory signals and carrying instructions, which, when executed by at least one data processor of a system, cause the system to:
- receive a set of signal strength icon images captured from a plurality of mobile telephonic devices,
- wherein each signal strength icon image is a visual representation of a signal strength of a telecommunications signal at a time the signal strength icon image was captured, and
- wherein the set of signal strength icon images includes signal strength icon images representing multiple signal strengths at each of multiple types of the mobile telephonic devices;
- train an image processing model, using the set of signal strength icon images, to predict a crash of a communications processor based on a sequence of signal strength icon images;
- and
- provide the trained image processing model for use by an identified mobile telephonic device to detect a crash of a communications processor in the identified mobile telephonic device using signal strength icon images displayed by the identified mobile telephonic device.
Dependencies are inferred from the claim text.