Tata Consultancy Services Limited

Vikrant Vikas Shimpi

Maitreya Natu

Vaishali Paithankar Sadaphal

Neha Behl

Deepa Vaidyanathan

Vaishali Shashank Kulkarni

Satya Narayana Samudrala

Monika Bhave

Parag Agrawal

Siddartha Kshirsagar

Priyadarshi Rai

Data inaccuracy and insufficiency are critical aspects to be analyzed to improve batch predictions, specifically in context of SLA jobs as they are foremost in affecting deliverables. Embodiments of the present disclosure provide a method and system for enhancing batch predictions by localizing jobs contributing to time deviation and generating fix recommendations by fixing data inaccuracy and insufficiency. The term fix recommendation refers to recommending a list of plausible fixes to identified causes that reduce batch prediction errors enhancing accuracy of predictions. The localization is performed by bottom-up traversing of a batch graph representing a batch process, if the batch process has a Service level Agreement (SLA) job, by narrowing down to the SLA job that has end time inaccuracies. The localization enables identifying the origin or real contributors and root cause analysis is performed for the localized jobs to generate effective fix recommendations by fixing data inaccuracy and insufficiency.

Enhancing batch predictions by localizing jobs contributing to time deviation and generating fix recommendations

This disclosure relates generally to method and system for predicting batch processes. Conventional batch schedulers provide a single point of control for defining and monitoring background executions in a distributed network. The method of the present disclosure obtains a set of batch jobs from one or more users to generate a set of batch graphs by deriving a metadata. Further, a set of batch models is generated for the set of batch graphs. The set of batch models includes at least one of a forecasting model, a job-job regression model, and a job-workload regression model. Further, a batch job schedule is generated for the set of batch graphs to predict a revised batch job schedule with a real time feed and the set of batch models. Additionally, a proactive notification is sent to each user alarming one or more unexpected delays indicating the revised batch job schedule.

Method and system for predicting batch processes

A trouble ticket may contain various details of an observed issue and information of the actual issue which is hidden in the trouble ticket description along with other information. Embodiments herein describe an algorithm of algorithms (AoA) layer approach for extracting issues from trouble ticket descriptions. The method identifies the type of trouble ticket whether it is machine generated or user generated trouble tickets and accordingly selects the appropriate algorithm for issue extraction. It selects a relevant algorithm for the machine generated trouble tickets, and user generated trouble tickets based on trouble ticket data properties, historical performance, and a user feedback. It identifies right mix of columns from a service catalog to be used for matching based on presence of weighted keywords in the input data and identifies high-weighted keywords from input data descriptions and compares them with selected columns from catalog to generate accurate matches with their similarity score.

System and method for extracting issues based on trouble ticket mining

Described herein are a method and a system for extracting issues based on ticket mining. In one implementation, a plurality of tickets comprising descriptions of the issues in computing systems are received. The received descriptions are then cleaned by removing unwanted details. Upon cleaning, the clean descriptions are mapped with descriptions stored in service catalog data to obtain unmapped clean descriptions. In an example, the unmapped clean descriptions include one of user-generated descriptions, system-generated descriptions, and both the user-generated descriptions and the system-generated descriptions. For the user-generated descriptions; the issues are extracted by pre-processing the user-generated descriptions, determining keywords from the processed unmapped clean descriptions, constructing n-grams of keywords from the extracted keywords, and extracting the n-grams of keywords as the issues present in the computing systems.

Issue extraction based on ticket mining

Growing community of inventors

Pune, India

Vikrant Vikas Shimpi