Bot Answering Machine
The system is able to train its own Bot to be able to answer phone calls, greet users over the phone/SMS, and provide information about a client’s services.
The system allows a business to train its own chatbot that will be able to answer phone calls, greet users over the phone/SMS, provide information about a client’s services, and help users 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 their 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 / Platforms
Technical Solution
Because of the nature of chatbots and specific application requirements, the project is based on the following technologies:
• Natural Language Processing (NLP)
The application must be able to understand natural human language (and the variations that come with it) and translate it into signals that can be understood by machine/program. In our case, we are saying about Natural Language Classification (NLC) problem.
• Named-Entity Recognition (NER)
This component is needed to be able to recognize and extract important details like products, pricing, location, and date/time from users’ speech.. This allows the system to appropriately schedule appointments between practitioners and users.
• Speech to Text
This component is responsible for translating recorded/streamed voices into text, which can then be processed by the NLC component.
• Text to Speech
This component is responsible for converting predefined text answers to voice, which is then transferred to the user via phone.
As the team was developing an MVP, speed to market was identified as one of the key factors. That is why instead of using third-party services such as Google Tensorflow and API.ai, we strongly suggested using IBM Watson services because they can help with solving project tasks. We recommended 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 a 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 that was created to help build an Interactive Voice Response system. It ties together the following IBM services for that purpose: Watson Conversation, IBM Speech To Text, and IBM Text to Speech. The main use case for IBM Voice Gateway is the following:
The following diagram describes the main system components and a possible deployment scheme:
Service Orchestration engine’s main function can be the following:
Service Orchestration engine’s main function can be the following:
- De-identify requests to remove personal information such as PHI, PII, and PCI before it is sent to the Conversation service
- Personalize responses from the Conversation service, e.g., using a customer’s location information to provide a personalized weather forecast
- Enable telephony features, such as including caller ID or collecting DTMF digits for account numbers
- Customize interactions with customers by using APIs
- Use Voice Gateway state variables, e.g., to complete a long transaction
- Integrate voice security by using DTMF or biometrics
Related Projects
All Projects
Financial Data Analytical Platform for one of top 15 Largest Asset Management
Financial Data Analytical Platform for one of top 15 Largest Asset Management
- Fintech
- Enterprise
- ML/AI
- Project Audit and Rescue
AI-based data analytical platform for wealth advisers and fund distributors that analyzes clients’ stock portfolios, transactions, quantitative market data, and uses NLP to process text data such as market news, research, CRM notes to generate personalized investment insights and recommendations.
Contact Form
Drop us a line and we’ll get back to you shortly.
For Quick Inquiries
Offices
8, The Green, STE road, Dover, DE 19901
Żurawia 6/12/lok 766, 00-503 Warszawa, Poland