Abstract: A method, system, and computer program product for creating or augmenting a business process model using a question and answer (Q and A) system are provided in the illustrative embodiments. A request to create the business process model of a business process is received. A knowledgebase is created using a business process modeling (BPM) data and user domain data. The user domain data comprises a combination of unstructured documents and structured documents related to an operation in a user domain. A natural language (NL) question is formed corresponding to the request. The NL question and the knowledgebase are submitted to the Q and A system. A set of answers is received from the Q and A system responsive to the NL question. An answer is presented as a part of the business process model.

Abstract: Embodiments are directed to a question and answer (QA) pipeline system that adjusts answers to input questions based on a user criteria, thus implementing a content-based determination of access permissions. The QA system allows for information to be retrieved based on permission granted to a user. Documents are ingested and assigned an access level based on a defined information access policy. The QA system is implemented with the defined information access policy, the ingested documents, and the inferred access levels. For the QA system implementation, a user enters a question; primary search and answer extraction stages are performed; candidate answer extraction is performed using only content the user is allowed to access; the candidate answers are scored, ranked, and merged; ranked answers based on user permissions are filtered; and answers are provided to the user.

Abstract: Electronic natural language processing in a natural language processing (NLP) system, such as a Question-Answering (QA) system. A receives electronic text input, in question form, and determines a readability level indicator in the question. The readability level indicator includes at least a grammatical error, a slang term, and a misspelling type. The computer determines a readability level for the electronic text input based on the readability level indicator, and retrieves candidate answers based on the readability level.

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: Embodiments provide a generative group-based meal planning system and method for the creation of candidate meal plans based upon a pre-selected list of ingredients. The meal planning system can create parent meal plans based upon one or more recipes having one or more of the pre-selected ingredients. Child meal plans can be created by the random crossing of the recipes contained in the parent meal plans. The child meal plans can be scored against a genetic algorithm, such as a fitness function, which takes into consideration cost of ingredients, waste, flavor compatibility, preparation time, and ingredient shelf life. The meal planning system can utilize a cognitive system with natural language processing abilities to generate new recipes based off of waste or flavor compatibility. The child meal plans having the highest fitness score can be used as the parent meal plans in the next iteration of analysis. After a pre-determined number of iterations, a candidate meal plan can be output by the system.

Abstract: Curation of a corpus of a cognitive computing system is performed by reporting to a user a cluster model of a parse tree structure of discrepancies and corresponding assigned confidence factors detected between at least a portion of a first electronic document and a second or more electronic documents in the information corpus. Responsive to a selection by the user of a discrepancy cluster model, drill-down details regarding the discrepancy are returned to the user, for subsequent user selection of an administrative action option for handling the detected discrepancy to curate the information corpus.

Abstract: A mechanism is provided in a data processing system for tailoring question answering system output based on user expertise. The mechanism receives an input question from a questioning user and determines a set of features associated with text of the input question. The mechanism determines an expertise level of the questioning user based on the set of features associated with the text of the input question using a trained expertise model. The mechanism generates one or more candidate answers for the input question and tailors output of the one or more candidate answers based on the expertise level of the questioning user.

Abstract: Curation of a corpus of a cognitive computing system is performed interactively by reporting on user interface device to a user a parse tree illustration of discrepancies and corresponding assigned confidence factors detected between at least a portion of a first document and a second or more documents in the corpus. Responsive to a user selection of an illustrated discrepancy in the parse tree, a drill-down dialog is prepared and displayed which shows at least a text string for the portion of the first document and at least one conflicting text string from the second or more documents, and which provides at least one user-selectable administrative action option for handling the detected discrepancy. Responsive to receipt of user selection of an administrative action option, the computing system performs the action to handle the detected discrepancy.

Abstract: Embodiments generally relate a nutrition graph. In some embodiments, a method includes retrieving content associated with food from one or more food data sources. The method further includes classifying the content into food and nutrients, where each food contains one or more nutrients. The method further includes retrieving content associated with health from one or more health data sources, where the content associated with health includes information on physiological characteristics. The method further includes determining one or more of the physiological characteristics associated with a person ingesting one or more of the nutrients. The method further includes mapping a particular food, one or more of the nutrients, and one or more of the physiological effects. The method further includes generating the nutrition graph based on the mapping.

Abstract: Systems, methods, and computer program products to perform an operation comprising identifying a first available dataset having a degree of similarity to a received input dataset that exceeds a similarity threshold, determining, based on a plurality of features of the first available dataset and a plurality of features of the input dataset, a set of recommendations for transforming the input dataset, and transforming a text of the input dataset based on the set of recommendations and to optimize the input dataset for processing by a natural language processing (NLP) algorithm.

Abstract: A mechanism is provided for modifying an existing recipe to meet a set of desired colors for a final food dish. Responsive to receiving a request to modify the existing recipe to meet the set of desired colors, at least one of the set of existing colors to be changed to meet the desired set of colors is identified. An ingredient-action-sequence triplet associated with each at least one existing color to be changed is identified and, from a corpus of ingredient-action-sequence triplets associated with other existing recipes, one or more substitution candidates that can produce the at least one target color are identified. The one or more substitution candidates are ranked based on how each candidate pairs best with other ingredients in the existing recipe. Based on a selection of a substitution candidate from the one or more substitution candidates, the existing recipe is modified with the substitute candidate.

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 method, in a data processing system comprising a processor and a memory, for analyzing domain-specific features, the method comprising receiving a selection of a domain from a client device, ingesting domain data from a data server, extracting domain elements from the domain data that correspond to the selected domain, and retrieving actionable information for the selected domain by using natural language processing and machine learning on the extracted domain elements and determining that the actionable information corresponds to the selected domain, the actionable information comprising operating parameters for the selected domain.

Abstract: Electronic natural language processing in a natural language processing (NLP) system, such as a Question-Answering (QA) system. A receives electronic text input, in question form, and determines a readability level indicator in the question. The readability level indicator includes at least a grammatical error, a slang term, and a misspelling type. The computer determines a readability level for the electronic text input based on the readability level indicator, and retrieves candidate answers based on the readability level.

Abstract: Some embodiments include a method for scheduling data transactions in an electronic data transaction system. In some embodiments, the method can include presenting, by a filtering node, a user interface indicating options for rescheduling a data transaction to a later date; receiving, by the filtering node via the user interface, information indicating certain of the options that were user-selected; filtering, by the filtering node, the information to determine the user-selected options for rescheduling the data transaction to the later date; storing, in a transaction database, the user-selected options and the later date; identifying, by the filtering node on the later date, the data transaction in the transaction database; and processing, by the filtering node, the data transaction.

Abstract: A computer-implemented method according to one embodiment includes identifying an entity to be filled in within an image, determining a three-dimensional (3D) model for the entity, and filling in the entity within the image, utilizing the 3D model.

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: A computer-implemented method according to one embodiment includes identifying an entity to be filled in within an image, determining a three-dimensional (3D) model for the entity, and filling in the entity within the image, utilizing the 3D model.

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 method, system and computer-usable medium for utilizing personalized audio selection to facilitate achieving a target state comprising: identifying a target state for a user; identifying a set of audio selections for the user to achieve the target state; monitoring reactions by the user to the set of audio selections to determine an assessment; and responsive to determining when the assessment is below a desired level, adjusting the set of audio selections.