Validation Optimisation using Machine Learning Techniques

Abstract

Integration and validation is the most vital part before releasing products to customers in Intel. The validation team qualifies the release based on multiple stages of validation on hardware and software stack. Bugs are raised after execution of test cases on each platform and so similar bugs arise which are filed by the user. There is a immediate concern on this and hence, many issues are closed as duplicates.The main objective is to find these similar bugs for each bug filed and thereby,debug efforts can be reused.Similar bugs are found by term based search using ElasticSearch ,a text search engine and neural network based search where context is considered.Using elasticsearch,scoring algorithms based on driver  versions and platform hierarchy are applied to rank the similar bugs. LSTM neural networks are also incorporated to predict duplicate bugs by considering context of the sentence and thereby, increasing accuracy.