SRE_Chatbot_workflow.pptx
•Download as PPTX, PDF•
0 likes•6 views
Hello! My name is Claude. How can I help you? User: Hi Claude! I'm looking for information on chatbots.
Report
Share
SRE_Chatbot_workflow.pptx
- 2. Chatbot: Chatbot play important role because they serve as a guiding factor for both the brand and the users. Chatbots may be used to give online service, place purchases for clients, and help resolve customer complaints. Once the goal has been established, the organization may concentrate on personalizing the bot's communication pattern.
- 3. • Despite technology changing the way of interaction, the need for supportive bonds and conversation to address queries and share thoughts quickly is still considered to be vital. • Chatbots are the main formula for our rescue…! • Several companies today are investing in this conversation-based platform to provide the users with accurate information. Chatbot (contd;)
- 5. How our Chatbots work? Our Chatbots need the following to respond to an user question: • What (skill) is the user asking for? (Intent) • Did the user mention any specific information? (Slots) • What should the bot ask to get further details from the user? (Dialog flow/Maintaining Context) • How to fulfil the user request? (Action/Response/Fulfilment)
- 6. AI + SRE Ops:
- 7. AI + SRE case scenario -1 • User Utterance: “I am facing copy paste error”. • Chatbot: “Please use the blue eraser icon to mitigate copy/paste issue”. • User Utterance: “I don’t see blue eraser icon”. • Chatbot: “Please enter caseid/documented”. • Chatbot: “Your incident number ”INCxxxxx” is created and will be assigned shortly”. Intent •Content Issue Slots •Caseid – AR-xxxx •App – CAP-Console •Priority- P1 Dialog flow •Back and forth communication between bot and user Action/Fulfillment •Bot provides final results in the form of a link where case details are already entered and submitted.
- 8. AI + SRE case scenario -3 • User Utterance: “Unable to upload docs in RPM”. • Chatbot: “Hi, this Issue can be fixed on reposting the release message”. • Chatbot : “Do you want to open a ticket for this”. • User Utterance: “Yes”. • Chatbot: “Please enter jobid”. • Chatbot: “Your incident number ”INCxxxxx” is created and will be assigned shortly”. Intent •RDR Issue Slots •Jobid – PFR-xxx2 •App – RPM •Priority- P1 Dialog flow •Back and forth communication between bot and user Action/Fulfillment •Bot provides final results in the form of a link where case details are already entered and submitted.
- 9. AI + SRE case scenario -2 • User Utterance: “I can't seem to find ESG section on PR”. • Chatbot: “Please go to Section manager and enable ESG section”. • User Utterance: “Section Manager is disabled, can’t click”. • Chatbot: “Please enter caseid/documented”. • Chatbot: “Your incident number ”INCxxxxx” is created and will be assigned shortly”. Intent •Content Issue Slots •Jobid – PFR-xxx2 •App – RPM •Priority- P1 Dialog flow •Back and forth communication between bot and user Action/Fulfillment •Bot provides final results in the form of a link where case details are already entered and submitted.
- 10. Chatbot Program Workflow: Read csv / Snow SVM/CNN TF/IDF vectorization Lemmatization Accuracy check Stop words removal Feature Selection Extraction AWS Update CSV/.dat
- 11. Chatbot classification used for Intent prediction: Support Vector Machine (SVM) • SVMs maximize the margin around the separating hyperplane. A.k.a. large margin classifiers • The decision function is fully specified by a subset of training samples, the support vectors. • Solving SVMs is a quadratic programming problem • Seen by many as the most successful current text classification method* Support vectors Maximizes margin Narrower margin
- 12. Sample Python Bot interaction: