Bot Answering Machine
The system allows to train its own Bot to be able to answer phone calls, greet user over the phone/sms, provide information about client’s services
The system allows a business to train its own chatbot that will be able to answer phone calls, greet user over the phone/sms, provide information about a client’s services and also help a user to schedule an appointment based on the available time slots.
The application is HIPAA-compliant and has emergency calls scripts. There is also a dashboard where clients are able to create, configure and train very own conversational agent.
Solution
NLP, NER, Speech to Text, Text to Speech
Project Team
1 Tech Lead, 1 Full-stack developer, 1 BA/PM, 1 QA engineer
Tech Stack
Technical Solution
Because of the nature of the chatbots and in spite of some specific application requirements the project is based on the following technologies:
• Natural Language Processing (NLP)
as application should be able to understand human’s natural language and translate it into the signals can be understand by machine / program. In our case we are saying about Natural Language Classification (NLC) problem.
• Named-entity Recognition (NER)
component is required because such things as products, pricing, location and mainly time and dates should be recognized and extracted from the user’s speech. Thus the system will be able to appropriately schedule the appointment of practitioner and user.
• Speech to Text
is a component of the system which is responsible for translating recorded/streamed voice into the text which then can be processed by NLC component.
• Text to Speech
a component that is responsible for converting predefined text answer to voice, thus the answer can be transferred to user via phone.
As the team was developing an MVP, the speed to market is one of the key factors. That is why instead of third-party services such as Google Tensorflow, API.ai we strongly suggested using IBM Watson services which can help with solving project tasks. Especially the following:
• Watson Conversation
Quickly build and deploy chatbots and virtual agents across a variety of channels, including mobile devices, messaging platforms, and even robots.
• Watson Speech to Text
Easily convert audio and voice into written text for the quick understanding of content.
• Watson Text to Speech
Convert written text into natural-sounding audio in a variety of languages and voices.
• Voice Gateway
Cognitive Self-service agent. IBM Voice Gateway connects to a telephone network and routes the calls through Watson Speech-to-Text, Conversation, and Text to Speech services.
Voice Gateway is a kind of orchestration tool which was built with the main idea of helping with building of Interactive Voice Response system. It tights / orchestrates together the following IBM services for that purpose: Watson Conversation, IBM Speech To Text, IBM Text to Speech etc. The very base scenario IBM Voice Gateway helps to solve is the following:
The following diagram describes the main system components and possible deployment scheme:
Service Orchestration engine’s main function can be the following:
Service Orchestration engine’s main function can be the following:
- To de-identify requests to remove personal information such as PHI, PII, and PCI before it is sent to the Conversation service
- To personalize responses from the Conversation service, for example by using customer location information to provide a personal weather forecast
- To enable telephony features, such as including caller ID or collecting DTMF digits for account numbers
- To customize interactions with customers by using APIs
- To use Voice Gateway state variables, for example to complete a long transaction
- To integrate voice security by using DTMF or biometrics
Related Projects
All ProjectsDesign for Emergency Mobile App for Ambulance Call
Design for Emergency Mobile App for Ambulance Call
- Healthcare
The ultimate goal of the project was to create a life-saving emergency app to enable users to get help when one’s life is at stake and every second counts. In this case study, we focus on the design aspects of the project and reveal how our Design Team’s expertise helped to reconcile conflicting requirements and create an effective user-centered design.
Patient-centric Unified EHR/EMR Platform
Patient-centric Unified EHR/EMR Platform
- Healthcare
Patient-centric AI-based health record exchange platform that connects to hospital’s patient management systems, assembles and securely stores users’ health data. This platform allows the patient to own his personal health data and provide access to it other healthcare organizations on demand.
TeleMedicine Platform for Women’s Mental Health
TeleMedicine Platform for Women’s Mental Health
- Healthcare
A telemedicine platform for women to access a therapist, approach a mentor for support or become a mentor for others, and talk to other women in a safe, stress-free, and supportive environment.
Web & Mobile Pest Forecasting Application
Web & Mobile Pest Forecasting Application
- Artificial Intelligence
Web and mobile applications for farmers to take care of their yield crop, see predictions on pests, weather forecasts for a specific field, accept notifications on pest danger. This modern B2B platform in AgriTech sector is being developed for one of the largest research institutes in the USA. The users of the product are leading food production companies in North America and South America.
Design for Finance Data Management Platform
Design for Finance Data Management Platform
- Fintech
- Artificial Intelligence
A web app for people working in the financial sector to create analytical models. The app uses AI-based predictive modules reflecting the credit cycles to automate decision-making in Finance. Unlike the traditional statistical approach when making one analytic model takes 2-3 months, the application enables users to build, test, and deploy multiple predictive financial models within just a few clicks.
Educational Mobile App for CanadaQBank MCCEE QBank
Educational Mobile App for CanadaQBank MCCEE QBank
- Healthcare
- Education
Educational mobile app for the medical students. Allows to access synchronized CanadaQBank MCCEE question bank data across all platforms, makes possible for users to create a test with their customized level of difficulty/subjects, view test history, continue their next test/assess history from another device etc.
Credit Scoring SaaS App for Financial Organizations
Credit Scoring SaaS App for Financial Organizations
- Fintech
- Credit Scoring
- Machine Learning
The system is a SaaS platform allowing the client to evaluate solvency and reliability of the potential borrowers using statistical methods of analysis of the historical and nontraditional data sources such as social network profiles and others. It allows the client to upload his normalized and anonymized database of previous loans data, build mathematical models and calculate the credit score of the future potential borrowers entering their data through the system’s web interface.
Contact Form
Drop us a line and we’ll get back to you shortly.