Conversica, Inc.

Amazon Technologies, Inc.

Siddhartha Reddy Jonnalagadda

James D Harriger

Werner Koepf

Macgregor S Gainor

Joseph M Silverbears

William Dominic Webb-Purkis

Ryan Francis Ginstrom

George Alexis Terry

Arindam Mandal

Prakash Krishnan

Ariya Rastrow

Nikko Strom

Angeliki Metallinou

Vincent Auvray

Alex Terry

Will Webb-Purkis

David Chi-Wai Tang

Minmin Shen

Rohit Prasad

Ashish Kumar Agrawal

Chao Wang

Shiv Naga Prasad Vitaladevuni

Elizabeth E Shriberg

Viktor Rozgic

Raefer Christopher Gabriel

Ying Shi

Shishir Sridhar Bharathi

Aaron Challenner

Anushree Venkatesh

Savas Parastatidis

Katherine M Ryan

Alexandros Potamianos

Avani Parakh

Thomas Edward Taylor

Abhay Kumar Jha

Patrick D Griffin

Brian Matthew Kaminski

John Sansone

Jennifer Kirkland

Josey Diego Sandoval

Nishtha Gupta

Bonan Zheng

Amotz Maimon

Yun Lei

Arjit Biswas

Christopher Allan Long

Colin C Ferguson

Keith Godfrey

The present application provides techniques for implementing a skill component, configured to perform an assessment of a user, as part of a speech processing system. The system may receive a natural language user input requesting assistance. The skill component may, using one or more machine learning models, determine at least one characteristic of the natural language input (e.g., lexical embedding, acoustic embedding, topic, tone, etc.). The skill component may determine state data for a present session, where the state data indicates a topic of the natural language user input and/or a user state associated with the natural language user input. The skill component may determine past state data of one or more past sessions, and generate a question to the user based on the state data for the natural language user input and the past state data.

Conversation-based skill component for assessing a user's state

A natural language system may be configured to act as a participant in a conversation between two users. The system may determine when a user expression such as speech, a gesture, or the like is directed from one user to the other. The system may processing input data related the expression (such as audio data, input data, language processing result data, conversation context data, etc.) to determine if the system should interject a response to the user-to-user expression. If so, the system may process the input data to determine a response and output it. The system may track that response as part of the data related to the ongoing conversation.

Dialog management for multiple users

A system that is capable of resolving anaphora using timing data received by a local device. A local device outputs audio representing a list of entries. The audio may represent synthesized speech of the list of entries. A user can interrupt the device to select an entry in the list, such as by saying 'that one.' The local device can determine an offset time representing the time between when audio playback began and when the user interrupted. The local device sends the offset time and audio data representing the utterance to a speech processing system which can then use the offset time and stored data to identify which entry on the list was most recently output by the local device when the user interrupted. The system can then resolve anaphora to match that entry and can perform additional processing based on the referred to item.

Techniques for storing and using multi-session context are described. A system may store context data corresponding to a first interaction, where the context data may include action data, entity data and a profile identifier for a user. Later the stored context data may be retrieved during a second interaction corresponding to the entity of the second interaction. The second interaction may take place at a system different than the first interaction. The system may generate a response during the second interaction using the stored context data of the prior interaction.

Multi-session context

Systems and methods for improvements in AI model learning and updating are provided. The model updating may reuse existing business conversations as the training data set. Features within the dataset may be defined and extracted. Models may be selected and parameters for the models defined. Within a distributed computing setting the parameters may be optimized, and the models deployed. The training data may be augmented over time to improve the models. Deep learning models may be employed to improve system accuracy, as can active learning techniques. The models developed and updated may be employed by a response system generally, or may function to enable specific types of AI systems. One such a system may be an AI assistant that is designed to take use cases and objectives, and execute tasks until the objectives are met. Another system capable of leveraging the models includes an automated question answering system utilizing approved answers. Yet another system for utilizing these various classification models is an intent based classification system for action determination. Lastly, it should be noted that any of the above systems may be further enhanced by enabling multiple language analysis.

Systems and methods for training machine learning models using active learning

Systems and methods for scheduling appointments are provided. This scheduling process includes generating an introductory message proposing an appointment with the target with a request for timing. The target responds, and this response is processed for a positive interest and the presence of a proposed time. If there is an absence of positive interest then the messaging may be discontinued. However, in the presence of a positive interest, and a proposed time from the target, the system may access an external scheduling system when a proposed time is present. This includes determining availability of at least one resource at the proposed time. The system then iteratively provides suggested times close to the proposed time when the resource is not available for the proposed time. The system then confirms the appointment when the resource is available for either the proposed time or any of the suggested times.

Systems and methods for improved automated conversations with attendant actions

Systems and methods for natural language processing and classification are provided. In some embodiments, the systems and methods include a communication editor dashboard which receives the message, performs natural language processing to divide the message into component parts. The system displays the message in a first pane with each of the component parts overlaid with a different color, and displaying in a second pane the insights, the confidence scores associated with each insight, the sentiment and the actions. In another embodiment, the systems and methods include combining outputs from multiple machine learned AI models into a unified output. In another embodiment, the systems and methods include responding to simple question using natural language processing.

Systems and methods for natural language processing and classification

Systems and methods for a configurable response-action engine are provided. Actions are generated for a conversation when an insight is received from a natural language processing system. Industry, segment, client specific instructions, third party data, a state for the lead and lead historical patterns are also received. A decision making action model is tuned using this information. An objective for the conversation may be extracted from the state information for the lead. The tuned model is then applied to the insight and objective to output an action. A response message may be generated for the action. The action is directed to cause a state transition of the lead to a preferred state. In another embodiment, systems and methods are presented for feature extraction from one or more messages. In yet other embodiments, systems and methods for message cadence optimization are provided.

Systems and methods for configurable messaging response-action engine

Systems and methods for configurable messaging with feature extraction

Systems and methods for automated question response

Growing community of inventors

Bothell, WA, United States of America

Siddhartha Reddy Jonnalagadda