Abstract: Identifying an indistinct entity within an image can include generating by an image filter multiple gradients, each of which corresponds to one of a plurality of pixels of an image captured by an imager. The image can be searched for a likely repeating pattern. Responsive to detecting, based on the multiple gradients, a likely repeating pattern within the image, data structures can be generated, the data structures comprising a set of probabilistically weighted feature vectors corresponding to the likely repeating pattern. A machine learning model can classify each of the set of probabilistically weighted feature vectors. An identity of the likely repeating pattern can be output, the identity based on the machine learning model classifications of the probabilistically weighted feature vectors.

Abstract: An approach for assessing terms and conditions (TnC)s of a legal agreement is provided. A block of text, which contains a TnC of the set of TnC, in the legal agreement is identified using a cognitive system. A standardized significance value is assigned to the TnC by the cognitive system by applying the TnC to a TnC model containing corresponding industry TnCs from industry standard documents. A block currency that indicates a significance of an impact of the TnC to a contract party is computed for the TnC by the cognitive system. Based on the standardized significance value and the block currency, a personal impact of the TnC to the contract party is assessed by the cognitive system. The contract party is alerted to the TnC and the personal impact corresponding to the TnC.

Abstract: A computer-implemented method for providing a framework to identify questions and answers dynamically from a dataset based on previous learning and an evaluation score of a user. The method includes creating a library of potential questions and answers from the dataset based on the previous learning and evaluation score of the user, and generating a set of personalized questions, for the user, related to the dataset by utilizing sentence-based machine translation (SBMT) and natural language processing (NLP) tools. The method further includes identifying a plurality of answers for the set of personalized questions for the user, based on collective information available in the dataset, and providing, to the user, the plurality of answers for the set of personalized questions for verification and evaluation.

Abstract: Generating a work-flow diagram from technology specific literature includes using an analysis of technology specific literature which includes using natural language processing (NLP), to derive semantics for a plurality of components defined in the technology specific literature. The plurality of components are associated to symbols in a component symbol database. The associated symbols are assigned to each of the plurality of components, respectively. A relationship is determined for each of the plurality of components. Nodes are assigned, and vectors are assigned when applicable, for each of the symbols. A work-flow diagram is generated for the technology specific literature using the assigned associated symbols for each of the plurality of components and the nodes and the vectors for each of the symbols.

Abstract: Systems and methods for monitoring of utility assets using crowd-sourced digital image data are disclosed. In embodiments, a method includes: monitoring, by a computing device, incoming real-time utility data; determining, by the computing device, that a triggering event has occurred based on the monitoring; sending, by the computing device, an event message to one or more agent devices comprising a request for digital image collection at a location based on the triggering event, the event message including event information, wherein the one or more agent devices are associated with respective agents in a crowd-sourcing network; receiving, by the computing device, event data from the one or more agent devices, the event data including one or more digital images; and processing, by the computing device, the one or more digital images to determine next steps with respect to the triggering event.

Abstract: Generating a work-flow diagram from technology specific literature includes using an analysis of technology specific literature which includes using natural language processing (NLP), to derive semantics for a plurality of components defined in the technology specific literature. The plurality of components are associated to symbols in a component symbol database. The associated symbols are assigned to each of the plurality of components, respectively. A relationship is determined for each of the plurality of components. Nodes are assigned, and vectors are assigned when applicable, for each of the symbols. A work-flow diagram is generated for the technology specific literature using the assigned associated symbols for each of the plurality of components and the nodes and the vectors for each of the symbols.

Abstract: Systems and methods for monitoring of utility assets using crowd-sourced digital image data are disclosed. In embodiments, a method includes: monitoring, by a computing device, incoming real-time utility data; determining, by the computing device, that a triggering event has occurred based on the monitoring; sending, by the computing device, an event message to one or more agent devices comprising a request for digital image collection at a location based on the triggering event, the event message including event information, wherein the one or more agent devices are associated with respective agents in a crowd-sourcing network; receiving, by the computing device, event data from the one or more agent devices, the event data including one or more digital images; and processing, by the computing device, the one or more digital images to determine next steps with respect to the triggering event.