Walmart Apollo, LLC

Phani Ram Sayapaneni

Snehasish Mukherjee

Haoxuan Chen

Shankara Bhargava Subramanya

Ghodratollah Aalipour Hafshejani

Deepa Mohan

Arpit Sharma

Shankara Bhargava

Navin Naidu

Tanmay Peter Kuruvilla

Shankar Bhargava

Kotlasanthos Kumar

Sahana Radhakrishna

Venkata Naga Vamsi Krishna Nandanavanam

Ashish Kumar Vishwakarma

A system including one or more processors and one or more non-transitory computer-readable media storing computing instructions that, when executed configured to run on the one or more processors, cause the one or more processors to and perform operations: receiving a command from a user; transforming, using a trained machined learning model, the command by detecting an intent to add one or more recipe ingredients; determining a recipe from a set of recipes; determining one or more items and one or more quantities or sizes of the one or more items; selecting a respective quantity or size from quantities or sizes of available items of the one or more items, wherein the respective quantity or size, as selected, is overruled when a different quantity or size preference is indicated by the user; and automatically adding to the shopping cart the one or more items. Other embodiments are described.

Voice-enabled recipe selection

A system comprising 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, by a chat bot and from a user, an indication to talk to a live agent; calling, by the chat bot, an automatic call distribution server to initiate a live-agent session for the user; storing metadata for the live-agent session in a distributed table and a distributed queue; pulling, from an automatic call distribution connector, one or more messages from a conversation between the user and the chat bot based on the metadata; and connecting the live agent to the user in the live-agent session, wherein the user communicates with the live agent in the live-agent session through a same interface for the chat bot. Other embodiments are disclosed.

Chat bot asynchronous agent escalation

A system including one or more processors and one or more non-transitory computer-readable media storing computing instructions configured to run on the one or more processors and perform receiving a voice command from a user; transforming the voice command; transforming the voice command can include using a natural language understanding and rules execution engine into (a) an intent of the user to add recipe ingredients to a cart and (b) a recipe descriptor; determining a matching recipe from a set of ingested recipes based on the recipe descriptor; determining items and quantities associated with the items that correspond to a set of ingredients included in the matching recipe using a quantity inference algorithm; and automatically adding all of the items and the quantities associated with the items to the cart. Other embodiments are disclosed.

A method for automatically rectifying in real-time anomalies in natural language processing systems. The method can include determining an output corresponding to a user request from a user device for a user based on a new request template or machine learning. The method further can include retrieving one or more entity rules corresponding to entity data of the user request. The method also can include overwriting entity information of the entity data corresponding to the one or more entity rules. Additionally, the method can include outputting the output. Furthermore, the method can include transmitting, to the user device, a response to the user. Other embodiments are disclosed.

Automatically rectifying in real-time anomalies in natural language processing systems

A system for generating compressed product titles that can be used in conversational transactions includes a computing device configured to obtain product title data characterizing descriptive product titles of products available on an ecommerce marketplace and to determine compressed product titles based on the product title data using a machine learning model that is pre-trained using a replaced-token detection task. The computing device also stores the compressed product titles for use during conversational transactions.

Methods and apparatuses for discriminative pre-training for low resource title compression

The disclosed subject matter relates to a system and method for providing an automated assistant that retrieves information from a knowledge base in response to a user's natural language communications. A refinement signal based on a subsequent user communication relevant to a previous search, establishes the type of search to be performed by the automated assistant in generating a response to the user communications. A reply communication to the user includes the selected results from search type selected. The types of searches are SPECIFIC, RELATIVE and NEGATION searches.

Methods and apparatus for refining a search

A method for automatically rectifying in real-time anomalies in natural language processing systems. The method can include receiving command data from a user device of a user. The command data can correspond to a user request. The method further can include retrieving, from a new template database, a new request template corresponding to the user request. Additionally, the method can include retrieving, from the new template database, an output instruction corresponding to the new request template, when the new request template is found. The method further can include determining, by a machine learning system, the output instruction corresponding to the user request, when the new request template is not found. The method also can include transmitting the output instruction to a request processing system. The request processing system can be configured to perform the output instruction and transmit, to the user device, a response to the user request. Other embodiments are disclosed.

A system including one or more processors and one or more non-transitory computer-readable media storing computing instructions configured to run on the one or more processors and perform receiving a voice command from a user to perform a virtual action intended to apply to one item of two or more items in a cart of the user; generating a concept vector representing a concept in the voice command; transforming the respective item attributes for each of the two or more items into a respective feature vector; generating a respective candidate score for the each of the two or more items; identifying the one item to which the voice command is intended to apply; and executing an action with respect to the one item based on the voice command. Other embodiments are disclosed.

Detecting voice grocery concepts from catalog items

Systems and methods for contextual search query revision are disclosed. A user utterance including at least one semantic component is received and a plurality of candidate n-grams including the at least one semantic component and at least one additional semantic component selected from a set of prior semantic components is generated. A probability that each of the plurality of candidate n-grams is an intended n-gram is calculated and a selected one of the plurality of candidate n-grams is output based on the probability.

Growing community of inventors

Sunnyvale, CA, United States of America

Phani Ram Sayapaneni