Microsoft Technology Licensing, LLC

Poornima Muthukumar

Muiris Woulfe

Yuanyuan Dong

Tatiana Shubin

Sergiy Dubynskiy

Sandhya Shahdeo

A method and system for analyzing a proximity between a first user population and a second user population includes receiving a request to perform a proximity analysis between the first user population and the second user population, accessing data related to the first user population and the second user population, providing the data related to the first user population and the second user population as input to a machine-learning (ML) model for analyzing the data to determine the proximity between the first user population and the second user population, receiving from the ML model as an output at least one of a composite proximity score between the first user population and the second user population, and providing display data relating to the output to a visualization mechanism for display. The composite proximity score may be calculated based on multiple characteristics and/or comparison metrics.

System and method of determining proximity between different populations

A machine learning model can be trained to infer the probability of the presence of categories of a software bug in a source code file. A bug tracker can provide information concerning the category to which a software bug belongs. The bug data supplied to a machine learning model for inferring the presence of particular categories of bugs can be filtered to exclude a specified category or categories of bugs. Information including but not limited to organizational boundaries can be inferred from the category of bugs present in a body of source code. The inferred organization boundaries can be used to generate team-specific machine learning models.

Bug categorization and team boundary inference via automated bug detection

Information concerning software bugs including bug detection, bug prediction data and/or historical bug data can be used to determine whether it is safe to commit, integrate, deploy and/or deliver a software change. If the change is deemed unsafe, the change can be rejected automatically. Alternatively, the change can proceed following approval by an administrator, supervisor, implementer, manager and/or other designated approval mechanism. Actions taken to override a block can be recorded along with information concerning failed deployments and/or deliveries, a higher than normal customer failure rate after deployment and/or delivery or through manual data entry.

Engineering system robustness using bug data

For each detected bug, historical code with similar characteristics and bug corrections from a historical bug dataset can be displayed in a source code editor. Relevant training and/or testing data can be found by comparing an internal representation of the code under development with an internal representation of the original buggy code in the historical bug dataset. Training and/or testing data that is relevant to the current code can be distinguished from irrelevant training and/or testing data by determining that the code syntax tokens from the current and historical data overlap to at least a specified percentage. Code can be devolved into a set of metrics. The degree of overlap between the metric sets can be determined. If a computed risk factor for the bug correction meets or exceeds a specified threshold, the bug correction can be automatically applied. Additional testing can be automatically performed on and/or added to the corrected code.

Growing community of inventors

Seattle, WA, United States of America

Poornima Muthukumar