SWSongyi Wang

Songyi Wang

*This is an algorithmically generated author record based on publicly available information.

Songyi Wang has a total of 23 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    From Disaster Assessment to Route Planning: Multistage Decision Making for Low-Altitude Emergency Logistics with Independent Operation Bases

    by Songyi Wang, Haolin Wen, Delin Meng, Yuhe Shi, Zongjia Zhang, Xing Luo, Lili Yang

    When conventional ground transportation is disrupted, low-altitude transport can provide critical mobility for emergency supply delivery, but effective deployment depends on translating heterogeneous disaster information into timely and executable logistics decisions. Existing studies commonly treat demand quantities and response requirements as predefined inputs and focus on downstream allocation or routing, leaving disaster assessment insufficiently connected to supply assignment and route planning, particularly when transportation units and relief inventories are located at separate sites. This study develops a disaster-informed multistage planning framework for low-altitude emergency logistics with independent operation bases. The framework first establishes a traceable parameter generation approach that integrates multi-source disaster data with emergency response knowledge, translating data-derived severity profiles and LLM-structured response rules into node-specific demand quantities and latest allowable response times. These parameters then support supply facility assignment based on workload balance and spatial relationships, followed by multiobjective transportation unit deployment and pickup and delivery routing under independent operation bases, split deliveries, fleet capacity limits, and differentiated response requirements. An enhanced NSGA-II is developed for the routing problem, while route-level service outcomes are fed back to the allocation stage to coordinate supply assignment and routing decisions. Computational experiments on a multiscale Shenzhen dataset, including baseline comparisons with three established multiobjective algorithms, show that the proposed routing algorithm provides higher-quality and more stable solution sets as the problem scale increases; separate coordination experiments further demonstrate the benefit of routing-informed reassignment. Sensitivity analysis shows that increasing transportation speed reduces average first response time by 38.7%, severity-weighted tardiness by 83.5%, and response time dispersion within severity groups by 66.3%, whereas tighter latest allowable response times substantially increase tardiness. The framework establishes a traceable decision pathway from disaster assessment and response rule interpretation to supply assignment and route planning, enabling heterogeneous emergency information to be translated into implementable low-altitude distribution decisions.

  • Open Access

    A Knowledge-Based Human–LLM Interaction Decision Support System for Logistics Network Modeling and Optimization

    by Songyi Wang, Haolin Wen, Yuhe Shi, Xiao-Sheng Ni, Xing Luo, Lili Yang

    Large language models (LLMs) offer new opportunities for intelligent decision support in logistics network modeling and optimization, yet existing studies mainly treat them as algorithmic assistants, direct optimizers, or end-to-end generators. Less attention has been given to organizing open-ended human–LLM interaction into a reliable decision process for strict constraints, incomplete specifications, and outputs requiring independent verification. This study develops a knowledge-based human–LLM interaction decision support system (K-HLIDSS) for logistics network modeling and optimization, using UAV emergency scheduling as a representative application setting. K-HLIDSS integrates model-element input structuring, knowledge-guided reasoning, and feedback verification to support a traceable and verifiable optimization decision chain. Six experiments combine mechanism-level benchmark validation and application-level case validation, covering structured model prior knowledge, model-element verification, workflow-based algorithm generation and solution execution, multi-stage five-algorithm generation with path-level reverse verification, real-world UAV emergency scheduling, and dynamic new-demand re-dispatching. On Cordeau benchmark instances, the four benchmark experiments show that structured prior knowledge increases model-element accuracy from 79.17% to 99.58%, and model-element verification raises it to 100.00%. Feedback verification increases the valid route output rate from 22.50% to 90.00% and reduces constraint violations from 17.50% to 1.25%. Across 33 instances, verified results selected instance by instance from five generated algorithms yield an average gap of 2.20%. In Shenzhen, China, two case experiments further demonstrate the system's capability for network modeling, route generation, and dynamic re-dispatching under realistic spatial and demand conditions. K-HLIDSS offers a process-level pathway for reliable AI-assisted logistics network optimization. Code and data are available at https://github.com/outhouse1/AI_UAV

  • Version 6.6.1 - AI-KM: Agent skills and ontology-driven knowledge modeling

    by Haolin Wen, Songyi Wang, Bingjie Li, Junfen Xiong, Tong Chen, Xin Liang


  • Open Access

    AI-KM: A distributed multi-view and intelligent knowledge management software

    by Haolin Wen, Songyi Wang, Chaoyu Jiang, Fan Zhang, Jing Li, Xing Luo