Introduction to AI Search

The Synerise AI Search Engine is a powerful tool that can boost the search results relevancy on your website to the next level. There are numerous ways to improve your customers’ experience as well as shorten the path to conversion, from the basic search configuration, through synonyms, ending on query rules. The search engine can also detect typos and perform a search for the corrected query.

Benefits


  • Higher conversion
  • Increased revenue
  • Strengthened relationship with your customers

About search engine


Search engine is based on the product feed uploaded to catalogs and configuration of additional settings. The uploaded products are scored based on the indices (created to speed up the search process) and additional search settings. The more an item matches the query that a user is searching, the higher the score for that item is. The items are returned in the search results in order from highest score.

The search engine is capable of handling typos. It can detect a typo and still conduct a search for the proper query. This lets users handle a typo in a user-friendly way, for example by displaying a “Did you mean t-shirt” communicate to the customer, if the customer searched for t-shrt.

Each search type can be personalized, which means that the results can always be adjusted to the taste of the individual customer (described in the search setup procedure).

Search types


AI Search engine enables several types of search.

When a request is made with a query parameter, a full-text-search can be conducted. Read more about implementation.

The search engine also has an in-built option of autocompleting the searched query. This means that with every keystroke, it can predict what a customer is entering into the search. Read more about implementation.

Visual search allows customers to find exactly what they search for by using an image instead of describing the product in the right way. It significantly shortens the path to conversion and improves the customer experience.

The implementation process can be divided into three stages.

  1. Feed the image into a neural network, which outputs main keywords for the given image, for example the color, patterns, type of item, in a form of tags.
  2. Match the output tags with attributes in the item catalog.
  3. Filter and sort the results. The input photo can be uploaded or linked to the website. If the search engine is also integrated with a mobile app, the photo can be taken by the smartphone and uploaded.

Listing

If no search input is given, the search engine displays a list of products. The listing can be filtered by any given attribute, included in the items catalog. This means you can create, for example, a list of products filtered to a specific brand and sorted by color and price.

😕

We are sorry to hear that

Thank you for helping improve out documentation. If you need help or have any questions, please consider contacting support.

😉

Awesome!

Thank you for helping improve out documentation. If you need help or have any questions, please consider contacting support.