Slide 1
Slide 1 text
Assistant Recap (Session 3)
Yoichiro Tanaka, I/O Extended 2018 Tokyo@GDG
Slide 2
Slide 2 text
Yoichiro Tanaka
Software Engineer / IT Architect
Google Developers Expert (Assistant, Web)
twitter.com/yoichiro
google.com/+YoichiroTanaka
Slide 3
Slide 3 text
Assistant I/O 2018
I believe that this Google I/O 2018 may be renamed as "Assistant I/O 2018" !
Slide 4
Slide 4 text
Google Duplex demo movie.
Slide 5
Slide 5 text
Continued Conversation allows users not to need to say "Ok Google" each time.
Slide 6
Slide 6 text
Multiple Actions allows users to ask multiple phrases at one sentence to the Google Assistant.
Slide 7
Slide 7 text
By Pretty Please feature, if a child says some phrase with "please", Google Assistant replies "Thanks for saying please".
Slide 8
Slide 8 text
No content
Slide 9
Slide 9 text
Three Smart Display models will be released in July 2018.
Slide 10
Slide 10 text
The Google Assistant in navigation in Google Maps.
Slide 11
Slide 11 text
Google Assistant is in many devices, also many devices are connected by Google Assistant.
Slide 12
Slide 12 text
Users use different devices for each situation. Of course, contents, services and apps are different for situations.
Slide 13
Slide 13 text
We must support both voice-activated and visual devices.
Slide 14
Slide 14 text
Google Assistant is strongly integrated and connected with Android and Web.
Slide 15
Slide 15 text
App Actions
Slices App Links
AMP Support
Built-in Intents
Routine Suggestion
Table card
Theme customization
Notification
Many features were announced in this I/O to achieve the integration.
Slide 16
Slide 16 text
App Actions
Slices App Links
AMP Support
Built-in Intents
Routine Suggestion
Table card
Theme customization
Notification
First, talk about each feature to integrate Google Assistant with Android and Web.
Slide 17
Slide 17 text
Android Apps are suggested on All Apps page based on Routines, Context and etc.
Slide 18
Slide 18 text
When users select some text, related apps are suggested. By clicking the suggestion,
Slide 19
Slide 19 text
The related app is launched and is deep-linked. That is, the content about the selected text is shown.
Slide 20
Slide 20 text
Also, Google Assistant shows related apps for each content.
Slide 21
Slide 21 text
The AI recognizes the content, then the AI lists up actions which the user may do. Finally, related apps are suggested.
Slide 22
Slide 22 text
Up to now, users select an app to use, then some content is consumed in the app. From now on, they will be inverted.
Slide 23
Slide 23 text
Google prepares many Built-in Intents. Google's AI decides intents from a target content.
Slide 24
Slide 24 text
Each intent can have one or more parameters.
Slide 25
Slide 25 text
This is an "Actions.xml" file to define actions which the app can treat. Actions on Google recognizes this definitions.
Slide 26
Slide 26 text
When a user says some phrase like above,
Slide 27
Slide 27 text
Google Assistant shows the search result and suggests apps which can treat the content.
Slide 28
Slide 28 text
When the user clicks the suggestion, the app is launched with the deep-link based on the URL.
Slide 29
Slide 29 text
Of course, Conversational Actions can handle the Built-in Intents.
Slide 30
Slide 30 text
In the Dialogflow Console, when adding the "Play game" built-in intent to events of some intent,
Slide 31
Slide 31 text
If the user says "I want to play a game", Google Assistant suggests game apps which have the "Play game" intent.
Slide 32
Slide 32 text
Developers can provide "Sliced" UI for each content on the Search Result page and the Google Assistant (later this year).
Slide 33
Slide 33 text
Users can invoke an action directly by clicking a URL provided by Action Links.
Slide 34
Slide 34 text
Each link for Action Links can be generated on the Actions on Google Console.
Slide 35
Slide 35 text
If you have web contents, you can provide and optimize them for Google Assistant without creating Custom Actions.
Slide 36
Slide 36 text
Content Providers can provide "Content Actions" for Google Assistant.
Slide 37
Slide 37 text
For Content Actions, content providers need use AMP and Structured Data Markup as each content format.
Slide 38
Slide 38 text
For example, developers can create a content using AMP and embed a structured data markup dynamically.
Slide 39
Slide 39 text
The structured data markup is written by a definition of the Schema.org.
Slide 40
Slide 40 text
Google Assistant renders the content as rich component.
Slide 41
Slide 41 text
If AMP and Structured Data Markup supported, you will receive an email explaining how to claim your directory page.
Slide 42
Slide 42 text
App Actions
Slices App Links
AMP Support
Built-in Intents
Routine Suggestion
Table card
Theme customization
Notification
The preceding pages were how to integrate Android and Web with Google Assistant.
Slide 43
Slide 43 text
Related sessions
Getting started with App Actions
Android Slices: build interactive results for Google Search
Integrating your Android apps with the Google Assistant
Integrating your content with the Google Assistant using AMP and markup
An introduction to developing Actions for the Google Assistant
How to build a user base for your Actions
Slide 44
Slide 44 text
App Actions
Slices App Links
AMP Support
Built-in Intents
Routine Suggestion
Table card
Theme customization
Notification
Next, talk about new features of Google Assistant itself.
Slide 45
Slide 45 text
Users tends to ask Google Assistant multiple tasks at one time for each situation.
Slide 46
Slide 46 text
Default Routines are sets of actions for each event. One routine can has one or more actions.
Slide 47
Slide 47 text
Users cannot only use default routines, but they also create a Custom Routine and use it.
Slide 48
Slide 48 text
conv.ask(new Suggestion("Add to routine"));
"Routine Suggestions" is a new feature to suggest to add your action to the routine the user has.
Slide 49
Slide 49 text
For example, users can add the "Order Coffee to Starbucks" action to the "Commuting to work" routine.
Slide 50
Slide 50 text
Visual assistive
Another keyword is "Visual assistive".
Slide 51
Slide 51 text
Visual assistive will become more important concern than ever before. For example, Smart Display supporting.
Slide 52
Slide 52 text
A new rich response named "Table card" to show users 3x3 information brings more visual and more clear.
Slide 53
Slide 53 text
conv.ask("Simple response");
conv.ask(new Table({
dividers: true,
columns: ["Header1", "Header2", "Header3"],
rows: [
["Row1 Item1", "Row1 Item2", …],
["Row2 Item1", "Row2 Item2", …],
["Row3 Item1", "Row3 Item2", …]
]
});
Since actions-on-google-nodejs version 2.1.0, the Table card has been supported.
Slide 54
Slide 54 text
"Theme customization" allows you to customize the design of rich responses. When specifying the background image,
Slide 55
Slide 55 text
The background image is reflected to each rich response like a basic card above.
Slide 56
Slide 56 text
For monetization, Google Sign-in, Transactions API and some features have already been available.
Slide 57
Slide 57 text
Finally, developers can release apps for limited users with Alpha/Beta Release feature.
Slide 58
Slide 58 text
Related sessions
Design Actions for the Google Assistant: beyond smart speakers, to phones and smart display
10 tips for building better Actions
Best practices for testing your Actions
Personalize Actions for the Google Assistant
Add transactional capabilities to your Actions
Slide 59
Slide 59 text
Voice User Interface Design & Usecase
Building games for the Google Assistant on smart displays
Creating a persona: what does your product sound like?
Build engaging conversations for the Google Assistant using Dialogflow
Smart Home, Automotive and others
Integrate your smart home device with the Google Assistant
What's new in automotive
What's new with the Google Assistant SDK for devices
Slide 60
Slide 60 text
Build Actions for the Google Assistant (Level 1)
Creating a new project, intent, Using an entity and Handing them by fulfillment code with the
inline editor.
Build Actions for the Google Assistant (Level 2)
Creating own fulfillment code, custom entity, Adding a deep-link, follow-up intent
and Using helpers, SSML
Smart Home Washer
Creating a new project, a washer on local,
Adding modes, toggles, request syncs and report states
Codelabs
Slide 61
Slide 61 text
We just have been starting building an ecosystem of the Google Assistant. We need your cooperations.
Slide 62
Slide 62 text
Assistant Developer Community Japan
Google Groups
http://bit.ly/assistant-dev-japan
Slack
http://bit.ly/assistant-dev-slack
Slide 63
Slide 63 text
Any questions?