A Full-Lifecycle Intelligent Data Mapping Method and System Based on Digital Models

Abstract

This application provides a method and system for intelligent full-lifecycle data mapping based on digital models, relating to the field of data management technology. The method includes: acquiring full-lifecycle data of a device to be processed uploaded by a user, determining the user's target data upload intention, identifying product modeling data and semantic business data within the full-lifecycle data, generating an initial 3D mapping model of the device to be processed based on the product modeling data, constructing a correspondence between the semantic business data and the product modeling data, and annotating the initial 3D mapping model with attributes based on this correspondence to obtain the target 3D mapping model. This application aims to improve the fragmentation, inconsistent data formats, and disconnect between device status and 3D models in existing device data management. It addresses the shortcomings of existing methods in data sharing, real-time monitoring, and decision support, improving the accuracy and intelligence level of device management.

Description

Technical Field

[0001] This application relates to the field of data management technology, and in particular to a method and system for intelligent mapping of full-cycle data based on digital models. Background Technology

[0002] With the increasing complexity of manufacturing equipment and the deepening of the intelligent manufacturing concept, enterprises are paying more and more attention to data management and collaborative utilization throughout the entire equipment lifecycle. In actual engineering, a large amount of structured and unstructured data is generated at each stage of equipment design, manufacturing, testing, delivery to operation and maintenance, such as drawings, process parameters, test reports, welding images, and maintenance records. This data contains rich engineering knowledge and status information, which is of great value for improving product quality, shortening delivery cycles, and optimizing maintenance strategies.

[0003] However, this full-product data is often scattered across different systems, with problems such as inconsistent formats, ambiguous semantics, and inconsistent granularity, making it difficult to organize and utilize in a unified manner. Summary of the Invention

[0004] This application provides a full-cycle intelligent data mapping method based on a digital model. The embodiments of this application adopt the following technical solutions:

[0005] In a first aspect, embodiments of this application provide a full-cycle intelligent data mapping method based on a digital model, the method comprising:

[0006] Acquire the full lifecycle data of the devices to be processed uploaded by the user, and determine the user's intention to upload the target data;

[0007] Determine the user's target data upload intent, including product modeling data and semantic business data across the entire data lifecycle;

[0008] Based on the product modeling data that determines the user's target data upload intent, an initial 3D mapping model of the device to be processed is generated.

[0009] Based on the user's data upload intent, construct the correspondence between semantic business data that determines the user's target data upload intent and product modeling data that determines the user's target data upload intent;

[0010] Based on the product repair attribute data in the semantic business data of the user's target data upload intent, the initial three-dimensional mapping model of the user's target data upload intent is annotated with first-level attributes. Based on the product operation status attribute data in the semantic business data of the user's target data upload intent, the initial three-dimensional mapping model of the user's target data upload intent is annotated with second-level attributes. Based on the product quality inspection and evaluation attribute data in the semantic business data of the user's target data upload intent, the initial three-dimensional mapping model of the user's target data upload intent is annotated with third-level attributes.

[0011] By integrating the first-level attribute annotation results of the initial 3D mapping model for determining the user's target data upload intention, the second-level attribute annotation results of the initial 3D mapping model for determining the user's target data upload intention, and the third-level attribute annotation results of the initial 3D mapping model for determining the user's target data upload intention, a target 3D mapping model for determining the user's target data upload intention is obtained.

[0012] In one optional implementation, determining the user's target data upload intention involves obtaining the user's uploaded full-cycle data of the device to be processed, and determining the user's target data upload intention includes:

[0013] Based on the user type identifier carried in the full-cycle data to determine the user's target data upload intention, the user type data upload intention of the user is determined.

[0014] Based on the data format of the full-cycle data and the user's target data upload intention, determine the user's target data upload intention and the user's data format upload intention;

[0015] The user's target data upload intention is determined by matching the user type data upload intention with the data format upload intention.

[0016] In one optional implementation, based on the data type identifier and semantic recognition results carried by the full-lifecycle data, product modeling data and semantic business data in the full-lifecycle data are determined, including:

[0017] Based on the semantic recognition results, the first-level filtering of the full-cycle data is performed to obtain the first data set;

[0018] Based on the data type identifier, a second level of filtering is performed on the full-cycle data to obtain a second data set;

[0019] Based on the intersection of the first and second data sets, product modeling data and semantic business data are determined in the full-cycle data.

[0020] In one optional implementation, an initial 3D mapping model of the device to be processed is generated based on product modeling data, including:

[0021] Based on the structural topology data and geometric dimension data in the product modeling data, a three-dimensional geometric skeleton model of the device to be processed is generated.

[0022] Based on the assembly relationship data and component identification information in the product modeling data, the three-dimensional geometric skeleton model is constructed and identified and bound at the component level to generate the initial three-dimensional mapping model of the device to be processed.

[0023] In one optional implementation, a three-dimensional geometric skeleton model of the device to be processed is generated based on the structural topology data and geometric dimension data in the product modeling data, including:

[0024] Analyze the product modeling data to determine the assemblies that constitute the three-dimensional geometric skeleton model and the assembly identifiers corresponding to the assemblies;

[0025] Based on the geometric dimension data in the product modeling data, determine the geometric dimension data of each assembly, and generate multiple three-dimensional geometric skeleton models of each assembly based on the geometric dimension data of each assembly.

[0026] Based on the structural topology data in the product modeling data, the topological connection relationships between each assembly are determined, and each assembly is assembled according to the topological connection relationships between each assembly to obtain a three-dimensional geometric skeleton model of the device to be processed.

[0027] In one optional implementation, based on the user's data upload intent, a correspondence between semantic business data and product modeling data is constructed, including:

[0028] Parse semantic business data and extract semantic anchor feature information related to the data upload intent. The semantic anchor feature information includes at least the device location, component name, number, fault type, and operation time.

[0029] Based on the semantic matching strategy corresponding to the data upload intent, the target model objects in the product modeling data are filtered and associated using semantic anchor feature information to establish a binding relationship between semantic business data and product modeling data.

[0030] In one optional implementation, the target 3D mapping model is obtained by integrating the first-level attribute annotation results, the second-level attribute annotation results, and the third-level attribute annotation results of the initial 3D mapping model, including:

[0031] The multi-level attribute annotation results of the initial 3D mapping model are uniformly parsed and their formats standardized.

[0032] Based on component nodes, establish first-level attribute annotation results, second-level attribute annotation results, and third-level attribute annotation results.

[0033] The attribute fusion mapping relationship;

[0034] Based on the attribute fusion mapping relationship, a target 3D mapping model is generated.

[0035] Secondly, embodiments of this application provide a full-cycle intelligent data mapping system based on a digital model, the system comprising:

[0036] The acquisition module is used to acquire the full lifecycle data of the device to be processed uploaded by the user, determine the user's target data upload intention, and identify the product modeling data and semantic business data in the full lifecycle data.

[0037] The first determination module is used to determine the product modeling data and semantic business data in the full lifecycle data;

[0038] The first model building module is used to generate an initial 3D mapping model of the device to be processed based on the product modeling data.

[0039] The second determination module is used to construct the correspondence between semantic business data and product modeling data based on the user's data upload intent;

[0040] The second model construction module is used to perform first-level attribute annotation on the initial 3D mapping model based on product maintenance attribute data in the semantic business data, perform second-level attribute annotation on the initial 3D mapping model based on product operating status attribute data in the semantic business data, perform third-level attribute annotation on the initial 3D mapping model based on product quality inspection and evaluation attribute data in the semantic business data, and integrate the results of the first-level attribute annotation, the second-level attribute annotation, and the third-level attribute annotation of the initial 3D mapping model to obtain the target 3D mapping model.

[0041] In one optional implementation, the acquisition module includes:

[0042] The first determination submodule is used to determine the user's intention to upload user type data based on the user type identifier carried in the full-cycle data.

[0043] The second determination submodule is used to determine the user's data format upload intention based on the data format of the full-cycle data;

[0044] The third determination submodule is used to determine the user's target data upload intention based on the matching relationship between the user's type data upload intention and the data format upload intention.

[0045] In one alternative implementation, the first model building module includes:

[0046] The skeleton model construction submodule is used to generate a three-dimensional geometric skeleton model of the device to be processed based on the structural topology data and geometric dimension data in the product modeling data.

[0047] The mapping submodule is used to construct and bind the component hierarchy of the 3D geometric skeleton model based on the assembly relationship data and component identification information in the product modeling data, so as to generate the initial 3D mapping model of the device to be processed.

[0048] In one alternative implementation, the skeleton model construction submodule includes:

[0049] The parsing unit is used to parse product modeling data and determine the assemblies that constitute the three-dimensional geometric skeleton model and the assembly identifiers corresponding to the assemblies.

[0050] The determination unit is used to determine the geometric dimensions of each assembly based on the geometric dimension data in the product modeling data, and to generate multiple three-dimensional geometric skeleton models of each assembly based on the geometric dimension data of each assembly.

[0051] The splicing unit is used to determine the topological connection relationship between each assembly based on the structural topology data in the product modeling data, and to assemble each assembly according to the topological connection relationship between each assembly to obtain a three-dimensional geometric skeleton model of the device to be processed.

[0052] Thirdly, this application also provides an electronic device, which includes: a memory and one or more processors, the memory being coupled to the processors; wherein the memory stores computer program code, the computer program code including computer instructions, which, when executed by the processor, cause the electronic device to perform the method in any of the possible design embodiments of the first aspect described above.

[0053] Fourthly, this application provides a computer-readable storage medium including computer instructions; when the computer instructions are executed on an electronic device, they cause the electronic device to perform the method described in the first aspect above and any possible design of the above.

[0054] Fifthly, this application provides a computer program product that, when run on an electronic device, causes the electronic device to perform the method described in the first aspect above and any possible design of the above.

[0055] This application provides a full-lifecycle data intelligent mapping method based on digital models. By deeply integrating various data throughout the entire equipment lifecycle (such as design, manufacturing, operation, and maintenance) with the equipment's 3D digital model, it solves the problems of data silos, information fragmentation, and poor real-time performance in traditional equipment management methods. Through intelligent mapping technology, product modeling data and semantic business data (such as maintenance records, operating status, and quality inspection results) are accurately mapped and applied to the 3D model. This not only improves the intelligence and accuracy of equipment management but also achieves efficient integration and real-time sharing of cross-system data. Combined with visualization, users can intuitively obtain the comprehensive status of the equipment, quickly perform fault diagnosis, risk prediction, and maintenance decisions, thereby optimizing maintenance strategies, improving product quality, shortening delivery cycles, and significantly reducing operation and maintenance costs.

[0056] The technical effects of the second to fifth aspects refer to the technical effects of the first aspect and any of its embodiments, and will not be repeated here. Attached Figure Description

[0057] Figure 1 A flowchart illustrating the steps of a full-cycle intelligent data mapping method based on a digital model, as provided in this application embodiment;

[0058] Figure 2 This is a schematic diagram of the structure of a full-cycle data intelligent mapping system based on a digital model, provided in an embodiment of this application. Detailed Implementation

[0059] The terminology used in the following embodiments is for the purpose of describing particular embodiments only and is not intended to be limiting of this application. As used in the specification and appended claims of this application, the singular expressions “a,” “an,” “the,” “the,” and “this” are intended to also include expressions such as “one or more,” unless the context clearly indicates otherwise. It should also be understood that in the following embodiments of this application, “at least one” and “one or more” refer to one or more (including two). The character “ / ” generally indicates that the preceding and following objects are in an “or” relationship.

[0060] The technical solutions of the embodiments of this application will be described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments.

[0061] Hereinafter, the terms "first," "second," etc., are used for descriptive convenience only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Therefore, a feature defined with "first," "second," etc., may explicitly or implicitly include one or more of that feature. In the description of this application, unless otherwise stated, "multiple" means two or more. For example, multiple processing units refer to two or more processing units.

[0062] Furthermore, in the embodiments of this application, "upper," "lower," "left," and "right" are not limited to the orientation of the components schematically placed in the accompanying drawings. It should be understood that these directional terms can be relative concepts, used for relative description and clarification, and can change accordingly depending on the orientation of the components in the accompanying drawings. In the accompanying drawings, for clarity, the thickness of layers and regions is exaggerated, and the dimensional proportions between the parts in the drawings do not reflect the actual dimensional proportions.

[0063] In the embodiments of this application, unless otherwise explicitly specified and limited, the term "connection" should be interpreted broadly. For example, "connection" can be a fixed connection, a detachable connection, or an integral part; it can be a direct connection or an indirect connection through an intermediate medium. In addition, the term "electrical connection" can be a direct electrical connection or an indirect electrical connection through an intermediate medium.

[0064] In this application, the term "module" typically refers to a logically divided functional structure. A "module" can be implemented purely in hardware, or a combination of hardware and software. In this application, "and / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, B existing alone, or both A and B existing simultaneously.

[0065] In this application, the terms "exemplary" or "for example" are used to indicate that something is an example, illustration, or description. Any embodiment or design described as "exemplary" or "for example" in this application should not be construed as being better or more advantageous than other embodiments or designs. Specifically, the use of terms such as "exemplary" or "for example" is intended to present the relevant concepts in a specific manner.

[0066] With the continuous increase in the complexity of manufacturing equipment and the accelerated implementation of intelligent manufacturing concepts, manufacturing enterprises are paying increasing attention to the unified management and collaborative utilization of data generated at each stage of the equipment's entire lifecycle. In actual engineering scenarios, from product initiation, design and development, manufacturing and processing, quality inspection, delivery and commissioning, to operation and maintenance, fault repair, and even decommissioning, each stage generates a large amount of multi-source heterogeneous business data. This business data contains key engineering knowledge, process parameters, operating status, and quality information, which is of great value in supporting product quality control, lifecycle management, and intelligent analysis and decision-making. However, limited by traditional system architecture and data management methods, current lifecycle data generally faces the following bottlenecks: On the one hand, data is distributed across multiple departments and information systems, resulting in significant data silos. The lack of standardized data interfaces and semantic mapping mechanisms between different systems makes data flow and sharing difficult. On the other hand, data formats are diverse and standards are not uniform. Data from different sources differ significantly in structure, semantics, granularity, and other dimensions, making efficient integration and correlation analysis difficult. Furthermore, much critical data is still stored in the form of manual documents, images, or tables, which are semantically ambiguous, structurally unclear, and lack automatic parsing and intelligent recognition methods. This makes it difficult to support the construction of complex models and real-time data-driven visualization. Traditional project management and operation systems often rely on static reports or preset views, which are difficult to reflect real-time data changes and complex status linkages, resulting in delayed project status assessments, untimely risk identification, and insufficient decision-making basis.

[0067] To address the aforementioned issues, this application proposes the following technical concept: By performing structured extraction and semantic recognition on multi-source heterogeneous data generated during the design, manufacturing, testing, delivery, and operation and maintenance stages of equipment, product modeling data and semantic business data are distinguished, and an initial 3D mapping model is constructed based on the product modeling data. Furthermore, through semantic anchor point recognition and component identifier parsing, the correspondence between semantic business data and the 3D model is established, enabling attribute annotation and intelligent embedding of semantic information within the model. Ultimately, a target 3D mapping model is formed that integrates geometric structure and business semantics, supporting dynamic updates and visual analysis.

[0068] In a first aspect, embodiments of this application provide a full-cycle intelligent data mapping method based on a digital model, the method comprising:

[0069] S101: Obtain the full lifecycle data of the device to be processed uploaded by the user, and determine the user's target data upload intention.

[0070] In this embodiment, the equipment to be processed refers to equipment involved in all stages of its entire lifecycle, including design, manufacturing, testing, delivery, use, maintenance, and operation. It includes any equipment requiring data processing, status monitoring, fault diagnosis, maintenance, or optimization. Specifically, the equipment to be processed can be industrial equipment, machinery, electronic products, transportation vehicles, intelligent devices, etc., in a production line. Users can include designers, manufacturers, testers, and maintenance personnel, who generate a large amount of business data at different stages of equipment design, manufacturing, testing, delivery, and operation and maintenance. To achieve comprehensive data collection throughout the entire lifecycle, the system identifies various user identities based on preset user permissions and task nodes, guiding them to upload data content within their authorized scope. Simultaneously, to ensure data traceability and consistency, the system establishes a unified data acquisition interface and version management mechanism, capable of recording metadata such as the uploading user, time, source system, and associated project nodes for each piece of data.

[0071] A user's target data upload intent refers to the implicit business objectives and expected application path within the data management system when uploading full-lifecycle data at a specific lifecycle node. Examples include: driving structural modeling, supplementing production history, annotating test results, recording fault events, updating operational status, or collecting historical archives. This upload intent reflects the business semantics of the data and its corresponding model entity scope, functional dimensions, and attachment strategies. It can be obtained by comprehensively analyzing user type identifiers, data structure characteristics, time tags, data sources, and related metadata.

[0072] By identifying a user's intended data upload, semantic analysis and processing target definition of the data upload behavior can be achieved, thus providing a foundation for the system to build a clear data processing path. This process not only helps to clarify the "business orientation of data content," but can also be used to automatically determine the data organization method and mapping target, improving the system's ability to classify and process heterogeneous full-lifecycle data and its modeling and integration efficiency.

[0073] The specific steps include:

[0074] S1011: Determine the user's user type data upload intention based on the user type identifier carried in the full-cycle data;

[0075] S1012: Determine the user's data format upload intention based on the data format of the full-cycle data;

[0076] S1013: Determine the user's target data upload intention based on the matching relationship between the user type data upload intention and the data format upload intention.

[0077] In the implementations of S1011 to S1013, firstly, the user type data upload intent is determined based on the user type identifier carried in the full-cycle data. The user type identifier is pre-issued by the upper-level platform before user access and possesses unique and structured attributes, typically bound to user account permissions, business roles, and project stages. After identifying this identifier, the system determines the user's typical upload purpose and processing scope within the current business context based on the built-in role intent mapping rule set. For example, design users are typically associated with structural modeling or design changes; manufacturing users correspond to process data acquisition or quality control; testing users focus on reporting test results or anomaly record annotation; and operation and maintenance users focus on operational status logs or fault handling records, thus forming the user type data upload intent. Secondly, the system parses the data format of the uploaded full-cycle data, including but not limited to file encapsulation type, structural specifications, data field composition, and expression granularity. Combining the format type with its typical usage in the business process, the system infers the processing target indicated by the data format, thus forming the data format upload intent. For example, BOM (Bill of Materials) format data might be intended for binding to a material information model, image data for surface defect mapping, and structured messages for performance indicator collection. Finally, based on the matching relationship between the user's data upload intent based on type and data format, the user's target data upload intent is comprehensively inferred. As an example, if the user role is an inspector and the data format is an image file, the matching result could be: defect image annotation.

[0078] S102: Identify product modeling data and semantic business data in the full lifecycle data.

[0079] In this implementation, the system first acquires full-cycle data related to the equipment to be processed from multiple data sources. This data includes, but is not limited to, CAD drawings, 3D modeling files, and bills of materials (BOMs) generated during the design phase; process parameters and assembly flow records during the manufacturing phase; quality inspection reports and defect images during the testing phase; acceptance records and user manuals during the delivery phase; and maintenance work orders, monitoring logs, and maintenance plans generated during the operation and maintenance phase. Since this data is typically stored in heterogeneous formats (such as PDF, Excel, images, and 3D model files) across different systems (such as PDM, MES, SCADA, PLM, and ERP), the system first connects to the data sources and completes preliminary data aggregation and standardization processing to ensure consistency and accuracy in subsequent analysis. After data aggregation, the system uses a preset semantic recognition model and data classification rules to perform content analysis and intelligent parsing of the full-cycle data. Product modeling data primarily refers to drawings, 3D model files, and their associated attributes containing information such as equipment structure, dimensions, and connection relationships, forming the basic geometric semantics of the 3D mapping model. Semantic business data, on the other hand, refers to textualized and tagged information related to equipment status, task execution, and maintenance requirements, such as inspection conclusions, fault descriptions, maintenance suggestions, responsible units, and time nodes. This type of data often exists in document records, report descriptions, image annotations, or system logs, requiring in-depth understanding and extraction through technologies such as Natural Language Processing (NLP) and image recognition.

[0080] The specific steps may include:

[0081] S1021: Based on the data type identifier and semantic recognition results carried by the full-cycle data, determine the product modeling data and semantic business data in the full-cycle data.

[0082] In this embodiment, the product modeling data and semantic business data in the full-cycle data are then determined based on the data type identifier and semantic recognition results carried by the data. For structured data, the system can directly classify it according to the data type identifier bound at the time of upload; for unstructured data (such as text, images, tables, etc.), a preset semantic recognition model (such as a natural language processing model or image recognition model) is used to extract keywords, behavioral features, and semantic context to infer the category to which the data belongs. Specifically, if the data content involves the geometric dimensions, structural topology, assembly relationships, etc. of the equipment, the system identifies it as product modeling data; if the data reflects semantic information such as equipment status, usage behavior, maintenance records, and operation procedures, it is identified as semantic business data. Through this step, the system achieves automatic classification and organization of massive heterogeneous data, providing a high-quality, structured input data source for subsequent intelligent processing processes such as 3D modeling and attribute annotation, thereby improving the system's data processing efficiency and semantic fusion capabilities.

[0083] In one feasible implementation, based on the data type identifier and semantic recognition results carried by the full-lifecycle data, product modeling data and semantic business data in the full-lifecycle data are determined, including:

[0084] Based on the semantic recognition results, the first-level filtering of the full-cycle data is performed to obtain the first data set;

[0085] Based on the data type identifier, a second level of filtering is performed on the full-cycle data to obtain a second data set;

[0086] Based on the intersection of the first and second data sets, product modeling data and semantic business data are determined in the full-cycle data.

[0087] In this embodiment, the uploaded full-cycle data content is analyzed based on a semantic recognition model (such as natural language processing or image recognition technology) to identify information containing key business semantics, such as equipment structural features, defect descriptions, and maintenance behaviors. Data with business significance is then selected to form a first data set. Next, the system performs structured classification of the full-cycle data according to the data type identifier bound to each data entry during upload, forming a second data set. Finally, the system takes the intersection of the first and second data sets to ensure that the selection results have both effective semantic content and meet the structural type requirements, thereby determining the product modeling data and semantic business data in the full-cycle data.

[0088] As an example: Suppose the uploaded data includes a 3D structural model file A (data type identified as "CAD model", semantic recognition result includes "assembly relationship, structural dimensions"), an inspection report B (type identified as "inspection report", content description is "crack depth, weld defect"), an operation and maintenance log C (type is "operation and maintenance record", content is "replacement of parts, fault handling"), and a welding image D (type is "inspection image", AI recognition result is "defect area"). Then file A is classified as product modeling data, and files B, C, and D are classified as semantic business data.

[0089] S103: Generate the initial 3D mapping model of the device to be processed based on the product modeling data.

[0090] In this embodiment, the geometric information in the product modeling data is first parsed. This data typically includes information such as the device's geometric dimensions, structural topology, and component relationships, and is usually stored in the form of CAD drawings, 3D models, and assembly instructions. By parsing this data, the three-dimensional geometric shapes of each component of the device and their connection relationships, such as position, angle, and connection points, are extracted. This geometric data will form the basis for constructing the initial three-dimensional mapping model.

[0091] Next, the extracted geometric data is converted into three-dimensional spatial coordinates, and a preliminary three-dimensional model framework is constructed based on these coordinates. During this process, three-dimensional modeling algorithms (such as B-Rep modeling, mesh modeling, and SolidModeling) are used to generate the initial three-dimensional skeleton of the device. Specifically, each component is positioned in appropriate locations in three-dimensional space according to its size, shape, and positional relationships, generating the basic three-dimensional structure of the entire device.

[0092] After geometric modeling is completed, the model undergoes preliminary verification and optimization. For example, it checks whether the connection methods between components conform to design specifications and whether there are issues such as deformation or collisions. At this point, although the initial 3D mapping model of the equipment already has the shape and basic structure of the equipment, it does not yet contain business-level information, nor has it been annotated with detailed attributes.

[0093] After completing the initial 3D modeling, metadata such as model number and component identifier will be established for the 3D model to facilitate subsequent integration with semantic business data. At this stage, the initial 3D mapping model is only a physical representation of the device. Subsequent steps will further enrich the model by associating it with semantic business data to ensure that it reflects the device's true attributes, usage status, maintenance requirements, and other information.

[0094] The specific steps may include:

[0095] S1031: Generate a three-dimensional geometric skeleton model of the device to be processed based on the structural topology data and geometric dimension data in the product modeling data.

[0096] In this embodiment, the structural topology data of the equipment is first extracted from the product modeling data. This data describes the relationships and connection methods between the various components of the equipment. Structural topology data typically includes the relative position of each component, connection relationships, assembly sequence, connection points, and other structural information. By parsing this data, it is possible to identify how the components in the equipment are combined and the dependencies between them.

[0097] Next, the geometric dimensions of the equipment are extracted from the product modeling data. This data typically includes the dimensional parameters of each component (such as length, width, height, diameter, etc.) and their geometric shape characteristics (such as rectangle, circle, sphere, complex freeform shape, etc.). This geometric data will be used to define the shape of the components, ensuring that the dimensions of each component in three-dimensional space match the design requirements.

[0098] Combining structural topology data and geometric dimension data, a 3D geometric skeleton model of the device is generated using 3D modeling techniques. In this step, based on the geometric dimensions and topological relationships of the components, the positions and shapes of all components are placed in 3D space to form the initial 3D framework of the device. This model, called the 3D geometric skeleton model, represents the basic structure and shape of the device, but does not involve any additional information such as specific materials, colors, or surface treatments.

[0099] In one feasible implementation, generating a three-dimensional geometric skeleton model of the device to be processed includes:

[0100] Analyze the product modeling data to determine the assemblies that constitute the three-dimensional geometric skeleton model and the assembly identifiers corresponding to the assemblies;

[0101] Based on the geometric dimension data in the product modeling data, determine the geometric dimension data of each assembly, and generate multiple three-dimensional geometric skeleton models of each assembly based on the geometric dimension data of each assembly.

[0102] Based on the structural topology data in the product modeling data, the topological connection relationships between each assembly are determined, and each assembly is assembled according to the topological connection relationships between each assembly to obtain a three-dimensional geometric skeleton model of the device to be processed.

[0103] In this embodiment, the product modeling data is first parsed to identify and extract the various assemblies that constitute the equipment. Each assembly may consist of multiple parts, which are integrated together according to design requirements to form the various functional units of the equipment. For example, a mechanical device may have multiple assemblies, such as "power," "transmission," and "control panel." Each assembly has a corresponding assembly identifier, which is used to uniquely identify the assembly and ensure that the attributes, location, and function of the assembly can be accurately tracked in subsequent processing.

[0104] Next, based on the geometric dimensions in the product modeling data, the geometric dimensions of each assembly are determined, such as length, width, height, thickness, diameter, and curvature. This geometric data is typically provided by CAD models, design documents, or other structured data, ensuring that the dimensional information of each assembly matches the design requirements. Based on this dimensional data, a 3D geometric skeleton model of each assembly is generated. At this point, each assembly is treated as an independent 3D structural block with precise geometry and dimensions. The generated 3D geometric skeleton model provides the foundation for subsequent 3D assembly and integration.

[0105] Based on this, and according to the structural topology data in the product modeling data, the topological connections between each assembly are identified, that is, how each assembly is connected to each other through elements such as interfaces, connection points, or assembly holes. Topology data typically defines the relative positions, mating methods, and connection types between assemblies; for example, assembly A and assembly B are connected through screw holes, and assembly C is embedded in the slot of assembly D. Based on these topological connections, the assemblies are automatically assembled using appropriate assembly methods to form a complete three-dimensional geometric skeleton model of the device to be processed.

[0106] This three-dimensional geometric skeleton model is not merely a simple geometric shape; it accurately represents the connection methods and relative positions between the various functional modules and components of the device under test, thus laying the foundation for subsequent equipment analysis, simulation, and optimization. After the three-dimensional geometric skeleton model is constructed, the physical structure of the device is basically formed, and further refinement and enhancement can be carried out, such as adding information on material properties, color, and kinematic characteristics.

[0107] S1032: Based on the assembly relationship data and component identification information in the product modeling data, construct and bind the component hierarchy of the three-dimensional geometric skeleton model to generate the initial three-dimensional mapping model of the device to be processed.

[0108] In this implementation, the assembly relationship data is first used to identify how the various components in the equipment are assembled. This data typically describes the connection methods between different components, such as which components are nested together, which components are combined through connection points or interfaces, and how they are connected by bolts, welding, snap-fits, etc. By analyzing the assembly relationship data, the overall structure of the equipment and the logical and physical connection relationships between the various components can be understood.

[0109] Secondly, each component in the 3D geometric skeleton model will be assigned a unique identifier based on its component identification information. Component identification information typically includes each component's number, name, material type, and functional category, used to clearly identify the role, function, and location of each component within the equipment. By binding this identification information to the corresponding component in the 3D model, it can be ensured that each component can be accurately identified, tracked, and managed within the model.

[0110] Next, based on the parsed assembly relationship data and component identification information, a component-level hierarchical construction is performed on the 3D geometric skeleton model. Component-level hierarchical construction means decomposing the equipment into different hierarchical structures based on the interdependencies and assembly relationships between components, starting from the bottom layer of individual parts, progressing to sub-components in the middle layers, and finally to the top layer of the complete assembly. Each level of component is assigned a specific function and location to ensure an organized presentation within the overall equipment structure. This process helps build a clear equipment structure tree, thereby improving the efficiency of equipment management, maintenance, and updates.

[0111] Finally, these hierarchical structures and identification information are bound to the 3D geometric skeleton model to generate an initial 3D mapping model. This initial 3D mapping model not only contains the geometric information and assembly relationships of the equipment, but also integrates information such as the function, category, and location of each component into the model through identification binding. In this way, the model not only has the ability to present visual information, but also provides business information related to equipment operation and maintenance.

[0112] S104: Based on the user's data upload intent, construct the correspondence between semantic business data and product modeling data.

[0113] In this implementation, the first step is to parse and identify semantic business data. This data is typically unstructured or semi-structured, containing information about equipment status, usage, maintenance history, etc. Semantic business data may originate from multiple business domains, such as equipment operation data, sensor data, maintenance records, inspection reports, operation logs, etc. This data itself often cannot be directly combined with a 3D model; therefore, semantic recognition technologies (such as natural language processing, image recognition, data mining, etc.) are needed to transform this unstructured data into structured semantic information. For example, keywords such as "fault code," "replacement of parts," and "welding defects" in the text can be identified and labeled as specific business attributes.

[0114] Next, each data item in the semantic business data will be labeled based on the geometric information contained in the product modeling data (such as the identification, size, and location of each component). For example, if a maintenance record mentions a drive shaft failure, the semantic business data "drive shaft failure" will be associated with "drive shaft component" in the 3D model to ensure that the maintenance record corresponds to the correct component in the 3D model. Furthermore, business data can be accurately mapped to specific components or assemblies in the equipment model using component identification information, location coordinates, or topological relationships.

[0115] Simultaneously, based on the time information of business data, such as the time of failure and the time of maintenance completion, the business data will be combined with the lifecycle stage of the 3D model. In actual operation, a certain component may have different maintenance records or changes in operating status at different points in time. Based on this time information, the display status of the 3D model will be dynamically adjusted to reflect the current status of the equipment.

[0116] Finally, the correspondence between the generated semantic business data and product modeling data is stored in a database in some form for subsequent analysis, querying, and visualization. This mapping relationship allows for the combination of device geometric information and business information in subsequent displays or analyses. The specific steps include:

[0117] S1041: Parse semantic business data and extract semantic anchor feature information. The semantic anchor feature information shall include at least the equipment location, component name, number, fault type, and operation time.

[0118] S1042: Based on a preset semantic matching strategy, semantic anchor features are matched with corresponding component identification information to establish a binding relationship between semantic business data and product modeling data.

[0119] In the implementations of S1041 to S1042, semantic anchor feature information is first extracted from the semantic business data of the equipment. This feature information typically includes the equipment's location, component name, serial number, fault type, and operation time. This information often appears in unstructured or semi-structured form and may come from data sources such as maintenance records, fault logs, and operation reports. By performing semantic analysis on this data (such as natural language processing and image recognition technologies), core information related to the equipment and components can be extracted. Next, according to a preset semantic matching strategy, the semantic anchor feature information is precisely matched with the component identification information in the product modeling data. First, keyword matching is used, for example, matching "drive shaft" with "drive shaft component identification" in the product modeling data. If the component name or serial number mentioned in the semantic business data matches the identification information in the product modeling data, they are bound together. In addition, matching is also performed based on the equipment location. If the equipment mentioned in the semantic business data is located in "workshop A" and the product modeling data also contains the specific location of the equipment, the correspondence between the two data will be further confirmed. For fault types, the matching relationship is ensured by comparing the fault types in the semantic business data with the fault descriptions in the equipment modeling data. For example, "overload fault" is associated with the fault records of related components in the equipment model. Additionally, operating time is also an important matching feature. Time information is compared with the equipment's maintenance records or inspection logs to ensure that the equipment's fault and maintenance history corresponds to the timeline in its 3D model. Besides simple matching strategies, topology matching is also considered, i.e., determining the relationship between semantic data and the equipment model by analyzing the equipment's assembly relationships and the relative positions of components. Through these matching strategies, a binding relationship between semantic business data and product modeling data can be established, ensuring that the business data of each component (such as fault records, maintenance logs, inspection reports, etc.) can be accurately mapped to its corresponding component in the 3D model.

[0120] S105: Based on the product maintenance attribute data in the semantic business data, perform first-level attribute annotation on the initial 3D mapping model; based on the product operating status attribute data in the semantic business data, perform second-level attribute annotation on the initial 3D mapping model; based on the product quality inspection and evaluation attribute data in the semantic business data, perform third-level attribute annotation on the initial 3D mapping model; integrate the results of the first-level attribute annotation, the second-level attribute annotation, and the third-level attribute annotation of the initial 3D mapping model to obtain the target 3D mapping model.

[0121] In this implementation, firstly, based on the product maintenance attribute data in the semantic business data, first-level attribute annotations are performed on each component in the initial 3D mapping model. Maintenance attribute data typically includes information such as the equipment's maintenance history, maintenance records, and fault repair status, such as records like "The drive motor was replaced in December 2019" or "The hydraulic system was inspected and repaired in June 2022." This information is mapped to the corresponding components in the 3D model; for example, "Drive motor replaced" is annotated to the drive motor component in the 3D model, and the corresponding maintenance time, maintenance items, and maintenance frequency are displayed. This annotation process clearly presents the historical maintenance information of each component and helps users quickly understand the equipment's maintenance status.

[0122] Next, based on the product operational status attribute data from the semantic business data, second-level attribute annotations will be performed on the 3D mapping model. Operational status attribute data typically describes the equipment's current operating status, efficiency, fault warnings, and other information. Examples include data such as "drive motor temperature too high" or "pump operating normally." This operational status data will be added to the corresponding components in the 3D model, helping users monitor the equipment's operational health in real time. If a component's operational status is abnormal (such as excessively high temperature or low pressure), this status can be visually displayed in the model through annotations, allowing users to easily identify potential problems.

[0123] In the third step, the 3D mapping model is annotated with third-level attributes based on the product quality inspection and evaluation attribute data in the semantic business data. Quality inspection and evaluation attribute data typically includes equipment inspection reports, test results, performance evaluations, and other data. For example, data such as "The equipment's compressor has passed quality inspection and the result is qualified" or "The material strength of a certain component does not meet the requirements" will be mapped to the corresponding components to display the quality status of each component or whether it has passed inspection. Through the annotation of quality inspection and evaluation data, users can intuitively understand whether the equipment meets quality standards and whether there are any potential quality problems, further improving the precision of equipment management.

[0124] Finally, the attribute annotation results of the 3D mapping model from the first three steps are integrated, including the first-level (maintenance attributes), second-level (operating status), and third-level (quality inspection and evaluation) annotation results, and this annotation information is fused into the target 3D mapping model. The integrated target 3D mapping model not only includes the equipment's geometry but also key information such as the equipment's maintenance history, current operating status, and quality inspection results. This model can comprehensively reflect the equipment's current status and historical data, providing a dynamic and real-time equipment management view. In this way, users can intuitively see the status of each component in the 3D model, supporting functions such as equipment fault diagnosis, performance optimization, and preventative maintenance.

[0125] In one feasible implementation, the results of first-level attribute annotation, second-level attribute annotation, and third-level attribute annotation of the initial 3D mapping model are integrated to obtain the target 3D mapping model, including:

[0126] The multi-level attribute annotation results of the initial 3D mapping model are uniformly parsed and their formats standardized.

[0127] Based on component nodes, establish first-level attribute annotation results, second-level attribute annotation results, and third-level attribute annotation results.

[0128] The attribute fusion mapping relationship;

[0129] Based on the attribute fusion mapping relationship, a target 3D mapping model is generated.

[0130] In this implementation, the first step is to uniformly parse and standardize the format of the labeled attributes at all levels (first-level maintenance attributes, second-level operational status attributes, and third-level quality inspection and evaluation attributes). Since attribute data from different sources may have inconsistent formats, all labeled results need to be standardized. Specifically, the format and units (such as time, quantity, and temperature units) of each labeled data will be checked and converted into a unified standard format. For example, all date formats will be standardized to "YYYY-MM-DD", and different temperature units (such as degrees Celsius and Fahrenheit) will be standardized to degrees Celsius, ensuring that subsequent data processing and display are not affected by format differences.

[0131] After standardizing the annotation results, an attribute fusion mapping relationship will be established based on the component nodes (i.e., the node identifiers of each specific component or assembly) in the 3D model. Component nodes, as the basic units in the 3D model, represent each component or part of the model. Different levels of attribute annotations (such as maintenance history, operating status, and quality inspection evaluation) will be associated with the node information of each component. For example, the maintenance attribute "drive shaft failure" will be matched with the drive shaft component node, and then detailed fault information (such as fault time, maintenance process, etc.) will be annotated to that node. In this way, by establishing a fusion mapping relationship for various attribute annotations, all business data can be precisely bound to each component of the 3D model, achieving multi-dimensional data integration.

[0132] Finally, based on the established attribute fusion mapping relationship, all labeled attribute information (including maintenance data, operating status, quality assessment, etc.) will be applied to each component in the 3D model to generate the final target 3D mapping model. This target model not only includes the geometric structure information of the equipment but also incorporates all business data, providing a comprehensive, dynamic, and visualized digital model of the equipment. The status, historical records, and fault conditions of each component will be presented in an intuitive way, facilitating equipment management, status monitoring, and decision analysis for users.

[0133] This application provides a full-lifecycle data intelligent mapping method based on digital models. By tightly integrating various business data throughout the equipment's lifecycle with the equipment's three-dimensional digital model, it achieves comprehensive intelligent equipment management. Firstly, this method integrates data from different stages and types (such as design, manufacturing, testing, operation, and maintenance data) into the three-dimensional model using intelligent mapping technology. This allows the business data of each component (such as maintenance records, operating status, and quality assessments) to be combined with its geometric structure, assembly relationships, and other information to form a comprehensive digital equipment model. This model not only reflects the equipment's physical form but also presents the equipment's operating status and maintenance status in real time, thereby effectively improving the level of full lifecycle management of the equipment.

[0134] Secondly, the intelligent mapping method of this application overcomes the data silos and information fragmentation problems existing in current equipment management methods by deeply associating semantic business data and product modeling data. Existing methods typically store different equipment data in multiple systems, leading to problems such as inconsistent data formats, ambiguous semantics, and inconsistent granularity, making it difficult to achieve effective integration and accurate decision-making from a global perspective. In contrast, this application, through a unified digital model and intelligent mapping mechanism, enables efficient flow and sharing of equipment data across different data sources and systems, significantly improving data utilization efficiency.

[0135] Furthermore, through visualization based on the target 3D mapping model, users can view key information such as the equipment's operating status, historical maintenance records, and fault diagnosis results in real time, enabling them to make more accurate decisions. For example, maintenance personnel can quickly identify faulty components and detect potential risks using the model, allowing them to develop maintenance plans in advance, avoid equipment downtime or malfunctions, and reduce operating costs. This 3D model-based visualization method provides more intuitive and comprehensive data support compared to traditional text reports and 2D charts.

[0136] In summary, the beneficial effects of this application are reflected in the following aspects: First, it achieves seamless integration of equipment lifecycle data through intelligent mapping technology, improving the accuracy and intelligence level of equipment management; second, it breaks down the problem of data fragmentation between existing systems, optimizing data sharing and utilization; third, it improves the efficiency of equipment status monitoring and decision support through target 3D mapping models and visualization, which helps to improve product quality, shorten delivery cycles, optimize maintenance strategies, and ultimately achieve overall optimization of intelligent manufacturing and equipment operation and maintenance.

[0137] This application also provides a full-cycle data intelligent mapping system based on a digital model, referring to... Figure 2 The diagram shows a functional block diagram of a full-cycle data intelligent mapping system 200 based on a digital model, which may include the following modules:

[0138] The acquisition module 201 is used to acquire the full-cycle data of the device to be processed uploaded by the user, determine the user's target data upload intention, and determine the product modeling data and semantic business data in the full-cycle data.

[0139] The first determining module 202 is used to determine product modeling data and semantic business data in the full lifecycle data;

[0140] The first model building module 203 is used to generate an initial three-dimensional mapping model of the device to be processed based on the product modeling data.

[0141] The second determining module 204 is used to construct the correspondence between semantic business data and product modeling data based on the user's data upload intent;

[0142] The second model construction module 205 is used to perform first-level attribute annotation on the initial 3D mapping model based on product maintenance attribute data in the semantic business data, perform second-level attribute annotation on the initial 3D mapping model based on product operating status attribute data in the semantic business data, perform third-level attribute annotation on the initial 3D mapping model based on product quality inspection and evaluation attribute data in the semantic business data, and integrate the results of the first-level attribute annotation, the second-level attribute annotation, and the third-level attribute annotation of the initial 3D mapping model to obtain the target 3D mapping model.

[0143] In one optional implementation, the acquisition module includes:

[0144] The first determination submodule is used to determine the user's intention to upload user type data based on the user type identifier carried in the full-cycle data.

[0145] The second determination submodule is used to determine the user's data format upload intention based on the data format of the full-cycle data;

[0146] The third determination submodule is used to determine the user's target data upload intention based on the matching relationship between the user's type data upload intention and the data format upload intention.

[0147] In one optional implementation, the acquisition module includes:

[0148] The identification submodule is used to determine the product modeling data and semantic business data in the full-cycle data based on the data type identifier and semantic recognition results carried by the full-cycle data.

[0149] In one alternative implementation, the identification submodule includes:

[0150] The first-level filtering unit is used to perform first-level filtering on the full-cycle data based on the semantic recognition results to obtain the first data set;

[0151] The second-level filtering unit is used to perform a second-level filtering on the full-cycle data based on the data type identifier to obtain a second data set;

[0152] The combination unit is used to determine the product modeling data and semantic business data in the full-cycle data based on the intersection of the first data set and the second data set.

[0153] In one alternative implementation, the first model building module includes:

[0154] The skeleton model construction submodule is used to generate a three-dimensional geometric skeleton model of the device to be processed based on the structural topology data and geometric dimension data in the product modeling data.

[0155] The mapping submodule is used to construct and bind the component hierarchy of the 3D geometric skeleton model based on the assembly relationship data and component identification information in the product modeling data, so as to generate the initial 3D mapping model of the device to be processed.

[0156] In one alternative implementation, the skeleton model construction submodule includes:

[0157] The parsing unit is used to parse product modeling data and determine the assemblies that constitute the three-dimensional geometric skeleton model and the assembly identifiers corresponding to the assemblies.

[0158] The determination unit is used to determine the geometric dimensions of each assembly based on the geometric dimension data in the product modeling data, and to generate multiple three-dimensional geometric skeleton models of each assembly based on the geometric dimension data of each assembly.

[0159] The splicing unit is used to determine the topological connection relationship between each assembly based on the structural topology data in the product modeling data, and to assemble each assembly according to the topological connection relationship between each assembly to obtain a three-dimensional geometric skeleton model of the device to be processed.

[0160] In this embodiment, the present application also provides an electronic device, which may include a memory and one or more processors. The memory and processors are coupled. The memory is used to store computer program code, which includes computer instructions. When the processor executes the computer instructions, the electronic device can perform various functions or steps in the above method embodiments.

[0161] This embodiment also provides a computer-readable storage medium storing computer instructions that, when executed on an electronic device, cause the electronic device to perform the various functions or steps described in the above method embodiments.

[0162] This embodiment also provides a computer program product that, when run on a computer, causes the computer to perform the various functions or steps in the above method embodiments.

[0163] In this embodiment, the electronic device, computer-readable storage medium, and computer program product are all used to execute the corresponding methods provided above. Therefore, the beneficial effects they can achieve can be referred to the beneficial effects in the corresponding methods provided above, and will not be repeated here.

[0164] The above embodiments can be implemented, in whole or in part, by software, hardware (such as circuits), firmware, or any other combination thereof. When implemented using software, the above embodiments can be implemented, in whole or in part, as a computer program product. A computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, all or part of the flow or function according to the embodiments of this application is generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable system. The computer program or instructions can be stored in a computer-readable storage medium or transferred from one computer-readable storage medium to another. For example, a computer program or instructions can be transferred from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more sets of available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium. A semiconductor medium can be a solid-state drive.

[0165] It should be understood that in the various embodiments of this application, the order of the above-mentioned processes does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0166] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0167] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, units, and processes described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0168] In the embodiments provided in this application, it should be understood that the disclosed systems, methods, and approaches can be implemented in other ways. For example, the system embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between systems or units may be electrical, mechanical, or other forms.

[0169] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0170] In addition, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0171] If a function is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0172] The above are merely specific embodiments of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A full-cycle intelligent data mapping method based on a digital model, characterized in that, The method includes: Acquire the full lifecycle data of the devices to be processed uploaded by the user, and determine the user's intention to upload the target data; Identify the product modeling data and semantic business data within the full lifecycle data; Based on the product modeling data, an initial three-dimensional mapping model of the device to be processed is generated; Based on the user's data upload intent, a correspondence is constructed between the semantic business data and the product modeling data; Based on the product maintenance attribute data in the semantic business data, the initial 3D mapping model is annotated with first-level attributes. Based on the product operating status attribute data in the semantic business data, the initial 3D mapping model is annotated with second-level attributes. Based on the product quality inspection and evaluation attribute data in the semantic business data, the initial 3D mapping model is annotated with third-level attributes. The results of the first-level attribute annotation, the second-level attribute annotation, and the third-level attribute annotation of the initial 3D mapping model are integrated to obtain the target 3D mapping model. The process of acquiring the full-cycle data of the device to be processed uploaded by the user and determining the user's target data upload intention includes: Based on the user type identifier carried in the full-cycle data, determine the user's user type data upload intent; Based on the data format of the full-cycle data, determine the user's data format upload intention; Based on the matching relationship between the user type data upload intent and the data format upload intent, the user's target data upload intent is determined; The step of constructing the correspondence between the semantic business data and the product modeling data based on the user's data upload intent includes: The semantic business data is parsed, and semantic anchor feature information related to the data upload intent is extracted. The semantic anchor feature information includes at least the device location, component name, number, fault type, and operation time. Based on the semantic matching strategy corresponding to the data upload intent, the target model objects in the product modeling data are filtered and associated using the semantic anchor feature information to establish a binding relationship between semantic business data and product modeling data.

2. The intelligent full-cycle data mapping method based on a digital model according to claim 1, characterized in that, The determination of product modeling data and semantic business data in the full-cycle data includes: Based on the data type identifier and semantic recognition results carried by the full-cycle data, the product modeling data and semantic business data in the full-cycle data are determined.

3. The method for intelligent full-cycle data mapping based on a digital model according to claim 2, characterized in that, The step of determining product modeling data and semantic business data in the full-cycle data based on the data type identifier and semantic recognition result carried by the full-cycle data includes: Based on the semantic recognition results, the full-cycle data is subjected to a first-level screening to obtain a first data set; Based on the data type identifier, the full-cycle data is subjected to a second-level filtering to obtain a second data set; Based on the intersection of the first data set and the second data set, the product modeling data and semantic business data in the full-cycle data are determined.

4. The full-cycle intelligent data mapping method based on a digital model according to claim 1, characterized in that, The step of generating an initial 3D mapping model of the device to be processed based on the product modeling data includes: Based on the structural topology data and geometric dimension data in the product modeling data, a three-dimensional geometric skeleton model of the device to be processed is generated; Based on the assembly relationship data and component identification information in the product modeling data, the three-dimensional geometric skeleton model is constructed and identified and bound at the component level to generate the initial three-dimensional mapping model of the device to be processed.

5. The full-cycle intelligent data mapping method based on a digital model according to claim 3, characterized in that, The step of generating a three-dimensional geometric skeleton model of the device to be processed based on the structural topology data and geometric dimension data in the product modeling data includes: The product modeling data is analyzed to determine the assemblies that constitute the three-dimensional geometric skeleton model and the assembly identifiers corresponding to the assemblies. Based on the geometric dimension data in the product modeling data, determine the geometric dimension data of each assembly, and generate multiple three-dimensional geometric skeleton models of each assembly based on the geometric dimension data of each assembly. Based on the structural topology data in the product modeling data, the topological connection relationships between each assembly are determined, and each assembly is assembled according to the topological connection relationships between each assembly to obtain a three-dimensional geometric skeleton model of the device to be processed.

6. The full-cycle intelligent data mapping method based on a digital model according to claim 1, characterized in that, The process of integrating the first-level attribute annotation results, the second-level attribute annotation results, and the third-level attribute annotation results of the initial 3D mapping model to obtain the target 3D mapping model includes: The multi-level attribute annotation results of the initial 3D mapping model are uniformly parsed and standardized in format; Establish attribute fusion mapping relationships based on component nodes for first-level attribute annotation results, second-level attribute annotation results, and third-level attribute annotation results; Based on the attribute fusion mapping relationship, the target 3D mapping model is generated.

7. A full-cycle intelligent data mapping system based on a digital model, characterized in that, The system for implementing the method according to any one of claims 1-6, the system comprising: The acquisition module is used to acquire the full-cycle data of the device to be processed uploaded by the user, determine the user's target data upload intention, and determine the product modeling data and semantic business data in the full-cycle data. The first determining module is used to determine the product modeling data and semantic business data in the full-cycle data; The first model building module is used to generate an initial three-dimensional mapping model of the device to be processed based on the product modeling data. The second determining module is used to construct the correspondence between the semantic business data and the product modeling data based on the user's data upload intention; The second model construction module is used to perform first-level attribute annotation on the initial 3D mapping model based on product maintenance attribute data in the semantic business data, perform second-level attribute annotation on the initial 3D mapping model based on product operating status attribute data in the semantic business data, perform third-level attribute annotation on the initial 3D mapping model based on product quality inspection and evaluation attribute data in the semantic business data, and integrate the results of the first-level attribute annotation, the second-level attribute annotation, and the third-level attribute annotation of the initial 3D mapping model to obtain the target 3D mapping model. The acquisition module includes: The first determining submodule is used to determine the user's user type data upload intention based on the user type identifier carried in the full-cycle data; The second determining submodule is used to determine the user's data format upload intention based on the data format of the full-cycle data; The third determining submodule is used to determine the user's target data upload intention based on the matching relationship between the user type data upload intention and the data format upload intention; The second determining module includes: The parsing submodule is used to parse the semantic business data and extract semantic anchor feature information related to the data upload intent. The semantic anchor feature information includes at least the device location, component name, number, fault type, and operation time. A submodule is constructed to filter and associate target model objects in product modeling data based on the semantic matching strategy corresponding to the data upload intent, using the semantic anchor feature information, and to establish a binding relationship between semantic business data and product modeling data.

Images