CONTEXT & issues
Throughout the life cycle of industrial and nuclear facilities, operators generate a significant volume of documents in a variety of formats and on different mediums.
This information, which is essential for maintenance, audits, upgrades, extensions and decommissioning operations, requires regular and reliable access. However, traditional document management systems are now reaching their limits when faced with the scattered nature and complexity of this data.
The challenge is therefore to facilitate access to and use of this data through new capabilities for aggregation, structuring and querying, in order to make better use of existing information and strengthen decision support, at both operational and commercial levels.
the solution
DeepFinder is a solution developed by Assystem, based on a web-based architecture that provides a single point of access for exploring document data. It combines artificial intelligence (AI) with natural language processing (NLP) and generative AI capabilities to help users search for, structure, secure and utilise knowledge drawn from heterogeneous document repositories.
DeepFinder enables you to:
- Distribute documentary data across different types of corpus and different levels of accessibility
- Digitise documents and classify them by subject area
- Perform syntactic and semantic indexing of documents for rapid data retrieval
- Query document repositories using natural language or keywords to obtain accurate and consolidated answers.
- Create domain-specific ontologies
- Secure access to sensitive documents
- Consult domain experts via a forum
CHARACTERISTICS OF THE SOLUTION
The DeepFinder solution mixes traditional techniques for capturing and classifying textual documents (EDM, search engine) with the use of ontologies and new Deep Learning and Artificial Intelligence (AI) technologies applied to natural language processing (NLP).
The solution uses an innovative indexing engine that can search through millions of documents in a few seconds and return accurate responses to queries phrased in natural language. It relies on advanced models capable of contextualising information and consolidating content from multiple sources, in order to provide reliable and actionable results.
DeepFinder can be deployed across multiple data catalogues, with user management that allows access to be restricted to specific catalogues. Once deployed, DeepFinder synchronises data at a defined frequency, or on demand, while remaining available for use at all times.
objectives
-
DEMATERIALISE and TRANSFORM paper or digital documents into machine-readable text and data
-
CLASSIFY documents by subject area and key terms
-
SEARCH and STRUCTURE information and data contained in documents by their semantics due to Question Answering systems (search engine)
-
PROVIDE A SINGLE-ENTRY POINT to this mass of documents
-
SHARE information between actors
-
MANAGE several file catalogues
-
SECURE the storage and access to documents and data
Clients BENEFITS
-
Exploiting archived data
-
Quick access to data
-
Relevant data analysis
-
Easy to use
-
Decision support
-
Reduction of uncertainties
-
Data privacy management
-
Knowledge capitalization
-
Leveraging business expertise through a collaborative space