Who is the Client

A US-based Fortune 500 departmental store chain with more than 1000 stores across the states, they are bringing stylish clothing for the entire family since decades now.

The Challenge

The client runs a vast e-commerce website, and its success depends on customer satisfaction attributed to the shorter resolution time. Infrastructure, platform, and environment issues resolution required manual creation of tickets for the NOC team in incident management tools.

The manual process required command inputs, leading to an increase in the mean time to resolution (MTTR) and a slower root-cause analysis (RCA). Often, these requests would repeat over time with or without different parameters.

The objective was to automate the process for better resource utilization and increased environment stability, and eventually reduce the number of tickets raised.

The Solution

GSPANN’s Advanced Analytics team leveraged the Zeolite’s framework to build the virtual assistant leveraging Natural Language Processing (NLP) for natural conversations and Machine Learning (ML) for self-healing. The idea was to create a virtual assistant that could understand the request and auto-correct or auto-respond to the issue or the question raised.

The chatbot allows the users to make simple queries in human language. GSPANN identified chatbot use cases and integrated Zeolite with the client’s communication interface, which was Cisco WebEx. The chatbot even incorporated a security layer to comply with the client’s security protocols for data security and access.

The chatbot was deployed on the client’s virtual servers behind the security firewalls and ran in the client’s virtual private cloud. Zeolite’s core algorithms were used to determine user intentions, recognize entities, and execute tasks.

The chatbot provides the convenience of a human-like interaction. It has a menu-driven flow and prompts for missing information when performing a task. It is integrated with Cisco’s WebEx teams through webhooks and custom APIs. The chatbot also has an authorization and authentication layer so that only the client’s employees have access to it.

Business Impact

  • Manual creation of 1,600+ service tickets per month for fetching the status and executing basic tasks was reduced by 40% with the chatbot.
  • There has been 80% reduction in resolution time and 40% reduction in RCA time since the information is now readily available.
  • The client can now use the technical resources for other intelligent tasks.
  • Comparison Stats – Manual Vs. Zeolite (in mins)
    • Environment Changes Identification – 30 Vs. 1 (or less)
    • System/Services Health Check – 15 Vs. 1 (or less)
    • Configuration Changes – 10 Vs. 1 (or less)
    • Fetch Docker Logs – 5 Vs. 1 (or less)
    • Text Execution – 10 Vs. 1 (or less)

Technologies Used

Zeolite. An AIOps framework that utilizes artificial intelligence and machine learning to detect potential failures automatically
Jupyter. An open-source web application that allows you to create and share documents containing live code, equations, and visualizations
Control M. It makes it easy to build, define, schedule, manage, and monitor production workflows, ensuring visibility, reliability, and improving SLAs
Okta SSO. Simplify password management for employees with this single sign-on solution from Okta
Languages. Python and Linux
Google Cloud Platform. A suite of cloud computing services that runs on the same infrastructure that Google uses internally for its end-user products

Related Capabilities

Utilize Actionable Insights from Multiple Data Hubs to Gain More Customers and Boost Sales

Unlock the power of data insights buried deep within your diverse systems across the organization. We empower businesses to effectively collect, beautifully visualize, critically analyze, and intelligently interpret data to support organizational goals. Our team ensures good returns on the big data technology investment with effective use of the latest data and analytics tools.

Do you have a similar project in mind?

Enter your email address to start the conversation