Cognitive Architecture

Cognitive technology augments human expertise to unlock new intelligence from vast quantities of structured and unstructured data and to develop deep, predictive insights. Cognitive conversation is a runtime architecture that showcases the components that are involved in a trained and deployed cognitive conversation system. The cognitive discovery architecture uses IBM Watson® Discovery Service to discover trends and patterns in diverse sets of structured and unstructured data.

Shown below is a cognitive reference architecture.

Runtime Flow

1. A customer accesses the mobile application by using voice to ask what kind of connector is needed for a dishwasher.

2. Application logic determines that the request is a voice request and invokes the extend speech-to-text component.

3. The extend speech-to-text component converts the voice request to text.

4. Application logic uses the text to check with the conversation component for a trained response. Conversation is not trained with a specific response on connectors for a dishwasher.

5. Application logic uses the API to determine whether the information is available in the core ERP system. The system has the manual and information about the type of connector, but it does not have detailed information about how to use the connector to connect the dishwasher to the garbage disposal.

6. Application logic checks to learn whether the discovery component is trained to get specific information. Discovery is trained and gives the information to application logic.

7. Application logic uses the conversation component to get the correct response.

8. Application logic uses the extend text-to-speech component to translate the response from text to voice.

9. Application logic sends the voice response to the customer’s mobile application.

Design Time Flow

Step A: The ingestion application crawls customer feedback and comments on social media.

Step B: The ingestion application uses the discovery APIs to add the social media content to the collection.

Step C: The ingestion application crawls product information, product catalogs, descriptions, and product manuals that are stored in the customer data center.

Step D: The ingestion application uses the discovery APIs to add the data center content to the collection.

Step E: Subject matter experts train the conversation.

Products used in the reference architecture implementation

IBM Watson Discovery Service

The Watson Discovery Service Ingests, parses, indexes, and annotates content using cognitive functions.
It allows you to add a cognitive search and content analytics engine to applications to identify patterns, trends and actionable insights that drive better decision-making. Securely unify structured and unstructured data with pre-enriched content, and use a simplified query language to eliminate the need for manual filtering of results.

Here is a 10 Minutes of IBM Tech segment which presents an introduction to the Watson Discovery Service. The video will walk you through the creation of the service, uploading content, and querying the content.

Click Here to view a DEMO of IBM Watson Discovery.

IBM Watson Conversation Service

Watson Conversation allows you to add a natural language interface to your application to automate interactions with your end users. Common applications include virtual agents and chat bots that can integrate and communicate on any channel or device. You can train Watson Conversation service through an easy-to-use web application, designed so you can quickly build natural conversation flows between your apps and users, and deploy scalable, cost effective solutions.

Conversation enables creating virtual agents and bots that combine machine learning, natural language understanding, and integrated dialog tools to provide automated customer engagements. It provides an easy-to-use graphical environment to create natural conversation flows between your applications and your users.

This video is a walk through of Conversation Service’s tooling main components. The topics covered and the time markers are listed below. If you’d like more in-depth information on some of the topics mentioned, check out the links provided.

Click Here to view a DEMO of IBM Watson Conversation.


IBM Cognitive APIs

Components that add value to the cognitive applications.


IBM Watson® Speech to Text

IBM Watson Text to Speech

IBM Watson Tone Analyzer

IBM Watson Document Conversion

IBM Watson Natural Language Understanding

IBM Watson Natural Language Classifier

IBM Watson Personality Insights

IBM Watson Visual Recognition

Here is a video on how Watson’s APIs make it fast and simple to build cognitive capabilities right into your solution.

Click here to view a DEMO of IBM Watson Visual Recognition.