Journal of Engineering Design,
Год журнала:
2024,
Номер
unknown, С. 1 - 21
Опубликована: Апрель 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.
Computers in Industry,
Год журнала:
2024,
Номер
162, С. 104129 - 104129
Опубликована: Июль 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.
Engineering Reports,
Год журнала:
2024,
Номер
unknown
Опубликована: Июль 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
