Ebay, Incorporated

Wal-mart Stores, Inc.

Walmart Apollo, LLC

Srikanth Subramaniam

Narasimhan Rampalli

Chong Sun

Nikesh Lucky Garera

Dintyala Venkata Subrahmanya Ravikant

Heather Dawn Yalin

Raghav Gupta

Jean-Michel Leon

Aditya Arora

Benjamin David Foster

Seema Shah

Vijay Raman

Suhail Ansari

Adam Nash

Xavier Stonestreet

Abhishek Gattani

Tri Cao

Heather Marie Sevrens

Computerized data processing and electronic file management methods of organizing and indexing electronic records in an electronic database for categorizing new products that are being added to an existing database of product offerings and computerized digital data processing methods of transferring digital information between a plurality of computers and employing computer instructions to categorize new products that are being added to an existing database of product offerings. Multiple classification models classify a description of a particular product and the classifications are compared, and if found to be equivalent, are added to the existing database of product offerings. If the classifications from the models are not equivalent, then the description is sent to multiple people for classification and the classifications from the people are compared, and if found to be equivalent, are added to the existing database of product offerings.

Product classification data transfer and management

Systems and methods to communicate information are described. The system receives a query and retrieves a set of data items from a database based on the query. The system generates a distribution based on a count of data items from the set of data items that were retrieved for each domain in a set of domains and a count of requests to view data items from another set of data items for each domain in the set of domains. The system identifies whether the distribution exhibits a type of a distribution by comparing the distribution with at least one of a peak distribution and a hills distribution. Finally, the system generates interface information based on the type of distribution.

Methods and systems to communicate information

Techniques for providing improved search results for queries are provided. The techniques include obtaining a candidate pair from a query log comprising a single word unigram and a two word bigram which expresses the same content as the unigram, receive customer interaction data from the query log for the unigram and the bigram, and determining if the candidate pair includes a dominant form, equivalent form, or un-comparable pair. The techniques also include creating a rule regarding treatment of the unigram or bigram in analyzing a query. The techniques further include receiving a query, analyzing the query to identify modified query results according to the rule, and presenting the query results.

Method and system for resolving search query ambiguity in a product search engine

There is provided a method and system to communicate information. The system receives a first query that contains a first constraint and retrieves a first plurality of data items from a database based on the first query. Next, the system generates a first distribution based on the first plurality of data items, the first distribution utilizing a first plurality of domains that are used to identify data items. Next the system generates a second distribution based on a plurality of requests to view a second plurality of data items. Next the system generates a third distribution based on the first distribution and the second distribution. Finally, the system generates distribution data to be included within an interface, the interface to include at least one interface element that is positioned on the interface based on the third distribution, the at least one interface element to respectively represent at least one domain.

Systems and methods are disclosed herein for classifying records, such as product records, using a machine learning algorithm. After training a classification model according to a machine learning algorithm using an initial training set, records are classified and high confidence classifications identified. Remaining classifications are submitted to a crowdsourcing forum that validates or invalidates the classifications or marks them as to unclear to evaluate. Invalidated classifications are automatically analyzed to identify one or both of classification values and categories having a high proportion of invalidated classifications. Requests are transmitted to analysts to generate training data that is added to the training set. The process of classifying records and obtaining crowdsourced validation thereof may then repeat.

System and method for high accuracy product classification with limited supervision

Systems and methods are disclosed herein for performing classification of documents or performing other tasks based on rules. The rules may include context rules that define a mapping that relates a value and context in a document to an attribute to which the value corresponds. Products are selected for labeling with attributes by identifying patterns, e.g. values and contexts that are not covered by a current rule set. Those products having a highest score are selected for labeling in a crowd sourcing forum, where the score is based on the number of non-covered patterns and a frequency of occurrence of the non-covered patterns in a document corpus. Proposed rules are generated for frequently occurring patterns and submitted to analysts for one or both of completion and validation. Proposed rules may include a proposed attribute for a frequently occurring value and corresponding context.

Automated attribute disambiguation with human input

Systems and methods are disclosed herein for generating a normalized record from an import record, the normalized record having attribute-value pairs corresponding to a native schema. In import records, a plurality of attribute-value are identified each having an attribute label not found in a native schema. One or more attribute labels in the native schema having as possible values one or more values corresponding to the values of the plurality of attribute-value pairs are also identified. The computer system generates one or more normalization rules relating one or more attribute labels of the plurality of attribute-value pairs to at least a portion of the one or more attribute labels in the native schema. Normalization rules may be validated by crowdsourcing. Normalization rules may be applied by identifying implicated rules by classifying the import record and identifying rules applicable to the classification.

Product record normalization system with efficient and scalable methods for discovering, validating, and using schema mappings

Systems and methods are disclosed herein for obtaining a structured listing of attributes and corresponding values based on an unstructured document, such as a product description in a product record. Putative values are identified in the document and corresponding candidate attributes are identified in a taxonomy. Attribute-value pairs are then evaluated with respect to a plurality of rules. Attribute-value pairs and outputs of the one or more rules are evaluated using a machine-learning algorithm, such as a decision tree, in order to determine which attribute-value pairs to retain. Retained attribute-value pairs are stored and used to respond to search queries and facilitate comparison of products. Attributes selected may also be used to update a product template.

Ontology-based attribute extraction from product descriptions

Systems and methods are disclosed herein for classifying records, such as product records, using a machine learning algorithm. After training a classification model according to a machine learning algorithm using an initial training set, records are classified and high confidence classifications identified. Remaining classifications are submitted to a crowdsourcing forum that validates or invalidates the classifications or marks them as to unclear to evaluate. Invalidated classifications are automatically analyzed to identify one or both of classification values and categories having a high proportion of invalidated classifications. Requests are transmitted to analysts to generate training data that is added to the training set. The process of classifying records and obtaining crowdsourced validation thereof may then repeat. High confidence classifications may be identified using an accuracy model trained to relate an accuracy percentage to a confidence score output by the classification model.

System and method for classification with effective use of manual data input and crowdsourcing

The present disclosure extends to methods, systems, and computer program products for automatically determining key words within item information with product types, and classifying new items within product types within a merchant's database.

Ranking keywords for product types with manual curation

There is provided methods and systems to identify a preferred domain of a plurality of domains corresponding to a query. First, the system receives the query. Second, the system accesses demand information corresponding to the query, the demand information including navigation information associated with the query. Third, the system accesses supply information corresponding to the query, the supply information including a count of data items in each of the plurality of domains that match the query. Fourth, the system identifies the preferred domain based on the demand information and the supply information.

Method and system to identify a preferred domain of a plurality of domains

There are provided methods and systems to enable navigation of data items based on aspect-value pairs extracted from the data items. First, a system receives a query, Second, the system identifies a plurality of data items found by the query. Third, the system identifies an aspect of at least one of the plurality of data items, Fourth, the system identifies a value of a plurality of values corresponding to the aspect. Fifth, the system receives a request to navigate to a set of data items within the plurality of data items, the request comprising the aspect and a requested value of the plurality of value. Each one of the set of data items has the aspect and the value. Sixth, the system presents, in a user interface, information about each one of the set of data items.

Method and system to enable navigation of data items

There is provided a method and system to communicate information. The system receives a first query that contains at least one constraint and retrieves a first plurality of data items from a database based on the first query. Next the system generating a first distribution based on the first plurality of data items, the first distribution utilizing a first plurality of domains used to identify data items. Next the system generates a second distribution based on a plurality of requests to view a second plurality of data items. Next the system generates a third distribution based on the first distribution and the second distribution. Finally the system generates interface information, to be communicated to a user, based on the third distribution.

Growing community of inventors

San Jose, CA, United States of America

Srikanth Subramaniam