Palo Alto Research Center Inc.

Conduent Business Services, LLC

Kyle D Dent

Daniel Gureasko Bobrow

Daniel H Greene

Johan De Kleer

Eric Saund

Daniel Davies

Ion Matei

Margaret Helen Szymanski

John Turner Maxwell, Iii

Gaurang R Gavai

Matthew Klenk

Shekhar Gupta

Jesse Vig

Harish Arsikere

Luke R Plurkowski

Filip Masri

Marzieh Nabi-Abdolyousefi

Varnith Chordia

Described are natural language web browsers configured to provide a natural language interface to an existing web browser or a newly created web browser. That is, users interact with the web browser employing speech (or text) as input and output instead of using a mouse and keyboard as input and an electronic display screen as output. Embodiments of a natural language web browser converts user questions, statements, and/or commands into actions, reads the resulting HTML and converts the HTML into natural language descriptions to provide to the user.

Natural language web browser

A computer-implemented method for determining an answer to a question in a multi-party conversation includes receiving a multi-party conversation having multiple nodes of unstructured natural language. Each node is parsed into a plurality of elements. Each element of the plurality of elements that comprises a question is identified. A conversation node list is constructed that identifies relationships between the nodes. At least one answer to the question is produced based on the conversation node list.

Using conversation structure and content to answer questions in multi-part online interactions

Embodiments described herein provide a system for generating a draft proposal. During operation, the system obtains a schema that represents a general model of a request for proposal (RFP). The system generates a structured RFP from an RFP document by structuring one or more elements of the RFP document in the structured RFP based on the schema. The system then generates a proposal outline comprising one or more sections. A respective one of the one or more sections corresponds to one of the one or more elements. The system obtains a piece of content for a respective section of the one or more sections based on a requirement specified in an element corresponding to the section and inserts the piece of content in the section of the proposal outline.

System and method for generating a proposal based on a request for proposal (RFP)

Embodiments of the present invention provide a system for automatically extracting conversational structure from a voice record based on lexical and acoustic features. The system also aggregates business-relevant statistics and entities from a collection of spoken conversations. The system may infer a coarse-level conversational structure based on fine-level activities identified from extracted acoustic features. The system improves significantly over previous systems by extracting structure based on lexical and acoustic features. This enables extracting conversational structure on a larger scale and finer level of detail than previous systems, and can feed an analytics and business intelligence platform, e.g. for customer service phone calls. During operation, the system obtains a voice record. The system then extracts a lexical feature using automatic speech recognition (ASR). The system extracts an acoustic feature. The system then determines, via machine learning and based on the extracted lexical and acoustic features, a coarse-level structure of the conversation.

System for automatic extraction of structure from spoken conversation using lexical and acoustic features

One embodiment of the present invention provides a system for providing assistance to a user of a product in diagnosing faults in the product. During operation, the system receives, at a help server, data associated with current and/or past operation of the product; performs an optimization to determine a sequence of diagnostic actions that is expected to maximize a net benefit to the user. The sequence of diagnostic actions includes one or more actions that require the user to perform at least one task, and performing the optimization involves accounting for costs to the user for performing the at least one task and savings to the user for correcting the faults. The system then interacts with the user, which involves presenting the sequence of diagnostic actions to the user.

Frugal user engagement help systems

Growing community of inventors

San Carlos, CA, United States of America

Kyle D Dent