With the advancement of agricultural modernization, agricultural machinery is widely used for crop harvesting. Traditionally, agricultural machines must be refueled at gas stations regularly, affecting the harvesting efficiency. A mobile refueling service has emerged in recent years, in which refueling tankers can move to serve the refueling request. However, the current mobile refueling system is still in an on-demand mode, which may not achieve timely response. Therefore, in this paper, we propose a new mobile refueling mode, i.e., predictive mobile refueling. To tackle the challenge of sparse rewards in predictive mobile refueling, we develop a two-stage reinforcement learning-based scheduling strategy MobRef, which decouples the scheduling process into a central request dispatcher and a distributed tanker reposition scheduler, and further introduces a potential energy-based reward shaping function to facilitate the training of the reposition scheduler. Extensive experiments on two real-world datasets demonstrate the effectiveness of MobRef, which outperforms the best baseline by 12.71% on average. We also present a deployed system based on MobRef, which is used internally in China National Petroleum Corporation.

Human mobility prediction is a fundamental technique for many urban applications, e.g., location-based recommendation, traffic scheduling, and travel demand prediction. Over the past decades, many methods, e.g., Markov Model, RNN, Transformer, have been leveraged to tackle the problem. However, existing approaches mainly train a supervised model based on an offline training dataset, which overlooks the phenomenon that the mobility behaviors of humans vary across time, and the trained models may not achieve ideal performance when applied to the testing data. To tackle this challenge, in this paper, we propose AdaMove, an efficient Test-Time Adaptive (TTA) model for human mobility prediction. AdaMove has a Preference-aware Test-Time Adaptation module called PTTA, which can adjust the parameters of a trained model based on the input test trajectory such that the model can generalize to the test distribution. In addition, to address the issue of reduced inference efficiency caused by parameter adjustment during the testing phase, AdaMove is equipped with a Lightweight human Mobility prediction model called LightMob, which only requires the recent trajectory as input to accelerate the inference. It is enhanced by historical trajectory knowledge via contrastive learning during the training time, so it has competitive performance compared with existing models. Extensive experiments on three real-world human mobility datasets demonstrate that AdaMove outperforms the best baseline by 9.3% on average in accuracy, and accelerates the inference speed by 28.5% on average compared with the original TTA - based inference.

Inferring the actual road segment purely based on one positioning point, known as single-point map matching (SMM), is vital for many urban applications, e.g., ride-hailing and geo-tagging. However, it is challenging due to inherent positioning errors and extrinsic heterogeneous environments. Existing methods either overlook the heterogeneity of different regions, or do not exploit the commonality of different matching tasks. In this paper, we treat each region as an individual SMM task to tackle the heterogeneity, and propose Spatial Hierarchical Meta-Learning for SMM (SHSMM) to learn the shared knowledge across tasks. SHSMM is equipped with a Dual-view Map Matcher to perform the matching, which can perceive the knowledge of road segments globally. To learn the task-specific model parameters, SHSMM modulates initial parameters and scales the local update learning rate based on hierarchical geographical and semantic knowledge about spatial tasks. A local update learning rate scheduling strategy is further proposed to facilitate the meta-training. Extensive experiments as well as case studies based on two real-world datasets demonstrate the effectiveness of the proposed method.

With the increasing popularity of GPS modules, there are various urban applications such as car navigation relying on trajectory data modeling. In this work, we study the problem of modeling on-road trajectories, which is to predict the next road segment given a partial GPS trajectory. Existing methods that model trajectories with Markov chain or recurrent neural network suffer from various issues, including limited capability of sequential modeling, insufficiency of incorporating the road network context, and lack of capturing the underlying semantics of trajectories. In this article, we propose a new trajectory modeling framework called Multi-task Modeling for Trajectories (MMTraj+), which avoids these issues. Specifically, MMTraj+ uses multi-head self-attention networks for sequential modeling, captures the overall road network as the context information for road segment embedding, and performs an auxiliary task of predicting the trajectory destination information (namely the ID and bearing angle) to better guide the main trajectory modeling task (controlled by a carefully designed gating mechanism). In addition, we tailor MMTraj+ for the cases where the destination information is known by dropping its auxiliary task of predicting the trajectory destination information. Extensive experiments conducted on real-world datasets demonstrate the superiority of the proposed method over the baseline methods.

Intelligent logistics relies on accurately predicting the service time, which is a part of time cost in the last-mile delivery. However, service time prediction (STP) is non-trivial given complex delivery circumstances, location heterogeneity, and skewed observations in space, which are not well-handled by existing solutions. In our prior work, we treat STP at each location as a learning task to keep the location heterogeneity, propose a prior knowledge-enhanced meta-learning to tackle skewed observations, and introduce a Transformer-based representation module to encode complex delivery circumstances. Maintaining the design principles of prior work, in this extended paper, we propose MetaSTP+. In addition to fusing the prior knowledge after the meta-learning process, MetaSTP+also injects the prior knowledge before and during the meta-learning process to better tackle skewed observations. More specifically, MetaSTP+completes the support set of tasks with scarce samples from other tasks based on prior knowledge and is equipped with a prior knowledge-aware historical observation encoding module to achieve those purposes accordingly. Experiments show MetaSTP+outperforms the best baseline by 11.2% and 8.4% on two real-world datasets. Finally, an intelligent waybill assignment system based on MetaSTP+is deployed in JD Logistics.

Cross-domain sequential recommendation (CDSR) utilizes data from multiple domains to recommend the user’s next interaction based on his latest interaction sequence. Currently, many cross-domain sequential recommendation algorithms have been proven to achieve good recommendation performance. However, these algorithms overlook the influence of users’ long-term behavioral patterns and general interests when extracting their current preferences. In this article, we propose a Hierarchical Gating Network for Cross-Domain Sequential Recommendation (HGNCDSR). Specifically, we simultaneously train single-domain and cross-domain interaction sequences, utilizing a hierarchical gating network to capture user interest representations in single-domain and cross-domain, respectively. A feature gating and an instance gating are applied respectively to extract user interests at item feature level and instance level. While learning current preferences from behavior sequences, user representations that reflect behavioral patterns and general interests are simultaneously learned and strengthened. Additionally, we employ the item–item product to model the relationships between candidate items and those in the interaction sequence. Both current interests and item relevance are considered simultaneously, integrating single-domain and cross-domain user preferences to predict the user’s next interaction. We design extensive experiments to show that HGNCDSR has better recommendation performance than other state-of-the-art models.

Remote control malwares enable cyber attackers to achieve command and control over victim hosts, which are widely employed in ransomware attacks and espionage operations, jeopardizing personal privacy and state security. To effectively detect such malicious traffics holds high practical value. However, prior works have not adequately addressed the task due to challenges of encrypted traffics with misleading contents, incomplete sessions, and limited labels. To overcome these limitations, in this paper, we propose TrafCL, a contrastive learning framework for robust encrypted malicious traffic detection. In TrafCL, we first generate incomplete variants for the input session by Session Augmentation, then extract explicit session features with excluding misleading traffic contents by Triple-aspect Session Feature Extraction, and obtain session representations by Co-attention Session Encoder which fuses triple-aspect session features with capturing their interdependence. After that, we use a projection head to obtain final representations. TrafCL is pre-trained using unlabeled data to learn close representations for complete sessions and their incomplete variants, then fine-tuned on labeled data to detect encrypted malicious traffics. Experiment results show that TrafCL outperforms the best baseline by 11.35% and 6.71% in F1-scores on two datasets respectively.

Urban sensing aims to sense the status of the city, e.g., air quality, noise level, concentration of viruses, which can be completed by spatial crowdsourcing. Multi-destination people, who have many intermediate locations to visit before the final destination, e.g., couriers and tourists, are ideal recruitment candidates to conduct sensing tasks since they spend more time outside and have a wide spatio-temporal distribution. However, existing spatial crowdsourcing methods are only designed for workers who have single destinations, e.g., commuters, which are not applicable to recruit the multiple-destination people. Therefore, in this paper, we generalize the urban crowdsensing problem to the multi-destination scenario, namely, Urban Sensing for Multi-Destination Workers (USMDW). We prove its NP-hardness, and propose a framework Urban Sensing for Multi-destination Workers via Deep REinforcement learning, i.e., SMORE, to solve it effectively and efficiently. SMORE is composed of two steps: 1) candidate assignment initialization, which initializes all feasible sensing task-worker assignment pairs by a pre-trained reinforcement learning-based working route planning solver; and 2) reinforcement learning-based iterative selection, which iteratively selects a sensing task-worker pair to the current assignment via a novel policy network, i.e., Two-stage Assignment Selection Network (TASNet). Extensive experiments on three real-world datasets show SMORE outperforms the best baseline in data coverage by 5.2% on average with high efficiency.

Crime risk map plays a crucial role in urban planning and public security management. Traditionally, it is obtained solely from historical crime incidents or inferred from limited environmental factors, which are not sufficient to accurately model the occurrences of crimes over the geographical space well. Motivated by the impressive and realistic conditional generating power of diffusion models, in this paper, we propose a multimodal conditional diffusion method, namely, DiffCrime, to infer the crime risk map based on datasets in various domains, i.e., historical crime incidents, satellite imagery, and map imagery. It is equipped with a history-gated multimodal denoising network, i.e., HamNet, dedicated to the crime risk map inference. HamNet emphasizes the importance of historical crime data via a Gated-based History Fusion (GHF) module and adaptively controls multimodal conditions to be fused across different diffusion time steps via a Time step-Aware Modality Fusion (TAMF) module. Extensive experiments on two real-world datasets demonstrate the effectiveness of DiffCrime, which outperforms baselines by at least 43% and 31% in terms of RMSE, respectively.

Urban growth benefits significantly from local business development. However, factors like traffic and labor shortages sometimes cause companies to operate away from their registered addresses, resulting in governance challenges. This paper introduces "LocRecognizer," a data mining method that leverages e-commerce data to pinpoint companies' real-world operational locations. Based on the principle that areas with a high concentration of company-related users likely indicate actual workplaces, LocRecognizer combines hierarchical clustering with a deep learning model for accurate detection. When tested on datasets from Beijing and Nantong, it outperformed six baselines. A practical implementation of this system has been operational in Nantong since September 2021, attesting to its effectiveness.

Stay area detection is one of the most important applications in trajectory data mining, which is helpful to understand human's behavior intentions. Traditional stay area detection methods are based on GPS data with relatively high sampling rate. However, because of privacy issues, accessing GPS data can be difficult in most real-world applications. Fortunately, traffic surveillance cameras have been widely deployed in urban area, and it provides us a novel way of acquiring vehicles' trajectories. All the vehicles that traverse by can be recognized and recorded in a passive way. However, the trajectory data collected in this way is extremely coarse, because the surveillance cameras are only deployed in important locations, such as crossroads. This coarse trajectory introduces two challenges for the stay area detection problem, i.e., whether and where the stay event occurs. In this paper, we design a two-stage method to solve the stay area detection problem with coarse trajectories. It first detects the stay event between a surveillance camera record pair, then uses a layer-by-layer stay area identification algorithm to infer the exact stay area. Extensive experiments based on real-world data were used to evaluate the performance of the proposed framework. Results demonstrate the proposed framework SAInf achieved a 58% performance improvement compared with SOTA methods.

With the development of positioning technology, a large number of trajectories have been generated, which are very useful for many urban applications. However, it is challenging to manage trajectory data for its spatio-temporal dynamics and high-volume properties. Existing trajectory data management frameworks suffer from efficiency or scalability problem, and only support limited trajectory query types. This paper takes the first attempt to build a holistic distributed NoSQL trajectory storage engine, named TrajMesa, based on GeoMesa, an open-source indexing toolkit for spatio-temporal data. TrajMesa can manage a prohibitively large number of trajectories, and support plenty of query types efficiently. Specifically, we first design a novel trajectory storage schema, which reduces the storage size tremendously. We then devise a novel indexing key schema for time ranges, based on which ID temporal query can be supported efficiently. To reduce the amount of retrieved trajectory data for a spatial range query, we innovatively propose a position code to indicate the spatial location of trajectories accurately. We also propose a bunch of pruning strategies for similarity query and k-NN query in the NoSQL environment. Extensive experiments are conducted using two real datasets and one synthetic dataset, verifying the powerful query efficiency and scalability of TrajMesa.

Nowadays, couriers are still the main solution to address the "last mile" problem in logistics. They are usually required to record the delivery time of each parcel manually, which is essential for delivery insurances, delivery performance evaluations, and customer available time discovery. Stay points extracted from couriers' trajectories provide a chance to fill the delivery time automatically to ease their burdens. However, it is challenging due to inaccurate delivery locations and various stay scenarios. To this end, we propose the improved Delivery Time Inference (DTInf+), to infer the delivery time of waybills based on couriers' trajectories. Our solution is composed of three steps: 1) Data Pre-processing, which organizes waybills and stay points by delivery trips, 2) Delivery Location Mining, which obtains the delivery location for each address and each Geocoded waybill location by mining historical delivery caused stay points, and 3) Delivery Event-based Matching, which jointly selects the best-matched stay point for waybills at the same delivery location based on Pointer Network-like model SPSelector to infer the delivery time. Extensive experiments and case studies based on real-world datasets from JD Logistics confirm the effectiveness of our approach. Finally, a system powered by DTInf+ is deployed in JD Logistics.

The phenomena of data missing are common in the field of traffic, yet existing solutions for data imputation are not sufficient due to challenges of data sparsity, complex traffic situations and the lack of complete ground truths. In this paper, we propose a novel solution called STCPA for the speed imputation problem. STCPA captures complex traffic correlations among the spatial and temporal dimensions via the attention mechanism, which helps mitigate the data sparsity issue. In addition, STCPA adopts an imputation cycle consistency constraint for providing reliable supervisions on unobserved entries, which improves the training. Furthermore, it incorporates an extra Road-aware Perceptual Loss, which helps encourage to preserve more meaningful semantics for imputation. Extensive experiments are conducted on two real-world datasets, namely, Chengdu and New York, to demonstrate the effectiveness of STCPA, e.g., it outperforms the best baseline by 7.64% and 5.00% on Chengdu and New York datasets, respectively. The code is available at https://github.com/Sam1224/STCPA.

Similarity search has recently become an integral part of many trajectory data analysis tasks. As the number of trajectories increases, we must find similar trajectories among massive trajectories, necessitating a scalable and efficient frame-work. Typically, massive trajectory data can be managed by key-value data stores. However, existing works with key-value data stores use a coarse representation to store trajectory data. Besides, they do not provide efficient query processing to search similar trajectories. Thus, this paper proposes TraSS, an efficient framework for trajectory similarity search in key-value data stores. We propose a novel spatial index, XZ*, which utilizes fine-grained index spaces with irregular shapes and sizes to represent trajectories elaborately. Further, we devise a bijective function from the index spaces of XZ* to continuous integers, which is simple but effective for query processing. To improve the efficiency of similarity search, we employ two steps to prune dissimilar trajectories: (1) global pruning. It leverages the XZ* index to prune index spaces with no trajectories similar to the query trajectory. Our global pruning can only pick out index spaces with similar sizes and shapes to the query trajectory. Compared to the state-of-the-art index, our global pruning reduces I/O overhead up to 66.4 % during query processing; (2) local filtering. It filters dissimilar trajectories in a way with low complexity. We use a few representative features extracted from a trajectory by the Douglas-Peucker algorithm to accelerate the local filtering. We implement an open-source toolkit (TraSS) on a popular key-value data store. Extensive experiments show that TraSS outperforms state-of-the-art solutions.

Delivery locations are fundamental data source for intelligent logistics, which can be used in route planning, arrival time estimation, parcel allocation, etc. Using the Geocoded way-bill location of an address as the delivery location is not sufficient, due to wrong address parsing, coarse-grained POI database, or different preferences of customers. To mitigate the insufficiency of Geocoding, some methods have been proposed, which utilize couriers' locations when waybills are confirmed to be delivered for delivery location inference. Nevertheless, these methods highly rely on the quality of couriers' annotations and fail when couriers confirm deliveries with delays. We propose to infer actual delivery locations of addresses from couriers' trajectories. This idea lies on an observation that the semantics of delivering a parcel are well captured by couriers' trajectories (e.g., a stay point would be generated when a delivery occurs), which holds even couriers confirm deliveries with delays. Specifically, we design Delivery Location Inference under Mis-Annotation (DLInfMA), which (1)generates location candidates from stay points in couriers' trajectories; (2) extracts features from both an address and its location candidates; and (3) uses an attention-based neural network model LocMatcher to predict the delivery location for each address. Experiments on two real-world datasets from JD Logistics as well as synthetic datasets demonstrate the effectiveness, robustness and scalability of DLInfMA. We also present a deployed system along with two applications based on DLInfMA.

Service time is a part of time cost in the last-mile delivery, which is the time spent on delivering parcels at a certain location. Predicting the service time is fundamental for many downstream logistics applications, e.g., route planning with time windows, courier workload balancing and delivery time prediction. Nevertheless, it is non-trivial given the complex delivery circumstances, location heterogeneity, and skewed observations in space. The existing solution trains a supervised model based on aggregated features extracted from parcels to deliver, which cannot handle above challenges well. In this paper, we propose MetaSTP, a meta-learning based neural network model to predict the service time. MetaSTP treats the service time prediction at each location as a learning task, leverages a Transformer-based representation layer to encode the complex delivery circumstances, and devises a model-based meta-learning method enhanced by location prior knowledge to reserve the uniqueness of each location and handle the imbalanced distribution issue. Experiments show MetaSTP outperforms baselines by at least 9.5% and 7.6% on two real-world datasets. Finally, an intelligent waybill assignment system based on MetaSTP is deployed and used internally in JD Logistics.

With the increasing popularity of GPS modules, there are various urban applications relying on trajectory data modeling. In this work, we study the problem to model the vehicle trajectories by predicting the next road segment given a partial trajectory. Existing methods that model trajectories with Markov chain or recurrent neural network suffer from issues of modeling, context and semantics. In this paper, we propose a new trajectory modeling framework called Multi-task Modeling for Trajectories (MMTraj), which avoids these issues. Specifically, MMTraj uses multi-head self-attention networks for sequential modeling, captures the overall road network as the context information for road segment embedding, and performs an auxiliary task of predicting the trajectory destination to better guide the main trajectory modeling task (controlled by a carefully designed gating mechanism). Extensive experiments conducted on real-world datasets demonstrate the superiority of the proposed method over the baseline methods.

Spatially fine-grained urban flow data is critical for smart city efforts. Though fine-grained information is desirable for applications, it demands much more resources for the underlying storage system compared to coarse-grained data. To bridge the gap between storage efficiency and data utility, in this paper, we aim to infer fine-grained flows throughout a city from their coarse-grained counterparts. This task exhibits two challenges: the spatial correlations between coarse- and fine-grained urban flows, and the complexities of external impacts. To tackle these issues, we develop a model entitled UrbanFM which consists of two major parts: 1) an inference network to generate fine-grained flow distributions from coarse-grained inputs that uses a feature extraction module and a novel distributional upsampling module; 2) a general fusion subnet to further boost the performance by considering the influence of different external factors. This structure provides outstanding effectiveness and efficiency for small scale upsampling. However, the single-pass upsampling used by UrbanFM is insufficient at higher upscaling rates. Therefore, we further present UrbanPy, a cascading model for progressive inference of fine-grained urban flows by decomposing the original tasks into multiple subtasks. Compared to UrbanFM, such an enhanced structure demonstrates favorable performance for larger-scale inference tasks.

People often refer to a place of interest (POI) by an alias. In ecommerce scenarios, the POI alias problem affects the quality of the delivery address of online orders, bringing substantial challenges to intelligent logistics systems and market decision-making. Labeling the aliases of POIs involves heavy human labor, which is inefficient and expensive. Inspired by the observation that the users' GPS locations are highly related to their delivery address, we propose a ubiquitous alias discovery framework. Firstly, for each POI name in delivery addresses, the location data of its associated users, namely Mobility Profile are extracted. Then, we identify the alias relationship by modeling the similarity of mobility profiles. Comprehensive experiments on the large-scale location data and delivery address data from JD logistics validate the effectiveness.

The prevalence of positioning technologies has fostered massive trajectory data. Stay points from trajectories indicate the visiting of moving objects to locations, which provide an opportunity to understand the locations comprehensively. Many existing works rely on stay points to analyze locations. However, they are ad-hoc solutions to tackle specific problems, and it is time-consuming and tedious to develop each application. In this paper, we propose a universal StAy point-based LOcation aNalysis platform, i.e., SALON, with the characteristics of universality, efficiency and flexibility. It can retrieve stay points using flexible conditions, associate stay points with locations, extract comprehensive location profiles and visualize the analysis results to users. Based on the combination of these functions, we demonstrate three different location analysis scenarios, i.e., illegal location discovery, popular location ranking, location temporal analysis to show its characteristics.

The rapid development of positioning technology produces an extremely large volume of spatio-temporal data with various geometry types such as point, line string, polygon, or a mixed combination of them. As one of the most basic but time-consuming operations, k nearest neighbors join (kNN join) has attracted much attention. However, most existing works for kNN join either ignore temporal information or consider point data only.

Chemical materials are useful but sometimes hazardous, which requires strict regulation from the government. However, due to the potential economic benefits, many illegal hazardous chemical facilities are running underground, which poses a significant public safety threat. However, the traditional solutions, e.g., on-field screening and the anonymous tip-offs, involve a lot of human efforts. In this paper, we propose a ubiquitous approach called ICFinder to detecting illegal chemical facilities with chemical transportation trajectories. We first generate candidate locations by clustering stay points extracted from trajectories, and filter out known locations. Then, we rank those locations in suspicion order by modeling whether it has the loading/unloading events. ICFinder is evaluated over the real-world dataset from Nantong in China, and the deployed system identified 20 illegal chemical facilities in 3 months.

With the increasing adoption of GPS modules, there are a wide range of urban applications based on trajectory data analysis, such as vehicle navigation, travel time estimation, and driver behavior analysis. The effectiveness of urban applications relies greatly on the high sampling rates of trajectories precisely matched to the map. However, a large number of trajectories are collected under a low sampling rate in real-world practice, due to certain communication loss and energy constraints. To enhance the trajectory data and support the urban applications more effectively, many trajectory recovery methods are proposed to infer the trajectories in free space. In addition, the recovered trajectory still needs to be mapped to the road network, before it can be used in the applications. However, the two-stage pipeline, which first infers high-sampling-rate trajectories and then performs the map matching, is inaccurate and inefficient. In this paper, we propose a Map-constrained Trajectory Recovery framework, MTrajRec, to recover the fine-grained points in trajectories and map match them on the road network in an end-to-end manner. MTrajRec implements a multi-task sequence-to-sequence learning architecture to predict road segment and moving ratio simultaneously. Constraint mask, attention mechanism, and attribute module are proposed to overcome the limits of coarse grid representation and improve the performance. Extensive experiments based on large-scale real-world trajectory data confirm the effectiveness and efficiency of our approach.

Delivery stations play important roles in logistics systems. Well-designed delivery station planning can improve delivery efficiency significantly. However, existing delivery station locations are decided by experts, which requires much preliminary research and data collection work. It is not only time consuming but also expensive for logistics companies. Therefore, in this article, we propose a data-driven pipeline that can transfer expert knowledge among cities and automatically allocate delivery stations. Based on existing well-designed station location planning in the source city, we first train a model to learn the expert knowledge about delivery range selection for each station. Then we transfer the learned knowledge to a new city and design three strategies to select delivery stations for the new city. Due to the differences in characteristics among different cities, we adopt a transfer learning method to eliminate the domain difference so that the model can be adapted to a new city well. Finally, we conduct extensive experiments based on real-world datasets and find the proposed method can solve the problem well.

Gas theft of restaurants is a major concern in the gas industry, which causes revenue losses for gas companies and endangers the public safety seriously. Traditional methods of gas theft detection highly rely on active human efforts that are extremely ineffective. Thanks to the gas consumption data collected by smart meters, we can devise a data-driven method to tackle this issue. In this paper, we propose a gas-theft detection method msRank to discover suspicious restaurant users when only scarce labels are available. Our method contains three main components: 1)data pre-processing, which filters reading noises and excludes data-missing or zero-use users; 2)normal user modeling, which quantifies the self-stable seasonality of normal users and distinguishes them from unstable ones; and 3)gas-theft suspect detection, which discovers gas-theft suspects among unstable users by RankNet-based suspicion scoring on extracted deviation features. By using detected normal users as negative samples to train RankNet, the component of normal user modeling and that of gas-theft suspect detection are seamlessly connected, overcoming the problem of label scarcity. We conduct extensive experiments on three real-world datasets, and the results demonstrate advantages of our approach. We have deployed a system GasShield which provides a gas-theft suspect list weekly for a gas group in northern China.

With the prevalence of positioning techniques, a prodigious number of spatio-temporal data is generated constantly. To effectively support sophisticated urban applications, e.g., location-based services, based on spatio-temporal data, it is desirable for an efficient, scalable, update-enabled, and easy-to-use spatio-temporal data management system.This paper presents JUST, i.e., JD Urban Spatio-Temporal data engine, which can efficiently manage big spatio-temporal data in a convenient way. JUST incorporates the distributed NoSQL data store, i.e., Apache HBase, as the underlying storage, GeoMesa as the spatio-temporal data indexing tool, and Apache Spark as the execution engine. We creatively design two indexing techniques, i.e., Z2T and XZ2T, which accelerates spatio-temporal queries tremendously. Furthermore, we introduce a compression mechanism, which not only greatly reduces the storage cost, but also improves the query efficiency. To make JUST easy-to-use, we design and implement a complete SQL engine, with which all operations can be performed through a SQL-like query language, i.e., JustQL. JUST also supports inherently new data insertions and historical data updates without index reconstruction. JUST is deployed as a PaaS in JD with multi-users support. Many applications have been developed based on the SDKs provided by JUST. Extensive experiments are carried out with six state-of-the-art distributed spatio-temporal data management systems based on two real datasets and one synthetic dataset. The results show that JUST has a competitive query performance and is much more scalable than them.

Trajectory data is very useful for many urban applications. However, due to its spatio-temporal and high-volume properties, it is challenging to manage trajectory data. Existing trajectory data management frameworks suffer from scalability problem, and only support limited trajectory queries. This paper proposes a holistic distributed NoSQL trajectory storage engine, TrajMesa, based on GeoMesa, an open-source indexing toolkit for spatio-temporal data. TrajMesa adopts a novel storage schema, which reduces the storage size tremendously. We also devise novel indexing key designs, and propose a bunch of pruning strategies. TrajMesa can support plentiful queries efficiently, including ID-Temporal query, spatial range query, similarity query, and k-NN query. Experimental results show the powerful query efficiency and scalability of TrajMesa.

The rapid development of e-commerce requires efficient and reliable logistics services. Nowadays, couriers are still the main solution to address the "last mile" problem in logistics. They are usually required to record the accurate delivery time of each parcel manually, which provides vital information for applications like delivery insurances, delivery performance evaluations, and customer available time discovery. Couriers' trajectories generated by their PDAs provide a chance to infer the delivery time automatically to ease the burdens on the couriers. However, directly using the nearest stay point to infer the delivery time is under satisfactory due to two challenges: 1) inaccurate delivery locations, and 2) various stay scenarios. To this end, we propose Delivery Time Inference (DTInf), to automatically infer the delivery time of waybills based on couriers' trajectories. Our solution is composed of three steps: 1) Data Pre-processing, which detects stay points from trajectories, and separates stay points and waybills by delivery trips, 2) Delivery Location Correction, which infers true delivery locations of waybills by mining historical deliveries, and 3) Delivery Event-based Matching, which selects the best-matched stay point for waybills in the same delivery location to infer the delivery time. Extensive experiments and case studies based on large scale real-world waybill and trajectory data from JD Logistics confirm the effectiveness of our approach. Finally, we introduce a system based on DTInf, which is deployed and used internally in JD Logistics.

With the advances of web-of-things, human mobility, e.g., GPS trajectories of vehicles, sharing bikes, and mobile devices, reflects people’s travel patterns and preferences, which are especially crucial for urban applications such as urban planning and business location selection. However, collecting a large set of human mobility data is not easy because of the privacy and commercial concerns, as well as the high cost to deploy sensors and a long time to collect the data, especially in newly developed cities. Realizing this, in this paper, based on the intuition that the human mobility is driven by the mobility intentions reflected by the origin and destination (or OD) features, as well as the preference to select the path between them, we investigate the problem to generate mobility data for a new target city, by transferring knowledge from mobility data and multi-source data of the source cities. Our framework contains three main stages: 1) mobility intention transfer, which learns a latent unified mobility intention distribution across the source cities, and transfers the model of the distribution to the target city; 2) OD generation, which generates the OD pairs in the target city based on the transferred mobility intention model, and 3) path generation, which generates the paths for each OD pair, based on a utility model learned from the real trajectory data in the source cities. Also, a demo of our trajectory generator is publicly available online for two city regions. Extensive experiment results over four regions in China validate the effectiveness of the proposed solution. Besides, an on-field case study is presented in a newly developed region, i.e., Xiongan, China. With the generated trajectories in the new city, many trajectory mining techniques can be applied.

Cycling as a green transportation mode has been promoted by many governments all over the world. As a result, constructing effective bike lanes has become a crucial task to promote the cycling life style, as well-planned bike lanes can reduce traffic congestions and safety risks. Unfortunately, existing trajectory mining approaches for bike lane planning do not consider one or more key realistic government constraints: 1) budget limitations, 2) construction convenience, and 3) bike lane utilization. In this paper, we propose a data-driven approach to develop bike lane construction plans based on the large-scale real world bike trajectory data collected from Mobike, a station-less bike sharing system. We enforce these constraints to formulate our problem and introduce a flexible objective function to tune the benefit between coverage of users and the length of their trajectories. We prove the NP-hardness of the problem and propose greedy-based heuristics to address it. To improve the efficiency of the bike lane planning system for the urban planner, we propose a novel trajectory indexing structure and deploy the system based on a parallel computing framework (Storm) to improve the system's efficiency. Finally, extensive experiments and case studies are provided to demonstrate the system efficiency and effectiveness.

Bike-sharing systems become more and more popular in the urban transportation system, because of their convenience in recent years. However, due to the high daily usage and lack of effective maintenance, the number of bikes in good condition decreases significantly, and vast piles of broken bikes appear in many big cities. As a result, it is more difficult for regular users to get a working bike, which causes problems both economically and environmentally. Therefore, building an effective broken bike prediction and recycling model becomes a crucial task to promote cycling behavior. In this paper, we propose a predictive model to detect the broken bikes and recommend an optimal recycling program based on the large scale real-world sharing bike data. We incorporate the realistic constraints to formulate our problem and introduce a flexible objective function to tune the trade-off between the broken probability and recycled numbers of the bikes. Finally, we provide extensive experimental results and case studies to demonstrate the effectiveness of our approach.

Urban flow monitoring systems play important roles in smart city efforts around the world. However, the ubiquitous deployment of monitoring devices, such as CCTVs, induces a long-lasting and enormous cost for maintenance and operation. This suggests the need for a technology that can reduce the number of deployed devices, while preventing the degeneration of data accuracy and granularity. In this paper, we aim to infer the real-time and fine-grained crowd flows throughout a city based on coarse-grained observations. This task is challenging due to the two essential reasons: the spatial correlations between coarse- and fine-grained urban flows, and the complexities of external impacts. To tackle these issues, we develop a method entitled UrbanFM based on deep neural networks. Our model consists of two major parts: 1) an inference network to generate fine-grained flow distributions from coarse-grained inputs by using a feature extraction module and a novel distributional upsampling module; 2) a general fusion subnet to further boost the performance by considering the influences of different external factors. Extensive experiments on two real-world datasets validate the effectiveness and efficiency of our method, demonstrating its state-of-the-art performance on this problem.

Trajectory data preprocessing is to convert raw GPS logs into organized trajectories, which is a common, necessary but tedious task in many urban applications. This paper proposes CloudTP, a cloud-based flexible trajectory data preprocessing framework, to provide an efficient online service, easing the burdens of urban application builders. The proposed system is designed and implemented based on the cloud storage and parallel computing framework (i.e. Spark). Its features consist of 1) noise filtering, 2) trajectory segmentation, 3) map matching, and 4) index building. CloudTP is useful for both normal users and advanced users. By simply uploading trajectory datasets and setting corresponding parameters, normal users can get organized trajectories, statistics and visualizations on the cloud, while advanced users can also customize their own algorithms in any preprocessing module. Finally, usage scenarios are demonstrated to show the capability and flexibility of CloudTP.

Illegal vehicle parking is a common urban problem faced by major cities in the world, as it incurs traffic jams, which lead to air pollution and traffic accidents. Traditional approaches to detect illegal vehicle parking events rely highly on active human efforts, e.g., police patrols or surveillance cameras. However, these approaches are extremely ineffective to cover a large city. The massive and high quality sharing bike trajectories from Mobike offer us with a unique opportunity to design a ubiquitous illegal parking detection system, as most of the illegal parking events happen at curbsides and have significant impact on the bike users. Two main components are employed to mine the trajectories in our system: 1)~trajectory pre-processing, which filters outlier GPS points, performs map-matching and builds indexes for bike trajectories; and 2)~illegal parking detection, which models the normal trajectories, extracts features from the evaluation trajectories and utilizes a distribution test-based method to discover the illegal parking events. The system is deployed on the cloud internally used by Mobike. Finally, extensive experiments and many insightful case studies based on the massive trajectories in Beijing are presented.

A path query aims to find the trajectories that pass a given sequence of connected road segments within a time period. It is very useful in many urban applications, e.g., 1) traffic modeling, 2) frequent path mining, and 3) traffic anomaly detection. Existing solutions for path query are implemented based on single machines, which are not efficient for the following tasks: 1) indexing large-scale historical data; 2) handling real-time trajectory updates; and 3) processing concurrent path queries. In this paper, we design and implement a cloud-based path query processing framework based on Microsoft Azure. We modify the suffix tree structure to index the trajectories using Azure Table. The proposed system consists of two main parts: 1) backend processing, which performs the pre-processing and suffix index building with distributed computing platform (i.e., Storm) used to efficiently handle massive real-time trajectory updates; and 2) query processing, which answers path queries using Azure Storm to improve efficiency and overcome the I/O bottleneck. We evaluate the performance of our proposed system based on a real taxi dataset from Guiyang, China.

With the rapid development of location-acquisition techniques, massive trajectories are continuously generated. Many urban applications rely heavily on the data mining/analysis results of massive trajectory data. This demo presents a holistic data management system for both historical and real-time trajectory records based on a cloud platform, such as Microsoft Azure. The proposed system is able to efficiently support a variety of trajectory queries, including ID-Temporal query, Spatio-Temporal query, and Path-Temporal query. With these queries, we demonstrate that different urban applications can be realized in a much easier way.

Cycling as a green transportation mode has been promoted by many governments all over the world. As a result, constructing effective bike lanes has become a crucial task for governments promoting the cycling life style, as well-planned bike paths can reduce traffic congestion and decrease safety risks for both cyclists and motor vehicle drivers. Unfortunately, existing trajectory mining approaches for bike lane planning do not consider key realistic government constraints: 1) budget limitations, 2) construction convenience, and 3) bike lane utilization.