Surface detection for mobile devices

Patent metadata

Field	Value
Publication number	US-2021203769-A1
Application number	US-202117179097-A
Country	US
Kind code	A1
Filing date	Feb 18, 2021
Priority date	Dec 28, 2018
Publication date	Jul 1, 2021
Grant date	—

Abstract

A disclosed example includes providing vibration information to a model, the vibration information corresponding to a first vibration measured at a first mobile device when the first mobile device is in a state of non-use by a user, the model based on a plurality of vibration patterns that correspond to second vibrations measured by second mobile devices in different environments; identifying, using the model, one of the vibration patterns that corresponds to the vibration information; determining an environment of the first mobile device based on the one of the vibration patterns; and instructing the first mobile device to modify a functionality of the first mobile device based on the environment.

First claim

What is claimed is:

1 . A non-transitory computer readable medium comprising instructions which, when executed, cause a server to at least:
provide vibration information to a model, the vibration information corresponding to a first vibration measured at a first mobile device when the first mobile device is in a state of non-use by a user, the model based on a plurality of vibration patterns that correspond to second vibrations measured by second mobile devices in different environments; identify, using the model, one of the vibration patterns that corresponds to the vibration information; determine an environment of the first mobile device based on the one of the vibration patterns; and instruct the first mobile device to modify a functionality of the first mobile device based on the environment.

2 . The non-transitory computer readable medium of claim 1 , wherein the instructions, when executed, cause the server to execute the model.

3 . The non-transitory computer readable medium of claim 1 , wherein the instructions, when executed, cause the server to identify the one of the vibration patterns based on a confidence level that exceeds a threshold.

4 . The non-transitory computer readable medium of claim 1 , wherein the instructions, when executed, cause the server to determine the environment by determining the environment is one or more of: a clothing surface, a container surface, a soft surface, a rigid surface, a hand surface, a leather surface, a wood surface, or a paper surface.

5 . The non-transitory computer readable medium of claim 1 , wherein the instructions, when executed, cause the server to:
access training vibration information for the environment;
apply linear predictive coding (LPC) to the training vibration information;
generate the one of the vibration patterns that corresponds to the environment using the training vibration information; and
at least one of train or test the model using the one of the vibration patterns that corresponds to the environment.

6 . The non-transitory computer readable medium of claim 1 , wherein the instructions, when executed, cause the server to determine a type of the environment of the first mobile device when the first mobile device is in an idle mode.

7 . The non-transitory computer readable medium of claim 1 , wherein the instructions, when executed, cause the server to run the model by running at least one of a neural network or a machine learning model.

8 . A method comprising:
providing, by executing an instruction with a processor, first vibration information to a model, the first vibration information corresponding to a first vibration generated at a first mobile device when the first mobile device is in a state of non-use by a user, the model based on a plurality of vibration patterns that correspond to second vibrations measured by second mobile devices in different environments; identifying, using the model, one of the vibration patterns that corresponds to the first vibration information; determining, by executing an instruction with the processor, an environment of the first mobile device based on the one of the vibration patterns; and instructing, by executing an instruction with the processor, the first mobile device to modify a functionality of the first mobile device based on the environment.

9 . The method of claim 8 , wherein the identifying of the one of the vibration patterns includes running the model on a server.

10 . The method of claim 8 , wherein the identifying of the one of the vibration patterns is based on a confidence level that exceeds a threshold.

11 . The method of claim 8 , further including determining a type of the environment of the first mobile device when the first mobile device is in an idle mode.

12 . The method of claim 8 , further including receiving the first vibration information in response to a trigger event that triggers the first vibration, the trigger event to include an incoming voice call at the first mobile device or an incoming electronic message at the first mobile device.

13 . The method of claim 8 , wherein the determining of the environment includes determining the environment includes one or more of: a clothing surface, a container surface, a soft surface, a rigid surface, a hand surface, a leather surface, a wood surface, or a paper surface.

14 . The method of claim 8 , further including running the model by running at least one of a neural network or a machine learning model.

15 . A non-transitory computer readable medium comprising instructions which, when executed, cause a first mobile device to at least:
provide first vibration information to a model, the first vibration information corresponding to a first vibration generated at the first mobile device when the first mobile device is in a state of non-use by a user, the model to include a plurality of vibration patterns that correspond to second vibrations measured by second mobile devices in different environments; identify, using the model, one of the vibration patterns that corresponds to the first vibration information; determine an environment of the first mobile device based on the one of the vibration patterns; and modify a functionality of the first mobile device based on the environment.

16 . The non-transitory computer readable medium of claim 15 , wherein the instructions, when executed, cause the first mobile device to identify the one of the vibration patterns based on a confidence level that exceeds a threshold.

17 . The non-transitory computer readable medium of claim 15 , wherein the instructions, when executed, cause the first mobile device to modify a user preference or setting based on the environment of the first mobile device.

18 . The non-transitory computer readable medium of claim 15 , wherein the instructions, when executed, cause the first mobile device to modify the functionality of the first mobile device based on the environment to include one or more of: turning on or off a wireless module in the first mobile device, locking or unlocking the first mobile device, increasing or decreasing a volume of the first mobile device, turning on or off audio notifications for the first mobile device, or turning on or off vibratory notifications for the first mobile device.

19 . The non-transitory computer readable medium of claim 15 , wherein the instructions, when executed, cause the first mobile device to generate the first vibration information in response to a trigger event that triggers the first vibration, the trigger event to include an incoming voice call at the first mobile device or an incoming electronic message at the first mobile device.

20 . The non-transitory computer readable medium of claim 15 , wherein the instructions, when executed, cause the first mobile device to run the model by running at least one of a neural network or a machine learning model.

Assignees

• Intel Corp

Inventors

• Camacho Perez Jose
• Bernal Marin Miguel
• C Arevalo Mario Alfredo
• Cordourier Maruri Hector
• Cruz Vargas Jesus Adan
• Duenas De La Cruz Abraham
• Lopez Meyer Paulo
• Zamora Esquivel Julio

Classifications

• G06N7/01

  Probabilistic graphical models, e.g. probabilistic networks · CPC title

• G06N3/0499

  Feedforward networks · CPC title

• G06N3/09

  Supervised learning · CPC title

• H04M1/72454 Primary

  according to context-related or environment-related conditions · CPC title

• G01B17/08 Primary

  for measuring roughness or irregularity of surfaces · CPC title