Ebay, Incorporated

Atiq Islam

Ganesh Talele

Padmapriya Gudipati

Suchitra Ramesh

Timothy Keefer

Ashmeet Singh Rekhi

Shane Lin

John Weigel

Niaz Ahamed Khaja Nazimudeen

Fujun Zhong

Kenneth Crookston

Ritu Goel

Rodolfo Gonzales

Nish Parikh

Neeraj Garg

Suman Voleti

Ganesh Gopalakrishnan

Zhaohui Chen

Vinayak Agarwal

Shifa Fazal Mahamood

Satya Voleti

Example embodiments involve a system and methods for identifying valuable view item pages for search engine optimization. The system and methods provide an improvement over existing systems, which do nothing to identify or select valuable view item pages for use in driving traffic from display sites. The system and methods described herein improve the earlier system by predicting the probability of future traffic for a given product based on a number of product level factors as input variables, and identifying a selection of view item pages corresponding to the products with the probability of the highest future traffic in order to maximize the driving natural search traffic to a linked site of the corresponding view item page.

Search engine optimization by selective indexing

Example embodiments involve a system and methods for identifying valuable view item pages for search engine optimization. According to certain embodiments, the system performs operations that include predicting the probability of future traffic for a given product based on a number of product level factors as input variables, and identifying a selection of view item pages corresponding to the products with the probability of the highest future traffic in order to maximize the driving natural search traffic to a linked site of the corresponding view item page.

Embodiments of the present disclosure provide systems, methods, and computer storage media for implementing a nuanced-color search and recommendation system. Employing various techniques described herein, an improved search engine for categorizable items is provided to generate accurate color-based search results and recommendations that are relevant to a nuanced color provided as a search parameter. In various implementations, digital assets that depict categorizable items can be analyzed to characterize the depicted items with, among other things, a particular shade of a determined dominant color. In this way, categorizable items can be searched based at least in part on a selected shade of a particular dominant color to generate a primary search result. In further embodiments, other categorizable items can be generated as recommendations based on characteristics of the primary search result. That is, other items not necessarily subject of the search, can be provided as recommended items if predefined rules dictate that such items may complement the categorizable items included in the primary search result.

Nuanced-color search and recommendation system

Systems and methods generate browse node pages. A combination of a category and one or more aspects is identified by analyzing historical user behavior data associated with a network-based system. A determination is made regarding whether existing browse node pages for the network-based system includes a browse node page for the identified combination. Each browse node page for the network-based system is accessible by a respective uniform resource location (URL) and provides a grouping of items in a respective category with one or more respective aspects. Based on a determination that a browse node page does not exist for the identified combination of the category and the one or more aspects, a browse node page for the identified combination is generated. The generated browse node page corresponds with a URL and provides items matching the identified combination of the category and the one or more aspects.

Identifying missing browse nodes

Embodiments of the present disclosure provide systems, methods, and computer storage media for implementing a nuanced-color search and recommendation system. Employing various techniques described herein, an improved search engine for categorizable items is provided to generate accurate color-based search results and recommendations that are relevant to a nuanced color provided as a search parameter. In various implementations, digital assets that depict categorizeable items can be analyzed to characterize the depicted items with, among other things, a particular shade of a determined dominant color. In this way, categorizeable items can be searched based at least in part on a selected shade of a particular dominant color to generate a primary search result. In further embodiments, other categorizeable items can be generated as recommendations based on characteristics of the primary search result. That is, other items not necessarily subject of the search, can be provided as recommended items if predefined rules dictate that such items may complement the categorizable items included in the primary search result.

To improve the user experience, browse nodes for popular combinations of categories and aspects are desirable. When a particular combination of category and aspects is found to have been requested at a frequency that exceeds a threshold, the existence of a browse node for that combination is checked and, if the browse node is missing, a request to create the browse node is generated. In some example embodiments, an entire set of missing browse nodes is generated based on recognition of a pattern of category and aspect combinations being requested.

Example embodiments described herein disclose a specially configured device to generate and cause display of human readable titles for browse pages. The token based title system may be or include a group of one or more server machines. A user device may accordingly receive a search query and set of structured data elements (e.g., filter attributes), create a browse node based on the content of the search query and the structured data elements, access published content (e.g., an item inventory) based on the browse node, and generate a human readable page title to be displayed as a title of a browse page.

Generating titles for a structured browse page

In various example embodiments, a system and method for generating a concept graph are presented. Trending queries are determined from a query log stored in a database. Item pages that correspond to the trending queries are identified. Aspects from the item pages are also identified. The aspects from the item page may be stored as pre-defined data within the database. Query nodes for each of the trending queries are generated, and the query nodes are included in a graph. Leaf nodes for each of the aspects are generated. Connections between the leaf nodes and the query nodes are generated. A destination page that includes various aspects is generated.

Systems and methods to generate a concept graph

A system receives images of objects. The system identifies a category for each of the objects, and extracts features from the images. The features relate to a quality of the image. The features of the images are stored in a database according to the category of each object, such that each set of features is associated with its corresponding image. The system displays the images on a network-based publication system, and receives data relating to the displayed images. The data is analyzed, and the images are ranked as a function of the analysis. The system redisplays the images on the network-based publication system as a function of the ranking of the images.

Growing community of inventors

San Jose, CA, United States of America

Atiq Islam