Walmart Apollo, LLC

Zheng Yan

Jun Zhao

Guang Yang

Binwei Yang

Omer Ovenc

Cun Mu

Behzad Ahmadi

Junchao Zheng

Nitin Shailesh Baliga

Vishal Kumar Rathi

Nidhin Pattaniyil

Weiqi Tong

Antonio Khalil Moretti

Tanwir Zaman

Yiyi Huang

Anyi Chen

Eran Lewis

Chen Song

Ming Sun

Adithya Rajan

Aniket Ashok Limaye

Sanjay Shah

Andrew Thomas Catalano

Jingbo Liu

This application relates to apparatus and methods for automatically determining query corrections based on prior interactions of users with a search query. In some examples, a computing device receives a search query from a user, and returns a query correction to the user in response to the search query. The computing device obtains engagement data corresponding to the query correction from the user. The computing device also updates one of a query-correction database and a typo-candidate database based at least in part on the engagement data. When the computing device receives the search query from another user, it corrects the search query from the another user using the query-correction database and the typo-candidate database.

Methods and apparatus for correcting search queries

A method including extracting queries from historical search query data. The method also can include spellchecking each of the queries (i) using a first spellcheck model and (ii) using a second spellcheck model. A latency of the first spellcheck model is lower than a latency of the second spellcheck model, and an overall accuracy of the second spellcheck model is higher than an overall accuracy of the first spellcheck model. The method additionally can include determining first queries of the queries in which, for each of the first queries, a first respective spellcheck output from the first spellcheck model is different from a second respective spellcheck output from the second spellcheck model. The method further can include adding at least a portion of the first queries to a spellcheck cache for runtime spellchecking. Other embodiments are described.

Offline spellcheck candidates complementing runtime spellcheck

Systems and methods including one or more processors and one or more non-transitory storage devices storing computing instructions configured to run on the one or more processors and perform functions relating to detecting trending search queries that are popular in a short-term time period. User engagement metrics are derived from historical search engine data. A trending analysis function executes statistical analyses on the user engagement to identify the trending search queries. Other embodiments are disclosed herein.

Systems and methods for generating trending search queries using predictive search engines

Systems and methods including one or more processors and one or more non-transitory storage devices storing computing instructions configured to run on the one or more processors and cause the one or more processors to perform acts of: in response to receiving search queries at a search engine, storing search event data and ranking features in one or more databases; generating, using the search event data and the ranking features, a training dataset comprising training event samples; executing a hybrid labeling procedure that assigns labels to the training event samples based, at least in part, on individual engagement information associated with the training event samples; and training a personalized ranking model to rank search results using the training event samples and the labels. Other embodiments are disclosed herein.

Systems and methods for improving search result personalization and contextualization using machine learning models

Systems and methods including one or more processors and one or more non-transitory computer readable media storing computing instructions that, when executed on the one or more processors, perform: receiving user search queries and product items, the product items including metadata corresponding to product types; determining a data relationship between the user search queries and the product items based on a weighting factor, the data relationship including user search query nodes and product item nodes; determining a first vector representation for first ones of the product item nodes in the data relationship; determining a second vector representation for second ones of the product item nodes in the data relationship; grouping the first vector representation for first ones of the product item nodes and the second vector representation for second ones of the product item nodes into a product type group based on a proximity search; and modifying the metadata corresponding to the product types based on the product type group to mitigate a computing system from displaying non-compliant material to a user. Other embodiments are disclosed herein.

Systems and methods for mitigating display of non-compliant information

Systems and methods including one or more processors and one or more non-transitory computer readable media storing computing instructions that, when executed on the one or more processors, perform: receiving historical in-session user activity information; receiving, via a graphical user interface (GUI) of a user device, a partial search query from a user; analyzing the partial search query based on the historical in-session user activity information using one or more query suggestion systems to determine a respective score for respective suggested search queries from each of the one or more query suggestion systems; determining a respective absolute position metric for the respective suggested search queries from each of the one or more query suggestion systems; determining a respective efficiency metric for each of the one or more query suggestion systems based on the respective absolute position metric; analyzing the respective efficiency metric for each of the one or more query suggestion systems to determine a query suggestion system of the one or more query suggestion systems that satisfies a threshold; and transmitting instructions to modify the GUI to display the respective suggested search queries from the query suggestion system that satisfied the threshold.

Systems and methods for query engine analysis

A method including pre-screening second images from a database for a search result based on a first image and also based on respective substring distances between first binary substrings for the first image and respective second binary substrings for each of the second images. The method further can include after the pre-screening, determining a respective image distance for each third image of third images of the search result, wherein the respective image distance is between the first image and the each third image of the third images of the search result, and after determining the respective image distance for each third image of the third images of the search result, when the respective image distance for a particular one of the third images is greater than a predetermined image distance threshold, removing the particular one of the third images from the search result before the search result is displayed on a user device requesting the search result. Other embodiments are disclosed.

Image searching using a full-text search engine

A method including bit-operation and sub-code/substring filtering for image searching using a full-text search engine. The method can include determining a first binary vector comprising first binary substrings for a first image. The method also can include obtaining a respective second binary vector comprising second binary substrings for each of second images from a database. The method additionally can include determining a respective substring distance for each of the binary substring for each of the second images. The respective substring distance can be between at least a pair of a first binary substring of the first binary substrings of the first binary vector and a respective corresponding second binary substring of the second binary substrings of the respective second binary vector for each of the second images. In some embodiments, the method further can include after determining the respective substring distance for each of the binary substring for each of the second images, when the respective substring distance for one or more of the second images is not greater than a predetermined substring distance threshold, including the one or more of the second images in a search result. The method also can include determining a respective image distance for each respective third image of the search result, the respective image distance being between the first image and the each respective third image of the search result. The method additionally can include after determining the respective image distance for the each respective third image of the search result, when the respective image distance is greater than the predetermined image distance threshold, culling the each respective third image from the search result. Other embodiments are disclosed.

Growing community of inventors

Short Hills, NJ, United States of America

Zheng Yan