ImageVerifierCode 换一换
格式:PPT , 页数:7 ,大小:88.58KB ,
资源ID:373266      下载积分:2000 积分
快捷下载
登录下载
邮箱/手机:
温馨提示:
如需开发票,请勿充值!快捷下载时,用户名和密码都是您填写的邮箱或者手机号,方便查询和重复下载(系统自动生成)。
如填写123,账号就是123,密码也是123。
特别说明:
请自助下载,系统不会自动发送文件的哦; 如果您已付费,想二次下载,请登录后访问:我的下载记录
支付方式: 支付宝扫码支付 微信扫码支付   
注意:如需开发票,请勿充值!
验证码:   换一换

加入VIP,免费下载
 

温馨提示:由于个人手机设置不同,如果发现不能下载,请复制以下地址【http://www.mydoc123.com/d-373266.html】到电脑端继续下载(重复下载不扣费)。

已注册用户请登录:
账号:
密码:
验证码:   换一换
  忘记密码?
三方登录: 微信登录  

下载须知

1: 本站所有资源如无特殊说明,都需要本地电脑安装OFFICE2007和PDF阅读器。
2: 试题试卷类文档,如果标题没有明确说明有答案则都视为没有答案,请知晓。
3: 文件的所有权益归上传用户所有。
4. 未经权益所有人同意不得将文件中的内容挪作商业或盈利用途。
5. 本站仅提供交流平台,并不能对任何下载内容负责。
6. 下载文件中如有侵权或不适当内容,请与我们联系,我们立即纠正。
7. 本站不保证下载资源的准确性、安全性和完整性, 同时也不承担用户因使用这些下载资源对自己和他人造成任何形式的伤害或损失。

版权提示 | 免责声明

本文(The following diagrams detail the interaction of AWS, Alexa, .ppt)为本站会员(arrownail386)主动上传,麦多课文库仅提供信息存储空间,仅对用户上传内容的表现方式做保护处理,对上载内容本身不做任何修改或编辑。 若此文所含内容侵犯了您的版权或隐私,请立即通知麦多课文库(发送邮件至master@mydoc123.com或直接QQ联系客服),我们立即给予删除!

The following diagrams detail the interaction of AWS, Alexa, .ppt

1、The following diagrams detail the interaction of AWS, Alexa, Fitbit apis, and the user #1 User needs to link Fitbit account to skill #2 User needs to have a machine learning datasource created from Fitbit data #3 User needs to have a custom machine learning model created #4 The user askes for the be

2、st time to workout. Current data is pulled from the Fitbit platform and run against the machine learning model to create a recommendation.,Lambda: Get_Best_Workout_Time_Interface_Alexa,Alexa Best Workout Recommendation Skill,Workout_Recommendations,Amazon Dynamo,F,1A,1B,SNS Topic: Start_ML_Model,Lam

3、bda: Create_ML_Model_Workout_App,Amazon Machine Learning,Create_ML_Model_Workout App2 (runs every 30 minutes),1C,S3: Data for Machine Learning,1A User Asks “Alexa, ask Workout Recommendation to find the best time to go to the gym today?1B Alexa passes the request to the “Get_Best_Workout_Time_Interf

4、ace_Alexa” lambda function The function looks for a authorization token for a linked account No token is found, so Alexa responds “You must have a Fitbit account to use this skill. Please use the Alexa app to link your Amazon account with your Fitbit Account”1C User links Fitbit Account to app,Lambd

5、a: Get_Best_Workout_Time_Interface_Alexa,Alexa Best Workout Recommendation Skill,Workout_Recommendations,Amazon Dynamo,F,2A,2B,SNS Topic: Start_ML_Model,Lambda: Create_ML_Model_Workout_App,Amazon Machine Learning,Create_ML_Model_Workout App2 (runs every 30 minutes),2A User Asks “Alexa, ask Workout R

6、ecommendation to find the best time to go to the gym today?2B 2C Alexa passes the request to the “Get_Best_Workout_Time_Interface_Alexa” lambda function The function finds an authorization token and checks the Workout_Recommendations table to see if a Machine Learning Model exists No record is found

7、, so Alexa responds “Your Fitbit historical data needs to be analyzed to provide the best workout recommendations. This process will take about an hour.”2D-2E-2F The token is passed via SNS to another lambda function. The function uses the token to pull back activity records from Fitbit The data is

8、saved to an S3 bucket2G-2H A Machine Learning Data Source is created using the data saved in S3 The DynamnoDB status table is updatedNote: If the user were to query Alexa during the process, the response would be: “Your Fitbit historical data is being analyzed to provide the best workout recommendat

9、ions. Please check back in an hour.”,2C,S3: Data for Machine Learning,2D,2E,2F,2H,2G,Lambda: Get_Best_Workout_Time_Interface_Alexa,Alexa Best Workout Recommendation Skill,Workout_Recommendations,Amazon Dynamo,F,3A,SNS Topic: Start_ML_Model,Lambda: Create_ML_Model_Workout_App,Amazon Machine Learning,

10、Create_ML_Model_Workout App2 (runs every 30 minutes),3A User Asks “Alexa, ask Workout Recommendation to find the best time to go to the gym today?3A-3B The Create_ML_Model_Workout_App2 Lambda function runs every 30 minutes and queries the status table to determine if any action is needed on Machine

11、Learning services If the Datasource created in step 2 is complete, then the Machine Learning Model is created. The status table is updated to reflect that the Machine Learning Model is being created.3C-3D The Create_ML_Model_Workout_App2 Lambda function runs every 30 minutes and queries the status t

12、able to determine if any action is needed on Machine Learning services If the Machine Learning Model created in step 3A-3B is complete, then status table is updated to reflect that the system can be used.,S3: Data for Machine Learning,3B,3C,3D,Lambda: Get_Best_Workout_Time_Interface_Alexa,Alexa Best

13、 Workout Recommendation Skill,Workout_Recommendations,Amazon Dynamo,F,3A,SNS Topic: Start_ML_Model,Lambda: Create_ML_Model_Workout_App,Amazon Machine Learning,Create_ML_Model_Workout App2 (runs every 30 minutes),3A-3B The Create_ML_Model_Workout_App2 Lambda function runs every 30 minutes and queries

14、 the status table to determine if any action is needed on Machine Learning services If the Datasource created in step 2 is complete, then the Machine Learning Model is created. The status table is updated to reflect that the Machine Learning Model is being created.3C-3D The Create_ML_Model_Workout_A

15、pp2 Lambda function runs every 30 minutes and queries the status table to determine if any action is needed on Machine Learning services If the Machine Learning Model created in step 3A-3B is complete, then status table is updated to reflect that the system can be used.,S3: Data for Machine Learning

16、,3B,3C,3D,Lambda: Get_Best_Workout_Time_Interface_Alexa,Alexa Best Workout Recommendation Skill,Workout_Recommendations,Amazon Dynamo,F,4A,SNS Topic: Start_ML_Model,Lambda: Create_ML_Model_Workout_App,Amazon Machine Learning,Create_ML_Model_Workout App2 (runs every 30 minutes),S3: Data for Machine L

17、earning,4B,4C,4E,4A User Asks “Alexa, ask Workout Recommendation to find the best time to go to the gym today?4B 4C Alexa passes the request to the “Get_Best_Workout_Time_Interface_Alexa” lambda function The function finds an authorization token and checks the Workout_Recommendations table to see if

18、 a Machine Learning Model exists A Machine Learning model exists.4E The user token is used to retrieve current data from Fitbit. This includes, for the day the current users weight, the amount of sleep the user achieved, and the number of calories burned the previous day.4F The Fitbitdata, along wit

19、h the day of the week is passed to the Machine Learning Model The model evaluates 4 options working out in the morning, mid-day, afternoon, and evening and gives a prediction on the number of “very active minutes” for each time period.4G The lambda code determines the best option and Alexa tells the

20、 user: “Based on your previous activity, the best time for you to work out is Morning” (or Mid-Day, Afternoon, or Evening),4F,4G,Alexa, ask Workout Recommendation to find the best time to go to the gym today,Is User Account Linked,You must have a Fitbit account to use this skill. Please use the Alex

21、a app to link your Amazon account with your Fitbit Account.,Is a ML Model Available?,Based on your previous activity, the best time for you to work out is Morning *,Is the Model being built?,Your Fitbit historical data is being analyzed to provide the best workout recommendations. Please check back

22、in an hour.,Your Fitbit historical data needs to be analyzed to provide the best workout recommendations. This process will take about an hour.,Alexa, ask Workout Recommendation to find the best time to go to the gym, Today or Tomorrow,* Morning, Mid-Day, Afternoon, or Evening,You did not tell me what day to check. Please ask me, what is the best time to work out today or what is the best time to work out tomorrow.,Main Flow,Alternate Flow,User Query,Lambda Logic,Alexa Response,N,Y,N,N,Y,Y,Corresponding Flow Chart,1,4,3,2,

copyright@ 2008-2019 麦多课文库(www.mydoc123.com)网站版权所有
备案/许可证编号:苏ICP备17064731号-1