Mobile map apps such as the Baidu Maps app have become a ubiquitous and essential tool for users to find optimal routes and get turn-by-turn navigation services while driving. However, interacting with such apps while driving through visual-manual interaction modality inevitably causes driver distraction, due to the highly conspicuous nature of the time-sharing, multi-tasking behavior of the driver. In this paper, we present our efforts and findings of a 4-year longitudinal study on designing and implementing DuIVA, which is an intelligent voice assistant (IVA) embedded in the Baidu Maps app for hands-free, eyes-free human-to-app interaction in a fully voice-controlled manner. Specifically, DuIVA is designed to enable users to control the functionalities of Baidu Maps (e.g., navigation and location search) through voice interaction, rather than visual-manual interaction, which minimizes driver distraction and promotes safe driving by allowing the driver to keep "eyes on the road and hands on the wheel'' while interacting with the Baidu Maps app. DuIVA has already been deployed in production at Baidu Maps since November 2017, which facilitates a better interaction modality with the Baidu Maps app and improves the accessibility and usability of the app by providing users with in-app voice activation, natural language queries, and multi-round dialogue. As of December 31, 2021, over 530 million users have used DuIVA, which demonstrates that DuIVA is an industrial-grade and production-proven solution for in-app intelligent voice assistants.

Entity recommendation, providing entity suggestions to assist users in discovering interesting information, has become an indispensable feature of today’s Web search engine. However, the majority of existing entity recommendation methods are not designed to boost the performance in terms of serendipity, which also plays an important role in the appreciation of users for a recommendation system. To keep users engaged, it is important to take into account serendipity when building an entity recommendation system. In this article, we propose a learning to recommend framework that consists of two components: related entity finding and candidate entity ranking. To boost serendipity performance, three different sets of features that correlate with the three aspects of serendipity are employed in the proposed framework. Extensive experiments are conducted on large-scale, real-world datasets collected from a widely used commercial Web search engine. The experiments show that our method significantly outperforms several strong baseline methods. An analysis on the impact of features reveals that the set of interestingness features is the most powerful feature set, and the set of unexpectedness features can significantly contribute to recommendation effectiveness. In addition, online controlled experiments conducted on a commercial Web search engine demonstrate that our method can significantly improve user engagement against multiple baseline methods. This further confirms the effectiveness of the proposed framework.

Providing a plausible explanation for the relationship between two related entities is an important task in some applications of knowledge graphs, such as in search engines. However, most existing methods require a large number of manually labeled training data, which cannot be applied in large-scale knowledge graphs due to the expensive data annotation. In addition, these methods typically rely on costly handcrafted features. In this paper, we propose an effective pairwise ranking model by leveraging clickthrough data of a Web search engine to address these two problems. We first construct large-scale training data by leveraging the query-title pairs derived from clickthrough data of a Web search engine. Then, we build a pairwise ranking model which employs a convolutional neural network to automatically learn relevant features. The proposed model can be easily trained with backpropagation to perform the ranking task. The experiments show that our method significantly outperforms several strong baselines.