Abstract: One embodiment provides a method, including: receiving, in an environment for developing a conversational tutor, domain content corresponding to a domain of the conversational tutor, wherein the conversational tutor comprises a conversational agent designed to assist students in learning a domain; receiving, at the environment, tutoring content developed by a user, wherein the tutoring content comprises a tutoring script comprising questions to be presented to the student during a tutoring session with the conversational tutor to assist the student in learning the domain; evaluating, within the environment, the tutoring content against the domain content, wherein the evaluating comprises (i) identifying missing tutoring content, (ii) identifying the difficulty of the tutoring content, and (iii) identifying question dependencies; and providing, at the environment, at least one recommendation, identified from results of the evaluation, for adjusting the tutoring content.

Abstract: Aspects of the present disclosure relate to controlling virtual reality (VR) content displayed on a VR head mounted display (HMD). Communication can be established between a computer system, a VR HMD, and a mobile device. A user input configured to control VR content displayed on a display of the VR HMD can be received on the mobile device. The VR content displayed on the VR HMD can then be controlled based on the user input received on the mobile device.

Abstract: A first user access, directed to a first network document, of a first user is detected. One or more first network document concepts in the first network document are detected. A first user profile of the first user is retrieved based on the first user access. A first knowledge gap of the first user is identified based on the first network document concepts and based on the first user profile. One or more additional network documents are obtained based on the one or more first network document concepts. The additional network documents include at least a first concept of the one or more first network document concepts. The first network document is modified to include at least a portion of the first concept from the one or more additional network documents. The modification is based on the first knowledge gap and on the one or more additional network documents.

Abstract: Embodiments provide a computer-implemented method of recommending camera configuration parameters for taking one or more photographs, the method including: acquiring first spatial dimension data, first temporal dimension data, and first manufacturer dimension data of a particular camera for taking the one or more photographs; inputting the first spatial dimension data, the first temporal dimension data, and the first manufacturer dimension data to a trained machine learning model; recommending, by the trained machine learning model, one or more vantage points for taking the one or more photographs, each vantage point corresponding to a different set of predicted camera configuration parameters; receiving a selection of one of the one or more vantage points from the user; and providing a set of predicted camera configuration parameters corresponding to the selected vantage point.

Abstract: Methods, systems, and computer program products for customizing agricultural practices to maximize crop yield are provided herein. A computer-implemented method includes obtaining data pertaining to (i) a geographical area comprising a plurality of regions and (ii) one or more agricultural practices applied to the geographical area; assigning each of the plurality of regions to a respective cluster of a set clusters, based at least in part on comparing features identified in the data, wherein similar ones of said regions are assigned to the same cluster; generating instructions that are specific to a given cluster in the set, wherein the instructions relate to agricultural tasks to be performed on the regions assigned to the given cluster; and triggering, based on said instructions, one or more automated farming processing devices, thereby carrying out at least a portion of said agricultural tasks.

Abstract: Targeted acquisition of data for model training includes automatically generating metadata describing samples, of an initial dataset, in neighborhoods of an embedding space in which the samples are embedded. The samples described by the automatically generated metadata are classified by a classification model, and include both correctly classified samples in the neighborhoods and incorrectly classified samples in the neighborhoods. Additionally, attributes of one or more correctly classified samples of the collection of samples and one or more incorrectly classified samples of the collection of samples are identified, and queries are generated based on the identified attributes, the queries tailored, based on the attributes, to retrieve additional training data for training the classification model to more accurately classify samples and avoid incorrect sample classification.

Abstract: Provided are a computer program product, system, and method for generating constraints based on reported crop arrivals to marketplaces and remote sensed data to estimate farm yields of farm fields. A total arrival quantity constraint for a marketplace is generated comprising a function of a reported arrival of crops at a marketplace and an estimated arrival to the marketplace comprising a sum of farm yields for the farm fields, wherein the farm yields comprise variables to optimize. Sensed data of the farm fields is used to determine relationships of the farm yields for the farm fields. Comparative farm yield constraints are generated comprising relationships of the farm yields for different pairs of farms. A constraint optimization problem is solved based on the total arrival quantity constraint and comparative farm yield constraints to calculate the farm yields of the farm fields.

Abstract: One embodiment provides a method, including: receiving a plurality of consumer feedback comments regarding one of a plurality of agricultural food products, wherein each of the plurality of consumer feedback comments comprises information regarding a characteristic of a given agricultural food product, wherein each of the plurality of agricultural food products corresponds to an agricultural source producing an agricultural food product category; updating a rating of each of the plurality of agricultural food products based upon consumer feedback comments corresponding to a given agricultural food product, wherein the updating comprises aggregating the received consumer feedback comments with previously supplied consumer feedback comments for agricultural food products within the agricultural food product category of a given agricultural source; ranking the plurality of agricultural food products based upon the ratings of the plurality of agricultural food products, wherein the ranking comprises ranking the p

Abstract: A method includes providing a server executing computer code embodying the chat-bot, receiving, via the server, a requirement for customization of a main computer code, the main computer code including modules, and determining, by the chat-bot, top-k modules of the main computer code potentially affected given the requirement for customization. The determination of the top-k modules includes representing each of the modules of the main computer code in an embedding vector space, representing the requirement for customization as a vector in the embedding space, and fetching the top-k modules nearest the requirement for customization in the embedding space. The method further includes determining a question, communicating the question to an entity providing the requirement for customization, receiving a response to the question, and filtering the top-k modules using the response to determine a set of the modules associated with the requirement for customization.

Abstract: One embodiment provides a method, including: receiving a story, wherein the story is received in a text-based format; identifying conversational blocks contained within the story, wherein the identifying conversational blocks comprises (i) identifying conversational turns within the story, (ii) identifying topic switches between conversational turns, and (iii) grouping conversational turns occurring between topic switches into a conversational block; for each of the conversational blocks, obtaining at least one image illustrating the corresponding conversational block, wherein the obtaining comprises (i) extracting concepts from the conversational block and (ii) identifying images illustrating the concepts; and generating a visual storyline representing the story by ordering the images obtained for each of the conversational blocks, based upon an order of the conversational blocks within the story, wherein the generating comprises refining the images to maintain consistency between the images.

Abstract: One embodiment provides a method, including: receiving a plurality of transcripts, each transcript corresponding to an interaction between a student and a tutoring agent; identifying conversational patterns within the plurality of transcripts, the identified conversational patterns indicating a level of understanding regarding the interaction between the tutoring agent and the student, wherein the identifying comprises (i) identifying an exchange between the tutoring agent and the student, the exchange comprising a conversational turn by each of the tutoring agent and the student and (ii) classifying each of the conversational turns into a response type; determining, based upon the identified conversational patterns, a possible improvement to the tutoring agent, wherein the possible improvement is determined based upon the classified response types of each of (i) the tutoring agent and (ii) the student; and notifying a developer of the tutoring agent of the identified possible improvement.

Abstract: One embodiment provides a method, including: obtaining information related to farming activities of a farmer; predicting an annotation category for the information, wherein the annotation category identifies a topic of the information; selecting an annotator for annotating the information based upon the annotation category, wherein the selecting comprises utilizing (i) a social proximity constraint identifying a social connection between the farmer and another farmer and (ii) a farm signature constraint identifying a similarity of the farmer to another farmer; assigning the annotator to annotate the obtained information; and receiving annotations for the information

Abstract: An agricultural plot evaluation method, computer program product and system are provided. A processor receives a plot for evaluation. A processor determines one or more characteristics associated with the plot for evaluation. A processor identifies a plurality of similar plots based on at least one of the one or more characteristics associated with the plot for evaluation. A processor generates a prediction model for one or more features of the plurality of similar plots. A processor determines a score for the plot for evaluation based, at least in part, on the prediction model for one or more features of the plurality of similar plots.

Abstract: Technology for: receiving training data sets for a physical task performed by a set of human(s), with each training data set including: (i) a plurality of streams of sensor input, and (ii) an identification of a time of a first verification point instance; defining, by machine logic, a first verification point definition, with the first verification point definition including a plurality of parameter value ranges; monitoring, by a plurality of active sensors, an instance of the physical task as it is being performed by a set of human(s) to obtain a set of sensor stream parameter value(s) for each sensor of the plurality of active sensors; and determining, by machine logic, an occurrence of a first instance of the first verification point based on the plurality of parameter ranges of the first verification point definition and the set of sensor stream parameter value(s).

Abstract: Smart meal preparation can be performed where a consumer order for a food item and a consumer request related to the food item are received. One or more recipes for the food item are received. The one or more recipes are analyzed to determine a conflict with the consumer request. The consumer request and the determined conflict are transmitted to a wearable device worn by a cook who will prepare the food item. Alerts related to the conflict are provided to the cook via the wearable device during preparation of the food item. Preparation of the food item is monitored for compliance with the consumer request.

Abstract: Aspects of the present invention provide an approach for managing communications. In an embodiment, a set of informational components are extracted from a received textual message received at a user device. Based on these informational components, a group of pictorial representations is generated. Each pictorial representation that is generated corresponds to one of a plurality of the informational components of the textual message. The pictorial representations are assembled into a number of potential pictorial message representations that each represent the content of the textual message. An information loss is calculated for each of the potential pictorial message representation. A pictorial message is selected from the set based on the information loss and available display space of the user device and is displayed on the user device.

Abstract: Aspects of the present invention provide an approach for managing communications. In an embodiment, a set of informational components are extracted from a received textual message received at a user device. Based on these informational components, a group of pictorial representations is generated. Each pictorial representation that is generated corresponds to one of a plurality of the informational components of the textual message. The pictorial representations are assembled into a number of potential pictorial message representations that each represent the content of the textual message. An information loss is calculated for each of the potential pictorial message representation. A pictorial message is selected from the set based on the information loss and available display space of the user device and is displayed on the user device.

Abstract: Embodiments of the present invention describe identifying details of the area around a first vehicle and identifying a potential confusion point in a navigation route of the first vehicle. Additionally, embodiments of the present invention determining based on a threshold, whether to provide a driver of the first vehicle with a visual clue to assist with navigating through the identified potential confusion point, responsive to determining to provide a visual clue, identifying one or more visual clues from an area surrounding the first vehicle; and outputting the identified one or more visual clues to the driver.

Abstract: One embodiment provides a method, including: receiving a story, wherein the story is received in a text-based format; identifying conversational blocks contained within the story, wherein the identifying conversational blocks comprises (i) identifying conversational turns within the story, (ii) identifying topic switches between conversational turns, and (iii) grouping conversational turns occurring between topic switches into a conversational block; for each of the conversational blocks, obtaining at least one image illustrating the corresponding conversational block, wherein the obtaining comprises (i) extracting concepts from the conversational block and (ii) identifying images illustrating the concepts; and generating a visual storyline representing the story by ordering the images obtained for each of the conversational blocks, based upon an order of the conversational blocks within the story, wherein the generating comprises refining the images to maintain consistency between the images.

Abstract: Methods, systems and computer program products for automated learning are provided herein. A computer-implemented method includes authenticating a plurality of users for an automated learning session, wherein the plurality of users correspond to at least one device, and providing the automated learning session for the plurality of users. Providing the automated learning session comprises analyzing a plurality of learning models corresponding to one or more of the plurality of users, determining, based on the analysis, one or more activities to be performed by the plurality of users during the automated learning session, and executing the one or more activities on at least one device.