In one embodiment, a method includes receiving at a head-mounted device a speech input from a user and a visual input captured by cameras of the head-mounted device, wherein the visual input comprises subjects and attributes associated with the subjects, and wherein the speech input comprises a co-reference to one or more of the subjects, resolving entities corresponding to the subjects associated with the co-reference based on the attributes and the co-reference, and presenting a communication content responsive to the speech input and the visual input at the head-mounted device, wherein the communication content comprises information associated with executing results of tasks corresponding to the resolved entities.

An electronic devices comprises a display, a memory and a processor. The processor assigns priorities to a plurality of context information received in relation to a user, respectively, and stores the plurality of context information with the assigned priorities in the memory, modifies at least one item included in a selected recipe on the basis of the priorities assigned to the plurality of context information when the recipe is selected, and controls the display to display a customized recipe including the modified item.

A cognitive system (artificial intelligence) is optimized by assessing different data augmentation methods used to augment training data, and then training the system using a training set augmented by the best identified method. The augmentation methods are assessed by applying them to the same set of training data to generate different augmented training data sets. Respective instances of the cognitive system are trained with the augmented sets, and each instance is subjected to validation testing to assess its goodness. The validation testing can include multiple validation tests leading to component scores, and a combined validation score is computed as a weighted average of the component scores using respective weights for each validation test. The augmentation method corresponding to the instance having the highest combined validation score is selected as the optimum augmentation method for the particular cognitive system at hand.

A determination device according to the present application has an acquisition unit, a categorization unit, and a determination unit. The acquisition unit acquires the search queries, which have been input by a plurality of input customers who have input a reference query. The categorization unit categorizes the search queries, which have been input in a predetermined period among search queries, into a plurality of categories. The determination unit determines whether a categorization result by the categorization unit satisfies a predetermined determination condition or not.

Methods for providing enhanced services to users participating in communication sessions (CS), via a virtual assistant, are disclosed. One method receives content that is exchanged by users participating in the CS. The content includes natural language expressions that encode a conversation carried out by users. The method determines content features based on natural language models. The content features indicate intended semantics of the natural language expressions. The method determines a relevance of the content and identifies portions of the content that are likely relevant to the user. Determining the relevance is based on the content features, a context of the CS, a user-interest model, and a content-relevance model of the natural language models. Identifying the likely relevant content is based on the determined relevance of the content and a relevance threshold. A summary of the CS is automatically generated from summarized versions of the likely relevant portions of the content.

A detection is made that a user of a platform has provided first question text associated with a question via a user interface (UI). A first answer field format including a first data type associated with one or more first key terms of the question text is identified. The UI is updated to include first answer field options related to the first question text based on at least the first data type of the identified answer field format. In response to a detection that the user has provided second question text associated with the question via the UI, a second answer field format including a second data type associated with second key terms and at least one of the first key terms is identified. The UI is updated to include second answer field options related to the first question text and the second question text.

A quality assessment system models product or service quality based on contextual relevance. A neural network generates a contextual relevance model that differentiates descriptive characteristics based on a modeled relevance of each descriptive characteristic to the product or service. The system filters reviews based on the contextual relevance model to retain filtered reviews that reference any of the first set of descriptive characteristics. The system generates theme clusters with an encoder. Each theme cluster groups a different subset of the filtered reviews based on an amount of semantic similarity between the different subset of reviews and the theme cluster. The system presents an interface with a first visualization and a second visualization. The first visualization graphically represents a sentiment expressed in reviews grouped to the first theme cluster, and the second visualization graphically represents a sentiment expressed in reviews groups to the second theme cluster.

Systems and methods for a relationship-based search in a computing environment are provided. An example method includes providing a graph database. The graph database includes nodes representing workloads of the computing environment and edges representing relationships between the nodes. The method also includes enriching the graph database by associating the nodes with metadata associated with the nodes and the relationships. The method also includes receiving a user query including data associated with at least one of the metadata and the relationships. The method also includes determining, based on the user query, a subset of the nodes in the graph database and a subset of relationships between the nodes in the subset of the nodes. The method also includes displaying, via a graphical user interface, a graphical representation of the subset of the nodes and relationships between the nodes in the subset of the nodes.

A candidate document is received, for example, by a document filter. A determination is made based on the content of the candidate document, whether the candidate document is relevant to a document corpus. A determination is made based on the content of the candidate document, whether the candidate document is novel with respect to the document corpus. In response to determining that the candidate document is relevant to the document corpus and novel with respect to the document corpus, the candidate document is added to the document corpus to make at least a portion of the content of the candidate document available for a response to a search query.

An efficient blend of home/personal and work/productivity related content based on a user's intent is provided, wherein the user's intent can be determined based on context information, learned user interaction patterns, and historical work and home characteristics and patterns. The system is individualized to the user and operative to generate a user experience that provides a blend of relevant home/personal and work/productivity related information to the user based on the user's current work and life characteristics. From a determined user intent, various aspects provide personalized computing experiences tailored to the user and, in some examples, incorporation of the user's patterns into an efficient blend of personal and productivity workflows. In further examples, the blend of home/personal and work/productivity related content and workflows are selectively displayed to the user such that screen resources are efficiently and advantageously allocated based on a determined relevance to the user's current work and life characteristics.