Abstract: Chatbot conversation management includes a generic model associated with a first property associated with a chatbot manager. The generic model is generated based on machine learning. A refined model that is associated with the first property is generated based on the generic model and a first plurality of phrases. A first conversation is held between a chatbot and an end user. A determination is made regarding storage of a value of a first property for the end user that is obtained via the chatbot. The refined model is used to dynamically ask questions to the end user to determine a value of the first property for the end user.

Abstract: The present disclosure is related to systems and/or methods for energy storage in desert environments. Various embodiments described herein include a system for subterranean energy storage. The system can comprise a subterranean flexible storage vessel coupled to a heat exchanger. The heat exchanger can be configured to supply a cooled compressed gas stream to the subterranean flexible storage vessel. Further, the subterranean flexible storage vessel can be at least partially surrounded by sand. Additionally, the system can comprise a turbine generator coupled to the subterranean flexible storage vessel. The subterranean flexible storage vessel can be configured to supply a pressurized gas stream that is heated by the sand to the turbine generator.

Abstract: Methods and systems for similarity-based value-to-column classification are disclosed. A method includes: receiving, by a computing device, a natural language search query; determining, by the computing device, a filtering phrase in the natural language search query using a natural language understanding model; encoding, by the computing device, the filtering phrase; retrieving, by the computing device, a plurality of encoded columns; for each of the plurality of encoded columns, the computing device determining a similarity score based on a similarity between the encoded filtering phrase and the encoded column; and outputting, by the computing device, a column corresponding to an encoded column of the plurality of encoded columns having a highest similarity score.

Abstract: A computer-implemented method, system and computer program product for providing predictions tailored for a specific domain. Each field within a set of datasets is classified with a concept defined in a domain specific ontology. After receiving a target field and identifying a target concept tagged to the target field, concepts that have an influential impact directly to the target concept or indirectly to a concept tagged to a field associated with the target field are identified. Fields are then identified as candidates for predictors from the identified concepts using a semantic relationship and a numeric association combined approach. An influential confidence score and a numeric analytics score are then calculated for each of these candidates upon which a final confidence score is computed. The identified candidates are ranked based on the final confidence scores, and the top ranked candidates for predictors are selected to build a statistical model.

Abstract: Guided exploration of data is provided. A semantic graph corresponding to a dataset is generated using identified relations among columns of the dataset that are identified based on mapping the columns to main concepts in a generic ontology. A subgraph of the semantic graph is formed based on identification of nodes corresponding to relevant central concepts within the semantic graph using graph centrality metrics. A plurality of paths is identified in the subgraph using a bi-directional multiple hop search from the nodes corresponding to the relevant central concepts in the subgraph. A relevance score is assigned to each path in the plurality of paths using a graph-theoretic metric and the graph centrality metrics. A set of natural language questions based on relevant central concepts and concept relations corresponding to nodes in each respective path with an assigned relevance score greater than a minimum threshold score is output to the user.

Abstract: An approach is provided in which the approach performs object detection on an image to identify a set of edges and a set of tables from a set of objects corresponding to a set of data. The approach determines a set of associations between the set of tables and the set of edges in response to adjusting a set of bounding boxes corresponding to the set of edges. The approach generates a data module based on the set of associations, the set of tables, and the set of edges, and utilizes the data module to access the set of data.

Abstract: A computer-implemented method for joining data sets with mismatched geographic location naming conventions is provided. The method includes identifying, by the computer, a first dataset and a second dataset as join candidates. The method also includes joining, by the computer, the first dataset and the second dataset when, each row of the first user dataset is associated with a single geographic identifier using a geographic knowledge dataset that includes a geographic name lookup table and each row of the second user dataset is associated with a single geographic identifier using the geographic knowledge dataset, wherein the geographic name lookup table includes a plurality of alias names for each of a plurality of unique geographic locations.

Abstract: A big data analytics system includes an event monitoring controller that detects a user targeted event from an initial digital query data flow. An event conversion controller determines at least one contextual element associated with the at least one user targeted event, and automatically converts the at least one contextual element into a search criteria. An external data query builder controller automatically executes an external search query based on the search criteria. A data fusing controller automatically fuses the at least one contextual element generated from the at least one user targeted event, together with external search results generated from the external search query and the initial query data flow to generate a fused data file.

Abstract: Methods and systems for similarity-based value-to-column classification are disclosed. A method includes: receiving, by a computing device, a natural language search query; determining, by the computing device, a filtering phrase in the natural language search query using a natural language understanding model; encoding, by the computing device, the filtering phrase; retrieving, by the computing device, a plurality of encoded columns; for each of the plurality of encoded columns, the computing device determining a similarity score based on a similarity between the encoded filtering phrase and the encoded column; and outputting, by the computing device, a column corresponding to an encoded column of the plurality of encoded columns having a highest similarity score.

Abstract: Provided is a method for extracting features from an image of a dashboard. The method comprises detecting a position of one or more visualizations in an image of a dashboard. Each of the one or more visualizations is classified based on a type of object in the visualization. Features of the visualizations are extracted. The features include data points underlying the visualizations, one or more colors in the image, and text found in the image. An output array is generated based on the extracted features.

Abstract: Guided exploration of data is provided. A semantic graph corresponding to a dataset is generated using identified relations among columns of the dataset that are identified based on mapping the columns to main concepts in a generic ontology. A subgraph of the semantic graph is formed based on identification of nodes corresponding to relevant central concepts within the semantic graph using graph centrality metrics. A plurality of paths is identified in the subgraph using a bi-directional multiple hop search from the nodes corresponding to the relevant central concepts in the subgraph. A relevance score is assigned to each path in the plurality of paths using a graph-theoretic metric and the graph centrality metrics. A set of natural language questions based on relevant central concepts and concept relations corresponding to nodes in each respective path with an assigned relevance score greater than a minimum threshold score is output to the user.

Abstract: An approach is provided in which the approach performs object detection on an image to identify a set of edges and a set of tables from a set of objects corresponding to a set of data. The approach determines a set of associations between the set of tables and the set of edges in response to adjusting a set of bounding boxes corresponding to the set of edges. The approach generates a data module based on the set of associations, the set of tables, and the set of edges, and utilizes the data module to access the set of data.

Abstract: A computer-implemented method, system and computer program product for recommending a template or a dataset. A descriptor (input descriptor) of the input, corresponding to a dataset or a dashboard template, is extracted or fetched. The input descriptor may be the descriptor of the dataset which includes topics and concept combinations. Alternatively, the input descriptor may be the descriptor of the dashboard template which includes topics, concept combinations and column-to-visualization mappings. Scores are then generated for the candidate targets, corresponding to dashboard templates or datasets, based on one or more of the following: matching topics in the input descriptor with topics in the candidate target descriptors, matching concept combinations in the input descriptor with concept combinations in the candidate target descriptors, and determining compatibility of the datasets with the dashboard templates.

Abstract: A computer-implemented method, system and computer program product for creating a descriptor for a dashboard template. The column-to-visualization mappings are extracted from a dashboard of a created or modified dashboard (or a created or modified dashboard template). Furthermore, the concept combinations from each visualization of the dashboard are extracted. Additionally, topics from the dashboard are extracted. The concept combinations, topics and column-to-visualization mappings are aggregated into a dashboard template descriptor. The dashboard template descriptor is then stored. In this manner, the dashboard template descriptor captures how concept combinations are used in the visualizations of the dashboard as well as how high-level concepts (topics) are incorporated in the dashboard. Furthermore, the dashboard template descriptor captures how the concepts of the columns of a dataset are mapped to the visualizations of the dashboard.

Abstract: A computer-implemented method for joining data sets with mismatched geographic location naming conventions is provided. The method includes identifying, by the computer, a first dataset and a second dataset as join candidates. The method also includes joining, by the computer, the first dataset and the second dataset when, each row of the first user dataset is associated with a single geographic identifier using a geographic knowledge dataset that includes a geographic name lookup table and each row of the second user dataset is associated with a single geographic identifier using the geographic knowledge dataset, wherein the geographic name lookup table includes a plurality of alias names for each of a plurality of unique geographic locations.

Abstract: A computer-implemented method, system and computer program product for providing predictions tailored for a specific domain. Each field within a set of datasets is classified with a concept defined in a domain specific ontology. After receiving a target field and identifying a target concept tagged to the target field, concepts that have an influential impact directly to the target concept or indirectly to a concept tagged to a field associated with the target field are identified. Fields are then identified as candidates for predictors from the identified concepts using a semantic relationship and a numeric association combined approach. An influential confidence score and a numeric analytics score are then calculated for each of these candidates upon which a final confidence score is computed. The identified candidates are ranked based on the final confidence scores, and the top ranked candidates for predictors are selected to build a statistical model.

Abstract: A big data analytics system includes an event monitoring controller that detects a user targeted event from an initial digital query data flow. An event conversion controller determines at least one contextual element associated with the at least one user targeted event, and automatically converts the at least one contextual element into a search criteria. An external data query builder controller automatically executes an external search query based on the search criteria. A data fusing controller automatically fuses the at least one contextual element generated from the at least one user targeted event, together with external search results generated from the external search query and the initial query data flow to generate a fused data file.

Abstract: A big data analytics system includes an event monitoring controller that detects a user targeted event from an initial digital query data flow. An event conversion controller determines at least one contextual element associated with the at least one user targeted event, and automatically converts the at least one contextual element into a search criteria. An external data query builder controller automatically executes an external search query based on the search criteria. A data fusing controller automatically fuses the at least one contextual element generated from the at least one user targeted event, together with external search results generated from the external search query and the initial query data flow to generate a fused data file.

Abstract: Techniques are described for selecting, based on a data visualization intent specification and a defined set of data fields associated with a set of data, two or more Meta templates that meet the data visualization intent specification and that support the set of data fields, for determining chart parts that can be used within the selected Meta templates to form chart templates and for determining, based on a set of combination rules and the specification, the chart templates that meet the data visualization intent specification.

Abstract: A big data analytics system includes an event monitoring controller that detects a user targeted event from an initial digital query data flow. An event conversion controller determines at least one contextual element associated with the at least one user targeted event, and automatically converts the at least one contextual element into a search criteria. An external data query builder controller automatically executes an external search query based on the search criteria. A data fusing controller automatically fuses the at least one contextual element generated from the at least one user targeted event, together with external search results generated from the external search query and the initial query data flow to generate a fused data file.