Structural safety monitoring method, device, medium and equipment based on artificial intelligence

Abstract

The present invention proposes a structural safety monitoring method, device, medium and equipment based on artificial intelligence, which are applied to a client and a server. The server obtains data to be analyzed based on structural safety monitoring of a building sent by at least one client in real time; parses the data to be analyzed to obtain first data to be analyzed based on location features and second data to be analyzed based on early warning data; constructs a spatial coordinate system based on the first data to be analyzed, generates a BIM sub-model to be matched based on the data to be analyzed, and matches it with a pre-constructed BIM model. If a BIM sub-model exists, the BIM sub-model data is retrieved; the second data to be analyzed is matched with the BIM sub-model data to determine whether there is an abnormality. If so, an abnormal early warning message is sent to at least one client. The combination of improved BIM technology and artificial intelligence technology achieves high efficiency and accuracy in safety monitoring of building structures.

Description

Technical Field

[0001] The present invention relates to the field of construction engineering safety technology, and in particular to an artificial intelligence-based structural safety monitoring method, device, medium and equipment. Background Art

[0002] In recent years, with the continuous development of engineering technology, more and more building structure manufacturing technologies have gradually transformed and upgraded to intelligent manufacturing, thereby gradually transforming the traditional design-construction-operation and maintenance monitoring model into a new model of design-virtual-reality interaction-intelligent manufacturing-intelligent monitoring.

[0003] Artificial intelligence technology has been introduced in the field of intelligent manufacturing to assist in the intelligent management of building structures. For example, the invention patent with publication number CN118069469B discloses a construction engineering safety monitoring method and system based on artificial intelligence. It mainly detects mobile targets by introducing the YOLOv5 model based on the attention mechanism. It mainly detects human intrusion into dangerous areas. Although this monitoring mode improves the detection ability of the target detection model for relatively small target humans, it does not combine monitoring of the building structure itself during the detection process. This means that although artificial intelligence technology is used, efficient monitoring of the building structure itself is not achieved. Another example is the invention patent with publication number CN118800023A, which also discloses a building safety monitoring method and system based on artificial intelligence. It specifically obtains different data structures according to structural monitoring data and judges whether there are differences in combination with the BIM model, so as to judge whether there are safety hazards in the structure. This monitoring scheme combining artificial intelligence and BIM technology only compares and analyzes whether there are differences in the directly obtained data in this technical scheme. However, in fact, the introduction of BIM technology makes data analysis more complicated for large structural models, and the operation is also more troublesome. There are still large technical barriers to the monitoring of large-scale building structures.

[0004] Therefore, how to improve the monitoring efficiency of building structures by introducing artificial intelligence technology and combining it with BIM technology has become a technical problem that the present invention needs to solve. How to effectively improve the lightweight operation of BIM and combine it with artificial intelligence technology to realize intelligent monitoring of building structures has become an important content of the present invention. Summary of the invention

[0005] In order to solve the above technical problems, the present invention proposes a structural safety monitoring method, device, medium and equipment based on artificial intelligence. Combining artificial intelligence technology with BIM technology, on the one hand, using improved BIM technology to split the model makes BIM lighter, and on the other hand, using artificial intelligence-based data intelligent extraction, analysis and processing to achieve more efficient and accurate structural safety monitoring of buildings.

[0006] In a first aspect, the present invention proposes a structural safety monitoring method based on artificial intelligence, which is applied to a client and a server and specifically includes the following steps:

[0007] The server obtains in real time the data to be analyzed based on the structural safety monitoring of the building sent by at least one client;

[0008] Parsing the data to be analyzed to obtain first data to be analyzed based on the location feature and second data to be analyzed based on the early warning data;

[0009] Constructing a spatial coordinate system according to the first data to be analyzed, generating a BIM sub-model to be matched based on the data to be analyzed, and matching it with a pre-constructed BIM model; if a BIM sub-model exists, retrieving the BIM sub-model data;

[0010] The second data to be analyzed is matched with the BIM sub-model data to determine whether an abnormality exists, and if so, an abnormal warning message is sent to at least one client.

[0011] As a further improvement of the present invention, the step of the server acquiring in real time the data to be analyzed based on the structural safety monitoring of the building sent by at least one client includes the step of pre-building a BIM model, specifically:

[0012] The client generates a BIM meta-model based on different building structure data and sends it to the server;

[0013] After receiving the BIM metamodel sent by at least one client, the server generates a BIM metamodel thread pool corresponding to the client, and performs reconstruction in the BIM metamodel thread pool to generate a BIM main model and a BIM backup model;

[0014] The BIM backup model is split into multiple BIM sub-models, each of which includes a spatial coordinate system generated according to the position data of the building's structure in the BIM meta-model, and the BIM model is constructed based on the thread relationship between the BIM main model and the multiple BIM sub-models.

[0015] As a further improvement of the present invention, the server also includes a step of constructing an early warning data model before the step of obtaining in real time the data to be analyzed based on structural safety monitoring of the building sent by at least one client. The early warning data model includes an early warning data monitoring model generated based on the training results of historical early warning data and an early warning data diagnosis model analyzed based on the output results of the early warning data monitoring model.

[0016] As a further improvement of the present invention, the step of the server end acquiring in real time the data to be analyzed based on structural safety monitoring of a building sent by at least one client also includes that the client collects a structural safety monitoring data set based on the building, performs feature extraction on the data set, classifies data subsets of the same structure, and packages them with one or more data subsets of different structures based on the client identifier to generate data to be analyzed, wherein each data in the safety monitoring data set carries the location data and warning data of the structure of the building where the data is located.

[0017] As a further improvement of the present invention, a spatial coordinate system is constructed according to the first data to be analyzed, a BIM sub-model to be matched based on the data to be analyzed is generated, and the sub-model is matched with the pre-constructed BIM model. If a BIM sub-model exists, the step of retrieving the BIM sub-model data includes: obtaining the position feature data of the first data to be analyzed, constructing a spatial coordinate system based on the position feature data to generate a BIM sub-model to be matched, matching the BIM sub-model to be matched with the pre-constructed BIM model, judging whether there is a matching BIM sub-model in the BIM model, and if so, retrieving the matching BIM sub-model, and extracting image features from the BIM main model according to the retrieved BIM sub-model to generate BIM sub-model data, wherein the image feature is a three-dimensional image or a two-dimensional image converted from a three-dimensional image.

[0018] As a further improvement of the present invention, the step of extracting image features from the BIM main model according to the retrieved BIM sub-model to generate BIM sub-model data also includes: matching the retrieved BIM sub-model in the early warning data diagnostic model, determining whether there is a BIM sub-model associated with the retrieved BIM sub-model, and if so, generating a to-be-matched BIM sub-model based on the associated BIM sub-model and the retrieved BIM sub-model, and matching the to-be-matched BIM sub-model in the BIM main model to extract image features and generate BIM sub-model data.

[0019] As a further improvement of the present invention, the step of matching the second data to be analyzed with the BIM sub-model data to determine whether an abnormality exists, and if so, sending an abnormal warning message to at least one client comprises:

[0020] The second data to be analyzed is subjected to image segmentation and matching with the BIM sub-model data, and image feature scanning and matching is performed to determine whether there is an abnormality. If no abnormality exists, no processing is performed. If an abnormality exists, the abnormal sub-image is extracted, and the sub-image is input into the early warning monitoring model for matching to determine whether there is an abnormal matching result. If so, an abnormal early warning message is sent to the client. If not, the matched result is sent to the early warning data diagnosis model, and the early warning data diagnosis model performs abnormal diagnosis and outputs a diagnosis result. The early warning data diagnosis model sends the diagnosis result to the early warning data monitoring model and stores it with the corresponding BIM sub-model, and at the same time sends the diagnosis result to the client, wherein the early warning data diagnosis model establishes an association relationship between two or more BIM sub-models according to the diagnosis result and stores it.

[0021] In a second aspect, the present invention also proposes a device for a structural safety monitoring method based on artificial intelligence, which is applied to a client and a server.

[0022] The server includes:

[0023] An acquisition module, used for acquiring in real time the data to be analyzed based on structural safety monitoring of a building sent by at least one client;

[0024] A parsing module, used for parsing the data to be analyzed to obtain first data to be analyzed based on location features and second data to be analyzed based on early warning data;

[0025] A calling module, used for constructing a spatial coordinate system according to the first data to be analyzed, generating a BIM sub-model to be matched based on the data to be analyzed, and matching it with a pre-built BIM model, and if a BIM sub-model exists, calling the BIM sub-model data;

[0026] The processing module is used to match the second data to be analyzed with the BIM sub-model data to determine whether there is an abnormality, and if so, send an abnormal warning message to at least one client.

[0027] In a third aspect, the present invention proposes an electronic device, comprising a processor and a memory storing a computer program, wherein when the processor executes the computer program, the steps of the artificial intelligence-based structural safety monitoring method as described in the first aspect are implemented.

[0028] In a fourth aspect, the present invention proposes a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the artificial intelligence-based structural safety monitoring method as described in the first aspect.

[0029] The present invention proposes a method, device, medium and equipment for structural safety monitoring based on artificial intelligence, which are specifically applied to a client and a server. The server obtains data to be analyzed based on structural safety monitoring of a building sent by at least one client in real time; parses the data to be analyzed to obtain first data to be analyzed based on location features and second data to be analyzed based on early warning data; constructs a spatial coordinate system based on the first data to be analyzed, generates a BIM sub-model to be matched based on the data to be analyzed, and matches it with a pre-constructed BIM model. If a BIM sub-model exists, the BIM sub-model data is retrieved; the second data to be analyzed is matched with the BIM sub-model data to determine whether there is an abnormality. If so, an abnormal early warning message is sent to at least one client. The combination of improved BIM technology and artificial intelligence technology achieves high efficiency and accuracy in safety monitoring of building structures. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] Figure 1 This is a diagram showing an application scenario of the artificial intelligence-based structural safety monitoring method proposed in the present invention.

[0031] Figure 2 This is a flow chart of the artificial intelligence-based structural safety monitoring method proposed in the present invention.

[0032] Figure 3 Framework diagram of the artificial intelligence-based structural safety monitoring device proposed for the invention.

[0033] Figure 4 Schematic diagram of an electronic device. DETAILED DESCRIPTION

[0034] For ease of understanding, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments 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.

[0035] The terms used herein are only used for the purpose of describing specific example embodiments and are not restrictive. For example, unless the context clearly indicates otherwise, as used herein, the singular forms "a", "an" and "the" may also include plural forms. When used in this specification, the terms "include", "comprise" and / or "contain" mean that the associated integers, steps, operations, elements and / or components exist, but do not exclude the existence of one or more other features, integers, steps, operations, elements, components and / or groups or that other features, integers, steps, operations, elements, components and / or groups may be added in the system / method.

[0036] These and other features of the present specification, as well as the operation and function of the related elements of the structure, and the economy of combination and manufacture of the parts can be significantly improved in view of the following description. Reference is made to the accompanying drawings, all of which form a part of this specification. However, it should be clearly understood that the drawings are for illustration and description purposes only and are not intended to limit the scope of this specification. It should also be understood that the drawings are not drawn to scale.

[0037] The flowcharts used in this specification illustrate the operations implemented by the system according to some embodiments in this specification. It should be clearly understood that the operations of the flowcharts may not be implemented in sequence. On the contrary, the operations may be implemented in reverse order or simultaneously. In addition, one or more other operations may be added to the flowchart. One or more operations may be removed from the flowchart.

[0038] Figure 1 The following figure shows an example of an application scenario of the artificial intelligence-based structural safety monitoring method proposed in the present invention. Figure 1 As shown, the artificial intelligence-based structural safety monitoring method proposed in the present invention is applied to a client and a server, wherein the client is used to monitor the structures of different buildings, obtain relevant data, and interact with the server.

[0039] like Figure 1 As shown, the application scenario of the safety monitoring method of the present invention can realize data collection by deploying sensor networks in different building structures. In practice, the safety monitoring of the structure can include the analysis of abnormal data and can also include the analysis and processing of image data. In the prior art, there are many cases of data early warning by acquiring data (identity data of construction personnel, specific monitoring data of the structure, etc.), for example, by setting a threshold value, analyzing whether an abnormality occurs by comparing the collected data with the set threshold value. No improvement is made in this embodiment. The purpose of this embodiment is not limited to monitoring by comparing the threshold value of the actual digital value, but also includes analyzing the acquired image data. The image data can be a video or photo taken in real time. By analyzing the image, it is determined whether there is an abnormality. Therefore, in this embodiment, multiple nodes in the sensor network can be set as image acquisition devices.

[0040] In this embodiment, there can be one or more clients, and the same client can monitor one or more structures, and different clients can monitor the same or different structures. Therefore, when different clients upload image data of the same structure at the same time, if they are the same, only one image is analyzed and the result is sent to the two clients, thereby reducing the processing content of the server. In addition, each client is provided with a unique identifier, and the identifier is set so that the server can perform purposeful addressing. At the same time, it should be noted that the client can actually be a laptop, desktop, mobile phone or tablet, and this embodiment does not make specific restrictions, as long as it can perform communication interaction and data processing.

[0041] In this embodiment, the server can be set as one server, or multiple servers can be set to process data for client requests in different regions. In practice, large-volume structures may be deployed in different locations. Through multiple servers, processing efficiency can be effectively improved and communication loss can be reduced. It should be noted that the server set by the server of this embodiment can also be considered to be composed of multiple functional modules, each of which performs different functions, such as the acquisition module for data acquisition, the parsing module for data parsing, the processing module for data processing, etc. The server of this embodiment is also provided with a BIM model, an early warning data monitoring model, and an early warning data diagnosis model. In fact, a database can also be included to store data, but as a general data storage component, the present invention does not make specific limitations. It can be understood that the BIM model, the early warning data monitoring model, and the early warning data diagnosis model can all have a built-in sub-database, or a large database can be used for data storage and call. At the same time, a thread relationship is established between the BIM model, the early warning data monitoring model, and the early warning data diagnosis model to call the required data, thereby effectively improving the efficiency of data analysis and processing.

[0042] Through the above description, the specific application scenarios of the present invention are basically explained. The structural safety monitoring of buildings is realized by constructing the interaction between the server based on BIM model, early warning data monitoring model and early warning data diagnosis model and the client based on data source acquisition.

[0043] Figure 2 The flowchart of the structural safety monitoring method based on artificial intelligence proposed by the present invention is shown in FIG. Figure 2 As shown, the artificial intelligence-based structural safety monitoring method proposed in the present invention includes the following steps:

[0044] S201. The server obtains in real time the data to be analyzed based on structural safety monitoring of the building sent by at least one client.

[0045] In this embodiment, as described above, an interactive scenario between the client and the server is constructed, and structural safety monitoring of the building is performed in this scenario. In order to achieve the purpose of the present invention, in this embodiment, before the server obtains in real time the data to be analyzed based on the structural safety monitoring of the building sent by at least one client, it is necessary to perform the steps of constructing a BIM model and constructing an early warning data model, which are specifically explained below.

[0046] In this embodiment, the specific steps of constructing the BIM model include:

[0047] The client generates a BIM metamodel based on different building structure data and sends it to the server. In this embodiment, it is necessary to first establish an original BIM model, which is set as a BIM metamodel here. The BIM metamodel is established based on the drawing information of different buildings that the client has obtained. The establishment of the BIM metamodel is established by the existing technology, which is not specifically limited here. Therefore, the establishment process of the BIM metamodel is not repeated.

[0048] After receiving the BIM metamodel sent by at least one client, the server generates a BIM metamodel thread pool corresponding to the client, and performs reconstruction in the BIM metamodel thread pool to generate a BIM master model and a BIM backup model. In this embodiment, in order to achieve a lighter BIM model, a BIM master model and a BIM backup model are set, and the two are exactly the same when setting, and a thread correspondence is established.

[0049] The BIM preparation model is split into multiple BIM sub-models, each BIM sub-model generates a spatial coordinate system according to the position data of the building structure in the BIM meta-model, and the BIM model is constructed based on the thread relationship between the BIM main model and the multiple BIM sub-models. In this embodiment, the BIM main model is not changed, and the BIM preparation model is split into multiple BIM sub-models. This can be done based on the disassembly diagram of a certain building structure. For example, a BIM model of a bridge is split into a BIM sub-model of the bridge head and a BIM sub-model of the bridge body. Of course, it can also be split according to actual needs. The split BIM sub-model only retains the spatial feature data, such as the spatial coordinate system data. Since the split BIM sub-models are smaller than the original drawings, the spatial coordinate system data is relatively small, which means that each BIM sub-model stores the spatial position data without the need for more complex image data, making BIM more lightweight. Based on this, the BIM model includes a BIM main model and multiple BIM sub-models corresponding to the BIM main model. In practice, the BIM model can also set up multiple BIM main models as needed, and each main model corresponds to a BIM sub-model. In addition, each BIM sub-model establishes a thread relationship with the BIM main model for easy calling.

[0050] In this embodiment, before the step of obtaining in real time the data to be analyzed based on the structural safety monitoring of the building sent by at least one client, the server also includes the step of constructing an early warning data model, wherein the early warning data model includes an early warning data monitoring model generated based on the training results of historical early warning data and an early warning data diagnosis model analyzed based on the output results of the early warning data monitoring model. It should be noted that in this embodiment, the reason why the early warning data model is set up as two parts is that when the early warning data monitoring model cannot judge the result well when monitoring based on historical data, it is necessary to use the diagnosis model. In fact, the working process of the diagnosis model can include the information interaction process with external experts. The structural safety in the construction project cannot be completely solved by identifying it through historical data. It is also necessary to interact with experts in the expert database to obtain the diagnosis result, thereby effectively improving the accuracy of the monitoring result.

[0051] When the client sends the data to be analyzed to the server, the client collects a structural safety monitoring data set based on the building, extracts features from the data set, classifies the data subsets of the same structure, and generates the data to be analyzed after packaging with one or more data subsets of different structures based on the client identifier, wherein each data in the safety monitoring data set carries the location data and early warning data of the structure of the building where the data is located. It should be noted that, as described above, the client of the present invention may be one or more, and the monitoring of the same structure may be carried out by different clients at the same time, or different clients may monitor different parts of the same structure. Therefore, when these monitoring data form a data set, they need to be analyzed. A client classifies the data of different parts of the same structure, because the data collection process carried out simultaneously may also include data of other structures obtained by the same client. Therefore, when sending data, the data subsets of the same structure are classified, and the data subsets of different structures are packaged according to the structure identifier to generate the data to be analyzed. When the server parses the data to be analyzed of different clients, the data sent by different clients that may be based on the same structure can be directly extracted and analyzed and processed, without the need to process each data, thereby improving the processing efficiency.

[0052] S202. Parse the data to be analyzed to obtain first data to be analyzed based on location features and second data to be analyzed based on early warning data.

[0053] In this embodiment, each data to be analyzed will carry location feature data. Since a BIM metamodel has been established for each structure in reality, when the client collects data to generate data to be analyzed, it is necessary to match the spatial coordinate data of the collected data according to the metamodel established by the client to form location feature data and add it to the data to be analyzed. The warning data is the real-time data collected that needs to be judged whether it is abnormal.

[0054] S203. Construct a spatial coordinate system according to the first data to be analyzed, generate a BIM sub-model to be matched based on the data to be analyzed, and match it with a pre-constructed BIM model. If a BIM sub-model exists, retrieve the BIM sub-model data.

[0055] In this embodiment, the position feature data of the first data to be analyzed is obtained, a spatial coordinate system is constructed based on the position feature data to generate a BIM sub-model to be matched, the BIM sub-model to be matched is matched with a pre-constructed BIM model, and it is determined whether there is a matching BIM sub-model in the BIM model. If so, the matching BIM sub-model is retrieved, and image features are extracted from the BIM main model according to the retrieved BIM sub-model to generate BIM sub-model data, wherein the image feature is a three-dimensional image or a two-dimensional image converted from a three-dimensional image.

[0056] In this embodiment, after extracting the first data to be analyzed, the spatial coordinate system of the first data to be analyzed is constructed based on the position feature data and a BIM sub-model to be matched is generated, and the sub-model in the BIM model is matched. The BIM sub-model in the BIM model stores the spatial coordinate system data. Therefore, there are two ways to match. One is to directly match the data, for example, whether the data in the X direction, Y direction or Z direction are identical or contained, that is, the coordinate data of the sub-model to be matched exists in the coordinate data of a certain BIM sub-model, then the match is successful. The other is to match according to the constructed spatial coordinate system image. When the spatial coordinate system image constructed by the sub-model to be matched is in the spatial coordinate system image of a certain BIM sub-model, the match is considered to be successful. After the match is successful, the matched BIM sub-model is retrieved, and the image features corresponding to the coordinate system are matched in the BIM main model based on the thread relationship, and the image features of the part are intercepted to generate the BIM sub-model data, which can be either a three-dimensional image or a two-dimensional image converted from a three-dimensional image.

[0057] It should be noted that the step of extracting image features from the BIM main model according to the retrieved BIM sub-model to generate BIM sub-model data also includes: matching the retrieved BIM sub-model in the early warning data diagnostic model to determine whether there is a BIM sub-model associated with the retrieved BIM sub-model, and if so, generating a to-be-matched BIM sub-model according to the associated BIM sub-model and the retrieved BIM sub-model, and matching the to-be-matched BIM sub-model in the BIM main model to extract image features to generate BIM sub-model data. In the historical matching process, an anomaly based on a certain BIM sub-model will appear. According to the diagnosis result, the sub-model will be associated with an anomaly of the structural part corresponding to other sub-models. Therefore, when a certain matched BIM sub-model is abnormal, it is also necessary to retrieve the associated BIM sub-model identifier in the early warning data diagnostic model, and the thread of the associated BIM sub-model retrieves the image features of the BIM main model to analyze and determine whether there is an anomaly.

[0058] S204. Match the second data to be analyzed with the BIM sub-model data to determine whether there is an abnormality. If so, send an abnormal warning message to at least one client.

[0059] In this embodiment, the second data to be analyzed is subjected to image segmentation and matching with the BIM sub-model data, and image feature scanning and matching is performed to determine whether there is an abnormality. If no abnormality exists, no processing is performed. If an abnormality exists, the abnormal sub-image is extracted, and the sub-image is input into the early warning monitoring model for matching to determine whether there is an abnormal matching result. If so, an abnormal early warning message is sent to the client. If not, the matched result is sent to the early warning data diagnosis model, and the early warning data diagnosis model performs abnormal diagnosis and outputs a diagnosis result. The early warning data diagnosis model sends the diagnosis result to the early warning data monitoring model and stores it with the corresponding BIM sub-model, and at the same time sends the diagnosis result to the client, wherein the early warning data diagnosis model establishes an association relationship between two or more BIM sub-models according to the diagnosis result and stores it.

[0060] It should be noted that the second data to be analyzed is image data, but the abnormal part of the image is only a small part of the image. Therefore, the image can be segmented into several equal parts, or it can be segmented based on the structure in the image. After being segmented into several units, they are scanned unit by unit to determine the location of the unit where the abnormality is located. In addition, when the associated BIM sub-model is obtained, the server determines whether there is data of the structure corresponding to the associated BIM model from the received data to be analyzed. If so, it directly calls for analysis. If not, it sends a request message to the client to obtain the image data corresponding to the associated BIM model, and after receiving a response message based on the request, it parses the image data corresponding to the associated BIM model for analysis to determine whether it is abnormal. The judgment process is the same as above and will not be repeated.

[0061] Through the above content, the artificial intelligence-based structural safety monitoring method of the present invention effectively improves the efficiency and accuracy of structural safety monitoring.

[0062] In a third aspect, the present invention proposes a structural safety monitoring device based on artificial intelligence, such as Figure 3 As shown, the device includes: a client and a server, and the server includes:

[0063] An acquisition module, used for acquiring in real time the data to be analyzed based on structural safety monitoring of a building sent by at least one client;

[0064] A parsing module, used for parsing the data to be analyzed to obtain first data to be analyzed based on location features and second data to be analyzed based on early warning data;

[0065] A calling module, used for constructing a spatial coordinate system according to the first data to be analyzed, generating a BIM sub-model to be matched based on the data to be analyzed, and matching it with a pre-built BIM model, and if a BIM sub-model exists, calling the BIM sub-model data;

[0066] The processing module is used to match the second data to be analyzed with the BIM sub-model data to determine whether there is an abnormality, and if so, send an abnormal warning message to at least one client.

[0067] Figure 4 An example of a physical structure diagram of an electronic device is shown. Figure 4 As shown, the electronic device may include: a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus. The processor may call a computer program in the memory to execute the steps of the artificial intelligence-based structural safety monitoring method.

[0068] In addition, the logic instructions in the above-mentioned memory can be implemented in the form of software functional units and can be stored in a computer-readable storage medium when sold or used as an independent product. Based on this understanding, the technical solution of the present invention can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium, including several instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0069] On the other hand, an embodiment of the present application also provides a processor-readable storage medium, which stores a computer program, and the computer program is used to enable the processor to execute the steps of the artificial intelligence-based structural safety monitoring method provided in the above embodiments.

[0070] The processor-readable storage medium may be any available medium or data storage device that can be accessed by the processor, including but not limited to magnetic storage (e.g., floppy disks, hard disks, magnetic tapes, magneto-optical disks (MO), etc.), optical storage (e.g., CDs, DVDs, BDs, HVDs, etc.), and semiconductor storage (e.g., ROMs, EPROMs, EEPROMs, non-volatile memories (NANDFLASH), solid-state drives (SSDs), etc.).

[0071] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0072] Through the description of the above implementation methods, 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, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0073] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. 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 embodiments of the present invention.

Claims

1. A structural safety monitoring method based on artificial intelligence, characterized in that: The method is applied to the client and the server, and specifically comprises the following steps: The server obtains in real time the data to be analyzed based on the structural safety monitoring of the building sent by at least one client; Parsing the data to be analyzed to obtain first data to be analyzed based on the location feature and second data to be analyzed based on the early warning data; Constructing a spatial coordinate system according to the first data to be analyzed, generating a BIM sub-model to be matched based on the data to be analyzed, and matching it with a pre-constructed BIM model; if a BIM sub-model exists, retrieving the BIM sub-model data; Matching the second data to be analyzed with the BIM sub-model data to determine whether there is an abnormality, and if so, sending an abnormal warning message to at least one client; The step of pre-building a BIM model before the step of obtaining in real time the data to be analyzed based on the structural safety monitoring of the building sent by at least one client includes: The client generates a BIM meta-model based on different building structure data and sends it to the server; After receiving the BIM metamodel sent by at least one client, the server generates a BIM metamodel thread pool corresponding to the client, and performs reconstruction in the BIM metamodel thread pool to generate a BIM main model and a BIM backup model; Splitting the BIM backup model into multiple BIM sub-models, each BIM sub-model including a spatial coordinate system generated according to the position data of the structure of the building in the BIM meta-model, and generating a BIM model based on the thread relationship between the BIM main model and the multiple BIM sub-models; Before the step of obtaining the data to be analyzed based on the structural safety monitoring of the building sent by at least one client in real time, the server further includes: the step of constructing an early warning data model, wherein the early warning data model includes an early warning data monitoring model generated based on the training results of the historical early warning data and an early warning data diagnosis model analyzed based on the output results of the early warning data monitoring model; Among them, the step of the server end obtaining in real time the data to be analyzed based on the structural safety monitoring of the building sent by at least one client, also includes: the client collects the structural safety monitoring data set based on the building, and extracts features from the data set, classifies the data subsets with the same structure, and packages them with one or more data subsets with different structures based on the client identifier to generate the data to be analyzed, wherein each data in the safety monitoring data set carries the location data and warning data of the structure of the building where the data is located.

2. The artificial intelligence-based structural safety monitoring method according to claim 1 is characterized in that: The steps of constructing a spatial coordinate system according to the first data to be analyzed, generating a BIM sub-model to be matched based on the data to be analyzed, and matching the sub-model with the pre-constructed BIM model, and retrieving the BIM sub-model data if the BIM sub-model exists, include: obtaining position feature data of the first data to be analyzed, constructing a spatial coordinate system based on the position feature data to generate a BIM sub-model to be matched, matching the BIM sub-model to be matched with the pre-constructed BIM model, judging whether there is a matching BIM sub-model in the BIM model, and if so, retrieving the matching BIM sub-model, and extracting image features from the BIM main model according to the retrieved BIM sub-model to generate BIM sub-model data, wherein the image feature is a three-dimensional image or a two-dimensional image converted from a three-dimensional image.

3. The artificial intelligence-based structural safety monitoring method according to claim 2 is characterized in that: The step of extracting image features from the BIM main model according to the retrieved BIM sub-model to generate BIM sub-model data also includes: matching the retrieved BIM sub-model in the early warning data diagnosis model, determining whether there is a BIM sub-model associated with the retrieved BIM sub-model, and if so, generating a to-be-matched BIM sub-model according to the associated BIM sub-model and the retrieved BIM sub-model, and matching the to-be-matched BIM sub-model in the BIM main model to extract image features and generate BIM sub-model data.

4. The artificial intelligence-based structural safety monitoring method according to claim 3 is characterized in that: The step of matching the second data to be analyzed with the BIM sub-model data to determine whether an abnormality exists, and if so, sending an abnormal warning message to at least one client comprises: The second data to be analyzed is subjected to image segmentation and matching with the BIM sub-model data, and image feature scanning and matching is performed to determine whether there is an abnormality. If no abnormality exists, no processing is performed. If an abnormality exists, the abnormal sub-image is extracted, and the sub-image is input into the early warning monitoring model for matching to determine whether there is an abnormal matching result. If so, an abnormal early warning message is sent to the client. If not, the matched result is sent to the early warning data diagnosis model, and the early warning data diagnosis model performs abnormal diagnosis and outputs a diagnosis result. The early warning data diagnosis model sends the diagnosis result to the early warning data monitoring model and stores it with the corresponding BIM sub-model, and at the same time sends the diagnosis result to the client, wherein the early warning data diagnosis model establishes an association relationship between two or more BIM sub-models according to the diagnosis result and stores it.

5. A device for a structural safety monitoring method based on artificial intelligence, used to implement the structural safety monitoring method based on artificial intelligence according to any one of claims 1 to 4, characterized in that: The device is applied to the client and the server, The server includes: An acquisition module, used for acquiring in real time the data to be analyzed based on structural safety monitoring of a building sent by at least one client; A parsing module, used for parsing the data to be analyzed to obtain first data to be analyzed based on location features and second data to be analyzed based on early warning data; A calling module, used for constructing a spatial coordinate system according to the first data to be analyzed, generating a BIM sub-model to be matched based on the data to be analyzed, and matching it with a pre-built BIM model, and if a BIM sub-model exists, calling the BIM sub-model data; The processing module is used to match the second data to be analyzed with the BIM sub-model data to determine whether there is an abnormality, and if so, send an abnormal warning message to at least one client.

6. An electronic device comprising a processor and a memory storing a computer program, characterized in that: When the processor executes the computer program, the steps of the artificial intelligence-based structural safety monitoring method as described in any one of claims 1 to 4 are implemented.

7. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the artificial intelligence-based structural safety monitoring method as described in any one of claims 1 to 4 are implemented.

Images