A computer-implemented method includes tracking, by a computer device, movements of a user viewing a dashboard containing visualizations. The method also includes generating, by the computer device, heatmaps having hotspots onto the dashboards in view of the tracked movements of the user. Additionally, the method includes generating, by the computer device, bounding boxes around the hotspots. Further, the method includes mapping, by the computer device, the bounding boxes to the visualizations. The method also includes creating, by the computing device, a tree diagram listing the hotspots which correspond to the bounding boxes. Additionally, the method includes generating automatically, by the computing device, a story or exploration from the tree diagram.

A computer-implemented method includes: receiving, by a computing device, text extracted from a webpage in a browser and a Uniform Resource Locator (URL) of a linked webpage associated with the text; generating, by the computing device, questions based on the text; retrieving, by the computing device, content of the linked webpage using the URL; generating, by the computing device, answers to the questions using the retrieved content; and returning, by the computing device, the questions and the answers to the browser such that the browser displays the questions and the answers in the webpage.

A request to resolve a name of a domain of an identifier of web content is received. It is automatically determined that the name of the domain is to be resolved using a blockchain. A request is sent to a smart contract of the blockchain to obtain one or more resolution records for the domain. The one or more resolution records of the domain are received. The received one or more resolution records are utilized to resolve the name of the domain.

A media content item recommendation system recommends media content items based on one or more attributes of a seed playlist. The recommended media content items can be determined from a plurality of existing playlists that have been created over a period of time. Such existing playlists can be selected based on similarity to the seed playlist.

Provided is a method including obtaining a corpus and an associated set of domain indicators. The method includes learning a set of vectors in an embedding space based on n-grams of the corpus. The method includes updating ontology graphs comprising a set of vertices and edges associating the set of vertices with each other. The method also includes determining a vector cluster using hierarchical clustering based on distances of the set of vectors with respect to each other in the embedding space and determining a hierarchy of the ontology graphs based on a set of domain indicators of a respective set of vertices corresponding to vectors of the vector cluster. The method also includes updating an index based on the ontology graphs.

Embodiments of the present disclosure provide methods, apparatus, systems, computer program products for transferring a performance of a procedure found in technical documentation for an item via an interactive electronic technical manual system (IETM) configured to provide electronic and credentialed access to the technical documentation. In one embodiment, a method is provided comprising: providing the steps of the procedure in an order in which the steps are to be carried out; and while a user is participating in the performance of the procedure: causing a particular step that is being carried out to be highlighted; receiving input of a selection of a transfer mechanism and in response: causing an indication to be displayed between the particular step and a next step to be carried out identifying where the performance has been suspended; providing a transfer window displaying transfer information; and recording the transfer information and an identifier for the indication.

A computing device receives from a user a partial natural language input related to a data source. The computing device receives an additional keystroke corresponding to the partial natural language input. The partial natural language input and the additional keystroke comprise a character string. In response to the additional keystroke, the computing device generates one or more interpretations corresponding to entities in the data source. The computing device displays the interpretations. In some implementation, the character string comprises a sequence of terms, and the device displays the interpretations in a dropdown menu adjacent to the most recently entered term in the sequence. In some implementations, the dropdown menu includes a plurality of rows, each row displaying a respective data value and a respective data field corresponding to the respective data value. Some implementations display a statistical distribution of data values for a data field (displayed adjacent to the first interpretation).

An approach for a non-factoid question answering framework across tasks and domains may be provided. The approach may include training a multi-task joint learning model in a general domain. The approach may also include initializing the multi-task joint learning model in a specific target domain. The approach may include tuning the joint learning model in the target domain. The approach may include determining which task of the multiple tasks is more difficult for the multi-task joint learning model to learn. The approach may also include dynamically adjusting the weights of the multi-task joint learning model, allowing the model to concentrate on learning the more difficult learning task.

A third-party service may be used to assist entities in responding to requests of users by determining a suggested response to a received communication. The third party service may receive a request from a first entity, such as via an application programming interface request, that includes a message in a conversation. A conversation feature vector may be computed by processing the message with a first neural network. A suggested respond to the message may be determined by processing the conversation feature vector with a second neural network. The third-party service may then return the suggested response for use in the conversation. The third-party service may similarly be used to assist other entities in responding to requests of users.

Systems and methods for human-machine interaction using a conversation system.