The section called 'Technology' breaks the selected portfolios into its distinct technology clusters. You can selected an organisation, or a multiple organisations to cluster before generating your report.

A Cipher technology cluster is therefore a grouping of patent families relating to the same technical area. Technology clusters are based on ‘features’ or metadata of patents:

  1. Title
  2. Abstract
  3. Citations 
  4. CPC codes

Miscellaneous

Our clustering mechanism aims at creating up to 20 clusters. If the number is higher than 20, the clusters are rolled into 10 clusters being the 9 largest and 1 miscellaneous under which all the rest of the clusters go.

Unrelated

At the end of the list of technologies there is an option called ‘Unrelated’. This refers to the technologies that are not related to your chosen reference portfolio, but are in the portfolio of the comparable organisations.

If our reference portfolio is X and a comparable is Y – unrelated shows the technologies in Y’s portfolio that don’t overlap with X’s portfolio.

How are the Cluster names determined?

Cipher Cluster names are machine generated, by reference to the title and abstract. The Clusters are given a name that most closely describes all patent families in the Cluster using text summarisation, and natural language processing (NLP) techniques.

Our names have been shown to be more helpful and relevant compared to the defaulting of only using CPC codes, which are useful to patent examiners and specialists, but are not familiar to the broader business community.

Need help? Request support and we'll connect you with a Cipher expert.


Can't wait?
Contact us on 02039099222 or email support@cipher.ai

Did this answer your question?