Ebay, Incorporated

Paypal, Inc.

Nishith Parikh

Neelakantan Sundaresan

Gyanit Singh

Brian Scott Johnson

Zeqian Shen

Udayan Khurana

Mohammad Al Hasan

Alvaro Bolivar

Sanjay Pundlkrao Ghatare

Yan Chen

Guanglei Song

Baruch Perlov

Joseph Anthony Beynon

Chi-Hsien Chiu

Karin Mauge′

Suman Voleti

Neeraj Garg

Sathishkumar Veeraraghavan

Karin Mauge

Quang Anh Duong

Joe Anthony Beynon

A method and a system for providing recommendations based on branding are disclosed. In example embodiments, an index comprising predetermined brand relationships is maintained. Each predetermined brand relationship comprises a first brand, a second brand, and a recommendation score between the first brand and the second brand. A corpus containing a plurality of user queries is also maintained. A seed set of brands corresponding to a category in the index is expanded by accessing the corpus containing the plurality of user queries, evaluating user queries of the plurality of user queries that contain a disjunction of brand terms, and identifying a new brand to add to the seed set based on the evaluating.

Recommendations based on branding

Methods, systems, and computer programs are presented for identifying data representations across multiple network assets and generating content responsive to the representations. A method includes receiving a set of queries comprising a first set of keywords and identifying a set of results within a first database where the set of results includes a set of publications with an identification and a title. The method generates an association between the first set of keywords and the identifications and titles of the set of publications. The method generates a first association among keywords of the first set of keywords based on user activity received in response to identifying the set of results. The method identifies a second set of keywords based on the first set of keywords and associates the second set of keywords with the first set of keywords within the first database.

Context identification for content generation

A method and system for a search based on diversity is described. The system calculates a diversity index for a result set comprising results for a query. The diversity index is a measure of diversity among the results of the query. The diversity index relates to differences among the results. The system compares the diversity index to a threshold value. Finally, the system expands the query with one or more query terms based on the comparison.

Search based on diversity

Various example embodiments are provided for inferring relationships between a first query comprising a plurality of first terms and a second query comprising a plurality of second terms. In an example, queries are related based on the identification of common terms between the queries. One or more dissimilar terms are identified between the plurality of first terms and the plurality of second terms. A first number of dissimilar terms included in the first query and a second number of dissimilar terms included in the second query are identified. A weight is assigned to the relationship between the first query and the second query based on a difference between the first number and the second number.

Inference of query relationships based on retrieved attributes

A method and system analyze data associated with a marketplace category. In some embodiments, a query is received that identifies a marketplace category from multiple marketplace categories associated with an electronic commerce marketplace. Data associated with the marketplace category is accessed and analyzed to identify multiple keywords used to identify listings in the marketplace category. A user interface is generated to display the analysis results, including at least a portion of the multiple keywords used to identify listings in the marketplace category.

Category management and analysis

Query suggestions are provided using a query log including a number of user sessions that comprise training data. The training data includes a sequence of a plurality of sets of queries, some of the sets of queries including query transitions followed by a purchase related event. From a cleaned and normalized query log stationary scores and transition scores of at least some of the plurality of sets are generated. A set of query suggestions is built and similarity scores are computed for at least some of the set of query suggestions to determine whether individual ones of the at least some of the set of query suggestions meet a predetermined assurance level. Those that meet the assurance level are included as elements of the set of query suggestions. The set of query suggestions is mixed and ranked according to a user behavior that is sought to be influenced.

Query suggestion for e-commerce sites

In an embodiment, a method is provided for presenting a query directed at an information resource. In this method, a number of queries is accessed over a time period. A burst of the number of queries is detected within the time period. It should be noted that a burst is a determinable increase in the number of queries received within the time period relative to a historical number of queries received in a preceding time interval. Event-related information that is associated with the burst in the time is searched, and the query in conjunction with the event-related information is displayed at a display unit.

Presentation of query with event-related information

Systems and a method for expanding a query are described. The method calculates a diversity index for a plurality of query terms that are included in a plurality of other queries associated with the query. The diversity index is a measure of diversity among the plurality of query terms and relates to differences among the plurality of query terms. The method further compares the diversity index to a threshold value. Finally, the method expands the query with one or more of the plurality of query terms based on the comparison.

A method and a system for providing recommendations based on branding are disclosed. For example, a brand preference corresponding to a first brand and a first category may be identified based on user activity. A recommendation is provided to the user based on the brand preference. The recommendation may be provided based on a predetermined brand relationship comprising the first brand associated with the first category, a second brand associated with a second category, and a recommendation score between the first and second categories and brands. The recommendation may provided by accessing a relationships database to determine at least one brand relationship of the brand relationships corresponding to the brand preference.

Various example embodiments are provided for inferring relationships between queries. In an example, queries are related based on the identification of common terms between the queries. Another example is to relate queries based on the identification that the queries are associated with a single search session. Yet another example is to infer relationships based on the identification of relationships between item attributes retrieved from the submission of the queries.

In various example embodiments, a system and method for personalization of search results are provided. In example embodiments, a user interface that allows a user to establish optimization preferences used to personalize results based on a query is provided. The optimization preferences include values that are a portion of a total allowed value assigned to interrelated optimization factors. The optimization preferences are received via the user interface. The optimization preferences are applied to matches obtained based on the query to generate a personalized result set.

System and method for multi-dimensional personalization of search results

An example method of expanding a search is provided. In this example, a query used in the search is initially accessed. Other queries associated with the accessed query are identified, and these other queries include query terms. A diversity of the query terms is measured and the accessed query may be expanded with the query terms based on the measured diversity. Another example method is also provided for expanding a search. In this alternate example, a result set resulting from the search is accessed and a diversity of the result set is measured. The query used in the search may then be expanded based on this measured diversity.

Providing query suggestions using a query log including a number of user sessions that comprise training data including a sequence of a plurality of sets of queries. Some of the sets of queries include query transitions followed by a purchase related event. The query log is cleaned and normalized. Query log stationary scores and transition scores of at least some of the plurality of sets is generated. A set of query suggestions is built and similarity scores are computed for at least some of the set of query suggestions to determine whether individual ones of the at least some of the set of query suggestions meet a predetermined assurance level. Those that meet the level are included as elements of the set of query suggestions that meet the predetermined assurance level. That set of query suggestions are mixed and ranked in accordance with a user behavior sought to be optimized.

Growing community of inventors

Fremont, CA, United States of America

Nishith Parikh