Machine learning techniques for generating visualization recommendations

Patent metadata

Field	Value
Publication number	US-12462169-B2
Application number	US-202117207959-A
Country	US
Kind code	B2
Filing date	Mar 22, 2021
Priority date	Mar 22, 2021
Publication date	Nov 4, 2025
Grant date	Nov 4, 2025

Abstract

A visualization recommendation system generates recommendation scores for multiple visualizations that combine data attributes of a dataset with visualization configurations. The visualization recommendation system maps meta-features of the dataset to a meta-feature space and configuration attributes of the visualization configurations to a configuration space. The visualization recommendation system generates meta-feature vectors that describe the mapped meta-features, and generates configuration attribute sets that describe the attributes of the visualization configurations. The visualization recommendation system applies multiple scoring models to the meta-feature vectors and configuration attribute sets, including a wide scoring model and a deep scoring model. In some cases, the visualization recommendation system trains the multiple scoring models using the meta-feature vectors and configuration attribute sets.

First claim

What is claimed is:

1 . A system for generating a recommended visualization of a dataset, the system comprising:
a processing device; and a memory device in which instructions executable by the processing device are stored for configuring the processing device to perform operations including:
generating, from data attributes of an input dataset, a set of data attribute combinations;
modifying a meta-feature space that describes training meta-features of training datasets, wherein the modified meta-feature space includes first vector data describing i) meta-features extracted from the data attributes and ii) the training meta-features;
generating a set of multiple dense meta-feature vectors that includes, for each particular data attribute combination in the set of data attribute combinations, a respective dense meta-feature vector that includes respective meta-features describing the particular data attribute combination from the set of data attribute combinations;
generating a sparse meta-feature vector identifying a frequency of occurrences of the respective meta-features within the set of multiple dense meta-feature vectors;
identifying a set of visualization configurations, each visualization configuration including respective configuration attributes that describe visual characteristics of a dataset visualization;
accessing a configuration space that describes the set of visualization configurations, wherein the configuration space includes second vector data describing, for the each visualization configuration in the set of visualization configurations, the respective configuration attributes included in the each visualization configuration;
accessing a visualization scoring model that includes a wide scoring model and a deep scoring model, wherein the visualization scoring model is trained based on a visualization space that includes third vector data describing relationships of i) the training meta-features described by the meta-feature space with ii) the respective configuration attributes included in the each visualization configuration in the set of visualization configurations described by the configuration space;
generating (i) a dense configuration attribute set identifying the respective configuration attributes included in the each visualization configuration in the set of visualization configurations and (ii) a sparse configuration attribute set identifying a frequency of the respective configuration attributes in the dense configuration attribute set;
calculating, by the visualization scoring model and for the each visualization configuration in the set of visualization configurations, a respective recommendation score that is a combination of a respective wide score calculated by the wide scoring model and a respective deep score calculated by the deep scoring model;
identifying, based on the respective recommendation score for the each visualization configuration in the set of visualization configurations, a particular recommended visualization having a combination of (i) a particular visualization configuration from the set of visualization configurations and (ii) a particular meta-feature describing a particular data attribute combination from the dense meta-feature vector;
generating visualization image data based on the particular recommended visualization; and
causing a user interface to display the visualization image data.

2 . The system of claim 1 , wherein generating the set of data attribute combinations comprises identifying at least one combination of data attributes of the input dataset,
wherein at least one meta-feature in the set of multiple dense meta-feature vectors describes the at least one combination of data attributes.

3 . The system of claim 1 , the processing device further configured to perform operations including:
generating the visualization space, wherein the visualization space includes a combination of a first data attribute combination from the set of data attribute combinations with the each visualization configuration in the set of visualization configurations.

4 . The system of claim 3 , the processing device further configured to perform operations including:
calculating a recommendation score for each combination of the first data attribute combination from the set of data attribute combinations with the each visualization configuration in the set of visualization configurations; and identifying a first recommendation score having a ranking relationship to a second recommendation score, wherein identifying the recommended visualization is based on the first recommendation score having a higher ranking as compared to the second recommendation score.

5 . The system of claim 1 , the processing device further configured to perform operations including:
mapping the respective configuration attributes included in the each visualization configuration in the set of visualization configurations to the configuration space.

6 . The system of claim 1 , the processing device further configured to perform operations including:
calculating the respective recommendation score for the particular recommended visualization by applying the wide scoring model to a first combination of the sparse meta-feature vector with the sparse configuration attribute set and the deep scoring model to a second combination of at least one dense meta-feature vector from the set of multiple dense meta-feature vectors with the dense configuration attribute set.

7 . A non-transitory computer-readable medium embodying program code for generating a scoring function to identify a recommended visualization for a dataset, the program code comprising instructions which, when executed by a processor, cause the processor to perform operations comprising:
calculating multiple meta-features of a training dataset, each meta-feature describing a relationship between multiple data attributes of the training dataset; modifying a meta-feature space that describes the meta-features of the training dataset, wherein the modified meta-feature space includes first vector data describing the meta-features; generating a set of multiple dense meta-feature vectors that includes, for each particular data attribute combination in a set of combinations of the multiple data attributes, a respective dense meta-feature vector that includes respective meta-features describing at least one data attribute of the particular data attribute combination; generating a sparse meta-feature vector identifying a frequency of occurrences of the respective meta-features within the set of multiple dense meta-feature vectors; accessing a configuration space that describes a set of visualization configurations, wherein the configuration space includes second vector data describing, for each visualization configuration in the set of visualization configurations, respective configuration attributes describing characteristics of a dataset visualization; generating (i) a dense configuration attribute set identifying the respective configuration attributes of the each visualization configuration in the set of visualization configurations and (ii) a sparse configuration attribute set identifying a frequency of the respective configuration attributes in the dense configuration attribute set; modifying a visualization space to include third vector data describing relationships of the meta-features described by the meta-feature space with the respective configuration attributes of the set of visualization configurations described by the configuration space; calculating a wide scoring function configured to generate a wide score, the wide score based on co-occurrence of values in the sparse meta-feature vector and additional values in the sparse configuration attribute set;

Assignees

• Adobe Inc

Inventors

• Rossi Ryan
• Qian Xin
• Lee Tak Yeon
• Kim Sungchul
• Lee Sana
• Du Fan
• Koh Eunyee

Classifications

• G06F18/213

  Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods · CPC title

• G06N20/00 Primary

  Machine learning · CPC title

• G06N5/04 Primary

  Inference or reasoning models · CPC title