Method for user context recognition using sound signatures

A non-transitory computer-readable recording medium storing a program to implement a method comprising:

• recording, using a mobile device, a sound sample received by a microphone of the mobile device based on a trigger stimulus;
• collecting available hardware and software macro context data from the mobile device during the recording the sound sample;
• extracting, by at least one processor, a sound signature from the recorded sound sample;
• performing a sound comparison of the extracted sound signature to reference sound signatures stored in a sound database;
• checking, based on the sound comparison, whether the extracted sound signature was recognized in the sound database, and either using the recognized sound signature as an input or using the extracted sound signature as the input and updating the sound database with the extracted sound signature;
• performing a logical association between the input and the collected macro context data as micro context;
• performing a context comparison between the micro context and a reference context stored in a context database;
• checking, based on the context comparison, whether the micro context was recognized in the context database, and either setting the recognized micro context as a result or setting the micro context as the result and updating the context database with the micro context;
• providing the result to a context-aware application in the mobile device such that the application uses the result during an execution of the application.

An apparatus comprising:

• at least one memory configured to store instructions;
• and
• at least one processor configured to execute the stored instructions to implement a method comprising:
• recording, using a mobile device, a sound sample received by a microphone of the mobile device based on a trigger stimulus;
• collecting available hardware and software macro context data from the mobile device during the recording the sound sample;
• extracting, by the at least one processor, a sound signature from the recorded sound sample;
• performing a sound comparison of the extracted sound signature to reference sound signatures stored in a sound database;
• checking, based on the sound comparison, whether the extracted sound signature was recognized in the sound database, and either using the recognized sound signature as an input or using the extracted sound signature as the input and updating the sound database with the extracted sound signature;
• performing a logical association between the input and the collected macro context data as micro context;
• performing a context comparison between the micro context and a reference context stored in a context database;
• checking, based on the context comparison, whether the micro context was recognized in the context database, and either setting the recognized micro context as a result or setting the micro context as the result and updating the context database with the micro context;
• providing the result to a context-aware application in the mobile device such that the application uses the result during an execution of the application.