246 results about "Logistic management" patented technology

The invention relates to the technical field of logistics management, in particular to an intelligent logistics terminal equipment collaborative management and control system based on AI edge computing, and the system comprises an edge data fusion and state recognition module which is deployed at an edge node, collects multi-source data of an operation state, environment perception, a communication link and the like, and generates an equipment state representation vector through fusion; the intelligent prediction and task scheduling decision module uploads the state vector to a cloud, predicts task completion capability and fault probability, and generates a task scheduling decision packet; the scheduling strategy issuing and edge execution collaboration module issues a scheduling packet through a multi-protocol gateway, and an edge node completes task distribution, communication switching and resource scheduling and caches a key strategy. According to the invention, the real-time sensing of the state of the logistics terminal equipment, the intelligent prediction and resource optimization of task scheduling, and the quick response and fault-tolerant control in a fault scene are realized, and the operation efficiency, the intelligent level and the stability of the system are remarkably improved.

The invention discloses a product logistics management scheduling method based on a block chain, a medium and equipment, and the method comprises the steps: generating an initial transportation path scheme through collecting logistics transportation demand information and supply chain node data; constructing a decentralized logistics resource pool, and collecting and verifying transportation fluctuation parameters to generate a credible state matrix; inputting the initial transportation path scheme and the logistics resource credible state matrix into a graph neural network scheduling model, and outputting a dynamic scheduling scheme; compliance verification of task allocation and scheduling instructions is automatically executed through the smart contract; and finally, updating the scheduling execution result and the logistics resource credible state matrix to a distributed account book, and outputting a logistics management report. Through deep cooperation of the intelligent contract and dynamic path optimization, real-time credible scheduling of the transportation process is realized, the problems of insufficient dynamic response and multi-party cooperation trust deficiency of an existing logistics system are solved, and the reliability and efficiency of cold chain and other sensitive commodity transportation are improved.

The invention relates to the technical field of data analysis, provides a logistics access dynamic management report generation method and system based on an Internet of Things lock, and is used for realizing full-process intelligent generation and optimization of a logistics management report. The method comprises the following steps: acquiring an access event data set of a target logistics area; performing cross-modal feature extraction processing on the access event data set to obtain a dynamic access feature set containing space-time dimension features; based on a preset report type template, inputting the dynamic access feature set into a trained report generation model for multi-task analysis processing, and generating an initial logistics management report set; performing semantic integrity verification and logic conflict detection processing on the initial logistics management report set to generate an optimized target logistics management report; and binding the target logistics management report with an authorized access interface of the user terminal, and performing incremental updating operation on the target logistics management report according to the access event triggered in real time.

The invention discloses a logistics order management system and method, and belongs to the technical field of logistics information management. The method comprises the following steps: step 1, generating a unique digital fingerprint for each logistics order; step 2, performing multi-level security encryption and state synchronization management on order information; 3, constructing a digital twinborn model corresponding to the order, collecting and preprocessing key data in real time and visually displaying the key data in the logistics process, and realizing dynamic monitoring of the whole process; step 4, based on an order state consensus mechanism, automatically matching optimal logistics resources and driving an order processing flow, and generating a verifiable order execution proof chain at the same time; and step 5, performing intelligent analysis and adaptive optimization on the full-life-cycle data of the order, and continuously improving the overall efficiency and precision of logistics management.

The invention relates to the technical field of logistics information management, and discloses a cross-border logistics information management method and system based on a logistics management platform, and the method comprises the steps: carrying out the analysis of a received customer order in a domestic logistics system, and obtaining a labeling parameter set; querying equipment specification information of an overseas logistics system, and converting the labeling parameter set based on the equipment specification information to obtain an overseas execution instruction; the overseas execution instruction is transmitted to overseas warehouse labeling equipment of an overseas logistics system for automatic labeling operation, and labeling process data is obtained; state monitoring is conducted on the labeling process data, a labeling state report is obtained, the labeling state report is transmitted back to the domestic logistics system, and synchronous confirmation information is generated. According to the method, full-process automation and intelligentization of cross-border logistics labeling information coordination processing are realized.

The invention discloses a production and manufacturing management method and system based on digital twinning, which are used in the field of production and manufacturing management, and the method comprises the following steps: collecting logistics management data in logistics storage and operation data of a production line, and constructing a logistics digital twinning processing model; simulating a logistics management process based on a logistics digital twin processing model, and tracking the positions of goods and transportation tools in real time by using a positioning and identification technology; utilizing a demand prediction model to predict a material demand and a product demand based on the data in the logistics digital twinborn model updated in real time, and adjusting the stock of logistics storage according to a prediction result; and calculating an optimal transportation path by using a path optimization algorithm, making a production and manufacturing plan of logistics storage, and monitoring the production and manufacturing process in real time. According to the bidirectional fast random search tree, a new path can be quickly recalculated, and the accuracy and adaptability of decision making are improved by comprehensively considering various transportation and operation constraints.

The invention discloses a production optimization method and system combined with logistics management, and relates to the technical field of production optimization. The invention discloses a production optimization system combined with logistics management. The production optimization system comprises a personalized order analysis module, a logistics state acquisition module, an internal logistics modeling module, an external logistics optimization module, a supply strategy management module, a joint scheduling optimization module, a scheduling execution module and a congestion monitoring and simulation feedback module. According to the invention, an external logistics resource supply strategy is structured and expressed as a transport time window matrix and a dynamic transport capacity allocation table, and the transport time window matrix and the dynamic transport capacity allocation table are used as boundary conditions to be introduced into a joint scheduling optimization model, so that a scheduling system can dynamically adjust a production and logistics collaborative plan according to an external resource state; and the adaptive capacity of the scheduling strategy to external supply changes is effectively enhanced.

The invention discloses a shipping logistics flow direction prediction method and system based on multi-source data fusion, and relates to the field of logistics prediction, and the method comprises the steps: constructing a shipping network diagram based on shipping data; acquiring trajectory data, marine meteorological data, port log data and cargo electronic shipping bill data of a ship automatic identification system in real time; carrying out logistics flow direction prediction on logistics in transportation, obtaining ship data in a future time period, and perfecting a shipping network diagram; carrying out logistics flow direction prediction on the logistics in berthing, and obtaining the remaining loading and unloading amount and the estimated completion time in a future time period; integrating the logistics transportation prediction model and the logistics loading and unloading prediction model, and constructing an end-to-end logistics flow direction prediction model; and correcting the model based on the error between the actual logistics flow direction data and the prediction data. The method has the advantages that the LSTM and Transform models are combined, the shipping logistics flow direction is accurately predicted, the transportation and loading and unloading efficiency is optimized, the prediction precision is improved, and the shipping logistics management efficiency and decision support are improved.

The invention provides an intelligent logistics management system based on a large language model, and relates to the field of intelligent logistics management. According to the method, a low-rank adaptation technology general large language model is adopted in advance for fine tuning, and an external LLM service obtained through fine tuning is innovatively and deeply fused into a task decision process, so that deep understanding of user intentions and accurate analysis of complex environment situations can be realized, and an optimal distribution scheme is autonomously generated based on the deep understanding of the user intentions and the accurate analysis of the complex environment situations. Besides, the urban environment management module, the logistics management scheduling module, the simulation engine module and the large language model interface module included in the system do not work independently, but closely cooperate through an event-driven and message-passing mechanism, so that a complete unmanned aerial vehicle logistics management closed loop from environment perception to decision making and execution to event feedback is formed. The architecture can reflect and control the distribution task of the unmanned aerial vehicle in real time, and carries out self-correction on a set scheme, thereby finally remarkably improving the intelligent level and operation efficiency of logistics management.

The invention relates to the technical field of logistics management and control, and provides a community shared logistics management and control method and system, and the method achieves the precise matching of resources and the intelligent planning of a distribution path through integrating mobile resource data, fixed resource data and environment data, constructing a logistics resource map and a logistics passing network, dynamically monitoring the distribution process, and carrying out the timely adjustment. The operation efficiency and the service quality of community logistics are obviously improved on the whole; specifically, the logistics management and control system can optimize resource configuration, reduce idle and waste of resources, reduce logistics operation cost, effectively deal with the problems of traffic congestion, abnormal traffic events and the like by planning a main path and a standby path in advance and combining real-time environment change to perform path adjustment, shorten logistics distribution time, improve distribution timeliness and improve logistics distribution efficiency. The logistics task distribution process is comprehensively monitored and dynamically adjusted, the stability and reliability of the logistics service are guaranteed, the user satisfaction is enhanced, and the sustainable development of community shared logistics is promoted.

The invention relates to the technical field of warehouse logistics management, in particular to a dynamic picking path optimization method and system based on deep reinforcement learning, and the method comprises the steps: obtaining a picker state vector based on warehouse structured coding data analysis; calculating the movement value density of orders in each channel according to the to-be-processed order queue data and the picker state vector; defining a state space according to the picker state vector and the to-be-processed order queue data; based on the state space and the discrete execution action space, modeling a warehouse order selection problem as a Markov decision process; solving a Markov decision process by using a deep reinforcement learning neural network model based on the real-time state and the moving value density of the picker to obtain an optimal order picking path decision; and controlling a picker to execute picking operation according to the optimal picking path decision. According to the method, the Markov decision process is solved in combination with the deep reinforcement learning neural network model, accurate optimization of the order picking path is realized, and the warehouse order picking efficiency is effectively improved.

The invention belongs to the technical field of logistics management, and particularly relates to a monitoring management system for e-commerce logistics, which comprises a parameter acquisition module, a parameter preprocessing module, a parameter processing module, a dynamic scheduling module, an early warning execution module and a strategy optimization module. On the basis of dynamic matching of delivery urgency, cost coefficient and vehicle bearing capacity, transportation resource allocation is optimized, the no-load rate and resource waste are reduced, and the logistics resource utilization rate is remarkably increased; a three-level early warning mechanism and an elastic scheduling strategy quickly cope with load fluctuation, overload and load reduction / low-load capacity expansion, the logistics delay risk is reduced, and the order performance timeliness is guaranteed; through data-driven priority delivery coefficient calculation and simulation optimization threshold adjustment, manual dependence is reduced, and the scientificity and foresight of scheduling decisions are improved; the strategy optimization module constructs a self-adaptive logistics management system through historical data backtracking and bottleneck diagnosis, a dynamic iteration algorithm model and threshold parameters, and improves industry competitiveness for a long time.

The invention discloses a digital intelligent logistics management system, relates to the technical field of logistics management, and solves the technical problems that multi-source data is difficult to fuse, a spatio-temporal feature joint construction model is lacked to predict time and position space, and a deviation analysis and early warning mechanism is imperfect. Comprising an express multi-source data fusion and real-time tracking module, a logistics space-time prediction and intelligent scheduling module, a logistics prediction deviation analysis and evaluation module and a logistics prediction abnormity early warning and optimization module. Parcel coordinates are collected in real time through RFID, and a multi-source express information database is constructed; fusing the spatial features and the time features to construct an artificial intelligence model to predict transportation time and position coordinates; quantitative indexes of the relative time deviation value and the relative position deviation value are calculated, and a dynamic threshold value is set in combination with service requirements; and finally, constructing a transportation time prediction model and a position coordinate prediction model, and respectively optimizing transportation time probability output and position coordinates.

The invention provides a labor insurance article order dynamic scheduling and inventory management method based on the industrial internet, and relates to the technical field of logistics scheduling, and the method comprises the steps: obtaining the order demand information of each enterprise in an industrial park, and the real-time inventory data and historical delivery records of suppliers, and dynamically constructing a probability density function of the delivery capability of the suppliers, and a gravitation model is combined to calculate the adaptation degree between the supplier and the order demand, so that an accurate order distribution scheme is generated. In this way, order allocation rationality and efficiency can be improved, and order delay and resource waste are reduced. Besides, through an improved isochronous circle division method and a dynamic space-time combination optimization algorithm, clustering analysis and scheduling optimization are performed on the distribution path, so that the timeliness of distribution and the rationality of the path can be remarkably improved, the logistics cost is reduced, and the overall logistics management efficiency of the industrial park is improved.

The invention relates to the technical field of logistics management, and discloses a logistics distribution path intelligent management method and system based on the Internet of Things, and the method comprises the steps: firstly carrying out the static path planning, then collecting the vehicle, cargo, traffic and order data in real time through an Internet of Things sensing layer in the distribution process, and carrying out the real-time management of a logistics distribution path. And dynamically judging whether to trigger path re-planning or not after edge computing node cleaning, fusion and standardization processing. The triggering conditions comprise road section state sudden change, new order insertion and carrying abnormity. Once triggered, the system quickly regenerates a global optimal path by taking the current position of the vehicle as a new starting point and taking the remaining nodes as a new task set. For large-range distribution, a three-level radiation area layered progressive planning mechanism is introduced, layer-by-layer independent planning is carried out, relay is carried out at an actual terminal point, and self-adaption, efficient optimization and reliable execution of a path in a complex environment are achieved.

The invention relates to the technical field of logistics management, in particular to a logistics order transportation management and control system based on digital driving, and the system comprises a data collection module which is used for collecting order data of a logistics order, environment data of an initial path and traffic data, carrying out the preprocessing of the collected data, and carrying out the fusion construction of a basic data set after the processing; and the path evaluation module is used for carrying out trafficability risk evaluation on the initial path based on the basic data set and judging whether to adjust the initial path based on an evaluation result. According to the invention, through cooperative work of the data acquisition module, the path evaluation module and the path planning module, full-process digital management of logistics transportation is realized; by utilizing dynamic path planning and multi-dimensional risk assessment, the influence of extreme weather on logistics transportation is effectively solved, and the transportation timeliness is guaranteed, especially under the conditions of road closing, icing and the like in snowy weather.

The invention relates to the technical field of logistics information management, and discloses a logistics information management platform, which comprises a data acquisition module, a data processing module, a business logic module, an interface adaptation module, a data storage module and an information output module, wherein the data acquisition module acquires logistics related data, the data processing module performs standardization processing on the logistics related data, the business logic module executes a logistics management business process, the interface adaptation module realizes adaptation interaction with an external logistics service system, and the data storage module stores the related data. And the information output module outputs logistics key information. According to the invention, unified management and automatic processing of logistics information are realized, the logistics business processing efficiency and accuracy are improved, the multi-system docking cost is reduced, the business continuity is ensured, and the method is suitable for a cross-regional multi-service provider logistics management scene.

The invention relates to the technical field of logistics management, and particularly discloses a modern medicine logistics management operation system. The method is used for solving the problems of high cost, low utilization rate and difficulty in achieving SLA caused by separation of a box and a path, imperceptible and non-quantifiable temperature control risk, slow border-crossing disposal, insufficient loading stability and difficulty in balancing cost and carbon emission in medicine cold chain distribution. Comprising a customer order management module, a vehicle-mounted monitoring module, a boxing path optimization module, an execution scheduling module, an accounting module and a tracing alarm module. According to the method, an encasement-path integrated optimization system is driven by an equivalent stability index generated by multi-source monitoring, path feasibility and loading feasibility are unified through early warning trigger constraint injection and local recalculation, dynamic rescheduling and linkage accounting, meanwhile, carbon emission, time window, stability and compliance event monetization are merged into a target function, and the load performance is improved. The cooperation of a temperature control early warning closed loop and an encasement path is realized, the cost and carbon emission are reduced, and the SLA achievement rate and the transportation efficiency are improved.

The invention discloses an intelligent bulk commodity freight logistics management method and system, and belongs to the technical field of logistics management, and the method comprises the steps: obtaining the multi-dimensional information of a transportation task, and generating a task semantic tag set; collecting state data and performance behaviors of the transportation units to construct a resource feature vector set; constructing a multi-model scheduling system including transportation risks, node passing trends and loading and unloading waiting prediction, and generating candidate scheduling strategies; performing game optimization on the strategy set in a dynamic environment through a reinforcement learning optimizer, and outputting an optimal scheduling strategy; deploying a continuous monitoring mechanism at edge nodes, and realizing adaptive reconfiguration of paths and resources according to abnormal scores; the intelligent level and the response capability of transportation scheduling can be remarkably improved, the delay risk is reduced, the resource utilization rate is improved, and the method is suitable for a bulk commodity multi-path multi-node combined transportation scene.

The invention discloses an emergency material distribution vehicle scheduling method based on collaborative guarantee, and relates to the technical field of traffic transportation and logistics management, and the method comprises the following steps: uniformly accessing instructions from different platforms into a centralized management scheduling system, and collecting and aggregating scheduling requests and resource information of all departments; and carrying out standardized analysis and preprocessing operation on the obtained scheduling request and resource information, and storing all processed effective scheduling information into a unified data set according to a set data structure so as to support subsequent feature extraction and intelligent analysis. Multi-source scheduling instructions are uniformly accessed and processed in a standardized mode, conflict intelligent identification and dynamic arbitration are achieved in combination with a machine learning model, and repeated resource allocation is avoided; task priority allocation is carried out through an arbitration window mechanism, and the continuity, scheduling stability and cooperation efficiency of emergency material distribution are improved.

The invention relates to the technical field of logistics management, in particular to a dynamic monitoring method and system for logistics waybills, computer equipment and a storage medium. The dynamic monitoring method comprises the steps of obtaining logistics data of a plurality of stages of goods in the whole transportation process, starting to judge the logistics data of the stage after obtaining the logistics data of the first stage, if the logistics data of the stage is consistent with the logistics data set by the system, marking the logistics data of the stage as valid data, and if not, marking the logistics data of the stage as invalid data; and a manual verification program is started. And comparing the logistics data of the next stage. Obtaining comparison results of the four stages in sequence and performing judgment; if the logistics data of the four stages are all valid data, marking the logistics waybill as a real waybill; and if the logistics data of any stage is invalid data, marking the logistics waybill as an abnormal waybill. The authenticity of the transportation task is dynamically monitored by collecting information data of key nodes in the transportation process.

The invention relates to the technical field of logistics management systems, and particularly discloses an artificial intelligence-based supply chain logistics information management system, which comprises a data acquisition module, a demand analysis module, a logistics decision module, a dynamic sensing module and a supply chain monitoring module. Through multi-source data acquisition and standardized preprocessing, the problem of traditional system data is solved, and a foundation is laid for analysis; on the basis of an improved LSTM model and a dynamic threshold value, demands are accurately predicted, risks are early warned, and inventory and stockout losses are reduced; a hybrid algorithm is adopted to collaboratively optimize paths, assess inventory and dynamically adjust environmental interference, and balance logistics efficiency and cost; a toughness index is generated by means of an Attention-LSTM model, and risk quantitative traceability and rapid disposal are realized in combination with hierarchical response and visualization; the modules are in real-time cooperative closed loop, cooperate with parameter self-optimization and threshold updating, adapt to industry and environment changes, and provide stable and intelligent support for supply chain management.

The invention relates to the technical field of logistics management, in particular to an intelligent supervision control system for operation and maintenance of a cold chain system, which comprises the steps of collecting path environment data to screen an operation and maintenance optimal section, then identifying an energy consumption over-limit risk in the section, and executing main-standby switching on equipment with temperature rise exceeding the standard, meanwhile, power supply sufficiency is judged according to load requirements so as to start a redundant power supply, finally, a priority scheduling object is determined according to resource and task urgency by integrating a power supply state and energy consumption data, and a cold chain operation and maintenance centralized supervision control set is generated. According to the method, path selection is optimized by monitoring path environment fluctuation in real time to filter unstable road sections, energy consumption data and load standards are compared to identify and early warn overload risks, equipment switching and power supply scheduling are automatically executed to avoid operation and maintenance interruption when equipment temperature rise is too high or power supply is insufficient, and finally each link is intelligently scheduled through linkage management and control. The system operates stably and efficiently, the energy use efficiency is improved, and the sudden failure influence is reduced.

The invention discloses a production and logistics management method and system based on digital twinning, and the method comprises the steps: obtaining a real-time data flow from a production equipment sensor and a logistics node, carrying out the cleaning and formatting of the real-time data flow through a streaming processing technology, and obtaining a structured real-time data set; aiming at the structured real-time data set, detecting equipment abnormity and order fluctuation by applying a time sequence analysis algorithm; if equipment abnormity or order fluctuation is detected, carrying out real-time simulation on production and logistics links through a pre-established digital twinborn model to obtain a dynamic change trend of event influence; and according to the dynamic change trend, a reinforcement learning algorithm is adopted to optimize and adjust the production scheduling and logistics path, and an optimized production and transportation plan is determined. According to the invention, intelligent cooperation of production and logistics links is realized, abnormal conditions can be quickly responded, scheduling decisions are dynamically optimized, and the overall operation efficiency is improved.

The embodiment of the invention discloses a third-party transport capacity resource scheduling method and device, a storage medium and a server, and relates to the field of logistics management. The method comprises the steps of receiving order attribute data of a customer logistics order; automatically judging whether the order exceeds the service capability of the logistics enterprise according to the order attribute data; if so, screening a conforming carrier from a third-party supplier library according to the order attribute; calculating the transportation cost and the transportation duration of processing the order by each carrier; obtaining personalized transportation cost and transportation duration weight preference of the client according to the unique identity label of the client; calculating a comprehensive service score of each carrier based on the weight; and finally, assigning the order to the third-party carrier with the highest score. According to the method and the device, automatic scheduling of third-party transport capacity resources can be realized, the problem of uncontrollable timeliness and cost caused by low manual decision-making efficiency under the condition that the logistics service capability is limited is effectively solved, and the logistics distribution efficiency and customer satisfaction are remarkably improved.

The invention discloses a general-purpose general cargo wharf typical operation scene stockpiling strategy optimization method, and relates to the technical field of port logistics management, and the method comprises the steps: generating a storage yard global state true phase source data pool through multi-source data perception and fusion processing; carrying out storage yard state entropy calculation and chaos degree quantitative evaluation based on the storage yard global state true phase source data pool to obtain global and partitioned real-time entropy monitoring reports; according to global and partitioned real-time entropy monitoring reports, carrying out adaptive switching decision making to obtain a strategy switching instruction and a new strategy parameter; and according to the strategy switching instruction and the new strategy parameter, carrying out dynamic reconstruction and elastic resource allocation on the virtual stockpiling container to obtain a latest virtual stockpiling container distribution diagram. According to the method, collaborative stockpiling plan generation and operation instruction issuing are performed based on the newest distribution diagram to obtain a plan diagram and an instruction list, decision rules are optimized and updated through closed-loop feedback and entropy learning after execution and monitoring, and self-adaptive optimization of a stockpiling strategy is realized.

The invention discloses a WMS inventory optimization method and system based on digital twinning, and relates to the technical field of warehouse logistics management, and the method comprises the steps: collecting cargo inventory state data, refrigerated transport resource data and seasonal operation progress data from each cold chain warehouse management system, converting the data into different data formats through employing a standardized protocol, and carrying out the optimization of the data formats; the method comprises the following steps: acquiring a real-time inventory data set in a unified format, synchronizing the real-time inventory data set to a central processing node by adopting a distributed database mechanism according to the acquired real-time inventory data set, determining current cargo inventory levels and available refrigerated transport capacities of all cold-chain warehouse nodes, and if the cargo inventory level of a certain cold-chain warehouse node is determined to be lower than a preset threshold value, sending the cold-chain warehouse node to the central processing node; if yes, comparing the cargo inventory level and the transportation capacity available evaluation of adjacent warehouse nodes through an inventory level threshold; according to the WMS inventory optimization method and system based on digital twinning, efficient circulation of cold chain products such as goods is guaranteed.

The invention discloses an intelligent warehouse logistics management system and method based on a mobile robot, and relates to the technical field of warehouse logistics, and the system comprises a warehouse-in management module, a warehouse-out management module, an operation management module, an inventory management module, a report management module, a task management module and a log management module. The warehousing management module comprises an arrival list sub-module, a production plan list sub-module, a red character material warehouse-out sub-module and a manual warehousing list sub-module; the warehouse-out management module comprises a material picking application list sub-module, a delivery list sub-module, a manual warehouse-out list sub-module and a sales order sub-module; and the operation management module comprises a spot receiving operation sub-module, a sampling inspection confirmation sub-module, an inspection submodule, a quality inspection operation sub-module, a warehouse returning operation sub-module, a racking operation sub-module, a goods picking operation sub-module and a warehouse moving operation sub-module. Automatic storage and taking of the robot are achieved, the material carrying accuracy and efficiency are improved, and line side warehouses and three-dimensional warehouses are dynamically managed. And cost reduction and benefit increase of enterprises are realized.

The invention discloses a comprehensive logistics management method and system based on an AI algorithm and big data analysis, and relates to the technical field of intelligent logistics management.The system comprises the steps that sensing terminals are deployed at key nodes of an e-commerce logistics park, and resources, equipment and path data are collected and summarized into a multi-dimensional data set; constructing and training a multilayer neural network model, extracting task scheduling and equipment state features, and realizing scheduling analysis and strategy prediction; calculating a resource scheduling adaptation coefficient and comparing the resource scheduling adaptation coefficient with a threshold value to judge a scheduling state; aGV operation stability is monitored, and a state fluctuation coefficient is calculated; identifying an abnormal operation behavior and calculating an abnormal behavior coefficient; finally, multiple evaluation results are fed back to the AI model, model parameters are dynamically optimized, and the scheduling intelligence and stability of the system are improved.

The invention relates to the technical field of warehouse logistics management and artificial intelligence, in particular to a warehouse logistics dynamic scheduling optimization method and system based on deep learning, and the method comprises the steps: collecting static map data and dynamic sensor data of a warehouse environment; constructing a dynamic space-time diagram state at the current moment; in response to a business logic rule of the warehouse management system, triggering a scheduling optimization process, which comprises the following steps: generating a preliminary scheduling intention set by a constraint reinforcement learning scheduler; predicting to obtain a future space-time congestion thermodynamic diagram through a space-time diagram attention network predictor; quantitative processing is carried out through a self-defined aggregation function, and the future congestion cost of the scalar is determined; correcting the preliminary scheduling intention set by constraining a Lagrange solving framework of a reinforcement learning scheduler, and generating a final scheduling intention; outputting the final scheduling intention to a warehousing control system for execution; according to the method, the problem that decision making and prediction are disjointed in traditional scheduling is solved, and conversion from lagging response to active avoidance is achieved.