Natural language to customize data visualization
AssigneePalo Alto Networks, Inc.
InventorsSameer D. Merchant, Zana Vosough, Rajesh Bhagwat
Life of this patent
Estimating the term…
Abstract
A system, method, and device for generating data visualizations are disclosed. The method includes (i) obtaining a natural language query, (ii) determining an intent for the natural language query, (iii) generating one or more data requests to one or more selected data sources, the one or more data requests being based at least in part on the intent, (iv) obtaining a predicted visualization definition based at least in part on abstracting the result data, and (v) generating a visualization for the result data based at least in part on the predicted visualization definition.
Claims18
A system for visualizing data, comprising:
- one or more processors configured to:
- obtain a natural language query;
- determine an intent for the natural language query based at least in part on querying a first machine learning (ML) model to interpret the natural language query;
- generate, based at least in part on the intent, one or more data requests to one or more selected data sources;
- obtain result data that is responsive to the one or more data requests;
- obtain a predicted visualization definition that is in an intermediate language interpretable by a large language model, comprising:
- (i) abstracting the result data based on one or more characteristics of the result data to obtain a data abstraction for the result data,
- (ii) querying, based on the data abstraction, a second ML model that is different from the first ML model for a visualization type, and
- (iii) using a predefined data visualization language based at least in part on a particular statistical representation format in which at least part of the result data is to be presented indicated by the visualization type to obtain the predicted visualization definition;
- and
- generate a statistical representation as a visualization for the result data based at least in part on the result data and the visualization type according to which the result data is to be visualized indicated by the predicted visualization definition;
- and
- a memory coupled to the one or more processors and configured to provide the one or more processors with instructions.
A method for visualizing data, comprising:
- obtaining, by one or more processors, a natural language query;
- determining an intent for the natural language query based at least in part on querying a first machine learning (ML) model to interpret the natural language query;
- generating, based at least in part on the intent, one or more data requests to one or more selected data sources;
- obtaining result data that is responsive to the one or more data requests;
- obtaining a predicted visualization definition that is in an intermediate language interpretable by a large language model, comprising:
- (i) abstracting the result data based on one or more characteristics of the result data to obtain a data abstraction for the result data,
- (ii) querying, based on the data abstraction, a second ML model that is different from the first ML model for a visualization type, and
- (iii) using a predefined data visualization language based at least in part on a particular statistical representation format in which at least part of the result data is to be presented indicated by the visualization type to obtain the predicted visualization definition;
- and
- generating a statistical representation as a visualization based at least in part on the result data and the visualization type according to which the result data is to be visualized indicated by the predicted visualization definition.
A non-transitory computer readable medium embodied computer program product for visualizing data, and the computer program product comprising computer instructions that, when executed by one or more processors, cause the one or more processors to perform a method, the method comprising:
- obtaining, by one or more processors, a natural language query;
- determining an intent for the natural language query based at least in part on querying a first machine learning (ML) model to interpret the natural language query;
- generating, based at least in part on the intent, one or more data requests to one or more selected data sources;
- obtaining result data that is responsive to the one or more data requests;
- obtaining a predicted visualization definition that is in an intermediate language interpretable by a large language model, comprising:
- (i) abstracting the result data based on one or more characteristics of the result data to obtain a data abstraction for the result data,
- (ii) querying a second ML model that is different from the first ML model for a visualization type, and
- (iii) using a predefined data visualization language based at least in part on a particular statistical representation format in which at least part of the result data is to be presented indicated by the visualization type to obtain the predicted visualization definition;
- and
- generating a statistical representation as a visualization based at least in part on the result data and the visualization type according to which the result data is to be visualized indicated by the predicted visualization definition, wherein the statistical representation is based at least part of the result data.
Dependencies are inferred from the claim text.