In this article, I present the fragrance knowledge in a graph model (knowledge graph) in Neo4j graph database and use it to draw some interesting inferences that can help a perfume designer better design a product. For an introduction to graph databases and Neo4j, refer to ( ). The knowledge graph in turn allows us to build or extract inferences that was not originally present in the dataset. The entity nodes and edge relations in a graph essentially captures the inherent knowledge within the dataset and hence a Neo4j graph model is often termed as ‘knowledge graph’. Graph databases, especially Neo4j is getting popular for its ability to perform interesting analytics by modeling the relationships between entities and using graph algorithms to analyze and obtain novel insights. In this article, we explore the use of the popular graph database software from Neo4j to help us run better analytics and navigate this space with ease using sophisticated algorithms Neo4j and Graph Databases Computer aided design of fragrances using Artificial Intelligence, Machine Learning and other advanced technology are being explored by researchers in USA and Europe. Hence, it is imperative that the perfume designers be provided with some automated help to better design their fragrances. In order to cater to this demand, perfume designers and manufacturers need to continuously innovate to come up with better and attractive fragrances that would not only please their customers but also demand premium price and thus increased profits. The global perfume market size in 2018 was valued at USD 31.4 billion and is expected to expand at a CAGR of 3.9% from 2019 to 2025 ( ).
In recent years, perfumes have become a major business in the personal care industry.
0 kommentar(er)
