In the design of visual analytics systems, good understanding of user intents can make systems adapt to user needs and help users better complete analytical tasks. However, user intent is difficult to observe directly. Current work tends to focus more on analyzing user behaviors and overlook the potential connections between data. In this paper, we propose an approach to understanding user intents by automatically extracting data features and combining them with user interaction history. We develop a framework for understanding user intents based on graph neural networks to support two high-level tasks: 1) real-time recommendation for the next interaction based on interaction history, and 2) real-time storytelling to characterize user intents. In our framework, we apply an SR-GATNE model based on graph neural networks to real-time recommendations and story generation. We incorporate the framework in a visual analytics system for industry analysis and evaluating the system. Results of evaluation show that our approach can help users complete the tasks better and improve their experience in analytical tasks.

Interaction is an important channel to offer users insights in interactive visualization systems. However, which interaction to operate and which part of data to explore are hard questions for public users facing a multi-view visualization for the first time. Making these decisions largely relies on professional experience and analytic abilities, which is a huge challenge for non-professionals. To solve the problem, we propose a method aiming to provide diverse, insightful, and real-time interaction recommendations for novice users. Building on the Long-Short Term Memory Model (LSTM) structure, our model captures users' interactions and visual states and encodes them in numerical vectors to make further recommendations. Through an illustrative example of a visualization system about Chinese poets in the museum scenario, the model is proven to be workable in systems with multi-views and multiple interaction types. A further user study demonstrates the method's capability to help public users conduct more insightful and diverse interactive explorations and gain more accurate data insights.