Averbis - Binary Classifier

Introduction

In addition to the Averbis Multi-Label Classifier, Averbis also offers the option of a binary classifier. This classifier has already been used for relevant / non-relevant recognition.

The Binary Classifier has now been integrated into the Classifier / Automatic Classification so that its use can be better controlled. This means that the Binary Classifier can be trained on 2 folders. The result is a trained classifier that assigns patents either to one or the other folder (never to both folders).

Automatic Classification

If a binary Classifier Is selected In Automatic classification, the user interface Is adapted accordingly. The 2 binary Folders (e.g. For Relevant and not relevant) must then be selected. A Click on Execute will execute the Automatic classification directly.

The Binary Classifier can therefore be used specifically for a relevant/non-relevant check. For this purpose, 2 folders with relevant and non-relevant patents must be created for the training (folder 1 contains the relevant patents). An Automatic Classification is then created that refers to the Binary Classifier.

The target folder of the automatic search is taken as the input. The result (folder 1) is written to the new input folder of the monitoring task. The non-relevant patents (folder 2) should be made available to the expert for review (write permissions for the monitoring task group).

Equivalently, this is also possible with the New Extended Workflow model.