O slideshow foi denunciado.
Utilizamos seu perfil e dados de atividades no LinkedIn para personalizar e exibir anúncios mais relevantes. Altere suas preferências de anúncios quando desejar.
1
How to build cool & useful voice
commerce applications
(such as Alexa & Google Home)
1
Victoria Livschitz, Founder
Decem...
2
Today’s talk
・ At Grid Dynamics, we’ve been working on conversational systems since 2017
・ Particular focus on voice com...
3
So, you want to order some flowers for you mom?
4
Plausible
actual
conversation
5
But it’s not all roses. Typical gotchas and hiccups
6
Live demo!
7
General system’s architecture
8
How about an AI recommendation system for a camera?
・ Hint: a lot harder than flowers!
・ 1,000s of products; wide range ...
9
Live demo!
Scenario 1: “I want a camera for hiking”, “I want a camera for travels”
Scenario 2: Expert that knows exactly...
10
Understanding customer queries using Deep Learning
11
ML bag of tricks
2. 3.
Transfer learning
12
Design cycle: yep, it’s a cycle. Particularly in AI systems.
If you don’t understand your customer’s behavior, your cus...
13
Where do you get the training data?
14
Finally, testing and certification. There is a lot to it.
15
Conclusion
・ Availability of high-quality AI models is spreading =>
・ The price & complexity of conversational applicat...
16
To learn more
・ Detailed blog post that spills all the beans:
https://blog.griddynamics.com/how-we-built-a-conversation...
Próximos SlideShares
Carregando em…5
×
Próximos SlideShares
What to Upload to SlideShare
Avançar
Transfira para ler offline e ver em ecrã inteiro.

0

Compartilhar

"How to build cool & useful voice commerce applications using devices like Alexa & Google Home" by Victoria Livschitz, founder of Grid Dynamics

Baixar para ler offline

In this talk, we describe how to build conversational e-commerce applications for the growing market of voice-powered AI devices using Dialog Flow. This talk demonstrates the capabilities of "Flower Genie," a teaching-oriented chatbot that can recommend a bouquet for any occasion, then take an order and deliver the flower arrangement via Alexa. We present the overall architecture of a voice application developed with Dialog Flow, including dialog management and NLU, and then discuss the finer points of testing and publishing a voice application for Alexa.

  • Seja a primeira pessoa a gostar disto

"How to build cool & useful voice commerce applications using devices like Alexa & Google Home" by Victoria Livschitz, founder of Grid Dynamics

  1. 1. 1 How to build cool & useful voice commerce applications (such as Alexa & Google Home) 1 Victoria Livschitz, Founder December 2019
  2. 2. 2 Today’s talk ・ At Grid Dynamics, we’ve been working on conversational systems since 2017 ・ Particular focus on voice commerce: selling products & services via Alexa/Google Home/etc. ・ How good is modern conversational AI from pragmatic application standpoint? ・ So, what does it take to write a conversational application? Let’s take a close look at the “Flower Genie” and “Camera Genie”: our “Petshops of Conversational AI”
  3. 3. 3 So, you want to order some flowers for you mom?
  4. 4. 4 Plausible actual conversation
  5. 5. 5 But it’s not all roses. Typical gotchas and hiccups
  6. 6. 6 Live demo!
  7. 7. 7 General system’s architecture
  8. 8. 8 How about an AI recommendation system for a camera? ・ Hint: a lot harder than flowers! ・ 1,000s of products; wide range on categories, from cheap point-n-shoot to professional ・ Technical product with wildly different features ・ Some customers know exactly what they want (hobbists, pros); others - nothing at all Help me choose the right camera. How hard is it? What else do we want from the dialog? ・ Know the difference between advisory vs. order-taking. Adopt the dialog accordingly ・ Determine customer’s knowledge level. Adopt the dialog accordingly ・ Graceful switch between “leading the witness” & provide useful information. ・ Deal with “I dunno”
  9. 9. 9 Live demo! Scenario 1: “I want a camera for hiking”, “I want a camera for travels” Scenario 2: Expert that knows exactly what he wants ・ Step 1: quickly determine that I don’t know much about cameras ・ Step 2: gently find out what I need camera for, then lead me through selection ・ Step 3: ask and answer reveland (to the purpose) questions ・ Step 4: close the deal ・ Step 1: quickly determine that I already know a lot about what I want. ・ Step 2: provide direct, complete, factual information. Follow, not lead. ・ Step 3: close the deal
  10. 10. 10 Understanding customer queries using Deep Learning
  11. 11. 11 ML bag of tricks 2. 3. Transfer learning
  12. 12. 12 Design cycle: yep, it’s a cycle. Particularly in AI systems. If you don’t understand your customer’s behavior, your customers will not understand your AI
  13. 13. 13 Where do you get the training data?
  14. 14. 14 Finally, testing and certification. There is a lot to it.
  15. 15. 15 Conclusion ・ Availability of high-quality AI models is spreading => ・ The price & complexity of conversational applications is rapidly coming down => ・ Best practices in design, testing and certification of conversational apps are emerging => ・ This is already practical to create a wide range of useful eCommerce voice / visual apps today
  16. 16. 16 To learn more ・ Detailed blog post that spills all the beans: https://blog.griddynamics.com/how-we-built-a-conversational-ai-for-ordering-flowers/ ・ More about conversational AI development services: https://www.griddynamics.com/technologies/ai/voice-application-development-services ・ Write to us! vlivschitz@griddynamics.com info@griddynamics.com

In this talk, we describe how to build conversational e-commerce applications for the growing market of voice-powered AI devices using Dialog Flow. This talk demonstrates the capabilities of "Flower Genie," a teaching-oriented chatbot that can recommend a bouquet for any occasion, then take an order and deliver the flower arrangement via Alexa. We present the overall architecture of a voice application developed with Dialog Flow, including dialog management and NLU, and then discuss the finer points of testing and publishing a voice application for Alexa.

Vistos

Vistos totais

157

No Slideshare

0

De incorporações

0

Número de incorporações

1

Ações

Baixados

4

Compartilhados

0

Comentários

0

Curtir

0

×