Engineering data linkage method, device, equipment, storage medium and program product

Abstract

This document discloses a method, apparatus, device, storage medium, and program product for engineering data linkage. The method includes: responding to first change information generated by the design end for a first design parameter of a first engineering project, generating second change information linked to the first change information through a first large model; the first large model is established based on engineering domain data, which includes: design change records of a second engineering project, and a linkage impact analysis report corresponding to the design change records; based on the second change information, updating the first design parameter to obtain the second design parameter of the first engineering project. Therefore, it is possible to calculate the chain reaction effects of design parameter changes in real time, thereby better meeting dynamic design needs and improving design efficiency.

Description

Technical Field

[0001] This document relates to the field of engineering design technology, and in particular to an engineering data linkage method, device, equipment, storage medium and program product. Background Technology

[0002] In the field of engineering design, the design processes of different disciplines are isolated from each other, and there is a disconnect between the design and production ends. Design parameters (such as component dimensions and material specifications) need to be manually converted into production parameters (such as casting dimensions and processing accuracy of precast components). This isolated and inefficient processing mode cannot support the dynamic iteration of design and is prone to data deviations that lead to production rework. Summary of the Invention

[0003] The purpose of the embodiments in this specification is to provide an engineering data linkage method, device, equipment, storage medium, and program product that can calculate the chain effects of design parameter changes in real time, and realize the automatic conversion and synchronization of design parameters to production parameters, thereby connecting the design-production link, better meeting dynamic design needs, and improving design and production efficiency.

[0004] To achieve the above objectives, the embodiments in this specification adopt the following technical solutions: Firstly, embodiments of this specification provide an engineering data linkage method, including: In response to the first change information generated by the design end for the first design parameter of the first engineering project, a second change information linked to the first change information is generated through the first large model; the first large model is established based on engineering domain data, which includes: design change records of the second engineering project, and a linkage impact analysis report corresponding to the design change records; Based on the second change information, the first design parameters are updated to obtain the second design parameters for the first project.

[0005] Secondly, embodiments of this specification provide an engineering data linkage device, comprising: The linkage analysis module is used to respond to the first change information generated by the design end for the first design parameter of the first engineering project, and generate second change information linked with the first change information through the first large model; the first large model is established based on engineering domain data, which includes: design change records of the second engineering project, and linkage impact analysis reports corresponding to the design change records; The update module is used to update the first design parameters based on the second change information to obtain the second design parameters of the first project.

[0006] Thirdly, embodiments of this specification provide an electronic device including a processor, a memory, and a computer program stored in the memory and executable on the processor. When the computer program is executed by the processor, it implements the steps of the engineering data linkage method provided in the first aspect.

[0007] Fourthly, embodiments of this specification provide a computer-readable storage medium that, when instructions in the storage medium are executed by a processor of an electronic device, enables the electronic device to perform the steps of the engineering data linkage method provided in the first aspect.

[0008] Fifthly, embodiments of this specification provide a computer program product, the computer program product including a non-transitory computer-readable storage medium storing a computer program operable to cause a computer to perform steps of the engineering data linkage method provided in the first aspect.

[0009] The above-described at least one technical solution adopted in the embodiments of this specification can achieve the following beneficial effects: By leveraging the semantic understanding and processing capabilities of large-scale models, when design parameters for engineering projects are changed at the design end, the cascading effects of the change are calculated in real time, identifying other related changes. Furthermore, the design parameters are updated based on these other changes. This enables cascading changes to design parameters, better meeting dynamic design needs, improving design efficiency, and is widely applicable to the digital collaborative implementation of complex engineering scenarios such as architecture, machinery, and municipal engineering. Attached Figure Description

[0010] The accompanying drawings, which are included to provide a further understanding of this specification and form part of this specification, illustrate exemplary embodiments and are used to explain this specification, but do not constitute an undue limitation thereof. In the drawings: Figure 1 This is a schematic diagram of an example environment in which the embodiments of this specification can be implemented; Figure 2 A flowchart illustrating an engineering data linkage method provided in an embodiment of this specification; Figure 3 This is a schematic diagram of the structure of an engineering data linkage device provided in the embodiments of this specification; Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this specification. Detailed Implementation

[0011] To make the objectives, technical solutions, and advantages of this specification clearer, the technical solutions of this specification will be clearly and completely described below in conjunction with specific embodiments and corresponding drawings. Obviously, the described embodiments are only a part of the embodiments of this specification, and not all of them. All other embodiments obtained by those skilled in the art based on the embodiments in this specification without creative effort are within the scope of protection of this document.

[0012] The term "comprising" and its variations as used in this document are open-ended, meaning "including but not limited to". The term "based on" means "at least partially based on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". Definitions of other terms will be given in the following description. The term "in response to" indicates that the performed operation depends on a condition or state. When the dependent condition or state is met, one or more operations may be performed in real time or with a set delay. Unless otherwise specified, there is no restriction on the order in which multiple operations are performed.

[0013] It should be noted that the concepts of "first" and "second" mentioned in this document are used only to distinguish different devices, modules or units, and are not used to restrict the order of functions performed by these devices, modules or units or their interdependencies.

[0014] It should be noted that the terms "one" and "more" used in this document are illustrative rather than restrictive, and those skilled in the art should understand that, unless explicitly stated otherwise in the context, they should be understood as "one or more".

[0015] The names of messages or information exchanged between multiple devices in this document are for illustrative purposes only and are not intended to limit the scope of such messages or information.

[0016] It should be understood that the training and prediction processes of the artificial intelligence (AI) models involved in the various embodiments of this specification all adhere to multiple legal and compliant principles, including legal data sources, compliant data content, compliant data governance, compliant training objectives and schemes, compliant training processes, compliant training environments and tools, and compliant ethical verification of training results, and comply with the requirements of Article 5 of the Patent Law. Among them: Data source legitimacy: All datasets used for AI model training were obtained through legal means, covering three categories: publicly authorized data, data authorized by partners, and self-collected compliant data. Publicly authorized data comes from compliant data sources following open-source licenses such as Apache 2.0, with complete copyright attribution and authorization scope clearly marked, and no unauthorized open-source code or data reuse. Data authorized by partners has been subject to formal data usage agreements, clearly defining the scope, duration, and confidentiality obligations, and possessing a complete authorization chain. For self-collected data involving personal information, strict informed consent procedures have been followed, and anonymization processes (including but not limited to field masking, feature anonymization, and differential privacy technology applications) have been used to remove personally identifiable information, fully complying with the requirements of the "Interim Measures for the Administration of Generative Artificial Intelligence Services," the "Personal Information Protection Law," and other relevant laws and regulations.

[0017] Data content compliance: The AI ​​model's dataset undergoes multiple screenings and cleaning processes to remove all content that may violate social morality or harm public interests. It contains no obscene, pornographic, violent, discriminatory, or information that endangers national or public safety, nor does it involve the illegal acquisition or use of genetic resources. For data in sensitive fields (such as healthcare and finance), an additional privacy-preserving computation module (including federated learning and secure multi-party computation technologies) ensures that the data is "usable but not visible," avoiding compliance risks during the original data transmission process and ensuring that the data application scenarios and uses comply with public order and good morals and industry regulatory requirements.

[0018] Data governance norms: A complete data traceability system is established during the AI ​​model training process to automatically record the source, collection time, annotation process, cleaning rules, and permission allocation of training data, generating traceable compliance reports to ensure that the data is verifiable throughout its entire lifecycle. The dataset annotation process for AI models is completed by a professional human R&D team, clearly defining the proportion of human creative contributions and avoiding reliance on AI-generated data that has not undergone substantial human modification, thus meeting the examination requirements for "human main contributions" in AI patent applications.

[0019] Training objectives and plans are compliant: The AI ​​model training objectives are focused on engineering design and production scenarios. The training scheme and the final output results do not violate any mandatory provisions of laws and administrative regulations, do not harm the public interest or the legitimate rights and interests of others, and do not pose any potential risks of being used for illegal activities, infringing on privacy, or disrupting public safety. The model strictly adheres to the ethical principle of "intelligent for good".

[0020] Training process compliance: A closed-loop training framework is adopted to ensure compliance and controllability of the training process. The specific process is as follows: First, training samples are obtained through compliant data sources. After the aforementioned data cleaning and desensitization, they are input into the neural network model to generate preliminary training results. Second, an expert system is introduced to verify the preliminary results. Based on preset rules and human expert experience, the feasibility of the results is evaluated, and outputs that may pose ethical risks or compliance hazards are corrected (such as removing decision-making logic that violates public order and good morals, and adjusting model parameters that do not comply with safety regulations). Finally, the loss function weights are dynamically optimized based on expert system feedback to strengthen the model's learning of compliant results, avoid overfitting errors or non-compliant labels, and form a closed-loop control of "data input - model training - expert verification - parameter optimization - result feedback" to ensure that the entire training process complies with A5 ethical review requirements.

[0021] Training environment and tool compliance: AI model training is implemented using nationally licensed chips and a compliant training platform. All open-source frameworks and components used in the training process have obtained their corresponding licenses, and copyright statements and patent citation information are fully retained, with no instances of infringement or reuse. The training environment is built using virtual devices (containers / virtual machines) with fixed random seeds and initial parameter configurations to ensure the reproducibility of the training process. Furthermore, through access control and operation log recording, risks such as data leakage and parameter tampering during training are prevented, ensuring the security and compliance of the training process.

[0022] Training results ethical verification compliance: After the model is trained, it undergoes additional third-party ethical compliance assessment and algorithm filing review to verify that the model output does not violate social morality or harm public interests. For potentially sensitive scenarios (such as public services and intelligent decision-making), a special result verification mechanism is established to ensure that the model always complies with Article 5 of the Patent Law and relevant laws and regulations in practical applications.

[0023] In summary, the data and training process used in the AI ​​model of this specification strictly comply with the relevant provisions of Article 5 of the Patent Law and the Patent Examination Guidelines. There are no violations of laws, social ethics, public interests, or illegal use of genetic resources, and the model fully meets the compliance requirements for patent authorization.

[0024] Intelligent linkage refers to connecting and coordinating different devices or systems through Internet of Things (IoT) technology to achieve data sharing and automated control, thereby improving operational efficiency, optimizing resource utilization, and enhancing user experience. It is widely used in many fields such as smart homes, industrial automation, and smart cities. Its core lies in the organic combination of sensing, communication, and decision-making capabilities, enabling each component to automatically execute corresponding actions based on preset conditions or real-time environmental changes, forming an efficient and collaborative working mode.

[0025] Currently, the engineering design field still lacks the capabilities for real-time calculation and cross-disciplinary collaboration, as well as design-production linkage. Design processes across different disciplines are isolated, and there is a disconnect between the design and production ends. This necessitates manual conversion of design parameters (such as component dimensions and material specifications) into production parameters (such as precast component casting dimensions and processing precision). After some design parameters change, it can take hours to days to obtain the impact of changes on other related design parameters, failing to meet the needs of dynamic design. Furthermore, the disconnect between the design and production processes, coupled with the inefficient manual conversion process, easily leads to data discrepancies, resulting in production rework and impacting production efficiency.

[0026] In view of this, the embodiments of this specification propose an engineering data linkage method. Utilizing the semantic understanding and processing capabilities of a large model, it calculates the cascading effects of design parameter changes in real time, and determines other change information linked to the current change information. This enables cascading changes to design parameters, better meeting dynamic design needs, improving design efficiency, and is widely applicable to the digital collaborative implementation of complex engineering scenarios such as architecture, machinery, and municipal engineering.

[0027] Optionally, the modified design parameters can be converted into production parameters through a large model, achieving automatic conversion and synchronization between design and production parameters, thus streamlining the design-production process. This better meets dynamic design needs and improves design and production efficiency.

[0028] It should be understood that the engineering data linkage method provided in the embodiments of this specification can be executed by an electronic device. The electronic device referred to herein can include any type of mobile terminal, fixed terminal, or portable terminal, specifically including but not limited to: smartphones, tablets, laptops, desktop computers, smart voice interaction devices, smart wearable devices, etc.; or, the electronic device can also include a server, such as an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server providing cloud computing services.

[0029] The technical solutions provided in the various embodiments of this specification are described in detail below with reference to the accompanying drawings.

[0030] Figure 1 A schematic diagram of an example environment in which embodiments of this specification can be implemented is shown. This example environment includes a design end 110, an engineering data linkage device 120, and a production end 130.

[0031] Design terminal 110 may include various design systems, which are designed for designers in different disciplines. Designers can use these systems to design and modify engineering projects. For example, design system 1 is for architects, used to design and modify architectural parameters; design system 2 is for structural engineers, used to design and modify structural parameters; and design system 3 is for mechanical and electrical engineers, used to design and modify mechanical and electrical parameters.

[0032] The production end 130 can include multiple production systems. Each production system processes different production parameters.

[0033] The engineering data linkage device 120 is communicatively connected to both the design end 110 and the production end 130. The engineering data linkage device 120 can access various design systems in the design end 110 and various production systems in the production end 130. The engineering data linkage device 120 can obtain design parameters for the engineering project from the production end 110, call up the large model, perform linkage analysis based on changes to design parameters in some design systems, determine the design parameters to be changed from other design systems, and send change information to other design systems. The engineering data linkage device 120 can also convert the design parameters of the engineering project into production parameters through the large model and send them to the production end 130.

[0034] In some embodiments, the engineering data linkage device 120 may include the following six levels: Data access layer: Accesses various design systems on the design end 110 and various production systems on the production end 130, and performs unified access and format standardization processing of data from these systems.

[0035] Linked Calculation Layer: Based on the large model, it realizes the linkage of design changes and the automatic conversion from design parameters to production parameters.

[0036] Information processing layer: Provides functions such as cross-disciplinary semantic parsing, key information extraction, and compliance verification, enabling large models to achieve cross-disciplinary semantic understanding of professional terms.

[0037] Collaborative Control Layer: Provides functions such as dynamic process scheduling, conflict early warning, and change tracking. The large model dynamically adjusts the collaborative process based on project stages (such as scheme design, construction drawings, and production preparation), and identifies design conflicts and design-production adaptation conflicts (such as design component dimensions exceeding the processing range of production equipment) in advance by combining linkage analysis results.

[0038] Design-Production Linkage Layer: Provides functions such as pushing design data to the production end and synchronizing production feedback to the design end. It synchronizes design changes from the large model to the production end (such as the production system of a precast component plant) in real time, and receives feedback from the production end (such as design adjustment suggestions due to material shortages), forming a closed loop.

[0039] Application presentation layer: Provides functions such as visual monitoring, collaborative interaction, and production progress linkage display. It supports the linkage display of design models and production progress dashboards, and designers can view the "impact of design changes on production scheduling" in real time.

[0040] In practical applications, the engineering data linkage device 120 can be deployed in electronic devices. The electronic devices referred to here can include any type of mobile terminal, fixed terminal, or portable terminal, specifically including but not limited to: smartphones, tablets, laptops, desktop computers, intelligent voice interaction devices, intelligent wearable devices, etc.; or, the electronic devices can also include servers, such as independent physical servers, server clusters or distributed systems composed of multiple physical servers, or cloud servers that provide cloud computing services.

[0041] Based on the above example environment, this specification also provides an engineering data linkage method. Please refer to... Figure 2 This is a flowchart illustrating an engineering data linkage method provided in an embodiment of this specification. The method includes the following steps: S202, in response to the first change information generated by the design end for the first design parameter of the first engineering project, a second change information linked with the first change information is generated through the first large model.

[0042] The first engineering project can be understood as any engineering project to be processed. The first design parameter can be understood as the current design parameter of the first engineering project. The first design parameter may include multiple sub-parameters, which may belong to different disciplines. In some embodiments, the design end includes multiple design systems, which correspond to different disciplines, and the sub-parameters are derived from the design system corresponding to their respective disciplines.

[0043] For example, the first project is an 18-story residential building. Its first design parameters include sub-parameters from multiple disciplines such as architecture, structure, and mechanical and electrical systems. Architectural sub-parameters may include, but are not limited to, at least one of the following: floor height, bay / depth dimensions, door and window opening dimensions, exterior wall decoration material specifications, insulation layer thickness, stair tread dimensions, bathroom slab drop height, balcony railing height, etc. Structural sub-parameters may include, but are not limited to, at least one of the following: structural beam height, slab thickness, concrete strength grade, rebar specifications and spacing, precast component (composite slab / shear wall) casting dimensions, post-cast strip location, connecting sleeve type, structural slope, etc. Mechanical and electrical sub-parameters may include, but are not limited to, at least one of the following: net height of mechanical and electrical pipelines, pipe diameter and material of water supply and drainage pipes, cable tray specifications and elevation, duct interface dimensions, cable type, switch and socket positioning dimensions, pipe shaft dimensions, equipment foundation type, etc.

[0044] In this scenario, the design end can include design systems corresponding to multiple disciplines such as architecture, structure, and MEP. The design system corresponding to architecture (such as Revit) is used to design and modify the sub-parameters of architecture, the design system corresponding to structure (such as PKPM) is used to design and modify the sub-parameters of structure, and the design system corresponding to MEP (such as RevitMEP and MagiCAD) is used to design and modify the sub-parameters of MEP.

[0045] The first change information may include the first sub-parameter and the amount of change of the first sub-parameter. The first sub-parameter can be understood as the sub-parameter among the aforementioned sub-parameters that has changed. The second change information may include the second sub-parameter and the amount of change of the second sub-parameter. The second sub-parameter can be understood as the sub-parameter among the aforementioned sub-parameters that is linked to the first sub-parameter, or the sub-parameter that is affected by the first sub-parameter.

[0046] Optionally, the second change information may also include the compliance boundaries of the second sub-parameter, such as the requirement that changes to the second sub-parameter "beam height" must comply with the GB 50010 seismic code.

[0047] The first change information can be obtained in various ways. In one implementation, the first design parameters and their first change information for the first project can be read through the interface of the design end. In another implementation, the first design parameters and their first change information can also be received actively pushed by the design end.

[0048] The first major model can be understood as a large model applicable to the field of engineering design. This large model can include, but is not limited to, large language models, multimodal large models, etc. The first major model possesses the ability to understand and process data in the engineering design field, and can perform linked analysis on the first design parameters to obtain second change information linked to the first change information.

[0049] The first major model can be built based on engineering data, which includes: design change records of the second engineering project, and the corresponding impact analysis report of the design change records.

[0050] The second engineering project refers to the engineering project used as a training sample, such as a historical engineering project. The design change record can include the changed sub-parameters, the amount of change in the sub-parameters, etc., while the linkage impact analysis report records the impact of the change of one or more sub-parameters on other sub-parameters, such as which other sub-parameters were affected and the amount of change in other sub-parameters, etc.

[0051] In the embodiments of this specification, S202 described above can be implemented in various ways.

[0052] In one implementation, S202 may include: S2022, through the first major model, performs a linkage analysis on multiple sub-parameters to obtain the second sub-parameter and the influence coefficient of the first sub-parameter on the second sub-parameter.

[0053] The second sub-parameter includes sub-parameters that are linked to the first sub-parameter among multiple sub-parameters.

[0054] Specifically, the first major model invokes the correlation matrix to query the second sub-parameter and the influence coefficient of the first sub-parameter on the second sub-parameter. The correlation matrix includes the linkage relationships and influence coefficients between multiple sub-parameters. The correlation matrix is ​​based on engineering domain data supervision for the first major model. This engineering domain data includes: design change records for the second engineering project, and corresponding linkage impact analysis reports for those design change records.

[0055] The first major model can leverage its understanding and processing capabilities of information in the field of engineering design to understand and analyze design change records and their corresponding linkage impact analysis reports, summarize the linkage relationships and impact coefficients between multiple sub-parameters, and generate a correlation matrix accordingly.

[0056] By calling the correlation matrix through the primary model, the impact coefficient of any second sub-parameter on changes in the first sub-parameter can be queried in real time. This effectively solves the pain points of independent design and information fragmentation in the traditional model. Therefore, the design process no longer relies on manual judgment of the impact of changes, but is automatically extrapolated based on historical data, ensuring full-discipline collaboration on design changes and avoiding problems such as information asynchrony and impact on subsequent production caused by independent design of sub-parameters across disciplines. Furthermore, the correlation matrix is ​​not a static rule base, but is generated by training the primary model based on real design change records and linkage impact analysis reports of the second engineering project. This means that the primary model has self-learning capabilities, and when similar changes occur in a new project, it can quickly retrieve historical linkage relationships to better meet dynamic design needs.

[0057] S2024, Based on the influence coefficient and the change in the first sub-parameter, determine the change in the second sub-parameter; based on the second sub-parameter and the change in the second sub-parameter, generate the second change information.

[0058] Specifically, the second change information may include the second sub-parameter and the amount of change of the second sub-parameter. The amount of change of the second sub-parameter can be determined by multiplying the amount of change of the first sub-parameter by the influence coefficient.

[0059] For example, continuing with the aforementioned 18-story residential project, assuming the design team changed the floor height (the first sub-parameter), the first major model, by calling the correlation matrix, determines the second sub-parameter, which includes the structural beam height and the net height of the mechanical and electrical pipelines. Then, the change in the structural beam height ΔL = k1 × ΔH, where ΔH represents the change in floor height and k1 represents the influence coefficient of floor height on the structural beam height; the change in the net height of the mechanical and electrical pipelines ΔN = k2 × ΔH, where k2 represents the influence coefficient of floor height on the net height of the mechanical and electrical pipelines.

[0060] It is evident that by using the primary model for collaborative analysis and change information generation, the model's ability to understand and process information in the engineering design field can be fully utilized. This enables real-time responses to changes in primary design parameters and cross-disciplinary collaboration, effectively addressing the pain points of independent design and information fragmentation in the traditional model. Consequently, the design process no longer relies on manual judgment of the impact of changes but is automatically extrapolated based on historical data. This ensures full-disciplinary collaboration in design changes and avoids issues such as information asynchrony and subsequent production impacts caused by independent design of sub-parameters across different disciplines.

[0061] In another implementation, a prompt message is generated, which may include task description, first design parameters, first change information, etc. The prompt message is then input into the first main model, which performs a linkage analysis based on the content contained in the prompt message and outputs the second change information.

[0062] The foregoing illustrates a partial implementation of S202. It should be understood that S202 can also be implemented in other ways, and the embodiments in this specification do not limit this implementation.

[0063] S204, based on the second change information, update the first design parameters to obtain the second design parameters of the first project.

[0064] Specifically, the second change information can be sent to the design team, who will then decide whether to adopt it. If the design team adopts the second change information, the first design parameters are updated based on the first and second change information to obtain the second design parameters. If the design team does not adopt the second change information, the first design parameters are updated based on the first change information to obtain the second design parameters. Alternatively, the design team can also modify the second change information. In this case, the first design parameters are updated based on the first change information and the modified second change information to obtain the second design parameters.

[0065] For example, the design end may include multiple design systems. The first change information originates from the first design system and includes a first sub-parameter and its change. The second change information includes a second sub-parameter and its change. In response to the second sub-parameter originating from the second design system, the second change information is sent to the second design system, which is a different design system from the first. If the second design system decides to adopt the second change information, it updates both the first and second sub-parameters based on their changes, resulting in the second design parameter. If the second design system decides not to adopt the second change information, it updates only the first sub-parameter based on its change, resulting in the second design parameter.

[0066] The engineering data linkage method provided in the embodiments of this specification utilizes the semantic understanding and processing capabilities of a large model to calculate the chain reaction of changes to design parameters of an engineering project in real time at the design end, and determine other change information linked to the current change information; furthermore, the design parameters are updated based on other change information. This enables chain changes to design parameters, better meeting dynamic design needs, improving design efficiency, and is widely applicable to the digital collaborative implementation of complex engineering scenarios such as architecture, machinery, and municipal engineering.

[0067] In other embodiments, the above-described engineering data linkage method may further include: S206, through the first major model, converts the second design parameters into the production parameters of the first engineering project.

[0068] Production parameters refer to all the specific values ​​and process instructions required during the engineering construction process to translate design intentions into physical components, guiding the processing, fabrication, and installation. For example, production parameters may include, but are not limited to, at least one of the following: mold dimensions, blanking dimensions, positioning coordinates, reserved openings, casting process parameters, material and formula parameters, material and management parameters, etc.

[0069] The first major model, through studying the design and production parameters of a large number of engineering projects, has mastered the mapping relationship between design parameters and production parameters, and can convert the second design parameter into a production parameter that is compatible with it.

[0070] In one implementation, S206 may include the following steps: obtaining production equipment information and production material information from the production end; and, based on the production equipment information and production material information, instructing the first large model to convert the second design parameters into production parameters for the first engineering project.

[0071] Production equipment information may include various information reflecting the capacity limits of production equipment, such as, but not limited to, the maximum size of molds, the machining accuracy of machine tools, and the tonnage of lifting equipment. Production material information may include various information reflecting the characteristics of production materials, such as, but not limited to, the actual specifications of inventory materials (e.g., the standard length of steel bars, the width of sheet metal).

[0072] For example, continuing with the aforementioned 18-story residential project, its second design parameters include: precast wall panel dimensions of 3.6m (length) × 2.8m (width) × 0.2m (thickness), and concrete strength of C30. Production equipment information includes: maximum precast long mold dimensions of 3.8m × 3.0m, and production material information includes: C30 concrete pouring shrinkage rate of 0.1%. Inputting the information containing this data into the first main model will yield the following production parameters: Mold dimensions: Length 3.6036m (considering shrinkage) × Width 2.8028m × Thickness 0.2002m; Pouring process parameters: vibration frequency 50Hz, curing temperature 20℃.

[0073] Production equipment information reflects the capacity boundaries of the production equipment, while production material information reflects the characteristics of the production materials. Combining these two factors instructs the first major model to convert the second design parameters into production parameters. This allows the first major model to not only automatically match the capacity boundaries of the production equipment during parameter conversion but also optimize the conversion based on the actual specifications of the inventory materials. This improves the accuracy and automation level of the design-production conversion and reduces the risk of rework.

[0074] In another implementation, S206 above may include the following steps: instructing the first large model to convert the second design parameters into production parameters for the first engineering project.

[0075] The foregoing illustrates a partial implementation of S206. It should be understood that S206 can also be implemented in other ways, and the embodiments in this specification do not limit this implementation.

[0076] S208 sends production parameters to the production end.

[0077] You can call the production-side interface to send production parameters to the production system. Specifically, there can be multiple production parameters, and the production system can include various production systems, each handling different production parameters. Therefore, these production parameters can be sent to the corresponding production system for processing.

[0078] For example, if the production parameters include the production parameters of prefabricated components, and the production end includes the Manufacturing Execution System (MES) system used by the prefabrication plant, then the production parameters of the prefabricated components can be sent to the MES system.

[0079] The engineering data linkage method provided in the embodiments of this specification utilizes the semantic understanding and processing capabilities of a large model to calculate the cascading effects of changes to design parameters in engineering projects in real time at the design end, identifying other change information linked to the current change information. Based on this, the large model converts the changed design parameters into production parameters and sends them to the production end, achieving automatic conversion and synchronization from design parameters to production parameters, thus streamlining the design-production chain. This better meets dynamic design needs, improves design and production efficiency, and is widely applicable to the digital collaboration and design-production integration of complex engineering scenarios such as architecture, machinery, and municipal engineering.

[0080] In other embodiments, the engineering data linkage method provided in this specification also introduces a design conflict early warning mechanism. Specifically, the first design parameter includes multiple sub-parameters. Before obtaining the second design parameter of the first engineering project, the engineering data linkage method provided in this specification may further include: determining, through a first large model, whether the second change information causes a conflict between multiple sub-parameters; and in response to determining that the second change information causes a conflict between multiple sub-parameters, sending a first early warning message to the design end.

[0081] For example, the first design parameter includes several sub-parameters such as floor height and clear height of mechanical and electrical pipelines. The current floor height is 0.60m. The first change information indicates an increase of 0.06m in the floor height. The current clear height of mechanical and electrical pipelines is 2.40m. The second change information indicates an increase of 0.16m in the clear height of mechanical and electrical pipelines. After updating the clear height of mechanical and electrical pipelines based on the second change information, the clear height becomes 2.56m, which does not meet the code requirement (structural beam height not less than 2.6m). Therefore, it is determined that the second change information causes a conflict between multiple sub-parameters, and a first warning message is sent to the design department, such as "It is recommended that the floor height be adjusted to 3.3m." After the design department confirms the adjustment, the linkage calculation between each sub-parameter is re-performed through the first large model until there are no conflicts.

[0082] For example, if the current floor height is 0.60m, and the first change information indicates an increase of 0.06m, and the current net height of the mechanical and electrical pipelines is 2.40m, and the second change information indicates an increase of 0.20m, then after updating the net height of the mechanical and electrical pipelines based on the second change information, the net height becomes 2.60m. Although this meets the code requirement (structural beam height not less than 2.6m), an overlap between the mechanical and electrical pipelines and the structural beams is identified. Therefore, it is determined that the second change information causes a conflict between multiple sub-parameters, and a first warning message is sent to the design team, such as "The current adjustment of the net height of the mechanical and electrical pipelines will cause an overlap between the mechanical and electrical pipelines and the structural beams; a redesign is recommended." After the design team confirms the adjustment, the linkage calculation between each sub-parameter is re-performed through the first large model until there are no conflicts.

[0083] Determining whether the second change information causes a conflict among multiple sub-parameters using the first main model can be achieved in various ways. In one implementation, a corresponding prompt message can be sent to the first main model. This prompt message may include a task description, first design parameters, first change information, and second change information, to instruct the first main model to identify whether the second change information causes a conflict among multiple sub-parameters.

[0084] In another implementation, a first main model is used to update multiple sub-parameters based on first and second change information, and a first design drawing is generated based on the updated multiple sub-parameters; a graph neural network is used to identify the first design drawing to determine whether the second change information causes a conflict between multiple sub-parameters.

[0085] Specifically, the first major model can use graph generation algorithms (such as rule-based layout) to automatically draw two-dimensional engineering drawings, three-dimensional models, or interactive visualization charts, making it easier to intuitively understand parameter relationships. Graph Neural Network (GNN) extracts features from the first design diagram and performs conflict judgment and localization based on the extracted features, thereby determining whether the second change information causes conflicts between multiple sub-parameters.

[0086] By converting the updated sub-parameters into a first design graph using the first major model, the parameter relationships can be intuitively reflected; then, by utilizing the powerful graph recognition capabilities of graph neural networks for conflict identification, the accuracy of conflict identification can be improved.

[0087] In the above embodiments, the first large model, based on its powerful data processing and analysis capabilities, can quickly process a large number of complex design parameters and change information, comprehensively and deeply analyze the complex relationship between change information and design parameters, and accurately identify potential conflicts. This high-precision detection helps ensure the accuracy and rationality of the design scheme, avoiding design defects and errors caused by parameter conflicts; by providing timely warnings of design parameter conflicts, the design team can discover problems and make adjustments before production, improving design quality. Furthermore, compared to traditional manual inspection methods, it can determine whether change information has caused design parameter conflicts within a very short time. This significantly shortens the inspection time in the design process, ensuring rapid recommendation of the first engineering project and improving overall design efficiency.

[0088] In other embodiments, the engineering data linkage method provided in this specification also introduces a production conflict early warning mechanism. Specifically, before S208 above, the engineering data linkage method provided in this specification may further include the following steps: obtaining production capacity information from the production end; comparing production parameters and production capacity information through a first large model; and in response to a mismatch between production parameters and production capacity information, sending a second early warning message to the design end.

[0089] Production capacity information can include various information reflecting the production capacity of the production end, such as, but not limited to, at least one of the following: equipment processing range, material inventory, etc.

[0090] For example, continuing with the aforementioned 18-story residential project, the wall panel length in the second design parameter is 3.6m. The production capacity information is as follows: the maximum processing length of the existing cutting machine is 3.5m.

[0091] The first model reads the aforementioned second design parameters and production capacity information. Through comparison, it finds that the component size exceeds the equipment's processing capacity, and then sends the following second warning message to the design end: "Warning: The wall panel is 3.6m long, which exceeds the maximum processing length of the cutting machine (3.5m). It is recommended to adjust it to 3.4m." It is evident that the production conflict early warning mechanism forms a closed loop of "design change - linkage analysis - conflict early warning - production synchronization". By sensing production constraints in real time and driving design optimization in reverse, the adaptive flow of engineering data is achieved.

[0092] In some embodiments, the first major model can be obtained by training (e.g., pre-training, fine-tuning) a general major model based on engineering domain data. This engineering domain data may include design change records of the second engineering project, corresponding impact analysis reports of the design change records, and design and production adaptation cases of the second engineering project.

[0093] The design change log and its associated impact analysis report have been introduced above and will not be repeated here. Design and production adaptation cases can include various design parameters and their corresponding production parameters. Design change logs can originate from multiple design systems, and design and production adaptation cases can originate from multiple production systems. This allows the primary model to better support unified data access from multiple design systems and multiple production systems, automatically completing format standardization and semantic alignment.

[0094] Optionally, engineering data may also include engineering specification corpora, etc. This helps improve the accuracy of the first major model in cross-disciplinary semantic understanding and collaborative calculation. The engineering specification corpus may include, but is not limited to, at least one of the following: specifications, design manuals, project drawings, etc., from multiple disciplines such as architecture, structure, and mechanical and electrical engineering.

[0095] Specifically, a general-purpose model (such as the GPT series) can be used as a foundation. This general-purpose model can then be pre-trained using an engineering specification corpus to enhance its engineering semantic understanding capabilities. This pre-trained model will be able to deeply understand various professional terms and specifications, avoiding cross-disciplinary ambiguity. Then, using design change records from a second engineering project, corresponding impact analysis reports, and design and production adaptation cases from the second project, the pre-trained general-purpose model can be fine-tuned. This will enable the model to master linkage analysis and design-production parameter conversion capabilities, resulting in the first major model.

[0096] More specifically, the first step is to clean and structure the engineering data. This involves converting non-text data into editable text, using tools (such as CAD plugins) to extract tables and annotations from drawings, removing irrelevant data, and then converting the remaining data into structured data such as JSON or Markdown. For example, a specification could be transformed into {"condition": "Building height > 50m", "requirement": "Positive pressure ventilation is required in smoke-proof stairwells"}.

[0097] Next, based on the general-purpose model, pre-training is performed using a cleaned and structured corpus of engineering specifications. For example, technical terms can be masked to allow the general-purpose model to make predictions, and the parameters of the general-purpose model can be adjusted based on the prediction results to obtain a pre-trained model.

[0098] Furthermore, based on the pre-trained model, fine-tuning is performed using cleaned and structured design change records, impact analysis reports, and design and production adaptation cases. For example, part of the design change record is as follows: Input="Architecture will move the exterior wall outward by 200mm", Output="Structural engineers need to adjust the cantilever beam dimensions, and MEP engineers need to verify the length of exterior facade pipelines". Part of the impact analysis report is as follows: Input="Structural beam height increased by 300mm", Output="HVAC ducts need to pass through beams to avoid insufficient clearance; it is recommended to change to flat ducts or adjust the route". Part of the design and production adaptation case is as follows: Input="Rebar diameter in the BIM model", Output="Rebar cutting list for factory processing (including hook length and standard length)".

[0099] Specifically, instruction-response pairs are constructed based on cleaned and structured design change records, linkage impact analysis reports, and design and production adaptation cases. For example, an instruction-response pair for linkage analysis is as follows: { "instruction": "The architecture team plans to move the exterior wall outward by 200mm. Please analyze the impact on the structure and mechanical and electrical systems." "input": "", Output: 1. [Structure] The cross-section of the exterior wall beams needs to be increased, and the cantilever length needs to be increased by 200mm. Overturning resistance needs to be verified. 2. [Mechanical & Electrical] The HVAC risers need to be moved outwards accordingly. Sufficient space in the pipe shafts needs to be checked. 3. [Conclusion] The structural beam height needs to be adjusted, and the mechanical & electrical piping routes need to be rearranged. } An instruction-response pair for design-production parameter mapping is as follows: { "instruction": "Convert the 20mm diameter HRB400 steel bars in the BIM model into a processing and cutting list, with a protective layer thickness of 25mm and a hook angle of 135 degrees." "input": "Design length: 8000mm", Output: "Thinking process: Cutting length = Design length + Hook increase length - Bending adjustment value. HRB400 diameter 20mm, 135-degree hook increase length is 4.9d. The protective layer does not affect the cutting length calculation. Calculation: 8000 + (4.9)" 20) = 8098mm. \nFinal JSON: {\"rebar_id\": \"HRB400-20\", \"cutting_length\": 8098, \"bend_details\": \"135-deg\"}" } The constructed instruction-response pair is input into the pre-trained model. A reinforcement learning and precision alignment strategy is employed, and the output of the pre-trained model is scored based on a pre-defined reward model to obtain a reward score. For example, if the output of the pre-trained model contains a logical omission, the score is 10 points; if the output of the pre-trained model conforms to the specifications, the score is +5 points.

[0100] Finally, adjust the model parameters based on the reward score. Repeat the above process multiple times until the training stopping condition is met.

[0101] It is worth noting that the fine-tuning process can be performed according to pre-configured hyperparameters (such as learning rate, epochs, batch size, etc.). For example, the learning rate can be a value between 2e-4 and 5e-5, the epochs can be 3 to 10 epochs, and the batch size can be 4 to 8, etc. These parameters can be set according to actual needs, and this application embodiment does not limit them.

[0102] The foregoing has described specific embodiments of this specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims may be performed in a different order than that shown in the embodiments and may still achieve the desired result. Furthermore, the processes depicted in the drawings do not necessarily require the specific or sequential order shown to achieve the desired result. In some embodiments, multitasking and parallel processing are possible or may be advantageous.

[0103] Based on the same inventive concept, embodiments of this specification also provide an engineering data linkage device. Please refer to... Figure 3 This is a schematic diagram of the structure of an engineering data linkage device 300 provided in the embodiments of this specification. The device 300 includes a linkage analysis module 310 and an update module 320.

[0104] The linkage analysis module 310 is used to respond to the first change information generated by the design end for the first design parameters of the first engineering project, and to generate second change information linked to the first change information through a first large model. The first large model is built based on engineering domain data, which includes: design change records of the second engineering project, and linkage impact analysis reports corresponding to the design change records.

[0105] The update module 320 is used to update the first design parameters based on the second change information to obtain the second design parameters of the first project.

[0106] In other embodiments, the first design parameter includes multiple sub-parameters, and the first change information includes the first sub-parameter and the amount of change of the first sub-parameter. The linkage analysis module is used for: The first large model is used to perform a linkage analysis on the multiple sub-parameters to obtain the second sub-parameter and the influence coefficient of the first sub-parameter on the second sub-parameter; the second sub-parameter includes the sub-parameters that are linked to the first sub-parameter among the multiple sub-parameters; Based on the influence coefficient and the change in the first sub-parameter, determine the change in the second sub-parameter; The second change information is generated based on the second sub-parameter and the amount of change of the second sub-parameter.

[0107] In other embodiments, the linkage analysis module obtains the second sub-parameter and the influence coefficient of the first sub-parameter on the second sub-parameter in the following manner: The first large model is used to call the correlation matrix, and the second sub-parameter and the influence coefficient of the first sub-parameter on the second sub-parameter are queried in the correlation matrix. The correlation matrix includes the linkage relationship and influence coefficients among the multiple sub-parameters, and the correlation matrix is ​​established by the first major model based on the engineering domain data.

[0108] In other embodiments, the design end includes multiple design systems, and the first change information originates from a first design system; The sending module is also used to send the second change information to the second design system in response to the second sub-parameter originating from the second design system; the second design system and the first design system are different design systems among the multiple design systems.

[0109] In other embodiments, the first design parameter includes multiple sub-parameters; The engineering data linkage device also includes: The conflict analysis module is used to determine, through the first large model, whether the second change information causes a conflict between the multiple sub-parameters; The sending module is further configured to send a first warning message to the design end in response to determining that the second change information causes a conflict among the plurality of sub-parameters.

[0110] In other embodiments, the conflict analysis module is used for: Using the first large model, the plurality of sub-parameters are updated based on the first change information and the second change information, and a first design drawing is generated based on the updated plurality of sub-parameters; The first design diagram is identified using a graph neural network to determine whether the second change information causes a conflict between the multiple sub-parameters.

[0111] In another embodiment, the engineering data linkage device may further include: a conversion module and a sending module; The conversion module is used to convert the second design parameters into production parameters for the first engineering project using the first large model; The sending module is used to send the production parameters to the production end.

[0112] In other embodiments, the conversion module is used for: Obtain the production equipment information and production material information of the production end; Based on the production equipment information and the production material information, the first large model is instructed to convert the second design parameters into production parameters for the first engineering project.

[0113] In other embodiments, the engineering data linkage device further includes: The acquisition module is used to acquire the production capacity information of the production end; The comparison module is used to compare the production parameters and the production capacity information using the first large model; The sending module is also used to send a second warning message to the design end in response to a mismatch between the production parameters and the production capacity information.

[0114] Obviously, the engineering data linkage device 300 provided in the embodiments of this specification can be used as the above-mentioned... Figure 2 The execution entity of the engineering data linkage method shown above is therefore able to realize the above engineering data linkage method in Figure 2 The functions implemented are the same, so they will not be explained again here.

[0115] Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this specification. Please refer to it. Figure 4 At the hardware level, the electronic device includes a processor, and optionally also includes an internal bus, a network interface, and memory. The memory may include main memory, such as high-speed random-access memory (RAM), or non-volatile memory, such as at least one disk drive. Of course, the electronic device may also include other hardware required for other business operations.

[0116] The processor, network interface, and memory can be interconnected via an internal bus, which can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus, or an EISA (Extended Industry Standard Architecture) bus, etc. This bus can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 4 The symbol is represented by a single double-headed arrow, but this does not mean that there is only one bus or one type of bus.

[0117] Memory is used to store programs. Specifically, programs may include program code, which includes computer operation instructions. Memory may include main memory and non-volatile memory, and provides instructions and data to the processor.

[0118] The processor reads the corresponding computer program from non-volatile memory into main memory and then runs it, forming a logical data linkage mechanism. The processor executes the program stored in memory and specifically performs the following operations: In response to the first change information generated by the design end for the first design parameter of the first engineering project, a second change information linked to the first change information is generated through the first large model; the first large model is established based on engineering domain data, which includes: design change records of the second engineering project, and a linkage impact analysis report corresponding to the design change records; Based on the second change information, the first design parameters are updated to obtain the second design parameters for the first project.

[0119] The above is as described in this specification. Figure 2 The method executed by the engineering data linkage device disclosed in the illustrated embodiments can be applied to a processor or implemented by a processor. The processor may be an integrated circuit chip with signal processing capabilities. During implementation, each step of the above method can be completed by integrated logic circuits in the processor's hardware or by instructions in software form. The processor can be a general-purpose processor, including a Central Processing Unit (CPU), a Network Processor (NP), etc.; it can also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field-Programmable Gate Array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this specification. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in the embodiments of this specification can be directly embodied in the execution of a hardware decoding processor, or executed by a combination of hardware and software modules in the decoding processor. The software module can reside in a mature storage medium in the field, such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, or registers. This storage medium is located in memory, and the processor reads information from the memory and, in conjunction with its hardware, completes the steps of the above method.

[0120] The electronic device can also perform Figure 2 The method, and realize the engineering data linkage device in Figure 2 The functions of the embodiments shown are not described in detail here.

[0121] Of course, in addition to software implementation, the electronic device described in this specification does not exclude other implementation methods, such as logic devices or a combination of hardware and software. In other words, the execution subject of the following processing flow is not limited to each logic unit, but can also be hardware or logic devices.

[0122] This specification also provides an embodiment of a computer-readable storage medium that stores one or more programs, the programs including instructions that, when executed by an electronic device including multiple applications, enable the electronic device to perform... Figure 2 The method of the illustrated embodiment is specifically used to perform the following operations: In response to the first change information generated by the design end for the first design parameter of the first engineering project, a second change information linked to the first change information is generated through the first large model; the first large model is established based on engineering domain data, which includes: design change records of the second engineering project, and a linkage impact analysis report corresponding to the design change records; Based on the second change information, the first design parameters are updated to obtain the second design parameters for the first project.

[0123] This specification also provides a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program operable to cause a computer to perform the steps of the engineering data linkage method provided in this specification.

[0124] In summary, the above description is merely a preferred embodiment of this specification and is not intended to limit the scope of protection of this document. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this document should be included within the scope of protection of this document.

[0125] The systems, devices, modules, or units described in the above embodiments can be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, a computer can be, for example, a personal computer, laptop computer, cellular phone, camera phone, smartphone, personal digital assistant, media player, navigation device, email device, game console, tablet computer, wearable device, or any combination of these devices.

[0126] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0127] It should also be noted that 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 limitation, 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.

[0128] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to interchangeably. 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 in the method embodiments.

Claims

1. A method for linking engineering data, characterized in that, include: In response to the first change information generated by the design end for the first design parameter of the first engineering project, a second change information linked with the first change information is generated through the first large model; The first major model is built based on engineering domain data, which includes: design change records of the second engineering project and the linkage impact analysis report corresponding to the design change records; Based on the second change information, the first design parameters are updated to obtain the second design parameters for the first project.

2. The method according to claim 1, characterized in that, The first design parameter includes multiple sub-parameters, and the first change information includes the first sub-parameter and the amount of change of the first sub-parameter; The generation of second change information linked to the first change information through the first large model includes: The first large model is used to perform a linkage analysis on the multiple sub-parameters to obtain the second sub-parameter and the influence coefficient of the first sub-parameter on the second sub-parameter; the second sub-parameter includes the sub-parameters that are linked to the first sub-parameter among the multiple sub-parameters; Based on the influence coefficient and the change in the first sub-parameter, determine the change in the second sub-parameter; The second change information is generated based on the second sub-parameter and the amount of change of the second sub-parameter.

3. The method according to claim 2, characterized in that, The step of performing a linkage analysis on the multiple sub-parameters through the first large model to obtain the second sub-parameter and the influence coefficient of the first sub-parameter on the second sub-parameter includes: The first large model is used to call the correlation matrix, and the second sub-parameter and the influence coefficient of the first sub-parameter on the second sub-parameter are queried in the correlation matrix. The correlation matrix includes the linkage relationship and influence coefficients among the multiple sub-parameters, and the correlation matrix is ​​established by the first major model based on the engineering domain data.

4. The method according to claim 2, characterized in that, The design terminal includes multiple design systems, and the first change information originates from a first design system; the method further includes: In response to the fact that the second sub-parameter originates from the second design system, the second change information is sent to the second design system; the second design system and the first design system are different design systems among the multiple design systems.

5. The method according to claim 1, characterized in that, The first design parameter includes multiple sub-parameters; Before updating the first design parameters based on the second change information to obtain the second design parameters of the first project, the method further includes: Using the first large model, determine whether the second change information causes a conflict between the multiple sub-parameters; In response to determining that the second change information causes a conflict among the multiple sub-parameters, a first warning message is sent to the design end.

6. The method according to claim 5, characterized in that, The step of determining whether the second change information causes a conflict among the multiple sub-parameters through the first large model includes: Using the first large model, the plurality of sub-parameters are updated based on the first change information and the second change information, and a first design drawing is generated based on the updated plurality of sub-parameters; The first design diagram is identified using a graph neural network to determine whether the second change information causes a conflict between the multiple sub-parameters.

7. The method according to claim 1, characterized in that, The method further includes: The second design parameters are converted into production parameters for the first engineering project using the first large model; The production parameters are sent to the production end.

8. The method according to claim 7, characterized in that, The process of converting the second design parameters into production parameters for the first engineering project using the first large model includes: Obtain the production equipment information and production material information of the production end; Based on the production equipment information and the production material information, the first large model is instructed to convert the second design parameters into production parameters for the first engineering project.

9. The method according to claim 7, characterized in that, Before sending the production parameters to the production end, the method further includes: Obtain the production capacity information of the production end; The first large model compares the production parameters and the production capacity information, and in response to a mismatch between the production parameters and the production capacity information, sends a second warning message to the design end.

10. An engineering data linkage device, characterized in that, include: The linkage analysis module is used to respond to the first change information generated by the design end for the first design parameter of the first engineering project, and generate second change information that is linked with the first change information through the first large model. The first major model is built based on engineering domain data, which includes: design change records of the second engineering project and the linkage impact analysis report corresponding to the design change records; The update module is used to update the first design parameters based on the second change information to obtain the second design parameters of the first project.

11. An electronic device, characterized in that, It includes a processor, a memory, and a computer program stored in the memory and executable on the processor, wherein the computer program, when executed by the processor, implements the steps of the engineering data linkage method as described in any one of claims 1 to 9.

12. A computer-readable storage medium, characterized in that, When the instructions in the storage medium are executed by the processor of the electronic device, the electronic device is able to perform the steps of the engineering data linkage method as described in any one of claims 1 to 9.

13. A computer program product, characterized in that, The computer program product includes a non-transitory computer-readable storage medium storing a computer program operable to cause a computer to perform the steps of the engineering data linkage method as described in any one of claims 1 to 9.

Images