BigData Chatbot – chatbot powered by machine learning that acquires knowledge from company documents
Imagine this is the first time you’re using a company car. Unfortunately, the fuel light turns on in the middle of the route. You don’t want to bother your colleagues, so you wonder where you could find the address of the nearest petrol station cooperating with your company on your own. You know that there is such information in “The Rules Governing the Use of the Fleet for Business Trips”, but you don’t have it at hand, and even if you did, you wouldn’t imagine stopping the car on the shoulder of the road and searching through a few dozen pages because you need an answer now.
And suddenly… it dawns on you that your colleagues kept saying “if you need anything just ask the chatbot”. You stop the car, ask a question and your phone immediately displays a list of petrol stations where you can refuel your company car and you can breathe in peace again.
How will BigData Chatbot work?
BigData Chatbot uses intelligent data processing methods and artificial intelligence to extract information from large collections of company documents. Then, thanks to the acquired knowledge, it’s able to answer questions about the organization you work for at any given time. We know that there are more interesting and enjoyable activities than reading piles of company documents and studying them every time they are updated. With BigData Chatbot you won’t have to do this anymore. Simply ask BigData Chatbot a question through your browser or mobile app and get an immediate response.
Chatbot will find answers to questions given by users in large collections of documents.
Chatbot will understand synonyms (refuelling -> buy fuel; company car -> business driving.)
Who will be able to use BigData Chatbot?
BigData Chatbot will be a solution that will be used mainly by multi-departmental companies that have large numbers of structured documents in their collections, such as regulations, procedures, contracts, terms of reference, software documentation, etc. Thanks to the chatbot, thousands of employees, e.g. Customer Service Representatives will be able to minimize the time spent on simple and repetitive activities, such as searching for the relevant documents and reviewing them in order to find the information the customer needs. What’s important, BigData Chatbot can run on company servers so only authorized users will have access to them.
Although there are no keywords asked by the user in the text, such as “monthly / semi-annual / annual fee”
or “payment selection”, chatbot will find the answer that suits the best the context of the conversation.
BigData Chatbot vs full text search engine
This chatbot, unlike an ordinary search engine, performs semantic analysis of the query and examines relationships between words to give the user the most accurate and concise answers to their questions. For example, in the case of the question “What are the Service Centre contact details?” the search engine could return both of the following excerpts or only the first one, because it contains more keywords given by the user:
⦁ “At the time of the conclusion of the contract, the following Client contact details should be provided to the Service Centre: name, surname, personal identity number, address of residence”.
⦁ “Service Center – the center organizing the service is open 24 hours a day, 7 days a week, available at the phone number 22 123 45 67 and e-mail address email@example.com to which you should report the incident in order to obtain assistance”.
However, only the second excerpt answers the user’s question and only this one would be provided by the chatbot.
Chatbot will connect information from various parts of documents and remember the context of the conversation
A pioneering solution
Although a huge number of chatbots have already been created around the world for various practical purposes, BigData Chatbot will be the only tool that will use the potential of artificial intelligence to make it easier for you to work on documents in Polish and English in the next step.
Chatbot will read the technical documentation of the software, and then respond to the user’s questions regarding the use of the application.
Where did the idea for BigData Chatbot come from? Expansio has been working on its own advanced chatbot for programming programming since 2018: CodeAll (you can also read about CodeAll on this blog). In cooperation with Volkswagen Poznań Expansio, it also prepared a mobile app for communication. The next step was to think – how can this technology be developed to acquire knowledge on its own? It turned out that adding the use of artificial intelligence can significantly reduce the time and cost of preparing knowledge for chatbots – chatbot will be able to learn independently from the provided documents.
If you feel that this solution may be useful for your business and you would like to collaborate with us, please contact us at firstname.lastname@example.org – we will be happy to answer all your questions!