Name: | Description: | Size: | Format: | |
---|---|---|---|---|
6.76 MB | Adobe PDF |
Abstract(s)
This project described in this dissertation is being carried out for the Ministry
of Social and Economic Inclusion (MIES) of Ecuador based on its current problems.
The de ciencies that government entities have to help their citizens with
information and paperwork has exceeded their operational capacity. The MIES
currently has a Marketing and Information department that is saturated with
questions through channels such as call centers, information centers in their of-
ces and social networks outside their o ce hours.
In recent years there has been an increase in requests for information through
digital channels such as its Facebook page, since internet access to places far
from the big cities has increased. This has been seen as an opportunity for
improvement by creating an chatbot agent that helps citizens 24 hours a day, 7
days a week. Most of the queries can be made through a query to their internal
data and this allows the operational burden of the operators to be released to
carry out management processes and not just information.
Many public and private companies have resorted to using chatbots to help
their users with simple information tasks. They have also relied on these technological
tools to create registration and management functions. Today we can
use chatbots development tools and platforms such as Dialog
ow that allow to
create chatbots in a manageable and scalable way according to needs. Facebook
has multiple connection tools that allow it to integrate safely and e ciently with
its platforms such as Facebook Messenger, allowing customers to create applications
that will reach the majority of citizens who have internet access.
Developing a chatbot agent can be a simple and straightforward task, but in
which the remaining time must be invested in training and helping the chatbot
agent to understand words or idioms of language used in di erent regions of the
same country. In the development of a chatbot, the training cycle is constant
and allows the chatbot to increase its ability to understand the users who use
them.
In the tests carried out on this chatbot, it was concluded that although the
use of these tools allows to release the operational load, it does not avoid the
need for users to interact with natural persons, but the requirement is drastically
reduced. In the tests it was also obtained that many problems can be obtained
by nding a wide range of synonyms and local expressions, but correct training
and constant review of the answers provided helps the chatbot to self-train and
evolve its answers over time interactions.
Description
Keywords
Chatbot Dialogow Facebook Developers Natural Language Processing