BIM system informatization processing method and system based on artificial intelligence

Abstract

The embodiment of the invention provides a BIM system informatization processing method and system based on artificial intelligence, and the method comprises the steps: capturing the structural data of a BIM system, analyzing the features of the structural data according to a building performance evaluation standard, and obtaining the attribute features of the structural data; creating a reference sample set of the building performance according to a preset triggering condition; constructing a sample library of the building performance according to the reference sample set of the building performance; based on the sample library of the building performance, using a deep learning model to analyze and predict the attribute features, and generating prediction output of the structured data; and if the prediction output shows that the integrity or accuracy of the structured data has deviation, generating and issuing warning information, thereby improving the efficiency and accuracy of the BIM system in processing and analyzing a large amount of structured data.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence technology, and more specifically, to an artificial intelligence-based BIM system information processing method and system. Background Art

[0002] With the rapid development of the construction industry, the Building Information Model (BIM) system, as an integrated and information-based construction management tool, has been widely used in various stages of building design, construction, operation and maintenance. The BIM system provides a comprehensive and dynamic information database for construction projects in a digital way, greatly improving the work efficiency and quality of the construction industry. However, when processing and analyzing a large amount of structured data, traditional BIM systems often face problems such as large data volume, low processing efficiency, and insufficient analysis accuracy.

[0003] Therefore, how to improve the efficiency and accuracy of BIM systems in processing and analyzing large amounts of structured data is an urgent problem to be solved. Summary of the invention

[0004] In view of this, the purpose of this application is to provide a BIM system information processing method and system based on artificial intelligence.

[0005] In conjunction with the first aspect of the present application, a method for information processing of a BIM system based on artificial intelligence is provided, comprising:

[0006] Capturing structured data of the BIM system;

[0007] Analyzing the characteristics of the structured data according to the building performance evaluation standard to obtain the attribute characteristics of the structured data; wherein the evaluation standard is used to characterize the integrity or accuracy of the structured data, and the evaluation standard includes a single attribute and a comprehensive attribute, the single attribute is used to reflect a certain dimension of the building performance alone, and the comprehensive attribute is related to at least two single attributes that have an interactive relationship;

[0008] According to a preset trigger condition, a benchmark sample set of the building performance is created; wherein the benchmark sample set includes typical samples and atypical samples, and the trigger condition includes a performance deviation determination criterion, the typical sample does not trigger the performance deviation determination criterion, and the atypical sample triggers the performance deviation determination criterion;

[0009] Constructing a sample library of the building performance according to the benchmark sample set of the building performance;

[0010] Based on the sample library of the building performance, the attribute characteristics are analyzed and predicted using a deep learning model to generate a prediction output of the structured data; wherein each attribute characteristic in the sample library includes a basic characteristic value and a derived characteristic value, the basic characteristic value is a numerical representation of a single attribute, and the derived characteristic value is a numerical representation of a comprehensive attribute;

[0011] If the prediction output indicates that there is a deviation in the integrity or accuracy of the structured data, a warning message is generated and issued, and the warning message indicates that the operating status of the BIM system is abnormal.

[0012] In a possible implementation manner of the first aspect, analyzing the characteristics of the structured data according to the building performance evaluation standard to obtain the attribute characteristics of the structured data includes:

[0013] According to the building performance evaluation standard, obtain energy consumption data and structural stability data that affect building performance;

[0014] Extracting single attribute features and comprehensive attribute features of the structured data according to the energy consumption data and the structural stability data;

[0015] Performing standardization processing on the single attribute feature and the comprehensive attribute feature to obtain standardized features of the structured data;

[0016] The attribute features of the structured data are obtained according to the standardized features.

[0017] In a possible implementation of the first aspect, the method further includes:

[0018] Obtaining a response status of the warning information, where the response status is used to indicate whether the warning information is ignored;

[0019] Based on the response status, classify the structured data corresponding to the warning information;

[0020] Based on the classified structured data, generating classification samples;

[0021] The classified samples are added to the sample library of the building performance evaluation standard.

[0022] In a possible implementation manner of the first aspect, adding the classified samples to a sample library of the building performance evaluation standard includes:

[0023] According to a preset update frequency, the classification samples generated within the preset update frequency are updated to the sample library of the building performance evaluation standard.

[0024] In a possible implementation of the first aspect, the classifying the real-time data corresponding to the warning information based on the response status includes:

[0025] When the response status of the warning information is ignored, the structured data is classified as normal; when the response status of the warning information is responded, the structured data is classified as abnormal.

[0026] In a possible implementation of the first aspect, the deep learning model includes a convolutional neural network model; the sample library based on the building performance uses the deep learning model to analyze and predict the attribute characteristics to generate a prediction output of the structured data, including:

[0027] Obtain the trained convolutional neural network model;

[0028] The attribute features are input into the classification decision function of the convolutional neural network model to obtain the predicted output of the structured data.

[0029] In a possible implementation manner of the first aspect, the convolutional neural network model is trained by the following steps:

[0030] Based on the sample library of the building performance evaluation standard, the objective function of the convolutional neural network model is optimized to obtain the weight coefficient of each sample in the sample library; wherein the activation function of the convolutional neural network model adopts a rectified linear unit function;

[0031] Based on the sample library and the weight coefficient of each of the samples, a threshold of the classification decision function is determined; and the weight coefficient of each of the samples in the sample library and the threshold are determined as model parameters of the convolutional neural network model.

[0032] In combination with the second aspect of the present application, an artificial intelligence-based BIM system information processing system is provided, wherein the artificial intelligence-based BIM system information processing system includes a machine-readable storage medium and a processor, wherein the machine-readable storage medium stores machine-executable instructions, and when the processor executes the machine-executable instructions, the artificial intelligence-based BIM system information processing system implements the aforementioned artificial intelligence-based BIM system information processing method.

[0033] In conjunction with the third aspect of the present application, a computer-readable storage medium is provided, in which computer-executable instructions are stored. When the computer-executable instructions are executed, the aforementioned artificial intelligence-based BIM system information processing method is implemented.

[0034] In conjunction with the fourth aspect of the present application, a computer program product is provided, which, when executed by a processor, implements the aforementioned artificial intelligence-based BIM system information processing method.

[0035] Combining any of the above aspects, by capturing structured data in real time, the timeliness and completeness of data processing are ensured. Then, advanced data analysis tools are used to perform in-depth feature extraction and standardization of the data, improving the availability of the data and the accuracy of the analysis. Through preset trigger conditions, the server accurately screens out typical and atypical samples and builds a representative and diverse benchmark sample set. These sample sets further enrich the building performance sample library and provide rich data resources for the training and prediction of deep learning models. Using deep learning models such as convolutional neural networks, the server intelligently analyzes and predicts the attribute features in the sample library and generates predicted outputs of structured data, thereby using deep learning to improve the efficiency and accuracy of the BIM system in processing and analyzing large amounts of structured data. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained by combining these drawings without paying creative work.

[0037] Figure 1 A flowchart of the information processing method of the BIM system based on artificial intelligence provided in the embodiment of the present application. DETAILED DESCRIPTION

[0038] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiment of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiment of the present invention. Obviously, the described embodiment is only a part of the embodiment of the present invention, not all of the embodiments. According to the embodiment of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0039] The terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, device, product or end that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units that are not listed, or may optionally include other steps or units inherent to these processes, methods, products or ends.

[0040] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present invention. The appearance of the phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0041] Figure 1 The flowchart of the BIM system information processing method based on artificial intelligence provided by the embodiment of the present application is shown. It should be understood that in other embodiments, the order of some steps in the BIM system information processing method based on artificial intelligence of this embodiment can be shared with each other according to actual needs, or some steps can be omitted or maintained. The details of the BIM system information processing method based on artificial intelligence include:

[0042] Step S110: capturing structured data of the BIM system.

[0043] In this embodiment, the server is integrated with the BIM system through a secure data interface to ensure the security and accuracy of data transmission. The server performs data capture tasks and receives data streams from the BIM system in real time. These data may include but are not limited to building geometry information, material specifications, component properties, and equipment parameters.

[0044] During the data capture process, the server uses efficient data parsing tools to convert the received data into a unified format for subsequent processing. The data is then stored in the server's local storage system or cloud storage service to ensure data accessibility and persistence. The server is also responsible for monitoring the data capture process to ensure data integrity and consistency, and to promptly detect and resolve possible data capture errors.

[0045] Step S120: Analyze the characteristics of the structured data according to the building performance evaluation standard to obtain the attribute characteristics of the structured data.

[0046] The evaluation criteria are used to characterize the integrity or accuracy of the structured data, and the evaluation criteria include a single attribute and a comprehensive attribute. The single attribute is used to reflect a certain dimension of the building performance alone, and the comprehensive attribute is related to at least two single attributes that have an interactive relationship.

[0047] The server determines the data features that need to be analyzed based on predefined building performance evaluation criteria, which cover aspects such as building energy efficiency, structural stability, and indoor environmental quality.

[0048] The server uses advanced data analysis tools to extract features from the captured structured data. This process includes identifying and quantifying single attributes, such as the thermal insulation performance of a wall or the daylighting area of ​​a window, as well as constructing composite attributes that may involve the interaction of multiple single attributes, such as combining wall thermal insulation and window area to assess the heat loss of a building.

[0049] During the feature extraction process, the server is also responsible for standardizing these features to eliminate the impact of different data sources and different dimensions. Standardization ensures the consistency and comparability of feature values ​​during model training and prediction.

[0050] The server further uses statistical analysis and machine learning techniques to conduct in-depth analysis of the extracted features to identify key features that have a significant impact on building performance. These key features are then used to construct the model's training set, providing a basis for subsequent deep learning model training and prediction.

[0051] Step S130: creating a benchmark sample set of the building performance according to a preset trigger condition.

[0052] The benchmark sample set includes typical samples and atypical samples, the trigger condition includes a performance deviation determination criterion, the typical sample does not trigger the performance deviation determination criterion, and the atypical sample triggers the performance deviation determination criterion.

[0053] The server selects a set of benchmark samples that represent building performance based on preset trigger conditions, which may be based on performance deviation criteria, such as energy consumption exceeding expected ranges or structural stability not meeting design standards.

[0054] The server analyzes structured data through algorithms and identifies samples that meet the trigger conditions. These samples are divided into typical samples and atypical samples. Typical samples represent data with building performance within the expected range, while atypical samples indicate possible performance issues or abnormal conditions. The server classifies these samples and stores them as a benchmark sample set, providing key data for subsequent sample library construction and model training.

[0055] Step S140: constructing a sample library of the building performance according to the benchmark sample set of the building performance.

[0056] The server uses the benchmark sample set as a basis to build a comprehensive building performance sample library. This sample library not only contains samples of the current project, but may also integrate historical data and data from other similar projects to increase the diversity and representativeness of the samples. When building the sample library, the server ensures the balance and coverage of the samples to support the generalization ability of the deep learning model.

[0057] Step S150, based on the sample library of the building performance, use the deep learning model to analyze and predict the attribute characteristics to generate the predicted output of the structured data.

[0058] Among them, each attribute feature in the sample library includes a basic feature value and a derived feature value, the basic feature value is a numerical representation of a single attribute, and the derived feature value is a numerical representation of a comprehensive attribute.

[0059] The server loads a deep learning model, such as a convolutional neural network model, to analyze and predict the attribute features in the sample library. The input of the model includes basic feature values ​​and derived feature values, where the basic feature value is the numerical representation of a single attribute, and the derived feature value is the numerical representation of a comprehensive attribute.

[0060] The server first configures the deep learning model, including selecting the appropriate network architecture, activation function, loss function, etc. Then, the server uses the data in the sample library to train the model and optimizes the model parameters through the back propagation algorithm to minimize the prediction error.

[0061] After the model training is completed, the server uses the trained model to make predictions on new structured data and generate prediction outputs. These prediction outputs reflect potential trends and possible problems in building performance.

[0062] Step S160: if the prediction output indicates that there is a deviation in the integrity or accuracy of the structured data, a warning message is generated and issued.

[0063] The warning information indicates that the operating status of the BIM system is abnormal.

[0064] After generating the forecast output, the server further analyzes the output to determine the integrity and accuracy of the structured data. If the forecast results show that the data is biased, such as the energy consumption forecast is significantly different from the actual measurement, or the forecast result of the structural stability exceeds the safety threshold, the server will automatically generate a warning message.

[0065] These warning messages are published to relevant personnel or systems through the communication interface of the server, such as through email, SMS, mobile application push or system notification. The content of the warning message may include a detailed description of the deviation, the scope of impact, and recommended inspection or correction measures to ensure the smooth progress of the construction project and the safe operation of the building.

[0066] Based on the above steps, the real-time capture of structured data ensures the timeliness and completeness of data processing. Then, advanced data analysis tools are used to perform in-depth feature extraction and standardization of the data, which improves the availability of the data and the accuracy of the analysis. Through the preset trigger conditions, the server accurately screens out typical and atypical samples and builds a representative and diverse benchmark sample set. These sample sets further enrich the building performance sample library and provide rich data resources for the training and prediction of deep learning models. Using deep learning models such as convolutional neural networks, the server intelligently analyzes and predicts the attribute features in the sample library and generates predicted outputs of structured data, thereby using deep learning to improve the efficiency and accuracy of the BIM system in processing and analyzing large amounts of structured data.

[0067] In addition, the server can monitor the prediction output in real time. Once a deviation in data integrity or accuracy is found, a warning message is immediately generated and issued, realizing real-time monitoring of the BIM system operation status and abnormal warning. By obtaining the response status of the warning information, classifying the structured data and updating the sample library, this method realizes the continuous optimization and knowledge accumulation of the deep learning model, and improves the generalization ability and prediction accuracy of the model.

[0068] In a possible implementation manner, analyzing the characteristics of the structured data according to the building performance evaluation standard to obtain the attribute characteristics of the structured data includes:

[0069] According to the building performance evaluation standard, obtain energy consumption data and structural stability data that affect building performance;

[0070] Extracting single attribute features and comprehensive attribute features of the structured data according to the energy consumption data and the structural stability data;

[0071] Performing standardization processing on the single attribute feature and the comprehensive attribute feature to obtain standardized features of the structured data;

[0072] The attribute features of the structured data are obtained according to the standardized features.

[0073] In this embodiment, the server first communicates with the API interface of the BIM system to request and receive the energy consumption data and structural stability data of the building. The energy consumption data may include historical records and real-time data of the consumption of electricity, water, gas, etc., while the structural stability data may involve parameters such as stress, strain and displacement of building components. The server uses an efficient data parsing module to convert these data from the format of the BIM system to a format suitable for further analysis.

[0074] The server uses a customized algorithm to extract single attribute features and comprehensive attribute features based on energy consumption data and structural stability data. Single attribute features may include the insulation performance of the wall, the thermal conductivity coefficient of the window, etc., while comprehensive attribute features may be calculated from multiple single attribute features, for example, the overall heat loss rate of the building calculated by combining the insulation performance of the wall and the thermal conductivity coefficient of the window.

[0075] To ensure consistency and comparability of different features in model training, the server normalizes the extracted features. This may include methods such as min-max normalization, Z-score normalization, or decimal scaling to transform feature values ​​into a uniform range, such as [0,1] or [-1,1]. After normalization, the server obtains standardized features of structured data. These features can now be used for deep learning model training and prediction to evaluate various aspects of building performance.

[0076] In a possible implementation, the method further includes:

[0077] Obtaining a response status of the warning information, where the response status is used to indicate whether the warning information is ignored;

[0078] Based on the response status, classify the structured data corresponding to the warning information;

[0079] Based on the classified structured data, generating classification samples;

[0080] The classified samples are added to the sample library of the building performance evaluation standard.

[0081] In a possible implementation manner, adding the classified samples to the sample library of the building performance evaluation standard includes:

[0082] According to a preset update frequency, the classification samples generated within the preset update frequency are updated to the sample library of the building performance evaluation standard.

[0083] In a possible implementation, the classifying the real-time data corresponding to the warning information based on the response status includes:

[0084] When the response status of the warning information is ignored, the structured data is classified as normal; when the response status of the warning information is responded, the structured data is classified as abnormal.

[0085] In this embodiment, the server monitors the alert information generated by the deep learning model in real time and tracks the response status of this information. The response status may be marked by the building manager through the user interface, or determined by the automation system according to preset rules. Once the response status of the alert information is determined, the server classifies the corresponding real-time data. If the alert message is ignored, the server marks the associated structured data as a "regular" category, which means that there is no abnormal situation that requires immediate attention. On the contrary, if the alert message is responded to, the server marks the data as an "abnormal" category, which may trigger further analysis or immediate action. The server can use automated scripts to handle data classification tasks. These scripts can automatically perform classification operations based on preset logic and conditions. For example, if an alert message is not responded to within a specified time, the server may automatically classify it as "abnormal".

[0086] For example, in a large commercial building, the server monitors energy consumption warning information generated by a deep learning model. Building managers view these warnings through a user interface and determine whether a response is needed based on the actual situation. For example, if an alert message about abnormally high energy consumption is not responded to within the specified time, the server automatically classifies the relevant energy consumption data as "abnormal". This operation is based on preset logic, that is, alerts that are not responded to within the specified time are considered abnormal situations that require further attention. The server runs an automated script to automatically send all energy consumption data classified as "abnormal" to building managers for further analysis. At the same time, these data are also added to the sample library for future model training and prediction.

[0087] In a possible implementation, the deep learning model includes a convolutional neural network model; the sample library based on the building performance uses the deep learning model to analyze and predict the attribute characteristics to generate the prediction output of the structured data, including:

[0088] Obtain the trained convolutional neural network model;

[0089] The attribute features are input into the classification decision function of the convolutional neural network model to obtain the predicted output of the structured data.

[0090] In a possible implementation, the convolutional neural network model is trained by the following steps:

[0091] Based on the sample library of the building performance evaluation standard, the objective function of the convolutional neural network model is optimized to obtain the weight coefficient of each sample in the sample library; wherein the activation function of the convolutional neural network model adopts a rectified linear unit function;

[0092] Based on the sample library and the weight coefficient of each of the samples, a threshold of the classification decision function is determined; and the weight coefficient of each of the samples in the sample library and the threshold are determined as model parameters of the convolutional neural network model.

[0093] In the above embodiments, the artificial intelligence-based BIM system information processing system for executing the above method embodiments has at least one processor, a control module (chip set) coupled to at least one of the (at least one) processors, a memory coupled to the control module, a non-volatile memory (NVM) / storage device coupled to the control module, at least one input / output device coupled to the control module, and a network interface coupled to the control module.

[0094] The processor may include at least one single-core or multi-core processor, and the processor may include any combination of general-purpose processors or special-purpose processors (such as graphics processors, application processors, baseband processors, etc.). For some alternative implementations, the BIM system information processing system based on artificial intelligence can be used as the BIM system information processing system device based on artificial intelligence such as the gateway described in the embodiments of the present application.

[0095] For some alternative embodiments, the artificial intelligence-based BIM system information processing system may include at least one computer-readable medium (e.g., a memory or NVM / storage device) having instructions and at least one processor integrated with the at least one computer-readable medium and configured to execute instructions to implement a module to perform the actions described in the present disclosure.

[0096] For one embodiment, the control module may include any suitable interface controller to provide any suitable interface to at least one of the processor(s) and / or any suitable device or component in communication with the control module.

[0097] The control module may include a memory controller module to provide an interface to the memory. The memory controller module may be a hardware module, a software module, and / or a firmware module.

[0098] The memory may be used, for example, to load and store data and / or instructions for an artificial intelligence-based BIM system information processing system. For one embodiment, the memory may include any suitable volatile memory, for example, a suitable DRAM.

[0099] For one embodiment, the control module may include at least one input / output controller to provide an interface to the NVM / storage device and (at least one) input / output device.

[0100] For example, the NVM / storage device may be used to store data and / or instructions. The NVM / storage device may include any suitable non-volatile memory (e.g., flash memory) and / or may include any suitable (at least one) non-volatile storage device (e.g., at least one hard disk drive (HDD), at least one compact disk (CD) drive, and / or at least one digital versatile disk (DVD) drive).

[0101] The NVM / storage device may include storage resources that are physically part of the device on which the artificial intelligence-based BIM system information processing system is installed, or it may be accessible to the device without being part of the device. For example, the NVM / storage device may be accessed via (at least one) input / output device based on a network.

[0102] (At least one) input / output device may provide an interface for the artificial intelligence-based BIM system information processing system to communicate with any other appropriate device, and the input / output device may include a communication component, a pinyin component, a sensor component, etc. The network interface may provide an interface for the artificial intelligence-based BIM system information processing system to communicate based on at least one network, and the artificial intelligence-based BIM system information processing system may wirelessly communicate with at least one component of a wireless network based on any standard and / or protocol of at least one wireless network standard and / or protocol, such as accessing a wireless network based on a communication standard.

[0103] For one embodiment, at least one of the (at least one) processor may be loaded together with the logic of at least one controller of the control module (e.g., a memory controller module). For one embodiment, at least one of the (at least one) processor may be loaded together with the logic of at least one controller of the control module to form a system level load. For one embodiment, at least one of the (at least one) processor may be integrated on the same die with the logic of at least one controller of the control module. For one embodiment, at least one of the (at least one) processor may be integrated on the same die with the logic of at least one controller of the control module to form a system on chip (SoC).

[0104] The embodiments of the present application are introduced in detail above. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method and core idea of ​​the present application. At the same time, for general technical personnel in this field, according to the idea of ​​the present application, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

[0105] An embodiment of the present invention discloses a computer-readable storage medium storing a computer program for electronic data exchange, wherein the computer program enables a computer to execute the steps of the artificial intelligence-based BIM system information processing method described in the aforementioned embodiment.

[0106] An embodiment of the present invention discloses a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to enable a computer to execute the steps in the artificial intelligence-based BIM system information processing method described in the aforementioned embodiment.

[0107] The device embodiments described above are only illustrative, wherein the modules described as separate components may or may not be physically separated, and the components displayed as modules may or may not be physical modules, that is, they may be located in one place, or they may be distributed on multiple network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Those of ordinary skill in the art may understand and implement it without creative work.

[0108] Through the specific description of the above embodiments, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on such an understanding, the above technical solution can be essentially or partly contributed to the prior art in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, and the storage medium includes a read-only memory (ROM), a random access memory (RAM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), a one-time programmable read-only memory (OTPROM), an electronically erasable rewritable read-only memory (EEPROM), a compact disc (CD-ROM) or other optical disc storage, magnetic disk storage, magnetic tape storage, or any other medium that can be used to be computer-readable with or store data.

[0109] Finally, it should be noted that what is disclosed above is only a preferred embodiment of the present invention, which is only used to illustrate the technical solution of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, it should be understood by those skilled in the art that the technical solutions described in the aforementioned embodiments can still be modified, or some of the technical features therein can be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A BIM system information processing method based on artificial intelligence, characterized in that: include: Capturing structured data of the BIM system; Analyzing the characteristics of the structured data according to the building performance evaluation standard to obtain the attribute characteristics of the structured data; wherein the evaluation standard is used to characterize the integrity or accuracy of the structured data, and the evaluation standard includes a single attribute and a comprehensive attribute, the single attribute is used to reflect a certain dimension of the building performance alone, and the comprehensive attribute is related to at least two single attributes that have an interactive relationship; According to a preset trigger condition, a benchmark sample set of the building performance is created; wherein the benchmark sample set includes typical samples and atypical samples, and the trigger condition includes a performance deviation determination criterion, the typical sample does not trigger the performance deviation determination criterion, and the atypical sample triggers the performance deviation determination criterion; Constructing a sample library of the building performance according to the benchmark sample set of the building performance; Based on the sample library of the building performance, the attribute characteristics are analyzed and predicted using a deep learning model to generate a prediction output of the structured data; wherein each attribute characteristic in the sample library includes a basic characteristic value and a derived characteristic value, the basic characteristic value is a numerical representation of a single attribute, and the derived characteristic value is a numerical representation of a comprehensive attribute; If the prediction output indicates that there is a deviation in the integrity or accuracy of the structured data, a warning message is generated and issued, and the warning message indicates that the operating status of the BIM system is abnormal.

2. The BIM system information processing method based on artificial intelligence according to claim 1 is characterized in that: Analyzing the characteristics of the structured data according to the building performance evaluation standard to obtain the attribute characteristics of the structured data includes: According to the building performance evaluation standard, obtain energy consumption data and structural stability data that affect building performance; Extracting single attribute features and comprehensive attribute features of the structured data according to the energy consumption data and the structural stability data; Performing standardization processing on the single attribute feature and the comprehensive attribute feature to obtain standardized features of the structured data; The attribute features of the structured data are obtained according to the standardized features.

3. The BIM system information processing method based on artificial intelligence according to claim 2 is characterized in that: The method further comprises: Obtaining a response status of the warning information, where the response status is used to indicate whether the warning information is ignored; Based on the response status, classify the structured data corresponding to the warning information; Based on the classified structured data, generating classification samples; The classified samples are added to the sample library of the building performance evaluation standard.

4. The BIM system information processing method based on artificial intelligence according to claim 3 is characterized in that: The step of adding the classified samples to the sample library of the building performance evaluation standard comprises: According to a preset update frequency, the classification samples generated within the preset update frequency are updated to the sample library of the building performance evaluation standard.

5. The BIM system information processing method based on artificial intelligence according to claim 4 is characterized in that: The classifying the real-time data corresponding to the warning information based on the response status includes: When the response status of the warning information is ignored, the structured data is classified as normal; when the response status of the warning information is responded, the structured data is classified as abnormal.

6. The BIM system information processing method based on artificial intelligence according to any one of claims 1 to 5, characterized in that: The deep learning model includes a convolutional neural network model; the sample library based on the building performance uses the deep learning model to analyze and predict the attribute characteristics to generate the prediction output of the structured data, including: Obtain the trained convolutional neural network model; The attribute features are input into the classification decision function of the convolutional neural network model to obtain the predicted output of the structured data.

7. The BIM system information processing method based on artificial intelligence according to claim 6 is characterized in that: The convolutional neural network model is trained by the following steps: Based on the sample library of the building performance evaluation standard, the objective function of the convolutional neural network model is optimized to obtain the weight coefficient of each sample in the sample library; wherein the activation function of the convolutional neural network model adopts a rectified linear unit function; Based on the sample library and the weight coefficient of each of the samples, a threshold of the classification decision function is determined; and the weight coefficient of each of the samples in the sample library and the threshold are determined as model parameters of the convolutional neural network model.

8. A BIM system information processing system based on artificial intelligence, characterized in that: It includes a processor and a computer-readable storage medium, wherein the computer-readable storage medium stores machine-executable instructions, and when the machine-executable instructions are executed by a computer, the artificial intelligence-based BIM system information processing method described in any one of claims 1 to 7 is implemented.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores machine-executable instructions, and when the machine-executable instructions are executed by a computer, the artificial intelligence-based BIM system information processing method described in any one of claims 1 to 7 is implemented.

10. 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 7 when being executed by a processor.

Images