CN119204954A - An AI-based smart logistics management system - Google Patents

An AI-based smart logistics management system Download PDF

Info

Publication number
CN119204954A
CN119204954A CN202411673591.9A CN202411673591A CN119204954A CN 119204954 A CN119204954 A CN 119204954A CN 202411673591 A CN202411673591 A CN 202411673591A CN 119204954 A CN119204954 A CN 119204954A
Authority
CN
China
Prior art keywords
module
warehouse
data
management
inventory
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202411673591.9A
Other languages
Chinese (zh)
Inventor
吴浠蓥
吴燕燕
吴琳炜
吴团结
吴伟鸿
吴晶怡
吴振霖
吴潇洋
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Jinjiang New Jianxing Machinery Equipment Co ltd
Original Assignee
Jinjiang New Jianxing Machinery Equipment Co ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Jinjiang New Jianxing Machinery Equipment Co ltd filed Critical Jinjiang New Jianxing Machinery Equipment Co ltd
Priority to CN202411673591.9A priority Critical patent/CN119204954A/en
Publication of CN119204954A publication Critical patent/CN119204954A/en
Pending legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/08—Logistics, e.g. warehousing, loading or distribution; Inventory or stock management
    • G06Q10/087—Inventory or stock management, e.g. order filling, procurement or balancing against orders
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/27—Regression, e.g. linear or logistic regression
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N20/00—Machine learning
    • G06N20/10—Machine learning using kernel methods, e.g. support vector machines [SVM]
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
    • G06Q10/06315—Needs-based resource requirements planning or analysis
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0635—Risk analysis of enterprise or organisation activities
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/10—Office automation; Time management
    • G06Q10/103—Workflow collaboration or project management
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2123/00—Data types
    • G06F2123/02—Data types in the time domain, e.g. time-series data

Landscapes

  • Business, Economics & Management (AREA)
  • Engineering & Computer Science (AREA)
  • Human Resources & Organizations (AREA)
  • Strategic Management (AREA)
  • Economics (AREA)
  • Theoretical Computer Science (AREA)
  • Entrepreneurship & Innovation (AREA)
  • General Physics & Mathematics (AREA)
  • Physics & Mathematics (AREA)
  • Tourism & Hospitality (AREA)
  • General Business, Economics & Management (AREA)
  • Marketing (AREA)
  • Quality & Reliability (AREA)
  • Operations Research (AREA)
  • Development Economics (AREA)
  • Data Mining & Analysis (AREA)
  • Game Theory and Decision Science (AREA)
  • General Engineering & Computer Science (AREA)
  • Software Systems (AREA)
  • Educational Administration (AREA)
  • Evolutionary Computation (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Artificial Intelligence (AREA)
  • Computing Systems (AREA)
  • Evolutionary Biology (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Mathematical Physics (AREA)
  • Medical Informatics (AREA)
  • Accounting & Taxation (AREA)
  • Finance (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

本申请公开了一种基于AI的智慧物流管理系统，涉及智慧物流管理技术领域，包括：仓储管理单元、数据融合采集单元和数字孪生监管单元；仓储管理单元用于对仓库的出入库信息、货物信息进行管理和库存风险提醒，以及进行需求预测和库存优化；数据融合采集单元用于采集仓库的人员、货物、设备和环境信息；数字孪生监管单元包括智能AI识别单元和数据分析处理单元，智能AI识别单元用于通过AI智能算法对仓库的人员、货物、设备和环境进行识别分析及风险提醒，数据分析处理单元用于将实体仓库的数据映射至数字孪生仓库，并对数字孪生仓库进行可视化交互管理及人员、货物和设备的智能调度，本申请使得仓库全面可监控，提高了货物存放与管理的效率。

The present application discloses an AI-based smart logistics management system, which relates to the technical field of smart logistics management, and includes: a warehouse management unit, a data fusion collection unit, and a digital twin supervision unit; the warehouse management unit is used to manage the warehouse's in-and-out information, cargo information, inventory risk reminders, and demand forecasting and inventory optimization; the data fusion collection unit is used to collect warehouse personnel, cargo, equipment, and environmental information; the digital twin supervision unit includes an intelligent AI recognition unit and a data analysis and processing unit, the intelligent AI recognition unit is used to identify and analyze the warehouse's personnel, cargo, equipment, and environment through AI intelligent algorithms, and to provide risk reminders; the data analysis and processing unit is used to map the data of the physical warehouse to the digital twin warehouse, and to perform visual interactive management of the digital twin warehouse and intelligent scheduling of personnel, cargo, and equipment. The present application makes the warehouse fully monitorable and improves the efficiency of cargo storage and management.

Description

Intelligent logistics management system based on AI
Technical Field
The application relates to the technical field of intelligent logistics management, in particular to an AI-based intelligent logistics management system.
Background
Along with the rapid development of information technology, the warehouse logistics industry gradually realizes informatization. The traditional warehouse construction and management inertia ensures that enterprises rely on a large amount of manual work to carry out operations such as scheduling, inspection, recording, loading, unloading and carrying, and the like, the corresponding information system construction also only adopts a traditional management mode, and the TMS transportation management system, the CRM customer relationship management system, the WMS warehouse management system and other information systems are in closed operation, so that data analysis and data operation cannot be provided for fine management. The management requirements and management modes are not matched, so that running problems and risks of some businesses are caused. The scheduling efficiency of resources such as people, equipment and the like is lower.
Disclosure of Invention
In view of the above, the application provides an AI-based intelligent logistics management system, which performs preprocessing analysis on warehouse data by using a digital twin supervision mode and an AI-aided analysis method, so that the problem that the traditional management mode can not provide data analysis and data operation for fine management is solved. The management requirements and management modes are not matched, so that running problems and risks of some businesses are caused. The technical problem that the scheduling efficiency of resources such as people, equipment and the like is low is solved.
In order to achieve the above purpose, the present invention provides the following technical solutions:
An AI-based intelligent logistics management system comprises a warehouse management unit, a data fusion acquisition unit and a digital twin supervision unit;
The warehouse management unit is used for managing warehouse in-out information and cargo information of the warehouse, reminding inventory risk, forecasting demand and optimizing inventory, and uploading the cargo information, the warehouse in-out information and the inventory information to the digital twin supervision unit;
the data fusion acquisition unit is used for acquiring personnel, goods, equipment and environmental information of the warehouse through a deployed data acquisition network and uploading the acquired information to the digital twin supervision unit;
The digital twin supervision unit comprises an intelligent AI identification unit and a data analysis processing unit, wherein the intelligent AI identification unit is used for carrying out identification analysis and risk reminding on personnel, goods, equipment and environments of the warehouse through an AI intelligent algorithm, and the data analysis processing unit is used for mapping data of the entity warehouse to the digital twin warehouse and carrying out visual interaction management and intelligent scheduling on the digital twin warehouse.
Further, the warehouse management unit comprises an warehouse entry management module, a goods management module and an inventory risk calculation module;
The warehouse-in and warehouse-out management module comprises an equipment management module and a service management module, wherein the equipment management module is used for carrying out real-time association management on state parameters and operation information of the warehouse-in and warehouse-out equipment and a job task, and the service management module is used for generating the warehouse-in and warehouse-out task according to the goods warehouse-in and warehouse-out requirements input by a user and matching corresponding carrying equipment and carrying paths according to the warehouse-in and warehouse-out task;
The goods management module comprises a data list module, a data updating module and a quality detection management module, wherein the data list module is used for recording inventory data of warehouse goods according to the logistics parameter list, establishing a multi-level product classification model according to the goods management list, managing goods position distribution, types, storage time and storage environment of the warehouse goods according to the multi-level product classification model, updating the recorded data of the list according to the data acquired by the data fusion acquisition unit, and the quality detection management module is used for recording and marking the damage condition and quality qualification standard of the surface of the warehouse goods and screening damaged goods;
The inventory risk calculation module is used for calculating the inventory quantity of the warehouse, comparing the calculation result with a preset risk threshold value and further outputting a risk grade value.
Further, the inventory risk calculation module comprises an inventory calculation module and a risk level matching module;
The inventory calculation module is used for adding the current inventory value and the goods value to be put in storage to obtain an in-stock value, subtracting the in-stock value from the out-of-storage goods value to obtain a new inventory value, comparing the new inventory value with each risk threshold value, and obtaining a risk grade value according to the comparison result;
the risk level matching module is used for judging the risk level to which the risk level matching module belongs according to the obtained risk level value, and highlighting and voice reminding are carried out on the manager according to the risk level.
Further, the warehouse management unit also comprises a prediction optimization module, wherein the prediction optimization module comprises a demand prediction module and an inventory optimization module;
The demand prediction module is used for classifying logistics demands by adopting a clustering algorithm, modeling logistics demand time sequences and historical data of different categories by adopting a time sequence model respectively, training an SVM model, carrying out nonlinear regression prediction on the logistics demands by using the trained SVM model to obtain prediction data of the logistics demands, determining a kernel function and parameters when training the SVM model, and optimizing parameters of RBF kernel functions in the SVM model by adopting a firefly algorithm;
The inventory optimization module is used for determining optimal ordering batches according to ordering cost and holding cost, setting maximum and minimum inventory levels according to logistics demand prediction and safety inventory, adjusting the inventory levels based on real-time demand data, and adjusting an inventory plan according to updated demand prediction.
Further, the data fusion acquisition unit comprises a data acquisition device and a data fusion processing module, the data acquisition device comprises a camera module, a sensor module, a UWB label and a 5G communication module, the camera module is used for acquiring image data information of people and equipment, the UWB label is used for acquiring motion track and position information of people, the sensor module is used for acquiring temperature and humidity change information, gas change information and fire information of warehouse area environment and speed, working time and pressure change information of each equipment, the camera module and the sensor module are all connected with the 5G communication module, and the 5G communication module is used for uploading processing data to the digital twin supervision unit through a 5G wireless network.
Further, the intelligent AI identification unit comprises a personnel safety identification module, a transportation equipment speed identification module, an environment safety identification module and a risk reminding module;
The personnel safety identification module is used for judging whether an operator stays in a dangerous area or not according to personnel positioning information acquired by the UWB tag and the divided coordinate information of each area of the warehouse, and judging that the stay condition and dangerous operation exist when the personnel positioning information exceeds 1min in a preset dangerous area;
the transportation equipment speed identification module is used for acquiring the current operation speed of the corresponding equipment according to the acquired equipment operation data, comparing the current operation speed with a preset safety speed threshold value, and judging whether overspeed or fault shutdown conditions of the transportation equipment occur according to the comparison result;
the environment safety recognition module is used for detecting environment parameters according to an AI environment recognition algorithm, extracting flame and smoke video features according to the collected video information, and recognizing the flame and the smoke based on the video features;
The risk reminding module is connected with the personnel safety recognition module, the transportation equipment speed recognition module and the environment safety recognition module, and carries out risk alarm on the abnormal recognition result in an audible and visual reminding mode and a highlighting mode according to the obtained recognition result.
Further, the data analysis processing unit comprises a modeling module, a data mapping module and a visual management module;
The modeling module is used for acquiring the coordinate and size information of the building space in the warehouse and the physical elements of equipment in the warehouse, establishing a static model and a dynamic model, and forming a digital twin warehouse model based on the established static model, dynamic model and digital model;
The data mapping module is used for mapping the acquired physical data information to an established digital model to drive a digital twin warehouse model, monitoring temperature and humidity, pressure data, equipment running state, personnel running track and abnormal conditions in the warehouse, monitoring cargo conditions and production requirements in the warehouse in real time through the digital twin warehouse model, and carrying out intelligent scheduling of personnel and equipment and distribution of the cargo according to the production requirements;
The visual management module is used for visually displaying and managing warehouse monitoring data and alarm data through a user-friendly visual management interface.
The data analysis processing unit further comprises a data sharing module, wherein the data sharing module is used for constructing a warehouse logistics data resource pool and sharing data in the warehouse logistics data resource pool with a third party system.
From the above technical solution, the advantages of the present invention are:
1. according to the application, intelligent demand prediction and inventory optimization are performed through the warehouse management unit, the warehouse goods delivery and warehouse operation is managed in real time, the goods storage and management efficiency is improved, the comprehensive monitoring of warehouse data is realized through the data fusion acquisition unit, the remote monitoring function is realized through the 5G communication network, finally, the acquired and uploaded warehouse and goods data are subjected to data analysis and intelligent AI identification through the digital twin supervision unit, the purpose of monitoring the environment, equipment, personnel and goods conditions and production demands of the warehouse in real time through the digital twin warehouse model is realized, and the intelligent scheduling of personnel and equipment and the distribution of goods are performed according to the production demands, so that the management mode is more reasonable, the risk is smaller, and the resource scheduling efficiency is higher.
2. The application provides services for connectivity and visibility of a logistics enterprise network through technologies such as video technology, big data, artificial intelligence and the like, realizes fine and intelligent management of warehouse logistics, enables the warehouse to be comprehensively monitored, improves the efficiency of goods storage and management, realizes migration of physical entities to virtual warehouse through digital twin technology, promotes informatization, intelligentization and intelligent development of logistics warehouse and improves the resource integration efficiency.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this specification, illustrate embodiments of the application and together with the description serve to explain the application.
Fig. 1 is a schematic structural view of the present application.
Fig. 2 is a schematic structural diagram of a warehouse management unit according to the present application.
Fig. 3 is a schematic structural diagram of the intelligent AI-recognition unit of the present application.
Fig. 4 is a schematic structural diagram of a data analysis processing unit according to the present application.
Detailed Description
The present application will be described in further detail with reference to the following embodiments and the accompanying drawings, in order to make the objects, technical solutions and advantages of the present application more apparent. The exemplary embodiments of the present application and the descriptions thereof are used herein to explain the present application, but are not intended to limit the application.
The intelligent warehouse carries out intelligent improvement and supervision on warehouse equipment management and cargo management processes through AI prediction recognition and digital twin information technology means, and the scheduling level of supply chains and business links is improved. The development trend of intelligent storage gradually develops from automation to high-flexibility automation, digitalization, transparentization, predictability, intellectualization and the like.
Referring to fig. 1 to 4, as shown in fig. 1, the present embodiment provides an AI-based intelligent logistics management system, which is a highly integrated and automated system for monitoring, analyzing and managing the operation conditions of a warehouse logistics system in real time, and specifically includes a warehouse management unit, a data fusion acquisition unit and a digital twin supervision unit. The warehouse management unit is used for managing warehouse in-out information and cargo information of the warehouse, reminding inventory risk, forecasting demand and optimizing inventory, and uploading the cargo information, the warehouse in-out information and the inventory information to the digital twin supervision unit. The digital twin supervision unit comprises an intelligent AI identification unit and a data analysis processing unit, wherein the intelligent AI identification unit is used for carrying out identification analysis and risk reminding on personnel, goods, equipment and environments of the warehouse through an AI intelligent algorithm, and the data analysis processing unit is used for mapping data of the entity warehouse to the digital twin warehouse and carrying out visual interaction management and intelligent scheduling on the digital twin warehouse.
The warehouse management unit comprises an warehouse management module, a goods management module and an inventory risk calculation module, wherein the warehouse management module comprises an equipment management module and a service management module, the equipment management module is used for carrying out real-time association management on state parameters, running information and operation tasks of the warehouse equipment, the service management module is used for generating the warehouse task according to the goods warehouse-in and warehouse-out requirements input by a user and matching corresponding carrying equipment and carrying paths according to the warehouse-in and warehouse-out tasks, the goods management module comprises a data list module, a data updating module and a quality detection management module, the data list module is used for recording inventory data of warehouse goods according to a logistics parameter list, establishing a multi-level product classification model according to the commodity management list, managing the distribution, types, storage time and storage environments of the warehouse goods according to the multi-level product classification model, the data updating module is used for updating recorded data of the list according to the data acquired by the data fusion acquisition unit, the quality detection management module is used for recording and marking the surface damage condition and quality qualification standard of the warehouse goods and screening the damaged goods, the inventory risk calculation module is used for calculating the inventory quantity of the warehouse and comparing the calculation result with a preset risk grade value.
The inventory risk calculation module is used for adding the current inventory value and the goods value to be put in storage to obtain an in-inventory value, subtracting the in-inventory value from the out-of-stock goods value to obtain a new inventory value, comparing the new inventory value with each risk threshold value to obtain a risk grade value according to a comparison result, and judging the risk grade to which the risk grade value belongs according to the obtained risk grade value by the risk grade matching module, and highlighting and reminding a manager according to the risk grade.
The warehouse management unit further comprises a prediction optimization module, wherein the prediction optimization module comprises a demand prediction module and an inventory optimization module, the demand prediction module is used for classifying logistics demands by adopting a clustering algorithm, modeling logistics demand time sequences and historical data of different categories by adopting a time sequence model respectively, training an SVM model, carrying out nonlinear regression prediction on the logistics demands by utilizing the trained SVM model to obtain prediction data of the logistics demands, determining a kernel function and parameters when training the SVM model, optimizing the parameters of the RBF kernel function in the SVM model by adopting a firefly algorithm, and the inventory optimization module is used for determining optimal ordering batches according to ordering cost and holding cost, setting maximum and minimum inventory levels according to logistics demand prediction and safety inventory, adjusting the inventory levels based on real-time demand data and adjusting an inventory plan according to updated demand prediction. In training the SVM model, historical logistic demand data needs to be collected, including characteristics of predicted time points (e.g., activity, seasons, holidays, etc.), the data set is divided into a training set and a test set (or validation set), and radial basis functions RBF are selected to deal with nonlinear relationships. The model is trained using training data and target stream demand values, and performance of the model is assessed using a test set, common assessment metrics including Mean Square Error (MSE), root Mean Square Error (RMSE), and the like. And finally, inputting the characteristic data into a trained SVM model to obtain a predicted logistics requirement value.
The data fusion acquisition unit is used for acquiring personnel, goods, equipment and environmental information of the warehouse through a deployed data acquisition network and uploading the acquired information to the digital twin supervision unit.
The data fusion acquisition unit comprises a data acquisition device and a data fusion processing module, the data acquisition device comprises a camera module, a sensor module, a UWB label and a 5G communication module, the camera module is used for acquiring image data information of people and equipment, the UWB label is used for acquiring motion trail and position information of the people, the sensor module is used for acquiring temperature and humidity change information, gas change information and fire information of warehouse area environment and speed, working time and pressure change information of each equipment, the camera module and the sensor module are all connected with the 5G communication module, the 5G communication module is used for uploading processing data to the digital twin supervision unit through a 5G wireless network, and the data fusion processing module is used for cleaning, screening and standardized processing of the acquired data.
The data in the system is divided into service monitoring data and control monitoring data, wherein the service monitoring data comprises decision analysis, data management, plan management, warehouse management and cost management data, and the data acquired by the bottom layer equipment are cleaned and arranged to form data with a standard data structure and are uploaded to a digital twin supervision unit through a data interface. The control monitoring data comprise intelligent scheduling, fault early warning, abnormal early warning, state monitoring, preventive maintenance and temperature and humidity control data, are collected through intelligent sensing equipment, comprise but are not limited to operation parameters, temperature and humidity parameters, technical standard parameters, control threshold values and the like of the equipment, are converted into a standardized data structure through preprocessing of the intelligent sensing equipment, and are uploaded to a digital twin supervision unit.
In the embodiment, the intelligent AI recognition unit comprises a personnel safety recognition module, a transportation equipment speed recognition module, an environment safety recognition module and a risk reminding module, wherein the personnel safety recognition module is used for judging whether an operator stays in a dangerous area according to personnel positioning information acquired by a UWB (ultra-wideband) tag and coordinate information of each area of a divided warehouse, judging that the operator stays in the dangerous area and dangerous operation exists when the personnel positioning information exceeds 1min in the preset dangerous area, analyzing the personnel position and the track is used for calculating the distance between the person and each base station according to signals of indoor base stations acquired by the UWB positioning tag, and carrying out positioning calculation on the person according to the distance between the person and each base station. The transportation equipment speed recognition module is used for acquiring the current operation speed of corresponding equipment according to the acquired equipment operation data, comparing the current operation speed with a preset safety speed threshold value, judging whether the transportation equipment has overspeed or fault outage conditions according to comparison results, the environment safety recognition module is used for detecting environment parameters according to an AI environment recognition algorithm, extracting flame and smoke video features according to acquired video information and recognizing the flame and the smoke based on the video features, and the risk reminding module is connected with the personnel safety recognition module, the transportation equipment speed recognition module and the environment safety recognition module and used for carrying out risk alarm on abnormal recognition results according to the acquired recognition results in an acousto-optic reminding mode and a highlighting mode.
The data analysis processing unit comprises a modeling module, a data mapping module and a visual management module, wherein the modeling module is used for acquiring the coordinate and size information of a building space in a warehouse and the physical elements of equipment in the warehouse, establishing a static model and a dynamic model, forming a digital twin warehouse model based on the established static model, the dynamic model and the digital model, the data mapping module is used for mapping the acquired physical data information to the established digital model to drive the digital twin warehouse model, monitoring the temperature and humidity, pressure data, equipment running state, personnel running track and abnormal conditions in the warehouse and monitoring the goods condition and production requirements in the warehouse in real time through the digital twin warehouse model, and carrying out intelligent scheduling of personnel and equipment and distribution of goods according to the production requirements, and the visual management module is used for carrying out visual display and management on warehouse monitoring data and alarm data through a user-friendly visual management interface.
The digital twin warehouse model is to collect data in the actual warehouse process, such as cargo information, warehouse equipment information, environment information, etc., and convert the data into a digital model. The digital twin warehouse model can truly reflect the actual warehouse situation and can be subjected to various analyses and optimizations. And processing the acquired data, manufacturing a digital twin model of workshop environment, equipment, personnel and key equipment nodes by using graphic software, endowing the corresponding digital twin model with the same data information as the physical entity, and realizing that the information of the shape, structure, parameters, spatial position and the like represented by the digital twin is consistent with the physical entity. Meanwhile, a mapping relation between the digital twin body and the physical entity is established, the digital twin body is driven to generate a physical entity synchronous action, and the physical entity synchronous action is truly restored to the logistics storage reality operation scene.
The data analysis processing unit also comprises a data sharing module, wherein the data sharing module is used for constructing a warehouse logistics data resource pool and sharing the data in the warehouse logistics data resource pool with a third party system.
The above description is only of the preferred embodiments of the present application and is not intended to limit the present application, and various modifications and variations can be made to the embodiments of the present application by those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the protection scope of the present application.

Claims (8)

1.一种基于AI的智慧物流管理系统，其特征在于，包括：仓储管理单元、数据融合采集单元和数字孪生监管单元；1. An AI-based intelligent logistics management system, characterized by comprising: a warehouse management unit, a data fusion collection unit and a digital twin supervision unit; 所述仓储管理单元用于对仓库的出入库信息、货物信息进行管理和库存风险提醒，以及进行需求预测和库存优化，并将货物信息、出入库和库存信息上传至所述数字孪生监管单元；The warehouse management unit is used to manage the warehouse's in-and-out information, cargo information, and inventory risk reminders, as well as to perform demand forecasting and inventory optimization, and upload cargo information, in-and-out information, and inventory information to the digital twin supervision unit; 所述数据融合采集单元用于通过部署的数据采集网络采集仓库的人员、货物、设备和环境信息，并将采集信息上传至所述数字孪生监管单元；The data fusion acquisition unit is used to collect personnel, goods, equipment and environmental information of the warehouse through the deployed data acquisition network, and upload the collected information to the digital twin supervision unit; 所述数字孪生监管单元包括智能AI识别单元和数据分析处理单元，所述智能AI识别单元用于通过AI智能算法对仓库的人员、货物、设备和环境进行识别分析及风险提醒，所述数据分析处理单元用于将实体仓库的数据映射至数字孪生仓库，并对数字孪生仓库进行可视化交互管理及人员、货物和设备的智能调度。The digital twin supervision unit includes an intelligent AI recognition unit and a data analysis and processing unit. The intelligent AI recognition unit is used to identify and analyze the personnel, goods, equipment and environment of the warehouse and provide risk reminders through AI intelligent algorithms. The data analysis and processing unit is used to map the data of the physical warehouse to the digital twin warehouse, and perform visual interactive management of the digital twin warehouse and intelligent scheduling of personnel, goods and equipment. 2.根据权利要求1所述的基于AI的智慧物流管理系统，其特征在于，所述仓储管理单元包括出入库管理模块、货物管理模块和库存风险计算模块；2. The AI-based smart logistics management system according to claim 1, characterized in that the warehouse management unit includes a warehouse entry and exit management module, a cargo management module and an inventory risk calculation module; 所述出入库管理模块包括设备管理模块和业务管理模块，所述设备管理模块用于对出入库设备的状态参数和运行信息与作业任务进行实时关联管理，所述业务管理模块用于根据用户输入的货物出入库需求，生成出入库任务，并根据出入库任务匹配对应的运载设备和运载路径；The in-and-out management module includes an equipment management module and a business management module. The equipment management module is used to manage the state parameters and operation information of the in-and-out equipment in real time in association with the operation tasks. The business management module is used to generate in-and-out tasks according to the goods in-and-out requirements input by the user, and match the corresponding transport equipment and transport path according to the in-and-out tasks. 所述货物管理模块包括数据列表模块、数据更新模块和质量检测管理模块，所述数据列表模块用于根据物流参数列表对仓库货物的盘点数据进行记录，并根据商品管理列表建立多层次的产品分类模型，根据多层次的产品分类模型对仓储货物的货位分布、种类、储存时间和储存环境进行管理，所述数据更新模块用于根据所述数据融合采集单元采集的数据对列表的记录数据进行更新，所述质量检测管理模块用于对入库的货品进行表面的破损情况、质量合格标准进行记录和标记，并筛选破损货品；The goods management module includes a data list module, a data update module and a quality inspection management module. The data list module is used to record the inventory data of the warehouse goods according to the logistics parameter list, and establish a multi-level product classification model according to the commodity management list, and manage the storage location distribution, type, storage time and storage environment of the warehoused goods according to the multi-level product classification model. The data update module is used to update the recorded data of the list according to the data collected by the data fusion acquisition unit. The quality inspection management module is used to record and mark the surface damage and quality standards of the goods entering the warehouse, and screen the damaged goods; 所述库存风险计算模块用于计算仓库的库存数量，并将计算结果与预设的风险阈值进行比较，进而输出风险等级值。The inventory risk calculation module is used to calculate the inventory quantity of the warehouse, compare the calculation result with the preset risk threshold, and then output the risk level value. 3.根据权利要求2所述的基于AI的智慧物流管理系统，其特征在于，所述库存风险计算模块包括库存计算模块和风险等级匹配模块；3. The AI-based smart logistics management system according to claim 2, characterized in that the inventory risk calculation module includes an inventory calculation module and a risk level matching module; 所述库存计算模块用于将当前的库存值与待入库货物值相加，得到入库存量值，将所述入库存量值与出库货物值相减，得到新的库存值，将所述新的库存值与各风险阈值进行比较，根据比较结果得到风险等级值；The inventory calculation module is used to add the current inventory value to the value of goods to be received to obtain the incoming inventory value, subtract the incoming inventory value from the outgoing goods value to obtain a new inventory value, compare the new inventory value with each risk threshold, and obtain a risk level value according to the comparison result; 所述风险等级匹配模块用于根据得到的风险等级值判断其所属的风险等级，根据风险等级对管理人员进行高亮显示及语音提醒。The risk level matching module is used to determine the risk level to which it belongs according to the obtained risk level value, and to highlight and voice remind the management personnel according to the risk level. 4.根据权利要求2所述的基于AI的智慧物流管理系统，其特征在于，所述仓储管理单元还包括预测优化模块，所述预测优化模块包括需求预测模块和库存优化模块；4. The AI-based smart logistics management system according to claim 2, characterized in that the warehouse management unit further comprises a forecasting optimization module, and the forecasting optimization module comprises a demand forecasting module and an inventory optimization module; 所述需求预测模块用于采用聚类算法对物流需求进行分类，将不同类别的物流需求时间序列和历史数据分别采用时间序列模型进行建模，并训练SVM模型，利用训练好的SVM模型对物流需求进行非线性回归预测，得到物流需求的预测数据，训练SVM模型时确定核函数及参数，采用萤火虫算法对SVM模型中RBF核函数的参数进行优化；The demand forecasting module is used to classify logistics demand by using a clustering algorithm, model different categories of logistics demand time series and historical data by using a time series model, and train an SVM model. The trained SVM model is used to perform nonlinear regression forecasting on the logistics demand to obtain forecast data of the logistics demand. The kernel function and parameters are determined when training the SVM model, and the firefly algorithm is used to optimize the parameters of the RBF kernel function in the SVM model. 所述库存优化模块用于根据订货成本和持有成本，确定最优订货批量，以及根据物流需求预测和安全库存设置最大、最小库存水平，并基于实时需求数据调整库存水平，还用于根据更新的需求预测调整库存计划。The inventory optimization module is used to determine the optimal order quantity based on ordering cost and holding cost, set the maximum and minimum inventory levels based on logistics demand forecast and safety stock, adjust the inventory level based on real-time demand data, and adjust the inventory plan based on updated demand forecast. 5.根据权利要求1所述的基于AI的智慧物流管理系统，其特征在于，所述数据融合采集单元包括数据采集装置和数据融合处理模块，所述数据采集装置包括摄像头模块、传感器模块、UWB标签和5G通信模块，所述摄像头模块用于采集人、设备的图像数据信息，所述UWB标签用于采集人员的运动轨迹和位置信息，所述传感器模块用于采集仓库区域环境的温湿度变化信息、气体变化信息和火灾信息以及各设备的速度、工作时间、压力变化信息，所述摄像头模块和所述传感器模块均与所述5G通信模块相连接，所述5G通信模块用于通过5G无线网络将处理数据上传至所述数字孪生监管单元。5. According to claim 1, the AI-based smart logistics management system is characterized in that the data fusion acquisition unit includes a data acquisition device and a data fusion processing module, the data acquisition device includes a camera module, a sensor module, a UWB tag and a 5G communication module, the camera module is used to collect image data information of people and equipment, the UWB tag is used to collect movement trajectory and location information of personnel, the sensor module is used to collect temperature and humidity change information, gas change information and fire information of the warehouse area environment, as well as the speed, working time and pressure change information of each equipment, the camera module and the sensor module are both connected to the 5G communication module, and the 5G communication module is used to upload processed data to the digital twin supervision unit through the 5G wireless network. 6.根据权利要求5所述的基于AI的智慧物流管理系统，其特征在于，所述智能AI识别单元包括人员安全识别模块、运输设备速度识别模块、环境安全识别模块和风险提醒模块；6. The AI-based smart logistics management system according to claim 5, characterized in that the intelligent AI recognition unit includes a personnel safety recognition module, a transportation equipment speed recognition module, an environmental safety recognition module and a risk reminder module; 所述人员安全识别模块用于根据UWB标签采集的人员定位信息与划分的仓库各区域坐标信息判断操作人员是否在危险区域逗留，当人员定位信息在预设的危险区域内超过1min则判定存在逗留情况及危险操作；The personnel safety identification module is used to determine whether the operator stays in the dangerous area based on the personnel positioning information collected by the UWB tag and the coordinate information of each area of the warehouse. If the personnel positioning information is in the preset dangerous area for more than 1 minute, it is determined that there is a stay and dangerous operation; 所述运输设备速度识别模块用于根据采集的设备运行数据获取对应设备当前的运行速度，将当前的运行速度与预设的安全速度阈值进行比较，根据比较结果判断运输设备是否发生超速或者故障停运情况；The transport equipment speed identification module is used to obtain the current operating speed of the corresponding equipment according to the collected equipment operation data, compare the current operating speed with the preset safety speed threshold, and determine whether the transport equipment is overspeeding or faulty and stopped according to the comparison result; 所述环境安全识别模块用于根据AI环境识别算法对环境参数进行检测，并根据采集的视频信息提取火焰和烟雾视频特征，基于视频特征对火焰和烟雾进行识别；The environmental safety identification module is used to detect environmental parameters according to the AI environmental identification algorithm, extract flame and smoke video features according to the collected video information, and identify flame and smoke based on the video features; 所述风险提醒模块与所述人员安全识别模块、所述运输设备速度识别模块和所述环境安全识别模块相连接，所述风险提醒模块根据获取的识别结果通过声光提醒方式及高亮显示方式对异常识别结果进行风险报警。The risk reminder module is connected to the personnel safety identification module, the transportation equipment speed identification module and the environmental safety identification module. The risk reminder module issues a risk alarm for abnormal identification results through sound and light reminders and highlight display according to the obtained identification results. 7.根据权利要求5所述的基于AI的智慧物流管理系统，其特征在于，所述数据分析处理单元包括建模模块、数据映射模块和可视化管理模块；7. The AI-based smart logistics management system according to claim 5, characterized in that the data analysis and processing unit includes a modeling module, a data mapping module and a visualization management module; 所述建模模块用于获取仓库内部建筑空间及仓库内设备的实体元件的坐标和尺寸信息，并建立静态模型和动态模型，基于建立的静态模型、动态模型和数字模型形成数字孪生仓库模型；The modeling module is used to obtain the coordinates and size information of the physical components of the internal building space of the warehouse and the equipment in the warehouse, and to establish a static model and a dynamic model, and to form a digital twin warehouse model based on the established static model, dynamic model and digital model; 所述数据映射模块用于将采集到的物理数据信息映射到建立的数字模型上驱动数字孪生仓库模型，通过数字孪生仓库模型实时监测仓库中的温湿度、压力数据、设备运行状态、人员运行轨迹和异常情况，及监测仓库中的货物情况和生产需求，并且可根据生产需求进行人员、设备的智能调度和货物的分配；The data mapping module is used to map the collected physical data information to the established digital model to drive the digital twin warehouse model. The digital twin warehouse model can monitor the temperature and humidity, pressure data, equipment operation status, personnel operation trajectory and abnormal conditions in the warehouse in real time, and monitor the goods situation and production demand in the warehouse, and can perform intelligent scheduling of personnel and equipment and distribution of goods according to production needs; 所述可视化管理模块用于通过用户友好可视化管理界面对仓库监控数据、报警数据进行可视化显示和管理。The visual management module is used to visually display and manage warehouse monitoring data and alarm data through a user-friendly visual management interface. 8.根据权利要求7所述的基于AI的智慧物流管理系统，其特征在于，数据分析处理单元还包括数据共享模块；所述数据共享模块用于构建仓储物流数据资源池，并将仓储物流数据资源池中的数据与第三方系统进行共享。8. According to the AI-based smart logistics management system of claim 7, it is characterized in that the data analysis and processing unit also includes a data sharing module; the data sharing module is used to build a warehousing and logistics data resource pool, and share the data in the warehousing and logistics data resource pool with a third-party system.
CN202411673591.9A 2024-11-21 2024-11-21 An AI-based smart logistics management system Pending CN119204954A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202411673591.9A CN119204954A (en) 2024-11-21 2024-11-21 An AI-based smart logistics management system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202411673591.9A CN119204954A (en) 2024-11-21 2024-11-21 An AI-based smart logistics management system

Publications (1)

Publication Number Publication Date
CN119204954A true CN119204954A (en) 2024-12-27

Family

ID=94074150

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202411673591.9A Pending CN119204954A (en) 2024-11-21 2024-11-21 An AI-based smart logistics management system

Country Status (1)

Country Link
CN (1) CN119204954A (en)

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN119417369A (en) * 2025-01-03 2025-02-11 成都秦川物联网科技股份有限公司 Warehouse management method, system, equipment and medium based on industrial Internet of Things
CN119990988A (en) * 2025-04-11 2025-05-13 阿童木云仓(杭州)人工智能科技有限公司 A warehouse in and out management method and system based on Internet of Things devices
CN120279198A (en) * 2025-06-11 2025-07-08 上海易迪尔信息技术有限公司 Digital twin body construction method and system applied to customs supervision
CN120430576A (en) * 2025-05-07 2025-08-05 杭州数创自动化控制技术有限公司 A packaging paper production line scheduling system based on BIM model
CN120543093A (en) * 2025-07-29 2025-08-26 山东港云数字科技有限公司 An intelligent cargo supervision method and system based on twin neural network
CN120996512A (en) * 2025-10-21 2025-11-21 厦门银江智慧城市技术股份有限公司 An intelligent enterprise logistics operation and maintenance platform based on the Internet of Things and mobile Internet

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112418764A (en) * 2020-11-24 2021-02-26 上海治云智能科技有限公司 5G visual warehouse pipe system
CN113947226A (en) * 2021-11-03 2022-01-18 山西大同大学 Equipment maintenance equipment demand prediction method
US20240046204A1 (en) * 2022-08-04 2024-02-08 Dematic Corp. Method for using reinforcement learning to optimize order fulfillment
CN118469447A (en) * 2024-05-31 2024-08-09 江西昌鹤医药供应链管理有限公司 Intelligent medicine warehousing system based on digital twinning and management method

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112418764A (en) * 2020-11-24 2021-02-26 上海治云智能科技有限公司 5G visual warehouse pipe system
CN113947226A (en) * 2021-11-03 2022-01-18 山西大同大学 Equipment maintenance equipment demand prediction method
US20240046204A1 (en) * 2022-08-04 2024-02-08 Dematic Corp. Method for using reinforcement learning to optimize order fulfillment
CN118469447A (en) * 2024-05-31 2024-08-09 江西昌鹤医药供应链管理有限公司 Intelligent medicine warehousing system based on digital twinning and management method

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
胡雯;: "智慧仓储 让物流仓储智能化――物流仓储的智慧性研究", 运输经理世界, no. 08, 5 August 2012 (2012-08-05) *

Cited By (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN119417369A (en) * 2025-01-03 2025-02-11 成都秦川物联网科技股份有限公司 Warehouse management method, system, equipment and medium based on industrial Internet of Things
CN119990988A (en) * 2025-04-11 2025-05-13 阿童木云仓(杭州)人工智能科技有限公司 A warehouse in and out management method and system based on Internet of Things devices
CN120430576A (en) * 2025-05-07 2025-08-05 杭州数创自动化控制技术有限公司 A packaging paper production line scheduling system based on BIM model
CN120279198A (en) * 2025-06-11 2025-07-08 上海易迪尔信息技术有限公司 Digital twin body construction method and system applied to customs supervision
CN120543093A (en) * 2025-07-29 2025-08-26 山东港云数字科技有限公司 An intelligent cargo supervision method and system based on twin neural network
CN120543093B (en) * 2025-07-29 2025-11-04 山东港云数字科技有限公司 A Smart Cargo Supervision Method and System Based on Siamese Neural Networks
CN120996512A (en) * 2025-10-21 2025-11-21 厦门银江智慧城市技术股份有限公司 An intelligent enterprise logistics operation and maintenance platform based on the Internet of Things and mobile Internet
CN120996512B (en) * 2025-10-21 2026-03-24 厦门银江智慧城市技术股份有限公司 Enterprise logistics intelligent operation and maintenance platform based on Internet of things and mobile Internet

Similar Documents

Publication Publication Date Title
CN119204954A (en) An AI-based smart logistics management system
CN117853078B (en) Unmanned aerial vehicle-based dynamic safety alarm system and method for construction site of building engineering
CN116862199A (en) Building construction optimizing system based on big data and cloud computing
JP2023524250A5 (en)
CN119005886A (en) Engineering decoration intelligent management system and method based on artificial intelligence
CN117350492A (en) A MES operation management system that compares historical data with intelligent control
CN116703303A (en) Warehouse Visual Supervision System and Method Based on Multilayer Perceptron and RBF
CN117114573A (en) Warehouse time supervision system and method based on big data
Chongwatpol Prognostic analysis of defects in manufacturing
CN117078163A (en) Logistics storage management and control system and method based on digital twinning
Arman et al. AI revolutionizes inventory management at retail giants: examining Walmart’s US operations
Rath et al. Integration of artificial intelligence and internet of things technology solutions in smart manufacturing
KR102876834B1 (en) A logistics warehouse management method that provides real-time logistics status information and enables customized order processing
CN117303147A (en) Elevator Internet of things monitoring system, method and terminal based on Zigbee and big data
KR20240098672A (en) System for distribution transfer management for bis scaling of distribution transfer management employing active tag
CN116095723A (en) Asset management system of communication base station
CN120431524A (en) A logistics warehousing monitoring system based on visual recognition technology
CN115167290A (en) Fully-connected digital factory based on 5G network and MEC technology
US12499415B2 (en) System and method for template creation, configuration, and identification
US20250384383A1 (en) System and method of managing operations in a warehouse
EP4345711A1 (en) System and method for data connector for external labor management systems
EP4345710A1 (en) Methods and systems for management of events and disruptions
KR20260021144A (en) Data-based production status monitoring method and system for ai analysis
US20240104484A1 (en) Systems and methods for next generation connected-worker solutions for occupational safety, health, and productivity
CN119204858A (en) Production cockpit construction method and production cockpit

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
RJ01 Rejection of invention patent application after publication

Application publication date: 20241227

RJ01 Rejection of invention patent application after publication