Page 102 - ITU Journal Future and evolving technologies Volume 2 (2021), Issue 5 – Internet of Everything

ITU Journal on Future and Evolving Technologies, Volume 2 (2021), Issue 5

Fig. 8 – Bot tests: request of data and setting of the device

con igure the bot and use it to interact naturally with the
Configuration Flow
1.0
IoT platform. We speci ically focused on platform access,
0.8 device setting and data request. It has to be said that for
these experiments the operations carried out were sim‑
Scores 0.6 ple but still encouraging for future developments. One of
0.4 the most interesting actions is certainly the ability to de‑
0.2 ploy applications quickly and easily as well as being able
Best
Worst to use the bot as a guide for troubleshooting, knowing in
0.0
1 2 3 4 5 6 7 8 9 10 real time if the various devices are faulty or malfunction‑
Questions
ing, so as to restart them automatically.
Fig. 9 – Scores that have been obtained by matching the queries with the
intent during the platform accessing activities
ACKNOWLEDGEMENT
Data Manage Flow
1.0 This work has been partially found by the POR
FESR Sardegna 2014 with the project Farmainforma
0.8
(RICERCA_1C‑38).
Scores 0.6
0.4
REFERENCES
0.2
Best
Worst [1] i. Gartner. 2020. URL: https : / / www . gartner .
0.0
1 2 3 4 5 6 7 8 com / smarterwithgartner / top - cx - trends -
Questions
for - cios - to - watch / # : ~ : text = Chatbots \
Fig. 10 – Scores that have been obtained by matching the queries with %2C \ %20virtual \ %20assistants \ %20and \
the intent during the setting of the devices and data retrieval
%20robots , up \ %20from \ %2015 \ %25 \ %20in \
%202018..
8. CONCLUSIONS [2] G. Neff and P. Nagy. “Automation, Algorithms, and
Politics Talking to Bots: Symbiotic Agency and the
This study has investigated the possibility of integrating
Case of Tay”. In: International Journal of Communi‑
a virtual assistant, developed in the form of a chatbot,
cation 10.0 (2016).
within an IoT platform to help and guide the user to eas‑
[3] J. Weizenbaum. “ELIZA—a Computer Program for
ily carry out the various operations that would otherwise
the Study of Natural Language Communication be‑
be cumbersome and sometimes complicated. This need,
tween Man and Machine”. In: Commun. ACM 9.1
as we know, derives from the fact that the con igurations
(1966), pp. 36–45.
and requests for data, for an inexperienced user, are not
immediate but may require various steps to be completed [4] R. Wallace. “The anatomy of A.L.I.C.E”. In: 2009,
and may be frustrating. pp. 181–210.
A bot has been then developed which, thanks to a natu‑
[5] R. Kar and R. Haldar. “Applying chatbots to the in‑
ral language understanding engine, is able to process the
ternet of things: Opportunities and architectural
user’s requests formulated in a natural language. The bot
elements”. In: arXiv preprint arXiv:1611.03799
essentially works as a mediator between the real world
(2016).
and the virtual world. In the experiments that have been
carried out it has been possible to see how simple it is to
90 © International Telecommunication Union, 2021