Abstract: Generative artificial intelligence (AI) agents can output simulated paralinguistic data. AI can also be used to infer paralinguistic data using sensors that detect contextual cues from users. Paralinguistic systems and methods explained herein involve presenting paralinguistic data (whether simulated or inferred) to a user concurrently with verbal data (e.g., words) in real time during a live interaction with an AI agent and/or another user in an intuitive manner. These concepts include multiple representations of paralinguistic data that are appropriate for various output channels, depending on the mode of interaction. The paralinguistic systems enable the user to have a better understanding of the responses from the AI agent, avoid misunderstanding, and better use the AI agent to roleplay mock conversations. These concepts also enable the user to be more aware of her own contextual cues as well as contextual cues being exhibited by other users.

Abstract: In addition to an original prompt that is manually provided by a user, contextual information is sent to a generative AI to elicit a higher quality response. Sensors collect audio, video, physiological, cognitive, environmental, and digital data from the user. Machine-learning models evaluate the sensor data to infer the emotional state of the user. The emotional state is used to augment the original prompt with contextual information. The augmented prompt is fed into the generative AI to make it context-aware. Accordingly, the generative AI can automatically pick up on non-verbal cues that the user did not manually articulate in the original prompt. Just as a human-to-human conversation involves a combination of verbal and non-verbal communications, the present concepts enable the generative AI to also leverage non-verbal communication when interacting with human users.

Abstract: The present disclosure relates to a four-dimensional (4D) recommendation system for training and implementing a 4D recommendation model to provide health-related recommendation for an individual that is a subject of a volumetric capture performed by a calibrated multi-camera system. In particular, the 4D recommendation system may capture 4D data objects including time-series three-dimensional models and associated annotations and generate a knowledge base including a collection of 4D data objects stored thereon. An input 4D data object may be obtained and compared to the collection of 4D data objects to determine one or more recommendations for the input 4D data object related to the health status of the individual.

Abstract: In a precision agriculture application, using an imagery task constraint corresponding to an image capture task, an autonomous vehicle (AV) is selected to perform the task. The AV is caused to perform the task according to the imagery task constraint, causing the AV to autonomously record image data of an area in a field of view of the AV. Image data responsive to the task is received from the AV. From analysis of the image data using a processor and a memory, a material distribution task and a corresponding distribution task constraint are generated. Using the distribution task constraint, a second AV to perform the material application task is selected. The second AV is caused to perform the material distribution task according to the distribution task constraint, causing the autonomous vehicle to autonomously trigger dispersal of a material in an area in a field of view of the autonomous vehicle.

Abstract: A technique relates to tracking a foodstuff. A device images human consumable code formed on the foodstuff, the human consumable code being part of the foodstuff, the foodstuff being unpackaged. A coding associated with the human consumable code is determined. Product information of the foodstuff is retrieved from a computer system by using the coding. The product information of the foodstuff is provided on the device.

Abstract: A method for temperature control includes acquiring image data, and analyzing the image data to identify one or more individuals within the image data. A level of thermal comfort is estimated for each of the identified individuals based on the image data. The determined level of thermal comfort indicates whether each individual appears to be feeling too hot, appears to be feeling too cold or appears to be feeling satisfied with an ambient temperature. An air-conditioning unit or a heating unit is controlled based on the estimation of the level of thermal comfort for each of the identified individuals.

Abstract: To identify spaces on shelves which are not full of product and need restocking, markers having a pattern are placed on or near shelves containing product. A camera obtains an image of the shelf, products, and markers. A processor executing software is used to analyze the image to identify the markers and the shelf. Next, storage areas on the shelf are analyzed to identify vacant areas represented by a lower light intensity relative to adjacent areas. The processor determines a location of the vacant areas, and determines the size of the vacant areas using the known marker size and the size of the marker in the image, to generate a scale which is applied to the vacant area. This information and stored product information is used to determine which products should be restocked. The marker pattern can be selected to be readily recognizable by an image processing algorithm.

Abstract: An information processing system, a computer readable storage medium, and a method for identifying review material can include collecting assessment data at a server from a plurality of client devices for subject matter in a course, analyzing collectively the assessment data from the plurality of client devices, and based on the analyzing, identifying a deficient subset of topics. The method can further include selecting review material based on the deficient subset of topics identified and sending the review material or a signal representative of the review material to the plurality of client devices which can include presenting the review material to the plurality of client devices. The method can include presenting the review material to each of the plurality of client devices in a format based on a student profile corresponding to each client device in the plurality of client devices.