Abstract: A method, computer system, and a computer program product for providing an automated graphical and textual review summary of user submissions has been provided. In one embodiment this comprises obtaining a plurality of user submissions relating to a particular subject matter and having information relating to this subject matter. Extracting at least one feature and feature review relating to each of the user submissions and generating statistical insights relating to these features and features reviews and other relevant information relating. A summary review is then generated relating to these user submissions. The summary review includes information about each feature, feature review and statistical insights.

Abstract: Provided are techniques for data analysis and rule generation for providing a recommendation. Current features are identified from data in a corpus. In response to receiving an indication that the data has changed, a new feature is identified. A feature set is created by identifying one or more related features of the current features. A feature worthiness score for the feature set is generated. In response to the feature worthiness score exceeding a threshold, the feature set is input to a model. One or more rules from the model are received, where each of the one or more rules includes the one or more related features, the new feature, and a recommendation. In response to receiving a set of values for the one or more related features and the new feature, a rule of the one or more rules is applied to provide the recommendation for that set of values.

Abstract: A method, computer system, and a computer program product for persona-based navigation is provided. The present invention may include creating a persona. The present invention may include developing a routing system. The present invention may include enabling a user with at least one route option based on the created persona. The present invention may include displaying a selected route.

Abstract: Provided are techniques for data analysis and rule generation for providing a recommendation. Current features are identified from data in a corpus. In response to receiving an indication that the data has changed, a new feature is identified. A feature set is created by identifying one or more related features of the current features. A feature worthiness score for the feature set is generated. In response to the feature worthiness score exceeding a threshold, the feature set is input to a model. One or more rules from the model are received, where each of the one or more rules includes the one or more related features, the new feature, and a recommendation. In response to receiving a set of values for the one or more related features and the new feature, a rule of the one or more rules is applied to provide the recommendation for that set of values.

Abstract: A computer implemented method, computer program product, and computer system technique for optimizing automated teller machine (ATM) replenishment schedules to prevent an ATM from having insufficient product and also to prevent the inefficient use of product. The technique involves retrieving unstructured data from the users of the ATM. Then the technique analyzes the unstructured data using a natural language processing (NLP) model. The technique then inputs the results of the natural language processing deep neural network (DNN) trained with structured data. The result of the NLP and DNN analysis is a user persona. The user persona is used to generate the optimized ATM replenishment schedule.

Abstract: A computer implemented method, computer program product, and computer system technique for optimizing automated teller machine (ATM) replenishment schedules to prevent an ATM from having insufficient product and also to prevent the inefficient use of product. The technique involves retrieving unstructured data from the users of the ATM. Then the technique analyzes the unstructured data using a natural language processing (NLP) model. The technique then inputs the results of the natural language processing deep neural network (DNN) trained with structured data. The result of the NLP and DNN analysis is a user persona. The user persona is used to generate the optimized ATM replenishment schedule.

Abstract: Provided are techniques for data analysis and rule generation for providing a recommendation. Current features are identified from data in a corpus. In response to receiving an indication that the data has changed, a new feature is identified. A feature set is created by identifying one or more related features of the current features. A feature worthiness score for the feature set is generated. In response to the feature worthiness score exceeding a threshold, the feature set is input to a model. One or more rules from the model are received, where each of the one or more rules includes the one or more related features, the new feature, and a recommendation. In response to receiving a set of values for the one or more related features and the new feature, a rule of the one or more rules is applied to provide the recommendation for that set of values.

Abstract: An enhanced text summarizer is provided. A processor receives a request to generate a summarization of a text. A processor determines at least one domain associated with the text. A processor extracts one or more features from the text. A processor determines one or more relevance scores for the one or more features based on the determined at least one domain associated with the text. A processor determines a feature-based ranking for one or more sentences of the text. A processor determines an extractive-based ranking for one or more sentences of the text. A processor merges at least one sentence of the feature-based ranking and at least one sentence of the extractive-based ranking of the text. A processor generates the summarization of the text based on the merged the at least one sentence of the feature-based ranking and the at least one sentence of the extractive-based ranking of the text.

Abstract: An enhanced text summarizer is provided. A processor receives a request to generate a summarization of a text. A processor determines at least one domain associated with the text. A processor extracts one or more features from the text. A processor determines one or more relevance scores for the one or more features based on the determined at least one domain associated with the text. A processor determines a feature-based ranking for one or more sentences of the text. A processor determines an extractive-based ranking for one or more sentences of the text. A processor merges at least one sentence of the feature-based ranking and at least one sentence of the extractive-based ranking of the text. A processor generates the summarization of the text based on the merged the at least one sentence of the feature-based ranking and the at least one sentence of the extractive-based ranking of the text.

Abstract: A plurality of segments in an e-mail collection by parsing content of e-mails is generated. Corresponding segment signature for each segment is created and a signature index is populated using the generated segment signatures. After receiving a query e-mail, a plurality of query segments in the query e-mail is generated using content of the query e-mail and corresponding query segment signature for each query segment is generated. A query root segment is identified and corresponding query root segment signature is generated. A set of root segment signatures of the signature index is identified and the query root segment signature is compared with each root segment signature from the signature index. A subset of the signature index is identified, using a match between the root segment signature and the query root segment signature. An e-mail thread hierarchy is built using the identified subset of the signature index.

Abstract: Embodiments of the invention are related to a method and system for identifying linked electronic mails by receiving a query from a user, wherein the query comprises at least a segment of an electronic mail; and based on the segment received, rendering to the user at least one of related subsets or a related supersets of electronic mails related to the received segment, wherein the related subsets and related supersets are threads of the segment received and arranged in a hierarchical manner.

Abstract: Embodiments of the invention are related to a method and system for identifying linked electronic mails by receiving a query from a user, wherein the query comprises at least a segment of an electronic mail; and based on the segment received, rendering to the user at least one of related subsets or a related supersets of electronic mails related to the received segment, wherein the related subsets and related supersets are threads of the segment received and arranged in a hierarchical manner.

Abstract: A plurality of segments in an e-mail collection by parsing content of e-mails is generated. Corresponding segment signature for each segment is created and a signature index is populated using the generated segment signatures. After receiving a query e-mail, a plurality of query segments in the query e-mail is generated using content of the query e-mail and corresponding query segment signature for each query segment is generated. A query root segment is identified and corresponding query root segment signature is generated. A set of root segment signatures of the signature index is identified and the query root segment signature is compared with each root segment signature from the signature index. A subset of the signature index is identified, using a match between the root segment signature and the query root segment signature. An e-mail thread hierarchy is built using the identified subset of the signature index.