Our data enrichment feature uses artificial intelligence to find, extract, and classify extra information about your products. Data enrichment analyses your product images and webpages, and then extracts and categorises the information – descriptive labels, keywords, and colours – into Insight data tags.
Use insight data enrichment
To use data enrichment, your insight data collection must include at least one of two data fields:
An
image_pathfield, with a URL to a product image.A
urlfield, with a URL to a product page.
For best results, include both of these in your Insight data collection.
Enrichment types
Data enrichment is extracted in the following ways:
Type of data extracted | Required Insight data field | How it works |
Image labels |
| Artificial intelligence analyses the image and provides detailed descriptive tags, which a user can create filters against in the builder. For example: shirt, short-sleeved, summer, collar. |
Image colors |
| Artificial intelligence identifies dominant colours by the hex value. These values are then abstracted to their named colour. This means a user creating a recommendation can create simple descriptive filters like "blue". |
Meta scraping |
| The meta tags are extracted from the product webpage. |
Once you add the required Insight data fields to your Insight data collection, you can enable product data enrichment to start the data extraction process.
Enable product data enrichment
Go to Connect > Account insight data.
For your product catalog, select the Properties icon.
Under Enrichment settings, select Enabled for Data enrichment.
Select APPLY.
Once enabled, we start to enrich your product data automatically. The first enrichment might take several hours, especially if your catalog is very large. If you add new products to your catalog, we automatically enrich them when they next synchronise with Dotdigital.
Once data enrichment completes, your Insight data collection has an additional field labelled data_enrichment. The data_enrichment field contains an array of tags that you can use to filter your product recommendations; for example, you might want to filter your best sellers by jackets with a hood.
