The search in Voyado Elevate is based on sophisticated query analysis and product listing relevance, including product life cycle analysis, visitor behavioral insights, and more.
Query analysis is used for both search results and product suggestions, and impacts the phrase suggestions in the Autocomplete query. Query analysis combines basic text processing with advanced features, such as natural language processing, concept understanding, and multi-level spelling corrections to truly capture the visitor's search intent.
Lemmatization and word scanning
All product searches employ advanced techniques such as lemmatization and word scanning, if an ontological understanding is present.
Pluralization handling
Pluralization handling uses different techniques to analyze a search term and identify its corresponding term in singular/plural form to present relevant search hits. Pluralization is treated separately from stemming and includes special handling of cases where seemingly corresponding words are not related.
Example: "shorts" is not the plural of "short".
Multi-level spelling corrections
When a visitor enters a search phrase, automatic spelling correction helps the visitor find an item even if it is misspelled in the search. Automatic corrections also help visitors find products when the product data itself is misspelled or has spelling variations. For example, if a visitor searches for "adidas" and the brand name of a product is misspelled as "addidas" the product with the misspelled name is still found.
The level of differentiation between the phrase and the content is considered in the ranking. Relevant products are not left out but less likely interpretations are ranked lower.
Color
A search phrase often includes the color of a product, which makes color an important concept to understand. Based on identification of color terms in the search query, and color analysis of garments, Elevate can apply color closeness as a part of the ranking. Ranking is affected both by how well the queried color matches the precise nuance of a garment, and how much of that nuance is present in the garment.
Color distance
Using a color distant measurement called CIE-distance (Commission internationale de l'éclairage), Elevate can correctly evaluate the color match criteria based on the nuance of each product. This allows variations that lean slightly towards purple or lighter red to be incorporated, but ranked lower.
Color distribution
The more of the color in the search phrase that is present in the product, the better the product is considered to match the color criteria.
Title
Product titles often hold significant information and are considered especially important for match ranking.
Product titles often consist of a composition of other values. For example, a title can be a combination of both its proper name, the product type, and a color name.
Normally, a full match of an attribute is ranked higher than a partial match. Product titles are an exception due to the their special composition. This means that the search query "shirt" matches the titles "shirt" and "Elana shirt - pink rose" equally well.
Name
In some industries, it is common for products to have a proper name. For instance, in electronics a phone may have the name "iPhone 14 Max Pro" while the title may include additional information such as memory size and color.
Elevate allows the visitor to filter and sort product lists by name. Separating the name from the rest of the title also makes it easier to style the name on the product card.
Model ID
Elevate has a designated model ID search feature that accommodate intricate patterns. For instance, when seeking a product with the ID "XX-11YYY22-33" shoppers can enter queries such as "YYY" or "YYY22" and still receive accurate matches. A model ID search assists shoppers to find a product, even if they only remember a partial model ID. Additionally, it reduces the need for the retailer to enrich the data in custom fields.
Product taxonomy
To prevent misleading hits within categories with multiple product types and an "&" in the title, such as "Scarves & Hats", Elevate differentiates product taxonomies. For example, products tagged with "Scarves & Hats" do not necessarily match the term "hat" as the item might be a scarf.
Size
To avoid prefix matches that a visitor does not expect, an exact match is required when searching for sizes. For example, when searching for "one piece" a visitor does not expect to get all products that are available in "onesize" after typing "one".
Measurements
For measurements, Elevate performs automatic unit conversion. A table with a height given as 75 cm will match searches for “table 75 cm” but also “table 0.75 m” and “table 750 mm”. Elevate also supports range facets where products in different units are correctly positioned, such that 1 m > 50 cm > 3 in > 16 mm. This is especially important for search results with a mixed set of product types.
Phrase coverage
If a visitor is searching for a t-shirt, it doesn't matter if the search phrase used is "t-shirt", "tshirt" or "t shirt", the same result will be returned. The dynamic phrase coverage ensures that not only is the queried data present in the product, but it also provides additional relevant matches.
Synonyms
Synonyms are used to extend searches of a phrase to include similar search phrases. For example, a synonym is used to also search for "holidays" when using the search phrase "christmas". Synonyms are managed in the Synonyms tab in the Experience application area. Additionally, Elevate's natural language processing capabilities enables the use of automated conceptual synonyms.
Article last updated