From 2dcb041f79a0882beb791203b38c713bc870c8f6 Mon Sep 17 00:00:00 2001 From: Deborah Dahl Date: Wed, 6 Nov 2024 10:19:47 -0500 Subject: [PATCH] Update paArchitecture-1-3.htm added paragraph about LLMs in the introduction --- .../paArchitecture/paArchitecture-1-3.htm | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) diff --git a/voice interaction drafts/paArchitecture/paArchitecture-1-3.htm b/voice interaction drafts/paArchitecture/paArchitecture-1-3.htm index a50c0bc..c5cdc59 100644 --- a/voice interaction drafts/paArchitecture/paArchitecture-1-3.htm +++ b/voice interaction drafts/paArchitecture/paArchitecture-1-3.htm @@ -123,8 +123,8 @@

Table of Contents

1. Introduction

-

Intelligent Personal Assistants (IPAs) are now available in - our daily lives through our smart phones. Apple’s Siri, Google +

Intelligent Personal Assistants (IPAs) are now widely available in + our daily lives and can be accessed in many ways. Apple’s Siri, Google Assistant, Microsoft’s Cortana, Samsung’s Bixby and many more are helping us with various tasks, like shopping, playing music, setting a schedule, sending messages, and offering answers to @@ -132,7 +132,10 @@

smart speakers like Amazon’s Alexa or Google Home which are available without the need to pick up explicit devices for these sorts of tasks or even control household appliances in our - homes. As of today, there is no interoperability among the + homes. +

+ +

As of today, there is no interoperability among the available IPA providers. Especially for exchanging learned user behaviors this is unlikely to happen at all.

Furthermore, in addition to these general-purpose assistants, @@ -147,6 +150,9 @@

assistants. Without this kind of interoperability, enterprise developers will need to re-implement their intelligent assistants for each major generic platform.

+

+ Recently, the increase in the availability of Large Language Models (LLMs) has greatly improved the natural language processing capabilities of IPAs. However, these technical improvements do not directly affect the architecture described in this document, as it applies to IPAs based on LLMs as well as IPAs based on traditional technologies. This is because this document primarily concerns the interoperation of IPAs rather than their specific components. The architectural diagrams below in Figure 2b and Figure 3 show how this architecture accomodates both technologies. +

This document is a first step in our strategy for IPA standardization. It describes a general architecture of IPAs and