Interest modeling in recommender system has been a constant topic for improving user experience, and typical interest modeling tasks (e.g. multi-interest, long-tail interest and long-term interest) ...have been investigated in many existing works. However, most of them only consider one interest in isolation, while neglecting their interrelationships. In this paper, we argue that these tasks suffer from a common "interest amnesia" problem, and a solution exists to mitigate it simultaneously. We figure that long-term cues can be the cornerstone since they reveal multi-interest and clarify long-tail interest. Inspired by the observation, we propose a novel and unified framework in the retrieval stage, "Trinity", to solve interest amnesia problem and improve multiple interest modeling tasks. We construct a real-time clustering system that enables us to project items into enumerable clusters, and calculate statistical interest histograms over these clusters. Based on these histograms, Trinity recognizes underdelivered themes and remains stable when facing emerging hot topics. Trinity is more appropriate for large-scale industry scenarios because of its modest computational overheads. Its derived retrievers have been deployed on the recommender system of Douyin, significantly improving user experience and retention. We believe that such practical experience can be well generalized to other scenarios.
In this paper, we propose a novel LiDAR extrinsic parameter self-calibration method, DyLESC. With the driving trajectories obtained from GPS/IMU, a set of point cloud maps can be established by ...accumulating the LiDAR frames. The method introduces a function to evaluate the blurriness of the point cloud maps, which involves both geometrical features and point-number factors. By minimizing the blurriness of the point cloud maps, LiDAR extrinsic parameters are automatically calibrated. The method limits the frame number in a point cloud map to avoid the accumulated bumpy errors of GPS/IMU. For improving the robustness, the moving objects are removed from the LiDAR frames. We test the method both in a simulation environment and in the real world. The experiment result shows that DyLESC can accurately calibrate the LiDAR extrinsic parameters.