Emergency
response
missions
require
rapid
and
accurate
information
processing
in
noisy,
chaotic
environments
where
oral
communications
present
significant
challenges,
leading
to
cognitive
overload
impaired
decision-making.
Augmented
Reality
(AR)
Large
Language
Models
(LLMs)
have
shown
potential
enhancing
situational
awareness
by
integrating
digital
data
with
the
physical
world
improving
dialogue
management.
However,
effectively
synthesizing
these
technologies
into
a
system
that
aids
first
responders
real-time
remains
challenge,
clear
need
for
research
validate
their
impact
on
clarity
coordination
of
during
high-pressure
missions.
This
study
investigates
integration
AR
LLMs
emergency
response,
focusing
controlling
load
related
communications.
Utilizing
AR's
capability
overlay
critical
onto
LLMs'
advanced
logic
reasoning,
aims
develop
an
AI
co-agent
aiding
audio
dialogue-based
tasks
high-risk
A
customized
system,
incorporating
Microsoft
HoloLens2
monitoring,
was
tested
participants
human
factor
experiment
(N=30).
The
2x2
factorial
evaluated
effects
LLM
assistance
performance
load.
Results
showed
notable
improvements
task
accuracy
reduced
load,
demonstrating
effectiveness
supporting
operations.
findings
underline
importance
further
this
technologically
innovative
area,
crucial
optimizing
strategies.
Engineering Reports,
Journal Year:
2024,
Volume and Issue:
unknown
Published: July 7, 2024
Abstract
Maintenance
manuals
are
crucial
information
sources
for
maintenance
and
repair.
Prior
studies
explored
factual
knowledge
extraction
from
textual
documents.
However,
in
is
more
task‐centric
rather
than
often
documented
an
unstructured
Portable
Document
Format
(PDF),
posing
challenges
extraction.
Addressing
this,
this
research
develops
effective
methods
to
extract
PDF
manuals.
A
new
Task‐centric
Knowledge
Graph
(TCKG)
schema
centralized
on
task
components
(MTCs)
proposed
address
the
need
structured
representation.
method
(Heterogeneous
Graph‐based
Method,
HGM)
then
proposed,
which
enhanced
by
incorporating
visual
spatial
information.
In
experiments,
HGM
exhibits
robust
performance
process,
surpassing
baseline
Interaction
Model
with
a
Tracker
(GIT)
MTCs
13.3%,
Translate
Embedding
(TransE)
MTCs'
relation
3.8%.
series
of
ablation
also
prove
that
including
through
can
improve
over
10%.
This
supplies
valuable
insights
future
developments
Computers in Industry,
Journal Year:
2024,
Volume and Issue:
162, P. 104129 - 104129
Published: July 31, 2024
The
use
of
Digital
Intelligent
Assistants
(DIAs)
in
manufacturing
aims
to
enhance
performance
and
reduce
cognitive
workload.
By
leveraging
the
advanced
capabilities
Large
Language
Models
(LLMs),
research
understand
impact
DIAs
on
assembly
processes,
emphasizing
human-centric
design
operational
efficiency.
study
is
novel
considering
three
primary
objectives:
evaluating
technical
robustness
DIAs,
assessing
their
effect
operators'
workload
user
experience,
determining
overall
improvement
process.
Methodologically,
employs
a
laboratory
experiment,
incorporating
controlled
setting
meticulously
assess
DIA's
performance.
experiment
used
between-subjects
comparing
group
participants
using
DIA
against
control
relying
traditional
manual
methods
across
series
tasks.
Findings
reveal
significant
enhancement
reduction
load,
an
quality
process
outputs
when
employed.
article
contributes
potential
AI
integration
manufacturing,
offering
insights
into
design,
development,
evaluation
industrial
settings.
Journal of Engineering Design,
Journal Year:
2024,
Volume and Issue:
unknown, P. 1 - 21
Published: April 12, 2024
Generally,
the
existing
methods
for
constructing
a
knowledge
graph
used
in
question
answering
system
adopted
two
different
models
respectively,
one
is
identifying
entities,
and
other
extracting
relationships
between
entities.
However,
this
method
may
reduce
quality
of
because
it
very
difficult
to
keep
contextual
information
consistent
with
same
entities
models.
To
address
issue,
paper
proposes
model
called
GPB
(GlobalPointer
+
BiLSTM)
which
integrates
BiLSTM
into
GlobalPointer
through
concatenation
operations
simultaneously
guarantee
rationality
identified
In
addition,
enhance
user
experience
using
an
intelligent
motor
fault
maintenance
system,
BAC
(BiLSTM
Attention
CRF)
proposed
identify
named
questions,
BERT-wwm
classify
intentions
improve
answers.
Finally,
verify
advantages
BAC,
comparative
experiments
real
application
effects
developed
are
demonstrated
on
our
built
dataset.
The
experimental
results
indicate
that
constructed
provide
engineers
high-quality
services.
Emergency
response
missions
require
rapid
and
accurate
information
processing
in
noisy,
chaotic
environments
where
oral
communications
present
significant
challenges,
leading
to
cognitive
overload
impaired
decision-making.
Augmented
Reality
(AR)
Large
Language
Models
(LLMs)
have
shown
potential
enhancing
situational
awareness
by
integrating
digital
data
with
the
physical
world
improving
dialogue
management.
However,
effectively
synthesizing
these
technologies
into
a
system
that
aids
first
responders
real-time
remains
challenge,
clear
need
for
research
validate
their
impact
on
clarity
coordination
of
during
high-pressure
missions.
This
study
investigates
integration
AR
LLMs
emergency
response,
focusing
controlling
load
related
communications.
Utilizing
AR's
capability
overlay
critical
onto
LLMs'
advanced
logic
reasoning,
aims
develop
an
AI
co-agent
aiding
audio
dialogue-based
tasks
high-risk
A
customized
system,
incorporating
Microsoft
HoloLens2
monitoring,
was
tested
participants
human
factor
experiment
(N=30).
The
2x2
factorial
evaluated
effects
LLM
assistance
performance
load.
Results
showed
notable
improvements
task
accuracy
reduced
load,
demonstrating
effectiveness
supporting
operations.
findings
underline
importance
further
this
technologically
innovative
area,
crucial
optimizing
strategies.
