Abstract: Methods and apparatuses are described for automated testing of mobile devices. A server establishes a connection with a client device via a high-latency connection. The server receives input from the client device comprising (i) a selection of mobile devices for testing and (ii) a selection of a test interaction. The server generates predicted interactions for each of the selected mobile devices using historical device interaction data. The server converts the predicted interactions into test scripts, each test script formatted for use with one of the selected mobile devices. The server deploys each test script for execution on the corresponding mobile device, and transmits results from the test script executions to the client device.

Abstract: Methods and apparatuses are described for automated testing of mobile devices. A server establishes a connection with a client device via a high-latency connection. The server receives input from the client device comprising (i) a selection of mobile devices for testing and (ii) a selection of a test interaction. The server generates predicted interactions for each of the selected mobile devices using historical device interaction data. The server converts the predicted interactions into test scripts, each test script formatted for use with one of the selected mobile devices. The server deploys each test script for execution on the corresponding mobile device, and transmits results from the test script executions to the client device.

Abstract: A computer-implemented method of training, using a computer log file, an application error prediction engine to identify one or more application errors includes parsing the computer log file into a plurality of data sets. Each data set is associated with a unique computing session having a session identifier and ending in an application or. The method also includes extracting, from each data set, values for a specified set of parameters in each data set. The method also includes encoding the extracted values for each data set into a corresponding data structure. The method also includes generating, for each data structure, a corresponding vector, the corresponding vectors collectively forming a matrix. The method also includes calculating, based on the matrix, a set of clusters, each cluster corresponding to a known error type, the set of clusters used to create a model used to identify new error types.

Abstract: A computer-implemented method of training, using a computer log file, an application error prediction engine to identify one or more application errors includes parsing the computer log file into a plurality of data sets. Each data set is associated with a unique computing session having a session identifier and ending in an application or. The method also includes extracting, from each data set, values for a specified set of parameters in each data set. The method also includes encoding the extracted values for each data set into a corresponding data structure. The method also includes generating, for each data structure, a corresponding vector, the corresponding vectors collectively forming a matrix. The method also includes calculating, based on the matrix, a set of clusters, each cluster corresponding to a known error type, the set of clusters used to create a model used to identify new error types.