Insights

A Smart ChatBot for Specialist Domanis

Conversational interfaces are among the most innovative technologies of recent years, and especially the research and industry worlds are paying increasing attention to tools such as ChatBots and VoiceBots. In fact, there are many companies that have integrated virtual assistants or Conversational Agents within their business processes to communicate with customers, suppliers and consumers in a highly personalized and interactive, as well as automated, way.

Through pre-programmed dialogue structures, these AI applications enable a narrowing of the gap between users and digital architectures, allowing people to interact with devices as if they were communicating with a real interlocutor.

The article "A Smart ChatBot for Specialist Domains" stems from the close collaboration that Fiven Group has been undertaking for several years now with the University of Naples Federico II and in particular with the Department of Electrical Engineering and Information Technology to define new innovation trajectories, initiate R&D projects in an Open Innovation logic and contribute to the technological progress and digital transformation of the business and socio-cultural context.

The research aims to present a particular Chatbot for the Cultural Heritage sector, capable of responding to user queries according to increasing levels of personalization, through the collection and processing of conversations between individuals and AI interface.

The vast amount of data available in the cultural heritage sector has necessitated the definition of new infrastructures and methodologies to support users in their cultural visits so that they can fully enjoy the experience and easily locate the point of interest with respect to their desires.

Based on these assumptions, Fabio Sorrentino - Fiven's Head of Digital Solutions - and professors from the University of Naples Federico II, propose the application of a new chatbot interface architecture to cultural heritage that aims to suggest interesting places and events in the vicinity of the geographical location to users. This innovative system takes advantage of natural language processing techniques and, thanks to a user-friendly interface, allows users to ask multiple and consecutive voice questions to the system, which is able to answer each of them accurately.

As Sorrentino pointed out, "Our research shows how messaging apps are increasingly becoming the preferred channel for communicating with institutions. ChatBots, in fact, in addition to increasing operational efficiency, save time and resources by offering greater convenience and a wide range of additional services, without neglecting that part of personalization and proactivity that remain key factors for all stakeholders".

But for which users is this tool designed? Mainly for two categories: users who interact by asking questions and public or private entities who want to promote their cultural heritage or events in a smart and effective way.

Turning to the system architecture, this was developed on a dual level: the Conversational Interface (Chatbot) and the back-end server. In more detail, the Conversational Interface is based on a deep learning technique that analyzes questions posed by users on a given topic of interest through a Graphical User Interface (GUI). A given question is then processed by a Natural Language Processing (NLP) tool with the purpose of recognizing the entity name and projecting the input question into the same vector space as the training set.

The purpose of the back-end architecture is to support the conversational interface and provide services geared toward the proper conduct of tourist visits and descriptions of the relevant cultural heritage.

The outputs delivered by the back-end system are many and can be distinguished into the following four types:

1.Information about points of interest to visit, such as monuments, buildings, churches, paintings or statues;

2.Information about upcoming events by type or geographic location;

3.Information on nearby places of refreshment or rest;

4.Suggestions on cultural routes to follow according to the request or wishes made explicit by the user.

The continuous improvement of the ChatBot's performance comes from continuous learning mechanisms, made possible by the profiling of the users who use it. For each user who interfaces with the Chatbot, the system tracks and analyzes the conversational flows that have taken place, thereby ensuring that responses are always consistent and perfectly aligned with interests and requests.

Heading 1

Heading 2

Heading 3

Heading 4

Heading 5
Heading 6

Lorem ipsum dolor sit amet, consectetur adipiscing elit, sed do eiusmod tempor incididunt ut labore et dolore magna aliqua. Ut enim ad minim veniam, quis nostrud exercitation ullamco laboris nisi ut aliquip ex ea commodo consequat. Duis aute irure dolor in reprehenderit in voluptate velit esse cillum dolore eu fugiat nulla pariatur.

Block quote

Ordered list

  1. Item 1
  2. Item 2
  3. Item 3

Unordered list

Text link

Bold text

Emphasis

Superscript

Subscript

Share
Latest News

Let’s build some
future together.

Contact us
Thank you! Your submission has been received! We will get back to you as soon as possible.
Oops! Something went wrong while submitting the form.
Texture Footer