Systems and methods are described herein for interpreting natural language search queries that account for contextual relevance of words of the search query that would ordinarily not be processed, including, for example, processing each word of the query. Each term or phrase is associated with a respective part of speech, and a frequency of occurrence of a combination of adjacent terms or phrases public domain is determined. A relevance of each term is then determined based on its respective type of term and frequency of occurrence in the public domain. The natural language search query is then interpreted based on the importance or relevance of each term.

Systems are configured for processing user queries to generate search results that are contextually relevant for the user based on customer values associated with a corresponding customer schema associated with the user and that are indexed in a customer value index. When search queries are received, they are processed to identify customer values associated with the user context and to perform an initial search query based on the initial search query terms. The systems also generate additional altered search queries to perform contemporaneously, based on the initial search terms and restructured/reformatted based on the customer values. Resulting supplement search results are obtained for the additional altered search queries, which are merged with the initial search results. The merged results are then ranked and provided to the user. These systems facilitate obtaining search results that are more relevant than results obtained by conventional systems.

Provided is a system and method for detecting a SQL command from a natural language input using neural networks which works even when the SQL command has not been seen before by the neural networks. In one example, the method may include storing a candidate set comprising structured query language (SQL) templates paired with respective text values, reducing, via a first predictive network, the candidate set into a subset of candidates based on a natural language input and the text values included in the candidate set, selecting, via a second predictive network, an SQL template from among the subset of candidates based on the natural language input and text values included in the subset of candidates, and determining a SQL command that corresponds to the natural language input based on the selected SQL template and content from the natural language input.

A computing device receives user input to specify a natural language command directed to a data source. In accordance with the user input, the device forms an intermediate expression according to a context-free grammar and a semantic model of data fields in the data source. The natural language command includes (i) a first term that specifies an aggregation type in a first aggregation, (ii) a second term that specifies a data field, in the semantic model, to be aggregated for the first aggregation, and (iii) terms that specify data fields, in the semantic model, to determine grouping for the first aggregation. The device translates the intermediate expression into database queries, executes the database queries to retrieve one or more data sets from the data source, aggregated according to the first aggregation, then generates and displays a data visualization of the retrieved data sets.

Embodiments may provide a cache for query results that can adapt the cache-space utilization to the popularity of the various topics represented in the query stream. For example, a method for query processing may perform receiving a plurality of queries for data and requesting data responsive to at least one query from a data cache comprising a temporal cache, wherein the temporal cache is configured to store data based on a topic associated with the data and is configured to retrieve data based on a topic, and wherein the data cache is configured to retrieve data responsive to at least one query from the computer system.

Methods, systems and computer readable media are provided for automatically creating a semantic model of a relational database for processing natural language queries. A computing device automatically extracts relational database metadata. The computing device prompts a user to enter textual labels for columns of the extracted metadata. The computing device automatically generates a schema annotation file based upon the relational database metadata and the textual labels for the columns. A natural language query is processed for the relational database using the schema annotation file.

A method includes receiving audio data corresponding to an utterance spoken by the user and captured by the user device. The utterance includes a command for a digital assistant to perform an operation. The method also includes determining, using a hotphrase detector configured to detect each trigger word in a set of trigger words associated with a hotphrase, whether any of the trigger words in the set of trigger words are detected in the audio data during the corresponding fixed-duration time window. The method also includes determining identifying, in the audio corresponding to the utterance, the hotphrase when each other trigger word in the set of trigger words was also detected in the audio data. The method also includes triggering an automated speech recognizer to perform speech recognition on the audio data when the hotphrase is identified in the audio data corresponding to the utterance.

Examples of the present disclosure describe systems and methods for generating multiple semantic hypotheses for search query intent understanding. In aspects, a search query may be received by a query analysis component associated with a search system. The query analysis component may be used to evaluate the search query for ambiguity in the domain, intent, and/or slot(s) of the search query. A set of hypotheses representing for one or more combinations of the domain, intent, and/or slot(s) of the search query may be generated. The set of hypotheses may be scored and/or ranked. Based on the scores/ranks, one or more of the hypotheses in the set of hypotheses may be provided to a user and/or one or more processing components accessible to the search system.

An electronic device that includes one or more input sensor devices, one or more output devices, one or more computer processors and a memory containing computer program code that, when executed by operation of the one or more computer processors, performs an operation. The operation includes collecting information, using one or more input sensor devices, about the plurality of users within a physical environment. The operation includes analyzing the collected information to determine a present situational context for the plurality of users that are currently present within the physical environment. An action to perform is determined based on the determined present situational context. The determined action is executed using the one or more output devices.

Methods and systems for translating a natural language user query into a graph database query are described. In some instances, the methods may comprise receiving a first input from a user comprising a natural language query regarding data in a graph database; processing the natural language query using a named entity recognition (NER) machine learning model to extract named entities from the natural language query and tag them according to an entity type; processing the tagged named entities using a semantic similarity algorithm to identify corresponding nodes and edges, and their associated properties, in the graph database; processing the natural language query using an intent classification machine learning model to determine a user intent for the natural language query; and applying a user intent-based template to the identified nodes and edges to formulate a graph database query that corresponds to the natural language query.