Abstract: A computing device receives, via a user interface, a drawing input directed to a dataset of time series data. The computing device converts the drawing input into a set of search terms and executes a query against a search index for the dataset using the set of search terms to retrieve a plurality of labeled trend events. Each of the labeled trend events corresponds to a respective portion of a respective line chart of a set of line charts representing the time series data and has a respective chart identifier. The computing device generates a first subset of line charts according to the retrieved plurality of labeled trend events. The computing device displays, on the user interface, one or more line charts of the first subset of line charts.

Abstract: A computing device, in response to a user query regarding a dataset that includes variability, obtains a multimodal data representation of the dataset. The device displays an interactive media playback element in a first region of a user interface. In response to receiving a user input via the interactive media playback element, the device causes playback of the multimodal data representation on the user interface, including presenting audio content describing data in the multimodal representation; and while presenting the audio content, simultaneously presenting visual content via a visualization in a second region of the user interface. The visual content is time-synchronized with the audio content. The device detects a user interaction with the interactive media playback element. The device, in response to detecting the user interaction, modifies a playback portion of the visual content and the audio content that is time-synchronized with the visual content.

Abstract: A computing device performs an automated analysis of a data source and generates one or more first natural language outputs in accordance with the automated analysis. The device displays the first natural language outputs in a graphical user interface and receives user selection of a natural language output of the first natural language outputs. In response to receiving the user selection, the device generates a first data visualization according to the automated analysis, one or more data fields of the data source specified in the natural language output, and/or analytical operations specified in the natural language output. The device displays the first data visualization in the graphical user interface. The device generates one or more second natural language outputs and displays the second natural language outputs in the graphical user interface.

Abstract: Embodiments are directed to intent driven dashboard recommendations. A plurality of collection specifications that declare visualization declarations may be provided such that each collection specification is associated with an author intent. And attributes-of-interest selected from a data source may be provided. A plurality of collections may be generated based on the plurality of collection specifications, the attributes-of-interest, or data from the data source such that each collection may include visualizations that may be based on the visualization declarations. A preference score may be generated for each collection based on the author intent, visualizations in each collection, or the attributes-of-interest. The plurality of collections may be classified based on the preference scores associated with the classified collections such that the classified collections may be displayed based on the preference scores.

Abstract: A method uses natural language processing for visual analysis of a dataset. The method includes receiving a first natural language (NL) input directed to a data source, from a first client. The method also includes parsing the first NL input into tokens based on a grammar and the data source. The method also includes generating and outputting an intermediate NL response, to a second client, based on the tokens and output modality of the second client. In response to receiving a user input to provide missing information: the method also includes generating an input query based on the user input; and querying the data source using the input query, to obtain a result set. The method also includes generating and outputting, to the second client, a first NL output and a snapshot of a data visualization, based on the result set and the output modality of the second client.

Abstract: A computing device receives a natural language input specifying search terms directed to a dataset. The device parses the input into tokens and executes queries against a search index to retrieve a plurality of labeled trend events. Each labeled trend event has a respective chart identifier. The device determines a respective composite score for each labeled trend event and individually assigns each labeled trend event to a respective group. For each group, the device sorts the respective labeled trend events within the respective group according to respective composite scores, determines a respective final score for each group, and ranks the groups according to one or more determined final scores. The device retrieves data corresponding to a first subset of line charts having the respective chart identifiers of the ranked groups, generates the first subset of line charts, and displays one or more line charts of the first subset with annotation.

Abstract: A computing device receives user selection of a data source. In accordance with the user selection, the device generates one or more initial natural language utterances according to metrics of data fields in the data source and/or previous user interaction with the data source. Each of the initial natural language utterances corresponds to a respective suggestion to guide visual analysis of the data source. The device displays the initial utterances in a graphical user interface. The device receives user selection of a first initial utterance of the initial utterances. In response to the user selection, the device generates and displays a first data visualization in accordance with data fields and/or analytical operations specified in the first initial utterance. The device also generates updated natural language utterances in accordance with the first initial utterance and the first data visualization, and displays the updated utterances with the first data visualization.

Abstract: A computing device receives a natural language input specifying search terms directed to a dataset. The device parses the input into tokens and executes queries against a search index to retrieve a plurality of labeled trend events. Each labeled trend event has a respective chart identifier. The device determines a respective composite score for each labeled trend event and individually assigns each labeled trend event to a respective group. For each group, the device sorts the respective labeled trend events within the respective group according to respective composite scores, determines a respective final score for each group, and ranks the groups according to one or more determined final scores. The device retrieves data corresponding to a first subset of line charts having the respective chart identifiers of the ranked groups, generates the first subset of line charts, and displays one or more line charts of the first subset with annotation.

Abstract: System, method and interface for interpreting natural language comparisons during visual analysis are provided. The system includes obtaining a natural language utterance that includes a comparison query and a dataset of attributes and values relevant to interpreting the comparison query. The system also includes interpreting the natural language utterance based on the dataset using multi-step chain-of-thought reasoning prompting to generate a response to the comparison query. The system also includes generating a visualization based on the response and a text summary describing the multi-step chain-of-thought reasoning for the comparison query.

Abstract: A computing device receives a natural language input specifying a first search term and a second search term, directed to a dataset. The device (i) executes, for the first search term, first queries against a search index to retrieve a first set of labeled trend events; and (ii) executes for the second search term, second queries against the search index to retrieve a second set of labeled trend events. Each labeled trend event has a respective chart identifier. The device constructs sequences of labeled trend events based on the retrieved sets of labeled trend events, assigns each sequence into groups according to the respective chart identifier, and ranks the groups. The device retrieves data corresponding to a subset of line charts having the respective chart identifiers of the ranked groups, generates the subset of line charts, and displays one or more line charts of the subset.

Abstract: A method provides visual analysis of datasets. A system receives a natural language search query that is directed to data repositories including data sources and data visualizations. The system parses search tokens to determine if the natural language search query contains analytic intents. The system also determines if the search tokens match fields in one or more data sources, using a semantic search. When (i) the search tokens match fields in the one or more data sources and (ii) the natural language search query contains analytic intents, the system generates and displays visualization responses. When (i) the search tokens do not match fields in the data sources or (ii) the natural language search query does not contain the analytic intents, the system displays pre-authored content from the data visualizations.

Abstract: A computing device receives a natural language command directed to a data source. The device applies one or more respective rules to determine whether the natural language command comprises an ambiguous and/or underspecified request. In accordance with a determination that the natural language command comprises an ambiguous and/or underspecified request, the device infers information to resolve the ambiguous and/or underspecified request according to (i) the one or more respective rules, (ii) metadata for the data source, and (iii) metadata for one or more data fields specified in the natural language command. The device updates a respective intent specification based on the inferred information, retrieving data sets from the data source according to the respective intent specification, and generates and displays a data visualization based on the retrieved data sets.

Abstract: A computing device parses a user-specified natural language command to form a first expression. The computing device determines that the first expression is ambiguous or underspecified. The computing device, in accordance with the determination, infers first information using one or more inferencing rules, where at least one of the inferencing rules is based on an attribute of data fields and/or data values in a data source. The computing device forms a second expression based on the first expression using and the first information. The computing device retrieves one or more data sets from the data source using according to the second expression. The computing device generates and displays a data visualization of the retrieved one or more data sets.

Abstract: A method is provided for reusing custom concepts in visual analytics workflows. The method includes displaying a data visualization for a data source. The method also includes receiving a natural language input directed to the visualization. The method also includes parsing the natural language input to data fields and/or data values. The method also includes executing queries to data sources for retrieving results, based on the data fields and/or the data values. The method also includes generating and storing a named concept from the results, including either (i) saving underlying data as the named concept or (ii) querying the results and saving resulting data as the named concept. Saving the underlying data corresponds to saving data in an attribute. Querying the results is performed when a referenced attribute is not part of the results so a new query is issued that adds data from the referenced attributes.

Abstract: A method executes at a computing device that includes a display, one or more processors, and memory. The device displays a data visualization based on a dataset retrieved from a database. The device also displays one or more first phrases in a first region. The first phrases define the data visualization. The device receives a first user input in a second region to specify a natural language command related to the displayed data visualization. In response to the first user input, the device displays one or more proposed actions. The device receives user selection of a first proposed action of the proposed actions. In response to the user selection, the device generates an updated data visualization. The device displays the updated data visualization and displays a plurality of second phrases in the first region. The second phrases define the updated data visualization.

Abstract: An electronic device has a first device type. The device receives a request directed to a data source. The request includes one or more intent types and one or more predefined attributes associated with the one or more intent types. The device formulates, for each of the intent types, a respective intent specification according to the request. In some implementations, the device determines respective properties of the respective intent specification according to the respective predefined attributes and according to data fields, from the data source, specified in the request. The device generates, for each of the intent types, a respective output specification that specifies a respective recommended data visualization type. The device renders data analysis responsive to the request in accordance with the electronic device having the first device type.

Abstract: A computing device displays a data visualization interface and receives user selection of a data source and a natural language command directed to the data source. The device forms a first intermediate expression according to a context-free grammar and a semantic model of data fields in the data source. In accordance with a determination that the first intermediate expression omits sufficient information for generating a data visualization, the device infers the omitted information associated with the data source using one or more inferencing rules based on syntactic and semantic constraints imposed by the context-free grammar. The device forms an updated intermediate expression, and translates the updated intermediate expression into database queries. It executes the database queries to retrieve data sets from the data source, then generates and displays a data visualization of the retrieved data sets.

Abstract: A plurality of interrelated block objects are obtained. Each block object having a respective specification that includes (i) a layout type; (ii) a mark type; (iii) one or more visual encodings; and (iv) one or more data fields of a data source. A respective data field of the one or more data fields is associated with a respective visual encoding of the one or more visual encodings. A respective query generated for each block object of the plurality of block objects is executed to retrieve a respective set of tuples from the data source. Each tuple comprising data values for the respective one or more data fields of the block object. A data visualization is generated in accordance with the respective specifications of the interrelated block objects. Each tuple in each of the respective set of tuples is represented as a visual mark in the data visualization.

Abstract: A computing device displays a data visualization in a graphical user interface. The device receives user input to specify a natural language command related to the data visualization. The device determines that the natural language command includes a metacommand to modify the data visualization by: (1) adding a new data field, or (2) removing one of the one or more first data fields, or (3) replacing one of the one or more first data fields with another data field. The device determines one or more proposed actions in accordance with the metacommand and ranks the proposed actions based on the saliency or weight of a missing term that is inferred from the natural language command. The device receives user selection of a first proposed action. In response to the user selection, the device generates and displays an updated data visualization.

Abstract: At a computer system a graphical user interface is displayed on a display. The graphical user interface includes (a) a schema region displaying data field icons, each data field icon representing a respective data field from a user-selected data source, and (b) a canvas region. In response to receiving user input selecting a data field icon from the schema region and placing it on the canvas region, a block card is displayed on the canvas region. The block card includes user interface affordances to designate (i) a layout type that specifies a row-based arrangement, a column-based arrangement, or an inline arrangement, (ii) a mark type that specifies a shape for visual data marks, and (iii) one or more visual encodings. A data visualization for the data source is generated and displayed according to the layout type, the mark type, and the visual encodings specified on the block card.