Intelligent equipment full-life-cycle management method and device, equipment and storage medium

Abstract

The invention discloses a full-life-cycle management method, device and equipment for intelligent equipment and a storage medium, and the method comprises the steps: collecting the operation data of the intelligent equipment in real time, carrying out the preprocessing of the operation data, and obtaining the preprocessed target data; training a preset AI model according to a preset machine learning framework to obtain a trained target AI model; a target AI model is deployed, the target AI model is integrated into a business process, target data is managed and monitored, and interaction service is provided through a user interface, so that the service life of equipment can be prolonged, the non-planned downtime can be greatly reduced, each link can be ensured to obtain the most appropriate resource support, and the efficiency is improved. The user can directly dialogue with the AI model without a threshold, the learning use cost is not needed, and the speed and efficiency of intelligent equipment full-life-cycle management are improved.

Description

Technical Field

[0001] This invention relates to the field of data tracking and management technology, and in particular to a method, device, equipment, and storage medium for the full lifecycle management of intelligent equipment. Background Technology

[0002] An equipment lifecycle management system is a comprehensive management system integrating multiple advanced technologies, aiming to achieve comprehensive tracking and management of assets throughout their entire lifecycle, from procurement to disposal. Existing equipment lifecycle management systems primarily integrate Internet of Things (IoT) technology, cloud computing technology, and big data technology.

[0003] 1. Internet of Things (IoT) technology: The Internet of Things (IoT) plays a crucial role in the equipment lifecycle management system. Through IoT, the system can achieve real-time perception and monitoring of equipment status. By installing sensors and other devices on the equipment, the system can collect operational data and location information of the equipment in real time and transmit these data to the management center for analysis and processing. This helps to detect abnormal situations in the equipment in a timely manner and improve the reliability and safety of the equipment.

[0004] 2. Cloud computing technology: Cloud computing technology provides powerful data storage and processing capabilities for the equipment lifecycle management system. Through the cloud computing platform, the system can realize centralized storage and management of equipment data, making it convenient for users to access and query data anytime and anywhere. At the same time, the cloud computing platform can also provide a wealth of data analysis tools to help users conduct in-depth mining and analysis of equipment data, providing support for decision-making.

[0005] 3. Big Data Technology: Big data technology enables equipment lifecycle management systems to process and analyze massive amounts of equipment data. Through big data technology, the system can comprehensively analyze and mine equipment operation data, maintenance records, fault records, etc., to discover the patterns and trends of equipment operation, and provide a basis for preventive maintenance and optimized management of equipment.

[0006] With the existing technical approach and architecture, the system operation and business logic are very complex, requiring a large learning curve for ordinary users. Business decisions and usage also require a lot of manual calculation and processing, making it impossible to achieve efficient processing.

[0007] An equipment lifecycle management system is a system used to track and manage assets throughout their entire lifecycle, from procurement to disposal. It involves multiple fields, including but not limited to information technology, mechanical engineering, supply chain management, and finance. While equipment lifecycle management systems have achieved significant success in improving efficiency, reducing costs, and optimizing resource utilization with technological advancements, some technical challenges still exist in the implementation of actual projects. 1. Data integration and interoperability: Because the equipment lifecycle management system needs to achieve data integration and interoperability between different systems; and in general, enterprises usually use a variety of different software solutions to manage their business processes, such as Enterprise Resource Planning (ERP), Supply Chain Management (SCM), Customer Relationship Management (CRM), etc., these systems have different data formats, standards and protocols; ensuring that these systems can exchange information seamlessly is a complex process that requires the development of customized interfaces or the adoption of middleware technology.

[0008] 2. Big data processing capabilities The amount of data generated throughout the entire equipment lifecycle is enormous, covering multiple aspects such as design documents, maintenance records, performance parameters, and usage status. How to effectively collect, store, process, and analyze this massive amount of data to extract valuable information to support decision-making is a major test of existing computing power and algorithms; in particular, rapid data processing capabilities are crucial for real-time monitoring and predictive maintenance functions.

[0009] 3. Security and privacy protection As digitalization deepens, cybersecurity threats are also increasing. Equipment lifecycle management systems contain a large amount of sensitive information, such as corporate intellectual property and customer data; leaks of this information can have serious consequences. Therefore, establishing a robust security protection system, including encryption technology, access control, and audit trails, to ensure data security and user privacy has become a critical issue.

[0010] 4. Balancing Standardization and Personalization Different industries, and even different companies within the same industry, have vastly different needs for equipment management. On the one hand, they must comply with international or national standards, and on the other hand, they must meet the specific needs of individual companies. Finding a balance between the two, ensuring both the universality and flexibility of the system, is a challenging task. Summary of the Invention

[0011] The main objective of this invention is to provide a method, device, equipment, and storage medium for intelligent equipment lifecycle management, aiming to solve the technical problems of insufficient data integration and interoperability, poor big data processing capabilities, low security and privacy protection, and inability to guarantee a balance between versatility and flexibility in existing equipment lifecycle management systems.

[0012] In a first aspect, the present invention provides a method for full lifecycle management of intelligent equipment, the method comprising the following steps: Real-time acquisition of operational data from intelligent equipment; preprocessing of the operational data to obtain preprocessed target data; The preset AI model is trained according to the preset machine learning framework to obtain the trained target AI model; Deploy the target AI model, integrate the target AI model into the business process, manage and monitor the target data, and provide interactive services through the user interface.

[0013] Optionally, the real-time acquisition of operational data from the intelligent equipment, and the preprocessing of the operational data to obtain preprocessed target data, include: The sensors in the data acquisition layer of the full life cycle management system collect the operation data and equipment-related information of the intelligent equipment in real time, and transmit the operation data to the preprocessing layer of the full life cycle management system. The preprocessing layer sequentially performs data cleaning, formatting, normalization, feature extraction, and dimensionality reduction on the operational data based on the equipment-related information to obtain the preprocessed target data.

[0014] Optionally, the step of training a preset AI model according to a preset machine learning framework to obtain a trained target AI model includes: The AI ​​model training and evaluation layer of the full lifecycle management system selects a preset training algorithm and a preset optimizer adapted to the intelligent equipment from a preset machine learning framework. The preset AI model is trained according to the preset training algorithm and the preset optimizer to obtain the trained target AI model.

[0015] Optionally, the step of training the preset AI model according to the preset training algorithm and the preset optimizer to obtain the trained target AI model includes: The corresponding training parameters are selected according to the preset training algorithm, and the corresponding learning rate is selected according to the preset optimizer. The preset AI model is trained according to the training parameters and the learning rate to obtain the trained AI model to be adjusted. The accuracy and reliability of the AI ​​model to be adjusted are verified and evaluated to obtain the optimized and trained target AI model.

[0016] Optionally, the step of verifying and evaluating the accuracy and reliability of the AI ​​model to be adjusted to obtain the optimized and trained target AI model includes: The AI ​​model to be adjusted is subjected to cross-validation and A / B testing. The AI ​​model with an accuracy greater than a preset accuracy threshold and a stability greater than a preset stability threshold is selected as the target AI model for optimization and training.

[0017] Optionally, the deployment of the target AI model, the integration of the target AI model into the business process, the management and monitoring of the target data, and the provision of interactive services through a user interface include: The target AI model is converted into a deployable format according to the model deployment layer of the full lifecycle management system to obtain the target AI model after format conversion. The target AI model after format conversion is containerized and orchestrated to obtain an orchestrated AI model. Perform security and privacy authentication on the orchestration AI model, and integrate the authenticated orchestration AI model into the business process; The target data is managed and monitored by the service layer of the full lifecycle management system, and interactive services are provided through the user interface.

[0018] Optionally, the step of managing and monitoring the target data according to the service layer of the full lifecycle management system and providing interactive services through a user interface includes: The target data is analyzed according to different business processes based on the service layer of the full lifecycle management system to obtain data analysis results; Based on the data analysis results, back up the data that needs to be backed up from the target data, and restore the data that needs to be restored from the target data. The full lifecycle management system is subjected to security audits according to a preset audit cycle, and vulnerability scans are performed on the full lifecycle management system according to a preset scanning cycle. The user interface layer of the full lifecycle management system provides interactive services to users through the user interface.

[0019] Secondly, to achieve the above objectives, the present invention also proposes an intelligent equipment lifecycle management device, the intelligent equipment lifecycle management device comprising: The data acquisition and preprocessing module is used to acquire the operating data of the intelligent equipment in real time, preprocess the operating data, and obtain the preprocessed target data. The AI ​​model training module is used to train a preset AI model according to a preset machine learning framework to obtain a trained target AI model. The data monitoring and management module is used to deploy the target AI model, integrate the target AI model into the business process, manage and monitor the target data, and provide interactive services through the user interface.

[0020] Thirdly, to achieve the above objectives, the present invention also proposes an intelligent equipment lifecycle management device, which includes: a memory, a processor, and an intelligent equipment lifecycle management program stored in the memory and executable on the processor. The intelligent equipment lifecycle management program is configured to implement the steps of the intelligent equipment lifecycle management method described above.

[0021] Fourthly, to achieve the above objectives, the present invention also proposes a storage medium storing an intelligent equipment lifecycle management program, wherein when the intelligent equipment lifecycle management program is executed by a processor, it implements the steps of the intelligent equipment lifecycle management method described above.

[0022] The intelligent equipment lifecycle management method proposed in this invention collects real-time operational data of intelligent equipment, preprocesses the operational data to obtain preprocessed target data, trains a preset AI model according to a preset machine learning framework to obtain a trained target AI model, deploys the target AI model, integrates the target AI model into the business process, manages and monitors the target data, and provides interactive services through a user interface. This enables all relevant parties to access the latest and most accurate data, thereby improving overall collaboration efficiency. It not only extends the service life of equipment but also significantly reduces unplanned downtime, improving production efficiency. Adjusting resource allocation schemes based on real-time data ensures that each link receives the most suitable resource support. It provides users with an intuitive operating interface and personalized service options, allowing even first-time users to quickly get started and improving work efficiency. Users can directly interact with the AI ​​model without any learning curve, increasing the speed and efficiency of intelligent equipment lifecycle management. Attached Figure Description

[0023] Figure 1 This is a schematic diagram of the device structure of the hardware operating environment involved in the embodiments of the present invention; Figure 2 This is a flowchart illustrating the first embodiment of the intelligent equipment lifecycle management method of the present invention; Figure 3This is a flowchart illustrating the second embodiment of the intelligent equipment lifecycle management method of the present invention; Figure 4 This is a flowchart illustrating the third embodiment of the intelligent equipment lifecycle management method of the present invention; Figure 5 This is a flowchart illustrating the fourth embodiment of the intelligent equipment lifecycle management method of the present invention; Figure 6 This is a schematic diagram of the system framework in the intelligent equipment full life cycle management method of the present invention; Figure 7 This is a functional block diagram of the first embodiment of the intelligent equipment lifecycle management device of the present invention.

[0024] The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0025] It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

[0026] The solution of this invention mainly involves: collecting real-time operational data of intelligent equipment, preprocessing the operational data to obtain preprocessed target data; training a preset AI model according to a preset machine learning framework to obtain a trained target AI model; deploying the target AI model and integrating it into the business process; managing and monitoring the target data; and providing interactive services through a user interface. This enables all relevant parties to access the latest and most accurate data, thereby improving overall collaboration efficiency. It not only extends equipment lifespan but also significantly reduces unplanned downtime, increasing production efficiency. Adjusting resource allocation schemes based on real-time data ensures that each link receives the most suitable resource support. It provides users with an intuitive interface and personalized service options, allowing even first-time users to quickly get started and improving work efficiency. Users can directly interact with the AI ​​model without any learning curve, increasing the speed and efficiency of intelligent equipment lifecycle management. This solves the technical problems of insufficient data integration and interoperability, poor big data processing capabilities, low security and privacy protection, and the inability to guarantee a balance between versatility and flexibility in existing equipment lifecycle management systems.

[0027] Reference Figure 1 , Figure 1 This is a schematic diagram of the device structure of the hardware operating environment involved in the embodiments of the present invention.

[0028] like Figure 1As shown, the device may include: a processor 1001, such as a CPU; a communication bus 1002; a user interface 1003; a network interface 1004; and a memory 1005. The communication bus 1002 is used to enable communication between these components. The user interface 1003 may include a display screen or an input unit such as a keyboard; optionally, the user interface 1003 may also include a standard wired interface or a wireless interface. The network interface 1004 may optionally include a standard wired interface or a wireless interface (such as a Wi-Fi interface). The memory 1005 may be high-speed RAM or non-volatile memory, such as a disk drive. Optionally, the memory 1005 may also be a storage device independent of the aforementioned processor 1001.

[0029] Those skilled in the art will understand that Figure 1 The device structure shown does not constitute a limitation on the device and may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0030] like Figure 1 As shown, the memory 1005, which serves as a storage medium, may include an operating device, a network communication module, a user interface module, and a smart equipment lifecycle management program.

[0031] The device of this invention calls the intelligent equipment lifecycle management program stored in the memory 1005 through the processor 1001 and performs the following operations: Real-time acquisition of operational data from intelligent equipment; preprocessing of the operational data to obtain preprocessed target data; The preset AI model is trained according to the preset machine learning framework to obtain the trained target AI model; Deploy the target AI model, integrate the target AI model into the business process, manage and monitor the target data, and provide interactive services through the user interface.

[0032] The device of this invention, through processor 1001 calling the intelligent equipment lifecycle management program stored in memory 1005, also performs the following operations: The sensors in the data acquisition layer of the full life cycle management system collect the operation data and equipment-related information of the intelligent equipment in real time, and transmit the operation data to the preprocessing layer of the full life cycle management system. The preprocessing layer sequentially performs data cleaning, formatting, normalization, feature extraction, and dimensionality reduction on the operational data based on the equipment-related information to obtain the preprocessed target data.

[0033] The device of this invention, through processor 1001 calling the intelligent equipment lifecycle management program stored in memory 1005, also performs the following operations: The AI ​​model training and evaluation layer of the full lifecycle management system selects a preset training algorithm and a preset optimizer adapted to the intelligent equipment from a preset machine learning framework. The preset AI model is trained according to the preset training algorithm and the preset optimizer to obtain the trained target AI model.

[0034] The device of this invention, through processor 1001 calling the intelligent equipment lifecycle management program stored in memory 1005, also performs the following operations: The corresponding training parameters are selected according to the preset training algorithm, and the corresponding learning rate is selected according to the preset optimizer. The preset AI model is trained according to the training parameters and the learning rate to obtain the trained AI model to be adjusted. The accuracy and reliability of the AI ​​model to be adjusted are verified and evaluated to obtain the optimized and trained target AI model.

[0035] The device of this invention, through processor 1001 calling the intelligent equipment lifecycle management program stored in memory 1005, also performs the following operations: The AI ​​model to be adjusted is subjected to cross-validation and A / B testing. The AI ​​model with an accuracy greater than a preset accuracy threshold and a stability greater than a preset stability threshold is selected as the target AI model for optimization and training.

[0036] The device of this invention, through processor 1001 calling the intelligent equipment lifecycle management program stored in memory 1005, also performs the following operations: The target AI model is converted into a deployable format according to the model deployment layer of the full lifecycle management system to obtain the target AI model after format conversion. The target AI model after format conversion is containerized and orchestrated to obtain an orchestrated AI model. Perform security and privacy authentication on the orchestration AI model, and integrate the authenticated orchestration AI model into the business process; The target data is managed and monitored by the service layer of the full lifecycle management system, and interactive services are provided through the user interface.

[0037] The device of this invention, through processor 1001 calling the intelligent equipment lifecycle management program stored in memory 1005, also performs the following operations: The target data is analyzed according to different business processes based on the service layer of the full lifecycle management system to obtain data analysis results; Based on the data analysis results, back up the data that needs to be backed up from the target data, and restore the data that needs to be restored from the target data. The full lifecycle management system is subjected to security audits according to a preset audit cycle, and vulnerability scans are performed on the full lifecycle management system according to a preset scanning cycle. The user interface layer of the full lifecycle management system provides interactive services to users through the user interface.

[0038] This embodiment, through the above-described scheme, collects real-time operational data of intelligent equipment, preprocesses the operational data to obtain preprocessed target data, trains a preset AI model according to a preset machine learning framework to obtain a trained target AI model, deploys the target AI model, integrates the target AI model into the business process, manages and monitors the target data, and provides interactive services through a user interface. This enables all relevant parties to access the latest and most accurate data, thereby improving overall collaboration efficiency. It not only extends the service life of equipment but also significantly reduces unplanned downtime, improving production efficiency. Adjusting resource allocation schemes based on real-time data ensures that each link receives the most suitable resource support. It provides users with an intuitive operating interface and personalized service options, allowing even first-time users to quickly get started, improving work efficiency. Users can directly interact with the AI ​​model without any learning curve, increasing the speed and efficiency of intelligent equipment lifecycle management.

[0039] Based on the above hardware structure, an embodiment of the intelligent equipment full life cycle management method of the present invention is proposed.

[0040] Reference Figure 2 , Figure 2 This is a flowchart illustrating the first embodiment of the intelligent equipment lifecycle management method of the present invention.

[0041] In the first embodiment, the intelligent equipment lifecycle management method includes the following steps: Step S10: Collect the operating data of the intelligent equipment in real time, preprocess the operating data, and obtain the preprocessed target data.

[0042] It should be noted that after collecting the operating data of the intelligent equipment in real time, the operating data can be preprocessed to obtain the preprocessed target data.

[0043] Step S20: Train the preset AI model according to the preset machine learning framework to obtain the trained target AI model.

[0044] It should be understood that a pre-set artificial intelligence (AI) model can be trained using a pre-configured machine learning framework to obtain a trained target AI model.

[0045] Step S30: Deploy the target AI model, integrate the target AI model into the business process, manage and monitor the target data, and provide interactive services through the user interface.

[0046] It is understandable that after the AI ​​model is trained, it can be deployed and integrated into the business process to manage and monitor the target data. It can also provide interactive services through the user interface to display relevant information to users and respond to user interaction commands.

[0047] This embodiment, through the above-described scheme, obtains the current motor speed of the electric heavy truck, performs segmented calibration of the motor speed, and obtains segmented speed calibration results; determines the corresponding torque correction amount based on the segmented speed calibration results, and calibrates the maximum torque-to-current ratio (MTPA) curve at the target speed based on the torque correction amount and voltage level compensation amount, obtaining calibration data; performs Excel checks on the calibration data, verifies the calibration accuracy of the target calibration data after passing the check, and outputs the final calibration data after passing the verification. This allows all relevant parties to access the latest and most accurate data, thereby improving overall collaboration efficiency. It can not only extend the service life of equipment but also significantly reduce unplanned downtime, improving production efficiency. Adjusting resource allocation schemes based on real-time data ensures that each link receives the most suitable resource support. It provides users with an intuitive operating interface and personalized service options, enabling even first-time users to quickly get started, improving work efficiency. Users can directly communicate with the AI ​​model without any learning costs, improving the speed and efficiency of intelligent equipment lifecycle management.

[0048] Furthermore, Figure 3 This is a flowchart illustrating the second embodiment of the intelligent equipment lifecycle management method of the present invention, as shown below. Figure 3 As shown, based on the first embodiment, a second embodiment of the intelligent equipment full life cycle management method of the present invention is proposed. In this embodiment, step S10 specifically includes the following steps: Step S11: Collect the operation data and equipment-related information of the intelligent equipment in real time through the sensors of the data acquisition layer of the full life cycle management system, and transmit the operation data to the preprocessing layer of the full life cycle management system.

[0049] It should be noted that relevant data can be collected in the data acquisition layer of the full life cycle management system. The data acquisition and preprocessing layer is the foundation of the equipment full life cycle management system. Through Internet of Things technology, real-time perception and monitoring of equipment status can be realized. Through sensors, the operation data and related information of intelligent equipment can be collected in real time, and the operation data is transmitted to the preprocessing layer of the full life cycle management system.

[0050] In practice, the data acquisition layer collects equipment operation data and location information in real time through sensors and other devices, and transmits these data to the preprocessing layer for processing.

[0051] Step S12: The preprocessing layer sequentially performs data cleaning, formatting, normalization, feature extraction, and dimensionality reduction on the operating data based on the equipment-related information to obtain the preprocessed target data.

[0052] It is understood that the preprocessing layer sequentially performs data cleaning, formatting, normalization, feature extraction, and dimensionality reduction on the operational data based on the equipment-related information, thereby obtaining the preprocessed target data.

[0053] In practice, the preprocessing layer includes operations such as data cleaning, formatting, and normalization to ensure data quality and consistency. At the same time, the preprocessing layer also needs to perform feature extraction and dimensionality reduction on the data to reduce data redundancy and complexity and improve the efficiency of subsequent model training and application.

[0054] This embodiment, through the above-described scheme, uses sensors in the data acquisition layer of the full lifecycle management system to collect real-time operational data and equipment-related information of intelligent equipment. The operational data is then transmitted to the preprocessing layer of the full lifecycle management system. The preprocessing layer performs data cleaning, formatting, normalization, feature extraction, and dimensionality reduction on the operational data based on the equipment-related information to obtain preprocessed target data. This enables all relevant parties to access the latest and most accurate data, thereby improving overall collaboration efficiency.

[0055] Furthermore, Figure 4 This is a flowchart illustrating the third embodiment of the intelligent equipment lifecycle management method of the present invention, as shown below. Figure 4 As shown, based on the first embodiment, a third embodiment of the intelligent equipment full life cycle management method of the present invention is proposed. In this embodiment, step S20 specifically includes the following steps: Step S21: Select a preset training algorithm and preset optimizer adapted to the intelligent equipment from the preset machine learning framework based on the AI ​​model training evaluation layer of the full life cycle management system.

[0056] It should be noted that, based on the AI ​​model training evaluation layer of the full lifecycle management system, preset training algorithms and preset optimizers adapted to the intelligent equipment can be selected from the preset machine learning framework.

[0057] Step S22: Train the preset AI model according to the preset training algorithm and the preset optimizer to obtain the trained target AI model.

[0058] It is understood that the preset AI model can be trained according to the preset training algorithm and the preset optimizer to obtain the trained target AI model.

[0059] Furthermore, step S22 specifically includes the following steps: The corresponding training parameters are selected according to the preset training algorithm, and the corresponding learning rate is selected according to the preset optimizer. The preset AI model is trained according to the training parameters and the learning rate to obtain the trained AI model to be adjusted. The accuracy and reliability of the AI ​​model to be adjusted are verified and evaluated to obtain the optimized and trained target AI model.

[0060] It should be understood that, according to the preset training algorithm, corresponding training parameters can be selected, and according to the preset optimizer, corresponding learning rates can be selected; then, the preset AI model is trained according to the training parameters and the learning rate to obtain the trained AI model to be adjusted; after further verification and evaluation of accuracy and reliability, the optimized and trained AI model is obtained as the target AI model.

[0061] Furthermore, the step of verifying and evaluating the accuracy and reliability of the AI ​​model to be adjusted to obtain the optimized and trained target AI model specifically includes the following steps: The AI ​​model to be adjusted is subjected to cross-validation and A / B testing. The AI ​​model with an accuracy greater than a preset accuracy threshold and a stability greater than a preset stability threshold is selected as the target AI model for optimization and training.

[0062] In practical implementation, the AI ​​large-scale model training and evaluation layer is the core of the system. This layer requires training the AI ​​large-scale model using machine learning frameworks (such as TensorFlow and PyTorch). During training, appropriate training algorithms and optimizers need to be selected, and reasonable training parameters and learning rates need to be set. Simultaneously, evaluation methods such as cross-validation and A / B testing are required to ensure the model's accuracy and reliability. Furthermore, the model needs continuous optimization and adjustment during training to improve its performance and reliability in specific scenarios.

[0063] This embodiment, through the above-described scheme, selects a preset training algorithm and a preset optimizer adapted to the intelligent equipment from a preset machine learning framework through the AI ​​model training and evaluation layer of the full lifecycle management system; trains the preset AI model according to the preset training algorithm and the preset optimizer to obtain a trained target AI model; enables all relevant parties to access the latest and most accurate data, thereby improving overall collaboration efficiency, not only extending the service life of equipment, but also significantly reducing unplanned downtime, improving production efficiency, and increasing the speed and efficiency of the full lifecycle management of intelligent equipment.

[0064] Furthermore, Figure 5 This is a flowchart illustrating the fourth embodiment of the intelligent equipment lifecycle management method of the present invention, as shown below. Figure 5 As shown, based on the first embodiment, a fourth embodiment of the intelligent equipment full life cycle management method of the present invention is proposed. In this embodiment, step S30 specifically includes the following steps: Step S31: Convert the format of the target AI model into a deployable format according to the model deployment layer of the full lifecycle management system to obtain the target AI model after format conversion.

[0065] It should be noted that after obtaining the target AI model, a format conversion is required. That is, the target AI model's format is converted into a deployable format according to the model deployment layer of the full lifecycle management system, thereby obtaining the format-converted target AI model.

[0066] Step S32: Containerize and orchestrate the target AI model after format conversion to obtain the orchestrated AI model.

[0067] It is understandable that by containerizing and orchestrating the target AI model after format conversion, an orchestrated AI model can be obtained.

[0068] Step S33: Perform security and privacy authentication on the orchestration AI model, and integrate the authenticated orchestration AI model into the business process.

[0069] It should be understood that, considering the security and privacy protection of the model, the orchestration AI model can be subjected to security and privacy authentication, and then the authenticated orchestration AI model can be integrated into the business process.

[0070] Step S34: Manage and monitor the target data according to the service layer of the full lifecycle management system, and provide interactive services through the user interface.

[0071] It is understood that the service layer of the full lifecycle management system can manage and monitor the target data, and can provide interactive services through the user interface.

[0072] In practical implementation, the model deployment and service layer involves deploying the trained AI model to a suitable environment and providing service support. In this layer, the trained model needs to be converted into a deployable format, such as a RESTful API, microservice, or embedded application. At the same time, tools such as Docker and Kubernetes are needed for containerization and orchestration to achieve efficient model management and services. During the deployment process, the security and privacy protection of the model also need to be considered to ensure the security and privacy of the data.

[0073] Furthermore, step S34 specifically includes the following steps: The target data is analyzed according to different business processes based on the service layer of the full lifecycle management system to obtain data analysis results; Based on the data analysis results, back up the data that needs to be backed up from the target data, and restore the data that needs to be restored from the target data. The full lifecycle management system is subjected to security audits according to a preset audit cycle, and vulnerability scans are performed on the full lifecycle management system according to a preset scanning cycle. The user interface layer of the full lifecycle management system provides interactive services to users through the user interface.

[0074] It should be noted that by conducting data analysis based on different business types, data analysis results can be obtained, and then the target data can be backed up and restored. According to the pre-set audit cycle and scanning cycle, security audit and vulnerability scanning operations can be performed on the system, and corresponding interactive services can be provided to users based on the user interface.

[0075] In the specific implementation, see Figure 6 , Figure 6 This is a schematic diagram of the system framework in the intelligent equipment lifecycle management method of the present invention, as shown below. Figure 6As shown, the system functions include user management, equipment ledger, equipment inventory, and equipment requisition and return; platform management includes data asset management, algorithm library management, model library management, and model plugin management; the integrated development environment includes data access, data preprocessing, feature engineering, and vector data conversion; core AI technologies include knowledge graphs, vector databases, knowledge reasoning, deep learning, machine learning, model development, and algorithms including but not limited to: Computer Vision (CV), Natural Language Processing (NLP), time series, classification, aggregation, regression, Recurrent Neural Network (RNN), and Convolutional Neural Network (CNN); data processing includes: data access, data preprocessing, feature engineering, and vector data conversion; and computing power management includes: computing power pool management and computing power scheduling.

[0076] See Figure 6 The system is divided into two parts: platform functions and AI middleware. The platform functions are the functions of the equipment lifecycle management platform, mainly including user management, status ledger information, equipment inventory, equipment requisition and return, etc. The AI ​​middleware is the core of the system, including AI algorithm management, data processing, platform management, etc.

[0077] As a core component of the equipment lifecycle management system, the platform aims to comprehensively coordinate and efficiently manage the entire lifecycle of equipment, from procurement to disposal. It not only covers the initial procurement process, ensuring that each step meets budget and demand planning, but also delves into all aspects of equipment use, maintenance, performance monitoring, and final disposal. Through an integrated information platform, it enables real-time tracking and management of equipment status, supports the formulation of preventive maintenance strategies, extends equipment service life, and optimizes resource allocation and reduces overall costs while ensuring safety.

[0078] The AI ​​platform is a comprehensive platform integrating multiple functions, designed to accelerate the development, deployment, and management of AI applications within enterprises. The main functions of the AI ​​platform are: 1. Computing power management Computing power management is one of the core functions of an AI platform. It is responsible for optimizing the allocation and scheduling of computing resources to support efficient data processing and model training. This includes, but is not limited to, the intelligent scheduling of hardware resources such as the Central Processing Unit (CPU) and the Graphics Processing Unit (GPU) to ensure that different tasks can obtain the corresponding computing power support. In addition, this function also involves the dynamic expansion and contraction of resources to maximize cost-effectiveness.

[0079] 2. Data Processing The data processing capabilities cover a range of operations, from raw data collection, cleaning, and transformation to feature engineering. The AI ​​platform provides powerful ETL (Extract, Transform, Load) tools to support the processing of large-scale datasets. Through the built-in data quality management module, the accuracy and consistency of the data can be effectively guaranteed, laying a solid foundation for subsequent AI model training.

[0080] 3. Core AI technologies The core AI technologies include support for various algorithm frameworks such as machine learning and deep learning, as well as specialized technologies in fields such as natural language processing (NLP). These core technologies enable the AI ​​platform to provide comprehensive model building, training, and evaluation services. At the same time, the platform also integrates a pre-trained model library, which makes it easy for users to quickly start projects and can be customized according to specific business needs.

[0081] 4. Platform Management The platform's management functions focus on providing a stable and secure operating environment, covering multiple aspects such as user permission management, version control, and API management. Through detailed role permission settings, it ensures that users at different levels can only access resources and services of the corresponding level. In addition, the platform also supports continuous integration (CI) / continuous deployment (CD) processes, facilitating rapid iteration and updates to meet the needs of market changes.

[0082] The business logic and user interface layer serves as the interface between the equipment lifecycle management system and users. In this layer, the AI ​​big data model needs to be integrated into the business process, and interactive services should be provided through user interfaces such as web applications and mobile applications. The user interface needs to be designed to be simple, intuitive, and easy to use, facilitating users' management and monitoring of equipment. At the same time, the business logic layer also needs to implement equipment data processing and analysis functions to provide decision support for users.

[0083] The security and compliance layer is a crucial part of ensuring the security of the equipment lifecycle management system. This layer requires implementing encryption, access control, and other measures to protect data security and ensure that AI applications comply with industry standards and national regulations. It also necessitates establishing robust data backup and recovery mechanisms to prevent data loss or corruption. Furthermore, regular security audits and vulnerability scans are required to ensure the system's security and stability.

[0084] By integrating large AI models, the equipment lifecycle management system can further enhance the system's intelligence level and achieve more precise and efficient management of equipment. With the continuous development and improvement of AI technology, the equipment lifecycle management system will bring more opportunities and challenges to enterprises. Enterprises need to pay close attention to the development and application trends of new technologies and continuously optimize and improve the system's technical architecture and functional design to adapt to the ever-changing market and business needs.

[0085] This embodiment achieves efficient management of equipment throughout its entire lifecycle, from procurement to disposal, by introducing advanced AI technology and big data analytics capabilities. It primarily addresses issues in traditional equipment management systems related to management methods and actual user experience. 1. Data silos and lack of information transparency In traditional equipment management systems, the lack of a unified data platform and standards often leads to data silos between different departments, resulting in information stagnation and a lack of transparency. This situation not only affects decision-making efficiency but may also lead to redundant investment and resource waste. Intelligent systems, by integrating large AI models, can break down these data silos and provide a unified information platform, enabling all relevant parties to access the latest and most accurate data, thereby improving overall collaboration efficiency.

[0086] 2. Insufficient predictive maintenance Traditional maintenance strategies rely primarily on periodic inspections or post-failure repairs, which wastes resources and increases downtime. Intelligent systems, leveraging the powerful data analysis capabilities of AI big data models, can learn from vast amounts of historical data and identify potential failure modes, providing early warnings of possible malfunctions and supporting the development of preventative maintenance plans. This not only extends equipment lifespan but also significantly reduces unplanned downtime and improves production efficiency.

[0087] 3. Inefficient resource allocation In the management and use of equipment, how to rationally allocate limited resources has been a long-standing challenge. Intelligent systems use AI algorithms to optimize resource allocation, adjusting resource distribution plans based on real-time data to ensure that each link receives the most suitable resource support. For example, when faced with sudden demands, the system can quickly assess the current resource status and propose the optimal resource allocation suggestions.

[0088] 4. Poor user experience In the past, many equipment management systems were complex in design and had unfriendly user interfaces, requiring employees to spend a lot of time learning how to operate them. Intelligent systems, on the other hand, focus on user experience design, providing intuitive interfaces and personalized service options, enabling even first-time users to get started quickly and improving work efficiency. Users can directly converse with AI models without any learning curve or cost.

[0089] This embodiment, through the above-described scheme, converts the target AI model's format into a deployable format via the model deployment layer of the full lifecycle management system, obtaining a format-converted target AI model; the format-converted target AI model is then containerized and orchestrated to obtain an orchestrated AI model; the orchestrated AI model undergoes security and privacy authentication, and the authenticated orchestrated AI model is integrated into the business process; the target data is managed and monitored according to the service layer of the full lifecycle management system, and interactive services are provided through a user interface; this enables all relevant parties to access the latest and most accurate data, thereby improving overall collaboration efficiency, extending equipment lifespan, significantly reducing unplanned downtime, and increasing production efficiency; adjusting resource allocation schemes based on real-time data ensures that each link receives the most suitable resource support; it provides users with an intuitive operating interface and personalized service options, allowing even first-time users to quickly get started, improving work efficiency; users can directly interact with the AI ​​model without any learning curve, increasing the speed and efficiency of intelligent equipment lifecycle management.

[0090] Accordingly, the present invention further provides an intelligent equipment lifecycle management device.

[0091] Reference Figure 7 , Figure 7 This is a functional block diagram of the first embodiment of the intelligent equipment lifecycle management device of the present invention.

[0092] In the first embodiment of the intelligent equipment lifecycle management device of the present invention, the intelligent equipment lifecycle management device includes: The data acquisition and preprocessing module 10 is used to acquire the operating data of the intelligent equipment in real time, preprocess the operating data, and obtain the preprocessed target data.

[0093] AI model training module 20 is used to train a preset AI model according to a preset machine learning framework to obtain a trained target AI model.

[0094] The data monitoring and management module 30 is used to deploy the target AI model, integrate the target AI model into the business process, manage and monitor the target data, and provide interactive services through the user interface.

[0095] The data acquisition and preprocessing module 10 is further configured to collect the operation data and equipment-related information of the intelligent equipment in real time through the sensors of the data acquisition layer of the full life cycle management system, and transmit the operation data to the preprocessing layer of the full life cycle management system; the preprocessing layer performs data cleaning, formatting, normalization, feature extraction and dimensionality reduction on the operation data according to the equipment-related information to obtain the preprocessed target data.

[0096] The AI ​​model training module 20 is further configured to select a preset training algorithm and a preset optimizer adapted to the intelligent equipment from a preset machine learning framework based on the AI ​​model training evaluation layer of the full life cycle management system; and to train the preset AI model according to the preset training algorithm and the preset optimizer to obtain the trained target AI model.

[0097] The AI ​​model training module 20 is further configured to select corresponding training parameters according to the preset training algorithm, select corresponding learning rates according to the preset optimizer; train the preset AI model according to the training parameters and the learning rate to obtain the trained AI model to be adjusted; verify and evaluate the accuracy and reliability of the AI ​​model to be adjusted to obtain the optimized target AI model.

[0098] The AI ​​model training module 20 is also used to perform cross-validation and A / B testing on the AI ​​model to be adjusted, and to obtain an AI model whose accuracy is greater than a preset accuracy threshold and whose stability is greater than a preset stability threshold as the optimized target AI model.

[0099] The data monitoring and management module 30 is further configured to convert the format of the target AI model into a deployable format according to the model deployment layer of the full lifecycle management system, thereby obtaining the format-converted target AI model; containerize and orchestrate the format-converted target AI model to obtain the orchestrated AI model; perform security and privacy authentication on the orchestrated AI model, and integrate the authenticated orchestrated AI model into the business process; manage and monitor the target data according to the service layer of the full lifecycle management system, and provide interactive services through the user interface.

[0100] The data monitoring and management module 30 is further configured to analyze the target data according to different business processes based on the service layer of the full lifecycle management system to obtain data analysis results; back up the data that needs to be backed up in the target data according to the data analysis results, and restore the data that needs to be restored in the target data; perform security audits on the full lifecycle management system according to a preset audit cycle, and perform vulnerability scans on the full lifecycle management system according to a preset scanning cycle; and provide interactive services to users through the user interface layer of the full lifecycle management system.

[0101] The steps for implementing each functional module of the intelligent equipment lifecycle management device can be referred to in the various embodiments of the intelligent equipment lifecycle management method of the present invention, and will not be repeated here.

[0102] Furthermore, this embodiment of the invention also proposes a storage medium storing a smart equipment lifecycle management program, which, when executed by a processor, performs the following operations: Real-time acquisition of operational data from intelligent equipment; preprocessing of the operational data to obtain preprocessed target data; The preset AI model is trained according to the preset machine learning framework to obtain the trained target AI model; Deploy the target AI model, integrate the target AI model into the business process, manage and monitor the target data, and provide interactive services through the user interface.

[0103] Furthermore, when the intelligent equipment lifecycle management program is executed by the processor, it also performs the following operations: The sensors in the data acquisition layer of the full life cycle management system collect the operation data and equipment-related information of the intelligent equipment in real time, and transmit the operation data to the preprocessing layer of the full life cycle management system. The preprocessing layer sequentially performs data cleaning, formatting, normalization, feature extraction, and dimensionality reduction on the operational data based on the equipment-related information to obtain the preprocessed target data.

[0104] Furthermore, when the intelligent equipment lifecycle management program is executed by the processor, it also performs the following operations: The AI ​​model training and evaluation layer of the full lifecycle management system selects a preset training algorithm and a preset optimizer adapted to the intelligent equipment from a preset machine learning framework. The preset AI model is trained according to the preset training algorithm and the preset optimizer to obtain the trained target AI model.

[0105] Furthermore, when the intelligent equipment lifecycle management program is executed by the processor, it also performs the following operations: The corresponding training parameters are selected according to the preset training algorithm, and the corresponding learning rate is selected according to the preset optimizer. The preset AI model is trained according to the training parameters and the learning rate to obtain the trained AI model to be adjusted. The accuracy and reliability of the AI ​​model to be adjusted are verified and evaluated to obtain the optimized and trained target AI model.

[0106] Furthermore, when the intelligent equipment lifecycle management program is executed by the processor, it also performs the following operations: The AI ​​model to be adjusted is subjected to cross-validation and A / B testing. The AI ​​model with an accuracy greater than a preset accuracy threshold and a stability greater than a preset stability threshold is selected as the target AI model for optimization and training.

[0107] Furthermore, when the intelligent equipment lifecycle management program is executed by the processor, it also performs the following operations: The target AI model is converted into a deployable format according to the model deployment layer of the full lifecycle management system to obtain the target AI model after format conversion. The target AI model after format conversion is containerized and orchestrated to obtain an orchestrated AI model. Perform security and privacy authentication on the orchestration AI model, and integrate the authenticated orchestration AI model into the business process; The target data is managed and monitored by the service layer of the full lifecycle management system, and interactive services are provided through the user interface.

[0108] Furthermore, when the intelligent equipment lifecycle management program is executed by the processor, it also performs the following operations: The target data is analyzed according to different business processes based on the service layer of the full lifecycle management system to obtain data analysis results; Based on the data analysis results, back up the data that needs to be backed up from the target data, and restore the data that needs to be restored from the target data. The full lifecycle management system is subjected to security audits according to a preset audit cycle, and vulnerability scans are performed on the full lifecycle management system according to a preset scanning cycle. The user interface layer of the full lifecycle management system provides interactive services to users through the user interface.

[0109] Those skilled in the art will understand that all or part of the steps in the methods described above can be implemented by a program instructing related hardware. The program is stored in a storage medium and includes several instructions to cause a device (which may be a microcontroller, chip, etc.) or processor to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium is a computer-readable storage medium, including: USB flash drive, mobile hard drive, read-only memory (ROM), random access memory (RAM), magnetic disk or optical disk, and other media that can store program code.

[0110] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0111] The sequence numbers of the above embodiments of the present invention are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0112] The above are merely preferred embodiments of the present invention and do not limit the scope of the patent. Any equivalent structural or procedural transformations made based on the description and drawings of the present invention, or direct or indirect applications in other related technical fields, are similarly included within the scope of patent protection of the present invention.

Claims

1. A method for full lifecycle management of intelligent equipment, characterized in that, The intelligent equipment full lifecycle management method includes: Real-time acquisition of operational data from intelligent equipment; preprocessing of the operational data to obtain preprocessed target data; The preset AI model is trained according to the preset machine learning framework to obtain the trained target AI model; Deploy the target AI model, integrate the target AI model into the business process, manage and monitor the target data, and provide interactive services through the user interface.

2. The intelligent equipment full life cycle management method as described in claim 1, characterized in that, The real-time acquisition of operational data from the intelligent equipment, followed by preprocessing of the operational data to obtain preprocessed target data, includes: The sensors in the data acquisition layer of the full life cycle management system collect the operation data and equipment-related information of the intelligent equipment in real time, and transmit the operation data to the preprocessing layer of the full life cycle management system. The preprocessing layer sequentially performs data cleaning, formatting, normalization, feature extraction, and dimensionality reduction on the operational data based on the equipment-related information to obtain the preprocessed target data.

3. The intelligent equipment full life cycle management method as described in claim 1, characterized in that, The step of training a preset AI model according to a preset machine learning framework to obtain a trained target AI model includes: The AI ​​model training and evaluation layer of the full lifecycle management system selects a preset training algorithm and a preset optimizer adapted to the intelligent equipment from a preset machine learning framework. The preset AI model is trained according to the preset training algorithm and the preset optimizer to obtain the trained target AI model.

4. The intelligent equipment full life cycle management method as described in claim 3, characterized in that, The step of training a preset AI model according to the preset training algorithm and the preset optimizer to obtain a trained target AI model includes: The corresponding training parameters are selected according to the preset training algorithm, and the corresponding learning rate is selected according to the preset optimizer. The preset AI model is trained according to the training parameters and the learning rate to obtain the trained AI model to be adjusted. The accuracy and reliability of the AI ​​model to be adjusted are verified and evaluated to obtain the optimized and trained target AI model.

5. The intelligent equipment full life cycle management method as described in claim 4, characterized in that, The process of verifying and evaluating the accuracy and reliability of the AI ​​model to be adjusted to obtain the optimized and trained target AI model includes: The AI ​​model to be adjusted is subjected to cross-validation and A / B testing. The AI ​​model with an accuracy greater than a preset accuracy threshold and a stability greater than a preset stability threshold is selected as the target AI model for optimization and training.

6. The intelligent equipment full life cycle management method as described in claim 1, characterized in that, The process of deploying the target AI model, integrating the target AI model into the business process, managing and monitoring the target data, and providing interactive services through a user interface includes: The target AI model is converted into a deployable format according to the model deployment layer of the full lifecycle management system to obtain the target AI model after format conversion. The target AI model after format conversion is containerized and orchestrated to obtain an orchestrated AI model. Perform security and privacy authentication on the orchestration AI model, and integrate the authenticated orchestration AI model into the business process; The target data is managed and monitored by the service layer of the full lifecycle management system, and interactive services are provided through the user interface.

7. The intelligent equipment full life cycle management method as described in claim 6, characterized in that, The management and monitoring of the target data according to the service layer of the full lifecycle management system, and the provision of interactive services through the user interface, include: The target data is analyzed according to different business processes based on the service layer of the full lifecycle management system to obtain data analysis results; Based on the data analysis results, back up the data that needs to be backed up from the target data, and restore the data that needs to be restored from the target data. The full lifecycle management system is subjected to security audits according to a preset audit cycle, and vulnerability scans are performed on the full lifecycle management system according to a preset scanning cycle. The user interface layer of the full lifecycle management system provides interactive services to users through the user interface.

8. A smart equipment lifecycle management device, characterized in that, The intelligent equipment lifecycle management device includes: The data acquisition and preprocessing module is used to acquire the operating data of the intelligent equipment in real time, preprocess the operating data, and obtain the preprocessed target data. The AI ​​model training module is used to train a preset AI model according to a preset machine learning framework to obtain a trained target AI model. The data monitoring and management module is used to deploy the target AI model, integrate the target AI model into the business process, manage and monitor the target data, and provide interactive services through the user interface.

9. A smart equipment lifecycle management device, characterized in that, The intelligent equipment lifecycle management device includes: a memory, a processor, and an intelligent equipment lifecycle management program stored in the memory and executable on the processor, wherein the intelligent equipment lifecycle management program is configured to implement the steps of the intelligent equipment lifecycle management method as described in any one of claims 1 to 7.

10. A storage medium, characterized in that, The storage medium stores an intelligent equipment lifecycle management program, which, when executed by a processor, implements the steps of the intelligent equipment lifecycle management method as described in any one of claims 1 to 7.

Images