CN-122022685-A - Intelligent warehouse management and resource optimization method

CN122022685ACN 122022685 ACN122022685 ACN 122022685ACN-122022685-A

Abstract

The invention discloses an intelligent warehouse management and resource optimization method which comprises the steps of S1, multi-source data acquisition and fusion processing, S2, real-time analysis and dynamic prediction of a warehouse state, S3, intelligent generation and priority scheduling of warehouse tasks, S4, collaborative path planning and resource optimization allocation, S5, task execution monitoring and real-time dynamic re-optimization, S6, task closed-loop analysis and strategy optimization, S7, simulation optimization of warehouse layout and resource configuration. According to the method, the storage data are acquired in real time through the equipment and the sensors of the Internet of things, and the intelligent collaborative optimization of storage resources and operation tasks is realized by combining a dynamic analysis model, and the storage tasks can be automatically generated and adjusted by monitoring the storage state and the equipment operation condition in real time, so that the equipment path and the resource allocation are optimized, and the storage operation efficiency and the resource utilization rate are remarkably improved.

Inventors

NIU LIJUAN
MA ZHEXUAN

Assignees

中环低碳节能技术(北京)有限公司

Dates

Publication Date: 20260512
Application Date: 20260129

Claims (10)

1. The intelligent warehouse management and resource optimization method is characterized by comprising the following steps of: S1, multi-source data acquisition and fusion processing, namely acquiring warehouse environment data, inventory state data, equipment operation data and order stream data in real time through a business data interface of an Internet of things sensor network, RFID read-write equipment and a warehouse management system which are deployed in a warehouse area, preprocessing the data through an edge computing node, denoising and aligning time stamps, and transmitting the data to a central database for standardized storage and fusion to form a unified real-time warehouse digital image; S2, analyzing and dynamically predicting the stock state in real time, namely analyzing the stock state data and the order stream data of each storage area, the stock change rate, the static storage time length and the dynamic turnover rate of each goods in real time based on the integrated stock state data and the order stream data of the central database, and identifying low turnover dead goods, urgent need replenishment goods lower than safety stock and unreasonable distributed scattered goods by comparing the low turnover dead goods with a preset stock threshold model; S3, intelligent generation and priority scheduling of storage tasks, namely dynamically generating a job task set according to the order instruction received in real time, the inventory abnormal condition identified in the step S2 and the flow prediction result, generating task metadata describing the content, the target position, related goods and constraint conditions of each task, comprehensively considering the emergency degree of the order, the goods validity period, potential conflict of a task execution path and the real-time load condition of an equipment resource pool by task generation logic, calculating the dynamic priority score for each task in the task set by adopting a mixed decision mechanism based on rules and weighted scores, and carrying out initial sequencing and scheduling according to the dynamic priority score; s4, collaborative path planning and resource optimization allocation, namely, aiming at the scheduled task set generated in the step S3, taking the highest overall operation efficiency and the lowest overall energy consumption as optimization targets, calling a resource optimization allocation engine; S5, task execution monitoring and real-time dynamic re-optimization, namely issuing the executable operation instruction packet to a corresponding storage equipment control system and personnel terminal, enabling driving equipment and personnel to execute according to the instruction, continuously monitoring the actual position, task progress and storage environment change of equipment through the sensor network in the whole task execution period, feeding actual execution data back to a central database in real time, setting up a dynamic re-optimization trigger, triggering a local or global re-optimization flow immediately when equipment faults, greatly delayed task execution, urgent high priority order insertion or path burst blocking are monitored, and rapidly re-planning and adjusting paths, priorities and resource allocation of subsequent tasks based on the latest system state, and synchronizing the adjusted instruction to affected equipment and personnel in real time.
2. The intelligent warehouse management and resource optimization method according to claim 1, wherein the warehouse environment data comprise real-time temperature and humidity, illumination intensity and safety monitoring video streams of each storage partition, the inventory status data comprise goods identifications, quantity, access time stamps and expected storage periods of each goods location, the equipment operation data comprise real-time position coordinates, working states, battery power and fault alarm information of each AGV trolley, a stacker and a conveying line, and the order stream data comprise warehouse entry orders, warehouse exit orders, inventory instructions and inventory transfer instructions which are received in real time.
3. The intelligent warehouse management and resource optimization method according to claim 2, wherein in the step S2, the specific process of identifying the abnormal inventory condition further comprises automatically generating a cross-regional or cross-warehouse allocation proposal scheme for the identified dead goods in combination with the storage position, commodity attribute and associated predicted demand information, generating a proposal scheme for replenishment to a sorting area or early warning to a purchasing system for the urgent need of replenishment, wherein the generation of the allocation proposal scheme and the replenishment proposal scheme is realized through a lightweight machine learning model, and the lightweight machine learning model uses the historical movement frequency of goods, seasonal factors, associated sales data and the overall inventory distribution of the current warehouse as input characteristics to carry out deduction calculation by using the minimized future expected shortage rate and the overall transportation cost as optimization targets.
4. The intelligent warehouse management and resource optimization method according to claim 1, wherein in the step S3, the dynamic priority score is calculated by assigning a configurable weight coefficient to a plurality of dimensions of order deadline urgency, cargo shelf life urgency, task execution path length, required equipment scarcity, and task contribution to relieving the current warehouse congestion state, and weighting and summing each task after normalizing the scores in each dimension.
5. The intelligent warehouse management and resource optimization method according to claim 4, wherein in the step S4, the resource optimization allocation engine adopts an improved collaborative path planning algorithm integrating time window constraint and dynamic traffic control strategy to plan an optimal job path sequence with no conflict or minimum conflict cost for each available AGV trolley and stacker based on a warehouse digital map, equipment state information and task metadata refreshed in real time, and the improved collaborative path planning algorithm is a multi-agent path planning algorithm combining conflict search and time window optimization, which plans a time-staggered and space-collision-free smooth path for a plurality of mobile equipment by carrying out conflict prediction and resolution on an abstract space-time map.
6. The intelligent warehouse management and resource optimization method according to claim 1, further comprising S6, task closed-loop analysis and strategy optimization, wherein after a single or a batch of tasks are executed, the system automatically collects actual completion time of the tasks, actual energy consumption of equipment, path deviation and operation accuracy data, compares the actual completion time, the actual energy consumption of the equipment, the path deviation and the operation accuracy data with preset reference values or simulation expected values, and carries out self-adaptive adjustment on task priority weight coefficients in the step S3 and path planning in the step S4 based on comparison results.
7. The intelligent warehouse management and resource optimization method according to any one of claims 6, wherein the task closed-loop analysis in step S6 establishes a multi-dimensional performance evaluation model, and the multi-dimensional performance evaluation model includes a time and energy consumption efficiency index, a device utilization balance, and a hot zone task dispersion.
8. The intelligent warehouse management and resource optimization method according to claim 1, wherein in the step S1, the preprocessing performed by the edge computing node further comprises real-time analysis of data from video monitoring, identification of whether personnel enter a dangerous area, whether goods stacking is inclined or not, and immediate sending of an alarm to a central system, and coordinated control of nearby devices to enter a creep or pause state.
9. The intelligent warehouse management and resource optimization method according to claim 8, wherein the edge computing node can independently decide and control the start and stop of intelligent ventilation, air conditioning or dehumidification equipment in the area while uploading data according to temperature and humidity data analyzed in real time.
10. The intelligent warehouse management and resource optimization method according to claim 1, further comprising S7, starting a simulation optimization module of the warehouse layout and resource configuration periodically or according to needs, constructing a digital twin simulation model of warehouse operation based on long-term accumulated historical operation data, equipment fault records and future service growth predictions by the simulation optimization module, and automatically evaluating cost, efficiency and robustness of each scheme by simulating operation effects under different cargo space layout schemes, different equipment configuration numbers and scheduling strategies on the digital twin simulation model, and finally outputting warehouse physical layout adjustment suggestions and key equipment resource configuration optimization schemes.

Description

Intelligent warehouse management and resource optimization method Technical Field The invention relates to the technical field of warehouse management systems, in particular to an intelligent warehouse management and resource optimization method. Background With the rapid development of the logistics industry, the traditional warehouse management method has difficulty in meeting the high-efficiency and accurate operation requirements. In the prior art, the stock management and task scheduling are carried out by relying on manual experience or static rules, so that the problems of low efficiency of warehouse operation, unreasonable resource allocation, low response speed and the like are caused. Especially under the conditions of large order fluctuation and various goods, the conventional method often cannot adjust strategies in real time, and warehouse congestion, stock backlog or equipment idling are easily caused. Although some systems introduce automation equipment, the overall warehouse operation cost is still high due to the lack of global coordination and dynamic optimization capability, and the flexibility and complexity requirements of modern logistics are difficult to adapt. Disclosure of Invention Therefore, the invention provides the intelligent warehouse management and resource optimization method to solve the problems that the overall warehouse operation cost is still high and the flexibility and complexity requirements of modern logistics are difficult to adapt due to the lack of global cooperation and dynamic optimization capability in the prior art. In order to achieve the above object, the present invention provides the following technical solutions: The intelligent warehouse management and resource optimization method comprises the following steps: S1, multi-source data acquisition and fusion processing, namely acquiring warehouse environment data, inventory state data, equipment operation data and order stream data in real time through a business data interface of an Internet of things sensor network, RFID read-write equipment and a warehouse management system which are deployed in a warehouse area, preprocessing the data through an edge computing node, denoising and aligning time stamps, and transmitting the data to a central database for standardized storage and fusion to form a unified real-time warehouse digital image; S2, analyzing and dynamically predicting the stock state in real time, namely analyzing the stock state data and the order stream data of each storage area, the stock change rate, the static storage time length and the dynamic turnover rate of each goods in real time based on the integrated stock state data and the order stream data of the central database, and identifying low turnover dead goods, urgent need replenishment goods lower than safety stock and unreasonable distributed scattered goods by comparing the low turnover dead goods with a preset stock threshold model; S3, intelligent generation and priority scheduling of storage tasks, namely dynamically generating a job task set according to the order instruction received in real time, the inventory abnormal condition identified in the step S2 and the flow prediction result, generating task metadata describing the content, the target position, related goods and constraint conditions of each task, comprehensively considering the emergency degree of the order, the goods validity period, potential conflict of a task execution path and the real-time load condition of an equipment resource pool by task generation logic, calculating the dynamic priority score for each task in the task set by adopting a mixed decision mechanism based on rules and weighted scores, and carrying out initial sequencing and scheduling according to the dynamic priority score; s4, collaborative path planning and resource optimization allocation, namely, aiming at the scheduled task set generated in the step S3, taking the highest overall operation efficiency and the lowest overall energy consumption as optimization targets, calling a resource optimization allocation engine; S5, task execution monitoring and real-time dynamic re-optimization, namely issuing the executable operation instruction packet to a corresponding storage equipment control system and personnel terminal, enabling driving equipment and personnel to execute according to the instruction, continuously monitoring the actual position, task progress and storage environment change of equipment through the sensor network in the whole task execution period, feeding actual execution data back to a central database in real time, setting up a dynamic re-optimization trigger, triggering a local or global re-optimization flow immediately when equipment faults, greatly delayed task execution, urgent high priority order insertion or path burst blocking are monitored, and rapidly re-planning and adjusting paths, priorities and resource allocation of subsequent tasks based on the latest system