Emc IP Holding Company LLC

Haim Halbfinger

Omer Sagi

Nimrod Milo

Alon Grubshtein

Gilad Braunschvig

Ronen Halsadi

Danny Croitoru

A machine learning-based recommendation system is provided for root cause analysis of service issues. An illustrative method of a machine learning system comprises extracting features from service issue investigation log sets corresponding to previously considered service issues; generating representations for the service issue investigation log sets based on the corresponding extracted features; and storing the representations in a knowledge base. In conjunction with obtaining an additional service issue investigation log set, the illustrative method generates a representation of the additional service issue investigation log set; identifies representations previously stored in the knowledge base as candidate service issues related to the additional service issue based on pairwise probabilities indicating whether the additional service issue is related to at least a subset of the previously considered service issues; and presents information characterizing the service issue investigation log sets corresponding to respective ones of the identified representations.

Machine learning-based recommendation system for root cause analysis of service issues

A method in one embodiment comprises extracting features from each of a plurality of software investigation log sets, generating representations for respective ones of the software investigation log sets based at least in part on the corresponding extracted features, and storing the representations in a knowledge base. In conjunction with obtaining at least one additional software investigation log set, the method generates a representation of the additional software investigation log set, identifies one or more of the representations previously stored in the knowledge base that exhibit at least a specified similarity to the representation of the additional software investigation log set in accordance with one or more statistical models, and presents information characterizing the one or more software investigation log sets corresponding to respective ones of the identified one or more representations in a user interface. The method is illustratively implemented in a machine learning system of a processing platform.

Similarity-based retrieval of software investigation log sets for accelerated software deployment

Growing community of inventors

Raanana, Israel

Haim Halbfinger