The explosion of multimedia data in information-rich environments has intensified the challenges of personalized content discovery, positioning recommendation systems as an essential form of passive data management. Multimodal sequential recommendation, which leverages diverse item information such as text and images, has shown great promise in enriching item representations and deepening the understanding of user interests. However, most existing models rely on heuristic fusion strategies that fail to capture the dynamic and context-sensitive nature of user-modal interactions. In real-world scenarios, user preferences for modalities vary not only across individuals but also within the same user across different items or categories. Moreover, the synergistic effects between modalities-where combined signals trigger user interest in ways isolated modalities cannot-remain largely underexplored. To this end, we propose CAMMSR, a Category-guided Attentive Mixture of Experts model for Multimodal Sequential Recommendation. At its core, CAMMSR introduces a category-guided attentive mixture of experts (CAMoE) module, which learns specialized item representations from multiple perspectives and explicitly models inter-modal synergies. This component dynamically allocates modality weights guided by an auxiliary category prediction task, enabling adaptive fusion of multimodal signals. Additionally, we design a modality swap contrastive learning task to enhance cross-modal representation alignment through sequence-level augmentation. Extensive experiments on four public datasets demonstrate that CAMMSR consistently outperforms state-of-the-art baselines, validating its effectiveness in achieving adaptive, synergistic, and user-centric multimodal sequential recommendation.

The scientific computation of large deformations in elastic-plastic solids is crucial in various manufacturing applications. Traditional numerical methods exhibit several inherent limitations, prompting Deep Learning (DL) as a promising alternative. The effectiveness of current DL techniques typically depends on the availability of high-quantity and high-accuracy datasets, which are yet difficult to obtain in large deformation problems. During the dataset construction process, a dilemma stands between data quantity and data accuracy, leading to suboptimal performance in the DL models. To address this challenge, we focus on a representative application of large deformations, the stretch bending problem, and propose FilDeep, a Fidelity-based Deep Learning framework for large Deformation of elastic-plastic solids. Our FilDeep aims to resolve the quantity-accuracy dilemma by simultaneously training with both low-fidelity and high-fidelity data, where the former provides greater quantity but lower accuracy, while the latter offers higher accuracy but in less quantity. In FilDeep, we provide meticulous designs for the practical large deformation problem. Particularly, we propose attention-enabled cross-fidelity modules to effectively capture long-range physical interactions across MF data. To the best of our knowledge, our FilDeep presents the first DL framework for large deformation problems using MF data. Extensive experiments demonstrate that our FilDeep consistently achieves state-of-the-art performance and can be efficiently deployed in manufacturing.

In last-mile logistics, couriers are typically assigned fixed zones to perform door-to-door deliveries. In practice, packages in some delivery zones might not be fulfilled on time due to couriers taking irregular leave for sickness or higher-priority task assignments, e.g., services for VIPs and regulatory training. Beyond the costly real-world practice, i.e., hiring temporary workers, analysis of historical data reveals that a daily delivery task rescheduling among on-duty couriers can be a cost-effective and efficient alternative. It involves individual workload assessments and delivery task assignments, both of which existing methods can not address adequately: (i) Existing courier workload assessment methods are not tailored for downstream optimization tasks, leading to poor performance. (ii) Efficiency-oriented task assignment methods may lead to unfair workload among the couriers. To address the above two limitations, in this paper, we propose D3-TR, a data-driven method for task reassignment among present couriers. Firstly, we design a consistency-guided predictor that can quickly and precisely predict the workload of couriers. Secondly, based on this predictor, we design a workload-aware genetic algorithm to solve the optimal task allocation problem. Experimental results underscore the superiority of our method over several baselines. Furthermore, real-world deployment on millions of orders demonstrates the effectiveness of our solution, yielding an average of 3.9% improvement in the on-time delivery rate.

Scientific computing for large deformation of elastic-plastic solids is critical for numerous real-world applications. Classical numerical solvers rely primarily on local discrete linear approximation and are constrained by an inherent trade-off between accuracy and efficiency. Recently, deep learning models have achieved impressive progress in solving the continuum mechanism. While previous models have explored various architectures and constructed coefficient-solution mappings, they are designed for general instances without considering specific problem properties and hard to accurately handle with complex elastic-plastic solids involving contact, loading and unloading. In this work, we take stretch bending, a popular metal fabrication technique, as our case study and introduce LaDEEP, a deep learning-based surrogate model for La rge De formation of Elastic-Plastic Solids. We encode the partitioned regions of the involved slender solids into a token sequence to maintain their essential order property. To characterize the physical process of the solid deformation, a two-stage Transformer-based module is designed to predict the deformation with the sequence of tokens as input. Empirically, LaDEEP achieves five magnitudes faster speed than finite element methods with a comparable accuracy, and gains 20.47% relative improvement on average compared to other deep learning baselines. We have also deployed our model into a real-world industrial production system, and it has shown remarkable performance in both accuracy and efficiency. Code is available at https://github.com/therontau0054/LaDEEP.

Textual description of a physical location, commonly known as an address, plays an important role in location-based services(LBS) such as on-demand delivery and navigation. However, the prevalence of abnormal addresses, those containing inaccuracies that fail to pinpoint a location, have led to significant costs. Address rewriting has emerged as a solution to rectify these abnormal addresses. Despite the critical need, existing address rewriting methods are limited, typically tailored to correct specific error types, or frequently require retraining to process new address data effectively. In this study, we introduce AddrLLM, an innovative framework for address rewriting that is built upon a retrieval augmented large language model. AddrLLM overcomes aforementioned limitations through a meticulously designed Supervised Fine-Tuning module, an Address-centric Retrieval Augmented Generation module and a Bias-free Objective Alignment module. To the best of our knowledge, this study pioneers the application of LLM-based address rewriting approach to solve the issue of abnormal addresses. Through comprehensive offline testing with real-world data on a national scale and subsequent online deployment, AddrLLM has demonstrated superior performance in integration with existing logistics system. It has significantly decreased the rate of parcel re-routing by approximately 43%, underscoring its exceptional efficacy in real-world applications.

Cross-Domain Sequential Recommendation (CDSR) is a hot topic in sequence-based user interest modeling, which aims at utilizing a single model to predict the next items for different domains. To tackle the CDSR, many methods are focused on domain overlapped users’ behaviors fitting, which heavily relies on the same user’s different-domain item sequences collaborating signals to capture the synergy of cross-domain item-item correlation. Indeed, these overlapped users occupy a small fraction of the entire user set only, which introduces a strong assumption that the small group of domain overlapped users is enough to represent all domain user behavior characteristics. However, intuitively, such a suggestion is biased, and the insufficient learning paradigm in non-overlapped users will inevitably limit model performance. Further, it is not trivial to model non-overlapped user behaviors in CDSR because there are no other domain behaviors to collaborate with, which causes the observed single-domain users’ behavior sequences to be hard to contribute to cross-domain knowledge mining. Considering such a phenomenon, we raise a challenging and unexplored question: How to unleash the potential of non-overlapped users’ behaviors to empower CDSR? To this end, we propose a novel CDSR framework with Neural Processes (NP), briefly termed CDSRNP, where NP combines the advantages of meta-learning and stochastic processes. As a meta-learning based method, we first sample some observed overlapped users’ behaviors as the support set to empower query users’ prediction. Next, we employ the NP principle to align the cross-domain correlation prior/posterior distributions generated by support/query user sets, thus the query user (e.g., non-overlapped user) behaviors sequence could also establish a straight bridge to connect other domain items. Additionally, we design a fine-grained interest adaptive layer to identify the users’ interests to enhance prediction. Experimental results illustrate that CDSRNP1 outperforms state-of-the-art methods in two real-world datasets.

An efficient last-mile delivery scheme in logistics benefits customers, couriers, and the platform. In practice, the delivery scope of a delivery station is divided into multiple areas, each of which is covered by a courier. The long distances between the delivery station and areas limit the couriers' delivery efficiency given that they need to travel back and forth multiple times a day. To solve this problem, we explore an inter-trip cooperation scheme for last-mile delivery, in which couriers traveling to the delivery station and back to corresponding areas earlier can help to take others' orders back. Coordinating the courier cooperation is challenging because we need to consider the courier's status, e.g., locations, and vehicle capacity constraint simultaneously. In this work, we design an inter-trip cooperation-based last-mile delivery system, InCo, aiming to minimize the average order delivery time. InCo includes two components: i) a time-aware spanning tree algorithm to generate the cooperation result for a group of couriers; and ii) a capacity-constrained courier grouping algorithm to optimize the courier grouping result iteratively. Extensive evaluation results with real-world order data collected from one of the largest logistics companies show that InCo improves the average saved delivery time and reduces average travel time by up to 80.2% and 28.4%, respectively, compared to baseline methods. The deployment results show InCo improves the average courier working efficiency by 21.6% to the state-of-the-practice.

Recently, integrated warehouse and distribution logistics systems are widely used in E-commerce industries to adjust to constantly changing customer demands. It makes the prediction of purchase demand and delivery supply capacity a crucial problem to streamline operations and improve efficiency. The interaction between such demand and supply not only relies on their economic relationships but also on consumer psychology caused by daily events, such as epidemics, promotions, and festivals. Although existing studies have made great efforts in the joint prediction of demand and supply considering modeling the demand-supply interactions, they seldom refer to the impacts of diverse events. In this work, we propose MulSTE, a Multi-view Spatio-Temporal learning framework with heterogeneous Event fusion. Firstly, an Event Fusion Representation (EFR) module is designed to fuse the textual, numerical, and categorical heterogeneous information for emergent and periodic events. Secondly, a Multi-graph Adaptive Convolution Recurrent Network (MGACRN) is developed as the spatio-temporal encoder (ST-Encoder) to capture the evolutional features of demand, supply, and events. Thirdly, the Event Gated Demand-Supply Interaction Attention (EGIA) module is designed to model the demand-supply interactions during events. The evaluations are conducted on two real-world datasets collected from JD Logistics and public websites. The experimental results show that our method outperforms state-of-the-art baselines in various metrics.

Geocoding, associating textual addresses with corresponding GPS coordinates, is vital for many location-based services (e.g., logistics, ridesharing, and social networks). One of the most common Geocoding solutions is using commercial map services such as Google Maps. However, this is typically not practical for some location-based service providers due to real-world challenges like commercial competition and high costs (recurring fees). In this paper, we design a new cost-effective Geocoding framework to automatically infer the geographic coordinates from textual addresses. To achieve this, we take the E-Commerce logistics service as a concrete scenario and designCoMiner, an unsupervised coordinate inference framework based on textual address data, delivery event data, and courier trajectory data.CoMinerincludes three main components, (1) A POI-level clustering model, (2) A Delivery Mobility Graph (DMG), and (3) A behavior-driven address ranking model. Furthermore, we designCoMiner-W, a coordinates mining algorithm based on WiFi data, to further enhance the effectiveness ofCoMiner. We conduct extensive experiments on three large-scale datasets whereCoMineroutperforms the state-of-the-art methods by 20.3%. Moreover, we have designed an abnormal delivery event detection system based onCoMinerand deployed it at JD Logistics, which brings a significant reduction in abnormal delivery event rates.

Points of Interest (POIs), such as entertainment, dining, and living, are crucial for urban planning and location-based services. However, the high dynamics and expensive updating costs of POIs pose a key roadblock for their urban applications. This is especially true for developing countries, where active economic activities lead to frequent POI updates (e.g., merchants closing down and new ones opening). Therefore, POI updating, i.e., detecting new POIs and different names of the same POIs (alias) to update the POI database, has become an urgent but challenging problem to address. In this paper, we attempt to answer the research question of how to detect and update large-scale POIs via a low-cost approach. To do so, we propose a novel framework called UrbanPOI, which formulates the POI updating problem as a tagging and detection problem based on multi-modal logistics delivery data. UrbanPOI consists of two key modules: (i) a hierarchical POI candidate generation module based on the POINet model that detects POIs from shipping addresses; and (ii) a new POI detection module based on the Siamese Attention Network that models multi-modal data and crowd intelligence. We evaluate our framework on real-world logistics delivery datasets from two Chinese cities. Extensive results show that our model outperforms state-of-the-art models in Beijing City by 26.2% in precision and 10.7% in F1-score, respectively.

Last-mile delivery from delivery stations to customers’ places is now mainly finished by dedicated couriers. In practice, each courier generally collects orders destined for one delivery area at the delivery station and delivers orders to customers. However, the long distance between the delivery station and the delivery area due to practical reasons, e.g., expensive delivery station rental fee in the downtown area, increases the delivery courier’s travel time and decreases the efficiency of the state-of-the-practice last-mile delivery scheme. In this paper, we solve the problem with relay transportation, where a relay courier collects orders at the delivery station and sends them to delivery couriers, and delivery couriers focus on the order delivery at corresponding delivery areas. We design a real-time relay courier scheduling system called REDE to minimize the average relay order delivery time (ARODT) considering the relay and delivery couriers’ mobility and the order destination distribution. First, a heterogeneous task aware route prediction algorithm is proposed to characterize the delivery courier’s mobility. Then a distance-aware greedy algorithm and an ARODT-constrained exchange algorithm are designed to generate the relay route, which is updated with real-time order pickup requests. Extensive evaluation results with real-world logistics data from 100 delivery stations in 38 cities show that REDE reduces ARODT by up to 8.4% compared to baseline methods. The online A/B tests show that compared to the state-of-the-practice method, REDE improves the delivery courier’s working efficiency and the daily number of pickup orders by 20.13% and 4.51%, respectively.

The popularity of online e-commerce has promoted the rapid development of last-mile logistics in recent years. In last-mile services, to ensure delivery efficiency and enhance user experience, the delivery zone is proposed to perform delivery task assignment, which is a fundamental part of last-mile delivery. Each courier is responsible for one delivery zone. Couriers will collect orders belonging to their delivery zones from the delivery station and deliver orders to customers. Existing delivery zone partition practices in last-mile logistics consist of manual experience-based and static optimization-based methods, which perform order amount balancing among different zone but suffer from dissatisfaction and inefficiency because of two limitations: (i) using order amount is not always a good balancing metric considering deliveries' various difficulties (e.g., residence or industrial park, with or without elevators); (ii) less considering couriers' familiarity and preference behaviors. To generate delivery zone partition with equitable workload assignment, in this paper, we propose E-partition, a data-driven delivery zone partition framework to achieve equitable workload assignment in last-mile logistics. We first design a learning-based workload prediction model to estimate service time given a partition plan that consists of unseen courier-zone matching scenarios. Then, a delivery zone partition algorithm is proposed to iterative optimize couriers' core-AOI (i.e., area of interest) generation and AOI assignment process. Extensive offline experimental results show that our model outperforms baselines in working time prediction and workload balancing performances. Real-world deployment results at JD Logistics also verify the effectiveness of equitable-assignment aware delivery zone partition, with a 2.2% increase in service on-time rate compared to state-of-practice partition solutions.

With the rapid development of sharing economy, we have access to massive sharing systems such as Uber, Airbnb, and bike sharing nowadays. The sharing economy, at its core, is to achieve efficient use of resources. However, the actual usage of shared resources is still unclear to us. Little measurement or analysis, if any, has been conducted to investigate the resource usage patterns with the large-scale data collected from these sharing systems. In this paper, we first analyze the shared bike usage patterns in three typical bike sharing systems based on 140-month multi-event data. From our data-driven analysis, we found that the most used 20% of shared bikes account for 45% of total usage, while the least used 20% of bikes account for less than 1% of usage. To efficiently utilize shared bikes, we propose a usage balancing design called eShare+ to improve the bike sharing systems by considering both the quality of service and bike maintenance, which includes three key components: (i) a statistical model based on archived data to infer historical usage; (ii) an entropy and contextual LSTM-based prediction model with both real-time and archived data to infer future usage; (iii) a model-driven optimal calibration engine for bike selection to dynamically balance usage. We develop an ID swapping-based evaluation methodology to measure the efficiency of eShare+ with data from three large-scale bike sharing systems including 84,000 bikes and 3,300 service stations. Our results show that eShare+ not only fully utilizes shared bikes with efficient maintenance but also improves the quality of service. In addition, eShare+ also has the potential to be applicable to different fleet sizes.

The popularity of e-commerce has promoted the rapid development of the logistics industry in recent years. As an important step in logistics, last-mile delivery from delivery stations to customers' addresses is now mainly finished by couriers, which requires accurate workload assessment based on actual efforts. However, the state-of-the-practice assessment methods neglect a vital factor that orders with the same customer's address (i.e., Homogeneous orders) can be delivered in a group (i.e., in a single trip) or separately (i.e., in multiple trips). It would cause unfair assessment among couriers if following the same rule. Thus, grouping homogeneous order accurately in the workload assessment is significant for achieving fair courier's workload assessment. To this end, we design, implement, and deploy a nationwide homogeneous order grouping system called FHOG for improving the accuracy of homogeneous order grouping in last-mile delivery for fair courier's workload assessment. FHOG utilizes the courier's reporting behavior for order inspection, collection, and delivery to identify homogeneous orders in the delivery station simultaneously for homogeneous order grouping. Compared with the state-of-the-practice method, our evaluation shows FHOG can effectively reduce order amounts with the higher and lower assessed courier's workload. We further deploy FHOG online in 8336 delivery stations to provide homogeneous order grouping service for more than 120 thousand couriers and 12 million daily orders. The results of the two surveys show that the couriers' acceptance rate is improved by 67% with FHOG after the promotion.

Geocoding, associating textual addresses with corresponding GPS coordinates, is vital for many location-based services (e.g., logistics, ridesharing, and social networks). One of the most common Geocoding solutions is using commercial map services (e.g., Google Maps) by uploading textual addresses to obtain corresponding coordinates. However, this is typically not practical for some location-based service providers due to real-world challenges like commercial competition and high costs (recurring fees). In this paper, we design a new cost-effective Geocoding framework to automatically infer the geographic coordinates from textual addresses for service providers. To achieve this, we take the E-Commerce logistics service as a concrete scenario and design CoMiner, an unsupervised coordinate inference framework based on textual address data, delivery event data, and courier trajectory data. There are three main components in CoMiner. (1) A POI-level clustering model by modeling customers' shopping patterns at different spatial granularities; (2) A Delivery Mobility Graph (DMG) by modeling couriers' delivery events and geographic coordinates; (3) A behavior-driven address ranking model by mining couriers' uncertain reporting behaviors to further infer coordinates on DMG. We extensively verify the performance of CoMiner with a three-phase evaluation from data-driven experiments to real-world deployment. (i) We conduct extensive experiments on three large-scale datasets where CoMiner achieves an average accuracy of 95.1%, which outperforms the state-of-the-art methods by 20.3%. (ii) We deploy CoMiner in JD Logistics, inferring coordinates for over 30 million addresses with an average accuracy of 93.3%. (iii) We utilize CoMiner for two Geocoding-based applications, i.e., parcel re-routing optimization and abnormal delivery event detection.

An address, a textual description of a physical location, plays an important role in location-based services such as on-demand delivery and e-commerce. However, abnormal addresses (i.e., an address without detailed information representing a spatial location) have led to significant costs. In real-world settings like e-commerce, abnormal address detection is not trivial because it needs to be completed in real-time to support massive online queries. In this study, we design FastAddr, a fast abnormal address detection framework, which detects abnormal addresses among millions of addresses in a short time. By investigating and modeling the hierarchical structure of address data, we first design a novel contrastive address augmentation approach to generate training data via learning the entity transition probability matrix. We further design a lightweight multi-head attention model for learning compact address representation by modeling the address characteristics. We conduct a comprehensive three-phase evaluation. (i) We evaluate FastAddr on a real-world dataset and it yields the average F1 of 85.7% in 0.058 milliseconds, which outperforms the state-of-the-art models by 47.4% with similar detection time. (ii) An offline A/B test shows that FastAddr outperforms the previous deployed model significantly. (iii) We also conduct an online A/B test to compare FastAddr with the deployed model, which shows an improvement of F1 by more than 20%. Moreover, a real-world case study demonstrates both the efficiency and effectiveness of FastAddr.

We are witnessing a rapid growth of electrified vehicles due to the ever-increasing concerns on urban air quality and energy security. Compared to other types of electric vehicles, electric buses have not yet been prevailingly adopted worldwide due to their high owning and operating costs, long charging time, and the uneven spatial distribution of charging facilities. Moreover, the highly dynamic environment factors such as unpredictable traffic congestion, different passenger demands, and even the changing weather can significantly affect electric bus charging efficiency and potentially hinder the further promotion of large-scale electric bus fleets. To address these issues, in this article, we first analyze a real-world dataset including massive data from 16,359 electric buses, 1,400 bus lines, and 5,562 bus stops. Then, we investigate the electric bus network to understand its operating and charging patterns, and further verify the necessity and feasibility of a real-time charging scheduling. With such understanding, we design busCharging , a pricing-aware real-time charging scheduling system based on Markov Decision Process to reduce the overall charging and operating costs for city-scale electric bus fleets, taking the time-variant electricity pricing into account. To show the effectiveness of busCharging , we implement it with the real-world data from Shenzhen, which includes GPS data of electric buses, the metadata of all bus lines and bus stops, combined with data of 376 charging stations for electric buses. The evaluation results show that busCharging dramatically reduces the charging cost by 23.7% and 12.8% of electricity usage simultaneously. Finally, we design a scheduling-based charging station expansion strategy to verify our busCharging is also effective during the charging station expansion process.

With the rapid development of sharing economy, massive sharing systems such as Uber, Airbnb, and bikeshare have percolated into people's daily life. The sharing economy, at its core, is to achieve efficient use of resources. The actual usage of shared resources, however, is unclear to us. Little measurement or analysis, if any, has been conducted to investigate the resource usage status with the large-scale data collected from these sharing systems. In this paper, we analyze the bike usage status in three typical bikeshare systems based on 140-month multi-event data. Our analysis shows that the most used 20% of bikes account for 45% of usage, while the least used 20% of bikes account for less than 1% of usage. To efficiently utilize shared bikes, we propose a usage balancing design called eShare which has three components: (i) a statistical model based on archived data to infer historical usage; (ii) an entropy-based prediction model based on both real-time and archived data to infer future usage; (iii) a model-driven optimal calibration engine for bike selection to dynamically balance usage. We develop an ID swapping based evaluation methodology and measure the efficiency of eShare with data from three systems including the world's largest bikeshare system with 84,000 bikes and 3,300 stations. Our results show that eShare not only fully utilizes shared bikes but also improves service quality.

Carpooling taxicab services hold the promise of providing additional transportation supply, especially in extreme weather or rush hour when regular taxicab services are insufficient. Although many recommendation systems about regular taxicab services have been proposed recently, little research, if any, has been done to assist passengers to find a successful taxicab ride with carpooling. In this paper, we present the first systematic work to design a unified recommendation system for both regular and carpooling services, called CallCab, based on a data driven approach. In response to a passenger's request, CallCab aims to recommend either (i) a vacant taxicab for a regular service with no detour, or (ii) an occupied taxicab heading to the similar direction for a carpooling service with less detour, yet without assuming any knowledge of destinations of passengers already on occupied taxicabs. To analyze these unknown destinations of occupied taxicabs, CallCab generates and refines taxicab trip distributions based on GPS datasets and context information collected in the existing taxicab infrastructure. To improve CallCab's efficiency to process such a big dataset, we augment the efficient MapReduce model with a Measure phase tailored for our application. We evaluate CallCab with a real world dataset of 14,000 taxicabs, and results show that compared to ground truth, CallCab can reduce 64% of the total mileage to deliver all passengers and 63% of passenger's waiting time.

Identifying hot spots of moving vehicles in an urban area is essential to many smart city applications. The practical research on hot spots in smart city presents many unique features, such as highly mobile environments, supremely limited size of sample objects, and the non-uniform, biased samples. All these features have raised new challenges that make the traditional density-based clustering algorithms fail to capture the real clustering property of objects, making the results less meaningful. In this paper we propose a novel, non-density-based approach called mobility-based clustering. The key idea is that sample objects are employed as "sensors" to perceive the vehicle crowdedness in nearby areas using their instant mobility, rather than the "object representatives". As such the mobility of samples is naturally incorporated. Several key factors beyond the vehicle crowdedness have been identified and techniques to compensate these effects are proposed. We evaluate the performance of mobility-based clustering based on real traffic situations. Experimental results show that using 0.3% of vehicles as the samples, mobility-based clustering can accurately identify hot spots which can hardly be obtained by the latest representative algorithm UMicro.