In Broadcast - August 2017 - 69

69

www.inbroadcast.com | Vol: 7 - Issue 8 | August 2017

InMedia

Broadcast Management Systems cont'd...
Machine Learning Makes Inroads
A lot of what is now referred to as AI
and machine learning (ML) is actually
just image or metadata analysis.
Rather than 'learn' themselves, the
machines need to be trained in detail
to get good results and only get better
through additional training.
Nonetheless, in terms of assisting
broadcasters and other media
companies in automating manual tasks
that improve the efficiency of media
workflows, freeing up engineers and
operators to dedicate more of their
attention to the delivery of quality
content and other performance issues,
the ML capabilities of AI are already
making significant contributions.
Imagine
Communications,
for
example,
is
seeing
significant
gains
in
operational
efficiency
through the tight integration
of its playout and scheduling
systems. "The combination
of
machine
learning
and the elimination of
traditional barriers between
operational and business
systems is helping media

companies improve efficiency through
the reduction of manual processes,
such as schedule import and export,
which also helps to reduce the
incidences of human error," says
Glodina Lostanlen, CMO.
Data Gathering
Already within Pebble Beach's
Marina automation large amounts
of data logging about a channel and
the way it's being managed, are
being gathered. "It's possible that the
application of AI and ML to the data
we capture could be used to help drive
decisions on device deployment and
resource availability," says Crockett.
"AI has the potential to help with
monitoring activity and log files across

Broadview Promo Campaign Manager

the system, with the possibility of preempting potential problems, rather
than the user waiting for something
bad to happen and then reacting to it."
Currently, Provys import and analyse
viewing data from widely spread
'people-meters', and says it clearly
recognises that Google's personal
recommendation engine concept could
easily bring significant benefits to the
monetisation of broadcasting.
"There is obviously some risk and
pain involved in allowing AI to take
over any important function, to say
nothing of the loss of another good
member of staff, and we feel that
in all these aspects of broadcasting
administration, it is still necessary to
maintain the human touch, and so we
hold with the philosophy of
"efficiency with a human
face".
One of the hot topics
now in technology in
general (not just video)
is personalisation. In the
context of BMS this can
mean personalised (e.g.
linguistic
or
cultural)
content,
personalised

commercials and promos, and
personalised recommendations for ondemand content.
"The automated generation and
manipulation of metadata, both with
regards to the content and viewer
profiles, plays a great part in the
success of this personalisation and as
such we see interaction with AI tools
at several points in the content chain,"
says Arvato's Davenport.
"We can also use smart technology
within our products themselves.
Avatega has the ability to generate
its own schedules based on channel
themes and available rights while
our S4AdOpt software maximises
revenue from advertisement contracts,
automating the placement of slots
while being aware of slot value and
contractual obligations."
AI can "definitely" play an important
role in improving accuracy and
reliability for placement," says Atkin.
BroadView's new Promo Campaign
Management tool for example learns
from previous passes and works to
deliver improved placement results
with each pass. Scheduling at both
planning and presentation level can be
more automated and done in a manner
that improves operations by learning
from past runs."
http://www.inbroadcast.com http://www.broadviewsoftware.com/ http://www.appeartv.com http://www.appeartv.com http://ibc17.mapyourshow.com/7_0/exhibitor/exhibitor-details.cfm?ExhID=3894
Table of Contents for the Digital Edition of In Broadcast - August 2017
