Abstract: In some examples, a software agent executing on a server receives a communication comprising a first utterance from a customer and predicts, using an intent classifier, a first intent of the first utterance. Based on determining that the first intent is order-related, the software agent predicts, using a dish classifier, a cart delta vector based at least in part on the first utterance and modifies a cart associated with the customer based on the cart delta vector. The software agent predicts, using a dialog model, a first dialog response based at least in part on the first utterance and provides the first dialog response to the customer using a text-to-speech converter.

Abstract: In some aspects, an edge appliance is placed in an active mode and causes a software agent that is based on a machine learning algorithm to engage in a conversation to take an order from a customer that is located at an order post. The edge appliance provides, using a communication interface, audio data that includes the conversation, to a communications system of a restaurant. The edge appliance provides, using the communication interface, a content of a cart associated with the order to a point-of-sale terminal of the restaurant. If the edge appliance determines, using the communication interface, that a microphone of the communication system is receiving audio input from an employee, the edge appliance automatically transitions the edge appliance from the active mode to an override mode, enabling the employee to receive a remainder of the order from the customer.

Abstract: In some examples, a server may receive an utterance from a customer. The utterance may be included in a conversation between the artificial intelligence engine and the customer. The server may convert the utterance to text and determine a customer intent based on the text and a user history. The server may determine a user model of the customer based on the text and the customer intent. The server may update a conversation state associated with the conversation based on the customer intent and the user model. The server may determine a user state based on the user model and the conversation state. The server may select, using a reinforcement learning based module, a particular action from a set of actions, the particular action including a response and provide the response to the customer.

Abstract: In some aspects, an edge appliance is placed in an active mode and causes a software agent that is based on a machine learning algorithm to engage in a conversation to take an order from a customer that is located at an order post. The edge appliance provides, using a communication interface, audio data that includes the conversation, to a communications system of a restaurant. The edge appliance provides, using the communication interface, a content of a cart associated with the order to a point-of-sale terminal of the restaurant. If the edge appliance determines, using the communication interface, that a microphone of the communication system is receiving audio input from an employee, the edge appliance automatically transitions the edge appliance from the active mode to an override mode, enabling the employee to receive a remainder of the order from the customer.

Abstract: A software agent, comprising a machine learning algorithm trained to engage in a conversation with a customer to take an order, receives an utterance from a customer. The utterance is converted to text and an analysis of the text performed. If the software agent determines, based on the analysis, that the software agent is untrained to respond to the text, the software agent establishes a connection to a point-of-sale device associated with a human agent. The human agent may perform a modification (e.g., an edit to the text, a modification to a cart, or provide input) to a modifiable portion displayed by the point-of-sale device. The software agent, based at least in part on the modification, resumes the conversation with the customer. The human agent does not directly interact with the customer during the conversation between the software agent and the customer.

Abstract: In some examples, a server may receive an utterance from a customer. The utterance may be included in a conversation between the artificial intelligence engine and the customer. The server may convert the utterance to text and determine a customer intent based on the text and a user history. The server may determine a user model of the customer based on the text and the customer intent. The server may update a conversation state associated with the conversation based on the customer intent and the user model. The server may determine a user state based on the user model and the conversation state. The server may select, using a reinforcement learning based module, a particular action from a set of actions, the particular action including a response and provide the response to the customer.

Abstract: In some examples, a software agent executing on a server receives a communication comprising a first utterance from a customer and predicts, using an intent classifier, a first intent of the first utterance. Based on determining that the first intent is order-related, the software agent predicts, using a dish classifier, a cart delta vector based at least in part on the first utterance and modifies a cart associated with the customer based on the cart delta vector. The software agent predicts, using a dialog model, a first dialog response based at least in part on the first utterance and provides the first dialog response to the customer using a text-to-speech converter.

Abstract: In some examples, a software agent executing on a server receives a communication comprising a first utterance from a customer and predicts, using an intent classifier, a first intent of the first utterance. Based on determining that the first intent is order-related, the software agent predicts, using a dish classifier, a cart delta vector based at least in part on the first utterance and modifies a cart associated with the customer based on the cart delta vector. The software agent predicts, using a dialog model, a first dialog response based at least in part on the first utterance and provides the first dialog response to the customer using a text-to-speech converter.

Abstract: In some examples, a software agent executing on a server an utterance from a customer. The software agent converts the utterance to text. The software agent creates an audio representation of the text and performs a comparison of the audio representation and the utterance. The software agent creates edited text based on the comparison. For example, the software agent may determine, based on the comparison, audio differences between the audio representation and the utterance, create a sequence of edit actions based on the audio differences, and apply the sequence of edit actions to the text to create the edited text. The software agent outputs the edited text as a dialog response to the utterance.

Abstract: The present invention relates to systems and methods for searching a document archive in such a manner that it is easy to search, drill down, drill-up and drill across documents in an archive using multiple, independent hierarchical category taxonomies of the document archive.

Abstract: The present invention relates to systems and methods for searching an information directory in such a manner that it is easy to search, drill down, drill up and drill across an information directory using multiple independent hierarchical category taxonomies of the directory.

Abstract: The present invention relates to systems and methods for interactively searching a database (905) in such a manner that it is quick and easy to search, drill down, drill-up and drill across a data collection (905) presenting the user with summary information using multiple independent hierarchical category taxonomies (915) of the data collection (905). The present invention also relates to business methods associated with providing information to users based on the searching systems and methods, and the revenue stream attached thereto. The present invention also relates to retrieving information from a database based on content aggregation, management and distribution.

Abstract: The present invention relates to systems and methods for searching a document archive in such a manner that it is easy to search, drill down, drill-up and drill across documents in an archive using multiple, independent hierarchical category taxonomies of the document archive.

Abstract: The present invention relates to systems and methods for searching a data collection of employment information in such a manner that it is easy to search, drill down, drill-up and drill across the data collection using multiple independent hierarchical category taxonomies of the data collection.

Abstract: The present invention relates to systems and methods for searching a bioinformatics data collection in such a manner that it is easy to search, drill down, drill-up and drill across biological data in the data collection using multiple, independent hierarchical category taxonomies of the biological data in the bioinformatics data collection.

Abstract: The present invention relates to systems and methods for searching a product catalog data collection in such a manner that it is easy to search, drill down, drill-up and drill across products in the data collection using multiple, independent hierarchical category taxonomies of the products in the product catalog data collection.

Abstract: The present invention relates to systems and methods for searching an information directory in such a manner that it is easy to search, drill down, drill up and drill across an information directory using multiple independent hierarchical category taxonomies of the directory.