2019 DevDay DUET: How To Make AI Reservation Agent via Telephony > KyoungTae Doh > NAVER Biz AI / DUET TF

DUET = Project AiCall = Product

No content

Why We Started This Project

Does anyone call the restaurant to make reservations these days?

Which device do people use… …when making reservations?

65 vs 35

Reality != Guesses, Assumptions Meet the user. Take a different approach. Data. Data. Data.

Before development began… We just called… So many times

1. People are not good at answering phones • Human error is a factor in telephony • Not well trained for answering calls • We are not aiming for the sky Restaurants want to cut costs on answering calls

AI Speaker pattern - Command and Control Phone Call pattern - Build-up “Clova, Play songs of BTS” “Yes, playing the music” ( play the music) “Hello” “This is A Restaurant. May I help you?” “I would like to make a reservation” “Yes, When?” 2. Having a conversation over the phone with an AI is nothing like interacting with an AI Speaker

3. Having a conversation over the phone with an AI is nothing like interacting with an Chatbot • Chatbot has Visual Display • User can see the entire conversation • User can not remember everything on the phone • Chabot use multi-modal interface • Phone call can use voice only

Conversational UX

UX Designer interview

Understand the Conversation Space

Conversation space Conversation space for AiCall Conversation Opening Conversation Closing Body User Request Agent Response Preclosing Signals Greeting + Cap. Check Phone call situation > No wake word context > Agent always says first > Users usually start conversations with a capability check > Need to detect preclosing signal > A conversation consists of an opening, body and closing > From the opening to the closing - time space

Understand the Characteristics of Spoken Dialogue

What Do Users Want in Spoken Dialogue? Consider time as a critical constraint Time Overlap Silence Balance Mind turn allocation • Conversations can overlap with each other • Turn allocation should be handled naturally in this context Mind the length of utterances • Balancing the length of an utterance is fundamental in spoken dialogue • Spoken prompts should be written considering the length of utterances Mind silence • There could be silence during a conversation • Find ways to minimize silence and get users back on track during silence > Users want natural, continuous conversations > Conversations in the Voice User Interface (VUI) need to consider time as a critical constraint

AiCall Conversation Design Framework

AiCall Conversation Design Framework Activity Task Turn Sequence

AiCall Conversation Design Framework 3 activities 1 task 8 turns 4 sequences A: Hello. This is OUTBACK STEAKHOUSE. What can I help you with? U: Hi. I’d like to make a reservation. A: Okay. When are you coming? U: 7 p.m. tomorrow. A: How many people in your party? U: Four, maybe. A: Okay. Let me see. We have a table for 4 at 7. Want to make a reservation? U: Yes, please. Opening Scheduling Confirmation Reservation Made

Sequence and Expansion

੿ࠁ۝ (UTFS੄౸ױ 4FRVFODF ୶о Q. ݻ द ө૑ ৔স੉ۄҳਃ? য٣ ੿ܨ੢੉ਃ? ୶о Q. OVER MEET LESS USER QUESTION AICALL ANSWER WRONG The amount of information (perceived by users) Additional Question Additional Question When do you close? Which subway line?

U: How can I get there? A: You can find the store…ten-minute walk distance from the subway station. U: How can I get there? A: You can find the store…ten-minute walk distance from the subway station. U: From where? A: From the subway station. Partial Repeat Request Definition Request U: I am going with my parents, and um can you recommend something for them? A: I think tenderloin steak and Toowoomba pasta will be great for your parents. U: What is Towoomba pasta? A: Toowomba pasta is our premium pasta based on spicy cream sauce.

Activities

Definition Usage • Activity as a module • Customized for each task • Subset of task • Consists of sequences for completing one explicit action

Activity Graph "DUJWJUZ "DUJWJUZ "DUJWJUZ "DUJWJUZ "DUJWJUZ "DUJWJUZ "DUJWJUZ ૓ੑ׮ন 5BTL "DUJPO /PU 6TFE "DUJWJUZ Multi- entry

There’s No Failure in Conversation

AI Technology on Telephony

GATEWAY DM NLU ASR Stream Stream Request Text Voice User Speaker Wav Stream Response Text SYNTH

GATEWAY DM NLU ASR Stream Send Full Duplex Receive Request Text Voice User Phone Wav Stream Response Text SYNTH

Consider time as a critical constraint Time Overlap Silence Balance Barge-in

No content

8K 16K 24K Speech Recognition

Natural Tone via telephony Speaker Voice Actor Tone Synth Tone Speech Synthesis

Amount of discourse Pace Overlap Questions Stories Prosodic variation Loudness Gesture (Multimodal) High Considerateness High Involvement

Using Models for Telephony Contextual Hints Multi-turn Task Movement Barge-in

Multi-turn NLU vs Single-turn NLU Context Command & control

72 vs 99

2 weeks ago API problem Kanji to database

Call NLU

Single turn

Multi-turn

72 vs 99

72 vs 99

Engineering Issues

( Engineer Interview video )

Twilio, Nexmo, Other Local Carriers PSTN VoIP WebSocket

Latency 6 6 6 6 Sensitive at latency Using mid result Realtime Duplex Stream AsyncIO GPU Optimization Network optimization Stream optimization Usimg mid result

Why UX Engineering is Important

Between design and engineering • Designed Path != What users really say • Understand the efficient way of improvement: Design or Engineering Finding a "realistic" path Activity 0 Opening Activity 10 Rescheduling Activity 5 Avail. Check Activity 7 Confirmation Activity 0 Opening Activity 10 Rescheduling Activity 5 Avail. Check Activity 7 Confirmation Activity 1 Scheduling S%!#" & U% 5!" S%"& U% " !# S%! & U%3! 5!$

Facing the Real Problem Task jump is real • Conversation without borders • Example: Reservation task with FAQ task Continue or not: Problem after task jump • Turn reconstruction • Sequence re-flow • Activity reconstruction Examples Reservation Reservation FAQ FAQ A,"()& - U,"(- A,'&9(#%* U,9(#! A,"$ - A,10( + - U,"(- A,'&11(#%* U, A,10( + -

Redesign both System and Conversation for Improvements Dialog management as a traffic light • Interface between UX designer and UX Engineers • DM can be a quick prototyping tool

Lessons Learned And More…

No content

No content