Bloomreach's semantic engine helps parse product types from user queries and product data. This information is then used to optimize the Recall and Ranking in various ways.

Bloomreach is extending this semantic capability to two additional languages: French and German. Bloomreach’s semantic engine will be able to parse product types in French and German, which will impact Search Ranking and Recall in French and German catalogs.

Semantic Understanding examples

These examples show what Bloomreach’s semantic engine identifies as the product type.

French

German

Impact on Search Ranking

Product types are identified from the product feed and from incoming user queries in real-time.  Products that match the product type from the user query are boosted in ranking. This increases relevance near the top of the result set for all queries, and especially benefits cases with less user behavior data, such as torso/tail queries.

For example, a user searches for “blooma barbecue”. Without semantic understanding, some of the top products include barbecue accessories like “grilles”.

With semantic understanding, the product type is identified as “barbecue”, so the products of product type “barbecue” are boosted above the other products.

Impact on Search Recall

If no product match is found for a user query, the query is relaxed to show other products that match on the identified product type. This helps reduce null search result rate, improve user experience, and increase conversions by showing related products instead of a null result.

For example, a user searches for "fauteuil rio" and no matches are found. The product type is identified as “fauteuil” (armchair), so the query is relaxed to show other armchairs.

🚧

Note: The API response also includes information that the query has been relaxed so it can be displayed to the end user to avoid confusion when they see related products instead of exact matches.

How to enable this feature?

French and German Semantic Understanding feature will be generally available from July 7th, 2022.
There is no additional charge to enable this feature. No extra integration steps are required.