Empowering Women through Google Assistant & Artificial Intelligence @IWD Ankara & Kütahya 2020 👩💻🤖
In this special edition in commemoration of the International Women’s Day 2020, we are going to share with more than 600 Turkish Women in Tech the workshop: Empowering Women through Google Assistant & NLP models.
The first event will take place in Kütahya the 14th of March, where are invited more than 150 women’s in technology, the second event is the 21st of March in Ankara, hosted by Women’s in Tech at Ankara for more than 500 women in tech that will learn more about How they can create actions for the Google Assistant and use Natural Language Processing (NLP) models to solve Women communities challenges.
This event series seeks to empower more women communities get into Artificial Intelligence and Machine Learning fields, and also back them to keep studying Science, Technology, Engineering and Mathematics (STEM) careers. Our goal is to rethink AI education in Turkey in a way that encourages gender diversity in the tech industry, and also help close the gender pay gap for tech jobs by providing them; new skills and competencies.
In this sessions, I’m going to share resources about Speech Recognition, Text Classification and Voice interfaces for the Turkish language, and how you can interact with a virtual agent through voice commands and text interactions in a human-like conversational manner, understanding what users are saying and typing, at the same time we can help users get things done with the Assistant. As well, attendees will build their own solutions through the workshop to address local challenges in their Women communities and learn more about different integrations of Actions on Google with Messaging Platforms, G Suite, among many others products and APIs.
So Hey Google, Let’s start!
- Go to the Github repo and download IWDTurkey2020.zip file.
2. Now go to your project in Dialogflow console
3. RESTORE the project with the zip file.
4. The project includes the intents; 'meetups'; 'mentors'; 'studygroups';
5. <Add> = ‘[>20&&<=2000]’; training phrases per Intent, for example on 'meetups'; 'When is the next tech meetup in Ankara' 'Where I can find VC meetups next weeks in Istanbul', 'When there is a machine learning event near me' and in the intent'studygroups'; 'I'm looking for a Data Science Study Groups’ 'Tell me more about Fintech groups in Turkey' 'Set an alert for Data Science workshops'
6. The project has the Entities (Text Classifiers); $socialguide and $topic which allow our action to create a decision tree based on the topics of interest of each user.
7. Define training phrases and the Action invocations types: 1) Explicit invocations: occurs when users tell the Assistant that they explicitly want to use your Action by it’s given name. 2) Implicit invocations: occurs when the Assistant chooses to invoke your Action without users calling it by name.
On this action, specify intents that include training phrases such as 'Hey Google, ask Izmir the Tech Guide in Turkey when is the next Hackathon in Ankara/Kütahya/Istanbul/Turkey' and this would trigger a“deep-link” action in the app, allowing users to invoke by specific functionality.
8. Now let’s try the action, go to the integrations section of the Dialogflow console, click on the Google Assistant integration settings <add> Specific intents that are triggered when users request the app by name;'meetups'; 'mentors'; 'studygroups';
https://console.actions.google.com/u/0/project/your_project_ID/simulator
9. Publish your action in the Google Assistant directory; For this step you need to add: Short and Full description about your action, Sample invocations, Small Logo, Developer name and email, Terms of Use and Privacy Policy for your Action, chose a category and other optional settings.
Also you need to provide the Location targeting, surface capabilities, company details, Brand verification (such as sites, Android apps) in order to enable cross-platform functionality,
11. Beta & Alpha Testers, Release and App Review: Once your action is Tested you are ready por Production and you can submitted for Review:Then you’ll receive an email with the complete review.
12. Policies and guidelines: You read the launch checklist, which outlines key policies and guidelines.
Now you are ready to keep training your Action and integrate with external APIs such as Google Calendar, Sheets, among many others, and also you can add new channels to your agent such as Messaging Apps.
🗣️🤖 See you all in the workshop!
//Disclaimer: Opinions are my own, not of the company or their programs. Each Google Developers Expert is fully responsible for their services, and is not affiliated with Google nor do they offer services on behalf of Google. Customers are fully responsible for their use of services, if any. This code is a sample, should not be used for any potential production workloads.//
