Ivo Pisařovic

Bio: Ivo Pisařovic is an academic researcher from Mendel University. The author has contributed to research in topics: Chatbot & Synchronization (computer science). The author has an hindex of 1, co-authored 5 publications receiving 6 citations.

Chatbots for Enterprises: Outlook

Abstract: Chatbots are going to be the main tool for automated conversations with customers. Still, there is no consistent methodology for choosing a suitable chatbot platform for a particular business. This paper proposes a new method for chatbot platform evaluation. To describe the current state of chatbot platforms, two high-level approaches to chatbot platform design are discussed and compared. WYSIWYG platforms aim to simplicity but may lack some advanced features. All-purpose chatbot platforms require extensive technical skills and are more expensive but give their users more freedom in chatbot design. We provide an evaluation of six major chatbot solutions. The proposed method for the chatbot selection is demonstrated on two sample businesses - a large bank and a small taxi service.

Development of a Location-Based Service for a Brno City District

Abstract: There are many different types of places in any city. These places include playgrounds, dog runs, cultural heritage sites and many more. A city usually wants to provide information about location and equipment of these places. The common way is via a city website. However, nowadays a much more common source of information are mobile applications. This article deals with a development of a mobile application for the Brno-North district of Brno city. The application is designed to inform the citizens of the city district about interesting places in their vicinity. The central element of the application is a map which shows where all the interesting places are located. The application is focused primarily on families; however, it can be useful for any citizen of the district.

Preprocessing of Normative Documents for Interactive Question Answering

Abstract: Every larger organisation must establish a set of normative documents to control its processes and describe solutions to common problems. These documents are usually formally written and hard to read. This leads to the necessity of different customer services. Nowadays, a lot of companies are developing chatbots to automate first-line customer support. If a company does not have a large question-answer dataset to build a chatbot, the answers can be automatically answered directly from the documents. However, we found that the automatic answering usually does not work well on the normative documents. In this paper, we describe a novel method for preprocessing of normative documents in order to use them for such automatic question answering. Our method efficiently exploits the strict document structure that is typical for normative documents. We increased the recall from 35% to 84% (for paragraph-size answers) on selected normative documents from university and bank domains.

Smart Displays: Personalisation of Information Panels

Abstract: Information panels are a common part of university or administrative buildings. We can see large panels with news or social media feeds as well as small displays on conference rooms with information about their occupancy. All these panels usually present general information without any relation to a present audience. Presentation of personalised information for a particular user can be very helpful; however, for such personalisation we must take into account many aspects: identification of users in the display vicinity, sharing of the screen among multiple users etc. This paper is focused on the architecture of such system that allows presenting customised information on information panels for users within university buildings. Our solution allows detection of a user via Bluetooth beacons. The selected close display then presents information related to the user. In case there are multiple users in the display vicinity, the system evaluates their requirements and decides how to share the display.

Effective Collaborative Mapping Based on Mobile Devices

Abstract: There are numerous situations when it is utmost important to share efficiently some spatial data among a group of people. Floods can be taken as an obvious example. Many stakeholders including mayor or rescue service workers must have actual information about the conditions in the terrain. And most importantly, all of these can contribute to the information. Among these situations involving the crisis management, we dare to mention especially the inventory process. Traffic signs, road lanes, trees, lights and many other different object must be regularly maintained. Most of the organizations use some kind of geographical information system to keep the information about the maintained property. Our article is focused on development of mobile application that allows to acquire spatial data that are later used in these information systems. Thanks to real-time data synchronization between multiple devices, field workers can cooperate and share data immediately to an operating center or with the other workers. We describe the design of our mobile mapping application, comparison with other existing solutions and problems of real-time synchronization between different devices. Finally, we provide details about application usage in different municipalities.

Graph-Based Conversational AI: Towards a Distributed and Collaborative Multi-Chatbot Approach for Museums

Abstract: Nowadays, museums are developing chatbots to assist their visitors and to provide an enhanced visiting experience. Most of these chatbots do not provide a human-like conversation and fail to deliver the complete requested knowledge by the visitors. There are plenty of stand-alone museum chatbots, developed using a chatbot platform, that provide predefined dialog routes. However, as chatbot platforms are evolving and AI technologies mature, new architectural approaches arise. Museums are already designing chatbots that are trained using machine learning techniques or chatbots connected to knowledge graphs, delivering more intelligent chatbots. This paper is surveying a representative set of developed museum chatbots and platforms for implementing them. More importantly, this paper presents the result of a systematic evaluation approach for evaluating both chatbots and platforms. Furthermore, the paper is introducing a novel approach in developing intelligent chatbots for museums. This approach emphasizes graph-based, distributed, and collaborative multi-chatbot conversational AI systems for museums. The paper accentuates the use of knowledge graphs as the key technology for potentially providing unlimited knowledge to chatbot users, satisfying conversational AI’s need for rich machine-understandable content. In addition, the proposed architecture is designed to deliver an efficient deployment solution where knowledge can be distributed (distributed knowledge graphs) and shared among different chatbots that collaborate when is needed.

Desirable Features of a Chatbot-building Platform

Abstract: There is a visible eagerness in the business community to integrate chatbots with their websites and mobile apps. They provide a humanised interface to information and can serve as digital assistants that can perform tasks on behalf of an individual. There are many commercial platforms which provide interfaces to build these chatbots. They are used by both professional software developers as well as people from non-IT backgrounds. Based on our experiences with three popular chatbot-building platforms - Google Dialogflow, IBM Watson Assistant and Amazon Lex, we present a list of desirable features that these platforms should exhibit in order to cater to their mixed user base. We also rate the availability and ease of use of these features on the current versions of these platforms.

How to Make chatbots productive - A user-oriented implementation framework

Abstract: Many organizations are pursuing the implementation of chatbots to enable automation of service processes. However, previous research has highlighted the existence of practical setbacks in the implementation of chatbots in corporate environments. To gain practical insights on the issues related to the implementation processes from several perspectives and stages of deployment, we conducted semi-structured interviews with developers and experts of chatbot development. Using qualitative content analysis and based on a review of literature on human computer interaction (HCI), information systems (IS), and chatbots, we present an implementation framework that supports the successful deployment of chatbots and discuss the implementation of chatbots through a user-oriented lens. The proposed framework contains 101 guiding questions to support chatbot implementation in an eight-step process. The questions are structured according to the people, activity, context, and technology (PACT) framework. The adapted PACT framework is evaluated through expert interviews and a focus group discussion (FGD) and is further applied in a case study. The framework can be seen as a bridge between science and practice that serves as a notional structure for practitioners to introduce a chatbot in a structured and user-oriented manner.

Chatbots for CRM and Dialogue Management

Abstract: In this chapter, we learn how to manage a dialogue relying on the discourse of its utterances. We show how a dialogue structure can be built from an initial utterance. After that, we introduce an imaginary discourse tree to address the problem of involving background knowledge on demand, answering questions. An approach to dialogue management based on a lattice walk is described. We also propose Doc2Dialogue algorithm of converting a paragraph of text into a hypothetical dialogue based on an analysis of a discourse tree for this paragraph. This technique allows for a substantial extension of chatbot training datasets in an arbitrary domain. We evaluate constructed dialogues and conclude that deploying the proposed algorithm is a key in successful chatbot development in a broad range of domains where manual coding for dialogue management and providing relevant content is not practical.