Methods and systems for presenting time series for analysis. A method may receive a first input defining a metric that indicates a relationship between a first and a second time series that are each associated with at least a first data object of a plurality of data objects, generate a first plot depicting the metric as determined from the first and the second time series, receive, via the user interface, a second input of a selection of a second data object of the plurality of data objects, determine, via an ontology, a relationship of the second data object with a third and a fourth time series that, respectively, are associated with series types that match series types associated with the first and the second time series, and generate and display, in the user interface, a second plot depicting the metric as determined from the third and the fourth time series.

A service identifies a level of specificity of one or more identified entities in a user input comprising a query, within one of multiple levels of a hierarchy of a hierarchical coding system. Responsive to determining that additional levels of specificity beyond the identified level of specificity are recommended to return a minimum answer set to the query, the service returns one or more answers requesting one or more additional inputs refining the query based on one or more values identified in a next level. Responsive to determining that no additional levels of specificity beyond the identified level of specificity are recommended to return the minimum answer set to the query, the service returns an answer set comprising a selection of information for the current level of specificity from an ingested corpus of knowledge mapped to the hierarchical coding system.

The embodiment of the present disclosure provides a question-and-answer processing method, including: acquiring a to-be-answered question; determining standard questions meeting a preset condition as a plurality of candidate standard questions, from a plurality of preset standard questions, according to a text similarity with the to-be-answered question, based on a text statistical algorithm; determining, a candidate standard question with the highest semantic similarity with the to-be-answered question as a matching standard question, from the plurality of candidate standard questions, based on a deep text matching algorithm; and determining an answer to the to-be-answered question at least according to the matching standard question. The embodiment of the present disclosure also provides an electronic device and a computer readable medium.

This disclosure enables various technologies that can (1) learn new synonyms for a given concept without manual curation techniques, (2) relate (e.g., map) some, many, most, or all raw named entity recognition outputs (e.g., “United States”, “United States of America”) to ontological concepts (e.g., ISO-3166 country code: “USA”), (3) account for false positives from a prior named entity recognition process, or (4) aggregate some, many, most, or all named entity recognition results from machine learning or rules based approaches to provide a best of breed hybrid approach (e.g., synergistic effect).

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training a deep neural network. One of the methods includes generating a plurality of feature vectors that each model a different portion of an audio waveform, generating a first posterior probability vector for a first feature vector using a first neural network, determining whether one of the scores in the first posterior probability vector satisfies a first threshold value, generating a second posterior probability vector for each subsequent feature vector using a second neural network, wherein the second neural network is trained to identify the same key words and key phrases and includes more inner layer nodes than the first neural network, and determining whether one of the scores in the second posterior probability vector satisfies a second threshold value.

The present disclosure describes methods and systems to predict predicate metadata parameters in knowledge graphs via neural networks. The method includes receiving a knowledge graph based on a knowledge base including a graph-based dataset. The knowledge graph includes a predicate between two nodes and a set of predicate metadata. The method also includes determining a positive structural score, adjusting each positive structural score based on each corresponding significance parameter, generating a synthetic negative graph-based dataset, determining a negative structural score for each synthetic negative triple of the synthetic negative graph-based dataset, adjusting each negative structural score based on each corresponding significance parameter, determining a significance loss value based on the adjusted positive structural scores and the adjusted negative structural scores, and determining a likelihood score of a link between a third node and a fourth node in the knowledge graph based on the significance loss value.

One embodiment provides a method that includes determining candidate ontologies for alignment from multiple available knowledge bases. An initial target ontology is selected from the candidate ontologies and correcting the initial selected ontology with received refinement input. Concepts in the selected initial ontology are aligned with concepts of the target ontology using a deep learning hierarchical classification with received review input. A user is assisted to build, change and grow the selected initial ontology exploiting both the target ontology and new facts extracted from unstructured data.

Embodiments of the present invention provide a means for validating electronic forms using one or more semantic databases. The invention includes processing an electronic form into individual elements and generating entities for the individual elements. The closest matching ontology is found for each entity and the pairings are grouped into a general formal ontology tree. The entities in the general formal ontology tree are traversed using generated rules. This analysis yields validation results that are combined with the original form to create an annotated form.

The present disclosure relates to methods and systems for querying data in a data repository. According to a first aspect, this disclosure describes a method of querying a database, comprising: receiving, at a computing device, a plurality of keywords; determining, by the computer device, a plurality of datasets relating to the keywords; identifying, by the computer device, metadata for the plurality of datasets indicating a relationship between the datasets by examining an ontology associated with the datasets; providing, by the computer device, one or more suggested database queries in natural language form, the one or more suggested database queries constructed based on the plurality of keywords and the metadata; receiving, by the computing device, a selection of the one or more suggested database queries; and constructing, by the computer device, an object view for the plurality of datasets based on the selected query and the metadata.

Examples of the present disclosure describe systems and methods for ontology-based graph query optimization. In an example, ontology data relating to a graph or isolated collection may be collected. The ontology data may comprise uniqueness and topology information and may be used to reformulate a query in order to yield a query that is more performant than the original query when retrieving target information from a graph. In an example, reformulating a query may comprise reordering one or more parameters of the query relating to resources, relationships, and/or properties based on uniqueness information. In another example, the query may be reformulated by modifying the resource type to which the query is anchored based on the topology information. The reformulated query may then be executed to identify target information in the isolated collection, thereby identifying the same target information as the original query, but in a manner that is more performant.