Hack2023 2nd Prize: Difference between revisions

From MECwiki
Jump to: navigation, search
(Created page with "{{DISPLAYTITLE:<span style="position: absolute; clip: rect(1px 1px 1px 1px); clip: rect(1px, 1px, 1px, 1px);">{{FULLPAGENAME}}</span>}} <p class="center" style="font-size:34px;"><b>1<sup>st</sup> Prize Award</b><p> <p class="center" style="font-size:34px;"><b> Managing natural resources using AI, Edge Computing and Advanced Communication </b><p> <br> = Team= <div class="flex-row row"> <div class="col-xs-5 "> <div class="panel panel-default"> <div class="panel-bo...")
 
No edit summary
 
(3 intermediate revisions by the same user not shown)
Line 1: Line 1:
<p class="left" style="font-size:26px;"> ←''[[ETSI_-_LF_-_OCP_-_MEC_Hackathon_2023|MEC Hackathon 2023]]''<p>
<br>
{{DISPLAYTITLE:<span style="position: absolute; clip: rect(1px 1px 1px 1px); clip: rect(1px, 1px, 1px, 1px);">{{FULLPAGENAME}}</span>}}
{{DISPLAYTITLE:<span style="position: absolute; clip: rect(1px 1px 1px 1px); clip: rect(1px, 1px, 1px, 1px);">{{FULLPAGENAME}}</span>}}


<p class="center" style="font-size:34px;"><b>1<sup>st</sup> Prize Award</b><p>
<p class="center" style="font-size:34px;"><b>2<sup>nd</sup> Prize Award</b></p>


<p class="center" style="font-size:34px;"><b> Managing natural resources using AI, Edge Computing and Advanced Communication
<p class="center" style="font-size:34px;"><b> Project Sheikah Tower  </b></p>


  </b><p>
<p class="center" style="font-size:25px;"> AI Assistants powered by local people  </p>
 
<p class="center" style="font-size:25px;">Enhance usefulness based on time and place  </p>


<br>
<br>


= Team=
= Team=
<div class="flex-row row">
<div class="flex-row row">


<div class="col-xs-5 ">
<div class="col-xs-12 col-md-6 col-lg-7">
<div class="panel panel-default">
<div class="panel panel-default">
<div class="panel-body">
<div class="panel-body">
Team '''Sheikah Tower''' from '''Google LLC''' and '''Peking University'''
[[File:Sheikak1.png|300px|class=img-responsive]]
<p>from '''Google LLC''' and '''Peking University'''</p>
* Qi Tang - Senior Hardware Engineer - Google
* Qi Tang - Senior Hardware Engineer - Google
* Yi Han - Google
* Yi Han - Google
* Sharu Jiang - Peking University
* Sharu Jiang - Peking University
 
<br>
[[File:Sheikah4.png|400px|class=img-responsive]]
 
</div>
</div>
<!--  <div class="panel-footer">Footer text 1</div>  -->
<!--  <div class="panel-footer">Footer text 1</div>  -->
Line 29: Line 32:
</div><!-- End of col 1-->
</div><!-- End of col 1-->


<div class="col-xs-7">
<div class="col-xs-12 col-md-6 col-lg-5">
<div class="panel panel-default">
<div class="panel panel-default">


<div class="panel-body">
<div class="panel-body">
[[File:Sheikak1.png|300px|center|top|class=img-responsive]]
[[File:Sheikah5.png|300px|center|top|class=img-responsive]]
</div>
</div>
  <div class="panel-footer">From left to right,  Santiago Rodriguez  & Fernando Lamela</div>  
<!--
  <div class="panel-footer">From Left to right: </div>
-->
<!--  <div class="panel-footer">Footer text 1</div>  -->
<!--  <div class="panel-footer">Footer text 1</div>  -->
</div><!-- End of pan -->
</div><!-- End of pan -->
Line 42: Line 47:
</div><!-- end of row 1-->
</div><!-- end of row 1-->


[[File:Sheikak2.png|700px|center|top|class=img-responsive]]
</div>
<br>
= Introduction =  
= Introduction =  
<p>
<p>
Edge Native Real-time Voice AI Assistant provides local-info enhanced language and speech services (e.g. real-time translation and AI voice-bot) using the state-of-the-art AI models. The key features are the real-time streaming services by edge computing. We will also leverage the ETSI MEC APIs to fine-tune or prompt the LLM with available local information (such as dialects, geographics, local culture) to provide faster and more useful user contents. We will demonstrate the advantages of edge computing compared to traditional on-device and cloud based services. The end user interfaces can be mobile devices, wearables, IoTs, robots and/or vehicles.
Edge Native Real-time Voice AI Assistant provides local-info enhanced language and speech services (e.g. real-time translation and AI voice-bot) using the state-of-the-art AI models. </p>
Main Features:
<p>
● Users can easily find the nearby virtual assistants from a map view by leveraging MEC APIs
The key features are the real-time streaming services by edge computing. We will also leverage the ETSI MEC APIs to fine-tune or prompt the LLM with available local information (such as dialects, geographics, local culture) to provide faster and more useful user contents. We will demonstrate the advantages of edge computing compared to traditional on-device and cloud based services. The end user interfaces can be mobile devices, wearables, IoTs, robots and/or vehicles.</p>
● Local AI virtual assistant indexed by ZoneID and CellID
● “Local” means the Vector Database and Prompts are location dependent
● The Vector database and Prompts are uploaded and designed by the local business owners; Like
● The virtual assistants can be sophisticated / the-state-of-art AI models serving as a real-time language interpreter (For example, Meta’s latest Speech-to-Speech Massive Language models) which also can be found by the user from the map (as long as it is within the same ZoneID or CellID)
● The finding range can be also flexible: for example, indoor localization information from MEC APIs which is used serving for a museum exhibit tour (room specific) or a city tour based on the user’s device GPS signal
● The app is agnostic to various user end devices because computation, memory and location information is not on device per se. We choose iOS for demonstration purpose only.
</p>


<p>Main Features: </p>


[[File:Sheikah-archi.png|800px|center|top|class=img-responsive]]
<p>● Users can easily find the nearby virtual assistants from a map view by leveraging MEC APIs</p>
<p>● Local AI virtual assistant indexed by ZoneID and CellID </p>
<p>● “Local” means the Vector Database and Prompts are location dependent</p>
<p>● The Vector database and Prompts are uploaded and designed by the local business owners; </p>
<p>● The virtual assistants can be sophisticated / the-state-of-art AI models serving as a real-time language interpreter (For example, Meta’s latest Speech-to-Speech Massive Language models) which also can be found by the user from the map (as long as it is within the same ZoneID or CellID)</p>
<p>● The finding range can be also flexible: for example, indoor localization information from MEC APIs which is used serving for a museum exhibit tour (room specific) or a city tour based on the user’s device GPS signal</p>
<p>● The app is agnostic to various user end devices because computation, memory and location information is not on device per se. We choose iOS for demonstration purpose only.</p>
 
 
 
[[File:Sheikah-archi.png|600px|center|top|class=img-responsive]]
[[File:Sheikah-map.gif|300px|center|top|class=img-responsive]]
<br>
<br>


<!--
<div class="flex-row row">
<div class="col-xs-12 col-md-6 col-lg-7">
<div class="panel panel-default">
<div class="panel-body">


<br><br>
[[File:Sheikah-archi.png|500px|center|top|class=img-responsive]]
= Software resources =
</div>


• '''Project repository'''
<div class="col-xs-12 col-md-6 col-lg-5">
<div class="panel panel-default">


https://github.com/Dako2/sheikah-tower.git
<div class="panel-body">
[[File:Sheikah-map.gif|200px|center|top|class=img-responsive]]
</div>


<!--
</div><!
Web App for Managing green cyclops Edge app and model ecosystem as well as dashboard representations.
</div>


Need to be complemented with backend API not availbale in this repo, that is only uploaded to be used as inspiration or reusability, for another teams.
</div>
[[File:Github-optare.png|600px|center|class=img-responsive]]
-->
-->


= Project Videos =


<br><br>
= Software resources =
• '''Project repository'''


https://github.com/Dako2/sheikah-tower.git


= Project Videos =
{{#evu:https://www.youtube.com/watch?v=zmEYpDqo0FU
{{#evu:https://www.youtube.com/watch?v=zmEYpDqo0FU
|alignment=inline
|alignment=inline
|dimensions="120"
|dimensions="120"
}}
}}

Latest revision as of 09:05, 28 March 2024

←MEC Hackathon 2023


2nd Prize Award

Project Sheikah Tower

AI Assistants powered by local people

Enhance usefulness based on time and place


Team

Sheikak1.png

from Google LLC and Peking University

  • Qi Tang - Senior Hardware Engineer - Google
  • Yi Han - Google
  • Sharu Jiang - Peking University


Sheikah4.png

Sheikah5.png



Sheikak2.png



Introduction

Edge Native Real-time Voice AI Assistant provides local-info enhanced language and speech services (e.g. real-time translation and AI voice-bot) using the state-of-the-art AI models.

The key features are the real-time streaming services by edge computing. We will also leverage the ETSI MEC APIs to fine-tune or prompt the LLM with available local information (such as dialects, geographics, local culture) to provide faster and more useful user contents. We will demonstrate the advantages of edge computing compared to traditional on-device and cloud based services. The end user interfaces can be mobile devices, wearables, IoTs, robots and/or vehicles.

Main Features:

● Users can easily find the nearby virtual assistants from a map view by leveraging MEC APIs

● Local AI virtual assistant indexed by ZoneID and CellID

● “Local” means the Vector Database and Prompts are location dependent

● The Vector database and Prompts are uploaded and designed by the local business owners;

● The virtual assistants can be sophisticated / the-state-of-art AI models serving as a real-time language interpreter (For example, Meta’s latest Speech-to-Speech Massive Language models) which also can be found by the user from the map (as long as it is within the same ZoneID or CellID)

● The finding range can be also flexible: for example, indoor localization information from MEC APIs which is used serving for a museum exhibit tour (room specific) or a city tour based on the user’s device GPS signal

● The app is agnostic to various user end devices because computation, memory and location information is not on device per se. We choose iOS for demonstration purpose only.


Sheikah-archi.png
Sheikah-map.gif





Software resources

• Project repository

https://github.com/Dako2/sheikah-tower.git

Project Videos

Retrieved from "https://mecwiki.etsi.org/index.php?title=Hack2023_2nd_Prize&oldid=4231"