Abstract: This application relates to apparatus and methods for applying trained machine learning models to determine an item's relevance to a search query. In some examples, a query and data identifying a plurality of items are received. Item attributes for each of the plurality of items are obtained, and features are generated based on the item attributes. Further, a score is generated for each item by applying a trained machine learning model to the corresponding features and the query. Matching attributes are determined for each of the plurality of items based on the corresponding item attributes and the query, and the score of each of the plurality of items is adjusted based on the matching attributes. Further, the ranking data is generated based on the adjusted score of each of the plurality of items. The ranking data may be transmitted to a web server for display of the items.

Abstract: Methods for making a storage stable bulk gummy form that is a meltable precursor for making individual serving gummies are disclosed, as well as methods for making individual serving gummies from a meltable and storage stable bulk gummy form.

Abstract: Pectin-based melt-to-make bulk gummy mix is disclosed that is shelf stable and formulated, optionally with flavors and colors, in a bulk mix form that is convenient for the next step in manufacturing individual serving pectin gummies. The bulk pectin-based gummy mix can be formulated by companies making infused gummies in a convenient manner to consistently manufacture pectin-based gummies in any size and dose. Methods for making a storage stable bulk pectin-based gummy mix that is a precursor for making individual serving pectin gummies are disclosed, as well as methods for making individual serving pectin gummies from a storage stable bulk pectin-based gummy mix. Kits comprising a two-part pectin-based gummy mix and acidulent for initiating pectin gelling are also described for the convenient manufacture of individual serving pectin-based gummies.

Abstract: This application relates to apparatus and methods for applying trained machine learning models to determine an item's relevance to a search query. In some examples, a query and data identifying a plurality of items are received. Item attributes for each of the plurality of items are obtained, and features are generated based on the item attributes. Further, a score is generated for each item by applying a trained machine learning model to the corresponding features and the query. Matching attributes are determined for each of the plurality of items based on the corresponding item attributes and the query, and the score of each of the plurality of items is adjusted based on the matching attributes. Further, the ranking data is generated based on the adjusted score of each of the plurality of items. The ranking data may be transmitted to a web server for display of the items.