Upgrade to Pro
— share decks privately, control downloads, hide ads and more …
Speaker Deck
Features
Speaker Deck
PRO
Sign in
Sign up for free
Search
Search
What understood about that we've used LUIS thro...
Search
Sponsored
·
Your Podcast. Everywhere. Effortlessly.
Share. Educate. Inspire. Entertain. You do you. We'll handle the rest.
→
NAVITIME JAPAN
PRO
January 16, 2018
Technology
26
0
Share
What understood about that we've used LUIS through the year
What understood that we've used LUIS through the year.
NAVITIME JAPAN
PRO
January 16, 2018
More Decks by NAVITIME JAPAN
See All by NAVITIME JAPAN
つよつよリーダーが 抜けたらどうする? 〜ナビタイムのAgile⽀援組織の変遷〜
navitimejapan
PRO
23
16k
実践ジオフェンス 効率的に開発するために
navitimejapan
PRO
3
1k
安全で使いやすいCarPlayアプリの 魅せ方:HIGと実例から学ぶ
navitimejapan
PRO
1
280
見えないユーザの声はログに埋もれている! ~ログから具体的なユーザの体験を数値化した事例紹介~
navitimejapan
PRO
6
3.3k
ユーザーのためなら 『デザイン』 以外にも手を伸ばせる
navitimejapan
PRO
2
1.8k
フツーのIT女子が、 Engineering Managerになるまで
navitimejapan
PRO
3
430
不確実性に打ち勝つOKR戦略/How to manage uncertainty with OKR strategy
navitimejapan
PRO
4
3.9k
アジャイルを小さいままで 組織に広める 二周目 / Agile Transformation in NAVITIME JAPAN iteration 2
navitimejapan
PRO
4
1.5k
変更障害率0%よりも「継続的な学習と実験」を価値とする 〜障害を「起こってはならないもの」としていた組織がDirtの実施に至るまで〜 / DevOps Transformation in NAVITIME JAPAN
navitimejapan
PRO
8
6k
Other Decks in Technology
See All in Technology
サイボウズ、プラットフォームエンジニアリング始めるってよ ― プラットフォームチームの事業貢献と組織アラインメントの強化
ueokande
0
110
Tachikawa.any 運営挨拶
daitasu
0
170
AIと乗り切った1,500ページ超のヘルプサイト基盤刷新とさらにその先の話
mugi_uno
2
340
続 運用改善、不都合な真実 〜 物理制約のない運用改善はほとんど無価値 / 20260518-ssmjp-kaizen-no-value-without-physical-constraints
opelab
1
140
AIエージェントの支払い基盤 AgentCore Payments概要
kmiya84377
2
170
2026年春のAgentCoreアプデ 細かいやつ全部まとめ
minorun365
3
230
SLI/SLO、「完全に理解した」から「チョットデキル」へ
maruloop
5
440
生成AIはソフトウェア開発の革命か、ソフトウェア工学の宿題再提出なのか -ソフトウェア品質特性の追加提案-
kyonmm
PRO
2
890
多角的な視点から見たAGI
terisuke
0
130
ServiceによるKubernetes通信制御ーClusterIPを例に
miku01
1
160
「強制アップデート」か「チームの自律」か?エンタープライズが辿り着いたプラットフォームのハイブリッド運用/cloudnative-kaigi-hybrid-platform-operations
mhrtech
0
190
20260516_SecJAWS_Days
takuyay0ne
2
340
Featured
See All Featured
Heart Work Chapter 1 - Part 1
lfama
PRO
6
35k
How to Get Subject Matter Experts Bought In and Actively Contributing to SEO & PR Initiatives.
livdayseo
0
110
Darren the Foodie - Storyboard
khoart
PRO
3
3.3k
KATA
mclloyd
PRO
35
15k
Lightning talk: Run Django tests with GitHub Actions
sabderemane
0
180
What does AI have to do with Human Rights?
axbom
PRO
1
2.1k
The Anti-SEO Checklist Checklist. Pubcon Cyber Week
ryanjones
0
140
Discover your Explorer Soul
emna__ayadi
2
1.1k
Navigating the Design Leadership Dip - Product Design Week Design Leaders+ Conference 2024
apolaine
0
300
Color Theory Basics | Prateek | Gurzu
gurzu
0
310
Sam Torres - BigQuery for SEOs
techseoconnect
PRO
0
260
The SEO Collaboration Effect
kristinabergwall1
1
440
Transcript
What understood about that we’ve used LUIS through the year
Shinichi Tanabe January 12, 2018 Minami Aoyama Night #5
Speaker Shinichi Tanabe (田邊 晋一/たなべ しんいち) • NAVITIME JAPAN
Co., Ltd. ◦ Joined in 2008 ◦ Cogbot project ◦ Programmer
Products
None
Encounter
September 15, 2016
None
None
First impression
Easy to use, runs fast and smart.
Easy to use
Let’s go to the portal site! https://www.luis.ai
Step1. Create new app
None
Step2. Add intent
None
Step3. Add utterances
None
Step4. Add entities
None
None
Step5. Train
None
Step6. Test
None
None
None
None
None
Step7. Publish
None
None
That’s all!
Furthermore...
You can get a happy bonus.
Versioning
None
None
None
None
Runs fast and smart
Comparison between and LUIS Dialogflow
Test model
Test model Intent Places.FindPlace Utterances おいしいカレーが食べたいな どこか近くでおすすめのレストランを教えて Entities Cuisine カレー
PlaceType レストラン
Training speed
LUIS 2 - 4 sec Dialogflow 4 - 8 sec
The training speed result of test model
Precision and recall
Test utterance LUIS Dialogflow Intent Entity Intent Entity おいしいカレーが食べたいな 〇
〇 〇 〇 どこか近くでおすすめのレストラ ンを教えて 〇 〇 〇 〇 Precision result of test model
Test utterance LUIS Dialogflow Intent Entity Intent Entity おすすめのバーを教えて 〇
〇 × × おすすめのバー教えて 〇 × × × おいしいうどんが食べたい 〇 〇 〇 × おいしいうどん食べたい 〇 × 〇 × Recall result of test model
Yes, he was perfect!
Getting started
But, we had some questions.
Questions 1. How should we defines intents and entities? 2.
How do we know accuracy and precision? 3. When will he go GA(General Availability)?
1. How should we defines intents and entities?
Anti pattern Utterance : Intent ≒ 1 : 1
Use or copy pre-build model positively.
None
None
2. How do we know accuracy and precision?
Comprehensive test on model
Batch testing
Test result details in a visualized view.
Error matrix
True positive True negative Green zone indicates correct prediction
False negative False positive Red zone indicates incorrect prediction
3. When will he go GA?
LUIS is now GA!!
How to get along with LUIS
Points 1. Start small model which has few intents. 2.
Use or copy pre-build model positively. 3. Raise requests before do something about that yourself.
Thank you!