System base map nested identification checking method and system based on artificial intelligence

Abstract

The invention belongs to the technical field of engineering design automation and artificial intelligence, and discloses an artificial intelligence-based system base map nested identification checking method set and system, which comprises the following steps of: retrieving a matched standard base map from a nested base map database according to a current design stage identifier; based on a system base map data structure, automatically nesting the standard base map into a current system base map in a space matching manner to generate composite map file data; an AI recognition engine is called to recognize the composite drawing file data according to the checking rule, and a preliminary recognition report is generated; based on the report, automatically mapping and integrating to obtain a structured check conclusion; triggering a corresponding processing mechanism instruction according to the structured checking conclusion to drive a checking process; if the process is rejected, a backtracking path diagram is automatically generated according to the operation history, the process state is reset, double-base diagram dynamic coupling verification is utilized, full-process automation, intelligence and standardization of design verification are achieved, and the verification efficiency, precision and quality controllability are remarkably improved.

Description

Technical Field

[0001] This invention relates to the fields of engineering design automation and artificial intelligence technology, and in particular to a system and system for nested identification and verification of system base maps based on artificial intelligence. Background Technology

[0002] In engineering design, downstream professional designs are generally constrained by upstream professional requirements. Sometimes, upstream professionals make multiple revisions and requests, leading to repeated revisions, checks, countersigning, and communication with construction units for downstream engineering drawings. Often, during the bidding process for construction drawings, the verification of construction drawings, and the process of project commissioning, inconsistent quality control standards among different design roles result in various hidden errors in the drawings (minor dimensions, collisions, and omissions), leading to frequent design changes. Design changes not only reduce the design efficiency, quality, and service quality of designers but also increase their repetitive, redundant, and tedious workload, resulting in lower design productivity. This affects the quality of the final design, overall project milestones, and contract performance reputation, and may even lead to rework, hindering on-site construction progress and further impacting the smooth commissioning and achievement of project excellence.

[0003] Traditional engineering design processes suffer from several drawbacks, including inconsistent verification standards, difficulty in quality control, repetitive and inefficient verification work, low design productivity, unclear scope of impact from changes, and delayed updates.

[0004] The above content is only used to help understand the technical solution of the present invention and does not represent an admission that the above content is prior art. Summary of the Invention

[0005] The main objective of this invention is to provide a system and method for nested recognition and verification of system base maps based on artificial intelligence, which aims to solve the technical problems of high labor production costs, repetitive workload, low labor productivity, and low per capita output in traditional engineering design processes.

[0006] To achieve the above objectives, the present invention provides a system base map nesting recognition and verification method based on artificial intelligence, the system base map nesting recognition and verification method based on artificial intelligence includes the following steps: A system base map data structure and a nested base map database are constructed. The system base map data structure is used to define the data organization format and version management framework of the editable basic map atlas. The nested base map database stores read-only standard map atlases used for verification reference and their associated verification rule knowledge base. In response to the verification instruction, a matching standard base map is retrieved from the nested base map database based on the current design stage identifier, and the standard base map is automatically nested into the current system base map in a spatial matching manner based on the system base map data structure to generate composite drawing data; The artificial intelligence recognition engine is invoked to automatically recognize the composite map data according to the verification rules in the nested base map database, and a preliminary recognition report is generated. The preliminary recognition report includes the error type, coordinate location, and violation rule number. Based on the preliminary identification report, the results are automatically mapped and integrated to obtain a structured verification conclusion, which includes the error level, error location box, and modification suggestions. Based on the error level in the structured verification conclusion, the corresponding processing mechanism instruction is automatically triggered to execute the verification process; If the verification process is rejected by the authorized node, a backtracking path diagram is automatically generated based on the rejection instruction and the operation history stored in the system base map data structure, and the process status is reset to the specified stage.

[0007] In one embodiment, the step of retrieving a matching standard base map from the nested base map database based on the current design stage identifier, and automatically nesting the standard base map into the current system base map using spatial matching based on the system base map data structure to generate composite map data includes: Parse the metadata of the current system base map and extract the current design stage identifier, which includes the professional type identifier and the design stage code; Using the professional type identifier and the design stage code as query conditions, a matching standard base map is retrieved from the nested base map database; The standard base map is embedded into the system base map in read-only visualization mode to form the composite map data, and a globally unique version identifier is generated for the composite map data.

[0008] In one embodiment, the step of invoking the artificial intelligence recognition engine to automatically recognize the composite map data based on the verification rules in the nested base map database and generate a preliminary recognition report includes: The composite drawing data is parsed to extract geometric figures, text annotations, and entity model information, and then converted into a standardized feature vector set. The graphics processing engine is invoked to perform spatial alignment calculations between the standard base map and the current system base map, generating a spatial alignment matrix. Based on the spatial alignment matrix, a logical link between the standard base map and the system base map design elements is established in the association layer defined by the system base map data structure, and a topological dependency matrix describing the dependency relationship of the logical link is automatically calculated and generated. The geometric feature recognition sub-engine is invoked. Based on the elements associated with the topological dependency matrix, the corresponding line type and size data in the standardized feature vector set are processed by a convolutional neural network. The data is then compared with the pre-stored standardized primitives in the nested base map database to output a geometric feature deviation dataset. The semantic rule recognition sub-engine is invoked to load the industry standard knowledge graph in the nested base map database based on the system base map design elements associated with the logical links, perform semantic parsing and compliance verification, and output a list of rule violation items. The collision detection sub-engine is invoked, and based on the spatial hierarchy defined by the topological dependency matrix, a voxelized spatial segmentation algorithm is used to perform spatial interference analysis on the multi-disciplinary 3D entities in the composite drawing data, and output a set of spatial collision and conflict coordinates. The geometric feature deviation dataset, the list of rule violations, and the spatial collision conflict coordinate set are integrated and normalized according to a preset format to form a preliminary identification report.

[0009] In one embodiment, the automatic mapping and integration of results based on the preliminary identification report to obtain a structured verification conclusion includes: The data in the preliminary identification report are automatically compared with the preset multi-level matching threshold parameters; If the comparison result is within the allowable threshold range, a status marker is generated and rendered at the corresponding coordinate position of the composite image data. If the comparison result exceeds the allowable threshold, the system generates a highlighted warning box graphic data at the corresponding coordinates according to the error type, and automatically associates it with the solution knowledge base in the nested base map database to generate modification suggestion text; Integrate all data from status markers, highlighted warning boxes, and suggested modifications, and generate a structured verification conclusion according to the report template defined by the system's base map data structure.

[0010] In one embodiment, the step of automatically triggering a corresponding processing mechanism instruction based on the error level in the structured verification conclusion to execute the verification process includes: Based on the preset error classification-strategy mapping table, the error types in the structured verification conclusions are automatically classified into general errors or major conflicts; For general errors, a layer local lock command is automatically generated to restrict editing of the erroneous area, and a correction countdown monitoring task is started simultaneously; For major conflicts, a three-level interlocking processing instruction sequence is automatically triggered, wherein the three-level interlocking processing instruction sequence includes, in turn: generating a full-drawing association freeze instruction to lock the editing and circulation permissions of all related drawings; generating an alarm push instruction to the preset approval node system account; generating a cross-professional joint signature process creation instruction and automatically assigning joint signature tasks; The execution feedback of the processing mechanism instructions is continuously monitored, and the corresponding verification process control status is maintained until the AI ​​re-examination pass signal corresponding to the error item is received.

[0011] In one embodiment, the method further includes: Based on the aforementioned topology dependency matrix, continuously monitor the version status identifiers of all upstream base maps associated with the current composite map data; When a change in the version status identifier of any upstream base map is detected, the version comparison engine is automatically invoked to analyze the changes and generate a design change impact analysis report. Based on the design change impact analysis report, combined with the logical links and the topological dependency matrix, assess the level of impact of the change on specific design elements in the current composite drawing data. A nested adaptation suggestion report is generated based on the impact level. The nested adaptation suggestion report includes the drawing areas that need to be re-performed nesting and verification, as well as the associated design point identifiers. Update the status of the current composite map data to pending re-nesting, and push a forced re-verification notification instruction to the relevant responsible node system account according to the impact level.

[0012] In one embodiment, the method further includes: Capture every key operational event from constructing the system base map data structure to generating the structured verification conclusion to form an operational event chain, the operational event chain carrying a timestamp; An event feature hash value is generated based on the core data of each event in the operation event chain. The core data includes the operation content, execution context, and hash digests of input and output data. The event feature hash value is uploaded to the blockchain evidence storage network in real time for distributed storage. When a quality traceability request is initiated, the complete trusted operation history chain is retrieved and restored from the blockchain evidence storage network based on the globally unique version identifier or time range. Based on the trusted operation history chain, a visual full-process traceability path diagram is dynamically generated and displayed in the graphical interface. In the visual full-process traceability path diagram, all approval nodes, process rejection points and related design modification operations are highlighted.

[0013] Furthermore, to achieve the above objectives, this invention also proposes an AI-based system base map nested recognition and verification system, which is applied to the AI-based system base map nested recognition and verification method described above. The system includes: The construction module is used to build the system base map data structure and the nested base map database. The system base map data structure defines the data organization format and version management framework for the editable basic map atlas. The nested base map database stores read-only standard map atlases used for verification reference and their associated verification rule knowledge base. The nested module is used to respond to the verification command, retrieve the matching standard base map from the nested base map database according to the current design stage identifier, and automatically nest the standard base map into the current system base map in a spatial matching manner based on the system base map data structure to generate composite drawing data; The output module is used to call the artificial intelligence recognition engine to automatically recognize the composite map data according to the verification rules in the nested base map database and generate a preliminary recognition report. The preliminary recognition report includes the error type, coordinate location and violation rule number. The processing module is used to automatically map and integrate the results based on the preliminary identification report to obtain a structured verification conclusion, which includes the error level, error location box, and modification suggestions. The execution module is used to automatically trigger the corresponding processing mechanism instructions based on the error level in the structured verification conclusion to execute the verification process; The control module is used to automatically generate a backtracking path diagram and reset the process status to the specified stage if the verification process is rejected by the authorized node, based on the rejection instruction and the operation history stored in the system base map data structure.

[0014] Furthermore, to achieve the above objectives, the present invention also proposes an AI-based system base map nested recognition and verification device, which includes: a memory, a processor, and an AI-based system base map nested recognition and verification program stored in the memory and executable on the processor. The AI-based system base map nested recognition and verification program is configured to implement the steps of the AI-based system base map nested recognition and verification method described above.

[0015] Furthermore, to achieve the above objectives, the present invention also proposes a storage medium storing an AI-based system base map nested recognition and verification program, wherein when the AI-based system base map nested recognition and verification program is executed by a processor, it implements the steps of the AI-based system base map nested recognition and verification method described above.

[0016] This invention retrieves matching standard base maps from the nested base map database based on the current design stage identifier, and automatically nests the standard base maps into the current system base map using spatial matching based on the system base map data structure, generating composite drawing data. An AI recognition engine is invoked to recognize the composite drawing data according to verification rules, generating a preliminary recognition report. Based on this report, a structured verification conclusion is automatically mapped and integrated. According to the structured verification conclusion, corresponding processing mechanism instructions are triggered to drive the verification process. If the process is rejected, a backtracking path diagram is automatically generated based on the operation history, and the process state is reset. By utilizing dynamic coupling verification with dual base maps, the entire design verification process is automated, intelligent, and standardized, significantly improving verification efficiency, accuracy, and quality controllability. Attached Figure Description

[0017] Figure 1 This is a flowchart illustrating the first embodiment of the system base map nested recognition and verification method based on artificial intelligence of the present invention; Figure 2 This is a structural block diagram of the first embodiment of the system base map nested recognition and verification system based on artificial intelligence of the present invention.

[0018] The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0019] It should be understood that the specific embodiments described herein are for illustrative purposes only and are not intended to limit the scope of the invention.

[0020] This invention provides an artificial intelligence-based system base map nested recognition and verification method, referring to... Figure 1 , Figure 1 This is a flowchart illustrating the first embodiment of a system base map nested recognition and verification method based on artificial intelligence according to the present invention.

[0021] In this embodiment, the AI-based system base map nested recognition and verification method includes the following steps: Step S10: Construct the system base map data structure and nested base map database.

[0022] In this embodiment, the execution entity is an AI-based system base map nested recognition and verification device. This AI-based system base map nested recognition and verification device has functions such as data processing, data communication, and program execution. The AI-based system base map nested recognition and verification device can be a computer terminal device or other network device, or other devices with similar functions. This embodiment does not limit this.

[0023] It should be noted that in engineering design, downstream professional designs are generally constrained by the requirements of upstream professionals. Sometimes, upstream professionals make multiple revisions and requests, leading to repeated revisions, checks, countersigning, and communication with construction units for some engineering drawings in downstream projects. Typically, during the bidding process for construction drawings, the verification of construction drawing designs, and the process of achieving project completion and commissioning, the quality control standards for verification among different design roles are inconsistent. Various hidden errors exist in the drawings (minor dimensions, collisions, and omissions, etc.), resulting in frequent design changes. Design changes not only reduce the design efficiency, design quality, and service quality of designers, but also increase their repetitive, redundant, and tedious workload, leading to low design productivity. This affects the quality of the finished design, the overall project design milestones, and contract performance reputation, and may even necessitate rework, hindering on-site construction progress and further impacting the smooth commissioning and achievement of project excellence. Traditional engineering design processes suffer from inconsistent verification standards, difficulties in quality control, repetitive and inefficient verification work, low design productivity, unclear scope of change impact, and delayed updates.

[0024] To address the aforementioned technical issues, this embodiment retrieves a matching standard base map from the nested base map database based on the current design stage identifier. Then, based on the system base map data structure, the standard base map is automatically nested into the current system base map using spatial matching, generating composite drawing data. An AI recognition engine is invoked to identify the composite drawing data according to verification rules, generating a preliminary recognition report. Based on this report, a structured verification conclusion is automatically mapped and integrated. The structured verification conclusion triggers corresponding processing mechanism instructions to drive the verification process. If the process is rejected, a backtracking path diagram is automatically generated based on the operation history, and the process state is reset. Utilizing dynamic coupling verification with dual base maps, the entire design verification process is automated, intelligent, and standardized, significantly improving verification efficiency, accuracy, and quality controllability. Specifically, this can be implemented as follows.

[0025] It should be noted that, in some other embodiments, this application proposes a nested identification and verification method for system base maps based on artificial intelligence. For ease of understanding, the following explains some key terms in this embodiment: System Base Map Data Structure: This data structure is designed to define the data organization format and version management framework of the editable base map atlas. Its function is to standardize the storage, access, and modification of design data, and to ensure the effective management and traceability of different versions of design drawings. Nested Base Map Database: This database is configured to store read-only standard atlases used for verification reference and their associated verification rule knowledge base. Its core function is to provide a stable and authoritative reference source to support the automated verification process. Editable Base Map Atlas: This atlas refers to the collection of original design drawings created and modified by designers during the engineering design process. Its content is dynamically changing and requires continuous verification and updating. Read-Only Standard Atlas: This atlas refers to the collection of reference drawings that have been reviewed and approved by authoritative institutions or expert teams as design specifications and industry standards. Its content is usually fixed and used for comparison and verification with the editable base map atlas. Verification Rule Knowledge Base: This knowledge base is constructed to contain a series of predefined rules, specifications, and standards to guide the AI ​​recognition engine in automatically verifying design drawings. These rules can cover multiple aspects such as geometric dimensions, semantic logic, and spatial relationships. Verification Command: This command is triggered by the user or system to initiate the automated verification process for design drawings. It can be issued according to different design stages or requirements. Current Design Stage Identifier: This identifier uniquely identifies the specific stage of the current design project, such as preliminary design or construction drawing design. Its function is to guide the system to retrieve the standard base map required for this stage. Composite Drawing Data: This data refers to the integrated drawing file formed by nesting read-only standard drawings into the current system base map using spatial matching. It contains current design content and standard reference content, forming the basis for automated recognition and verification. AI Recognition Engine: This engine is configured to use artificial intelligence technology to automatically analyze and recognize composite drawing data according to verification rules. It can detect potential errors, conflicts, or non-compliance with specifications in the design drawings. Preliminary Identification Report: This report is the output of the AI ​​recognition engine's automated identification process. It includes the detected error type, the specific coordinates of the error's location, and the violated verification rule number. Structured Verification Conclusion: This conclusion, based on the preliminary identification report, is a more instructive verification result formed after result mapping and integration. It includes the error level, error location box, and targeted modification suggestions. Processing Mechanism Instructions: These instructions are a series of operation commands automatically triggered based on the error level in the structured verification conclusion, used to execute the corresponding verification process, such as locking the error area, sending an alert, or initiating a countersigning process. Authorized Node: This node refers to a specific user or system role with approval authority in the verification process.It is responsible for reviewing and making decisions regarding verification results or process status, such as approval or rejection. Backtracking Path Diagram: This diagram is a visual path automatically generated based on the rejection instruction and operation history when the verification process is rejected. It clearly shows the historical trajectory of design modifications and process flow, facilitating tracing and correction. Operation History: This history refers to the sequence of all key operational events recorded by the system during the design and verification process. It includes information such as operation content, timestamps, and execution context, providing a basis for backtracking and auditing.

[0026] In this embodiment, for example, the data structure can organize the map files using a basic file naming convention and folder hierarchy, and record version information through a manually maintained change log. The nested base map database stores read-only standard maps for verification reference and their associated verification rule knowledge base. For example, the standard maps can be stored as independent graphic files, while the verification rule knowledge base can be maintained as a simple text list.

[0027] Step S20: In response to the verification instruction, retrieve a matching standard base map from the nested base map database according to the current design stage identifier, and automatically nest the standard base map into the current system base map in a spatial matching manner based on the system base map data structure to generate composite drawing data.

[0028] It should be noted that the nested structure in this embodiment is defined as (1) System base map: adopting a CAD layer management architecture, including a dynamic editing layer (user-drawn content), a metadata layer (design stage, responsible person, time node) and an association layer (logical link points with the nested base map). (2) Nested base map: stored in an independent encrypted database, embedded in the system base map in read-only mode, and achieving millimeter-level spatial matching through a coordinate alignment engine. (3) Nested operation: the executor calls the nested library through the CAD plugin, and the system automatically generates a topology relationship matrix to mark the dependency relationship between base maps, such as the civil engineering system base map nesting the architectural and structural professional wall positioning map. AI-driven dynamic nesting means that when the upstream base map is updated, the AI ​​version comparison engine automatically triggers the change impact analysis, generates a nesting adaptation report, and prompts the downstream related areas that need to be re-nested, such as the linkage calibration of the structural opening map after the HVAC and water pipe elevation is modified.

[0029] In a specific implementation, the step of retrieving a matching standard base map from the nested base map database based on the current design stage identifier, and automatically nesting the standard base map into the current system base map using spatial matching based on the system base map data structure to generate composite drawing data, includes: parsing the metadata of the current system base map and extracting the current design stage identifier, which includes a professional type identifier and a design stage code; retrieving a matching standard base map from the nested base map database using the professional type identifier and the design stage code as query conditions; embedding the standard base map into the system base map in read-only visualization mode to form the composite drawing data, and generating a globally unique version identifier for the composite drawing data.

[0030] Furthermore, the metadata of the current system base map is parsed to extract the current design stage identifier, which includes a professional type identifier and a design stage code. This step aims to obtain the inherent descriptive information, i.e., metadata, from the system base map currently undergoing design work, and identify key information for accurately matching the standard base map. The current design stage identifier is composite information used to uniquely determine the current design stage and professional field. The metadata of the system base map can be stored as an XML file, a JSON object, or a database record, containing predefined fields such as "professional type" and "design stage". The parsing process can be completed by reading these files or querying the database, and extracting the values ​​of the corresponding fields as the professional type identifier and design stage code. In addition, the metadata of the system base map can also be embedded in the header information of drawing files, such as the DWG / DXF file header of CAD drawings or the IFC file attributes of BIM models. The parser can use the corresponding API or library functions to read the file header and identify and extract the professional type identifier and design stage code according to preset tags or keywords.

[0031] Using the professional type identifier and the design phase code as query conditions, matching standard base maps are retrieved from the nested base map database. This step utilizes the precise design phase information obtained in the previous step as query parameters to search within the pre-built nested base map database to locate the standard base map that perfectly corresponds to the current design phase. The nested base map database can be implemented using a relational database (such as MySQL or PostgreSQL), where the metadata of the standard base map (including the professional type identifier and design phase code) is used as fields in the table. Query operations can be performed using SQL statements with WHERE clauses to precisely match the professional type identifier and design phase code. Alternatively, the nested base map database can also be implemented using a document-oriented database (such as MongoDB) or a key-value store (such as Redis), where each standard base map record contains its professional type identifier and design phase code. Query operations can be performed using the database's API, leveraging indexes or full-text search functions to efficiently retrieve data based on these two identifiers.

[0032] The standard base map is embedded into the system base map in read-only visualization mode to form the composite drawing data. A globally unique version identifier is generated for the composite drawing data. This step integrates the retrieved standard base map into the current system base map in a secure manner without affecting the original design, forming a unified view for verification and assigning it a unique identity for subsequent traceability and management. The embedding operation can be implemented through a graphics rendering engine, loading the standard base map as a background or reference layer into the display interface of the system base map. The read-only visualization mode can be achieved by setting the layer attributes to non-editable and non-selectable. The globally unique version identifier can be generated using the UUID (Universally Unique Identifier) ​​algorithm to ensure its uniqueness throughout the system. Alternatively, the embedding operation can be implemented by creating a new composite drawing file format, which contains references to the system base map and the standard base map and defines the spatial relationship between them. References to the standard base map can be marked as read-only. The globally unique version identifier can be generated by combining information such as timestamps, system IDs, and random numbers to ensure its uniqueness.

[0033] Step S30: Call the artificial intelligence recognition engine to automatically recognize the composite map data according to the verification rules in the nested base map database, and generate a preliminary recognition report.

[0034] In its specific implementation, the AI ​​recognition engine automatically identifies the composite map data based on the verification rules in the nested base map database, generating a preliminary recognition report. This includes: parsing the composite map data, extracting geometric figures, text annotations, and entity model information, and converting them into a standardized feature vector set; calling the graphics processing engine to perform spatial alignment calculations between the standard base map and the current system base map, generating a spatial alignment matrix; based on the spatial alignment matrix, establishing logical links between the standard base map and system base map design elements in the association layer defined in the system base map data structure, and automatically calculating and generating a topological dependency matrix describing the dependencies of the logical links; and calling the geometric feature recognition sub-engine to apply convolutional neural networks to the elements associated with the topological dependency matrix. The network processes the corresponding line type and dimension data in the standardized feature vector set and performs differential comparison with the pre-stored standard primitives in the nested base map database to output a geometric feature deviation dataset. It then calls the semantic rule recognition sub-engine to load the industry standard knowledge graph in the nested base map database based on the system base map design elements associated with the logical links, performing semantic parsing and compliance verification, and outputting a list of rule violations. Finally, it calls the collision detection sub-engine to perform spatial interference analysis on the multi-disciplinary 3D entities in the composite map data using a voxelized spatial segmentation algorithm, based on the spatial hierarchy defined by the topological dependency matrix, and outputs a spatial collision conflict coordinate set. Finally, it integrates the geometric feature deviation dataset, the list of rule violations, and the spatial collision conflict coordinate set and normalizes them according to a preset format to form a preliminary identification report.

[0035] It's important to note that parsing composite drawing data, extracting geometric shapes, text annotations, and entity model information, and converting it into a standardized feature vector set aims to transform raw, heterogeneous design data into a unified, computable format. This can be achieved using APIs provided by CAD / BIM software, such as AutoCAD ObjectARX or Revit API, to programmatically access information such as layers, line types, dimensions, text, block definitions, and 3D model components. Alternatively, specialized data parsing libraries, such as the Open Design Alliance Teigha library, can be used to perform low-level parsing of common file formats like DWG, RVT, and IFC, obtaining graphic primitives, attribute data, and topological structures. The converted standardized feature vector set can be a multi-dimensional array, where each dimension represents a specific design feature, such as line length, angle, text content, entity model volume, or material properties. These features are uniformly represented through encoding or embedding techniques.

[0036] In this embodiment, the graphics processing engine is invoked to perform spatial alignment calculations between the standard base map and the current system base map, generating a spatial alignment matrix. The purpose is to ensure that the two images are in the same spatial coordinate system before comparison. One implementation method is to use a feature-point-based registration algorithm, such as SIFT, SURF, or ORB, to identify common feature points in the two images and calculate a transformation matrix, i.e., the spatial alignment matrix, using robust estimation methods such as RANSAC, incorporating parameters such as translation, rotation, and scaling. Another implementation method is to use a geometry-based registration algorithm, such as fitting the transformation relationship of corresponding geometric elements in the two images using the least squares method, or performing manual or semi-automatic alignment using preset reference points. This spatial alignment matrix is ​​typically a 3x3 or 4x4 homogeneous transformation matrix.

[0037] In this embodiment, based on the spatial alignment matrix, logical links between the standard base map and system base map design elements are established in the association layer defined by the system base map data structure. A topological dependency matrix describing the dependencies of these logical links is automatically calculated and generated, aiming to clarify the inherent associations and mutual dependencies between design elements. The establishment of logical links can be achieved through spatial proximity analysis, attribute similarity matching (such as layer name, component ID), or semantic matching algorithms. For example, a wall in the standard base map can be matched with a wall in the system base map. Alternatively, a predefined rule base can be used to automatically identify and establish logical relationships such as "doorway is located in a wall" or "pipe passes through a floor slab" based on element type and spatial location. The topological dependency matrix can be an adjacency matrix or an association matrix, where the rows and columns represent design elements, and the values ​​in the matrix represent the dependency type between elements, such as containment, connection, constraint, or reference.

[0038] In this embodiment, the geometric feature recognition sub-engine is invoked. Based on the elements associated with the topological dependency matrix, the corresponding line type and dimension data in the standardized feature vector set are processed using a convolutional neural network. This data is then compared differentially with pre-stored standard primitives in a nested base map database, outputting a geometric feature deviation dataset. This dataset serves to check the geometric accuracy and standard compliance of the design primitives. Convolutional neural networks (CNNs) can be used to process line type data (such as line width, line type pattern, and color) and dimension data (such as labeled values ​​and actual measured values). These are encoded as image or sequence data and then input into a pre-trained CNN model for feature extraction and classification. Differential comparison can employ metrics such as Euclidean distance, cosine similarity, or structural similarity index (SSIM) to quantify the differences between design primitives and standard primitives. The geometric feature deviation dataset will include deviation type (such as out-of-tolerance dimensions or line type inconsistencies), deviation value, the ID of the involved primitive, and its coordinate position.

[0039] In this embodiment, a semantic rule recognition sub-engine is invoked. Based on the system base map design elements associated with logical links, an industry standard knowledge graph from a nested base map database is loaded for semantic parsing and compliance verification. A list of rule violations is output, aiming to check whether the design conforms to industry standards and norms from a semantic perspective. The industry standard knowledge graph can be constructed using semantic web technologies such as OWL and RDF, and includes ontology, concepts, relationships, and rules. The semantic parsing engine uses SPARQL queries or inference engines to query and reason about the knowledge graph. Alternatively, the knowledge graph can also be an expert system based on a rule engine, storing industry standards in the form of "IF-THEN" rules. Compliance verification is completed by matching the attributes of system base map design elements with the rules. The list of rule violations will include the violated rule number, the violated element ID, a description of the violation, and suggested corrective measures.

[0040] In this embodiment, the collision detection sub-engine is invoked. Based on the spatial hierarchy defined by the topological dependency matrix, a voxelized spatial segmentation algorithm is used to perform spatial interference analysis on multi-disciplinary 3D entities in the composite drawing data, outputting a spatial collision conflict coordinate set. The purpose is to identify physical conflicts between components from different disciplines. The voxelized spatial segmentation algorithm discretizes the 3D entity model into a series of small cubes (voxels), and detects collisions by checking the overlap of voxels from different disciplines. Alternatively, spatial indexing structures such as bounding boxes, octrees, or KD trees can be used in conjunction with GJK or SAT algorithms for collision detection. The spatial collision conflict coordinate set will include the coordinate range of the collision, the entity IDs involved, and the collision type (e.g., hard collision, soft collision).

[0041] In this embodiment, the geometric feature deviation dataset, the list of rule violations, and the spatial collision conflict coordinate set are integrated and normalized according to a preset format to form a preliminary identification report. The aim is to uniformly summarize all different types of verification results. This can be achieved by defining a unified data structure (such as JSON or XML), mapping the data fields output by different sub-engines to this structure, and performing data cleaning and deduplication. Alternatively, a preset report generation template can be used to populate various data into preset report fields, ensuring the report's structure and readability.

[0042] Step S40: Automatically map and integrate the results based on the preliminary identification report to obtain a structured verification conclusion.

[0043] In specific implementation, the automatic result mapping and integration based on the preliminary identification report to obtain a structured verification conclusion includes: automatically comparing each data in the preliminary identification report with preset multi-level matching threshold parameters; if the comparison result is within the allowable threshold range, generating and rendering a pass status marker at the corresponding coordinate position of the composite map data; if the comparison result exceeds the allowable threshold, the system generates highlighted warning box graphic data at the corresponding coordinates according to the error type, and automatically associates it with the solution knowledge base in the nested base map database to generate modification suggestion text; integrating all pass status markers, highlighted warning box graphic data, and modification suggestion text, and generating a structured verification conclusion according to the report template defined by the system base map data structure.

[0044] It should be noted that the data in the preliminary identification report refers to data formed after normalization of the geometric feature deviation dataset, the list of rule violations, and the spatial collision conflict coordinate set. This data includes various potential problems detected by the artificial intelligence recognition engine. The preset multi-level matching threshold parameter refers to a pre-defined set of values ​​or rules used to measure the degree of deviation between the identified problem and the standard, and to determine the nature or severity of the problem. This parameter can be stored in a configuration file (e.g., an XML file) or a database table, and different threshold levels (e.g., minor, moderate, severe) can be set according to different error types (e.g., size deviation, spacing discrepancy, collision depth, etc.). The automatic comparison refers to the system automatically comparing the data in the preliminary identification report with the preset threshold parameters without human intervention, for example, through numerical comparison or confidence assessment based on a machine learning model.

[0045] In practice, if the comparison result is within the allowable threshold range, it indicates that the check has passed and meets the specifications. At this time, the system will generate and render a pass status marker at the corresponding coordinate position of the composite drawing data. This pass status marker can be a green checkmark icon or "OK" text generated on a specific layer of the composite drawing data at the center point or boundary of the geometric or text annotation that has passed the check, and then rendered and displayed on the user interface; or it can be added by modifying the attribute field of the corresponding design element in the composite drawing data to add a "Check Status: Pass" label, and displaying these passed elements in a semi-transparent or specific color (such as light green) during visualization.

[0046] Furthermore, if the comparison results exceed the allowable threshold, it indicates that there are errors that need attention or correction. The system will generate a highlighted warning box graphic data at the corresponding coordinates based on the specific error type. This highlighted warning box graphic data can draw a red rectangle or circle border in the error area of ​​the composite drawing data (such as a collision area or a line segment with dimensional deviation), and make it flash to clearly mark the error area. Simultaneously, the system will automatically link to the solution knowledge base in the nested base map database to generate modification suggestion text. The solution knowledge base stores correction methods, standard practices, or best practices for various error types and their possible causes. Based on the detected error type (e.g., "pipe collision," "dimensional deviation"), the system will retrieve predefined modification suggestion templates from the knowledge base, such as "Please check if the pipe route is reasonable, or adjust the pipe diameter to avoid collisions" or "Please adjust the dimensions to the standard range [X, Y]".

[0047] Ultimately, the system integrates all generated status markers, highlighted warning box graphics, and suggested modification text, and generates a structured verification conclusion according to the report template defined by the system's base map data structure. The report template defined by the system's base map data structure is a predefined report framework that conforms to specific format and content requirements. This integration process can either populate all verification result data into a preset PDF or HTML report template, which may include a report title, project information, an error summary list (sorted by error level and type), and error details (error screenshots, coordinates, and modification suggestions); or store these verification result data in a specific database table and provide a user interface that allows users to dynamically generate and view structured verification conclusions based on different filtering conditions (such as error level and professional type). By automatically comparing the raw data in the preliminary identification report with preset multi-level matching threshold parameters, the system achieves quantitative evaluation and classification of the identification results. This comparison process can quickly determine whether each identified problem is within an acceptable range. For design elements whose comparison results are within the allowable threshold range, the system generates and renders pass status markers at the corresponding coordinate positions in the composite drawing data, intuitively showing designers the parts that have met the specifications, thereby reducing unnecessary attention. Conversely, if the comparison results exceed the allowable threshold, the system generates prominent highlighted warning boxes at the corresponding coordinate positions in the drawing, based on the specific error type, accurately indicating the problem. Furthermore, the system automatically connects to the solution knowledge base in the nested base map database, intelligently generating specific modification suggestion text based on the detected error type. Finally, this solution integrates all generated pass status markers, highlighted warning box graphics, and modification suggestion text, and generates a structured verification conclusion according to the predefined report template of the system's base map data structure. This conclusion not only clearly summarizes all verification results but also provides error levels, precise error location, and actionable modification suggestions, greatly improving the usability and guidance of the initial identification report. In this way, the solution transforms the original, scattered preliminary identification reports into structured information that is easy to understand and process, effectively solving the technical problems that designers find difficult to intuitively understand, quickly locate errors, and obtain effective modification guidance, thus significantly improving the efficiency of verification and the convenience of subsequent processing.

[0048] Step S50: Based on the error level in the structured verification conclusion, automatically trigger the corresponding processing mechanism instruction to execute the verification process.

[0049] The AI ​​recognition method used in this embodiment is shown in the table below:

[0050] Furthermore, the automated verification process is as follows: graph TD A [Start Verification] --> B (AI extracts system base map design elements) B --> C {Matches the nested basemap rule} C -->|Match successful| D[Generate green pass marker] C -->|Match failed| E [Location error coordinates + red warning box] E --> F [Related knowledge base push modification suggestions] In this embodiment, the closed-loop review and process reset include: 1. Hierarchical processing mechanism, general error: the system automatically locks the error area, and the executor must correct it within 24 hours and submit it for AI re-inspection (such as missing dimension annotation). Major conflict: triggers a three-level interlocking mechanism: (1) freeze the related drawing editing permissions (2) push an S-level alarm to the approver (SMS / platform pop-up) (3) automatically initiate a cross-professional joint signing process 2. Process reset logic, after the approver rejects, the system generates a "backtracking path diagram", highlights the base map version that needs to be re-nested and the related modification points, and leaves historical operation traces on the blockchain to ensure that the process cannot be tampered with and meets the design quality traceability requirements.

[0051] In specific implementation, the step of automatically triggering corresponding processing mechanism instructions based on the error level in the structured verification conclusion to execute the verification process includes: automatically classifying the error types in the structured verification conclusion into general errors or major conflicts according to a preset error classification-strategy mapping table; for general errors, automatically generating a layer local locking instruction to restrict editing of the error area and simultaneously starting a correction countdown monitoring task; for major conflicts, automatically triggering a three-level interlocking processing instruction sequence, wherein the three-level interlocking processing instruction sequence includes, in turn: generating a full-drawing association freeze instruction to lock the editing and circulation permissions of all related drawings; generating an alarm push instruction to a preset approval node system account; generating a cross-professional joint signature process creation instruction and automatically assigning joint signature tasks; continuously monitoring the execution feedback of the processing mechanism instructions, and maintaining the corresponding verification process control state until receiving an AI re-inspection pass signal corresponding to the error item.

[0052] It should be noted that for general errors, the system automatically generates a layer local locking command to restrict editing of the erroneous area and simultaneously starts a correction countdown monitoring task. This feature provides a flexible yet effective control mechanism for general errors with minor harm and limited impact. Through local locking and countdown monitoring, designers are allowed to make corrections within a limited scope while ensuring the timeliness of the correction and preventing problems from being shelved for a long time. When the system identifies a general error, it sends a command to the CAD / BIM software interface to set the layer or specific area containing the error to read-only or edit-restricted status, while starting a timer in the background to record the remaining time for correction and periodically reminding relevant designers. Alternatively, the system can maintain an error processing queue, marking general errors as "pending correction" with a deadline. On the user interface, the erroneous area is highlighted with a specific color, and modifications to non-erroneous areas are prohibited until the error is corrected and passes the review. For major conflicts, the system automatically triggers a three-tiered interlocking processing instruction sequence, which includes: generating a full-drawing association freeze instruction to lock the editing and circulation permissions of all related drawings; generating an alarm push instruction to the preset approval node system accounts; and generating a cross-disciplinary co-signing process creation instruction and automatically assigning co-signing tasks. This feature adopts more stringent and mandatory multi-level processing measures for major conflicts that may lead to serious consequences. Through freezing, alarms, and co-signing, it ensures that major issues can be addressed immediately and that cross-departmental and cross-disciplinary collaborative resolution mechanisms are initiated to prevent the spread of risks. When a major conflict is detected, the system first sends an instruction to the version control system or drawing management system to set all drawing files associated with the current drawing to a "frozen" state, prohibiting any editing, submission, or circulation operations. At the same time, an emergency alarm is sent to preset approval nodes such as project managers and professional leaders through the enterprise internal messaging system or email service. Subsequently, the system automatically creates a new co-signing task in the workflow management platform and assigns the task to engineers of the relevant specialties according to preset professional association rules. Alternatively, the system can integrate a permission management module. When a major conflict occurs, this module temporarily revokes the editing permissions of relevant designers for the affected drawings and prevents their publication or printing. Alerts can be sent via SMS, instant messaging tools, or in-system notifications. The creation of the countersigning process can be based on a predefined template, automatically filling in conflict information and a list of relevant personnel, and initiating the approval flow. The system continuously monitors the execution feedback of the processing mechanism instructions, maintaining the corresponding verification process control state until it receives an AI re-check pass signal corresponding to the error item. This feature ensures the continuous closed-loop management and control of the verification process. Only after the error is corrected and confirmed by the AI ​​re-check will the corresponding restrictions be lifted, thus guaranteeing the quality of the correction and the rigor of the process.The system assigns a status listener to each triggered processing mechanism instruction (whether it's a local lock or a three-level interlock). Once the designer completes the correction and submits it, the system again invokes the AI ​​recognition engine to re-check the corrected area or drawing. Only when the AI ​​re-check result shows that the error has been resolved (i.e., an AI re-check pass signal is received) will the system release the corresponding lock or freeze state. Alternatively, the system maintains a list of errors awaiting re-check. After the designer submits a correction, the error item status changes to "awaiting AI re-check." The AI ​​recognition engine periodically scans this list, automatically re-checking items marked "awaiting AI re-check." If the re-check passes, the error status is updated to "resolved," and the previously applied control measures are automatically released.

[0053] Step S60: If the verification process is rejected by the authorized node, a backtracking path diagram is automatically generated based on the rejection instruction and the operation history stored in the system base map data structure, and the process status is reset to the specified stage.

[0054] In this embodiment, when an authorizing node issues a rejection instruction, the system can automatically generate a backtracking path diagram containing a list of operation steps based on the operation history stored in the system's underlying data structure (e.g., a simple operation log file). This path diagram can indicate the key operation nodes. Simultaneously, the system resets the process state to the historical stage specified in the rejection instruction.

[0055] Furthermore, in actual engineering design, upstream base maps associated with the current composite drawing data may undergo version changes. Failure to promptly detect and assess the impact of these changes on the current design could render completed verification results invalid, leading to design rework or potential engineering quality issues. To address this, this application proposes continuously monitoring the version status identifiers of all upstream base maps associated with the current composite drawing data based on the aforementioned topology dependency matrix. The topology dependency matrix is ​​structured data describing the logical relationships and dependency levels between design elements, its function being to clearly identify the external design information sources upon which the current composite drawing data depends, i.e., the upstream base maps. Continuously monitoring the version status identifiers of upstream base maps means that the system obtains the latest version information of the upstream base maps in real time through preset mechanisms, such as periodically querying the version control system of the upstream base maps or receiving change notifications from the upstream base map version management system. This aims to ensure that the current design is always based on the latest and most valid upstream data, avoiding design errors caused by information lag. When a change in the version status identifier of any upstream base map is detected, the system automatically invokes the version comparison engine to analyze the changes and generate a design change impact analysis report. When the system detects a change in the version status of the upstream base map, it automatically launches the version comparison engine. This engine can be a standalone software module or a set of algorithms for comparing differences in drawing data. It is responsible for performing a deep comparison of the old and new versions of the upstream base map, identifying all added, modified, or deleted design elements, such as geometric shapes, text annotations, and entity models. Subsequently, the engine organizes and summarizes this difference information, generating a detailed design change impact analysis report. This report clearly describes the specific content and scope of the changes, providing a data foundation for subsequent impact assessment. Based on the design change impact analysis report, combined with the logical links and the topological dependency matrix, the system assesses the impact level of the changes on specific design elements in the current composite drawing data. Upon receiving the design change impact analysis report, the system comprehensively utilizes the logical links and topological dependency matrix established in claim 3. The logical links reveal the direct association between the standard base map and the system base map design elements, while the topological dependency matrix further clarifies the dependency hierarchy of these associations. By analyzing the changes and their links and dependencies, the system can accurately assess the impact of upstream changes on specific design elements in the current composite drawing data and classify them into different impact levels, such as "low," "medium," and "high." This can be based on a preset rule base or intelligently evaluated using a machine learning model, allowing for differentiated processing measures. Based on the impact level, the system generates a nested adaptation suggestion report, which includes the drawing areas requiring re-nesting and verification, along with associated design point identifiers. Based on the assessed impact level, the system automatically generates a nested adaptation suggestion report.The core of this report is to clearly identify which drawing areas require re-nesting due to upstream changes, and which design elements need to be re-verified. The report includes the precise coordinate range or layer information of these affected areas and lists associated design point identifiers, providing designers with clear and specific guidance to avoid unnecessary global rework. Finally, the system updates the status of the current composite drawing data to "Pending Re-nesting" and pushes a mandatory re-verification notification to the relevant responsible node system accounts based on the impact level. After generating the nesting adaptation suggestion report, the system automatically updates the internal status of the current composite drawing data to "Pending Re-nesting" to mark it as requiring further processing. Simultaneously, based on the assessed impact level, the system pushes a mandatory re-verification notification to the relevant responsible node system accounts for the affected areas or design elements, such as specific designers or project managers. This instruction aims to ensure that all design parts affected by the changes are promptly and mandatorily reviewed and verified, thereby maintaining the overall quality and consistency of the design.

[0056] Furthermore, a method is proposed to capture every key operational event from constructing the system's base map data structure to generating structured verification conclusions, forming an operational event chain, which carries a timestamp. An event feature hash value is generated based on the core data of each event in the operational event chain, where the core data includes the operation content, execution context, and hash digests of input and output data. The event feature hash value is uploaded in real-time to a blockchain evidence storage network for distributed storage. When a quality traceability request is initiated, the complete trusted operational history chain is retrieved and restored from the blockchain evidence storage network based on a globally unique version identifier or time range. Based on the trusted operational history chain, a visualized full-process traceability path diagram is dynamically generated and displayed in a graphical interface, highlighting all approval nodes, process rejection points, and associated design modification operations.

[0057] It should be noted that capturing each key operational event to form an operational event chain, and attaching a timestamp, means that the system records every important operation or state change in the design verification process. These key operational events may include, but are not limited to, the creation of the system's base map data structure, the retrieval and nesting of the standard base map, the invocation of the artificial intelligence recognition engine, the generation of the preliminary recognition report, the formation of structured verification conclusions, the triggering of processing mechanism instructions, the rejection of the verification process, and any design modification operations. Capturing these events can be achieved by embedding event listeners or loggers in the system's key functional modules. When a specific function is invoked or the data state changes, an event record is immediately generated. Each event record is accompanied by a precise timestamp to identify the specific time the event occurred, ensuring the sequentiality and time-series traceability of the event chain. The formation of the operational event chain involves linking these independent event records in chronological or logical order to form a complete sequence reflecting the entire design verification process. An event feature hash value is generated based on the core data of each event in the operational event chain. This core data includes the operation content, execution context, and hash digests of input and output data. Core data constitutes the key information in the event record, detailing the nature and impact of the event. Operation content specifies the event type, such as "creating system base map data structure," "performing AI recognition," or "generating verification conclusions." The execution context provides environmental information at the time of the event, such as the user's identity, the terminal's IP address, and system configuration parameters. The hash digest of input and output data is a fixed-length string obtained by cryptographically hashing the key data (such as composite map data, preliminary identification reports, and structured verification conclusions) involved before and after event processing. The hash digest is unique and irreversible; any minor modification to the original data will result in a change to the hash digest, thus ensuring data integrity and tamper-proofness. By combining these core data and calculating their hash values, a unique "fingerprint" can be generated for each event, ensuring the authenticity and non-repudiation of the event record. Uploading the event feature hash value to the blockchain evidence storage network in real time for distributed storage means that after the hash value of each event is generated, it is immediately sent as transaction data to the pre-defined blockchain network. A blockchain-based evidence storage network can be a consortium blockchain or a private blockchain. Its key features include immutability of data once it's uploaded to the chain, and redundancy and high availability ensured through distributed ledger technology. Real-time upload mechanisms guarantee the timeliness of event recordings, avoiding the risk of data loss or tampering. Distributed storage means that event hash values ​​are replicated and stored across multiple nodes in the network, further enhancing data security and reliability. When a quality traceability request is initiated, the complete and trusted operational history chain is retrieved and restored from the blockchain-based evidence storage network based on a globally unique version identifier or time range.Quality traceability requests are typically initiated when auditing, troubleshooting, or verifying design compliance is required. Users can specify a specific globally unique version identifier (e.g., the version number of a composite drawing data) to trace all operational history of that version, or specify a time range to view all relevant operations within a specific time period. The system retrieves all matching event hashes and their associated metadata based on these conditions through the blockchain network's query interface. Due to the tamper-proof nature of the blockchain, the retrieved operational history chain is "trustworthy," meaning its integrity and authenticity are guaranteed. Based on the trusted operational history chain, a visual full-process traceability path diagram is dynamically generated and displayed in the graphical interface. This diagram highlights all approval nodes, process rejection points, and associated design modification operations. After obtaining the trusted operational history chain, the system uses this data to dynamically construct a flowchart or timeline on a user-friendly graphical interface. This traceability path diagram intuitively displays each step in the design verification process, the time of the event, the executor, and related data. To enhance readability and problem localization, the system highlights key nodes, such as "approval nodes" where decisions or confirmations are made manually, "process rejection points" where the process is interrupted or requires rework, and "related design modification operations" performed after rejection. This visualization allows users to understand the evolution of the entire process at a glance and quickly locate the location and cause of problems.

[0058] In this embodiment, a matching standard base map is retrieved from the nested base map database based on the current design stage identifier. The standard base map is then automatically nested into the current system base map using spatial matching based on the system base map data structure, generating composite drawing data. An AI recognition engine is invoked to identify the composite drawing data according to verification rules, generating a preliminary recognition report. Based on this report, a structured verification conclusion is automatically mapped and integrated. The structured verification conclusion triggers corresponding processing mechanism instructions to drive the verification process. If the process is rejected, a backtracking path diagram is automatically generated based on the operation history, and the process state is reset. By utilizing dynamic coupling verification with dual base maps, the entire design verification process is automated, intelligent, and standardized, significantly improving verification efficiency, accuracy, and quality controllability.

[0059] Furthermore, this embodiment of the invention also proposes a storage medium storing an AI-based system base map nested recognition and verification program. When the AI-based system base map nested recognition and verification program is executed by a processor, it implements the steps of the AI-based system base map nested recognition and verification method described above.

[0060] Reference Figure 2 , Figure 2This is a structural block diagram of the first embodiment of the system base map nested recognition and verification system based on artificial intelligence of the present invention.

[0061] like Figure 2 As shown, the system map nesting recognition and verification system based on artificial intelligence proposed in this embodiment of the invention includes: Module 10 is used to construct the system base map data structure and the nested base map database. The system base map data structure defines the data organization format and version management framework for the editable basic map atlas. The nested base map database stores read-only standard map atlases used for verification reference and their associated verification rule knowledge base. Nested module 20 is used to respond to the verification command, retrieve a matching standard base map from the nested base map database according to the current design stage identifier, and automatically nest the standard base map into the current system base map in a spatial matching manner based on the system base map data structure to generate composite drawing data; Output module 30 is used to call the artificial intelligence recognition engine to automatically recognize the composite map data according to the verification rules in the nested base map database and generate a preliminary recognition report. The preliminary recognition report includes error type, coordinate position and rule violation number. The processing module 40 is used to automatically map and integrate the results based on the preliminary identification report to obtain a structured verification conclusion, which includes the error level, error location box, and modification suggestions. The execution module 50 is used to automatically trigger the corresponding processing mechanism instruction based on the error level in the structured verification conclusion to execute the verification process; The control module 60 is used to automatically generate a backtracking path diagram and reset the process status to a specified stage if the verification process is rejected by the authorized node, based on the rejection instruction and the operation history stored in the system base map data structure.

[0062] In this embodiment, a matching standard base map is retrieved from the nested base map database based on the current design stage identifier. The standard base map is then automatically nested into the current system base map using spatial matching based on the system base map data structure, generating composite drawing data. An AI recognition engine is invoked to identify the composite drawing data according to verification rules, generating a preliminary recognition report. Based on this report, a structured verification conclusion is automatically mapped and integrated. The structured verification conclusion triggers corresponding processing mechanism instructions to drive the verification process. If the process is rejected, a backtracking path diagram is automatically generated based on the operation history, and the process state is reset. By utilizing dynamic coupling verification with dual base maps, the entire design verification process is automated, intelligent, and standardized, significantly improving verification efficiency, accuracy, and quality controllability.

[0063] This application embodiment also provides an artificial intelligence-based system base map nested recognition and verification device, including a processor, a communication interface, a memory, and a communication bus. The processor, communication interface, and memory communicate with each other through the communication bus. The memory is used to store the artificial intelligence-based system base map nested recognition and verification program. When the processor executes the program stored in the memory, it implements the above-mentioned artificial intelligence-based system base map nested recognition and verification method.

[0064] The communication bus mentioned in the aforementioned AI-based system map nested recognition and verification device can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. This communication bus can be divided into address bus, data bus, control bus, etc.

[0065] The communication interface is used for communication between the aforementioned AI-based system base map nested recognition and verification device and other devices.

[0066] The memory may include random access memory (RAM) or non-volatile memory (NVM), such as at least one disk storage device. Optionally, the memory may also be at least one storage device located remotely from the aforementioned processor.

[0067] The processors mentioned above can be general-purpose processors, including central processing units (CPUs), network processors (NPs), etc.; they can also be digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0068] In the above embodiments, implementation can be achieved entirely or partially through software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented entirely or partially in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (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 integrates one or more 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 (e.g., solid state disk (SSD)).

[0069] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0070] The various embodiments in this specification are described in a related manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, the system embodiments are basically similar to the method embodiments, so the description is relatively simple; relevant parts can be referred to the descriptions of the method embodiments.

[0071] The above embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

[0072] It should be understood that the above are merely illustrative examples and do not constitute any limitation on the technical solutions of the present invention. In specific applications, those skilled in the art can make settings as needed, and the present invention does not impose any restrictions on this.

[0073] It should be noted that the workflow described above is merely illustrative and does not limit the scope of protection of this invention. In practical applications, those skilled in the art can select some or all of the workflow to achieve the purpose of this embodiment according to actual needs, and no restrictions are imposed here.

[0074] In addition, for technical details not described in detail in this embodiment, please refer to the AI-based system base map nesting recognition and verification method provided in any embodiment of the present invention, which will not be repeated here.

[0075] Furthermore, it should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or system. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or system that includes that element.

[0076] The sequence numbers of the above embodiments of the present invention are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0077] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as read-only memory (ROM) / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods described in the various embodiments of the present invention.

[0078] The above are merely preferred embodiments of the present invention and do not limit the scope of the patent. Any equivalent structural or procedural transformations made based on the description and drawings of the present invention, or direct or indirect applications in other related technical fields, are similarly included within the scope of patent protection of the present invention.

[0079] It is understood that the system provided in the embodiments of the present invention corresponds to the method provided in the embodiments of the present invention, and the explanation, examples and beneficial effects of the relevant content can be referred to the corresponding parts of the above methods.

Claims

1. A system base map nested recognition and verification method based on artificial intelligence, characterized in that, The AI-based system base map nesting recognition and verification method includes: Construct a system base map data structure and a nested base map database. The system base map data structure is used to define the data organization format and version management framework of the editable basic map book. The nested base map database stores the read-only standard map book for verification reference and its associated verification rule knowledge base. In response to the verification instruction, a matching standard base map is retrieved from the nested base map database based on the current design stage identifier, and the standard base map is automatically nested into the current system base map in a spatial matching manner based on the system base map data structure to generate composite drawing data; The artificial intelligence recognition engine is invoked to automatically recognize the composite map data according to the verification rules in the nested base map database, and a preliminary recognition report is generated. The preliminary recognition report includes the error type, coordinate location, and violation rule number. Based on the preliminary identification report, the results are automatically mapped and integrated to obtain a structured verification conclusion, which includes the error level, error location box, and modification suggestions. Based on the error level in the structured verification conclusion, the corresponding processing mechanism instruction is automatically triggered to execute the verification process; If the verification process is rejected by the authorized node, a backtracking path diagram is automatically generated based on the rejection instruction and the operation history stored in the system base map data structure, and the process status is reset to the specified stage.

2. The system base map nesting recognition and verification method based on artificial intelligence as described in claim 1, characterized in that, The process of retrieving a matching standard base map from the nested base map database based on the current design stage identifier, and automatically nesting the standard base map into the current system base map using spatial matching based on the system base map data structure to generate composite drawing data includes: Parse the metadata of the current system base map and extract the current design stage identifier, which includes the professional type identifier and the design stage code; Using the professional type identifier and the design stage code as query conditions, a matching standard base map is retrieved from the nested base map database; The standard base map is embedded into the system base map in read-only visualization mode to form the composite map data, and a globally unique version identifier is generated for the composite map data.

3. The system base map nesting recognition and verification method based on artificial intelligence as described in claim 1, characterized in that, The process of calling the artificial intelligence recognition engine to automatically recognize the composite map data based on the verification rules in the nested base map database, and generating a preliminary recognition report, including: The composite drawing data is parsed to extract geometric figures, text annotations, and entity model information, and then converted into a standardized feature vector set. The graphics processing engine is invoked to perform spatial alignment calculations between the standard base map and the current system base map, generating a spatial alignment matrix. Based on the spatial alignment matrix, a logical link between the standard base map and the system base map design elements is established in the association layer defined by the system base map data structure, and a topological dependency matrix describing the dependency relationship of the logical link is automatically calculated and generated. The geometric feature recognition sub-engine is invoked. Based on the elements associated with the topological dependency matrix, the corresponding line type and size data in the standardized feature vector set are processed by a convolutional neural network. The data is then compared with the pre-stored standardized primitives in the nested base map database to output a geometric feature deviation dataset. The semantic rule recognition sub-engine is invoked to load the industry standard knowledge graph in the nested base map database based on the system base map design elements associated with the logical links, perform semantic parsing and compliance verification, and output a list of rule violation items. The collision detection sub-engine is invoked, and based on the spatial hierarchy defined by the topological dependency matrix, a voxelized spatial segmentation algorithm is used to perform spatial interference analysis on the multi-disciplinary 3D entities in the composite drawing data, and output a set of spatial collision and conflict coordinates. The geometric feature deviation dataset, the list of rule violations, and the spatial collision conflict coordinate set are integrated and normalized according to a preset format to form a preliminary identification report.

4. The system base map nesting recognition and verification method based on artificial intelligence as described in claim 3, characterized in that, The automatic mapping and integration of results based on the preliminary identification report to obtain structured verification conclusions includes: The data in the preliminary identification report are automatically compared with the preset multi-level matching threshold parameters; If the comparison result is within the allowable threshold range, a status marker is generated and rendered at the corresponding coordinate position of the composite image data. If the comparison result exceeds the allowable threshold, the system generates a highlighted warning box graphic data at the corresponding coordinates according to the error type, and automatically associates it with the solution knowledge base in the nested base map database to generate modification suggestion text; Integrate all data from status markers, highlighted warning boxes, and suggested modifications, and generate a structured verification conclusion according to the report template defined by the system's base map data structure.

5. The system base map nesting recognition and verification method based on artificial intelligence as described in claim 1, characterized in that, The step of automatically triggering corresponding processing mechanism instructions based on the error level in the structured verification conclusion to execute the verification process includes: Based on the preset error classification-strategy mapping table, the error types in the structured verification conclusions are automatically classified into general errors or major conflicts; For general errors, a layer local lock command is automatically generated to restrict editing of the erroneous area, and a correction countdown monitoring task is started simultaneously; For major conflicts, a three-level interlocking processing instruction sequence is automatically triggered, wherein the three-level interlocking processing instruction sequence includes, in turn: generating a full-drawing association freeze instruction to lock the editing and circulation permissions of all related drawings; generating an alarm push instruction to the preset approval node system account; generating a cross-professional joint signature process creation instruction and automatically assigning joint signature tasks; The execution feedback of the processing mechanism instructions is continuously monitored, and the corresponding verification process control status is maintained until the AI ​​re-examination pass signal corresponding to the error item is received.

6. The system base map nesting recognition and verification method based on artificial intelligence as described in claim 3, characterized in that, The method further includes: Based on the aforementioned topology dependency matrix, continuously monitor the version status identifiers of all upstream base maps associated with the current composite map data; When a change in the version status identifier of any upstream base map is detected, the version comparison engine is automatically invoked to analyze the changes and generate a design change impact analysis report. Based on the design change impact analysis report, combined with the logical links and the topological dependency matrix, assess the level of impact of the change on specific design elements in the current composite drawing data. A nested adaptation suggestion report is generated based on the impact level. The nested adaptation suggestion report includes the drawing areas that need to be re-performed nesting and verification, as well as the associated design point identifiers. Update the status of the current composite map data to pending re-nesting, and push a forced re-verification notification instruction to the relevant responsible node system account according to the impact level.

7. The system base map nesting recognition and verification method based on artificial intelligence as described in any one of claims 1 to 5, characterized in that, The method further includes: Capture every key operational event from constructing the system base map data structure to generating the structured verification conclusion to form an operational event chain, the operational event chain carrying a timestamp; An event feature hash value is generated based on the core data of each event in the operation event chain. The core data includes the operation content, execution context, and hash digests of input and output data. The event feature hash value is uploaded to the blockchain evidence storage network in real time for distributed storage. When a quality traceability request is initiated, the complete trusted operation history chain is retrieved and restored from the blockchain evidence storage network based on the globally unique version identifier or time range. Based on the trusted operation history chain, a visual full-process traceability path diagram is dynamically generated and displayed in the graphical interface. In the visual full-process traceability path diagram, all approval nodes, process rejection points and related design modification operations are highlighted.

8. A system map nesting recognition and verification system based on artificial intelligence, characterized in that, The AI-based system base map nested recognition and verification system is applied to the AI-based system base map nested recognition and verification method as described in any one of claims 1 to 7, wherein the system comprises: The construction module is used to build the system base map data structure and the nested base map database. The system base map data structure defines the data organization format and version management framework for the editable basic map atlas. The nested base map database stores read-only standard map atlases used for verification reference and their associated verification rule knowledge base. The nested module is used to respond to the verification command, retrieve the matching standard base map from the nested base map database according to the current design stage identifier, and automatically nest the standard base map into the current system base map in a spatial matching manner based on the system base map data structure to generate composite drawing data; The output module is used to call the artificial intelligence recognition engine to automatically recognize the composite map data according to the verification rules in the nested base map database and generate a preliminary recognition report. The preliminary recognition report includes the error type, coordinate location and violation rule number. The processing module is used to automatically map and integrate the results based on the preliminary identification report to obtain a structured verification conclusion, which includes the error level, error location box, and modification suggestions. The execution module is used to automatically trigger the corresponding processing mechanism instructions based on the error level in the structured verification conclusion to execute the verification process; The control module is used to automatically generate a backtracking path diagram and reset the process status to the specified stage if the verification process is rejected by the authorized node, based on the rejection instruction and the operation history stored in the system base map data structure.

9. A system base map nesting recognition and verification device based on artificial intelligence, characterized in that, The AI-based system base map nesting recognition and verification device includes: a memory, a processor, and an AI-based system base map nesting recognition and verification program stored in the memory and executable on the processor. The AI-based system base map nesting recognition and verification program is configured to implement the steps of the AI-based system base map nesting recognition and verification method as described in any one of claims 1 to 7.

10. A storage medium, characterized in that, The storage medium stores an AI-based system base map nested recognition and verification program, which, when executed by a processor, implements the steps of the AI-based system base map nested recognition and verification method as described in any one of claims 1 to 7.

Images