Siri

Siri, is a digital assistant that learns and uses a bunch of technologies to assist users:

  1. Automatic Speech Recognition (ASR) to convert speech into text
  2. Natural Language Processing (NLP) to parse text and convert into intent
  3. Question and Intent Analysis to convert intent into commands and actions
    1. Learn and associate
    2. Interface with APIs to get answers.  E.g.  Calendar, OpenTable etc.
    3. Fallback to WolframAlpha or Search if APIs not available
  4. Convert results to human understandable text
  5. Text-To-Speech (TTS) to convert text to synthesized speech

siri

Although it is possible to use Siri in loud environments by editing the results of automatic speech recognition, the experience is quite cumbersome.

warrors siri

Siri in iMessage is expected in iOS 11

Apple Patent indicates you will be able to include Siri in your iMessage conversations.

The conversations may be between you and Siri, or between your friends and Siri.

Apple Patent 20170132019,  was filed Nov 6, 2015 and  granted May 11, 2017.

Section [0031] from Patent

It can be desirable to implement a digital assistant in a messaging environment. The messaging platform can enable multiple modes of input (e.g., text, audio, images, video, etc.) to be sent and received.

A user request can thus define a request to the digital assistant using a combination of inputs (e.g., image and text). As described herein, this can increase the functionality and capabilities of the digital assistant, thereby providing a richer interactive experience between a user and a digital assistant.

In addition, the messaging platform is a visual interface which permits interactions in a broader range of environments than voice/audio based platforms.

A digital assistant in a message environment can thus enable greater accessibility to the digital assistant.

In particular, the digital assistant can be accessible in noisy environments or in environments where audio output is not desired (e.g., the library).

Further, the messaging platform can be a conversational interface where short concise communications are exchanged between two or more parties and presented in a chronological format.

A digital assistant in a message environment can thus enable the digital assistant to be a participant in a multi-party conversation where the benefits associated with the digital assistant can be shared among the multiple participants.

Moreover, the chronological format enables a user to conveniently review previous interactions with the digital assistant and utilize the contextual history associated with the previous interactions to define a wider range of tasks.

Examples

Conversing with Siri in iMessage

Screen Shot 2017-05-11 at 11.41.23 PM

Requesting Siri to scan a business card and store into contacts

Screen Shot 2017-05-11 at 11.42.22 PM

Requesting Siri to recognize a picture and take an action

Screen Shot 2017-05-11 at 11.42.10 PM

Conversation with John and Siri

Screen Shot 2017-05-11 at 11.43.06 PM

 

Chatbots are improving and becoming more and more helpful and accessible.  We have written extensively about Chatbots in the following article and blog posts:

Messaging between people and with roBOTs
Overcoming chatbot design challenges in order to make them convincing
Meaningful Personalization in Messaging & Conversational Interfaces
iMessage + Apps + Messages app

 

Posted by Dickey Singh

Dickey Singh is the CEO and co-founder at Pyze and has over two decades of experience in mobile, Big Data and SaaS. He started Pyze to help app publishers engage, retain and grow their mobile users using automation. https://twitter.com/DickeySingh Get Pyze: https://pyze.com