Amazon Technologies, Inc.

Krishnamurthy Koduvayur Viswanathan

Debprakash Patnaik

Jianhui Wu

Rongzhou Shen

Gabriel Parent

Taibai Xu

Wenke Zhang

Jiwei Cao

Embodiments disclosed herein include artificial intelligence systems and methods for automatically filling or completing required attribute values for features associated with an item that is being offered. In embodiments, an offer for an item may include an image of the item and unstructured text related to the item. Potential candidate values are selected and ranked according to generated confidence scores that represent the correct candidate value for the selected feature. A user interface may be presented to the user offering the item that presented the ranked potential candidate values and request confirmation. In response to the user confirming the candidate value for the feature a web page may be generated for offering the item with appropriate features and attribute values auto-populated thus providing an efficient method for offering items on behalf of a user.

Artificial intelligence feature extraction service for products

A technology is described for determining an item package quantity. An example method may include extracting a first item package quantity from a first attribute field for a product and extracting a second item package quantity from a second attribute field for the product. The first item package quantity and the second item package quantity may then be classified using a prediction model that determines a likely correctness of the first item package quantity and the second item package quantity. An item package quantity may then be selected from the first item package quantity and second item package quantity having a classification that indicates that the item package quantity is likely correct.

Determining a package quantity

Disclosed is a platform for assessing queries related to a catalog entry. The platform is able to determine what attributes of the catalog entry the query is directed to using one or more language processing techniques. Once an attribute is identified, the platform may check for appropriate unit types and/or formats based on a category associated with the attribute. The platform then parses additional data associated with the catalog entry (or another catalog entry within the same browse node) to identify a set of potential values for the identified attribute. One or more rule sets may be used to filter the set of potential values to a single probable value, which may then be provided in a response to the query.

Extracting product facets from unstructured data

Techniques for extracting unstructured quantitative data may be provided. For example, a process may attempt to extract unstructured quantitative data to form structured data. This quantitative data may be used for searchable ordering of items in an electronic marketplace. For example, a process may attempt to find common attributes amongst several item descriptions. The common attributes may be recognized in the unstructured data, stored as structured data, and incorporated with a network page to allow the user to search for a particular item with a particular attribute. The desired attribute can help narrow a set of results from a search query.

Extracting data from a catalog

Systems and methods involve filling missing attribute values from unstructured text. A computing device may provide a plurality of items, such as an item catalog for an electronic marketplace. When an item is found to have a missing attribute value, a plurality of existing values for that attribute is compiled by mining other items. Text associated with the item is parsed to determine possible values for the attribute. From those possible values, the most likely value is identified and the missing attribute value is populated with that value.

Growing community of inventors

Seattle, WA, United States of America

Krishnamurthy Koduvayur Viswanathan