Product management system and management method oriented to full life cycle

Abstract

The invention discloses a full-life-cycle-oriented product management system and management method, and relates to the technical field of product management, and the method comprises the steps: dividing a product life cycle, and determining the product data management content of each stage; performing preliminary analysis on the product data in the cache by using an AI technology; according to a root node number and a version number of a product, combining with the preliminary analysis report, recursively obtaining product data of each sub-node, constructing a virtual simulation model by utilizing a digital twin technology and combining with a classification result, carrying out full life cycle tracking through a block chain technology, and carrying out detection and warning by utilizing an AI technology; when the life cycle of the product is finished, product data updating is stopped; according to the method, the product life cycle is divided, the data management content of each stage is clarified, and the AI technology and the digital twinning technology are introduced, so that automatic acquisition, anomaly detection and simulation modeling of the product data are realized, and the overall efficiency and accuracy of product data management are remarkably improved.

Description

Technical Field

[0001] The present invention relates to the technical field of product management, and in particular to a product management system and management method oriented to the entire life cycle. Background Art

[0002] With the development of Industry 4.0 and intelligent manufacturing, product life cycle management (PLM) has gradually become an important means of informatization in the manufacturing industry. Traditional product management methods often only focus on data management at a certain stage of the life cycle, such as the design stage or the manufacturing stage, and lack unified management and coordination of data throughout the life cycle. This one-sided management method is prone to the following problems: data at various stages are often scattered in different systems and departments, lacking unified standards and interfaces, resulting in untimely information transmission and affecting work efficiency. Due to the lack of unified version management and data tracking mechanisms, the data versions used by different departments may be inconsistent, which can easily lead to problems such as misoperation, design or manufacturing errors. At multiple stages of the product life cycle, it is difficult to track the source and changes of data at each stage, affecting product quality control and rapid location of problems. Summary of the invention

[0003] In view of the above existing problems, the present invention is proposed.

[0004] Therefore, the present invention provides a product management system and management method oriented to the entire life cycle to solve the complexity and inefficiency problems in the existing product life cycle management.

[0005] In order to solve the above technical problems, the present invention provides the following technical solutions: In a first aspect, an embodiment of the present invention provides a product management method for the entire life cycle, which includes: dividing the product life cycle into five stages: design, trial production, procurement, maintenance, and mass production, and clarifying the product data management content of each stage; After each life cycle stage is clearly defined, product data is automatically collected and cached according to the product's root node number and version number. AI technology is used to perform preliminary analysis on the cached product data, check and mark product data anomalies, and generate a preliminary analysis report. According to the root node number and version number of the product combined with the preliminary analysis report, recursively obtain the product data of each child node and classify it. Use digital twin technology combined with the classification results to build a virtual simulation model and obtain simulation data; Integrate simulation data and classified product data to generate product data packages. Use blockchain technology to track the entire life cycle of product data packages from issuance to receipt, and use AI technology for detection and warning. When the product life cycle ends, all product data will be automatically archived, marked as finished, and product data updates will stop.

[0006] As a preferred solution of the product management method for the entire life cycle of the present invention, the product data management content of each stage is clarified, including the following steps: The design phase includes managing the product's bill of materials, design drawings, technical documents, and sign-off records; The product trial production stage includes the management of process documents, trial production plans, experimental test reports and review records of each process node; The procurement phase includes managing supplier information, purchase orders, and material receipt records; The maintenance phase includes managing maintenance plans, maintenance records, and failure analysis reports; The mass production stage includes the management of manufacturing BOM data, manufacturing process documents, packaging BOM data and production record documents.

[0007] As a preferred solution of the product management method for the entire life cycle of the present invention, AI technology is used to perform a preliminary analysis on the product data in the cache, check and mark abnormal product data, and generate a preliminary analysis report, including the following steps: Use AI’s automated data analysis technology to check whether product data at each stage contains necessary fields; Define criteria for anomaly detection based on historical product data; The Isolation Forest algorithm is selected to randomly partition product data, identify outliers, detect abnormal data points, and mark abnormal data items that exceed the standard; All incomplete data items, missing fields, and marked abnormal data items are integrated to generate a preliminary analysis report.

[0008] As a preferred solution of the product management method for the entire life cycle of the present invention, the product data of each child node is recursively obtained and classified according to the root node number and version number of the product in combination with the preliminary analysis report, including the following steps: The sub-nodes refer to multiple hierarchical sub-nodes of a product in the product data life cycle; Start from the root node of the product, obtain the data of the root node, and then retrieve the cached product data based on the root node number and version number; Use recursive algorithms to call child nodes layer by layer, obtain all associated data of child nodes, combine with preliminary analysis reports, and adopt processing strategies for different data states; In each recursive call, the current child node data is added to the data collection, and finally the complete hierarchical structure of the entire product is constructed; The recursively acquired product data is classified into BOM files, design files, process files, maintenance files, and review files.

[0009] As a preferred solution of the product management method for the entire life cycle of the present invention, the digital twin technology is combined with the classification results to build a virtual simulation model to obtain simulation data, including the following steps: Using the root node number and version number of the product in the classification result, create an initial virtual model of the product in the digital twin virtual simulation platform; Import the recursively acquired BOM file into the initial virtual model to define the product hierarchy, bill of materials, component relationships, quantity, and cost; Import design files into the initial virtual model to build the product's geometry and physical model; Import process files into the initial virtual model to define the manufacturing process flow of the product; Import maintenance files into the initial virtual model to build the product maintenance plan and health monitoring model; Import the review records and signature records in the review documents into the initial virtual model to build a product quality control and traceability mechanism; The initial virtual model after the product data is imported is integrated to form a virtual simulation model and obtain simulation data.

[0010] As a preferred solution of the product management method for the entire life cycle of the present invention, the blockchain technology is used to track the product data package from issuance to receipt throughout the entire life cycle, and AI technology is used for detection and warning, including the following steps: When the product data package is generated, it is uploaded to the blockchain network to record the generation time and publisher information of the product data package; When transmitting product data packets, the smart contract will automatically require the recipient to verify, and after verification, record the received information; Through blockchain, the entire life cycle of a product data package is tracked from generation to final mass production; During the tracking process, AI technology is used to detect whether there is any deviation between simulation data and classified product data; If no deviation occurs, tracking will continue until the end of the product life cycle; If any deviation occurs, product data will be collected again, a virtual simulation model will be built, and AI technology will be used for detection until no deviation occurs. Tracking will continue until the end of the product life cycle.

[0011] As a preferred solution of the product management method for the entire life cycle of the present invention, when the product life cycle ends, all product data are automatically archived, marked as finished, and product data update is stopped, including the following steps: At the end of the product life cycle, all product-related data is packaged to form a complete archive package; Compress the archive package and store it in a secure long-term data cloud storage system; Generate a hash value for the archive package, and record the archive event and hash value in the blockchain; Update the product's life cycle status to ended, record the status update to the blockchain, and use smart contracts to automatically lock the product's data update permissions after archiving.

[0012] In a second aspect, the present invention provides a product management system for the entire life cycle, including: a life cycle data management module, which is responsible for dividing the product life cycle into five stages: design, trial production, procurement, maintenance and mass production, and defining the product data management content of each stage; The automatic data collection and AI preliminary analysis module is responsible for automatically collecting product data after each life cycle stage is clearly defined, caching it according to the product's root node number and version number, using AI technology to perform preliminary analysis on the cached product data, checking and marking product data anomalies, and generating a preliminary analysis report; The recursive data acquisition and digital twin simulation module is responsible for recursively acquiring the product data of each child node according to the root node number and version number of the product in combination with the preliminary analysis report, and classifying it. It uses the digital twin technology combined with the classification results to build a virtual simulation model and obtain simulation data. The data packet integration and blockchain tracking module is responsible for integrating simulation data and classified product data to generate product data packets. Through blockchain technology, the product data packets are tracked throughout their life cycle from issuance to receipt, and AI technology is used for detection and warning. The AI ​​detection and data archiving module is responsible for automatically archiving all product data, marking the end, and stopping product data updates when the product life cycle ends.

[0013] In a third aspect, an embodiment of the present invention provides a computer device, comprising a memory and a processor, wherein the memory stores a computer program, wherein the computer program, when executed by the processor, implements any step of the product management method for the entire life cycle as described in the first aspect of the present invention.

[0014] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, any step of the product management method for the entire life cycle as described in the first aspect of the present invention is implemented.

[0015] The beneficial effects of the present invention are as follows: by using AI technology to monitor and automatically analyze product data in real time, anomalies in the data can be quickly discovered, the cost of manual intervention can be reduced, and the accuracy and efficiency of data processing can be improved. By recursively acquiring the data of each child node and combining digital twin technology to build a virtual simulation model, the performance of the product at different life cycle stages can be simulated more accurately, further improving the reliability of product design and maintenance. By using blockchain technology to track product data packages throughout their life cycle, data transparency and traceability are achieved, ensuring that each link from data generation to archiving has a high degree of security and integrity, and significantly improving the overall efficiency and accuracy of product data management. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0017] Figure 1 This is a flowchart of the product management method for the entire life cycle in Example 1.

[0018] Figure 2 This is a flow chart of the preliminary analysis results and optimization in Example 1. DETAILED DESCRIPTION

[0019] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.

[0020] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0021] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0022] Example 1, reference Figure 1 and Figure 2 , which is the first embodiment of the present invention, and provides a product management method for the entire life cycle, including the following steps: S1. Divide the product life cycle into five stages: design, trial production, procurement, maintenance and mass production, and clarify the product data management content of each stage, including the following steps: The design phase includes managing the product's bill of materials (BOM), design drawings, technical documents, and sign-off records; The product trial production stage includes the management of process documents, trial production plans, experimental test reports and review records of each process node; The procurement phase includes managing supplier information, purchase orders, and material receipt records; The maintenance phase includes managing maintenance plans, maintenance records, and failure analysis reports; The mass production stage includes the management of manufacturing BOM data, manufacturing process documents, packaging BOM data and production record documents.

[0023] S2. After each life cycle stage is clearly defined, the product data is automatically collected and cached according to the product's root node number and version number. AI technology is used to perform preliminary analysis on the cached product data, check and mark product data anomalies, and generate a preliminary analysis report, including the following steps: The root node number is assigned by the product data management system to identify the main data node of the product, representing the basic information and structure of the entire product. The root node number usually does not change over time. Even if the design, production or maintenance phase of the product changes, the root node number remains unchanged. The version number is used to identify different iterations of a product. Whenever the design, manufacturing process, or maintenance plan of a product changes, a new version number is generated. The version number changes throughout the product life cycle to distinguish product data at different stages. Remove noise, correct format errors, and fill missing values ​​from the product data in the cache; Use AI's automated data analysis technology to check whether the product data at each stage contains necessary fields. For example, BOM data must contain fields such as material number, name, quantity, etc. Define criteria for anomaly detection based on historical product data, for example, the quantity of a material must be positive and cannot exceed a certain range; The Isolation Forest algorithm is selected to randomly partition product data, identify outliers, detect abnormal data points, and mark abnormal data items that exceed the standard; It should be noted that the Isolation Forest algorithm is an unsupervised learning algorithm suitable for detecting abnormal data points. During the analysis process, fields that can reflect product characteristics should be selected as input features; for example: material quantity, production time, and test data; material quantity is used to determine whether the material exceeds the normal range; production time is used to determine whether the production cycle is abnormal; test data such as pressure and temperature are used to determine whether it exceeds the expected range; Isolation Forest continuously splits the data by randomly selecting features (such as material quantity, production time, etc.) and randomly determining partition points; if a data point can be separated out with fewer partitioning steps, it is likely to be an anomaly. Because normal data points are usually close to other points, more partitioning steps are required to be isolated. The Isolation Forest algorithm generates an anomaly score for each data point. The higher the score, the more likely the data point is an anomaly. The algorithm divides the data points into normal points and abnormal points based on the score.

[0024] All incomplete data items, missing fields, and marked abnormal data items are integrated to generate a preliminary analysis report.

[0025] S3. According to the root node number and version number of the product combined with the preliminary analysis report, recursively obtain the product data of each child node and classify it. Use digital twin technology combined with the classification results to build a virtual simulation model and obtain simulation data, including the following steps: S3.1. Subnodes refer to the hierarchical subnodes of a product in the product data lifecycle; Start from the root node of the product (B: product root node number, C: product version number), obtain the root node data, and then retrieve the cached product data based on the root node number and version number; Use recursive algorithms to call sub-nodes layer by layer, obtain all associated data of sub-nodes (such as sub-BOM, sub-design files, sub-process files, etc.), and adopt different processing strategies for different data states (complete, missing, abnormal) based on the preliminary analysis report; Specifically, if the product data is marked as complete and without exception, the recursive acquisition of child node data can be triggered normally; if the product data is marked as incomplete but without exception, the re-collection process is triggered. After the re-collection is successful, the child nodes are processed recursively; if the product data is marked as incomplete and with exceptions, the node can be skipped, provided that the node is not important. Even if the node is skipped, the impact on the overall product structure is small; if the product data is marked as complete but with exceptions, it is pushed to the relevant personnel for manual correction. At this time, the recursive process will be paused and continue after the data correction is completed; In each recursive call, the current child node data is added to the data collection, and finally the complete hierarchical structure of the entire product is constructed; The termination condition of the recursive call is that when a node has no more child nodes, the recursion stops and the complete data set is returned; Furthermore, the recursively acquired product data may come from different systems and sources (such as PDM, ERP, MES, etc.), and the data format and structure may be inconsistent. In order to ensure the availability of the data in the subsequent stages, the system needs to standardize the data to ensure that the data format is unified and complies with international standards (such as ISO 10303, STEP standards). The standardization process includes data classification, cleaning, format conversion, etc. Classify the recursively acquired product data into BOM files, design files, process files, maintenance files, and review files; It should be noted that the BOM file includes information such as the list of materials, quantity, cost, etc.; the design documents include two-dimensional drawings, three-dimensional models, etc.; the process documents include information such as production process steps, working hours, equipment usage, etc.; the maintenance documents include maintenance records, maintenance plans, etc.; the review documents include review and signature records of each stage of design and manufacturing.

[0026] S3.2. Use the root node number and version number of the product in the classification result to create an initial virtual model of the product in the digital twin virtual simulation platform; Import the recursively acquired BOM file into the initial virtual model to define the product hierarchy, bill of materials, component relationships, quantity, cost and other information; Specifically, parse the bill of materials information in the BOM file, create the hierarchical structure of the product, and add each component in the BOM to the initial virtual model, associate material information such as quantity and cost for each component, and build the hierarchical structure of the product (such as parent-child relationship) based on the bill of materials and component relationships in the BOM file to ensure that the hierarchical structure of the virtual simulation model is consistent with the actual product; Import design files (such as 2D drawings and 3D models) into the initial virtual model to build the product's geometry and physical model; Specifically, the geometric data in the design file (such as 3D model files, CAD drawings) is parsed, and the design information (such as geometric shape, material properties, etc.) is added to each component of the initial virtual model. Through the material properties and structural information in the design file, the physical properties of each component, such as density, stiffness, strength, etc., are set for subsequent physical simulation; Import the process files into the initial virtual model to define the manufacturing process of the product, including production steps, working hours, equipment usage and other information; Specifically, the production steps and process routes in the process file are parsed, the manufacturing process flow is defined for each component in the initial virtual model, the working hours and equipment usage are associated, and a dynamic process flow is defined for each component in the initial virtual model to ensure that during the simulation, the system can simulate the production process of the product and track the execution of the process steps; Import maintenance files into the initial virtual model to build the product maintenance plan and health monitoring model; Specifically, the maintenance records and maintenance plans are analyzed, and maintenance plans (such as regular maintenance, failure prediction, etc.) are defined for each component in the initial virtual model. Through maintenance data, a health monitoring model for the product is established to simulate the wear and failure of the product at different stages of use, and to monitor the operating status of the product in real time; Import the review records and signature records in the review documents into the initial virtual model to build a product quality control and traceability mechanism; Specifically, analyze the review records to ensure that each design change and process adjustment is authorized, keep the review records in the virtual model, and ensure that the review data at each stage is traceable; Integrate the initial virtual model after the product data is imported to form a virtual simulation model and obtain simulation data; It should be noted that after completing the import of product data, the digital twin technology is used to check whether the material properties (such as density, elastic modulus, hardness, etc.) in the initial virtual model are consistent with the material data in the design file. If inconsistencies are found, these physical properties are calibrated. Check whether the geometric accuracy (such as curve radius, thickness, aperture, etc.) in the initial virtual model is consistent with the design file. If there is an error, the geometric accuracy needs to be adjusted to ensure that the physical behavior of the initial virtual model is accurate, calibrate the production process steps in the process file, ensure that the initial process flow is consistent with the actual product manufacturing process, calibrate the working hours and equipment usage of each process step, and ensure that subsequent manufacturing simulation can reflect the actual production process. After completing the verification and calibration of the initial virtual model, the virtual simulation model has been formed.

[0027] S4. Integrate the simulation data and the classified product data to generate a product data package. Use blockchain technology to track the product data package from issuance to receipt throughout its life cycle, and use AI technology for detection and warning, including the following steps: Integrate simulation data and classified product data into a standardized product data package (such as JSON or XML file). The data package should have a common hierarchical structure and cover various types of data, such as BOM, geometric design, simulation data, process flow, maintenance records, etc. When the product data package is generated, it is uploaded to the blockchain network to record the generation time and publisher information of the product data package; It should be noted that the generated product data package is uploaded to the blockchain network, and the generation time, publisher information and hash value of the product data package are recorded. The immutability of the blockchain ensures the authenticity and security of the data package; When transmitting product data packets, the smart contract will automatically require the recipient to verify, and after verification, record the received information; It should be noted that during the transmission process, the smart contract will ensure that the receiver verifies the integrity and authenticity of the data packet within the specified time. The receiver needs to perform the following verification steps: the receiver calculates the hash value of the received data packet and compares it with the hash value recorded on the blockchain to ensure that the data packet has not been tampered with, and checks the version number of the data packet to ensure that the latest version is received. After successful verification, the smart contract will automatically record the reception information and record the reception status and time of the data packet in the blockchain; Through blockchain, the entire life cycle of a product data package is tracked from generation to final mass production; During the tracking process, AI technology is used to detect whether there is any deviation between simulation data and classified product data; If no deviation occurs, tracking will continue until the end of the product life cycle; If any deviation occurs, product data will be collected again, a virtual simulation model will be built, and AI technology will be used for detection until no deviation occurs. Tracking will continue until the end of the product life cycle.

[0028] S5. When the product life cycle ends, all product data is automatically archived, marked as finished, and product data updates are stopped, including the following steps: At the end of the product life cycle, all product-related data should be packaged to form a complete archive package. The archive package should contain a complete product data tree structure to ensure easy traceability in future inquiries; Compress the archive package and store it in a secure long-term data cloud storage system to ensure that the data storage location has high availability and security; Generate a hash value for the archived package to ensure that the integrity and authenticity of the data package can be verified in the future, and record the archived event and hash value in the blockchain to ensure that the archived information cannot be tampered with and is traceable; Update the product's life cycle status to ended, record the status update to the blockchain, ensure that the product's life cycle end status cannot be tampered with, and use smart contracts to automatically lock the product's data update permissions after archiving.

[0029] This embodiment also provides a product management system for the entire life cycle, including: a life cycle data management module, which is responsible for dividing the product life cycle into five stages: design, trial production, procurement, maintenance and mass production, and clearly defining the product data management content of each stage; The automatic data collection and AI preliminary analysis module is responsible for automatically collecting product data after each life cycle stage is clearly defined, caching it according to the product's root node number and version number, using AI technology to perform preliminary analysis on the cached product data, checking and marking product data anomalies, and generating a preliminary analysis report; The recursive data acquisition and digital twin simulation module is responsible for recursively acquiring the product data of each child node according to the root node number and version number of the product in combination with the preliminary analysis report, and classifying it. It uses the digital twin technology combined with the classification results to build a virtual simulation model and obtain simulation data. The data packet integration and blockchain tracking module is responsible for integrating simulation data and classified product data to generate product data packets. Through blockchain technology, the product data packets are tracked throughout their life cycle from issuance to receipt, and AI technology is used for detection and warning. The AI ​​detection and data archiving module is responsible for automatically archiving all product data, marking the end, and stopping product data updates when the product life cycle ends.

[0030] This embodiment also provides a computer device, which is suitable for the situation of a product management method for the entire life cycle, including: a memory and a processor; the memory is used to store computer executable instructions, and the processor is used to execute computer executable instructions to implement the product management method for the entire life cycle proposed in the above embodiment.

[0031] The computer device may be a terminal, and the computer device includes a processor, a memory, a communication interface, a display screen and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, an operator network, NFC (near field communication) or other technologies. The display screen of the computer device may be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device may be a touch layer covered on the display screen, or a key, trackball or touchpad provided on the housing of the computer device, or an external keyboard, touchpad or mouse, etc.

[0032] This embodiment also provides a storage medium on which a computer program is stored. When the program is executed by a processor, the product management method for the entire life cycle proposed in the above embodiment is implemented; the storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (Static Random Access Memory, referred to as SRAM), electrically erasable programmable read-only memory (Electrically Erasable Programmable Read-Only Memory, referred to as EEPROM), erasable programmable read-only memory (Erasable Programmable Read Only Memory, referred to as EPROM), programmable read-only memory (Programmable Red-Only Memory, referred to as PROM), read-only memory (Read-Only Memory, referred to as ROM), magnetic storage, flash memory, magnetic disk or optical disk.

[0033] In summary, the present invention uses: AI technology to monitor and automatically analyze product data in real time, which can quickly discover anomalies in the data, reduce the cost of manual intervention, and improve the accuracy and efficiency of data processing. By recursively acquiring the data of each child node and combining digital twin technology to build a virtual simulation model, the performance of the product at different life cycle stages can be simulated more accurately, further improving the reliability of product design and maintenance. By using blockchain technology to track product data packages throughout their life cycle, data transparency and traceability are achieved, ensuring that each link from data generation to archiving has a high degree of security and integrity, and significantly improving the overall efficiency and accuracy of product data management.

[0034] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A product management method for the entire life cycle, characterized in that: include: Divide the product life cycle into five stages: design, trial production, procurement, maintenance and mass production, and clarify the product data management content of each stage; After each life cycle stage is clearly defined, product data is automatically collected and cached according to the product's root node number and version number. AI technology is used to perform preliminary analysis on the cached product data, check and mark product data anomalies, and generate a preliminary analysis report. According to the root node number and version number of the product combined with the preliminary analysis report, recursively obtain the product data of each child node and classify it. Use digital twin technology combined with the classification results to build a virtual simulation model and obtain simulation data; Integrate simulation data and classified product data to generate product data packages. Use blockchain technology to track the entire life cycle of product data packages from issuance to receipt, and use AI technology for detection and warning. When the product life cycle ends, all product data will be automatically archived, marked as finished, and product data updates will stop.

2. The product management method for the entire life cycle as claimed in claim 1, characterized in that: Clarify the product data management content at each stage, including the following steps: The design phase includes managing the product's bill of materials, design drawings, technical documents, and sign-off records; The product trial production stage includes the management of process documents, trial production plans, experimental test reports and review records of each process node; The procurement phase includes managing supplier information, purchase orders, and material receipt records; The maintenance phase includes managing maintenance plans, maintenance records, and failure analysis reports; The mass production stage includes the management of manufacturing BOM data, manufacturing process documents, packaging BOM data and production record documents.

3. The product management method for the entire life cycle as claimed in claim 2, characterized in that: Use AI technology to perform preliminary analysis on the product data in the cache, check and mark product data anomalies, and generate a preliminary analysis report, including the following steps: Use AI’s automated data analysis technology to check whether product data at each stage contains necessary fields; Define criteria for anomaly detection based on historical product data; The Isolation Forest algorithm is selected to randomly partition product data, identify outliers, detect abnormal data points, and mark abnormal data items that exceed the standard; All incomplete data items, missing fields, and marked abnormal data items are integrated to generate a preliminary analysis report.

4. The product management method for the entire life cycle as claimed in claim 3, characterized in that: According to the root node number and version number of the product combined with the preliminary analysis report, recursively obtain the product data of each child node and classify it, including the following steps: The sub-nodes refer to multiple hierarchical sub-nodes of a product in the product data life cycle; Start from the root node of the product, obtain the data of the root node, and then retrieve the cached product data based on the root node number and version number; Use recursive algorithms to call child nodes layer by layer, obtain all associated data of child nodes, combine with preliminary analysis reports, and adopt processing strategies for different data states; In each recursive call, the current child node data is added to the data collection, and finally the complete hierarchical structure of the entire product is constructed; The recursively acquired product data is classified into BOM files, design files, process files, maintenance files, and review files.

5. The product management method for the entire life cycle as claimed in claim 4, characterized in that: Using digital twin technology combined with classification results to build a virtual simulation model and obtain simulation data includes the following steps: Using the root node number and version number of the product in the classification result, create an initial virtual model of the product in the digital twin virtual simulation platform; Import the recursively acquired BOM file into the initial virtual model to define the product hierarchy, bill of materials, component relationships, quantity, and cost; Import design files into the initial virtual model to build the product's geometry and physical model; Import process files into the initial virtual model to define the manufacturing process flow of the product; Import maintenance files into the initial virtual model to build the product maintenance plan and health monitoring model; Import the review records and signature records in the review documents into the initial virtual model to build a product quality control and traceability mechanism; The initial virtual model after the product data is imported is integrated to form a virtual simulation model and obtain simulation data.

6. The product management method for the entire life cycle as claimed in claim 5, characterized in that: Through blockchain technology, the product data package is tracked throughout its life cycle from issuance to receipt, and AI technology is used for detection and warning, including the following steps: When the product data package is generated, it is uploaded to the blockchain network to record the generation time and publisher information of the product data package; When transmitting product data packets, the smart contract will automatically require the recipient to verify, and after verification, record the received information; Through blockchain, the entire life cycle of a product data package is tracked from generation to final mass production; During the tracking process, AI technology is used to detect whether there is any deviation between simulation data and classified product data; If no deviation occurs, tracking will continue until the end of the product life cycle; If any deviation occurs, product data will be collected again, a virtual simulation model will be built, and AI technology will be used for detection until no deviation occurs. Tracking will continue until the end of the product life cycle.

7. The product management method for the entire life cycle according to claim 6, characterized in that: When the product life cycle ends, all product data will be automatically archived, marked as finished, and product data updates will stop, including the following steps: At the end of the product life cycle, all product-related data is packaged to form a complete archive package; Compress the archive package and store it in a secure long-term data cloud storage system; Generate a hash value for the archive package, and record the archive event and hash value in the blockchain; Update the product's life cycle status to ended, record the status update to the blockchain, and use smart contracts to automatically lock the product's data update permissions after archiving.

8. A product management system for the entire life cycle, based on the product management method for the entire life cycle according to any one of claims 1 to 7, characterized in that: include: The life cycle data management module is responsible for dividing the product life cycle into five stages: design, trial production, procurement, maintenance and mass production, and clarifying the product data management content of each stage; The automatic data collection and AI preliminary analysis module is responsible for automatically collecting product data after each life cycle stage is clearly defined, caching it according to the product's root node number and version number, using AI technology to perform preliminary analysis on the cached product data, checking and marking product data anomalies, and generating a preliminary analysis report; The recursive data acquisition and digital twin simulation module is responsible for recursively acquiring the product data of each child node according to the root node number and version number of the product in combination with the preliminary analysis report, and classifying it. It uses the digital twin technology combined with the classification results to build a virtual simulation model and obtain simulation data. The data packet integration and blockchain tracking module is responsible for integrating simulation data and classified product data to generate product data packets. Through blockchain technology, the product data packets are tracked throughout their life cycle from issuance to receipt, and AI technology is used for detection and warning. The AI ​​detection and data archiving module is responsible for automatically archiving all product data, marking the end, and stopping product data updates when the product life cycle ends.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the product management method for the entire life cycle described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the product management method for the entire life cycle described in any one of claims 1 to 7 are implemented.

Images