Why Service Management is embracing AI and Machine Learning Dean Clayton, SMAX Product Manager Max, SMAX Virtual Agent 13 August 2019
The Face of AI OR
Agenda Principles of AI and Machine Learning Research - Automation, AI, and Analytics: Reinventing ITSM Applying AI and Machine Learning to Service Management EMA, Autom omation on, AI and nd Ana nalytics: s: Reinv nvent nting ITSM, SM, rese search h Sum ummary Repo port April 2019
Principles of AI and Machine Learning
Terminology Artificial Intelligence Intelligence exhibited by machines or software Machine Learning Smart programs can learn from examples Representation/Feature Learning Transformation of raw data input to a representation Deep Learning One architecture to rule them all Neural Networks ( ANNs ) Computing models inspired by biological neural networks Simulation of human thought processes in a computerized Cognitive computing model
Most Common Machine Learning Tasks Classification Smart Ticket classification Regression Smart Change Analytics, Number of Incident projection Clustering Hot Topic clustering Transcription OCR used in Smart Ticket classification Machine translation On the fly translation Structured output Sentiment Analysis, User Profiling, Document labelling Anomaly detection Major Incident detection Synthesis and sampling Text2Voice, Virtual conversation response
Machine Learning Algorithms Maps an input to an output based Supervised learning Virtual Agent Intent training on example input-output pairs. Hot Topic analysis, Find similar cases, Infers a function that describes the Unsupervised learning suggest offerings based on past requests structure of "unlabeled" data with similar descriptions Use labelled and unlabeled data for Smart Ticketing - automatic training Semi-supervised learning training sample selection Use feedback to the program's ‘Helpful’ vs. ‘Not - Helpful’, feedback Reinforcement learning actions in a dynamic environment provided to a Virtual Agent flow for training
Research - EMA - Automation, AI, and Analytics: Reinventing ITSM EMA, A, Automation, AI I an and Analytics: Rei einventing IT ITSM, , res research Summary Report April 2019 019 www.microfocus.com/en-us/assets/it-operations-management/automation-ai-and-analytics-reinventing-itsm
• When you think of AI, what comes to mind?” • AI/analytics and automation findings • Obstacles in AI/analytics and automation • Top AI/analytic initiative
• When you think of AI, Machine learning 1. Big data what comes to mind?” 2. AI bots 3. • AI/analytics and Integrated automation 4. automation findings Virtual agents 5. • Obstacles in Analytics specific to business 6. performance AI/analytics and Predictive analytics 7. automation AIOps 8. • Top AI/analytic Behavioural analytics 9. initiative 10. Asset and cost optimization analytics EMA, Automation, n, AI and nd Ana nalytics: Reinv nventing ITSM, research Sum ummary Repo port Apr pril 2019
Enhanced levels of ITIL adoption • When you think of AI, strongly correlated with success in what comes to mind?” AI/analytics and automation adoptions • AI/analytics and IT productivity, cost savings, and automation findings increased end-user/customer • Obstacles in satisfaction show a strong presence in benefits achieved AI/analytics and from AI/ analytics and automation automation. • Top AI/analytic Cost savings and OpEx efficiencies across and beyond IT dominated initiative as leading drivers for AI/analytics and automation initiatives. EMA, Automation, n, AI and nd Ana nalytics: Reinv nventing ITSM, research Sum ummary Repo port Apr pril 2019
• When you think of AI, People training or skillset issues (e.g., lack of effective what comes to mind?” skillsets). • AI/analytics and Process and procedures automation findings issues (e.g., resistance to change) and changes to • Obstacles in processes AI/analytics and Technology -specific issues automation (e.g., lack of integration with current tools), resource • Top AI/analytic issues (e.g., cost budgeting initiative issues) and cultural/political. EMA, Automation, n, AI and nd Ana nalytics: Reinv nventing ITSM, research Sum ummary Repo port Apr pril 2019
• When you think of AI, what comes to mind?” • AI/analytics and automation findings • Obstacles in AI/analytics and automation • Top AI/analytic initiative EMA, Automation, n, AI and nd Ana nalytics: Reinv nventing ITSM, research Sum ummary Repo port Apr pril 2019
Applying AI and Machine Learning to Service Management
Typical Service Management issues ISSUE ROOT CAUSE Poor end user experience Asking too much information to “feed the system” Search hell No ontology for search Garbage in – Garbage out Bad input leads to bad decision Dark data Text and attachments not used for analysis (Not) moving from incident to problem No problem isolation process Service desk “technology platform” instead of semantic CSI mirage layer
Micro Focus’s "Three Laws of AI/Machine Learning" use case Built Automated and business Machine as a core outcomes Learning capability driven
Our Approach: Machine Learning & the Service Desk Business outcomes for key stakeholders Business user Agent Supervisor Process owner Productivity Process optimization Self-sufficiency Shorter processing KPI improvement Reduction of tickets time
User input Smart ticketing User improvement Enabling technologies ▪ Reduce the end user ▪ Optical Character input to the absolute Recognition (OCR) minimum, avoid “guess ▪ Supervised Machine data” required to feed Learning: the system - Training ▪ Infer as much information from user - Testing context – auto- categorization ▪ Allow for visual input
Virtual agent Natural Language Processing with virtual agents User improvement Enabling technologies ▪ Machine Learning ▪ Provide a human-like user interface 24x7 ▪ Chatbot ▪ Get rich contextual ▪ Natural Language and relevant answers Processing to questions, not pre- made ones
Search ITSM ontology for search Agent improvement Enabling technologies ▪ Search engine ▪ Provide strong typed search ▪ Semantic layer ▪ Pre-built common actions ▪ Filter search on ITSM artifact types (incident, knowledge, request, …)
Text analysis Context-sensitive meta-data recognition Agent Enabling technologies improvement ▪ Machine learning ▪ Automatic ▪ Semantic layer recognition of meta-data from text ▪ Contextual access to process artifacts without re-keying
Text analysis Text analysis for pattern clustering Agent improvement Enabling technologies ▪ Machine learning ▪ Identify recurring topics in patterns ▪ Bayesian algorithm ▪ Groups related artifacts to a theme ▪ Trigger common related actions
Prescriptive analytics Towards prescriptive process improvement Organizational Enabling technologies improvement ▪ Machine learning • Use of KPI library and related ▪ Semantic layer for process metrics KPIs • Suggest concrete actions to improve process KPIs in defined library • Assess process performance at varying degrees of granularity
Introducing Max! EFFORTS VIRTUAL AGENT: TAKE AUTOMATIC TASK ▪ Reply to frequently asked questions Virtual agent Live agent ▪ Help troubleshoot and solve common problems ▪ Help end user to fill in offering and support requests 30 LIVE AGENT: TAKE COMPLEX TASK ▪ Resolve complex problems 70 ▪ Submit requests on behalf of end user ▪ And more…
www.microfocus.com 25
Sampling of AI/ML in SMAX ▪ Smart Virtual Agent ▪ Smart Ticketing : ▪ Word-Vector Embedding for Natural ▪ Naive Bayes for Classification Language Modelling ▪ SVM and Neural Networks for OCR ▪ SVM for Indent Classification ▪ Anomaly Detection for Adaptive ▪ Naive Bayes for Entity Extraction Training ▪ CI Detection : ▪ Information Theory ▪ Naive Bayes ▪ Hot Topics : ▪ Information Theory ▪ Naive Bayes for Clustering ▪ CMS Automatic Software Recognition : ▪ LDA for Clustering ▪ Naive Bayes for Entity Extraction ▪ Information Theory ▪ Gradient Boost Decision Trees for ▪ Smart Search, Smart Email : Classification ▪ Naive Bayes ▪ Best Matching Ranking Function for Classification
Recommend
More recommend
