Abstract: A customer communication system is configured to automatically communicate with human customers in a conversation including an ordered sequence of messages. Messages from the system to the customers are selected based on a knowledge graph. The knowledge graph including multiple levels of clusters of customer messages, each of the clusters being associated with a responsive supporting message. The customer communication system is optionally configured to identify inadequacies in the knowledge graph and obtain corrections from a human expert. The system may be adapted to communicate with parties other than customers.

Abstract: In a crowd sourcing approach, responses to customer service inquiries are provided by routing the inquiries to an independent group of experts. Machine learning based systems are used in combination with contact center staff and/or the independent experts to resolve the customer service inquiries. The AI based systems can be configured to determine which of the customer service inquiries should be routed to the independent experts, and/or to generate content for inclusion in responses to the customer service inquiries. The machines systems are optionally trained based on scored responses to prior customer service inquiries. These scored responses can include content provided by a machine learning system and/or a human expert.

Abstract: In a crowd sourcing approach, responses to customer service inquiries are provided by routing a subset of the inquiries to an independent group of experts. The customer service inquiries are optionally routed to specific experts based on matches between identified subject matter of the inquiries and expertise of the experts. Embodiments include methods of classifying customer service inquiries, training a machine learning system, and/or processing customer service requests.

Abstract: In a crowd sourcing approach, responses to customer service inquiries are provided by routing a subset of the inquiries to an independent group of experts. The customer service inquiries are optionally routed to specific experts based on matches between identified subject matter of the inquiries and expertise of the experts. Embodiments include methods of classifying customer service inquiries, training a machine learning system, and/or processing customer service requests.

Abstract: In a crowd sourcing approach, responses to customer service inquiries are provided by providing the inquiries to an independent group of experts. These experts are typically able to resolve the inquiry before the inquiries are routed to a traditional contact center. The customer service inquiries are routed to specific experts based on matches between identified subject matter of the inquiries and expertise of the experts. In some embodiments, more than one expert can contribute to the resolution of an inquiry.

Abstract: In a crowd sourcing approach, responses to customer service inquiries are provided by providing the inquiries to an independent group of experts. These experts are typically able to resolve the inquiry before the inquiries are routed to a traditional contact center. The customer service inquiries are routed to specific experts based on matches between identified subject matter of the inquiries and expertise of the experts. In some embodiments, more than one expert can contribute to the resolution of an inquiry.

Abstract: Systems and methods of grading food items include a user customizable profile that allows a user to specify nutritional needs, dietary goals, or a medical state. The user profile is used to provide a user specific grade to one or more food items. This grade is configured for a user to compare food items and learn which provides better nutrition according to their profile. The user profile is optionally configured to take into account a medical state such as celiac disease, diabetes, or a nutritional deficiency. A grade can be provided for a single food item or to a list of food items.