Abstract: A system for entity-level clarification in conversation services includes a memory having instructions therein. The system also includes at least one processor in communication with the memory. The at least one processor is configured to execute the instructions to receive a conversation services training example set, build an entity usage map using the conversation services training example set, receive a user utterance, and, responsive to a reception of the user utterance, generate a clarification response using the entity usage map. The at least one processor is also configured to execute the instructions to provide the clarification response to a user.

Abstract: An approach is provided that captures a digital image of an object that has a number of facets. The approach further determines the actual sizes of various facets found on the object. The actual sizes of the facets are used to identify compatible objects based, with the compatible objects being objects that can work with the object.

Abstract: Embodiments provide dynamic consumer incentive generation by generating a combination discount offer that provides a total discount value to a customer in response to verifying that the customer executes a commercial activity at each of different (first and second) ones of a discount grouping plurality of businesses, in response to determining that it is probable as a function of historic purchasing data that the customer will purchase an item from the first business when they make a purchase from the second business; and allocating different portions of the total discount value as costs to the first and second businesses that have different values determined as a function of a difference between a first probability that the customer will purchase an item from the first business and a second probability that the customer will purchase an item from the second business.

Abstract: An approach is provided that captures a digital image of an object, such as a piece of home improvement hardware, that has any number of facets. From the captured digital image, the approach determines an actual size the object's facets, and further identifies any number of hardware tools that can be used to manipulate the hardware object based in part on the actual size of the object's facets.

Abstract: A method, system and computer-usable medium for augmenting the training of a conversational system. In certain embodiments, the method comprises: ingesting a training set to be used in training of the conversational system, the training set including objects for use in the training, wherein the objects include one or more object types, wherein the object types include one or more of an entity or intent; generating proposed reductions for inclusion in an augmented training set, wherein the proposed reductions include one or more of: reduction candidates generated using properties of objects included in the training set; reduction candidates obtained from search queries of one or more external resources, wherein the search queries relate to one or more objects included in the training set; filtering the proposed reductions to generate a reduced set of proposed reductions; and augmenting the training set with the reduced set of proposed reductions.

Abstract: A life-logging system is configured to register a plurality of cameras and a plurality of users to a life-logging network. The life-logging system receives a plurality of camera profiles associated with the plurality of cameras and a user profile associated with a user. The life-logging system determines location information associated with the user and identifies a camera of the plurality of cameras for capturing an image of the user based on the plurality of camera profiles, the user preferences, and the location information. The life-logging system arranges for the image of the user captured by the camera to be delivered to a client device.

Abstract: In an approach to determining one or more logical breaks in a digital text, a computer determines a reading speed of a user for a current reading session of a digital text and an available time for the current reading session for the user. The computer then determines, based, at least in part, on the reading speed and the available time, a user range in the digital text for the current reading session, and then one or more possible logical breaks within the user range. The computer further determines a first logical break, based on the determined user range, of the one or more possible logical breaks for the current reading session.

Abstract: An approach is provided to generate a trip itinerary. The approach receives a set of points of interest from a user with the user being one of a number of user that uses the system. The approach then retrieves user-defined factors from a user travel-based corpus that is accessible from a question-answering (QA) system with the user travel-based corpus corresponding to the requesting user. The QA system is utilized to analyze the user-defined factors in relation to each of the points of interest. In addition, constraints that pertain to each of the points of interest are identified by the QA system utilizing travel oriented data that has been ingested into the QA system. The approach then generates an itinerary based upon the analysis and the identified constraints.

Abstract: A website navigation system has an analysis system which receives a request for an Internet web page from a client device. The analysis system receives web page data associated with the web page from the Internet and performs a data analysis process to organize the web page data for use in a virtual conversation with the user in order to present the web page in an audible format. The analysis system identifies separate elements of the web page from the web page data and extracts information from the separate elements based on the web page data. The analysis system groups the separate elements into categories based on the extracted information and sorts the groups of separate elements based on usage statistics. The analysis system then generates a prompt for being output to the user by the client device as audible output based on the sorted groups of separate elements.

Abstract: A method, system and computer-usable medium for performing a meal kit personalization operation, comprising: receiving recipe purchase history information for a plurality of customers; associating the recipe purchase history information with a plurality of input recipes; identifying a plurality of input recipes for use for a particular time period; identifying elements of the input recipes that limit appeal of each of the plurality of input recipes for the particular time period, the elements being identified using purchase predictor information relating to the elements; generating alternative recipes based upon the input recipes; and selecting a predefined number of these input recipes and alternative recipes for presentation to a particular user.

Abstract: Systems, methods, and computer-readable media for constructing a conversation model using documentation of an application programming interface (API) are disclosed. The conversation model can be used to train a natural language classifier. API endpoints may be represented in the API documentation as (verb, resource, element) tuples. These tuples can be converted into intent and parameters of the API endpoints can be converted into entities. In addition, example utterances may be created for each intent. The conversation model can be generated using the intents, example utterances, and/or entities.

Abstract: Mechanisms for training a human user to perform an operation and provided. The mechanisms generate a domain specific knowledge base comprising a set of entities and corresponding domain specific attributes and expand the domain specific knowledge base to include values for the domain specific attributes through an automated bootstrap learning process that performs natural language processing and analysis of natural language content using a set of pre-condition annotated action terms, thereby generating an expanded domain specific knowledge base. The mechanisms evaluate an input from another device identifying an action associated with an entity in the set of entities, based on a retrieved domain specific attribute value and the retrieved pre-condition annotation from the expanded domain specific knowledge base. The mechanisms output a notification to a user computing device indicating whether the input is correct or incorrect to thereby train a user associated with the user computing device.

Abstract: A chatbot answer database can be generated from a question and answer document. A question/answer processor can receive a document that includes questions and answers. A set of entities can be determined from the answers in the document. A set of triplets can be constructed from the answers, and stored in a chatbot database. For each answer, the question/answer processor can determine text for slots of the triplet based on the entities extracted from the answer. The triplet can be stored as a tree structure in a database of tree structures associated with the document. A chatbot can receive questions, and provide answers based on the database of tree structures associated with the document.

Abstract: The disclosed embodiments include a system, computer program product, and computer-implemented method configured to modify a knowledge graph. The disclosed embodiments seek to improve the process of expanding a knowledge graph by identifying information that is useful and relevant to the needs of the users based on questions being asked by users. In one embodiment, the information is collected using a gaming platform. The disclosed embodiments augment the knowledge graph, by adding new entities and/or relationships, based on the gathered information.

Abstract: A computer-implemented method for building a semantic analysis model. In one embodiment, the computer-implemented method includes creating proxy tags comprising a set of surface form variants. The computer-implemented method creates training examples comprising a combination of terminal tokens and at least one of the proxy tags. The computer-implemented method builds the semantic analysis model using the training examples.

Abstract: A method includes receiving, by a first device of a transportation provider, a device ID of a particular device of a user and purchase information regarding a purchase, by the user, of one or more goods or services. The method includes sending, by the first device, the device ID of the particular user device to a central server. The method includes receiving, by the first device from the central server, information regarding the particular user device. The method includes determining, by the first device, a selected transportation vehicle based on the purchase information and the information regarding the particular user device. The method includes sending, by the first device, a vehicle ID of the selected transportation vehicle to the central server. The method includes providing a transportation service to the user using the particular user device and the selected transportation vehicle.

Abstract: An approach is provided that captures a digital image of an object that has a number of facets. The approach further determines the actual sizes of various facets found on the object. The actual sizes of the facets are used to identify compatible objects based, with the compatible objects being objects that can work with the object.

Abstract: Mechanisms for training a human user to perform an operation and provided. The mechanisms generate a domain specific knowledge base comprising a set of entities and corresponding domain specific attributes and expand the domain specific knowledge base to include values for the domain specific attributes through an automated bootstrap learning process that performs natural language processing and analysis of natural language content using a set of pre-condition annotated action terms, thereby generating an expanded domain specific knowledge base. The mechanisms evaluate an input from another device identifying an action associated with an entity in the set of entities, based on a retrieved domain specific attribute value and the retrieved pre-condition annotation from the expanded domain specific knowledge base. The mechanisms output a notification to a user computing device indicating whether the input is correct or incorrect to thereby train a user associated with the user computing device.

Abstract: An approach is provided that captures a digital image of an object that has a number of facets. The approach further determines the actual sizes of various facets found on the object. The actual sizes of the facets are used to identify compatible objects based, with the compatible objects being objects that can work with the object.

Abstract: Mechanisms for identifying hidden meaning in a portion of natural language content are provided. A primary portion of natural language content is received and a secondary portion of natural language content is identified that references the natural language content. The secondary portion of natural language content is analyzed to identify indications of meaning directed to elements of the primary portion of natural language content. A probabilistic model is generated based on the secondary portion of natural language content modeling a probability of hidden meaning in the primary portion of natural language content. A hidden meaning statement data structure is generated for the primary portion of natural language content based on the probabilistic model.