Abstract: 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.

Abstract: 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.

Abstract: 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.

Abstract: 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.

Abstract: 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.

Abstract: Systems and methods for processing automated message exchanges using artificial intelligence are providing. In some embodiments, a message is generated by populating variable fields within a message template with corresponding data from a knowledge set and/or a lead data set. Lead data is the data known about the intended recipient of the message, whereas the knowledge set is contextual knowledge useful for the artificial intelligence. Once the message has been generated, the system waits for a response from the lead. Once the response is received, the AI algorithms may categorize the response and generate a corresponding confidence value for the categorization. The categorization and confidence level are utilized to determine which subsequent action the system takes. The actions consist of sending a follow-up message, a subsequent message in the series, requesting user input, or discontinuing messaging.

Abstract: 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.

Abstract: Systems and methods for management of automated dynamic messages are providing. In some embodiments, a data store is populated with one or more knowledge sets and one or more lead datasets in response to a user's input. A campaign builder may be provided to the user for generating and initiating campaigns. A campaign is a series of messages designed to satisfy one or more objectives. The campaign builder allows the creation of a campaign by allowing the composition of a series of message templates with variable fields. The variable fields correspond to classes of data from the knowledge sets and/or the lead data. Once the campaign has been initiated, the system categorizes the responses using algorithms. These categorizations have corresponding confidence levels. If the confidence level is too low, manual user intervention may be required in order to determine which subsequent action the system should perform.

Abstract: Systems and methods for configuring AI algorithms and knowledge sets within an automated messaging system are providing. In some embodiments, a message is received. A subsection of text from the training message is selected. Likewise, a knowledge set is selected. The knowledge set includes probabilistic associations between a term and a category. The terms in the selected subsection of text are compared to the knowledge sets to generate insights and contexts. The insights enable the categorization of the training message. This categorization has an associated confidence value based upon how strongly the terms in the text subsection are associated with the category (per the selected knowledge set). A low confidence value causes the message to be a candidate for training (a training message). Once identified as a training message, it may be displayed to an AI developer for approval or rejection of the categorization.