developing ai-powered - dtw.tmforum.org · 16/05/2018 · nokia software andy fruhling developing...
TRANSCRIPT
© 2018 TM Forum | 1
Developing AI-powered conversational interfaces
Standards Project Director, Orange
Sophie Nachman May 16 2018 DTW Nice
© 2018 TM Forum | 2
Orange Group : facts and figures
273 million of customers worldwide – 41 billion € in 2017 - 152 000 employees - 31 Dec. 2017
Orange is one of the world’s leading telecommunications operators with sales of 41 billion euros in 2017 and 152,000 employees worldwide at 31 December 2017, including 93,000 employees in France. Present in 29 countries, the Group has a total customer base of 273 million customersworldwide at 31 December 2017, including 211 million mobile customers and 20 million fixedbroadband customers. Orange is also a leading provider of global IT and telecommunication services to multinational companies, under the brand Orange Business Services. In March 2015, the Group presented its new strategic plan “Essentials2020” which places customer experience at the heart of its strategy with the aim of allowing them to benefit fully from the digital universe and the power of its new generation networks.
Orange is listed on Euronext Paris (symbol ORA) and on the New York Stock Exchange (symbol ORAN).
For more information on the internet and on your mobile:
www.orange.com , www.orange-business.com or to follow us on Twitter: @orangegrouppr and @orange .
Orange is listed on the NYSE Euronext Paris (symbol ORA) and on the New York Stock Exchange (symbol ORAN).
For more information on the internet and on your mobile: www.orange.com, www.orange-business.com, livetv.orange.com or to follow us on Twitter: @orange, @orangegrouppr, @orangebusiness
© 2018 TM Forum | 3
Orange :Essentials 2020, strategic ambition
Towards an unmatched customer experience
© 2018 TM Forum | 4
AI powered conversational interfaces : Chatbot architecture
AI empowers NLU and Speech to text
© 2018 TM Forum | 6
Research project Catalyst in open innovation mode – TM Forum delivering enhanced customer experience through intelligent robots
© 2018 TM Forum | 9
• A chatbot (also known as talkbot, IM bot, chatterbot, interactive agent or Artificial conversational entity) is a computer program or an artificial intelligence which conducts a conversation via auditory or textual methods. Such programs are often designed to convincingly simulate how a human would behave as a conversational partner. Chatbotsare typically used in dialog systems for various purposes including customer care, optimizing sales, answering FAQ’s, educational sessions, entertainment. From Wikipedia
• Mosts chatbots are accessed via messaging apps such as FB messenger, Wechat, Whats’sapp, Viber, or via organizations’s apps and websites
• Or via Virtual assistants such as Amazon Alexa, Google Assistant, and soon: Orange Djingo
Chatbots acting through messaging apps , through apps or web sitesVirtual assistants
• Djingo is the intelligent assistant from Orange, controlled by voice or text. It offers an easy and intuitive way to navigate Orange TV, manage your connected home, make a call or send a SMS, or access lots of other services. Applying true AI, Djingolearns from its users to provide ever more relevant answers. ‘OK Djingo?’From orange.com web site
© 2018 TM Forum | 10
Orange digital guidelines for conversational User Interfaces – UIa ‘human inside’ approach to AI powered conversational interfacesPrinciples of designing Virtual Assistants &chatbot interactions
• Virtual assistant and chatbot are the new media of AI applied as direct communication to Orange customers, Despite plenty of excitement it is still early days far from its full potential as the major customer touchpoint.
• Chatbots offer a targeted and personal engagement with customers
• Both for text user interfaces and for voice user interfaces
• Rules such as Tone of voice
• To ensure consistent experiences for Orange customers any device any channel
Orange ethics – GDPR compliance – Trust
Honesty – to guaranty privacy of customers
• Different avatars to be used for chatbots and for human messaging to clearly differentiate them
© 2018 TM Forum | 11
PoC from CatalystPhygital store DTW 2018
GDPR May 25 2018
Trust party for customers – from GDPR regulation towards privacy customer dashboard
© 2018 TM Forum | 13
VP, Digital Experience Portfolio
Nokia Software
Andy Fruhling
Developing Successful AI-Powered Conversational
Interfaces
© 2018 TM Forum | 1414
End-customer expectations have changed
• Digital services• Empowered• Buy on own terms• Instant
gratification• Personalized• Contextual• Omni-channel• Rent vs. buy
© 2018 TM Forum | 15
One issue can have multiple solutions
The need for experts
Technology breadth
High customer effort
Customer effort is too high - asked to do too much to fix the problem
Customer care issues can be driven by a number of different network, operations or business technology domains
Requires a lot of experts with very detailed technical knowledge to improve just one step in a workflow
Root cause analysis is complex due to different technology domains; agents have to sort through many workflows to find cause
Digital service provider (DSP) challenges for customer care
© 2018 TM Forum | 16
Complex troubleshooting for DSPs leads to poor customer experience
Remediation process • Multiple causes• Many workflow paths• Requires technical expertise
Customer issue• My internet is slow• My home Wi-Fi isn’t working• My video is buffering
Technical environment• Different services • Multiple systems and silos• Many vendors
© 2018 TM Forum | 17
Chatbots are becoming an increasingly important part of the digitalcustomer care experience
© 2018 TM Forum | 18
Zero-touch care due to proactive issue remediation
Full autonomous care
Customer solves their own problems
Selfcare
Accelerate resolution when customer calls
Assistedcare
+70%
Empower “human” touch to solve issues faster
Augmentedcare
Humanoid interface deflects calls from human
Enhanced omni-channel care
Machine-learning algorithms enable bots to continuously learn and expand capability
Decreasing customer and operator effort
Issue resolution
The role of bots in customer care
© 2018 TM Forum | 19
Omni-channel support
Machine learning required at many levels
Multi-language support
Supports multi-conversational interfaces
Key elements of a chatbot platform for DSPs
© 2018 TM Forum | 20
Benefits
• Customers can use their preferred natural language channels 24/7
• Two-way conversational support over one-way static technology (e.g. Web, IVR)
• No need to repeat or to do too much to make the fix happen
• Improve NPS & Customer Effort Score
• Fully automate the high-volume low-complexity use cases
• Empower tier-1 agents for high-touch interactions and white-glove customer care for time-sensitive promotions
For customers For digital service providers
© 2018 TM Forum | 21
Summary • Today’s digital consumers expect a positive customer care experience with their service provider across any channel in real time
• A key challenge in meeting this need is the ability to quickly offer the right resolution to an issue given the complexity of the technical environment and the many paths an agent can take to solve it
• Chatbot platforms provide an opportunity to manage high volume, low complexity issues, leaving agents free to manage more complex issues and even upsell
© 2018 TM Forum | 29
THE BOOK OF WORDS
Valance (noun)
Prosody(noun)
lɪŋˈɡwɪstɪksLemma (noun)
n-grams
word-for-word
ف َحْرفاً بَِحرْ
wort-zum-wort
逐字地,一字不差地
mot-á-mot palabra-por-palabra