Browse Prior Art Database

A method and system a Smart Conversational System for dynamic response based on the User's context and queries tailored with User demographic information. Disclosure Number: IPCOM000249562D
Publication Date: 2017-Mar-03
Document File: 4 page(s) / 63K

Publishing Venue

The Prior Art Database


This article describes a Smart Conversational System to provide dynamic response to user queries, augmented with the user's context and demographic information. The system will also leverage machine learning, NLP (Natural Language Processing), Image and Sound processing and other Cognitive technologies to deliver chat responses in a secure and customized manner.

This text was extracted from a PDF file.
This is the abbreviated version, containing approximately 52% of the total text.


A method and system a Smart Conversational System for dynamic response based on the User's context and queries tailored with User demographic information .

Disclosed is an article that describes a Smart Conversational System that leverages Cognitive technologies to make conversations secure, augmented with contextual information, user demographics and preferences.

Current conversation services use request and response mechanism based upon questions asked by the user while leveraging pre-defined response styles. However in more complex real life scenario, when the user is using his mobile phone or tablet for conversation, the service can be made engaging and intelligent by introducing dynamic decision making capability coupled with machine learning techniques to securely respond to user queries considering the user's context, demographics and surrounding environment (ambient conditions).

Use Case: When the user asks a question related to say bank account balance, the response can be presented in one or multiple ways:

The response could be presented as text on the chat interface of the user's mobile 1. screen

The system can speak out loud the amount of money in the user's bank balance2.

The system can dynamically identify the user's ambience and context; for example, if 3. the user is using his bluetooth headset, then the conversation system can speak out the balance amount through the Bluetooth headphone to the user along with potentially presenting the information on his mobile device as well.

If user is in crowded place then the system will present the data on his screen in a 4. format which is easily understood by the user in attractive fonts and contrast (based on user preference and machine intelligence). However the system will prompt the user to slide his fingers across the screen as a confirmation to render the balance.

The system shall also determine the user's ambient condition through camera on the 5. mobile device or by detecting the level of background noise in the surrounding coming in from the mic and then decide how to present the information. The system will also alert the user if the selected mode of information delivery have any security vulnerabilities. The system can also take into account, if user needs any special accessibility requirement and then use it.

The system shall use the user's demographic profile to customize the conversation 6. and make the conversation system more engaging for the user. For i.e., the system shall use the user's age, gender, regional and other preferences (say preferred accent, dialect, selected voice i.e. male or female etc.)

The system will be trained through machine learning with the user's voice. When any 7. sensitive information is sought by the user (say bank balance, credit card details


etc.), the system will automatically switch to the enhanced security mode and first authenticate the user using voice recognition. On successful matching of the voice, the system will allow the con...