Conversica, Inc.

Werner Koepf

Siddhartha Reddy Jonnalagadda

James D Harriger

Macgregor S Gainor

Joseph M Silverbears

Ryan Francis Ginstrom

William Dominic Webb-Purkis

George Alexis Terry

Will Webb-Purkis

Alex Terry

Patrick D Griffin

Jennifer Kirkland

Christopher Allan Long

Colin C Ferguson

Keith Godfrey

Brian Matthew Kaminski

John Sansone

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

Seattle, WA, United States of America

Werner Koepf