Machine learning and artificial intelligence and their applications in customer care solutions are a logical continuation of our 20-year effort and democratization of clouds and technology is available to every customer. We bring you their applications:
Chatbot
Generative AI Foundation Models based Chatbot
We design, implement and deliver chatbot based on foundation models (FM) from leading startups such as Cohere, AI21, Claude, Amazon Titan using generative AI for your enterprise chatbot usecases. We extend them with retrieval augmented generation (RAG) to fetch the newest business data and context. We learn the chatbot just the topics and context of your business and for your needs. We deploy it both to the cloud and also on premise.
Oracle Digital Assistant
Say Hello to Enterprise Conversational AI
CCW offers consultancy, configuration, development and integration of the Oracle Digital Assistant also so called chatbot.Oracle Digital Assistant delivers a complete AI platform to create conversational experiences for business applications through text, chat, and voice interfaces.
The platform is so called Conversational AI which has following features :
- Generative AI features
- Nature language understanding and machine learning
- AI-powered voice
- Analytics and insights
- conversational designer
- dialogue and domain trainer
- native multilingual support
- multichannel support
- automated bot-to-agent transfer
Key features
- Conversationl Dialog Manager
- user context,
- Hierarchy,
- Dialog Types
- Advance natural language understanding (NLU) and AI powered
- Deep user input understanding,
- Tailored for Enterpise use cases,
- Multi-Lingual,
- Gen AI features
- No-code / Low-Code Platform
- Open Platform,
- easy to Integrate
- visual flow designing
- headless API
- one assistant for all applications
- prebuilt skills and templates
- multi-purpose
- proactive and predictive engagement
- complex cross skills interactions
- multimodality in user interfaces
- generative AI with SQL's dialogs
More information https://www.oracle.com/chatbots/
Menu driven Chatbot
- single page app developed in Angular
- Using REST API for the communication with the contact center, CRM and backend
- Google map api for the localization and geocoding
- deployed in dockers and possible in the cloud and also on premise
- dialog flow in json configuration
- possible integration with the translation service and with AI for sentiment recognition
Microsoft Azure OpenAI Conversational AI
AI-generated bots, questions and answers and contact center solutions to streamline and improve customer service.
The GPT-35-Turbo and GPT-4 models are language models that are optimized for conversational interfaces. The models behave differently than the older GPT-3 models. Previous models were text-in and text-out, meaning they accepted a prompt string and returned a completion to append to the prompt. However, the GPT-35-Turbo and GPT-4 models are conversation-in and message-out. The models expect input formatted in a specific chat-like transcript format, and return a completion that represents a model-written message in the chat. While this format was designed specifically for multi-turn conversations, you'll find it can also work well for non-chat scenarios too.
In Azure OpenAI there are two different options for interacting with these type of models:
- Chat Completion API.
- Completion API with Chat Markup Language (ChatML).
Some sample usecases for customized scenarios of Azue OpenAI for conversational AI :
- Azure OpenAI Virtual Assistant
- AI Powered Call Center Intelligence Accelerator
- Enterprise Chat with Azure Search
Azure AI Bot Service
Is to design and build enterprise-grade conversational AI bots.
Amazon Lex
is to build bots with Conversational AI.
Powered by the same technology as Alexa, Amazon Lex provides you with the tools to tackle challenging deep learning problems, such as speech recognition and language understanding, through an easy-to-use fully managed service. Amazon Lex integrates with AWS Lambda which you can use to easily trigger functions for execution of your back-end business logic for data retrieval and updates. Once built, your bot can be deployed directly to chat platforms, mobile clients, and IoT devices. You can also use the reports provided to track metrics for your bot. Amazon Lex provides a scalable, secure, easy to use, end-to-end solution to build, publish and monitor your bots.
- Natural conversations
- High quality speech recognition and natural language understanding
- Context management
- 8 kHz telephony audio support
- Multi-turn dialog
- Builder productivity
- Visual Conversation Builder
- Powerful Lifecycle Management Capabilities
- One-click deployment to multiple platforms
- Streaming conversations
- AWS service integrations
- Integration with Amazon Kendra
- Integration with Amazon Polly
- Integration with AWS Lambda
- Contact center integrations
- Amazon Connect
- Genesys Cloud CX
- Amazon Chime SDK
- AWS Contact Center Intelligence (CCI)
Amazon Bedrock
Designed to build and scale generative AI applications with foundation models.
Choice of models :
- Amazon Titan
- Jurassic
- Claude
- Llama 2
- Stable Diffusion
- Command
Amazon Bedrock can be used to build assistants that understand user requests, automatically break down tasks, engage in dialogue to collect information and take actions to fulfill the request.
It can also be designed to do search, text summarization, image generation and text generation .
Automate your IT processes, especially CRM and multichannel solutions with AI
- email classification and AI based routing and processing
- sentiment search in the customer multichannel communication : voice, email, chat, sms
- process automation
- GDPR data protection and search
- IT security automation
- Devops bot
Language Services
Natural Language Understanding (NLU) is used to extract information from documents, emails, chats and customer communication. Based on the model used the language can be detected, customer sentiment and opinions, text classification. All these information can be used to orchestrate business processes such as prioritize emails for routing, automatic closure of claims, service requests.
The language AI can do following tasks :
- Analyze sentiment and mine opinions
- detect language
- classify text and extract information
- Personally Identifiable Information (PII) detection
- Document summarization
- Conversation summarization
Azure AI Language Studio
Azure Example of sentiment analysis using Azure AI Language Studio using Azure AI Language service is analysing customer complaint about visiting telco shop in the shopping mall.
{
"documents": [
{
"id": "id__13312",
"sentiment": "mixed",
"confidenceScores": {
"positive": 0.17,
"neutral": 0.27,
"negative": 0.56
},
"sentences": [
{
"sentiment": "positive",
"confidenceScores": {
"positive": 0.65,
"neutral": 0.34,
"negative": 0
},
"offset": 0,
"length": 72,
"text": "Dobrý deň, Chcem reklamovať Vašu službu vo Vašej predajni v OC Central. "
},
{
"sentiment": "negative",
"confidenceScores": {
"positive": 0.03,
"neutral": 0.35,
"negative": 0.62
},
"offset": 72,
"length": 75,
"text": "Chcel som si kúpiť paušál, no v obchode nebol nikto ochotný sa mi venovať. "
},
{
"sentiment": "negative",
"confidenceScores": {
"positive": 0,
"neutral": 0.38,
"negative": 0.62
},
"offset": 147,
"length": 102,
"text": "Keď som prišiel po radu, povedali mi, že vaše systémy sú mimo prevádzky a mal by som prísť ďalší deň. "
},
{
"sentiment": "negative",
"confidenceScores": {
"positive": 0,
"neutral": 0,
"negative": 1
},
"offset": 249,
"length": 22,
"text": "som velmi nespokojny. "
},
{
"sentiment": "neutral",
"confidenceScores": {
"positive": 0.16,
"neutral": 0.84,
"negative": 0
},
"offset": 271,
"length": 23,
"text": "s pozdravom Jozef Novák"
}
],
"warnings": []
}
],
"errors": [],
"modelVersion": "2022-11-01"
}
AWS Amazon Comprehend
AWS Example of Personally Identifiable Information (PII) analysis mode in AWS Comprehend service
API call
{
"Text": "Good day,\nI want to complain about your service at your store in OC Central. I wanted to buy a flat rate, but there was no one in the store willing to attend to me. When I came for advice I was told your systems were down and I should come another day. I am very dissatisfied.\nSincerely,\nJozef Novák",
"LanguageCode": "en"
}
Result
{ "Entities": [ { "Score": 0.9995710253715515, "Type": "ADDRESS", "BeginOffset": 65, "EndOffset": 75 }, { "Score": 0.9999931454658508, "Type": "NAME", "BeginOffset": 288, "EndOffset": 299 } ]
}
Oracle Cloud Infrastructure AI Service – Language
OCI Example of complex analysis using language detection, text classification, named entity recognition, key phrase extraction, sentiment analysis.
AI Services for variety of industries and usage
- Anomaly detectors
- Translators
- Face APIs
- Computer vision
- Intelligent Recommendations
- Predictions
- Generative AI to design products
- Generative AI to create blogs and marketing text
- and much more
Conclusion
AI, ML, Generative AI are very often used terms to adapt into business growth and success. The development of the AI technologies is faster then the implementation into real life and often creates confusion and stress. The ML , AI, Generative AI are tightly connected with the need of very powerful computing, memory requirements, GPU requirements and storage requirement beyond the possibilities of even greatest enterprises. The best option to leverage them is to use them in and from the cloud. Second important decision is to use them for right purpose and process. We recommend to select good partner which has a multi-cloud knowledge to recommend you the right services with the right In this news we have listed some options from various cloud providers. CCW is learning and working hard to support you on this journey and get friendly with AI.
We know and have know how to implement other uses of artificial intelligence and learning such as image processing, data mining, speech recognition. Contact us if you are interested !