AENOR: Artificial Intelligence for the advanced search for regulations
Historically, information retrieval processes consist of taking advantage of information system resources relevant to a specific need. And these searches are usually based on indexing text or other content, which means that the results obtained are not always the desired ones.
This is further exacerbated when the collection of documents being searched is extremely large.
Plain Concepts designed an innovative project for AENOR to implement artificial intelligence solutions and cognitive services using the Microsoft Azure platform, based on two components: a search engine optimised with artificial intelligence and a virtual assistant / bot.
Aenor, leader in the certification of management systems, products and services, is responsible for the development and dissemination of UNE standards. It has distributed more than 50,000 of these certifications, to which must be added all the standards published by the standardisation bodies.
As part of a digitalisation process designed to boost both the organisation’s own productivity and the services it offers its users, Aenor had set itself the objective of presenting increasingly affordable services and providing a faster response to its customers. This objective included the digitalisation of the standards it disseminates and increasing user accessibility to the extensive knowledge base on standards and certifications.
The process :
The development of a virtual assistant or bot equipped with artificial intelligence was designed in the first phase to make it easier for employees to resolve any queries that users might have without having to leave their productivity environment.
A second phase was envisaged whereby, by visiting the AENOR website, it would be the users themselves who, with the help of the bot, would be able to locate the information they need more easily than by entering a database with all kinds of documents to sift through.
The main feature of the search engine designed by Plain Concepts is the use of artificial intelligence and machine learning to facilitate, through a vocabulary extension based on articles hosted on Wikipedia, users’ searches and the results obtained by both term matching and semantic searches.
Results
- Improving decision-making
- Achieve more efficient processes by applying machine learning, visual computing, text and sentiment analysis techniques.
- Facilitate user searches and the results obtained.
We are ready for new challenges
