An intelligent risk assessment method and system based on engineering drawing changes
By identifying differences in engineering drawings and mapping them to downstream data objects, a dependency graph and risk assessment model are constructed, solving the problem of difficulty in identifying and quantifying key changes in existing technologies. This enables intelligent and proactive early risk assessment, reducing rework and cost risks.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- 广州锦成信息技术有限公司
- Filing Date
- 2025-10-31
- Publication Date
- 2026-07-07
AI Technical Summary
Existing engineering drawing change management and risk assessment systems struggle to identify critical changes in complex, multi-source data environments and rapid iteration scenarios. This results in potential risks not being exposed in the early stages of design changes, and the systems are unable to achieve automatic propagation and quantitative assessment across systems, making it difficult to fully capture the scope of impact.
By acquiring the revised engineering drawings, identifying the differences and generating a structured change content vector, mapping it to downstream federated data objects, constructing a dependency graph and setting up a risk assessment model, calculating the risk index, and generating a risk report.
It enables early, multi-dimensional, and quantitative risk distribution assessment, helping managers quickly determine the potential impact of changes on production, supply chain, maintenance, and other aspects, thereby reducing the risk of rework and cost losses.
Smart Images
Figure CN121660427B_ABST
Abstract
Description
Technical Field
[0001] This invention belongs to the field of engineering drawing risk assessment technology, and more specifically, relates to an intelligent risk assessment method and system based on engineering drawing changes. Background Technology
[0002] In existing technologies, change management and risk assessment of engineering drawings largely rely on traditional PDM / PLM systems. The core methods involve comparing design versions, reviewing documents, and manual judgment by engineers. While this approach improved traceability to some extent in the early stages of information technology development, it has significant shortcomings when dealing with complex multi-source data environments and rapidly iterating engineering scenarios. First, most existing systems only support change comparison at the document level, i.e., comparing geometric differences in CAD drawings or textual annotation differences. Therefore, it is difficult to identify critical changes that truly impact downstream manufacturing, supply chains, and maintenance, such as "changing materials from A to B" or "adjusting assembly relationships." As a result, many potential risks are not exposed in the early stages of design changes, often only becoming apparent in the production or application phase, leading to rework or quality incidents. Second, existing methods have very limited consideration for downstream federated data objects. Although ERP, MES, and procurement systems have a natural connection to design drawings, mainstream PDM / PLM systems only provide shallow connections at the BOM level, failing to achieve automatic cross-system propagation and quantitative assessment, making it difficult to fully capture the scope of change impact.
[0003] Therefore, a technical solution is urgently needed to solve the above technical problems. Summary of the Invention
[0004] To address the above technical problems, this invention proposes an intelligent risk assessment method based on engineering drawing changes, comprising:
[0005] When engineering drawings are changed, the new engineering drawings are obtained and the differences in the changes are identified based on the old engineering drawings, generating a structured vector of change content.
[0006] Based on the dependency relationship between the engineering drawings and downstream federated data objects, the change content vector is mapped to the downstream federated data objects, and the attribute offset vector of each downstream federated data object caused by the change content vector is obtained level by level.
[0007] Set up a risk assessment model, calculate a risk index based on the attribute offset vector, and generate a risk report. The risk report includes: risk index, change content vector, and attribute offset vector.
[0008] Furthermore, based on the old engineering drawings, the identification of change differences and the generation of structured change content vectors include: loading the new and old engineering drawings into a structured model, calculating the change content vector of each geometric element in the structured model, and comparing it with the deviation threshold. If the deviation threshold is exceeded, the corresponding geometric element is marked as a geometric change.
[0009] Furthermore, mapping the change content vector to the downstream federated data object includes: dividing the new engineering drawing into multiple drawing elements, each drawing element corresponding to the corresponding change content vector and downstream federated data object;
[0010] Construct a dependency graph between drawing elements and downstream federated data objects, where drawing elements and downstream federated data objects are nodes in the dependency graph, and references or derivations are edges.
[0011] For each drawing element, trace down the dependency graph to all direct / indirect downstream federated data objects and set a maximum tracing depth to prevent overexpansion.
[0012] Furthermore, the risk assessment model includes:
[0013] ,
[0014] in, For the first The normalized final risk index corresponding to each attribute offset vector For the first The risk index corresponding to each attribute offset vector. For the first The risk index benchmark value corresponding to each attribute offset vector. This is an adjustment factor for the risk assessment model.
[0015] Furthermore, the first Risk index corresponding to each attribute offset vector include:
[0016] ,
[0017] in, For the first The first weight of the attribute offset vector For the first The corrected risk index corresponding to each attribute offset vector.
[0018] Furthermore, the first The corrected risk index corresponding to each attribute offset vector include:
[0019] ,
[0020] in, For the first The preliminary risk index corresponding to each attribute offset vector. For the first Attribute offset vector With the Attribute offset vector The interaction influence weight.
[0021] Furthermore, the first Preliminary risk index corresponding to each attribute offset vector include:
[0022] ,
[0023] in, For the first The second weight of the attribute offset vector For the first Each attribute offset vector For the first The baseline value corresponding to each attribute offset vector. For the first The first adjustment factor for the preliminary risk index corresponding to each attribute offset vector. For the first The tolerance threshold for each attribute offset vector. For the first The second adjustment factor for the preliminary risk index corresponding to each attribute offset vector.
[0024] This invention also proposes an intelligent risk assessment system based on engineering drawing changes, comprising:
[0025] The data processing module is used to obtain the new engineering drawings after the changes are made, and to identify the differences in the changes based on the old engineering drawings, and generate a structured change content vector.
[0026] The mapping module is used to map the change content vector to the downstream federated data object according to the dependency relationship between the engineering drawing and the downstream federated data object, and to obtain the attribute offset vector of each downstream federated data object caused by the change content vector.
[0027] The risk assessment module is used to set up a risk assessment model, calculate a risk index based on the attribute offset vector, and generate a risk report. The risk report includes: risk index, change content vector, and attribute offset vector.
[0028] Furthermore, based on the old engineering drawings, the identification of change differences and the generation of structured change content vectors include: loading the new and old engineering drawings into a structured model, calculating the change content vector of each geometric element in the structured model, and comparing it with the deviation threshold. If the deviation threshold is exceeded, the corresponding geometric element is marked as a geometric change.
[0029] Furthermore, mapping the change content vector to the downstream federated data object includes: dividing the new engineering drawing into multiple drawing elements, each drawing element corresponding to the corresponding change content vector and downstream federated data object;
[0030] Construct a dependency graph between drawing elements and downstream federated data objects, where drawing elements and downstream federated data objects are nodes in the dependency graph, and references or derivations are edges.
[0031] For each drawing element, trace down the dependency graph to all direct / indirect downstream federated data objects and set a maximum tracing depth to prevent overexpansion.
[0032] In summary, the technical solutions conceived by this invention have the following beneficial effects compared with the prior art:
[0033] The technical solution of this invention can provide a multi-dimensional and quantitative risk distribution in the early stage, which makes it easier for managers to quickly judge the potential impact of changes on production, supply chain, maintenance and safety, thereby realizing the pre-emptive and intelligent engineering decision-making and significantly reducing the risk of rework, delays and cost losses. Attached Figure Description
[0034] Figure 1 This is a flowchart of the method in Embodiment 1 of the present invention;
[0035] Figure 2 This is a system structure diagram of Embodiment 2 of the present invention. Detailed Implementation
[0036] To better understand the above technical solutions, the following will provide a detailed explanation of the technical solutions in conjunction with the accompanying drawings and specific implementation methods.
[0037] The method provided by this invention can be implemented in a terminal environment that may include one or more of the following components: a processor, a storage medium, and a display screen. The storage medium stores at least one instruction, which is loaded and executed by the processor to implement the method described in the following embodiments.
[0038] A processor may include one or more processing cores. The processor uses various interfaces and lines to connect various parts of the terminal, and performs various functions and processes data by running or executing instructions, programs, code sets or instruction sets stored in the storage medium, and by calling data stored in the storage medium.
[0039] Storage media can include random access memory (RAM) or read-only memory (ROM). Storage media can be used to store instructions, programs, code, code sets, or instructions.
[0040] The display screen is used to show the user interface of each application.
[0041] In addition, those skilled in the art will understand that the structure of the terminal described above does not constitute a limitation on the terminal. The terminal may include more or fewer components, or combine certain components, or have different component arrangements. For example, the terminal may also include radio frequency circuits, input units, sensors, audio circuits, power supplies, and other components, which will not be described in detail here.
[0042] Example 1
[0043] like Figure 1 As shown, this embodiment proposes an intelligent risk assessment method based on engineering drawing changes, including:
[0044] Step 101: When the engineering drawings are changed, obtain the new engineering drawings after the changes, identify the differences in the changes based on the old engineering drawings, and generate a structured change content vector.
[0045] Specifically, the process of identifying changes based on old engineering drawings and generating structured change content vectors includes: loading the new and old engineering drawings into a structured model (such as a CAD topology tree or B-Rep data), calculating the change content vector of each geometric element in the structured model, and comparing it with a deviation threshold. If the deviation threshold is exceeded, the corresponding geometric element is marked as a geometric change.
[0046] Preferably, the change content vector can be the amount of change in the typical size of the feature, such as the amount of change in the aperture or fillet diameter; the amount of change in the depth or elongation, such as the amount of change in the depth of a blind hole; the amount of change in the local curvature or fillet radius, reflecting the minimum machinable size; or the amount of change in the height or thickness.
[0047] Step 102: Based on the dependency relationship between the engineering drawings and the downstream federated data objects, map the change content vector to the downstream federated data objects, and obtain the attribute offset vector of each downstream federated data object caused by the change content vector.
[0048] Preferably, for example, the federated data object can be an ERP purchase order, MES work order, etc. If the engineering drawings are changed, the ERP purchase order, MES work order, etc. may also need to be changed.
[0049] Preferably, when engineering drawings are changed, the corresponding attributes of downstream federated data objects also need to change with the changed content vector. For example, if an ERP purchase order needs to be re-formulated, the purchase price will change accordingly, which will generate an attribute offset vector for the ERP purchase order. For example, if the size of a part changes, the corresponding part needs to be re-purchased, and the purchase price will change accordingly.
[0050] Specifically, mapping the change content vector to the downstream federated data object includes: dividing the new engineering drawing into multiple drawing elements, each drawing element corresponding to the corresponding change content vector and downstream federated data object;
[0051] Construct a dependency graph between drawing elements and downstream federated data objects, where drawing elements and downstream federated data objects are nodes in the dependency graph, and references or derivations are edges (e.g., “Part A → Assembly B → Purchase Order P”).
[0052] For each drawing element, trace down the dependency graph to all direct / indirect downstream federated data objects and set a maximum tracing depth to prevent overexpansion.
[0053] Step 103: Set up a risk assessment model, calculate the risk index based on the attribute offset vector, and generate a risk report, wherein the risk report includes: risk index, change content vector, and attribute offset vector.
[0054] Specifically, the risk assessment model includes:
[0055] ,
[0056] in, For the first The normalized final risk index corresponding to each attribute offset vector For the first The risk index corresponding to each attribute offset vector. For the first The risk index benchmark value corresponding to each attribute offset vector. Adjustment factors for risk assessment models (for example, It can belong to [1.0, 2.5]).
[0057] Specifically, the first Risk index corresponding to each attribute offset vector include:
[0058] ,
[0059] in, For the first The first weight of the attribute offset vector For the first The corrected risk index corresponding to each attribute offset vector.
[0060] Specifically, the first The corrected risk index corresponding to each attribute offset vector include:
[0061] ,
[0062] in, For the first The preliminary risk index corresponding to each attribute offset vector. For the first Attribute offset vector With the Attribute offset vector Interaction influence weights (e.g.) ∈[−1,1], the larger the value, the stronger the interaction effect).
[0063] Specifically, the first Preliminary risk index corresponding to each attribute offset vector include:
[0064] ,
[0065] in, For the first The second weight of the attribute offset vector For the first Each attribute offset vector For the first The baseline value corresponding to each attribute offset vector. For the first The first adjustment factor of the preliminary risk index corresponding to each attribute offset vector (for example) It can belong to [0.1, 3.0]). For the first The tolerance threshold for each attribute offset vector. For the first The second adjustment factor of the preliminary risk index corresponding to each attribute offset vector (for example) It can belong to [0.5, 3]).
[0066] Example 2
[0067] like Figure 2 As shown, this embodiment proposes an intelligent risk assessment system based on engineering drawing changes, including:
[0068] The data extraction module is used to obtain the new engineering drawings after the changes are made, and to identify the differences in the changes based on the old engineering drawings, and generate a structured vector of the changes.
[0069] Specifically, the process of identifying changes based on old engineering drawings and generating structured change content vectors includes: loading the new and old engineering drawings into a structured model (such as a CAD topology tree or B-Rep data), calculating the change content vector of each geometric element in the structured model, and comparing it with a deviation threshold. If the deviation threshold is exceeded, the corresponding geometric element is marked as a geometric change.
[0070] Preferably, the change content vector can be the amount of change in the typical size of the feature, such as the amount of change in the aperture or fillet diameter; the amount of change in the depth or elongation, such as the amount of change in the depth of a blind hole; the amount of change in the local curvature or fillet radius, reflecting the minimum machinable size; or the amount of change in the height or thickness.
[0071] The index calculation module is used to map the change content vector to the downstream federated data object according to the dependency relationship between the engineering drawing and the downstream federated data object, and obtain the attribute offset vector of the downstream federated data object caused by the change content vector for each downstream federated data object step by step.
[0072] Preferably, for example, the federated data object can be an ERP purchase order, MES work order, etc. If the engineering drawings are changed, the ERP purchase order, MES work order, etc. may also need to be changed.
[0073] Preferably, when engineering drawings are changed, the corresponding attributes of downstream federated data objects also need to change with the changed content vector. For example, if an ERP purchase order needs to be re-formulated, the purchase price will change accordingly, which will generate an attribute offset vector for the ERP purchase order. For example, if the size of a part changes, the corresponding part needs to be re-purchased, and the purchase price will change accordingly.
[0074] Specifically, mapping the change content vector to the downstream federated data object includes: dividing the new engineering drawing into multiple drawing elements, each drawing element corresponding to the corresponding change content vector and downstream federated data object;
[0075] Construct a dependency graph between drawing elements and downstream federated data objects, where drawing elements and downstream federated data objects are nodes in the dependency graph, and references or derivations are edges (e.g., “Part A → Assembly B → Purchase Order P”).
[0076] For each drawing element, trace down the dependency graph to all direct / indirect downstream federated data objects and set a maximum tracing depth to prevent overexpansion.
[0077] The feasibility analysis module is used to set up a risk assessment model, calculate a risk index based on the attribute offset vector, and generate a risk report. The risk report includes: risk index, change content vector, and attribute offset vector.
[0078] Specifically, the risk assessment model includes:
[0079] ,
[0080] in, For the first The normalized final risk index corresponding to each attribute offset vector For the first The risk index corresponding to each attribute offset vector. For the first The risk index benchmark value corresponding to each attribute offset vector. Adjustment factors for risk assessment models (for example, It can belong to [1.0, 2.5]).
[0081] Specifically, the first Risk index corresponding to each attribute offset vector include:
[0082] ,
[0083] in, For the first The first weight of the attribute offset vector For the first The corrected risk index corresponding to each attribute offset vector.
[0084] Specifically, the first The corrected risk index corresponding to each attribute offset vector include:
[0085] ,
[0086] in, For the first The preliminary risk index corresponding to each attribute offset vector. For the first Attribute offset vector With the Attribute offset vector Interaction influence weights (e.g.) ∈[−1,1], the larger the value, the stronger the interaction effect).
[0087] Specifically, the first Preliminary risk index corresponding to each attribute offset vector include:
[0088] ,
[0089] in, For the first The second weight of the attribute offset vector For the first Each attribute offset vector For the first The baseline value corresponding to each attribute offset vector. For the first The first adjustment factor of the preliminary risk index corresponding to each attribute offset vector (for example) It can belong to [0.1, 3.0]). For the first The tolerance threshold for each attribute offset vector. For the first The second adjustment factor of the preliminary risk index corresponding to each attribute offset vector (for example) It can belong to [0.5, 3]).
[0090] Example 3
[0091] This invention also proposes a storage medium storing multiple instructions for implementing the intelligent risk assessment method based on engineering drawing changes.
[0092] Optionally, in this embodiment, the storage medium may be located in any computer terminal in a group of computer terminals in a computer network, or in any mobile terminal in a group of mobile terminals.
[0093] Optionally, in this embodiment, the storage medium is configured to store program code for performing the following method steps: Step 101, when the engineering drawings are changed, obtain the new engineering drawings after the changes, identify the changes based on the old engineering drawings, and generate a structured change content vector;
[0094] Specifically, the process of identifying changes based on old engineering drawings and generating structured change content vectors includes: loading the new and old engineering drawings into a structured model (such as a CAD topology tree or B-Rep data), calculating the change content vector of each geometric element in the structured model, and comparing it with a deviation threshold. If the deviation threshold is exceeded, the corresponding geometric element is marked as a geometric change.
[0095] Preferably, the change content vector can be the amount of change in the typical size of the feature, such as the amount of change in the aperture or fillet diameter; the amount of change in the depth or elongation, such as the amount of change in the depth of a blind hole; the amount of change in the local curvature or fillet radius, reflecting the minimum machinable size; or the amount of change in the height or thickness.
[0096] Step 102: Based on the dependency relationship between the engineering drawings and the downstream federated data objects, map the change content vector to the downstream federated data objects, and obtain the attribute offset vector of each downstream federated data object caused by the change content vector.
[0097] Preferably, for example, the federated data object can be an ERP purchase order, MES work order, etc. If the engineering drawings are changed, the ERP purchase order, MES work order, etc. may also need to be changed.
[0098] Preferably, when engineering drawings are changed, the corresponding attributes of downstream federated data objects also need to change with the changed content vector. For example, if an ERP purchase order needs to be re-formulated, the purchase price will change accordingly, which will generate an attribute offset vector for the ERP purchase order. For example, if the size of a part changes, the corresponding part needs to be re-purchased, and the purchase price will change accordingly.
[0099] Specifically, mapping the change content vector to the downstream federated data object includes: dividing the new engineering drawing into multiple drawing elements, each drawing element corresponding to the corresponding change content vector and downstream federated data object;
[0100] Construct a dependency graph between drawing elements and downstream federated data objects, where drawing elements and downstream federated data objects are nodes in the dependency graph, and references or derivations are edges (e.g., “Part A → Assembly B → Purchase Order P”).
[0101] For each drawing element, trace down the dependency graph to all direct / indirect downstream federated data objects and set a maximum tracing depth to prevent overexpansion.
[0102] Step 103: Set up a risk assessment model, calculate the risk index based on the attribute offset vector, and generate a risk report, wherein the risk report includes: risk index, change content vector, and attribute offset vector.
[0103] Specifically, the risk assessment model includes:
[0104] ,
[0105] in, For the first The normalized final risk index corresponding to each attribute offset vector For the first The risk index corresponding to each attribute offset vector. For the first The risk index benchmark value corresponding to each attribute offset vector. Adjustment factors for risk assessment models (for example, It can belong to [1.0, 2.5]).
[0106] Specifically, the first Risk index corresponding to each attribute offset vector include:
[0107] ,
[0108] in, For the first The first weight of the attribute offset vector For the first The corrected risk index corresponding to each attribute offset vector.
[0109] Specifically, the first The corrected risk index corresponding to each attribute offset vector include:
[0110] ,
[0111] in, For the first The preliminary risk index corresponding to each attribute offset vector. For the first Attribute offset vector With the Attribute offset vector Interaction influence weights (e.g.) ∈[−1,1], the larger the value, the stronger the interaction effect).
[0112] Specifically, the first Preliminary risk index corresponding to each attribute offset vector include:
[0113] ,
[0114] in, For the first The second weight of the attribute offset vector For the first Each attribute offset vector For the first The baseline value corresponding to each attribute offset vector. For the first The first adjustment factor of the preliminary risk index corresponding to each attribute offset vector (for example) It can belong to [0.1, 3.0]). For the first The tolerance threshold for each attribute offset vector. For the first The second adjustment factor of the preliminary risk index corresponding to each attribute offset vector (for example) It can belong to [0.5, 3]).
[0115] Example 4
[0116] This invention also proposes an electronic device, including a processor and a storage medium connected to the processor. The storage medium stores multiple instructions, which can be loaded and executed by the processor to enable the processor to execute the aforementioned intelligent risk assessment method based on engineering drawing changes.
[0117] Specifically, the electronic device in this embodiment can be a computer terminal, which may include one or more processors and a storage medium.
[0118] The storage medium can be used to store software programs and modules, such as the intelligent risk assessment method based on engineering drawing changes in this embodiment of the invention. The corresponding program instructions / modules allow the processor to execute various functional applications and data processing by running the software programs and modules stored in the storage medium, thus realizing the aforementioned intelligent risk assessment method based on engineering drawing changes. The storage medium may include high-speed random access storage media, and may also include non-volatile storage media, such as one or more magnetic storage systems, flash memory, or other non-volatile solid-state storage media. In some instances, the storage medium may further include storage media remotely configured relative to the processor, which can be connected to the terminal via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.
[0119] The processor can call the information and application stored in the storage medium through the transmission system to execute the following method steps: Step 101, when the engineering drawings are changed, obtain the new engineering drawings after the changes, identify the changes based on the old engineering drawings, and generate a structured change content vector.
[0120] Specifically, the process of identifying changes based on old engineering drawings and generating structured change content vectors includes: loading the new and old engineering drawings into a structured model (such as a CAD topology tree or B-Rep data), calculating the change content vector of each geometric element in the structured model, and comparing it with a deviation threshold. If the deviation threshold is exceeded, the corresponding geometric element is marked as a geometric change.
[0121] Preferably, the change content vector can be the amount of change in the typical size of the feature, such as the amount of change in the aperture or fillet diameter; the amount of change in the depth or elongation, such as the amount of change in the depth of a blind hole; the amount of change in the local curvature or fillet radius, reflecting the minimum machinable size; or the amount of change in the height or thickness.
[0122] Step 102: Based on the dependency relationship between the engineering drawings and the downstream federated data objects, map the change content vector to the downstream federated data objects, and obtain the attribute offset vector of each downstream federated data object caused by the change content vector.
[0123] Preferably, for example, the federated data object can be an ERP purchase order, MES work order, etc. If the engineering drawings are changed, the ERP purchase order, MES work order, etc. may also need to be changed.
[0124] Preferably, when engineering drawings are changed, the corresponding attributes of downstream federated data objects also need to change with the changed content vector. For example, if an ERP purchase order needs to be re-formulated, the purchase price will change accordingly, which will generate an attribute offset vector for the ERP purchase order. For example, if the size of a part changes, the corresponding part needs to be re-purchased, and the purchase price will change accordingly.
[0125] Specifically, mapping the change content vector to the downstream federated data object includes: dividing the new engineering drawing into multiple drawing elements, each drawing element corresponding to the corresponding change content vector and downstream federated data object;
[0126] Construct a dependency graph between drawing elements and downstream federated data objects, where drawing elements and downstream federated data objects are nodes in the dependency graph, and references or derivations are edges (e.g., “Part A → Assembly B → Purchase Order P”).
[0127] For each drawing element, trace down the dependency graph to all direct / indirect downstream federated data objects and set a maximum tracing depth to prevent overexpansion.
[0128] Step 103: Set up a risk assessment model, calculate the risk index based on the attribute offset vector, and generate a risk report, wherein the risk report includes: risk index, change content vector, and attribute offset vector.
[0129] Specifically, the risk assessment model includes:
[0130] ,
[0131] in, For the first The normalized final risk index corresponding to each attribute offset vector For the first The risk index corresponding to each attribute offset vector. For the first The risk index benchmark value corresponding to each attribute offset vector. Adjustment factors for risk assessment models (for example, It can belong to [1.0, 2.5]).
[0132] Specifically, the first Risk index corresponding to each attribute offset vector include:
[0133] ,
[0134] in, For the first The first weight of the attribute offset vector For the first The corrected risk index corresponding to each attribute offset vector.
[0135] Specifically, the first The corrected risk index corresponding to each attribute offset vector include:
[0136] ,
[0137] in, For the first The preliminary risk index corresponding to each attribute offset vector. For the first Attribute offset vector With the Attribute offset vector Interaction influence weights (e.g.) ∈[−1,1], the larger the value, the stronger the interaction effect).
[0138] Specifically, the first Preliminary risk index corresponding to each attribute offset vector include:
[0139] ,
[0140] in, For the first The second weight of the attribute offset vector For the first Each attribute offset vector For the first The baseline value corresponding to each attribute offset vector. For the first The first adjustment factor of the preliminary risk index corresponding to each attribute offset vector (for example) It can belong to [0.1, 3.0]). For the first The tolerance threshold for each attribute offset vector. For the first The second adjustment factor of the preliminary risk index corresponding to each attribute offset vector (for example) It can belong to [0.5, 3]).
[0141] In the above embodiments of the present invention, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.
[0142] In the several embodiments provided by this invention, it should be understood that the disclosed technical content can be implemented in other ways. The system embodiments described above are merely illustrative; for example, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces, indirect coupling or communication connection between units or modules, and may be electrical or other forms.
[0143] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.
[0144] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.
[0145] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes: USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, optical disks, and other media capable of storing program code.
[0146] Obviously, the above embodiments are merely illustrative examples for clear explanation and are not intended to limit the implementation. Those skilled in the art will recognize that other variations or modifications can be made based on the above description. It is neither necessary nor possible to exhaustively list all possible implementations here. However, obvious variations or modifications derived therefrom are still within the scope of protection of this invention.
Claims
1. A smart risk assessment method based on engineering drawing changes, characterized in that, include: When engineering drawings are changed, the new engineering drawings are obtained and the differences in the changes are identified based on the old engineering drawings, generating a structured vector of change content. Based on the dependency relationship between the engineering drawings and downstream federated data objects, the change content vector is mapped to the downstream federated data objects, and the attribute offset vector of each downstream federated data object caused by the change content vector is obtained level by level. Set up a risk assessment model, calculate a risk index based on the attribute offset vector, and generate a risk report, wherein the risk report includes: risk index, change content vector, and attribute offset vector; Risk assessment models include: in, For the first The normalized final risk index corresponding to each attribute offset vector For the first The risk index corresponding to each attribute offset vector. For the first The risk index benchmark value corresponding to each attribute offset vector. This serves as an adjustment factor for the risk assessment model. No. Risk index corresponding to each attribute offset vector include: in, For the first The first weight of the attribute offset vector For the first The corrected risk index corresponding to each attribute offset vector; No. The corrected risk index corresponding to each attribute offset vector include: in, For the first The preliminary risk index corresponding to each attribute offset vector. For the first Attribute offset vector With the Attribute offset vector The interaction influence weight; No. Preliminary risk index corresponding to each attribute offset vector include: in, For the first The second weight of the attribute offset vector For the first Each attribute offset vector For the first The baseline value corresponding to each attribute offset vector. For the first The first adjustment factor for the preliminary risk index corresponding to each attribute offset vector. For the first The tolerance threshold for each attribute offset vector. For the first The second adjustment factor for the preliminary risk index corresponding to each attribute offset vector.
2. The intelligent risk assessment method based on engineering drawing changes as described in claim 1, characterized in that, Identifying changes based on old engineering drawings and generating structured change content vectors involves: loading the new and old engineering drawings into a structured model, calculating the change content vector for each geometric element in the structured model, and comparing it with a deviation threshold. If the deviation threshold is exceeded, the corresponding geometric element is marked as a geometric change.
3. The intelligent risk assessment method based on engineering drawing changes as described in claim 1, characterized in that, Mapping the change content vector to the downstream federated data object includes: dividing the new engineering drawing into multiple drawing elements, each drawing element corresponding to the corresponding change content vector and downstream federated data object; Construct a dependency graph between drawing elements and downstream federated data objects, where drawing elements and downstream federated data objects are nodes in the dependency graph, and references or derivations are edges. For each drawing element, trace down the dependency graph to all direct / indirect downstream federated data objects and set a maximum tracing depth to prevent overexpansion.
4. An intelligent risk assessment system based on engineering drawing changes, characterized in that, include: The data processing module is used to obtain the new engineering drawings after the changes are made, and to identify the differences in the changes based on the old engineering drawings, and generate a structured change content vector. The mapping module is used to map the change content vector to the downstream federated data object according to the dependency relationship between the engineering drawing and the downstream federated data object, and to obtain the attribute offset vector of each downstream federated data object caused by the change content vector. The risk assessment module is used to set up a risk assessment model, calculate a risk index based on the attribute offset vector, and generate a risk report, wherein the risk report includes: risk index, change content vector, and attribute offset vector; Risk assessment models include: in, For the first The normalized final risk index corresponding to each attribute offset vector For the first The risk index corresponding to each attribute offset vector. For the first The risk index benchmark value corresponding to each attribute offset vector. This serves as an adjustment factor for the risk assessment model. No. Risk index corresponding to each attribute offset vector include: in, For the first The first weight of the attribute offset vector For the first The corrected risk index corresponding to each attribute offset vector; No. The corrected risk index corresponding to each attribute offset vector include: in, For the first The preliminary risk index corresponding to each attribute offset vector. For the first Attribute offset vector With the Attribute offset vector The interaction influence weight; No. Preliminary risk index corresponding to each attribute offset vector include: in, For the first The second weight of the attribute offset vector For the first Each attribute offset vector For the first The baseline value corresponding to each attribute offset vector. For the first The first adjustment factor for the preliminary risk index corresponding to each attribute offset vector. For the first The tolerance threshold for each attribute offset vector. For the first The second adjustment factor for the preliminary risk index corresponding to each attribute offset vector.
5. The intelligent risk assessment system based on engineering drawing changes as described in claim 4, characterized in that, Identifying changes based on old engineering drawings and generating structured change content vectors involves: loading the new and old engineering drawings into a structured model, calculating the change content vector for each geometric element in the structured model, and comparing it with a deviation threshold. If the deviation threshold is exceeded, the corresponding geometric element is marked as a geometric change.
6. The intelligent risk assessment system based on engineering drawing changes as described in claim 5, characterized in that, Mapping the change content vector to the downstream federated data object includes: dividing the new engineering drawing into multiple drawing elements, each drawing element corresponding to the corresponding change content vector and downstream federated data object; Construct a dependency graph between drawing elements and downstream federated data objects, where drawing elements and downstream federated data objects are nodes in the dependency graph, and references or derivations are edges. For each drawing element, trace down the dependency graph to all direct / indirect downstream federated data objects and set a maximum tracing depth to prevent overexpansion.