Alexa Day 2019


Space Alpha Sannomiya – KOBE, Japan

Fully Amazon Alexa Focusing Conference and of the around ML, IoT technologies of AWS.
– Shift to Voice First –

Attendees 200 (Registrations 240)
Supporters: 24
Speakers: 18 + 7 challengers.
Staffs: 17

This is fully organized by volunteers from the AAJUG (Amazon Alexa Japan User Group) and JAWS-UG (Japan AWS User Group) community.

For Designers, Builders, and all interesters.

There were many sessions with many scopes. VUX Designing, Deep diving of development, Operations, Analytics, collaborating with Machine Learning, Case Studies in Cooking, Alexa Skills of Traffic company, and workshops.

Workshop for families

For families, Of making a robot who is controlled by Amazon Alexa.
All programming with Node-RED. Visual Style programming and building some board.

Blueprints Lab

Recently, Alexa Blueprints was launched in Japan. There were petit Labo of Blueprints with Alexa Evangelist. People all were surprised how quick with launching a skill!

After Party

Many attendees participated After Party. Many ‘real’ discussions. Have a mixing all of the contributors.

Go Next

We changed the Name of this event to ‘Voice Con Japan” to be more globally.
Enjoy Voice World Community, Enjoy more Humanic Ways of interaction.

Let’s make a simple observing with Notification powered by AWS deeplens and Amazon Alexa.

Today’s Goal

The goal of this post is that you can feel fun and you feel that using the AI and Alexa is easier.

Background Story

  • I’m a Japanese. I’m really missing Japanese foods.
  • Fortunately, I can get the really fresh fish every weekend at the Market.
  • I want to store these fishes longer. So I decided to make a dried fishes.

I tried to dry fishes at our balcony. And They came from the sea to pick up my lovely fishes.

Thus, I decided to observe our enemies to save my fish.

Designing of Observation


1. AWS Deeplens

The deeplens provides the power of AI easier. We can deploy pre build training model to the deeplens for several simple steps.

2. Amazon Echo

For notifying to me, I could use Amazon Echo.

Let’s go to cooking.

Setting and Deploying the Object Detection Model to the deeplens

Left : selecting Project template on the deeplens console
Middle: MQTT topic filter on the deeplens console
Right: testing dialog on the AWS IoT console

The deeplens provides the Project Template to implement models easier.

Select the Object Detection in Project template.


MQTT is the lightweight M2M protocol. When the model deployed to the deeplens, MQTT topic which sends the detecting status is deployed too. You can see on the deeplens console.

Also, you can test that the handling messages in AWS IoT Core console. You can access it from Project output column.

As you can see, Simple message is receiving on AWS Iot Core console like this.

{ "chair": <percentage of confidence> }

when some bird coming, the deeplens will send message as follows.

{ "bird": <percentage of confidence> }

Make the Alexa skill with notification

OK. Now We could make Object detection part. Let’s make Alexa Skill for accepting notification. To do this, We have to configure the Manifest file for using the Alexa proactive API. The API provides a capability to send notification which Alexa defined schemas.

Defined Schemas

Unfortunately, We can only use a defined schema. So In this demo, I alternatively use the WheatherAlert Schema for notifying as assuming the bird to storm. 🙂


If you want to add some schemas, You can send a request to add a new schema in the Alexa Developer Forum.

To use proactive API is a really simple modification in Alexa Skill Manifest (skill.json). You only add the permission block and the events block

Then, You can deploy by using ASK-CLI.

ask new
git clone
ask deploy


After deploying succeeded, Let see Alexa Developer Console. And check the ClientId and ClientSecret in the permission dialog. (these are used later)

Deploy Lambda function

Until now, You deployed two front interfaces individually. (deeplens, alexa skill). So Let’s connect each other!! This lambda code does two things.

  • Filtering the message to pick up the specific word ‘bird’
  • alling Alexa proactive API

To deploy this function, You need to pass 2 steps.

Step1: Add clientId and clientSecret to the parameter store on AWS System Manager

If you can use AWS CLI. Run the script. (Of course, You can set t on AWS Management Console)

aws ssm put-parameter --type String --name bird-detection-client-id --value <your-client-id>
aws ssm put-parameter --type String --name bird-detection-client-secret --value <your-client-secret>
aws ssm put-parameter --type String --name bird-detection-topic-filter --value <your-mqtt-topic-filter>

Step2: deploy lambda function by the serverless framework

The serverless framework is really useful to deploy function and around resources. This script deploy Lambda function and set the trigger from AWS IoT Rules.

git clone
cd bird-detect-message-handler
serverless deploy


After deploying, you can see lambda function and set the trigger on the AWS IoT Rules.

Now current configuration assumes the message has 80% confidence of the bird.

Note: AWS IoT Rules

AWS IoT Rules is a feature for filtering the message by (like) SQL query.

If you want to change the topic filter, and notify to another skill, You just modify serverless.yml

    handler: handler.handler
      - iot:
          name: 'birdDetection'
          sql: "select bird from '${self:custom.iot.topicFilter}' where bird > 0.800"
      STAGE: ${self:custom.stage}
      CLIENT_ID: ${self:custom.alexa.clientId}
      CLIENT_SECRET: ${self:custom.alexa.clientSecret}
      ALEXA_NOTIFICATION_EXPIRY_MINUTES: ${self:custom.alexa.notificationExpiryMinutes}

If you are in EU, or Asia Pacific region, You should be changed the PROACTIVE_EVENT_ENDPOINT to appropriate one.

Let’s take a check!

This film is for testing. I was setting the AWS IoT Rules as follows.

select 'person' from <<topic-filter>> where 'person' > 0.600

All Done! We could use AI power and Alexa without deeply knowledge of Machine Learning 🙂

Let’s enjoy Alexa style 🙂

Voice User Experience should be more humanic.

The Amazon would like to make Alexa to more HUMAN CENTRIC. You should not convert your web services to Alexa Skill directly.  What is the humanistic way? We consider these feature what we have.

  • We already have experience.  In conversation, We always complement information from our experience.
  • We often extend our conversation with the information that is stored each other.
  • We usually take care of him(or her) in conversation.
  • We store some keywords in our conversation for the next time.

In many cases of GUI systems, There are many implementations which we don’t go forward if all conditions should be clear. This is a not appropriate way for Voice User Experience. 


First Time
You:       Alexa, open booking concierge
Alexa:   Welcome booking concierge. What your name?

You:       hugtech
Alexa:    Welcome hugtech. ….

Secound Time
You:       Alexa, open booking concierge
Alexa:   Welcome booking concierge. What your name?

You:       (I already told my name to you….)

That is not humanistic! When you turn on the skill for the second time,  How about this?

Second Time
You:       Alexa, open booking concierge.
Alexa:   Welcome. I’m happy to see you again. 

In addition to this, We usually use several greeting. There are many patterns. Shall we modify greeting every time after Second time?

Third Time
You:       Alexa, open booking concierge
Alexa:   Welcome back, hugtech.

AAJUG Online Discussion #01

The AAJUG is a short name of Amazon Alexa Japan User Group.

The first online meetup was taken placed on 4 June 2018.

Thank you to all attendees!


  • self-introducing
  • about your skill
  • how do you usually do the test?
  • how to test the SSML
  • which is better node or python?
  • We wish the whole room can be Smart Home.
  • Clova, Google Home, Alexa, and Line
  • How about microphone’s performance of Spot and Show?
  • Which is better for designing the skill? Many conversations? Minimise?
  • advertisement(meetup, event etc..)

URL’s in the Topics

Python tutorial 5 munites alexa skill…/…/alexa-skill-python-tutorial


Alexa Skill: Backlog for Amazon Alexa…/…/B07B2MVNQH

Alexa Skill: OTAMESHI GACHA!…/…/

Alexa Skill: MHW JAKUTEN checker…/…/

Alexa Skill: Mesoko URANAI…/…/B07CND9KR7



tips Github/URL…/alexa-conversation-model-assert


[Amazon Key]




Give me the PR、issue


See you next online discussion and enjoy voice experience!


FB Group



Invitation link



This post is written in Japanese.

For thinking about community.


WordBench が終わることについて思うこと

僕は、WordPress のコミュニティにそれほど関わってる人間ではありません。WordBench には1、2回参加し、WordCamp KyotoでLTした、くらいの人間です。そんな数少ない参加でも、、それでも、WordBench は他のコミュニティよりも、よりピースフルな場所に感じていて、僕自身もWordPressではないですが、コミュニティを運営する立場の一人として、コミュニティに助けられた一人として、先日の「WordBench 終了」というのは、とても寂しい気持ちになった、というのが正直なところです。




「いままでありがとう! あとは僕らが引き継ぐ!」みたいなのが起こったらそれはそれで続ければいいんじゃない?と。

そんな単純は話でないことはわかっていますが、止めるという意思も尊重したい。WordBenchの存続を望む声が多いんなら、遅かれ早かれ、引き継ぐ人が出るでしょう。コミュニティは、それくらいの「軽さ」でいいんではないか? と思うのです。



今後 へ移行していくようですが、体裁やレギュレーションの差異はあれど、WordBenchの価値観がこれまでと変わりなく続いていくことに僕は楽観的です。これだけWordBenchを思う人たちが声をあげて議論がされてるところを見ると、作り上げてきたものはちゃんと伝搬してるのではないかと思います。




AWS Summit Benelux 2018


AWS Summit Benelux is the really big conference for developers.



Opening Session (Werner Vogels CTO of AWS)

Some new AWS service was introduced.

Although I’ve already known at re:Invent 2017, I recognized again AWS improve and more convenient the world.


Unfortunately, I didn’t watch sessions much. Here are sessions which I joined.


Machine Learning

 Introduction of AWS SageMaker.



 Making Serverless App with GraphQL


Culture of AWS

 Interviewing to Werner Vogels.


AWS Community Organizers in the Netherlands

They are AWS community organizers. Amsterdam, Hague, and JAWS-UG the Netherlands branch(it’s me)


Community pages

AWS Amsterdam

AWS Hague

JAWS-UG the Netherlands branch


Mr. Danilo again since re:Invent 2017 and a new nice guy in AWS

We met at re:Invent 2017.  Thanks to Danilo, I could join AWS community in the Netherlands.


See you next AWS Summit Benelux!


Backlog User Group Netherlands (NBUG) has birthed.

Bucklog User Group has booted up!

The Backlog is famous Project Management tool in Japan.

Manufacture of Backlog ( has come to the Netherlands recently. helped them to built up the community.


NBUG Netherlands Backlog UserGroup Meetup

Haarlem, NL
10 メンバー you interested in Project Management?Would you like to your PM operation to be easier and more enjoyable?With using the Backlog, It may come true.I…

Check out this Meetup Group →


We held pre meetup at 26 May in Amsterdam.

Check it and Let’s join us!

Jump to the community page


AWS Amsterdam meetup report


I participated AWS Amsterdam meetup for the first time.

I also would like to greet AWS user group NL organizers too.

It’s a nice office and there ware very interesting contents.

This is the photo report at AWS Amsterdam meetup Apr 24.

Jump to AWS Amsterdam(


Before starting sessions

In Japan,  Meetup usually starts from the session. It was a little bit funny situation form me.


A hosted company, Mirabeau has a cool bar counter and wine cellar. Are all Netherlands’s IT company same?


At the entrance.


With Martijn. AWS Amsterdam’s Organizer.



I often found the recognizable screen at the meetup. and Today’S main actor, He is DeepLens.

The demo was so funny.  They try to tic tac toe game using DeepLens, Echo Spot, and some AWS Services.

Unfortunately, Demo could not have succeeded.  Monster always lives in the Demo.



This was a nice meetup and good presentation.  Thanks to all staffs!! I enjoyed!!




Osaka, Kyoto, Kobe, Okayama, Wakayama are one of the prefectures in Japan.

We are going to hold the co-organized meetup with above 5 prefectures at 16 May 2018.

This is named to Alexa.west



  • TBD( JAWS-UG Okayama)
  • TBD中( JAWS-UG Kyoto)
  • Making Radio streaming Alexa Skill even if I was a beginner. (JAWS-UG WAKAYAMA Seiji Yamaguchi)
  • Experience of A4B 。 (JAWS-UG KOBE)
  • Amazon.Chime, Amazon.Connect and Alexa (JAWS-UG Osaka)

co-organized Branches

  • JAWS-UG Osaka
  • JAWS-UG Okayama
  • JAWS-UG Wakayama
  • JAWS-UG Kyoto

JAWS-UG all branches information


JAWS-UG KOBE Facebook Community believes the power of community.

Let’s join our community