Warehouse intelligent goods control system and device based on side cloud collaborative AI technology, and medium

Through the AI ​​technology of edge cloud, combined with the Internet of Things and AI recognition, the intelligent and efficient control and management of warehouse goods is achieved, and the low data processing efficiency and safety hazards of traditional warehouse management systems are solved, and the accuracy of warehouse management is improved. and security.

CN119048979APending Publication Date: 2024-11-29INSPUR YUNZHOU (SHANDONG) IND INTERNET CO LTD

Patent Information

Application Number
CN202411084170.2
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-08
Publication Date
2024-11-29

AI Technical Summary

Technical Problem

Traditional warehousing management systems have problems such as low data processing efficiency, low management accuracy, and major safety hazards, which are difficult to meet the needs of modern commercial society for efficient, accurate, intelligent and safe warehousing goods monitoring.

Method used

Adopt a warehouse intelligent cargo control system based on edge-cloud collaborative AI technology, through the collaborative work of cloud and edge-end devices, real-time data acquisition, analysis and management is achieved through the Internet of Things, AI training modules and cargo control service modules, combining video analysis and AI Identification technology conducts comprehensive monitoring and early warning to ensure cargo safety and system safety.

Benefits of technology

It improves warehouse management efficiency and accuracy, reduces operating costs, enhances cargo security, solves edge equipment management problems, and improves warehouse intelligence and adaptability.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119048979A_ABST
    Figure CN119048979A_ABST
Patent Text Reader

Abstract

The invention provides a warehouse intelligent goods control system and device based on an edge cloud cooperation AI technology, and a medium, and belongs to the technical field of edge cloud cooperation. The system comprises a cloud device and an edge device. The cloud equipment comprises a configuration management module which is used for monitoring the use condition of system resources in real time and dynamically adjusting and storing network resources according to requirements; the Internet of Things module is used for establishing network connection and communication between the cloud equipment and the edge equipment and performing communication management; the AI training module is used for performing deep learning and training by using historical data and an algorithm model to generate an AI model suitable for warehouse goods identification; and the goods control service module is used for analyzing the goods data uploaded by the side end equipment in real time by using an AI model, and carrying out automatic checking, anomaly detection and early warning notification on the goods on the basis of an analysis result in combination with preset rules and strategies. According to the invention, by introducing the side cloud collaborative AI technology, intelligent and efficient control and management of warehouse goods are realized.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of edge-cloud collaborative technology, and more specifically to a warehouse intelligent cargo control system, device and medium based on edge-cloud collaborative AI technology. Background Art

[0002] With the rapid development of science and technology, the warehouse management service industry is gradually changing from the traditional, manpower-based model to a highly automated and intelligent model. As the core node in the supply chain system, the warehouse's intelligence level is directly related to the efficiency and service quality of the entire supply chain system. However, traditional warehouse control systems often have problems such as slow data processing speed, poor accuracy, untimely response, and low intelligence level, which makes it difficult to meet the modern commercial society's demand for efficient, accurate, intelligent, and safe warehouse cargo monitoring.

[0003] The rise of IoT technology has enabled all kinds of equipment and goods in the warehouse to be connected and monitored in real time, which provides unlimited possibilities for the development of smart warehousing. Through IoT technology, we can obtain information such as the location, quantity, and status of goods in the warehouse in real time, so as to achieve accurate control and management of goods. However, relying solely on IoT technology is far from meeting the needs of modern warehouse management. Because the massive data generated by IoT needs to be effectively processed and analyzed to be transformed into valuable information to provide decision support for warehouse management.

[0004] Big data technology has emerged as the times require, providing powerful data analysis and processing capabilities for warehouse management. By deeply mining and analyzing the data collected by IoT devices, we can discover potential problems and optimization space in warehouse operations, thereby formulating more scientific and reasonable warehouse management strategies. However, big data processing requires powerful computing power and storage resources, which is a huge challenge for traditional warehouse management systems.

[0005] The emergence of cloud computing technology provides a solution for big data processing. Through cloud computing, data processing and analysis tasks can be handed over to cloud servers to complete, thereby releasing the computing pressure of local warehouse equipment and improving the speed and efficiency of data processing. At the same time, cloud computing also provides elastic computing and storage resources, which can be dynamically adjusted according to the actual needs of the warehouse, ensuring the scalability and flexibility of the system.

[0006] However, despite the many advantages of cloud computing, there are still some problems in its practical application. First, cloud computing relies on the network for data transmission and communication. If the network fails or is delayed, it will affect the normal operation of the entire system. Secondly, the security of cloud computing is also an issue that needs to be taken seriously. How to ensure the secure storage and transmission of data in the cloud and prevent data leakage and tampering are key issues that need to be solved in cloud computing applications.

[0007] It can be seen that although big data technology and cloud computing technology have been applied, the traditional warehouse management system still has problems such as low data processing efficiency, low management accuracy, and great security risks. Summary of the invention

[0008] In response to the above problems, the purpose of the present invention is to provide a warehouse intelligent cargo control system, device and medium based on edge-cloud collaborative AI technology. By introducing edge-cloud collaborative AI technology, intelligent and efficient control and management of warehouse cargo can be realized, warehouse management efficiency and accuracy can be improved, operating costs can be reduced, cargo security can be enhanced, edge device management problems can be solved, and the intelligence level and adaptability of the device can be improved.

[0009] In order to achieve the above object, the present invention is implemented through the following technical solutions: In a first aspect, the present invention discloses a warehouse intelligent goods control system based on edge-cloud collaborative AI technology, comprising: Cloud devices and edge devices are connected via network data; The cloud device includes: a configuration management module, an Internet of Things module, an AI training module and a cargo control service module; Configuration management module, used to monitor the usage of system resources in real time and dynamically adjust storage and network resources according to demand to optimize system performance; The IoT module is used to establish network connection and communication between cloud devices and edge devices through a preset communication method, and to manage communication; receive cargo data from edge devices through a standardized interface protocol, and send cloud instructions to edge devices; AI training module, which uses historical data and algorithm models to conduct deep learning and training to generate AI models suitable for warehouse cargo identification; The cargo control service module is used to use AI models to analyze cargo data uploaded by edge devices in real time, and to perform automated inventory, anomaly detection, and early warning notification of cargo based on the analysis results combined with preset rules and strategies; The edge device includes: a data acquisition module and an edge computing module; The data collection module is used to collect cargo data in real time through IoT devices deployed in the cargo warehouse and upload it to the cloud device; There are multiple AI Box devices in the edge computing module. The AI ​​Box devices are used to load the AI ​​models sent by the cloud devices, perform local reasoning and analysis on the cargo data through the AI ​​models, generate local reasoning results and send them to the cargo control service module.

[0010] Further, the configuration management module includes: a data management unit, a resource management unit, a security management unit, a network management unit, a node management unit and an application management unit; Data management unit, used to collect system resource data and provide storage, processing, backup and application functions of system resource data; The resource management unit is used to uniformly manage and schedule system resources, dynamically allocate and adjust resources according to the needs of each functional module in the system; monitor resource usage in real time, identify resource bottlenecks based on resource usage, and eliminate resource bottlenecks through a preset resource adjustment mechanism; The security management unit is used to perform identity recognition and security authentication management on users and login devices through identity authentication mechanism, permission management mechanism, access control mechanism and security audit mechanism; Network management unit, used to manage and maintain the system's network topology, network devices and network connections; The node management unit is used to monitor the load, health status and performance of each edge node, and add, delete or adjust edge nodes according to needs; The application management unit is used to deploy, configure, monitor and manage various applications in the system.

[0011] Further, the IoT module includes: a device management unit, a connection management unit, a message routing unit, a data parsing unit, a device linkage unit, and a security authentication unit; The device management unit is used to register and verify cloud devices and edge devices, and authorize the corresponding devices to access the system after verification. It is also used to manage the configuration information of cloud devices and edge devices, and detect the online status and workload of cloud devices and edge devices in real time. A connection management unit, used to establish and maintain network connections between cloud devices and edge devices; A message routing unit is used to route messages from the sender to the receiver according to preset rules and policies, and to perform QoS control during the message routing process; The data analysis unit is used to receive, analyze and process the cargo data from the edge device; extract the cargo status information and environmental parameters from the cargo data according to the preset data format and protocol; The device linkage unit is used to automatically trigger the action or response of the device according to the preset device linkage rules and policies; The security authentication unit is used to encrypt and decrypt communication data using encryption algorithms and key management technologies, and supports identity authentication and access control for cloud devices and edge devices.

[0012] Furthermore, the AI ​​training module includes: a model management unit, a data annotation unit, a model training unit, a model testing unit, a model publishing unit, and a model deployment unit; Model management unit, used to create, store and delete algorithm models, and perform version control on algorithm models; The data labeling unit classifies and labels the original cargo control data to facilitate algorithm model learning and identify cargo characteristics; The model training unit is used to perform model training using the labeled cargo control data and the algorithm model to learn and identify the characteristics of the cargo; and to record the training progress, loss value and accuracy of the algorithm model during the model training process; The model testing unit is used to test the trained algorithm model using an independent test data set and evaluate the accuracy, recall rate, and F1 value of the algorithm model in identifying cargo features to determine the test results; The model publishing unit is used to generate an AI model for identifying the value of goods from the algorithm model that has passed the test, and publish and share it; Model deployment unit, used to deploy AI models into the operating environment.

[0013] Furthermore, the cargo control service module includes: The cargo value warning unit is used to analyze the cargo data uploaded by the edge device in real time based on the AI ​​model, identify the cargo value based on the analysis results and local reasoning results, identify the cargo value anomaly according to the preset warning threshold range, and trigger the cargo value anomaly warning; The event warning unit is used for real-time monitoring and identification of video information in the cargo warehouse. When cargo movement events and personnel entry and exit events are identified, an alarm is triggered immediately and detailed event information and location are provided; Equipment early warning unit, used to monitor and evaluate the status of equipment in the cargo warehouse in real time to identify abnormal temperature and humidity of the equipment. When abnormal temperature or humidity is identified, an early warning is triggered immediately; A video warning unit is used to analyze the video stream in the video information of the cargo warehouse to identify potential safety hazard images. When a potential safety hazard image is identified, an early warning is immediately triggered and video clips related to the potential safety hazard image are saved; The environmental warning unit is used to determine whether the storage environment of the goods is abnormal based on the environmental parameters in the goods data; if the storage environment of the goods is abnormal, an early warning is triggered immediately.

[0014] Furthermore, the model publishing unit is specifically used for: Optimize and compress the algorithm model that has passed the test; Package the processed algorithm model into an executable format, generate an AI model, and publish it.

[0015] Furthermore, system resources include: computing resources, storage resources and network resources.

[0016] Furthermore, IoT devices include, but are not limited to: cameras, electronic fences, and weighing scales.

[0017] In the second aspect, the present invention also discloses a warehouse intelligent cargo control device based on edge-cloud collaborative AI technology, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it realizes the functions of any one of the above-mentioned warehouse intelligent cargo control systems based on edge-cloud collaborative AI technology.

[0018] In the third aspect, the present invention also discloses a readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the function of the warehouse intelligent cargo control system based on edge-cloud collaborative AI technology as described in any of the above items is realized.

[0019] Compared with the prior art, the present invention has the following beneficial effects: 1. The present invention introduces edge-cloud collaborative AI technology to achieve comprehensive integration and intelligent analysis of warehouse video resources and IoT device resources, thereby improving warehouse management efficiency and accuracy.

[0020] 2. Through the collaborative work of edge computing and cloud computing, the present invention can realize real-time processing and analysis of warehouse data, improve data processing efficiency, and reduce the cost of data transmission and storage.

[0021] 3. Through video analysis and AI recognition technology, the present invention can realize all-round, all-weather monitoring and early warning of warehouse goods, thereby enhancing the safety of warehouse goods.

[0022] 4. The present invention realizes unified management and scheduling of equipment through the coordination of cloud devices and edge computing device resources of each node. Cloud devices can monitor the status, performance and other information of equipment in real time, and perform remote configuration and debugging according to needs. At the same time, cloud devices can also perform batch update and maintenance of edge devices to improve the efficiency and convenience of equipment management.

[0023] 5. The present invention supports online batch updates of cloud algorithms, and can quickly adjust and optimize algorithm models according to actual needs. This enables the warehouse intelligent cargo control system to continuously learn and improve, adapt to changes in different warehouse environments and business needs, maintain its advancement and competitiveness, and improve the intelligence level and adaptability of the warehouse intelligent cargo control system.

[0024] 6. The present invention, by introducing edge-cloud collaborative AI technology, realizes intelligent and efficient control and management of warehouse goods, improves warehouse management efficiency and accuracy, reduces operating costs, enhances cargo security, solves edge device management problems, and improves the intelligence level and adaptability of cargo management. The present invention can provide strong support for the intelligent upgrade of the warehousing industry and promote the sustainable development and innovation of the industry.

[0025] It can be seen that compared with the prior art, the present invention has outstanding substantive features and significant progress, and the beneficial effects of its implementation are also obvious. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying creative work.

[0027] Figure 1 It is a system structure diagram of a specific implementation mode of the present invention.

[0028] In the figure, 1. Cloud device; 2. Edge device; 3. Configuration management module; 4. Internet of Things module; 5. AI training module; 6. Cargo control service module; 7. Data acquisition module; 8. Edge computing module; 31. Data management unit; 32. Resource management unit; 33. Security management unit; 34. Network management unit; 35. Node management unit; 36. Application management unit; 41. Device management unit; 42. Connection management unit; 43. Message routing unit; 44. Data analysis unit; 45. Device linkage unit; 46. Security authentication unit; 51. Model management unit; 52. Data annotation unit; 53. Model training unit; 54. Model testing unit; 55. Model testing unit; 56. Model deployment unit; 61. Cargo value warning unit; 62. Event warning unit; 63. Device warning unit; 64. Video warning unit; 65. Environment warning unit. DETAILED DESCRIPTION

[0029] In order to enable those skilled in the art to better understand the scheme of the present invention, the present invention is further described in detail below in conjunction with the accompanying drawings and specific implementation methods. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0030] See also Figure 1 As shown, this embodiment provides a warehouse intelligent cargo control system based on edge-cloud collaborative AI technology, including: a cloud device 1 and an edge device 2, and the cloud device 1 and the edge device 2 are connected via network data.

[0031] The cloud device 1 includes: a configuration management module 3, an Internet of Things module 4, an AI training module 5 and a cargo control service module 6.

[0032] Configuration management module 3 is used to monitor the usage of system resources in real time, and dynamically adjust storage and network resources according to demand to optimize system performance. Configuration management module 3 is the core management component of cloud devices, responsible for the resource configuration and scheduling of the overall system, ensuring that each functional module can work together efficiently, mainly including data management, resource management, security management, network management, node management, application management and other functions. Configuration management module 3 can monitor the usage of system resources in real time, and dynamically adjust computing, storage and network resources according to demand to optimize system performance. In addition, configuration management module 3 is also responsible for maintaining the security and stability of the system, and ensuring the security and privacy of data through means such as identity authentication, permission management and security auditing.

[0033] The Internet of Things module 4 is used to establish network connection and communication between cloud devices and edge devices through a preset communication method, and to perform communication management; through a standardized interface protocol, it receives cargo data from edge devices and sends cloud instructions to edge devices. Specifically, the Internet of Things module 4 is responsible for realizing the connection and communication between cloud devices and edge devices, mainly including functions such as device management, connection management, message routing, data analysis, device linkage, and security authentication. It receives data from edge devices, such as cargo status, environmental parameters, etc., through standardized interface protocols, and sends cloud instructions to edge devices. It should be noted that the Internet of Things module 4 supports multiple communication methods, such as wireless LAN, Bluetooth, Zigbee, etc., to ensure real-time data transmission and seamless connection of devices.

[0034] The AI ​​training module 5 is used to utilize historical data and algorithm models to conduct deep learning and training, and generate an AI model suitable for warehouse cargo identification.

[0035] In a specific implementation, the AI ​​training module 5 is the core intelligent component of the cloud device. The AI ​​training module 5 is used to use a large amount of historical data and algorithm models for deep learning and training to generate an AI model suitable for warehouse cargo identification, mainly including model management, data labeling, model training, model testing, model publishing, model deployment and other functions. The AI ​​training module 5 supports a variety of machine learning algorithms and deep learning frameworks, and can perform customized model training according to the actual needs of the warehouse. After the training is completed, the AI ​​training module 5 will send the model parameters and optimization results to the edge device 2 for real-time cargo identification and analysis.

[0036] The cargo control service module 6 is used to use the AI ​​model to analyze the cargo data uploaded by the edge devices in real time, and perform automatic inventory, anomaly detection and early warning notification of the cargo based on the analysis results combined with preset rules and strategies.

[0037] In a specific implementation, the cargo control service module 6 is the part of the cloud device that provides core services. The cargo control service module 6 is specifically used to: based on the model generated by the AI ​​training module 5, intelligently identify, warn and control the warehouse goods, mainly including cargo value warning, event warning, equipment warning, video warning, environmental warning and other functions. The cargo control service module 6 can analyze the cargo data uploaded by the edge device in real time, and combine the preset rules and strategies to realize the functions of automatic inventory, anomaly detection, warning notification and other functions of the cargo. At the same time, the cargo control service module 6 also supports integration with other warehouse management systems to realize data sharing and business collaboration.

[0038] The edge device 2 includes: a data acquisition module 7 and an edge computing module 8.

[0039] The data collection module 7 is used to collect cargo data in real time through the Internet of Things devices deployed in the cargo warehouse and upload it to the cloud device 1.

[0040] In a specific implementation, the data acquisition module 7 is a key component of the edge device 2. It collects information such as the location, quantity, and status of goods, as well as environmental parameters such as temperature and humidity in real time through various sensors deployed in the warehouse, such as cameras, electronic fences, weighbridges, and other IoT devices. The data acquisition module 7 has the characteristics of high sensitivity and high precision, which can ensure the accuracy and reliability of the data. At the same time, the module also supports data preprocessing and filtering functions to reduce redundant data and network transmission burden.

[0041] The edge computing module 8 is equipped with multiple AI Box devices, which are used to load the AI ​​model sent by the cloud device 1, perform local reasoning analysis on the cargo data through the AI ​​model, generate local reasoning results and send them to the cargo control service module 6.

[0042] In a specific implementation, the edge computing module 8 is the core processing unit of the edge device 2. It uses local computing power to process and analyze the data collected by the data acquisition module in real time, and mainly includes multiple AI Box devices, each of which is deployed by the cloud device 1 with data acquisition, data synchronization, local reasoning and other functions. The edge computing module 8 is loaded with the AI ​​model issued by the cloud device 1, which can intelligently identify the goods and upload the identification results to the cloud. Through edge computing, the delay and bandwidth requirements of data transmission can be reduced, and the real-time and response speed of the system can be improved. In addition, the edge computing module 8 also supports local decision-making and execution functions, and can quickly adjust and optimize the goods without relying on the cloud.

[0043] In a specific implementation, the configuration management module 3 includes: a data management unit 31 , a resource management unit 32 , a security management unit 33 , a network management unit 34 , a node management unit 35 and an application management unit 36 ​​.

[0044] The data management unit 31 is used to collect system resource data and provide storage, processing, backup and application functions for system resource data. The data management unit 31 is specifically used to: collect, store, process and apply system resource data; ensure the integrity, accuracy and consistency of data, and provide efficient data query and analysis capabilities; back up and restore data to cope with possible data loss or damage.

[0045] The resource management unit 32 is used to uniformly manage and schedule system resources, dynamically allocate and adjust resources according to the needs of each functional module in the system; monitor resource usage in real time, identify resource bottlenecks based on resource usage, and eliminate resource bottlenecks through a preset resource adjustment mechanism.

[0046] As an example, the resource management unit 32 is specifically used to: uniformly manage and schedule system resources, including computing resources, storage resources, network resources, etc.; dynamically allocate and adjust resources according to the needs of each functional module to ensure that the system can run efficiently; monitor resource usage and promptly discover and resolve resource bottlenecks.

[0047] The security management unit 33 is used to perform identity recognition and security authentication management on users and login devices through identity authentication mechanism, authority management mechanism, access control mechanism and security audit mechanism.

[0048] As an example, the security management unit 33 adopts a variety of security mechanisms and technical means, such as identity authentication, authority management, access control, security auditing, etc., to ensure that only legitimate users and devices can access system resources and prevent data leakage and illegal intrusion.

[0049] The network management unit 34 is used to manage and maintain the network topology, network devices and network connections of the system. The network management unit 34 can monitor the status and performance of the network, discover and solve network failures in a timely manner, and ensure smooth data transmission and communication reliability.

[0050] The node management unit 35 is used to monitor the load, health status and performance of each edge node, and add, delete or adjust the edge node according to the demand. The node management unit 35 can ensure the scalability and high availability of the system.

[0051] The application management unit 36 ​​is used to deploy, configure, monitor and manage various applications in the system so that the applications can run correctly and meet business needs; it is also used to provide application version control, upgrade maintenance and troubleshooting functions; it is also used for application performance analysis and optimization to improve application operation efficiency and user experience.

[0052] In a specific implementation, the Internet of Things module 4 includes: a device management unit 41, a connection management unit 42, a message routing unit 43, a data parsing unit 44, a device linkage unit 45 and a security authentication unit 46.

[0053] The device management unit 41 is used for registration and verification of cloud devices and edge devices, and authorizes the corresponding devices to access the system after verification; it is also used to manage the configuration information of cloud devices and edge devices, and to detect the online status and workload of cloud devices and edge devices in real time.

[0054] Specifically, the device management unit 41 is responsible for device registration and verification to ensure that only authorized devices can access the system. It also manages the configuration information of the device, such as IP address, port number, etc., so as to communicate correctly. In addition, the device management unit 41 is also responsible for device status monitoring, real-time detection of the device's online status, workload and other information to ensure the normal operation of the device.

[0055] The connection management unit 42 is used to establish and maintain the network connection between the cloud device and the edge device.

[0056] The message routing unit 43 is used to route the message from the sender to the receiver according to preset rules and policies, and perform QoS control during the message routing process.

[0057] Specifically, the message routing unit 43 supports a flexible message routing mechanism for routing messages from the sender to the receiver according to preset rules and policies. Through message routing, data can be transferred between different devices, applications and services, improving the efficiency and flexibility of data processing. At the same time, the message routing unit 43 also supports QoS (message delivery quality) control to ensure reliable transmission of messages.

[0058] The data analysis unit 44 is used to receive, analyze and process the cargo data from the edge device; and extract the cargo status information and environmental parameters in the cargo data according to the preset data format and protocol.

[0059] The device linkage unit 45 is used to automatically trigger the action or response of the device according to the preset device linkage rules and strategies. The device linkage unit 45 supports the linkage operation between devices and realizes the collaborative work between devices. It can automatically trigger the action or response of the device according to the preset rules and strategies, such as automatically starting the backup device or sending an alarm message when a certain device fails. Through the device linkage unit 45, the automation degree and operation efficiency of the device can be improved.

[0060] The security authentication unit 46 is used to encrypt and decrypt communication data using encryption algorithms and key management technologies, and supports identity authentication and access control of cloud devices and edge devices. The security authentication unit 46 is specifically used to: implement a security authentication mechanism between devices to ensure the security of communication; use encryption algorithms and key management technologies to encrypt and decrypt communication data to prevent data leakage and tampering; support device identity authentication and access control to ensure that only legitimate users and devices can access system resources.

[0061] In a specific implementation, the AI ​​training module 5 includes: a model management unit 51, a data annotation unit 52, a model training unit 53, a model testing unit 54, a model publishing unit 55 and a model deployment unit 56.

[0062] The model management unit 51 is used to create, store and delete algorithm models, and to perform version control on the algorithm models. The model management unit 51 is specifically used to: manage the entire model life cycle, including operations such as model creation, storage, version control and deletion; ensure the orderly organization and efficient use of the model, and provide model search and location functions to facilitate users to quickly find the required model.

[0063] The data labeling unit 52 classifies and labels the original cargo control data to facilitate the algorithm model to learn and identify the characteristics of the cargo.

[0064] As an example, data annotation is an important preparatory work for model training. The data annotation unit 52 is used to annotate the original data, that is, to label or classify the data so that the model can learn and identify the characteristics of the goods. The accuracy and completeness of data annotation directly affect the training effect and recognition accuracy of the model.

[0065] The model training unit 53 is used to perform model training using the labeled cargo control data and the algorithm model to learn and identify the characteristics of the cargo; and to record the training progress, loss value and accuracy of the algorithm model during the model training process.

[0066] The model training unit 53 is the core function of the AI ​​training module 5. The model training unit 53 uses the labeled data and the selected algorithm model for training, and continuously adjusts the parameters and structure of the model so that the model can gradually learn and identify the characteristics of the goods. During the training process, the model training unit 53 will record indicators such as the model's training progress, loss value, and accuracy, so that the user can understand the training situation.

[0067] The model testing unit 54 is used to test the trained algorithm model using an independent test data set, and evaluate the accuracy, recall rate, and F1 value of the algorithm model in identifying cargo features to determine the test results.

[0068] As an example, the model testing unit 54 implements the process of evaluating the performance of the trained model, specifically for: using an independent test data set to test the model, and evaluating the accuracy, recall rate, F1 value and other indicators of the model in identifying goods. Through testing, the performance of the model can be understood, and possible problems and deficiencies can be found.

[0069] The model publishing unit 55 is used to generate an AI model for identifying the value of goods from the algorithm model that has passed the test, and publish and share it.

[0070] As an example, the model publishing unit 55 is specifically used to: package the model into an executable format and provide it to other modules or users for use; before publishing, perform necessary optimization and compression on the model to improve the operating efficiency and stability of the model.

[0071] The model deployment unit 56 is used to deploy the AI ​​model into the operating environment. The model deployment unit 56 implements the process of deploying the trained model into the actual operating environment. The model deployment unit 56 is specifically used to integrate the model into the relevant system or application and ensure that the model can operate normally and identify goods in the actual scenario. During the deployment process, factors such as the performance, compatibility and security of the model need to be fully considered.

[0072] In a specific implementation, the cargo control service module 6 includes: a cargo value warning unit 61 , an event warning unit 62 , an equipment warning unit 63 , a video warning unit 64 and an environment warning unit 65 .

[0073] The cargo value warning unit 61 is used to analyze the cargo data uploaded by the edge device in real time based on the AI ​​model, identify the cargo value based on the analysis results and local reasoning results, identify the abnormal cargo value according to the preset warning threshold interval, and trigger the abnormal cargo value warning to notify relevant personnel to handle it. This helps to timely discover and handle the abnormal cargo value and ensure the safety and value of the warehouse cargo.

[0074] The event warning unit 62 is used for real-time monitoring and identification of video information of the cargo warehouse. When cargo movement events and personnel entry and exit events are identified, an early warning is immediately triggered and detailed event information and location are provided. This helps to quickly respond to and handle various emergencies and ensure the normal operation and safety of the warehouse.

[0075] The equipment early warning unit 63 is used to monitor and evaluate the status of the equipment in the cargo warehouse in real time to identify abnormal temperature and humidity of the equipment. When abnormal temperature or humidity is identified, an early warning is triggered immediately and relevant personnel are notified to perform maintenance or replacement. This helps to ensure the normal operation of the equipment and avoid adverse effects of equipment failure on the warehouse goods.

[0076] The video warning unit 64 is used to perform image analysis on the video stream in the video information of the cargo warehouse to identify potential safety hazard images. When a potential safety hazard image is identified, an early warning is immediately triggered, and video clips related to the potential safety hazard image are saved. The video early warning unit 64 can combine the video surveillance system and the AI ​​model to realize intelligent analysis of the real-time video stream in the warehouse. When the system detects abnormal behavior or objects, such as illegal intrusion, fire, etc., it will automatically trigger an early warning and save relevant video clips as evidence. This helps to promptly discover and deal with potential safety hazards and ensure the safety and stability of the warehouse.

[0077] The environmental warning unit 65 is used to determine whether the storage environment of the goods is abnormal based on the environmental parameters in the goods data; if the storage environment of the goods is abnormal, an early warning is triggered immediately.

[0078] The environmental warning unit 65 is specifically used to determine whether the environment is suitable for the storage of goods by real-time monitoring of environmental parameters in the warehouse, such as temperature, humidity, light, etc. When the environmental parameters exceed the set safety range, an early warning is immediately triggered to remind relevant personnel to adjust the environmental conditions or take corresponding measures. This helps to ensure that the goods are stored in a suitable environment and prevent damage or deterioration of the goods due to environmental factors.

[0079] In addition, based on the above system architecture, the overall collaborative workflow of this system is as follows: First, based on the current situation of the warehouse, the basic equipment is upgraded and renovated. For example, advanced IoT sensor devices such as high-definition video cameras and electronic fences are installed in the warehouse. Then, an edge device 2 is assigned as an edge computing node and connected to the cloud device 1. The sensor device data is collected through the edge computing node and pushed to the cloud device 1. After the cloud device 1 parses the data, it is provided to the AI ​​training module 5 for model training. The AI ​​training module 5 publishes and deploys the trained model to the AI ​​Box device of the edge device 2. The data acquisition module 7 of the edge device 2 collects the sensor device data in real time and transmits it to the AI ​​Box device. The AI ​​Box device performs real-time local reasoning and analysis, and then feeds the result information back to the cargo control service module 6 of the cloud device 1 for unified result output. At the same time, if equipment control is required, the control information will be transmitted to the cloud IoT, and the cloud IoT platform will issue control instructions to the equipment.

[0080] It can be seen that the present invention provides a warehouse intelligent cargo control system based on edge-cloud collaborative AI technology, which makes full use of the advantages of technologies such as the Internet of Things, big data, cloud computing, and edge computing, and realizes intelligent identification, early warning, and control of warehouse goods through artificial intelligence technologies such as video analysis and AI recognition. This system not only improves the operational efficiency and cargo management accuracy of the warehouse, reduces safety hazards, but also provides strong support for the intelligent upgrade of the logistics industry.

[0081] The present invention also provides a warehouse intelligent cargo control device based on edge-cloud collaborative AI technology, comprising a memory, a processor, and a computer program stored in the memory and runnable on the above processor. When the processor executes the computer program, it implements the function of the warehouse intelligent cargo control system based on edge-cloud collaborative AI technology as described in any one of the above items.

[0082] The present invention also provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, it implements the functions of the warehouse intelligent cargo control system based on edge-cloud collaborative AI technology.

[0083] The processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field programmable gate arrays (FPGAs), or a microcontroller. Gate array) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor can be a microprocessor or any conventional processor.

[0084] The memory can be used to store the computer program and / or module, and the processor realizes various functions of the warehouse intelligent cargo control system based on edge-cloud collaborative AI technology in the invention by running or executing the data stored in the memory. The memory may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc. In addition, the memory may include a high-speed random access memory and may also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card, a secure digital card, a flash memory card, at least one disk storage device, a flash memory device, or other volatile solid-state storage devices. If the warehouse intelligent cargo control system based on edge-cloud collaborative AI technology is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present invention implements all or part of the process in the above-mentioned embodiment method, and can also be stored in a computer-readable storage medium through a computer program. When the computer program is executed by the processor, it can implement the steps of each of the above-mentioned method embodiments. Among them, the computer program includes computer program code, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device that can carry the computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory, random access memory, point carrier signal, telecommunication signal and software distribution medium. It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction.

[0085] The present invention has described the basic concepts. Obviously, for those skilled in the art, the above detailed disclosure is only for example and does not constitute a limitation of this specification. Although not explicitly stated herein, those skilled in the art may make various modifications, improvements and corrections to this specification. Such modifications, improvements and corrections are suggested in this specification, so such modifications, improvements and corrections still belong to the spirit and scope of the exemplary embodiments of this specification. In addition, it will be understood by those skilled in the art that various aspects of this specification may be illustrated and described by a number of patentable categories or situations, including any new and useful process, machine, product or combination of substances, or any new and useful improvements thereto. Accordingly, various aspects of this specification may be performed entirely by hardware, entirely by software (including firmware, resident software, microcode, etc.), or by a combination of hardware and software. The above hardware or software may be referred to as "data blocks", "modules", "engines", "units", "components" or "systems". In addition, various aspects of this specification may be represented as a computer product located in one or more computer-readable media, which includes computer-readable program code. A computer storage medium may include a propagated data signal containing computer program code, for example, in baseband or as part of a carrier wave. The propagated signal may be in a variety of forms, including electromagnetic, optical, etc., or a suitable combination. A computer storage medium may be any computer-readable medium other than a computer-readable storage medium, which can be connected to an instruction execution system, device or apparatus to communicate, propagate or transmit the program for use. The program code on the computer storage medium may be transmitted via any suitable medium, including radio, cable, fiber optic cable, RF, or similar media, or any combination of the above media. The computer program code required for the operation of each part of this specification can be written in any one or more programming languages, including object-oriented programming languages ​​such as Java, Scala, Smalltalk, Eiffel, JADE, Emerald, C++, C#, VB.NET, Python, etc., conventional procedural programming languages ​​such as C language, Visual Basic, Fortran 2003, Perl, COBOL2002, PHP, ABAP, dynamic programming languages ​​such as Python, Ruby and Groovy, or other programming languages, etc. The program code can be run entirely on the user's computer, or run on the user's computer as an independent software package, or run partially on the user's computer and partially on a remote computer, or run entirely on a remote computer or server. In the latter case, the remote computer can be connected to the user's computer through any network form, such as a local area network (LAN) or a wide area network (WAN), or connected to an external computer (e.g., via the Internet), or in a cloud computing environment, or used as a service such as software as a service (SaaS). In addition, unless explicitly stated in the claims, the order of the processing elements and sequences described in this specification, the use of alphanumeric characters, or the use of other names are not intended to limit the order of the processes and methods of this specification. Although the above disclosure discusses some invention embodiments that are currently considered useful through various examples, it should be understood that such details are only for illustrative purposes, and the attached claims are not limited to the disclosed embodiments. On the contrary, the claims are intended to cover all modifications and equivalent combinations that are consistent with the essence and scope of the embodiments of this specification. For example, although the system components described above can be implemented by hardware devices, they can also be implemented only by software solutions, such as installing the described system on an existing server or mobile device. Similarly, it should be noted that in order to simplify the description disclosed in this specification and thus help understand one or more embodiments of the invention, in the above description of the embodiments of this specification, multiple features are sometimes combined into one embodiment, figure or description thereof. However, this disclosure method does not mean that the features required by the subject matter of this specification are more than the features mentioned in the claims. In fact, the features of the embodiments are less than all the features of the single embodiment disclosed above. Although the preferred embodiments of the present invention have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention. Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A warehouse intelligent cargo control system based on edge-cloud collaborative AI technology, characterized in that: include: Cloud devices and edge devices are connected via network data; The cloud device includes: a configuration management module, an Internet of Things module, an AI training module and a cargo control service module; Configuration management module, which is used to monitor the usage of system resources in real time and dynamically adjust storage and network resources according to demand to optimize system performance; The IoT module is used to establish network connection and communication between cloud devices and edge devices through a preset communication method, and to manage communication; receive cargo data from edge devices through a standardized interface protocol, and send cloud instructions to edge devices; AI training module, which uses historical data and algorithm models to conduct deep learning and training to generate AI models suitable for warehouse cargo identification; The cargo control service module is used to use AI models to analyze cargo data uploaded by edge devices in real time, and to perform automated inventory, anomaly detection, and early warning notification of cargo based on the analysis results combined with preset rules and strategies; The edge device includes: a data acquisition module and an edge computing module; The data collection module is used to collect cargo data in real time through IoT devices deployed in the cargo warehouse and upload it to the cloud device; There are multiple AI Box devices in the edge computing module. The AI ​​Box devices are used to load the AI ​​models sent by the cloud devices, perform local reasoning and analysis on the cargo data through the AI ​​models, generate local reasoning results and send them to the cargo control service module.

2. The warehouse intelligent cargo control system based on edge-cloud collaborative AI technology according to claim 1 is characterized in that: The configuration management module includes: a data management unit, a resource management unit, a security management unit, a network management unit, a node management unit and an application management unit; Data management unit, used to collect system resource data and provide storage, processing, backup and application functions of system resource data; The resource management unit is used to uniformly manage and schedule system resources, dynamically allocate and adjust resources according to the needs of each functional module in the system; monitor resource usage in real time, identify resource bottlenecks based on resource usage, and eliminate resource bottlenecks through a preset resource adjustment mechanism; The security management unit is used to perform identity recognition and security authentication management on users and login devices through identity authentication mechanism, permission management mechanism, access control mechanism and security audit mechanism; Network management unit, used to manage and maintain the system's network topology, network devices and network connections; The node management unit is used to monitor the load, health status and performance of each edge node, and add, delete or adjust edge nodes according to needs; The application management unit is used to deploy, configure, monitor and manage various applications in the system.

3. The warehouse intelligent cargo control system based on edge-cloud collaborative AI technology according to claim 2 is characterized in that: The Internet of Things module includes: a device management unit, a connection management unit, a message routing unit, a data parsing unit, a device linkage unit and a security authentication unit; The device management unit is used to register and verify cloud devices and edge devices, and authorize the corresponding devices to access the system after verification. It is also used to manage the configuration information of cloud devices and edge devices, and detect the online status and workload of cloud devices and edge devices in real time. A connection management unit, used to establish and maintain network connections between cloud devices and edge devices; A message routing unit is used to route messages from the sender to the receiver according to preset rules and policies, and to perform QoS control during the message routing process; The data analysis unit is used to receive, analyze and process the cargo data from the edge device; extract the cargo status information and environmental parameters from the cargo data according to the preset data format and protocol; The device linkage unit is used to automatically trigger the action or response of the device according to the preset device linkage rules and policies; The security authentication unit is used to encrypt and decrypt communication data using encryption algorithms and key management technologies, and supports identity authentication and access control for cloud devices and edge devices.

4. The warehouse intelligent cargo control system based on edge-cloud collaborative AI technology according to claim 3 is characterized in that: The AI ​​training module includes: a model management unit, a data annotation unit, a model training unit, a model testing unit, a model publishing unit and a model deployment unit; Model management unit, used to create, store and delete algorithm models, and perform version control on algorithm models; The data labeling unit classifies and labels the original cargo control data to facilitate algorithm model learning and identify cargo characteristics; The model training unit is used to perform model training using the labeled cargo control data and the algorithm model to learn and identify the characteristics of the cargo; and to record the training progress, loss value and accuracy of the algorithm model during the model training process; The model testing unit is used to test the trained algorithm model using an independent test data set and evaluate the accuracy, recall rate, and F1 value of the algorithm model in identifying cargo features to determine the test results; The model publishing unit is used to generate an AI model for identifying the value of goods from the algorithm model that has passed the test, and publish and share it; Model deployment unit, used to deploy AI models into the operating environment.

5. The warehouse intelligent cargo control system based on edge-cloud collaborative AI technology according to claim 4 is characterized in that: The cargo control service module includes: The cargo value warning unit is used to analyze the cargo data uploaded by the edge device in real time based on the AI ​​model, identify the cargo value based on the analysis results and local reasoning results, identify the cargo value anomaly according to the preset warning threshold range, and trigger the cargo value anomaly warning; The event warning unit is used for real-time monitoring and identification of video information in the cargo warehouse. When cargo movement events and personnel entry and exit events are identified, an alarm is triggered immediately and detailed event information and location are provided; Equipment early warning unit, used to monitor and evaluate the status of equipment in the cargo warehouse in real time to identify abnormal temperature and humidity of the equipment. When abnormal temperature or humidity is identified, an early warning is triggered immediately; A video warning unit is used to analyze the video stream in the video information of the cargo warehouse to identify potential safety hazard images. When a potential safety hazard image is identified, an early warning is immediately triggered and video clips related to the potential safety hazard image are saved; The environmental warning unit is used to determine whether the storage environment of the goods is abnormal based on the environmental parameters in the goods data; if the storage environment of the goods is abnormal, an early warning is triggered immediately.

6. The warehouse intelligent cargo control system based on edge-cloud collaborative AI technology according to claim 4 is characterized in that: The model publishing unit is specifically used for: Optimize and compress the algorithm model that has passed the test; Package the processed algorithm model into an executable format, generate an AI model, and publish it.

7. The warehouse intelligent cargo control system based on edge-cloud collaborative AI technology according to claim 1 is characterized in that: The system resources include: computing resources, storage resources and network resources.

8. The warehouse intelligent cargo control system based on edge-cloud collaborative AI technology according to claim 1 is characterized in that: The IoT devices include but are not limited to: cameras, electronic fences and weighing scales.

9. A warehouse intelligent cargo control device based on edge-cloud collaborative AI technology, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, it implements the function of intelligent warehouse cargo control based on edge-cloud collaborative AI technology as described in any one of claims 1 to 8.

10. A readable storage medium, characterized in that: The readable storage medium stores a computer program, which, when executed by a processor, implements the function of intelligent warehouse cargo control based on edge-cloud collaborative AI technology as described in any one of claims 1 to 8.

Citation Information

Patent Citations

  • Method and system for remotely and intelligently detecting goods in storage space

    CN115147748A

  • Cloud local software defined network architecture

    CN115941513A

  • Warehousing system and method, electronic equipment and storage medium

    CN116703294A

  • Intelligent control system based on cloud platform technology

    CN117478672A

  • Warehouse goods monitoring system, equipment and medium

    CN117611054A

Cited By

  • Camera point supplementing cloud storage data method and system based on RFID article checking

    CN119815191A

  • Camera supplemental point cloud data storage method and system based on RFID inventory

    CN119815191B

  • Distributed new energy data scheduling processing method based on cloud side-end cooperation

    CN120416258A