AI Classifier Introduction
AI Classifier can automatically learn from your existing taxonomy and the records you have categorized against it and make predictions for newer, uncategorized records. The classifier supports hierarchical taxonomies and saves you the time and effort of manually classifying new records. The Classifier once enabled on your projects continues to learn in the background based on your feedback and multiple modes of operation allow you to choose the level of intervention you want in the process.
Two modes of AI Classifier:
Automatic mode: In this mode the records will automatically get tagged with the categories that you have created based on a subset of the records i.e. your training data.
Moderation mode: In this mode the records that have been auto categorized will be provided to you for review, basically the categories that have been assigned you can cross check the categories, modify it, remove it completely and then move further to the next record.
For the AI Classifier to run, the most basic requirement will be to create categories within the dataset, the categorization could be based on the applications of the technology, based on the important aspects or the key features of the patent documents etc.
The second requirement is to create a training dataset. There needs to be a set of records that you have manually categorized in the project, the minimum requirement is 5 records per category, however, we recommend the users to at least keep 10-15 records per category.
The training dataset can be the one that you have created for the project on which you are running the AI Classifier as mentioned above. However, you can use categories that you have created in an other related project as a training dataset.
Meaning if you have a project in which you have already categorised the records or you have already run the AI classifier, then this dataset can be used as a training model for the project on which you are working currently. The requirement here is that you will have to create similar categories in the project that you are working on currently. Also, here you can either get the predictions based on all the categories from the selected project or you can select the categories as per your choice and run the AI Classifier.
The AI classifier once enabled on your project keeps learning and adding records to the categories as and when you add new records to the project.
Steps to set the AI Classifier:
- Open the project.
- Look for the Categories filter and select the highlighted option
3. Select the Automatic option.
4. Select the Categories on which you want to run the AI Classifier
OR
Select the project in which you have already categorised the records or you have already run the AI classifier or select the categories from that project as per your choice and run the AI Classifier
5. Click on readiness check (This option checks the minimum number of records whether present or not within every category you have selected)
6. Select the mode of AI Classifier that you need to run on, either Automatic or With moderation.
7. Select the threshold, based on your requirements. You can select from 30 to 90.
8. Click on Confirm to enable the AI Classifier.
Notes:
- AI Classifier would not work on the External results
- If the source project (training model) will not have categories then the confirm option will be disabled.
- If the source project has categories but the destination project does not then the AI Classifier will create categories in the destination project.
- For the AI classifier to run properly on the project you are working on must contain categories that would be used as a training model.
- Available only in the ProX edition of PatSeer