Aneesh Mon N here for Identifying Similar Nodes

[aneeshmonn]

I am working on a use case I have 10 Million nodes and looking for a way to identify the similar nodes with these

[oleg_neo4j]

Hello
What kind of data do you have in your nodes?

[aneeshmonn]

Hi,

I have Patents Data, which has date, title, descriptions, and few tags etc.

A subset of my data set is as here.
https://www.kaggle.com/jessicali9530/how-to-query-google-patents-public-data/data

Any pointers on this would be appreciable

[nils_hahn]

Hello Aneesh,
Maybe the Node Similarity Algorithm is applicable in your use case.
I am working with it right now, aiming to do something similar.
Here is the link: https://neo4j.com/docs/graph-algorithms/current/algorithms/node-similarity/

[aneeshmonn]

Hi @nils.hahn, Yes; I am already using it. Looking for expert advices on dealing with millions of nodes and using ga.nlp.annotate on text fields