Classification Auto-Classification page

The Auto-Classification page appears in a Classification's properties dialogue box when the feature Auto-Classification in the System Options page Features is selected.

On this page, you can set the Classification to be available for Content Manager to file records under it automatically. For more detail about this feature, see Auto-Classification.

• This Classification is not suitable for the auto-classification process - default - select to not use this Classification for auto-classification
• Use this Classification to hold records waiting to be auto-classified - select to use this Classification to hold records that are waiting to be automatically assigned to a Classification. The Classification then acts as a holding bay. On principle, it can be anywhere within the Classification system; however, it cannot have child Classifications. To use the Content Manager feature Auto-Classification, you must have at least one designated holding bay Classification.
• Make this Classification available for selection by the auto-classification process - select to use this Classification for the auto classification process.
  When this option is selected, the other fields on the page become available:
  • Minimum confidence level required - a number between 0 and 100 that indicates how certain the Content Index should be at a minimum when filing records under this Classification. When the Content Index confidence level about a record does not meet the minimum specified here, it will not file the record under this Classification.
    When using a higher value, the Content Index would only file records under this Classification when it is quite sure. When using a lower value, it would file more records, but probably with less accuracy. At a value of 0, the confidence level setting is completely turned off. You can probably turn off the setting after the initial learning period, when you are confident that the Content Index engine files records under this Classification correctly.
  • When auto-classifying a document find or create a suitable container - select this option for Content Manager to automatically create containers for the records under the Classifications. Click Configure Settings to display the Create Container Settings dialogue. See Container Creation Settings for details on how to configure the creation of containers when adding documents using this Classification.
  • Category Training - only available after the Administration menu function Auto-Classification has run. Displays the Auto-Classification Training dialogue with the terms the Content Index engine generated from the training records to represent the Classification. The Content Index engine then uses these terms to match records with this Classification. Their weight indicates how important the term is for the Content Index when determining a Classification match for the record.
    Terms can be filtered by using the Filter Terms field. The filter string can be a simple string to match part of a word, or it can be a regular expression.  For example, to match all words starting with "a", the  regular expression "^a" would show only words starting with "a".
    If using IDOL for Content Indexing, the terms appear stemmed by default; if using Elasticsearch for Content Indexing, the terms will only appear stemmed if stemming is enabled on the Elasticsearch Content Index. The column Generated Weight displays the weight that the Content Index engine assigned the term initially. When this value does not exist, then the term was not generated by the Content Index engine. In the column Custom Weight, you can see the term's current weight.
    You can double-click to change the terms that were not generated by the Content Index, and you can change every term's weight if you find that the terms need some fine-tuning to make auto-classification work better for this Classification. Setting the weight of a term to 0 makes the Content Index engine ignore that term for auto-classification.
    Click OK to save your changes to the training terms.

Related information