Intuit, Inc.

Other

Faraz Sharafi

Igor A Podgorny

Matthew Cannon

Benjamin Indyk

Vitor R Carvalho

Pavlo Malynin

Sparsh Gupta

Ling Feng Wei

Greg Coulombe

Jeff W Geisler

Yason Khaburzaniya

Michael R Cowgill

Darren Duc Dao

Pratik Desai

Vitor Carvalho

Systems and methods for providing customized automatic speech recognition (ASR) in a customer support system are disclosed. In an example method, one or more data sources for training an ASR language model associated with the customer support system are identified, and one or more weighting models are selected, each weighting model applying a corresponding weight to each data source of the one or more data sources. The ASR language model is then trained based at least in part on the one or more data sources and the one or more weighting models, and a transcript may be generated for one or more customer support calls of the customer support system using the trained ASR language model.

Integrating automatic speech recognition and community question answering

A method and system provides personalized assistance to users of a data management system. The method and system trains an analysis model with both a supervised machine learning process and an unsupervised machine learning process to identify relevant assistance topics based on a user query and the attributes of the user that provided the query. The method and system outputs personalized assistance to the user based on the analysis of the analysis model.

Method and system for user experience personalization in data management systems using machine learning

A method for executing a computerized query includes receiving a new query from a user device. The query includes natural language text. Based on a type of user, and using an alternative term generator, a selected data model is selected from among pre-determined data models. The selected data model is particular to the type of user. Each of the pre-determined data models includes a corresponding semantic graph data model that establishes semantic relationships between words. Query words in the natural language text are compared to the selected data model using the alternative term generator to find at least one alternative term. The alternative term has a semantic relationship to a query word in query words. The semantic relationship exceeds a first threshold value. The alternative term is substituted for a query word to form a revised query. The revised query is executed on a search engine using the alternative terms.

Modifying computerized searches through the generation and use of semantic graph data models

A customer self-help system employs artificial intelligence and machine learning to identify self-help content that is responsive to a user query by analyzing and searching a plurality of customer self-help systems. The customer self-help system generates a self-help relationship model by applying one or more processes/algorithms on training set data. In response to a user query, the customer self-help system identifies ones of the plurality of customer self-help systems that are relevant to the user query and searches the relevant ones of the plurality of customer self-help systems for self-help content that is responsive to the user query. The customer self-help system then provides the self-help content to the user in response to receipt of the user query from the user.

System and method for responding to search queries using customer self-help systems associated with a plurality of data management systems

A method for text classification involves generating, using a bilingual embedding model, source language embeddings for source language documents; obtaining source language document labels of the source language documents; and training a source language classifier model and a label embedding network, executing on a computing system, using the source language embeddings and the source language document labels. The method further involves generating pseudo-labels for unlabeled target language documents, by: generating, using the bilingual embedding model, target language embeddings for the unlabeled target language documents, and applying the source language classifier model and the label embedding network to the target language embeddings to obtain the pseudo-labels for the unlabeled target language documents. In addition, the method involves training a target language classifier model executing on the computing system using the target language embeddings and the pseudo labels.

Cross-language models based on transfer learning

The invention relates to a method. The method includes receiving a flawed input comprising a domain specific misspelling. The method further includes encoding, by an encoder machine learning model executing on a computer processor, the flawed input on a per character basis to create a context vector. The method further includes decoding, by a decoder machine learning model executing on the computer processor, the context vector on the per character basis to create a rephrased input lacking the domain specific misspelling. The method further includes presenting the rephrased input.

Misspelling correction based on deep learning architecture

A method and system for employing biometric data includes first and second user computing systems coupled to respective first and second biometric devices for generating biometric data. A first user of the first user computing system uses the first biometric device, thus causing a generation of first biometric data which is then used as a database index to locate and authorize access to a database zone exclusively dedicated to the first user. The first user can further access the database zone on the second user computing system, and authorize access to a portion of data within the database zone to a second user of the second user computing system.

Method and system for employing biometric data to authorize cloud-based transactions

A method for decoding a natural language user query involves obtaining the user query submitted by a user, segmenting the user query into words, generating a character embedding for each of the words, and generating a word embedding for each of the words. The method further involves obtaining a clickstream from tracked clicks of the user, generating a clickstream embedding from the clickstream, and for each of the words, generating a unified feature representation based on the character embedding and the word embedding for each of the words, and the clickstream embedding. The method also involves decoding the unified feature representations to obtain a decoded user query, and processing the user query using the decoded user query.

Growing community of inventors

San Diego, CA, United States of America

Faraz Sharafi