The Omni-Chatbot Platform tool that is based on artificial intelligence

The purpose of the Omni-Chatbot Platform is to understand the user’s statements and, based on the available knowledge base, react to the intention of the statement, e.g. to understand the question and answer it.

This process is based on detecting defined meanings and contexts. Thanks to this approach, the user can freely formulate his/her statement to which they will always receive the correct reaction from the Platform.

Artifical Intelligence in business
Advanced chatbot for companies and institutions

Why Omni-Chatbot

The majority of suppliers of conversation systems provide solutions dedicated to one communication channel (e.g. smartphones, internet messengers or chat). In the times of multi-channel communication (omni-channel) it carries the necessity to maintain and integrate various solutions, and the analytics is far from perfect.

When creating the Omni-Chatbot we built a solution, which based on a one-time prepared knowledge database is able to work in various communication channels and provide a full image of the interactions with customers in one place. Such an approach is cheaper to install (one software installation, one integration works), impalement (one-time configured database, one training for the administrators) and maintain (one database in one place, one analytical tool collecting data from various channels).

Safety and efficiency

The Omni-Chatbot platform was created for corporate customers and large public institutions. Therefore, when creating the solution, we focused on the security, high performance and scalability of the solution.

OCP is based on the JAVA language and the PostgreSQL or Oracle corporate databases. The solution is regularly/continuously subjected to security tests and the architecture is adjusted to the standards of the high availability solutions (distributed data processing architecture, load-balancers, etc.).

Safety and efficiency of Omni-Chatbot Platform
Enterprise class architecture from Stanusch Technologies

Enterprise class architecture

OCP consists of many elements adjusted to our customers’ needs and architecture, in which it is to be implemented. The core of the solution is an application server based on microservices and the Administrative panel server. Depending on the selected interface automatic speech recognition (ASR), text-to-speech (TTS), interactive voice response (IVR), or middleware (for instant messengers) modules are added.

The data collected by OCP (log files) can be subjected to additional analytics by external solutions, such as Kibana or IBM Watson Explorer. Additionally, we also make the application programming interface, which enables creation of own solutions and interface (e.g. mobile applications or robots), available to the customers.

Flexible operation models and licenses

The OCP platform can be installed on both our clients’ infrastructure ( on-the-premises) and in the cloud (private or in one of the available locations in the European Union that are managed by Stanusch Technologies – Poland, Ireland or Germany).

The solution can also be licensed in the form of a traditional license as well as in the Cost-Per-Call model, under which our customers do not incur license and implementation costs and the billing is based solely on the actual number of interactions.

New technologies on the Omni-Chatbot Platform
Developers create modern chatbots

Advanced NLU tools

Twelve years of experience, realization of more than 130 projects and the ongoing development of the system contributed to the fact that our natural-language understanding algorithms (NLU) are one of the best in the world. Moreover, from the very beginning they were designed to handle the complexities of the Slavic languages grammar (i.e. flexible syntax grammar), rich inflection and word-formation diversity (synonyms, diminutives).

OCP understands users’ statements trough detecting intentions together with taking into consideration the context and information collected during conversation or derived from external systems. The conversation might be both of a ‘casual’ character, and also be a part of a structured dialog (e.g. authorization process). The way in which the system interprets a user’s statements can be controlled using the Administrative panel, which is equipped with tools facilitating the configuration process, such as intention patterns, ontologies, synonyms or word inflection databases.

NLG adapted to the communication channel

Depending on the communication channel, responses can take various forms, e.g. text (SMS channel), text with tags or simplified HTML (communicators, e.g. Facebook Messenger, Skype4Business, Skype, Slack), voice (telephone channel, mobile application), voice with a video avatar (chatbot on the website, multimedia kiosks, pseudo-holograms), a HTML multimedia document with the possibility of embedding JavaScript (WWW portal).

The responses that are generated by OCP can have different content variants depending on the context or the information that is downloaded from external solutions. System responses can also be generated on variants that are based on previously collected information. The speech content is controlled by the Groovy scripting language and special tags allow for the control of the speech synthesis.

A tool adapted to various communication channels
Easy chatbot configuration

Administrative panel

Configuration of the solution might be entirely conducted by trained members of our customer’s team or by Stanusch Technologies specialists. Advanced Administrative panel makes it possible to configure knowledge database, establish business rules concerning how the solution works and integrate the solution with external data sources. The panel is also equipped with tools automatizing the knowledge base testing (manual tests, automatic tests, conflict detection, etc.) and tools facilitating system learning.

The analytical part supplies current information on the way the platform is working and categorizes all conversations, whereas the machine learning techniques are used to detect trends and generate managerial alerts if abnormal situations occur (e.g. sudden increase in the number of complaints).