Smart emulator for wearable devices

• US 10,162,736 B2
• Filed: 11/17/2016
• Issued: 12/25/2018
• Est. Priority Date: 11/17/2016
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Bhuiya, Subhajit, Ekambaram, Vijay, Padilla, Donald A., Pandit, Sushain
• Primary Examiner(s): Chavis, John Q
• Application Number:
  US15/353,786
• Publication Number:
  US 20180137034A1
• Time in Patent Office: 768 Days
• Field of Search: 717124
• CPC Class Codes: G06F 11/3664 Environments for testing or debugging software
• CPC Class Codes: G06F 11/3684 for test design, e.g. generating new test cases

Abstract

Input of a video file is received. The video file includes video of a representation of a wearable device. One or more motion vector data is determined based on the video file. One or more motion sensor data is generated based on the motion vector data. One or more test results are determined using the motion sensor data. The video file, the motion vector data, and the motion sensor data are stored.

Claims

1. A method for generating data for testing applications designed for wearable devices via an emulator, the method comprising:

receiving, by one or more computer processors, an input of a video file, wherein the video file includes video of a representation of a wearable device;

determining, by one or more computer processors, one or more motion vector data based on the video file;

generating, by one or more computer processors, one or more motion sensor data based on the determined one or more motion vector data, wherein generating the one or more motion sensor data based on the determined one or more motion vector data comprises;

determining, by one or more computer processors, an initial weight for each motion vector in the determined one or more motion vector data, wherein the initial weight is determined based on an approach selected from the group consisting of;

selecting equal weights, selecting random weights, user input, and historical data;

determining, by one or more computer processors, a final weight for each motion vector in the determined one or more motion vector data, wherein;

a machine-learning algorithm is used to determine the final weight for each motion vector in the determined one or more motion vector data; and

the machine-learning algorithm is run iteratively starting with the initial weight for each motion vector in the determine one or more motion vector data in order to determine the final weight; and

generating, by one or more computer processors, one or more rules that best fit the determined one or more motion vector data, wherein;

the generated one or more rules are based on the final weight for each motion vector in the determined one or more motion vector data; and

the generated one or more rules allow for conversion of the motion vector data to the one or more motion sensor data;

determining, by one or more computer processors, one or more test results using the generated one or more motion sensor data; and

storing, by one or more computer processors, the video file, the one or more motion vector data, and the one or more motion sensor data.

2. The method of claim 1, wherein the machine-learning algorithm is selected from the group consisting of:

artificial neural networks, decision trees, random forests, nearest neighbors, and the Apriori algorithm.

3. The method of claim 1, wherein generating the one or more rules that best fit the determined one or more motion vector data comprises:

mapping, by one or more computer processors, existing motion vector data to motion sensor data, wherein the mapping is an offline labelling process using cognitive analysis;

labelling, by one or more computer processors, new motion vector data with corresponding motion sensor values based on a mapping of the existing motion vector data to motion sensor data; and

generating, by one or more computer processors, one or more rules that define a relationship between motion vector displacement and motion sensor displacement based on the new motion vector data labelled with corresponding motion sensor values.

4. The method of claim 1, further comprising:

receiving, by one or more computer processors, an indication of an application to be tested;

retrieving, by one or more computer processors, the one or more motion sensor data associated with the application to be tested;

determining, by one or more computer processors, one or more test results based on the retrieved one or more motion sensor data; and

storing, by one or more computer processors, the one or more test results.

5. The method of claim 4, wherein the application to be tested uses one or more motion sensors included in the wearable device.

6. The method of claim 4, wherein the association of the one or more motion sensor data to the application to be tested is based on receiving the one or more motion sensor data that corresponds to one or more sensors included in the wearable device.

7. A computer program product for generating data for testing applications designed for wearable devices via an emulator, the computer program product comprising:

one or more computer readable storage media; and

program instructions stored on the one or more computer readable storage media, the program instructions comprising;

program instructions to receive an input of a video file, wherein the video file includes video of a representation of a wearable device;

program instructions to determine one or more motion vector data based on the video file;

program instructions to generate one or more motion sensor data based on the determined one or more motion vector data, wherein program instructions to generate the one or more motion sensor data based on the determined one or more motion vector data comprise;

program instructions to determine an initial weight for each motion vector in the determined one or more motion vector data, wherein the initial weight is determined based on an approach selected from the group consisting of;

selecting equal weights, selecting random weights, user input, and historical data;

program instructions to determine a final weight for each motion vector in the determined one or more motion vector data, wherein;

a machine-learning algorithm is used to determine the final weight for each motion vector in the determined one or more motion vector data; and

the machine-learning algorithm is run iteratively starting with the initial weight for each motion vector in the determine one or more motion vector data in order to determine the final weight; and

program instructions to generate one or more rules that best fit the determined one or more motion vector data, wherein;

the generated one or more rules are based on the final weight for each motion vector in the determined one or more motion vector data; and

the generated one or more rules allow for conversion of the motion vector data to the one or more motion sensor data;

program instructions to determine one or more test results using the generated one or more motion sensor data; and

program instructions to store the video file, the one or more motion vector data, and the one or more motion sensor data.

8. The computer program product of claim 7, wherein the machine-learning algorithm is selected from the group consisting of:

artificial neural networks, decision trees, random forests, nearest neighbors, and the Apriori algorithm.

9. The computer program product of claim 7, wherein program instructions to generate the one or more rules that best fit the determined one or more motion vector data comprise:

program instruction to map existing motion vector data to motion sensor data, wherein the mapping is an offline labelling process using cognitive analysis;

program instruction to label new motion vector data with corresponding motion sensor values based on a mapping of the existing motion vector data to motion sensor data; and

program instruction to generate one or more rules that define a relationship between motion vector displacement and motion sensor displacement based on the new motion vector data labelled with corresponding motion sensor values.

10. The computer program product of claim 7, further comprising program instructions stored on the one or more computer readable storage media, to:

receive an indication of an application to be tested;

retrieve the one or more motion sensor data associated with the application to be tested;

determine one or more test results based on the retrieved one or more motion sensor data; and

store the one or more test results.

11. The computer program product of claim 10, wherein the application to be tested uses one or more motion sensors included in the wearable device.

12. The computer program product of claim 10, wherein the association of the one or more motion sensor data to the application to be tested is based on receiving the one or more motion sensor data that corresponds to one or more sensors included in the wearable device.

13. A computer system for generating data for testing applications designed for wearable devices via an emulator, the computer system comprising:

one or more computer processors;

one or more computer readable storage media; and

program instructions stored on the one or more computer readable storage media for execution by at least one of the one or more computer processors, the program instructions comprising;

program instructions to receive an input of a video file, wherein the video file includes video of a representation of a wearable device;

program instructions to determine one or more motion vector data based on the video file;

program instructions to generate one or more motion sensor data based on the determined one or more motion vector data, wherein program instructions to generate the one or more motion sensor data based on the determined one or more motion vector data comprise;

program instructions to determine an initial weight for each motion vector in the determined one or more motion vector data, wherein the initial weight is determined based on an approach selected from the group consisting of;

selecting equal weights, selecting random weights, user input, and historical data;

program instructions to determine a final weight for each motion vector in the determined one or more motion vector data, wherein;

a machine-learning algorithm is used to determine the final weight for each motion vector in the determined one or more motion vector data; and

the machine-learning algorithm is run iteratively starting with the initial weight for each motion vector in the determine one or more motion vector data in order to determine the final weight; and

program instructions to generate one or more rules that best fit the determined one or more motion vector data, wherein;

the generated one or more rules are based on the final weight for each motion vector in the determined one or more motion vector data; and

the generated one or more rules allow for conversion of the motion vector data to the one or more motion sensor data;

program instructions to determine one or more test results using the generated one or more motion sensor data; and

program instructions to store the video file, the one or more motion vector data, and the one or more motion sensor data.

14. The computer system of claim 13, wherein the machine-learning algorithm is selected from the group consisting of:

artificial neural networks, decision trees, random forests, nearest neighbors, and the Apriori algorithm.

15. The computer system of claim 13, wherein program instructions to generate the one or more rules that best fit the determined one or more motion vector data comprise:

program instruction to map existing motion vector data to motion sensor data, wherein the mapping is an offline labelling process using cognitive analysis;

program instruction to label new motion vector data with corresponding motion sensor values based on a mapping of the existing motion vector data to motion sensor data; and

program instruction to generate one or more rules that define a relationship between motion vector displacement and motion sensor displacement based on the new motion vector data labelled with corresponding motion sensor values.

16. The computer system of claim 13, further comprising program instructions stored on the one or more computer readable storage media, to:

receive an indication of an application to be tested;

retrieve the one or more motion sensor data associated with the application to be tested;

determine one or more test results based on the retrieved one or more motion sensor data; and

store the one or more test results.

17. The computer system of claim 16, wherein the application to be tested uses one or more motion sensors included in the wearable device.