Engineering model evaluation method, device, program product and electronic equipment

Abstract

The present disclosure provides an engineering model evaluation method, device, program product and electronic device, which relate to the field of computer technology. The method includes: obtaining an engineering model to be evaluated; determining engineering requirement information according to the type of the engineering model to be evaluated, matching the engineering model to be evaluated with the engineering requirement information, and determining a first evaluation value of the engineering model to be evaluated according to the matching result; sampling the engineering model to be evaluated at different finenesses to obtain sampling information corresponding to different finenesses, and obtaining a second evaluation value of the engineering model to be evaluated by comparing the sampling information corresponding to different finenesses; adding an extension module on the basis of the engineering model to be evaluated to obtain an extended engineering model corresponding to the engineering model to be evaluated, and determining a third evaluation value of the engineering model to be evaluated according to the extended engineering model; and determining a comprehensive evaluation value based on the first evaluation value, the second evaluation value and the third evaluation value. The present disclosure can objectively and accurately evaluate the quality of the engineering model.

Description

Technical Field

[0001] The present disclosure relates to the field of computer technology, and in particular to an engineering model evaluation method, an engineering model evaluation device, a computer program product and an electronic device. Background Art

[0002] Engineering models represented by BIM (Building Information Modeling) models serve the entire life cycle of a project and are an important foundation for digital design, construction, management and application. High-quality engineering models can provide effective guidance for the implementation of engineering projects.

[0003] At present, the evaluation of engineering models generally relies on human evaluation, which is limited by factors such as the evaluators' subjective feelings, evaluation standards, and professional level. There are problems such as inconsistent standards, low objectivity and accuracy of evaluation results. Summary of the invention

[0004] The present disclosure provides an engineering model evaluation method, an engineering model evaluation device, a computer program product and an electronic device, so as to at least to some extent solve the problem that the related technology relies on human evaluation.

[0005] According to a first aspect of the present disclosure, there is provided an engineering model evaluation method, the method comprising: obtaining an engineering model to be evaluated; determining engineering requirement information according to the type of the engineering model to be evaluated, matching the engineering model to be evaluated with the engineering requirement information, and determining a first evaluation value of the engineering model to be evaluated according to the matching result; sampling the engineering model to be evaluated at different finenesses to obtain sampling information corresponding to the different finenesses, and obtaining a second evaluation value of the engineering model to be evaluated by comparing the sampling information corresponding to the different finenesses; adding an extension module on the basis of the engineering model to be evaluated to obtain an extended engineering model corresponding to the engineering model to be evaluated, and determining a third evaluation value of the engineering model to be evaluated according to the extended engineering model; and determining a comprehensive evaluation value of the engineering model to be evaluated based on the first evaluation value, the second evaluation value, and the third evaluation value.

[0006] According to a second aspect of the present disclosure, there is provided an engineering model evaluation device, the device comprising: a model acquisition module, configured to acquire an engineering model to be evaluated; a first evaluation module, configured to determine requirement information according to the type of the engineering model to be evaluated, match the engineering model to be evaluated with the requirement information, and determine a first evaluation value of the engineering model to be evaluated according to the matching result; a second evaluation module, configured to sample the engineering model to be evaluated at different finenesses to obtain sampling information corresponding to the different finenesses, and obtain a second evaluation value of the engineering model to be evaluated by comparing the sampling information corresponding to the different finenesses; a third evaluation module, configured to add an extension module on the basis of the engineering model to be evaluated to obtain an extended engineering model corresponding to the engineering model to be evaluated, and determine a third evaluation value of the engineering model to be evaluated according to the extended engineering model; and a comprehensive evaluation module, configured to determine a comprehensive evaluation value of the engineering model to be evaluated based on the first evaluation value, the second evaluation value, and the third evaluation value.

[0007] According to a third aspect of the present disclosure, a computer program product is provided, including a computer program, wherein when the computer program is executed by a processor, the method of the first aspect and possible implementations thereof are implemented.

[0008] According to a fourth aspect of the present disclosure, an electronic device is provided, comprising: a processor; and a memory for storing executable instructions of the processor; wherein the processor is configured to execute the method of the above-mentioned first aspect and its possible implementation methods by executing the executable instructions.

[0009] The technical solution disclosed in this disclosure has the following beneficial effects:

[0010] It provides a scheme for objectively evaluating engineering models, which evaluates the comprehensiveness, refinement, and scalability of engineering models in matching engineering requirements, and obtains a comprehensive evaluation value based on the evaluation values ​​of different aspects. These aspects cover the problems that may be involved in different links of engineering models such as design, construction, management, and application, so that the evaluation results can fully and comprehensively reflect the quality of engineering models. It solves the problem of relying on human evaluation in related technologies, provides a unified and objective evaluation standard, and ensures the objectivity and accuracy of the evaluation results. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] Figure 1 A flowchart showing an engineering model evaluation method in this exemplary embodiment.

[0012] Figure 2 A flowchart for determining a first evaluation value in this exemplary embodiment is shown.

[0013] Figure 3A flow chart showing a completeness analysis in this exemplary embodiment.

[0014] Figure 4 A schematic diagram showing sampling information in this exemplary embodiment.

[0015] Figure 5 A flowchart for determining the second evaluation value in this exemplary embodiment is shown.

[0016] Figure 6 A flow chart of determining the degree of difference of different finenesses in this exemplary embodiment is shown.

[0017] Figure 7 A flowchart for determining the third evaluation value in this exemplary embodiment is shown.

[0018] Figure 8 A schematic flow of an engineering model evaluation method in this exemplary embodiment is shown.

[0019] Fig. 9 A schematic structural diagram of an engineering model evaluation device in this exemplary embodiment is shown.

[0020] Fig.10 A schematic structural diagram of an electronic device in this exemplary embodiment is shown. DETAILED DESCRIPTION

[0021] Exemplary embodiments of the present disclosure will be described more fully hereinafter with reference to the accompanying drawings.

[0022] The accompanying drawings are schematic diagrams of the present disclosure and are not necessarily drawn to scale. Some of the block diagrams shown in the accompanying drawings may be functional entities and do not necessarily correspond to physically or logically independent entities. These functional entities can be implemented in software form, or in hardware modules or integrated circuits, or in networks, processors or microcontrollers. The embodiments can be implemented in various forms and should not be construed as being limited to the examples set forth herein. The features, structures or characteristics described in the present disclosure may be combined in one or more embodiments in any suitable manner. In the description below, many specific details are provided to provide a full description of the embodiments of the present disclosure. However, those skilled in the art should appreciate that one or more specific details may be omitted when implementing the technical solution of the present disclosure, or one or more specific details may be replaced by other methods, components, devices, steps, etc.

[0023] Engineering models are usually three-dimensional digital models based on drawings, etc., and can include digital information related to the project. By establishing an engineering model, a unique and consistent information model can be provided to all parties involved in the project, providing effective guidance and basis for the implementation of the project.

[0024] Since the construction of engineering models depends on many factors, their quality may vary. In related technologies, the evaluation of engineering models generally relies on human evaluation, which is limited by factors such as the subjective feelings, evaluation standards, and professional level of evaluators. There are problems such as inconsistent standards, low objectivity and accuracy of evaluation results. If low-quality engineering models are used in engineering projects, it will bring a series of problems to subsequent construction, management, and application.

[0025] In view of the above problems, an exemplary embodiment of the present disclosure provides an engineering model evaluation method, which can comprehensively, fully and accurately evaluate the quality of an engineering model based on an objective and unified evaluation standard, so as to facilitate the use of high-quality engineering models in engineering projects.

[0026] Figure 1 An exemplary process of the engineering model evaluation method is shown, which may include the following steps S110 to S150:

[0027] Step S110, obtaining a project model to be evaluated;

[0028] Step S120, determining engineering requirement information according to the type of the engineering model to be evaluated, matching the engineering model to be evaluated with the engineering requirement information, and determining a first evaluation value of the engineering model to be evaluated according to the matching result;

[0029] Step S130, sampling the engineering model to be evaluated at different finenesses to obtain sampling information corresponding to the different finenesses, and obtaining a second evaluation value of the engineering model to be evaluated by comparing the sampling information corresponding to the different finenesses;

[0030] Step S140, adding an extension module on the basis of the engineering model to be evaluated to obtain an extended engineering model corresponding to the engineering model to be evaluated, and determining a third evaluation value of the engineering model to be evaluated according to the extended engineering model;

[0031] Step S150: determining a comprehensive evaluation value of the engineering model to be evaluated based on the first evaluation value, the second evaluation value, and the third evaluation value.

[0032] based on Figure 1The method provides a scheme for objectively evaluating engineering models, which evaluates the comprehensiveness, refinement, and scalability of engineering models in matching engineering requirements, and obtains a comprehensive evaluation value based on the evaluation values ​​of different aspects. These aspects cover the problems that may be involved in different links of engineering models such as design, construction, management, and application, so that the evaluation results can fully and comprehensively reflect the quality of engineering models. It solves the problem of relying on human evaluation in related technologies, provides a unified and objective evaluation standard, and ensures the objectivity and accuracy of the evaluation results.

[0033] Below Figure 1 Provide detailed instructions for each step.

[0034] refer to Figure 1 , in step S110, the engineering model to be evaluated is obtained.

[0035] The engineering model to be evaluated may be a BIM model or a digital model applied to other engineering scenarios. The engineering model to be evaluated may be a digital file in any format. In one embodiment, the engineering model evaluation method may be implemented as an application, and a user may import a file of the engineering model into the application, and the file is the engineering model to be evaluated.

[0036] Continue to refer Figure 1 In step S120, the engineering requirement information is determined according to the type of the engineering model to be evaluated, the engineering model to be evaluated is matched with the engineering requirement information, and a first evaluation value of the engineering model to be evaluated is determined according to the matching result.

[0037] Among them, different types of engineering models may be used in different engineering scenarios and need to match different engineering demand information. Engineering demand information can be written in advance for different types of engineering models, indicating that the corresponding types of engineering models require the engineering demand information. Taking the offshore photovoltaic construction project as an example, the project may use different types of engineering models. Among them, for the geological BIM model, it is necessary to establish the main geological structure, lithology, hydrogeology, physical geology and other information that meets the depth of the construction drawing design, establish the three-dimensional terrain and geological model of the project, and establish relevant attribute information. For the civil engineering BIM model, it is necessary to establish the photovoltaic module support foundation, cable trench, building monomer and other information that meets the depth of the construction drawing design, and establish relevant attribute information. For the electromechanical BIM model, it is necessary to establish the photovoltaic array installation, cable laying and other information that meets the depth of the construction drawing design, and establish relevant attribute information.

[0038] According to the type of the engineering model to be evaluated, the engineering requirement information corresponding to the type is determined. The engineering model to be evaluated is matched with the engineering requirement information. The matching result may include the proportion of the engineering model to be evaluated matching the engineering requirement information and the quality of the matching engineering requirement information, such as the depth, granularity, and rationality of the information that the engineering model to be evaluated can provide when it corresponds to different demand items. The matching result reflects the comprehensiveness and effectiveness of the engineering model to be evaluated in meeting the engineering requirement information, which can be quantified as the first evaluation value.

[0039] In one embodiment, reference Figure 2 As shown, the above-mentioned matching of the engineering model to be evaluated with the engineering requirement information and determining the first evaluation value of the engineering model to be evaluated according to the matching result may include the following steps S210 and S220:

[0040] Step S210, inputting the engineering model to be evaluated and the engineering requirement information into the first generative model, and outputting the engineering design information corresponding to the engineering requirement information through the first generative model;

[0041] Step S220: analyzing the completeness of the engineering design information, and determining a first evaluation value of the engineering model to be evaluated according to the completeness.

[0042] Among them, the first generative model can be a pre-trained artificial intelligence model or a model that has been fully trained in the engineering design scenario. Exemplarily, the first generative model can be an LLM (Large Language Model). The engineering requirement information is used to describe the requirements of the engineering design, and can be used as a prompt for the first generative model and input into the first generative model together with the engineering model to be evaluated. The first generative model answers the requirements in the engineering requirement information based on the information in the engineering model to be evaluated, and outputs the corresponding engineering design information.

[0043] If the information of the engineering model to be evaluated is comprehensive, the first generative model can provide a comprehensive and sufficient answer to the engineering demand information based on the engineering model to be evaluated, and output relatively complete engineering design information. If the engineering model to be evaluated lacks information in certain aspects, there will be corresponding incompleteness in the engineering design information output by the first generative model. Therefore, the completeness of the engineering design information can be analyzed. Exemplarily, in the process of outputting engineering design information, the first generative model can fill in preset characters (such as characters representing blanks, etc.) for unanswered requirements, and calculate the completeness of the engineering design information by detecting the number or proportion of preset characters in the engineering design information. The first evaluation value is determined based on the completeness. The higher the completeness, the more comprehensive the information of the engineering model to be evaluated, and the higher the first evaluation value.

[0044] In one implementation, the engineering requirement information includes multiple requirement items, each requirement item needs to be filled with design parameters, and the engineering design information includes design parameters corresponding to the multiple requirement items. It should be noted that the design parameters can be numerical parameters or non-numerical parameters, such as parameters representing classification information. Figure 3 As shown, the above analysis of the completeness of the engineering design information may include the following steps S310 and S320:

[0045] Step S310: performing validity analysis on the design parameters in the engineering design information to determine valid design parameters in the engineering design information.

[0046] Invalid design parameters include, but are not limited to, design parameters whose actual parameters are blank, design parameters that have no actual meaning, wrong design parameters, etc. Exemplarily, it is possible to detect whether the design parameter is a preset character representing a blank, or to analyze whether the design parameter has an actual meaning from a language level, or to check whether the design parameter is correct according to the design rules. The design parameter can also be input into a generative model (which can be the first generative model or other generative models), and the validity of the design parameter can be determined based on the validity of the output result. For each design parameter in the engineering design information, it can be analyzed whether it is valid, and valid design parameters can be screened out.

[0047] Step S320, calculating the completeness of the engineering design information according to the weights of the requirement items corresponding to the valid design parameters.

[0048] Different requirements may have different weights, such as designers can set weights in advance according to the importance of each requirement. For example, the weights of the requirements corresponding to each valid design parameter may be accumulated, and the accumulated result may be used as the completeness of the engineering design information, or the accumulated result may be normalized (such as divided by the sum of the weights of all the requirements) to obtain the completeness.

[0049] In one embodiment, the weights of all requirement items may be the same. For example, if the designer does not set the weights, the weights of all requirement items are defaulted to 1. Thus, the proportion of effective design parameters in all design parameters can be calculated to obtain the completeness of the engineering design information.

[0050] based on Figure 3 The scheme can quickly calculate the completeness of engineering design information, accurately and objectively reflect the quality of engineering design information, and thus indirectly reflect the comprehensiveness of the information of the engineering model to be evaluated.

[0051] When the completeness is obtained, the completeness may be used as the first evaluation value, or further calculation may be performed on the completeness, such as normalization processing, to obtain the first evaluation value.

[0052] Continue to refer Figure 1 In step S130, the engineering model to be evaluated is sampled at different finenesses to obtain sampling information corresponding to the different finenesses, and the second evaluation value of the engineering model to be evaluated is obtained by comparing the sampling information corresponding to the different finenesses.

[0053] Among them, since the engineering model to be evaluated includes a three-dimensional digital model, different information can usually be displayed at different levels of detail (LOD). The engineering model to be evaluated can be sampled at different levels of detail, and the sampled information includes but is not limited to: image information, video information, three-dimensional structure information, and size information. Figure 4 A schematic diagram showing sampling information corresponding to a certain level of precision.

[0054] If the precision of the engineering model to be evaluated is high, the sampling information shows obvious differences at different precisions, and more detailed information appears as the precision increases. Therefore, by comparing the sampling information corresponding to different precisions, the quality of the engineering model to be evaluated in terms of refinement can be evaluated to obtain the second evaluation value of the engineering model to be evaluated.

[0055] In one embodiment, reference Figure 5 As shown, the second evaluation value of the engineering model to be evaluated is obtained by comparing the sampling information corresponding to different finenesses, which may include the following steps S510 to S530:

[0056] Step S510: Determine the degree of difference between the different finenesses by comparing the difference of sampling information corresponding to the different finenesses.

[0057] The greater the difference between the sampling information corresponding to different finenesses, the higher the degree of difference between the different finenesses. For example, the difference between the sampling information corresponding to two adjacent finenesses can be compared in sequence, such as calculating the sampled image similarity, video similarity, three-dimensional structure similarity, etc., and obtaining the degree of difference by means of "1-similarity" and the like.

[0058] In one embodiment, reference Figure 6 As shown, the above-mentioned determination of the degree of difference of different finenesses by comparing the difference of sampling information corresponding to different finenesses may include the following steps S610 and S620:

[0059] Step S610, extracting feature information from sampling information corresponding to different degrees of precision respectively, to obtain feature information corresponding to different degrees of precision;

[0060] Step S620, for any two finenesses, calculate the similarity of two feature information corresponding to the two finenesses, determine the information increment between the two feature information, and determine the degree of difference between the two finenesses according to the similarity and the information increment.

[0061] Among them, the feature information is information that numerically represents the features in the sampled information. Exemplarily, the sampled information can be input into a feature extraction model (such as a pre-trained neural network model) to obtain the corresponding feature information. For two different finenesses, the similarity of the two corresponding feature information is calculated. For example, if the feature information is in the form of a vector, the similarity of the two vectors can be calculated. And the information increment between the two feature information is calculated, such as the numerical values ​​of the two vectors in each dimension can be subtracted, and the result obtained is the information increment. The similarity measures the similarity or dissimilarity of the two feature information (or two sampled information) from a global perspective, and the information increment represents the difference in details between the two feature information (or two sampled information). By combining the evaluation results of the similarity and the information increment, the difference between the two finenesses can be determined more comprehensively and accurately. For example, the weighted average of the result of "1-similarity" and the information increment can be calculated to obtain a quantitative difference value.

[0062] Step S520 , in the order of precision from low to high, when the precision is improved and the sampling information does not substantially change, the highest precision of the engineering model to be evaluated is determined.

[0063] Among them, in order from low to high precision, the sampling information corresponding to two adjacent different precisions is compared in turn. Since the precision is increased by one level, the sampling information should change substantially. If the sampling information does not change substantially, it means that the engineering model to be evaluated cannot provide detailed information at this precision. The similarity of the sampling information (or feature information) corresponding to the two precisions can be used to judge whether the sampling information has changed substantially. If the similarity of the sampling information corresponding to two adjacent precisions exceeds the similarity threshold (which can be set based on experience or specific circumstances), it means that they are too similar and no substantial changes have occurred. Therefore, the lower level of precision is used as the highest precision of the engineering model to be evaluated.

[0064] Step S530: determining a second evaluation value of the engineering model to be evaluated according to the difference degree and the highest precision.

[0065] The second evaluation value may be positively correlated with the difference degree and the highest precision. For example, the difference degree and the highest precision may be quantified into values ​​of the same numerical scale, such as quantifying and normalizing the two indicators, and then calculating the average value to obtain the second evaluation value.

[0066] based on Figure 5The method can fully evaluate the performance of the engineering model to be evaluated in terms of precision and obtain an objective and accurate second evaluation value.

[0067] Continue to refer Figure 1 In step S140, an extension module is added to the engineering model to be evaluated to obtain an extended engineering model corresponding to the engineering model to be evaluated, and a third evaluation value of the engineering model to be evaluated is determined according to the extended engineering model.

[0068] The third evaluation value is an indicator value for evaluating the project model from the perspective of scalability. From the perspective of long-term management and maintenance after project construction, the project object needs to have good scalability to facilitate subsequent transformation and upgrading.

[0069] In one embodiment, the above-mentioned adding an extension module on the basis of the engineering model to be evaluated to obtain an extended engineering model corresponding to the engineering model to be evaluated may include the following steps:

[0070] The extended requirement information corresponding to the engineering model to be evaluated and the extended module is input into the second generative model, and the extended engineering model is output through the second generative model.

[0071] Among them, the second generative model can be a pre-trained artificial intelligence model, or a model that has been fully trained in the scenario of model expansion. Exemplarily, the first generative model can be an LLM. The extended requirement information is used to describe the requirements for engineering expansion, such as what modules or functions need to be expanded, which can be used as prompt information (prompt) of the second generative model and input into the second generative model together with the engineering model to be evaluated. The second generative model adds, deletes, and transforms the engineering model to be evaluated based on the extended requirement information, and outputs the extended engineering model.

[0072] Ideally, when adding an extension module, the original engineering model to be evaluated does not need to be significantly modified, or even the original model components do not need to be changed at all. Generally, the higher the degree of modification required during the extension, the worse the scalability of the original model.

[0073] In one embodiment, reference Figure 7 As shown, the above-mentioned determination of the third evaluation value of the engineering model to be evaluated according to the extended engineering model may include the following steps S710 to S730:

[0074] Step S710, by comparing the extended project model with the project model to be evaluated, the degree of modification of the extended project model relative to the project model to be evaluated is obtained. For example, the extended project model can be deleted after the added extension module is removed, and then the similarity or difference between the extended project model and the original project model to be evaluated is calculated. The higher the similarity or the lower the difference, the lower the degree of modification.

[0075] Step S720, evaluate the extended engineering model to obtain an evaluation value of the extended engineering model. For example, the extended engineering model can be evaluated by determining the first evaluation value and the second evaluation value as described above, such as determining the first evaluation value of the extended engineering model based on the evaluation method of step S120, and determining the second evaluation value of the extended engineering model based on the evaluation method of step S130, and combining the two to obtain the final evaluation value of the extended engineering model. Alternatively, the first evaluation value or the second evaluation value can be used alone as the evaluation value of the extended engineering model.

[0076] Step S730: determining a third evaluation value of the engineering model to be evaluated according to the degree of transformation and the evaluation value of the extended engineering model.

[0077] The third evaluation value may be negatively correlated with the degree of transformation and positively correlated with the evaluation value of the extended engineering model. For example, the value of "1-degree of transformation" and the evaluation value of the extended engineering model may be averaged, weighted, or summed to obtain the third evaluation value.

[0078] based on Figure 7 The method is used to evaluate the scalability of the engineering model to be evaluated from two aspects: the degree of transformation and the quality of the extended engineering model itself. The third evaluation value obtained is relatively accurate and reasonable.

[0079] Continue to refer Figure 1 In step S150, a comprehensive evaluation value of the engineering model to be evaluated is determined based on the first evaluation value, the second evaluation value, and the third evaluation value.

[0080] For example, corresponding weights are pre-set for the first evaluation value, the second evaluation value, and the third evaluation value. For example, the first evaluation value evaluates the comprehensiveness of information, which is the most important and has the highest weight, while the third evaluation value evaluates the scalability, which is relatively unimportant and has a lower weight. The first evaluation value, the second evaluation value, and the third evaluation value can be weighted by weight to calculate a comprehensive evaluation value. Alternatively, the first evaluation value, the second evaluation value, and the third evaluation value can be accumulated or the average value can be calculated to obtain a comprehensive evaluation value.

[0081] Figure 8The schematic flow of the engineering model evaluation method is shown, including: determining engineering requirement information according to the type of the engineering model to be evaluated, inputting the engineering model to be evaluated and the engineering requirement information into the first generative model, outputting engineering design information, evaluating the integrity of the engineering design information, and obtaining a first evaluation value. Sampling the engineering model to be evaluated at different precisions to obtain sampling information corresponding to different precisions, performing graded comparison on the sampling information to determine the degree of difference, and determining the maximum precision, and combining the degree of difference and the maximum precision to obtain a second evaluation value. Inputting the engineering model to be evaluated and the extended requirement information into the second generative model, outputting the extended engineering model, comparing the engineering model to be evaluated and the extended engineering model to determine the degree of transformation, and evaluating the extended engineering model itself, and determining a third evaluation value according to the degree of transformation and the evaluation value of the extended engineering model. Combining the first evaluation value, the second evaluation value, and the third evaluation value, a comprehensive evaluation value is obtained. The comprehensive evaluation value can comprehensively and accurately reflect the quality of the engineering model to be evaluated.

[0082] In this way, the engineering models involved in the engineering project can be accurately evaluated and high-quality models can be screened out, such as models with a comprehensive evaluation value higher than a preset evaluation value (which can be set based on experience or specific circumstances). Different types of engineering models can also be sorted from high to low according to the comprehensive evaluation value, and the engineering models with the highest ranking can be selected for use in actual projects.

[0083] The exemplary embodiment of the present disclosure also provides an engineering model evaluation device. Fig. 9 As shown, the engineering model evaluation device 900 may include the following program modules:

[0084] The model acquisition module 910 is configured to acquire a model of the project to be evaluated;

[0085] A first evaluation module 920 is configured to determine requirement information according to the type of the engineering model to be evaluated, match the engineering model to be evaluated with the requirement information, and determine a first evaluation value of the engineering model to be evaluated according to the matching result;

[0086] The second evaluation module 930 is configured to sample the engineering model to be evaluated at different finenesses to obtain sampling information corresponding to the different finenesses, and obtain a second evaluation value of the engineering model to be evaluated by comparing the sampling information corresponding to the different finenesses;

[0087] The third evaluation module 940 is configured to add an extension module on the basis of the engineering model to be evaluated to obtain an extended engineering model corresponding to the engineering model to be evaluated, and determine a third evaluation value of the engineering model to be evaluated according to the extended engineering model;

[0088] The comprehensive evaluation module 950 is configured to determine the comprehensive evaluation value of the engineering model to be evaluated based on the first evaluation value, the second evaluation value, and the third evaluation value.

[0089] In one embodiment, the engineering model to be evaluated is matched with the engineering requirement information, and a first evaluation value of the engineering model to be evaluated is determined based on the matching result, including: inputting the engineering model to be evaluated and the engineering requirement information into a first generative model, and outputting engineering design information corresponding to the engineering requirement information through the first generative model; analyzing the completeness of the engineering design information, and determining the first evaluation value of the engineering model to be evaluated based on the completeness.

[0090] In one embodiment, the engineering requirement information includes multiple requirement items, and the engineering design information includes design parameters corresponding to the multiple requirement items; the analysis of the completeness of the engineering design information includes: performing a validity analysis on the design parameters in the engineering design information to determine the valid design parameters in the engineering design information; and calculating the completeness of the engineering design information based on the weights of the requirement items corresponding to the valid design parameters.

[0091] In one embodiment, the second evaluation value of the engineering model to be evaluated is obtained by comparing the sampling information corresponding to the different finenesses, including: determining the degree of difference of different finenesses by comparing the differences in the sampling information corresponding to the different finenesses; determining the highest fineness of the engineering model to be evaluated in the order of the finenesses from low to high when the fineness is improved and the sampling information does not substantially change; and determining the second evaluation value of the engineering model to be evaluated based on the degree of difference and the highest fineness.

[0092] In one embodiment, determining the degree of difference between different degrees of fineness by comparing the differences in sampling information corresponding to the different degrees of fineness includes: extracting feature information from the sampling information corresponding to the different degrees of fineness to obtain the feature information corresponding to the different degrees of fineness; for any two degrees of fineness, calculating the similarity between two feature information corresponding to the two degrees of fineness, and determining the information increment between the two feature information, and determining the degree of difference between the two degrees of fineness based on the similarity and the information increment.

[0093] In one embodiment, adding an extension module based on the engineering model to be evaluated to obtain an extended engineering model corresponding to the engineering model to be evaluated includes: inputting extended requirement information corresponding to the engineering model to be evaluated and the extension module into a second generative model, and outputting the extended engineering model through the second generative model.

[0094] In one embodiment, determining the third evaluation value of the engineering model to be evaluated based on the extended engineering model includes: obtaining a degree of modification of the extended engineering model relative to the engineering model to be evaluated by comparing the extended engineering model with the engineering model to be evaluated; evaluating the extended engineering model to obtain an evaluation value of the extended engineering model; and determining the third evaluation value of the engineering model to be evaluated based on the degree of modification and the evaluation value of the extended engineering model.

[0095] The specific details of each part of the above-mentioned device have been described in detail in the implementation method of the method part. The undisclosed details can be found in the implementation method of the method part, so they will not be repeated here.

[0096] It should be noted that, although several modules or units of the device for action execution are mentioned in the above detailed description, this division is not mandatory. In fact, according to the exemplary embodiments of the present disclosure, the features and functions of two or more modules or units described above can be embodied in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided into multiple modules or units to be embodied.

[0097] The exemplary embodiments of the present disclosure also provide a computer program product, which includes a computer program, and when the computer program is executed by a processor, the above-mentioned named entity recognition method is implemented.

[0098] In one embodiment, the computer program product may be a tangible product containing a computer program, such as a computer-readable storage medium storing a computer program. The readable storage medium may be a storage medium based on electrical, magnetic, optical, electromagnetic, infrared, or other signals, including but not limited to: random access memory (RAM), read-only memory (ROM), magnetic tape, floppy disk, flash memory (Flash), mechanical hard disk (HDD), solid state drive (SSD), and the like. Exemplarily, the computer program product may be implemented as a non-volatile storage medium storing a computer program, such as a read-only memory, a NAND flash memory (Nand Flash), and the like.

[0099] In one embodiment, the computer program product may be an intangible product including a computer program. Exemplarily, the computer program product may be implemented as a virtual digital product, such as a digital file storing an executable file, an installation package, etc. of the computer program.

[0100] The code of the computer program can be written in one or more programming languages. Programming languages ​​such as C language, Java, C++, etc. The program code can be executed completely on the user computing device, or partially on the user computing device, or as a separate software package, or partially on the user computing device and partially on the remote computing device, or completely on the remote computing device or server. In the case of a remote computing device, the remote computing device can be connected to the user computing device through any type of network, such as a local area network (LAN), a wide area network (WAN), etc., or can be connected to an external computing device (for example, through an Internet connection provided by an operator).

[0101] The computer program can be carried or transmitted through electrical, magnetic, optical, electromagnetic, infrared and other signals. The electronic device can convert the signal carrying the computer program into a digital signal, and then run the computer program. When the computer program runs on the electronic device, its code is used to enable the electronic device to execute (more specifically, the processor of the electronic device can execute) the method steps of various exemplary embodiments of the present disclosure, such as the following steps: step S110, obtaining the engineering model to be evaluated; step S120, determining the engineering requirement information according to the type of the engineering model to be evaluated, matching the engineering model to be evaluated with the engineering requirement information, and determining the first evaluation value of the engineering model to be evaluated according to the matching result; step S130, sampling the engineering model to be evaluated at different fineness to obtain sampling information corresponding to different fineness, and obtaining the second evaluation value of the engineering model to be evaluated by comparing the sampling information corresponding to different fineness; step S140, adding an extension module on the basis of the engineering model to be evaluated to obtain the extended engineering model corresponding to the engineering model to be evaluated, and determining the third evaluation value of the engineering model to be evaluated according to the extended engineering model; step S150, determining the comprehensive evaluation value of the engineering model to be evaluated based on the first evaluation value, the second evaluation value, and the third evaluation value.

[0102] Based on the execution of the above method steps by computer program, a scheme for objectively evaluating engineering models is provided, which evaluates the comprehensiveness, refinement, and scalability of the engineering model in matching engineering requirements, and obtains a comprehensive evaluation value based on the evaluation values ​​of different aspects. These aspects cover the problems that may be involved in the design, construction, management, and application of the engineering model, so that the evaluation results can fully and comprehensively reflect the quality of the engineering model. The problem of relying on human evaluation in related technologies is solved, and a unified and objective evaluation standard is provided to ensure the objectivity and accuracy of the evaluation results.

[0103] The exemplary embodiments of the present disclosure also provide an electronic device. The electronic device may include a processor and a memory. The memory stores executable instructions of the processor, such as a computer program. The processor executes the method steps of various exemplary embodiments of the present disclosure by executing the executable instructions.

[0104] Reference below Fig.10 , the electronic device is exemplarily described in the form of a general-purpose computing device. It should be understood that Fig.10 The electronic device 1000 shown is merely an example and should not limit the functions and scope of use of the embodiments of the present disclosure.

[0105] like Fig.10 As shown, the electronic device 1000 may include: a processor 1010 , a memory 1020 , a bus 1030 , an I / O (input / output) interface 1040 , and a network adapter 1050 .

[0106] The memory 1020 may include a volatile memory, such as a RAM 1021, a cache unit 1022, and may also include a non-volatile memory, such as a ROM 1023. The memory 1020 may also include one or more program modules 1024, such program modules 1024 include but are not limited to: an operating system, one or more application programs, other program modules, and program data, each of which or a combination thereof may include the implementation of a network environment. For example, the program module 1024 may include each module in the above-mentioned device.

[0107] The processor 1010 may include one or more processing units. For example, the processor 1010 may include an AP (Application Processor), a modem processor, a GPU (Graphics Processing Unit), an ISP (Image Signal Processor), a controller, an encoder, a decoder, a DSP (Digital Signal Processor), a baseband processor and / or an NPU (Neural-Network Processing Unit), etc.

[0108] The processor 1010 may be used to execute executable instructions stored in the memory 1020, which may include method steps of various exemplary embodiments of the present disclosure, such as the processor 1010 executing the following steps: step S110, obtaining the engineering model to be evaluated; step S120, determining the engineering requirement information according to the type of the engineering model to be evaluated, matching the engineering model to be evaluated with the engineering requirement information, and determining a first evaluation value of the engineering model to be evaluated according to the matching result; step S130, sampling the engineering model to be evaluated at different finenesses to obtain sampling information corresponding to the different finenesses, and obtaining a second evaluation value of the engineering model to be evaluated by comparing the sampling information corresponding to the different finenesses; step S140, adding an extension module on the basis of the engineering model to be evaluated to obtain an extended engineering model corresponding to the engineering model to be evaluated, and determining a third evaluation value of the engineering model to be evaluated according to the extended engineering model; step S150, determining a comprehensive evaluation value of the engineering model to be evaluated based on the first evaluation value, the second evaluation value, and the third evaluation value.

[0109] Based on the processor 1010 executing the above method steps, a scheme for objectively evaluating the engineering model is provided, which evaluates the comprehensiveness, refinement, and scalability of the engineering model in matching the engineering requirements, and obtains a comprehensive evaluation value based on the evaluation values ​​of different aspects. These aspects cover the problems that may be involved in the design, construction, management, and application of the engineering model, so that the evaluation results can fully and comprehensively reflect the quality of the engineering model. The problem of relying on human evaluation in related technologies is solved, and a unified and objective evaluation standard is provided to ensure the objectivity and accuracy of the evaluation results.

[0110] The bus 1030 is used to realize the connection between different components of the electronic device 1000, and may include a data bus, an address bus, and a control bus.

[0111] The electronic device 1000 can communicate with one or more external devices 1100 (eg, a keyboard, a mouse, an external controller, etc.) through the I / O interface 1040 .

[0112] The electronic device 1000 can communicate with one or more networks through the network adapter 1050. For example, the network adapter 1050 can provide mobile communication solutions such as 3G / 4G / 5G, or provide wireless communication solutions such as wireless LAN, Bluetooth, near field communication, etc. The network adapter 1050 can communicate with other modules of the electronic device 1000 through the bus 1030.

[0113] although Fig.10Not shown, other hardware and / or software modules may also be provided in the electronic device 1000, including but not limited to: a display, a microcode, a device driver, a redundant processor, an external disk drive array, a RAID system, a tape drive, and a data backup storage system.

[0114] As can be seen from the above, the technical solution of the present disclosure can be implemented as a method, an apparatus, a system, a computer program product, a storage medium, an electronic device, etc. Those skilled in the art can understand that various aspects of the present disclosure can be specifically implemented in the following forms, namely: a complete hardware implementation, a complete software implementation (including firmware, microcode, etc.), or an implementation combining hardware and software, such as being respectively referred to as a "circuit", "module" or "system".

[0115] It should be understood that the present disclosure is not limited to the specific method steps or structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from the scope thereof. Those skilled in the art will easily think of other embodiments based on the specific embodiments provided by the present disclosure. Therefore, the specific embodiments provided by the present disclosure are only exemplary, and the scope and spirit of the present disclosure are indicated by the claims, and any variations, uses or adaptive changes of the present disclosure should be covered, which follow the general principles of the present disclosure and include common knowledge or customary technical means in the technical field that are not disclosed in the present disclosure.

Claims

1. A method for evaluating an engineering model, characterized in that: The method comprises: Obtain the engineering model to be evaluated; Determining engineering requirement information according to the type of the engineering model to be evaluated, matching the engineering model to be evaluated with the engineering requirement information, and determining a first evaluation value of the engineering model to be evaluated according to the matching result; Sampling the engineering model to be evaluated at different degrees of precision to obtain sampling information corresponding to the different degrees of precision, and obtaining a second evaluation value of the engineering model to be evaluated by comparing the sampling information corresponding to the different degrees of precision; Adding an extension module on the basis of the engineering model to be evaluated to obtain an extended engineering model corresponding to the engineering model to be evaluated, and determining a third evaluation value of the engineering model to be evaluated according to the extended engineering model; Determine a comprehensive evaluation value of the engineering model to be evaluated based on the first evaluation value, the second evaluation value, and the third evaluation value; The step of matching the engineering model to be evaluated with the engineering requirement information and determining the first evaluation value of the engineering model to be evaluated according to the matching result includes: inputting the engineering model to be evaluated and the engineering requirement information into a first generative model, and outputting engineering design information corresponding to the engineering requirement information through the first generative model; analyzing the completeness of the engineering design information, and determining the first evaluation value of the engineering model to be evaluated according to the completeness; Obtaining a second evaluation value of the engineering model to be evaluated by comparing the sampling information corresponding to the different finenesses, including: determining the degree of difference of the different finenesses by comparing the difference of the sampling information corresponding to the different finenesses; determining the highest fineness of the engineering model to be evaluated in the order of the finenesses from low to high, when the fineness is improved and the sampling information does not substantially change; determining the second evaluation value of the engineering model to be evaluated according to the degree of difference and the highest fineness; Determining a third evaluation value of the engineering model to be evaluated based on the extended engineering model includes: obtaining a degree of modification of the extended engineering model relative to the engineering model to be evaluated by comparing the extended engineering model with the engineering model to be evaluated; evaluating the extended engineering model to obtain an evaluation value of the extended engineering model; and determining a third evaluation value of the engineering model to be evaluated based on the degree of modification and the evaluation value of the extended engineering model.

2. The method according to claim 1, characterized in that: The engineering requirement information includes a plurality of requirement items, and the engineering design information includes design parameters corresponding to the plurality of requirement items; and the analyzing the completeness of the engineering design information includes: Performing validity analysis on the design parameters in the engineering design information to determine valid design parameters in the engineering design information; The completeness of the engineering design information is calculated according to the weights of the requirement items corresponding to the effective design parameters.

3. The method according to claim 1, characterized in that: Determining the degree of difference of different finenesses by comparing the difference of sampling information corresponding to the different finenesses includes: Extracting feature information from the sampling information corresponding to the different degrees of refinement respectively to obtain feature information corresponding to the different degrees of refinement; For any two degrees of refinement, the similarity of two feature information corresponding to the two degrees of refinement is calculated, and the information increment between the two feature information is determined, and the degree of difference between the two degrees of refinement is determined according to the similarity and the information increment.

4. The method according to claim 1, characterized in that The step of adding an extension module on the basis of the engineering model to be evaluated to obtain an extended engineering model corresponding to the engineering model to be evaluated includes: The extended requirement information corresponding to the engineering model to be evaluated and the extended module is input into a second generative model, and the extended engineering model is output through the second generative model.

5. An engineering model evaluation device, characterized in that: The device comprises: A model acquisition module is configured to acquire a model of the project to be evaluated; A first evaluation module is configured to determine engineering requirement information according to the type of the engineering model to be evaluated, match the engineering model to be evaluated with the engineering requirement information, and determine a first evaluation value of the engineering model to be evaluated according to the matching result; A second evaluation module is configured to sample the engineering model to be evaluated at different finenesses to obtain sampling information corresponding to the different finenesses, and obtain a second evaluation value of the engineering model to be evaluated by comparing the sampling information corresponding to the different finenesses; A third evaluation module is configured to add an extension module on the basis of the engineering model to be evaluated to obtain an extended engineering model corresponding to the engineering model to be evaluated, and determine a third evaluation value of the engineering model to be evaluated according to the extended engineering model; A comprehensive evaluation module, configured to determine a comprehensive evaluation value of the engineering model to be evaluated based on the first evaluation value, the second evaluation value, and the third evaluation value; The step of matching the engineering model to be evaluated with the engineering requirement information and determining the first evaluation value of the engineering model to be evaluated according to the matching result includes: inputting the engineering model to be evaluated and the engineering requirement information into a first generative model, and outputting engineering design information corresponding to the engineering requirement information through the first generative model; analyzing the completeness of the engineering design information, and determining the first evaluation value of the engineering model to be evaluated according to the completeness; Obtaining a second evaluation value of the engineering model to be evaluated by comparing the sampling information corresponding to the different finenesses, including: determining the degree of difference of the different finenesses by comparing the difference of the sampling information corresponding to the different finenesses; determining the highest fineness of the engineering model to be evaluated in the order of the finenesses from low to high, when the fineness is improved and the sampling information does not substantially change; determining the second evaluation value of the engineering model to be evaluated according to the degree of difference and the highest fineness; Determining a third evaluation value of the engineering model to be evaluated based on the extended engineering model includes: obtaining a degree of modification of the extended engineering model relative to the engineering model to be evaluated by comparing the extended engineering model with the engineering model to be evaluated; evaluating the extended engineering model to obtain an evaluation value of the extended engineering model; and determining a third evaluation value of the engineering model to be evaluated based on the degree of modification and the evaluation value of the extended engineering model.

6. A computer program product, characterized in that The invention comprises a computer program, which implements the method according to any one of claims 1 to 4 when being executed by a processor.

7. An electronic device, characterized in that: include: processor; as well as A memory, configured to store executable instructions of the processor; The processor is configured to perform the method of any one of claims 1 to 4 by executing the executable instructions.

Images