|
|
|
|
| The validity of this goal |
|
To achieve and prove the validity of this goal, a wireless, easy to use, intelligent, real-time diagnostic and decision support application for the mobile worker is being created - accessed via devices such as wireless earphone/microphone, PDA, mobile telephone, or laptop computer. AMIRA will be capable of being used across a diverse range of disciplines and sectors.
|
|
Building on the work and results of current and previous RTD projects,
AMIRA is widening the applicability of advanced search and reasoning
technologies to make it possible to access these through a speech
dialogue interface. Although AMIRA will be capable of being used across
a diverse range of disciplines and sectors, the focus of the work, and
the basis for the AMIRA project, is on proving the application in
providing Multi-modal assistance at the point of intervention in
time-critical, safety/business critical incidents. In this way, AMIRA
will be demonstrated as providing a tool for the mobile worker in both
fairly simple and highly complex scenarios.
132_AnnualReport_v1.doc
| |
Advanced search
Building on the work and results of current and previous RTD projects,
AMIRA is widening the applicability of advanced search and reasoning
technologies to make it possible to access these through a speech
dialogue interface. By coupling speech dialogue technologies with
search and reasoning technologies, structural CaseBased Reasoning (CBR)
will drive the intelligence behind the dialogue, generating the
questions to be automatically answered (in the same way as it does
today for Web self service but targeting speech self service). AMIRA
will provide semantically based and context aware systems that can
acquire, organise, share and reuse knowledge in structured and
unstructured format. It will extend CBR with the ability to process
trends in data, in order to be able to identify and recall cases with
similar parameter shifts. | |
Full-text retrieval
From this perspective, AMIRA represents a seamless combination of
structural CBR (CaseBased Reasoning) and full-text search. In this
context, an intelligent information access system should be able to
function seamlessly with different types of knowledge, automatically
detecting how to process a query and what knowledge source is best
suited to answer a specific question.
These
requirements can be addressed by different types of knowledge sources
corresponding to different ways of combining structural CBR and
full-text retrieval results. In particular model-driven CBR retrieval,
hybrid CBR/full-text retrieval, and model-driven full-text retrieval. |
|
|
|
|
|
|
|
|
