Target damage assessment method and system, electronic equipment and storage medium

Abstract

The embodiments of the present application provide a target damage assessment method and system, electronic device, and storage medium, belonging to the field of artificial intelligence technology. The method includes: inputting first building sensor data into an initial damage assessment model to obtain first damage classification data and type classification probabilities, and training the initial damage assessment model based on the first damage classification data and type classification probabilities to obtain a first damage assessment model; then inputting second building sensor data related to the target building into the first damage assessment model to obtain second damage classification data, adjusting the parameters of the first damage assessment model based on the second damage classification data to obtain a second damage assessment model, and finally using the second damage assessment model to perform damage assessment on the target building. Therefore, the embodiments of the present application can improve the generalization capability, application efficiency, and accuracy of the target damage assessment method across scenarios and target types.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence technology, and in particular to a target damage assessment method and system, electronic equipment, and storage medium. Background Art

[0002] Target damage assessment methods aim to analyze and evaluate the impact of physical damage on targets. They can be applied to assessing the extent of damage to buildings, such as houses and bridges, after natural disasters, vandalism, and other physical damage. They can also be applied to assessing a building's resilience to damage. However, most existing target damage assessment methods use target damage assessment models. These models are typically pre-trained on building types such as bungalows, bridges, and high-rises. This results in high accuracy only when applied to the trained building types. If the target damage assessment model is applied to new building types for which it has not been trained, the target damage assessment method's generalization ability across scenarios and target types is poor, resulting in low damage assessment accuracy for new building types. To improve damage assessment accuracy for new building types, the target damage assessment model must be retrained based on the new building type, making the cross-scenario and cross-target application of the target damage assessment method inefficient. Summary of the Invention

[0003] The main purpose of the embodiments of the present application is to propose a target damage assessment method and system, electronic equipment and storage medium, aiming to improve the generalization capability of the target damage assessment method across scenarios and target types, thereby improving the damage assessment accuracy and application efficiency of the target damage assessment method on different types of buildings.

[0004] To achieve the above objectives, a first aspect of an embodiment of the present application provides a target damage assessment method, the method comprising:

[0005] Obtaining a first sample from a preset first sample set; wherein the first sample set includes at least two first samples, the first sample includes first building sensor data and a first building type of a sample building, and the first building types of the two first samples are different;

[0006] Inputting the first building sensor data into a preset initial damage assessment model for damage assessment to obtain first damage assessment data; wherein the first damage assessment data includes: first damage classification data and type classification probability;

[0007] Performing loss construction based on the first damage classification data to obtain a first damage classification loss function, and performing loss construction based on the type classification probabilities of the at least two sample buildings and the first building type to obtain a building type adversarial loss function; wherein the building type adversarial loss function is used to ensure that the type classification probability distributions of the at least two sample buildings of different building types are close to the same;

[0008] training the initial damage assessment model according to the first damage classification loss function and the building type adversarial loss function to obtain a first damage assessment model;

[0009] Acquire a second sample related to the target building from a preset second sample set; wherein the second sample includes second building sensor data of the target building;

[0010] inputting the second building sensor data into the first damage assessment model to perform damage assessment to obtain second damage assessment data; wherein the second damage assessment data includes second damage classification data;

[0011] Performing loss construction based on the second damage classification data to obtain a second damage classification loss function;

[0012] The target damage classifier of the first damage assessment model is parameter-adjusted according to the second damage classification loss function to obtain a second damage assessment model, so as to perform damage assessment on the target building using the second damage assessment model.

[0013] In some embodiments, before acquiring the second sample related to the target building from the preset second sample set, the method further includes:

[0014] Acquiring third building sensor data related to the target building;

[0015] Inputting the third building sensor data into the first damage assessment model for damage assessment to obtain a prediction label and a prediction confidence; wherein the prediction label represents the damage degree corresponding to the third building sensor data, and the prediction confidence is the confidence of the prediction label;

[0016] Comparing the prediction confidence with the preset third sample screening threshold to obtain first confidence comparison information;

[0017] When the first confidence comparison information indicates that the prediction confidence is higher than the third sample screening threshold, selecting the third building sensor data and the prediction label corresponding to the prediction confidence as a third sample;

[0018] constructing a third sample set according to the third sample;

[0019] The second sample set is updated according to the third sample set.

[0020] In some embodiments, before updating the second sample set according to the third sample set, the method further includes:

[0021] Comparing the prediction confidence with the preset fourth sample screening threshold to obtain second confidence comparison information;

[0022] When the second confidence comparison information indicates that the prediction confidence is higher than the fourth sample screening threshold, selecting the prediction label and the prediction label corresponding to the prediction confidence as the fourth sample;

[0023] constructing a fourth sample set according to the fourth sample;

[0024] Sample sampling is performed on the first sample set, the second sample set, and the fourth sample set according to a preset evaluation sample sampling ratio to obtain an evaluation sample set.

[0025] In some embodiments, the evaluation sample set includes: a fusion sample subset; the first sample set has a first sample number, which is the total number of the first samples; the second sample set has a second sample number, which is the total number of the second samples; the fourth sample set has a fourth sample number, which is the total number of the fourth samples;

[0026] The step of sampling the first sample set, the second sample set, and the fourth sample set according to a preset evaluation sample sampling ratio to obtain an evaluation sample set includes:

[0027] Obtaining the first sample number, the second sample number, and the fourth sample number;

[0028] determining a fifth sample sampling number based on the evaluation sample sampling ratio and the first sample number, determining a sixth sample sampling number based on the evaluation sample sampling ratio and the second sample number, and determining a seventh sample sampling number based on the evaluation sample sampling ratio and the fourth sample number;

[0029] Collect samples from the first sample set according to the fifth sample sampling number to obtain a fifth sample set;

[0030] Collect samples from the second sample set according to the sixth sample sampling number to obtain a sixth sample set;

[0031] Collect samples from the fourth sample set according to the seventh sample sampling number to obtain a seventh sample set;

[0032] The fifth sample set, the sixth sample set, and the seventh sample set are fused to obtain the fused sample subset.

[0033] In some embodiments, the evaluation sample set further includes: generating a sample subset, the fourth sample set including: at least one predicted positive sample and at least one predicted negative sample, the first sample set including at least one sample building positive sample and at least one sample building negative sample, and the second sample set including at least one target building positive sample and at least one target building negative sample;

[0034] The step of sampling the first sample set, the second sample set, and the fourth sample set according to a preset evaluation sample sampling ratio to obtain an evaluation sample set further includes:

[0035] Selecting a target positive sample from the predicted positive samples, the sample building positive samples, and the target building positive samples;

[0036] Selecting a target negative sample from the predicted negative sample, the sample building negative sample, and the target building negative sample; wherein the target positive sample and the target negative sample come from different sample sets;

[0037] Linearly adding the target positive sample and the target negative sample according to a preset linear addition ratio to obtain a generated sample;

[0038] The generated sample subset is constructed according to the generated samples.

[0039] In some embodiments, after adjusting parameters of a target damage classifier of the first damage assessment model according to the second damage classification loss function to obtain a second damage assessment model, the method further includes:

[0040] Selecting an evaluation sample from the evaluation sample set; wherein the evaluation sample includes evaluation building sensor data and a verification damage classification label, wherein the verification damage classification label represents the actual damage degree of the evaluation sample;

[0041] Inputting the sensor data of the assessment building into the second damage assessment model for damage assessment to obtain a quality assessment label and an assessment confidence level; wherein the quality assessment label represents the degree of damage obtained by the damage assessment of the sensor data of the assessment building, and the assessment confidence level is the confidence level of the quality assessment label;

[0042] determining a receiver operating characteristic curve of the second damage assessment model according to the quality assessment label, the assessment confidence, and the verification damage classification label;

[0043] A target confidence threshold is selected from the receiver operating characteristic curve according to a preset recall rate threshold, and the confidence threshold of the second damage assessment model is updated according to the target confidence threshold.

[0044] In some embodiments, the initial damage assessment model further includes: a feature extraction module and a target type adversarial classifier;

[0045] The step of inputting the first building sensor data into a preset initial damage assessment model to perform damage assessment to obtain first damage assessment data includes:

[0046] Performing feature extraction on the first building sensor data by the feature extraction module to obtain a first damage assessment feature;

[0047] performing target damage classification on the first damage assessment feature by the target damage classifier to obtain the first damage classification data;

[0048] The first damage assessment feature is subjected to target type adversarial classification by the target type adversarial classifier to obtain the type classification probability.

[0049] To achieve the above-mentioned objectives, a second aspect of an embodiment of the present application provides a target damage assessment system, the system comprising:

[0050] A first sample acquisition module is configured to acquire a first sample from a preset first sample set; wherein the first sample set includes at least two first samples, each of the first samples including first building sensor data and a first building type of a sample building, and the first building types of the two first samples are different;

[0051] a first damage assessment module, configured to input the first building sensor data into a preset initial damage assessment model for damage assessment to obtain first damage assessment data; wherein the first damage assessment data includes: first damage classification data and type classification probability;

[0052] a first loss construction module, configured to perform loss construction based on the first damage classification data to obtain a first damage classification loss function, and to perform loss construction based on the type classification probabilities of the at least two sample buildings and the first building type to obtain a building type adversarial loss function; wherein the building type adversarial loss function is configured to ensure that the type classification probability distributions of the at least two sample buildings of different building types are close to the same;

[0053] a first training module, configured to train the initial damage assessment model according to the first damage classification loss function and the building type adversarial loss function to obtain a first damage assessment model;

[0054] A second sample acquisition module is configured to acquire a second sample related to the target building from a preset second sample set; wherein the second sample includes second building sensor data of the target building;

[0055] a second damage assessment module, configured to input the second building sensor data into the first damage assessment model for damage assessment to obtain second damage assessment data; wherein the second damage assessment data includes second damage classification data;

[0056] a second loss construction module, configured to construct a loss function based on the second damage classification data to obtain a second damage classification loss function;

[0057] The second training module is used to adjust the parameters of the target damage classifier of the first damage assessment model according to the second damage classification loss function to obtain a second damage assessment model, so as to use the second damage assessment model to perform damage assessment on the target building.

[0058] To achieve the above-mentioned purpose, the third aspect of an embodiment of the present application proposes an electronic device, which includes a memory and a processor, wherein the memory stores a computer program, and the processor implements the method described in the first aspect when executing the computer program.

[0059] To achieve the above-mentioned purpose, the fourth aspect of the embodiments of the present application proposes a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, it implements the method described in the first aspect.

[0060] The target damage assessment method and system, electronic device, and storage medium proposed in this application use a first damage classification loss function to make the damage classification data output by the first damage assessment model close to the actual damage level of the building, and use a building type adversarial loss function to make at least two sample buildings of different building types approach the same in type classification probability distribution. This enables the first damage assessment model to perform damage assessment on the input sensor data that is only related to the damage level and not to the building type, thereby improving the damage assessment accuracy of the target damage assessment method on different types of buildings, that is, improving the generalization capability of the target damage assessment method across different scenarios and target types for different types of buildings. Furthermore, the target damage assessment method and system, electronic device, and storage medium proposed in this application train an initial damage assessment model based on first samples of different sample buildings to obtain a first damage assessment model, and then train the first damage assessment model using second samples related to the target building to obtain a second damage assessment model. This allows, when the target damage assessment model is deployed to a new building type, only a small number of second samples need to be collected to adjust the parameters of the first damage assessment model to obtain a second damage assessment model with higher accuracy in damage assessment of the target building, thereby improving the efficiency of the target damage assessment method across scenarios and target types. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] Figure 1 This is an optional flowchart of the target damage assessment method provided in an embodiment of the present application;

[0062] Figure 2 Schematic diagram of the structure of the initial damage assessment model provided in the embodiment of the present application;

[0063] Figure 3 yes Figure 1 Flowchart of step S102 in FIG.

[0064] Figure 4 This is another optional flow chart of the target damage assessment method provided in the embodiment of the present application;

[0065] Figure 5 This is another optional flow chart of the target damage assessment method provided in the embodiment of the present application;

[0066] Figure 6 yes Figure 5 Step S504 in an optional flowchart;

[0067] Figure 7 yes Figure 5 Another optional flowchart of step S504;

[0068] Figure 8 This is another optional flow chart of the target damage assessment method provided in the embodiment of the present application;

[0069] Figure 9 Schematic diagram of the overall architecture of the target damage assessment method provided in an embodiment of the present application;

[0070] Figure 10 Schematic diagram of the structure of the target damage assessment system provided in an embodiment of the present application;

[0071] Figure 11 This is a schematic diagram of the hardware structure of the electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0072] In order to make the purpose, technical solutions and advantages of this application more clear, the following further describes this application in detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not intended to limit this application.

[0073] It should be noted that although the system diagrams illustrate functional module divisions and the flowcharts illustrate logical sequences, in certain circumstances, the steps shown or described may be performed in a sequence that differs from the module divisions in the system or the sequence in the flowcharts. The terms "first," "second," and so on, in the specification, claims, and drawings, are used to distinguish similar items and are not necessarily used to describe a specific sequence or precedence.

[0074] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art to which this application pertains. The terms used herein are for the purpose of describing the embodiments of this application only and are not intended to limit this application.

[0075] First, let’s analyze some of the terms used in this application:

[0076] Artificial intelligence (AI) is a new technical discipline that studies and develops theories, methods, technologies, and application systems for simulating, extending, and expanding human intelligence. A branch of computer science, AI seeks to understand the essence of intelligence and create new intelligent machines that can respond in a manner similar to human intelligence. Research in this field includes image recognition, natural language processing, and expert systems. AI can simulate the information processes of human consciousness and thinking. It also encompasses theories, methods, technologies, and application systems that use digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, to perceive the environment, acquire knowledge, and use that knowledge to achieve optimal results.

[0077] Target damage assessment aims to analyze and evaluate the extent of damage to a target after physical destruction. This method can be applied to assessing the extent of damage to buildings, such as houses and bridges, after natural disasters, vandalism, and other physical damage. It can also be used to evaluate a building's resilience to damage. Common, low-cost target damage assessment methods typically rely on data from field-deployed sensors for judgment and analysis.

[0078] Based on the different data analysis methods, target damage assessment methods can be divided into two categories: those that judge target damage levels based on human experience, and those that classify target damage levels based on machine learning. However, target damage assessment methods that judge target damage levels based on human experience rely on manual experience and require constant adjustments for different targets, scenarios, and time periods, resulting in high costs and difficulty in scalability. Methods that classify target damage levels based on machine learning generally train target damage assessment models based on existing labeled data to classify target damage levels. However, damage assessment models are typically pre-trained on building types such as bungalows, bridges, and high-rise buildings, and then perform damage assessments on target buildings or scenes of the same pre-trained building types. This results in low damage assessment accuracy when the damage assessment model is applied to building types for which it has not been trained. This means that target damage assessment methods have poor generalization capabilities across scenarios and target types.

[0079] Based on this, the embodiments of the present application provide a target damage assessment method and system, an electronic device, and a storage medium, aiming to improve the generalization capability of the target damage assessment method across scenarios and target types, thereby improving the damage assessment accuracy of the target damage assessment method on different types of buildings and the application efficiency of the target damage assessment method across scenarios and target types.

[0080] The target damage assessment method and system, electronic device, and storage medium provided in the embodiments of the present application are specifically described through the following embodiments. First, the target damage assessment method in the embodiments of the present application is described.

[0081] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. Artificial Intelligence (AI) is the theory, method, technology, and application system that uses digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use knowledge to achieve optimal results.

[0082] Fundamental AI technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing, and operating / interaction systems. AI software technologies primarily encompass computer vision, robotics, speech processing, natural language processing, and machine learning / deep learning.

[0083] The target damage assessment method provided in the embodiment of the present application relates to the field of artificial intelligence technology. The target damage assessment method provided in the embodiment of the present application can be applied to a terminal, can be applied to a server side, or can be software running in a terminal or a server side. In some embodiments, the terminal can be a smart phone, a tablet computer, a laptop computer, a desktop computer, etc.; the server side can be configured as an independent physical server, or as a server cluster or distributed system composed of multiple physical servers, or as a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, CDN, and big data and artificial intelligence platforms; the software can be an application that implements the target damage assessment method, etc., but is not limited to the above forms.

[0084] The present application can be used in many general or special computer system environments or configurations. For example: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, and the like. The present application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. The present application can also be practiced in distributed computing environments in which tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media, including storage devices.

[0085] Figure 1 This is an optional flowchart of the target damage assessment method provided in the embodiment of the present application. Figure 1 The method can be applied to target damage assessment of a single target building, or can be applied to target damage assessment of buildings in a target scene, where the target scene contains at least one target building. The method may include, but is not limited to, steps S101 to S108.

[0086] Step S101: obtaining a first sample from a preset first sample set; wherein the first sample set includes at least two first samples, each of the first samples including first building sensor data and a first building type of a sample building, and the first building types of the two first samples are different;

[0087] Step S102: Inputting the first building sensor data into a preset initial damage assessment model for damage assessment to obtain first damage assessment data; wherein the first damage assessment data includes: first damage classification data and type classification probability;

[0088] Step S103: Performing loss construction based on the first damage classification data to obtain a first damage classification loss function, and performing loss construction based on the type classification probabilities of at least two sample buildings and the first building type to obtain a building type adversarial loss function; wherein the building type adversarial loss function is used to ensure that the type classification probability distributions of at least two sample buildings of different building types are close to the same;

[0089] Step S104: training the initial damage assessment model according to the first damage classification loss function and the building type adversarial loss function to obtain a first damage assessment model;

[0090] Step S105: obtaining a second sample related to the target building from a preset second sample set; wherein the second sample includes second building sensor data of the target building;

[0091] Step S106: Inputting the second building sensor data into the first damage assessment model to perform damage assessment to obtain second damage assessment data; wherein the second damage assessment data includes second damage classification data;

[0092] Step S107, constructing a loss function based on the second damage classification data to obtain a second damage classification loss function;

[0093] Step S108 , adjusting parameters of the target damage classifier of the first damage assessment model according to the second damage classification loss function to obtain a second damage assessment model, so as to perform damage assessment on the target building using the second damage assessment model.

[0094] In steps S101 to S108 illustrated in the embodiment of the present application, the damage classification data output by the first damage assessment model is made close to the actual damage extent of the building through a first damage classification loss function, and the type classification probability distribution of at least two sample buildings of different building types is made to be close to the same through a building type adversarial loss function. This enables the first damage assessment model to perform damage assessment on the input sensor data that is only related to the damage extent and not to the building type, thereby improving the damage assessment accuracy of the target damage assessment method on different types of buildings, that is, improving the generalization capability of the target damage assessment method across scenarios and target types for different types of buildings. Furthermore, the target damage assessment method and system, electronic device, and storage medium proposed in this application train an initial damage assessment model based on first samples of different sample buildings to obtain a first damage assessment model, and then train the first damage assessment model using second samples related to the target building to obtain a second damage assessment model. This allows the target damage assessment model to be deployed on a new building type by only collecting a small number of second samples to adjust the parameters of the first damage assessment model to obtain a second damage assessment model with higher accuracy in damage assessment of the target building. This allows the target damage assessment method to be quickly and scalably applied to target buildings of new building types, thereby improving the cross-scenario and cross-target type application efficiency of the target damage assessment method and shortening the training time of the second damage assessment model, thereby reducing the cost of adapting the target damage assessment method to new building types.

[0095] In step S101 of some embodiments, the sample building is the data source for the first sample, which is used to pre-train the initial damage assessment model. The first sample set is a collection of first samples, containing at least first samples from two sample buildings of different building types. The first samples describe the building type, actual building damage level, and sensor data of the sample buildings. Therefore, the first samples include at least, but are not limited to, the first building type, first building sensor data, and a first damage label. The first building type describes the building type of the sample building, the first building sensor data is sensor data collected from the sample building, and the first damage label describes the actual building damage level corresponding to the first building sensor data. For example, the first building type may include, but is not limited to, bridges, high-rise buildings, flat buildings, tunnels, ports, factories, and historical buildings. The first building sensor data may include, but is not limited to, target temperature, target vibration information, and packet loss rate of networked devices. Based on this, the present application can obtain the first sample from the first sample set. The specific method for obtaining the first sample from the preset first sample set can be random sampling or other acquisition methods conceivable by those skilled in the art, and this application does not impose any specific limitations. It should be noted that the type of the first damage label is an enumeration type. The first damage label can be a binary label or a multi-classification label. The specific first damage label can be set and labeled according to the actual needs of technical personnel in this field. If the first damage label is a binary label, the first damage label is used to describe whether the sample building is actually a damaged building or an intact building. The first sample set includes at least one positive sample of the sample building and at least one negative sample of the sample building. Among them, if the sample building is a damaged building, the first damage label labels the sample building as damaged, and the first sample is used as the positive sample of the sample building; if the sample building is an intact building, the first damage label labels the sample building as undamaged, and the first sample is used as the negative sample of the sample building. If the first damage label is a multi-classification label, the first sample is labeled according to the degree of damage received by the sample building. Taking the three-category labeling as an example, if the sample building is intact, the first sample of the sample building is labeled as no damage; if the sample building is slightly damaged, the first sample of the sample building is labeled as slightly damaged; if the sample building is severely damaged, the first sample of the sample building is labeled as severely damaged. Taking the four-category labeling as an example, if the sample building is intact, the first sample of the sample building is labeled as no damage; if the sample building is slightly damaged, the first sample of the sample building is labeled as slightly damaged; if the sample building is moderately damaged, the first sample of the sample building is labeled as moderately damaged; if the sample building is severely damaged, the first sample of the sample building is labeled as severely damaged.

[0096] In step S102 of some embodiments, the initial damage assessment model is an untrained target damage assessment model, which is used to perform damage assessment on the first building sensor data input into the initial damage assessment model to obtain first damage assessment data. The first damage assessment data describes the damage extent and type of the sample building obtained by the initial damage assessment model based on the first building sensor data. Therefore, the first damage assessment data includes first damage classification data and type classification probabilities. The first damage classification data describes the damage extent of the sample building obtained by the initial damage assessment model based on the first building sensor data, and the type classification probabilities describe the type classification probabilities obtained by the initial damage assessment model when classifying the sample building into different building types based on the first building sensor data. Based on this, the first building sensor data can be input into the preset initial damage assessment model for damage assessment to obtain the first damage assessment data. It should be noted that the type of the first damage classification data is the same as the type of the first damage label. For example, if the first damage label is a binary classification label, the first damage classification data is also binary classification data. In addition, the specific implementation of the first damage classification data is similar to the specific implementation of the first damage label. You can refer to the specific implementation of the first damage label, and this application will not repeat it again.

[0097] See also Figure 2 and Figure 3 In some embodiments, the initial damage assessment model includes: a feature extraction module, a target damage classifier, and a target type adversarial classifier. The feature extraction module is used to extract a first damage assessment feature from the first building sensor data, the target damage classifier is used to classify the damage degree of the sample building of the first sample according to the first damage assessment feature, and the target type adversarial classifier is used to classify the building type of the sample building of the first sample according to the first damage assessment feature, for example, the sample building belongs to a high-rise building, or the sample building belongs to a bridge building, etc. Specifically, the feature extraction module can be constructed based on a deep learning architecture, and the deep learning architecture can be a convolutional neural network (CNN) and a residual network (ResNet), etc. The target damage classifier includes at least one fully connected layer (FC), and the target type adversarial classifier includes at least one FC layer.

[0098] In some embodiments, step S102 may include but is not limited to steps S301 to S303:

[0099] Step S301: extracting features from the first building sensor data using a feature extraction module to obtain a first damage assessment feature;

[0100] Step S302: performing target damage classification on the first damage assessment feature using a target damage classifier to obtain first damage classification data;

[0101] Step S303: Perform target type adversarial classification on the first damage assessment feature through a target type adversarial classifier to obtain a type classification probability.

[0102] In step S301 of some embodiments, a feature extraction module may be used to extract features from the first building sensor data to obtain a first damage assessment feature. The first damage assessment feature is represented by a feature vector. Specifically, taking an 18-layer residual network (ResNet18) as an example, the feature extraction module may include a cascaded 7×7 convolutional layer (Cov), a 3×3 maximum pooling layer (Maxpool), four stages (Stage), a global average pooling layer (GAP), and an FC layer. The 7×7 convolutional layer has 64 output channels (c), a stride (s) of 2, and padding (p) of 3. The input size of the 7×7 convolutional layer is 3×64×64, indicating that the input first building sensor data has three channels, each of which is 64×64 in size. The output size of the 7×7 convolutional layer is 64×32×32, where 64 is the number of output channels and 32×32 is the spatial size of the feature map. The 3×3 max pooling layer is used to downsample the output feature map of the 7×7 convolutional layer to reduce the spatial size of the feature map to 16×16, and outputs the feature map with the reduced spatial size. The first stage of ResNet18 consists of two cascaded residual blocks (ResidualBlocks), each of which consists of two cascaded 3×3 convolutional layers. The number of output channels of each convolution operation is 64, the stride is 1, and the padding is 1. The second stage of ResNet18 includes two cascaded residual blocks, where the output size of the first residual block is 128×8×8; each residual block includes two cascaded 3×3 convolutional layers, the number of output channels of each convolution operation is 128, the stride of the first convolutional layer is 2, the stride of the second to fourth convolutional layers is 1, and the padding of each convolutional layer is 1; and in the first residual block, the input feature map is convolved by two cascaded 3×3 convolutional layers to obtain the first output feature map of the second stage, and is downsampled by a 1×1 convolutional layer with a stride of 2 to obtain the downsampled output feature map of the second stage, and then the first output feature map of the second stage and the downsampled output feature map of the second stage are used together as the input feature map of the second residual block, and the input feature map and output feature map of the second residual block are used as the input feature map of the next residual block.The third stage of ResNet18 includes two cascaded residual blocks, the first residual block includes two cascaded 3×3 convolutional layers, and the output size of the first residual block is 256×4×4; the second residual block includes a 3×3 convolutional layer, the number of output channels of each convolution operation is 256, the stride of the first convolutional layer is 2, the stride of the second and third convolutional layers is 1, and the padding of each convolutional layer is 1; and in the first residual block, the input feature map is convolved by two cascaded 3×3 convolutional layers to obtain the second output feature map of the third stage, and is downsampled by a 1×1 convolutional layer with a stride of 2 to obtain the downsampled output feature map of the third stage, and then the second output feature map of the third stage and the downsampled output feature map of the third stage are used together as the input feature map of the second residual block, and the input feature map and output feature map of the second residual block are used as the input feature map of the next residual block. The fourth stage of ResNet18 consists of two cascaded residual blocks, where the output size of the first residual block is 512×2×2. Each residual block consists of two cascaded 3×3 convolutional layers, each with 512 output channels. The stride of the first convolutional layer is 2, and the stride of the second to fourth convolutional layers is 1. The padding of each convolutional layer is 1. The processing of the output feature map in the fourth stage is similar to that in the second stage (see the second stage for details). The total output feature map of the fourth stage is then converted to a fixed-length feature vector through a cascade of global average pooling layers and FC layers to obtain the feature vector of the first damage assessment feature. The feature vector has a fixed length of 512.

[0103] In step S302 of some embodiments, target damage classification may be performed on the feature vector of the first damage assessment feature by a target damage classifier composed of at least one FC layer to obtain first damage classification data.

[0104] In step S303 of some embodiments, a target type adversarial classifier composed of at least one FC layer may be used to perform target type adversarial classification on the feature vector of the first damage assessment feature to obtain a type classification probability.

[0105] In steps S301 to S303 illustrated in the embodiment of the present application, first, a feature extraction module is used to extract features from the first building sensor data to obtain a first damage assessment feature. Then, a target damage classifier is used to perform target damage classification on the first damage assessment feature to obtain first damage classification data. Finally, a target type adversarial classifier is used to perform target type adversarial classification on the first damage assessment feature to obtain a type classification probability. This enables the target damage assessment method illustrated in the embodiment of the present application to obtain the first damage classification data and type classification probability for the first sample by the initial damage assessment model, so as to facilitate subsequent training of the initial damage assessment model to obtain the first damage assessment model.

[0106] In step S103 of some embodiments, a first damage classification loss function is used to describe the difference between the first damage classification data and the first damage label, and can be constructed based on the first damage classification data and the first damage label. A building type adversarial loss function can be constructed based on the type classification probability and the first building type, and is used to decouple the target damage classification task of the initial damage assessment model from the first building type, thereby preventing different building types from significantly interfering with the target damage classification task. Specifically, the building type adversarial loss function can decouple the target damage classification task from the first building type by constraining at least two sample buildings of different building types to have similar type classification probability distributions.

[0107] In step S104 of some embodiments, the initial damage assessment model can be trained based on the first damage classification loss function and the building type adversarial loss function to obtain the first damage assessment model. Specifically, the Adam method can be used to adjust the learning rate and perform gradient backpropagation on the initial damage assessment model. When the first damage classification loss function and the building type adversarial loss function converge, the first damage assessment model is obtained. Therefore, the target damage assessment method illustrated in this embodiment can decouple the target damage classification task from the first building type through the building type adversarial loss function during the training of the initial damage assessment model based on the first damage classification loss function and the building type adversarial loss function, thereby continuously weakening the influence of the first building type on feature extraction. As a result, the second damage assessment features extracted from the second sensor data by the trained first damage assessment model are only related to the damage classification and not the building type. This makes the first damage assessment model less susceptible to interference from the building type, thereby improving the robustness of the first damage assessment model.

[0108] See also Figure 4 In some embodiments, before step S105, the target damage assessment method of the embodiment of the present application may further include but is not limited to steps S401 to S406:

[0109] Step S401, obtaining third building sensor data related to the target building;

[0110] Step S402: Input the third building sensor data into the first damage assessment model to perform damage assessment, and obtain a prediction label and a prediction confidence; wherein the prediction label represents the damage level corresponding to the third building sensor data, and the prediction confidence is the confidence level of the prediction label;

[0111] Step S403: performing a comparison based on a preset third sample screening threshold and prediction confidence to obtain first confidence comparison information;

[0112] Step S404: When the prediction confidence represented by the first confidence comparison information is higher than the third sample screening threshold, the third building sensor data and the prediction label corresponding to the prediction confidence are selected as the third sample;

[0113] Step S405: constructing a third sample set based on the third sample;

[0114] Step S406: Update the second sample set according to the third sample set.

[0115] Before S401 in some steps, the first damage assessment model must be deployed on an online platform, such as a cloud platform like AWS, Azure, or Alibaba Cloud, a server, or an edge device. Then, the input of the first damage assessment model is connected to the target building's sensors via 4G networking equipment. This allows the target building's sensors to quickly transmit the collected sensor data from the third building to the first damage assessment model, improving the transmission efficiency of the third building's sensor data. Furthermore, the deployment cost of 4G networking equipment is low, saving the hardware cost of transmitting the third building's sensor data to the first damage assessment model.

[0116] In step S401 of some embodiments, the third building sensor data is continuously collected by sensors deployed on the target building. The specific implementation method for collecting the third building sensor data can be to collect the third building sensor data according to a preset collection command, or to collect the third building sensor data according to a specific collection cycle. The specific implementation method of the third building sensor data is similar to the specific real-time implementation method of the second building sensor data. Please refer to the implementation method of the second building sensor data, and this application will not repeat it again. It should be noted that the third building sensor data and the second building sensor data can be the same or different.

[0117] In step S402 of some embodiments, the third building sensor data is input into the first damage assessment model for damage assessment, resulting in a predicted label and prediction confidence. The predicted label describes the degree of damage corresponding to the third building sensor data. The specific implementation of the predicted label is similar to that of the first damage classification data and can be referenced for details. The prediction confidence is the confidence level of the predicted label, describing the probability that the predicted label is accurate.

[0118] In step S403 of some embodiments, the third sample screening threshold can be pre-stored in the storage space of the online platform or other storage space. The third building sensor data and predicted labels with a prediction confidence higher than the third sample screening threshold are used as the third sample to ensure the authenticity and accuracy of the third sample. The third sample is used to update the second sample, and the third sample is divided into positive samples and negative samples. Specifically, the third sample screening threshold is set according to the type of predicted label. For example, if the predicted label is a binary label, the third sample screening threshold may include: a third positive sample threshold and a third negative sample threshold. The third positive sample threshold is used to screen positive samples in the third sample, and the third negative sample threshold is used to screen negative samples in the third sample. The first confidence comparison information is used to describe the numerical relationship between the third sample screening threshold and the prediction confidence. The first confidence comparison information may include, but is not limited to, any one of the following: the prediction confidence is greater than the third sample screening threshold, the prediction confidence is equal to the third sample screening threshold, or the prediction confidence is less than the third sample screening threshold.

[0119] In step S404 of some embodiments, when the first confidence comparison information represents a prediction confidence that is higher than the third sample screening threshold, the third building sensor data and the prediction label corresponding to the prediction confidence can be selected as the third sample. For example, the third positive sample threshold and the third negative sample threshold can both be set to 98%. If the prediction confidence is higher than 98%, the third building sensor data and the prediction label corresponding to the prediction confidence are selected as the third sample. If the prediction label is a damaged building, the third building sensor data and the prediction label are used as positive samples in the third sample. If the prediction label is a complete building, the third building sensor data and the prediction label are used as negative samples in the third sample. The third positive sample threshold and the third negative sample threshold can also be set to other specific values. The third positive sample threshold and the third negative sample threshold can be equal, or the third positive sample threshold and the third negative sample threshold can be unequal. This is not limited in the present application.

[0120] In step S405 of some embodiments, a third sample set may be constructed based on the third samples. Specifically, all second samples may be directly combined into the second sample set, and all third samples may be combined into the third sample set.

[0121] In some embodiments, in step S406, the second sample set may be updated based on the third sample set. Specifically, the total number of third samples in the third sample set is first obtained as the third sample number, and the third sample number is compared with a preset second sample update threshold to obtain update comparison information, where the update comparison information indicates that the third sample number is not less than the second sample update threshold or that the third sample number is less than the second sample update threshold. If the update comparison information indicates that the third sample number is not less than the second sample update threshold, a preset second sample update ratio is obtained, and samples are sampled from the second and third sample sets according to the second sample update ratio to obtain a target sample set, thereby replacing the second sample set with samples from the target sample set. It should be noted that before the second sample set is updated for the first time based on the third sample set, the second samples are actual samples of the target building, including sensor data collected from the target building and actual damage types. Because the prediction confidence of the third samples is higher than the third sample screening threshold, the third samples are authentic and reliable, and can be considered actual samples of the target building.

[0122] In some embodiments, sampling the second sample set and the third sample set according to the second sample update ratio to obtain the target sample set includes: first, obtaining the second sample number from the total number of second samples in the second sample set; then, multiplying the third sample number by the second sample update ratio to obtain the third sample collection number, and then multiplying the second sample number by the second sample update ratio to obtain the second sample collection number; then, randomly collecting a third sample from the third samples according to the third sample collection number, and randomly collecting a second sample from the second samples according to the second sample collection number, so as to use the randomly collected third sample and the randomly collected second sample as target samples; and finally, constructing the target sample set based on the target samples. For example, if the second sample number is 10, the second sample update threshold is 10, and the second sample update ratio is 50%:50%, then if the third sample number is 10, then the third sample collection number and the second sample collection number are both determined to be 5, then 5 third samples are randomly sampled from the third sample set, and 5 second samples are randomly sampled from the second sample set, and the collected 5 third samples and 5 second samples are formed into the target sample set; finally, the target sample set replaces the second sample set. Therefore, the target damage assessment method shown in the embodiment of the present application can update the second sample set based on the third sample set to fully utilize the incremental target damage assessment information brought by the third sample, while retaining the target damage assessment information that has been verified in the second sample set, ensuring the stability and accuracy when adjusting the parameters of the first damage assessment model based on the updated second sample set.

[0123] It should be noted that the second sample update threshold can also be multiple values, for example, 10, 20, and 30, so that when the number of third samples reaches 10, 20, and 30, respectively, the second sample set is updated based on the third sample set, and the parameters of the first damage assessment model are adjusted three times respectively to improve the accuracy of damage assessment performed by the second damage assessment model. It should be noted that the total number of third samples in the third sample set can be obtained based on a specific third sample number acquisition period. The third sample number acquisition period can be one day, one hour, or other specific values, and can be selected according to actual needs. The total number of third samples in the third sample set can also be obtained once after each specific number of third samples are screened. The specific number can be once, twice, or other specific times.

[0124] In steps S401 to S406 illustrated in the embodiment of the present application, since the third sample is derived from the third building sensor data that is continuously collected in real time, by using the predicted label predicted by the first damage assessment model and the third building sensor data as the third sample and updating the second sample based on the third sample, the incremental target damage assessment information brought by the third sample can be fully utilized, and the target damage assessment information that has been verified in the second sample set can be retained, while ensuring the stability and accuracy when adjusting the parameters of the first damage assessment model based on the updated second sample set.

[0125] See also Figure 5 In some embodiments, before step S406, the target damage assessment method may further include but is not limited to steps S501 to S504:

[0126] Step S501, performing comparison based on a preset fourth sample screening threshold and prediction confidence to obtain second confidence comparison information;

[0127] Step S502: When the second confidence comparison information indicates that the prediction confidence is higher than a fourth sample screening threshold, a prediction label and a prediction label corresponding to the prediction confidence are selected as a fourth sample;

[0128] Step S503: constructing a fourth sample set based on the fourth sample;

[0129] Step S504 : sampling the first sample set, the second sample set, and the fourth sample set according to a preset evaluation sample sampling ratio to obtain an evaluation sample set.

[0130] In step S501 of some embodiments, the fourth sample screening threshold is used to select the third building sensor data and predicted labels with a prediction confidence higher than the fourth sample screening threshold as the fourth sample to ensure the quality and accuracy of the fourth sample. The fourth sample is used to adjust the confidence threshold of the second damage assessment model. If the predicted label is a binary classification label, the fourth sample can be divided into: predicted positive samples and predicted negative samples, wherein the predicted positive sample indicates that the target building is a damaged building, and the predicted negative sample indicates that the target building is an intact building. The fourth sample screening threshold can be pre-stored in the storage space of the online platform or other storage space. Specifically, the fourth sample screening threshold can be set according to the type of predicted label. For example, if the predicted label is a binary classification label, the fourth sample screening threshold can include: a fourth positive sample threshold and a fourth negative sample threshold, wherein the fourth positive sample threshold is used to screen predicted positive samples, and the fourth negative sample threshold is used to screen predicted negative samples in the third sample. The second confidence comparison information is used to describe the numerical relationship between the fourth sample screening threshold and the prediction confidence. The second confidence comparison information may include but is not limited to any one of the following: the prediction confidence is greater than the fourth sample screening threshold, the prediction confidence is equal to the fourth sample screening threshold, or the prediction confidence is less than the fourth sample screening threshold.

[0131] In other embodiments, sensor data from a fourth building related to the target building may be collected; wherein the sensor data from the second building, the sensor data from the third building, and the sensor data from the fourth building are all different. The fourth building sensor data is then input into the first damage assessment model to obtain candidate labels and candidate confidence levels. The candidate label is the damage level corresponding to the fourth building sensor data, and the candidate confidence level is the confidence level of the predicted label. Subsequently, candidate confidence levels exceeding a fourth sample screening threshold are selected as target labels, and the fourth building sensor data and candidate confidence levels corresponding to the target labels are used as fourth samples.

[0132] In step S502 of some embodiments, when the second confidence comparison information represents a prediction confidence that is higher than the fourth sample screening threshold, the prediction label and the prediction label corresponding to the prediction confidence are selected as the fourth sample. For example, since most of the prediction labels that mark the target building as a complete building are accurate, a lower fourth negative sample threshold can be selected. Therefore, the fourth positive sample threshold can be set to 95%, and the fourth negative sample threshold can be set to 50%. If the prediction confidence is higher than 95% and the prediction label is a damaged building, the third building sensor data and the prediction label corresponding to the prediction confidence are selected as the prediction positive sample; if the prediction confidence is higher than 50% and the prediction label is a complete building, the third building sensor data and the prediction label corresponding to the prediction confidence are selected as the prediction negative sample. The fourth positive sample threshold and the fourth negative sample threshold can also be set to other specific values. The fourth positive sample threshold and the third negative sample threshold can be equal, or the fourth positive sample threshold and the third negative sample threshold can be unequal. This is not limited in this application.

[0133] In step S503 of some embodiments, a fourth sample set may be constructed based on the fourth samples. Specifically, all fourth samples may be combined to obtain the fourth sample set.

[0134] In step S504 of some embodiments, the evaluation sample sampling ratio is used to collect samples from the first sample set, the second sample set, and the fourth sample set to obtain an evaluation sample set. The evaluation sample set is used to update the confidence threshold of the second damage assessment model so that the second damage assessment model outputs more accurate target damage assessment data.

[0135] In steps S501 to S504 shown in the embodiment of the present application, a comparison is first performed based on the preset fourth sample screening threshold and the prediction confidence to obtain second confidence comparison information, and when the second confidence comparison information indicates that the prediction confidence is higher than the fourth sample screening threshold, the prediction label and the prediction label corresponding to the prediction confidence are selected as the fourth sample. Then, a fourth sample set is constructed based on the fourth sample, and the first sample set, the second sample set, and the fourth sample set are sampled according to the preset evaluation sample sampling ratio to obtain an evaluation sample set, which can obtain a high-precision evaluation sample set. Moreover, since the evaluation sample set contains sample data of multiple building types, after the evaluation sample set is used to update the confidence threshold of the second damage assessment model, the second damage assessment model can comprehensively perform damage assessment on the target building, thereby improving the accuracy of the target damage assessment model data.

[0136] See also Figure 6In some embodiments, the evaluation sample set includes: a fused sample subset, which is directly constructed based on the evaluation samples sampled from the first sample set, the second sample set, and the fourth sample set. The first sample set has a first sample number, which is the total number of first samples; the second sample set has a second sample number, which is the total number of second samples; and the fourth sample set has a fourth sample number, which is the total number of fourth samples. Step S504 may include, but is not limited to, steps S601 to S605:

[0137] Step S601, obtaining a first sample number, a second sample number, and a fourth sample number;

[0138] Step S602, determining a fifth sample sampling number based on the evaluation sample sampling ratio and the first sample number, determining a sixth sample sampling number based on the evaluation sample sampling ratio and the second sample number, and determining a seventh sample sampling number based on the evaluation sample sampling ratio and the fourth sample number;

[0139] Step S603, collecting samples from the first sample set according to the fifth sample sampling number to obtain a fifth sample set;

[0140] Step S604, collecting samples from the second sample set according to the sixth sample sampling number to obtain a sixth sample set;

[0141] Step S605, collecting samples from the fourth sample set according to the seventh sample sampling number to obtain a seventh sample set;

[0142] Step S606: Fusing the fifth sample set, the sixth sample set, and the seventh sample set to obtain a fused sample subset.

[0143] In step S602 of some embodiments, the fifth sample sampling number may be determined based on the evaluation sample sampling ratio and the first sample number, the sixth sample sampling number may be determined based on the evaluation sample sampling ratio and the second sample number, and the seventh sample sampling number may be determined based on the evaluation sample sampling ratio and the fourth sample number. For example, the evaluation sample sampling ratio may be If the first sample number is 9, the second sample number is 9, and the fourth sample number is 9, then the fifth sample number can be determined to be 3 based on the evaluation sample sampling ratio and the first sample number, the sixth sample number can be determined to be 3 based on the evaluation sample sampling ratio and the second sample number, and the seventh sample number can be determined to be 3 based on the evaluation sample sampling ratio and the fourth sample number. The evaluation sample sampling ratio can also be other specific values, and this application does not impose any specific restrictions.

[0144] In step S603 of some embodiments, samples are collected from the first sample set according to the fifth sample sampling number to obtain a fifth sample set. A specific implementation of collecting samples from the first sample set according to the fifth sample sampling number may be random sampling. Below, the specific implementation of collecting samples from the second sample set according to the sixth sample sampling number to obtain the sixth sample set, and the specific implementation of collecting samples from the fourth sample set according to the seventh sample sampling number to obtain the seventh sample set, are similar to the specific implementation of collecting samples from the first sample set according to the fifth sample sampling number, and reference may be made to the specific implementation of collecting samples from the first sample set according to the fifth sample sampling number. It should be noted that if the first sample number, the second sample number, and the fourth sample number are not equal, the samples in the first sample set, the second sample set, and the fourth sample set can be resampled or downsampled first, and the resampled or downsampled first sample set is used as the eighth sample set, the resampled or downsampled second sample set is used as the ninth sample set, and the resampled or downsampled fourth sample set is used as the tenth sample set, wherein the total number of samples in the eighth sample set is the eighth sample number, the total number of samples in the ninth sample set is the ninth sample number, and the total number of samples in the tenth sample set is the tenth sample number, and the eighth sample number, the ninth sample number, and the tenth sample number are equal. Only then can the fifth sample number be determined based on the evaluation sample sampling ratio and the eighth sample number, the sixth sample number be determined based on the evaluation sample sampling ratio and the ninth sample number, or the seventh sample number be determined based on the evaluation sample sampling ratio and the tenth sample number. Finally, samples are collected from the eighth sample set according to the fifth sample sampling number to obtain the fifth sample set, samples are collected from the ninth sample set according to the sixth sample sampling number to obtain the sixth sample set, or samples are collected from the tenth sample set according to the seventh sample sampling number to obtain the seventh sample set. Resampling refers to increasing the total number of samples by repeatedly sampling the samples in the sample set, and downsampling refers to reducing the total number of samples by randomly deleting the samples in the sample set.

[0145] In step S606 of some embodiments, the fifth sample set, the sixth sample set, and the seventh sample set are fused to obtain a fused sample subset. A specific implementation of fusing the fifth sample set, the sixth sample set, and the seventh sample set may be to directly combine the fifth sample set, the sixth sample set, and the seventh sample set.

[0146] In steps S601 to S605 shown in the embodiment of the present application, by sampling and fusing the first sample set, the second sample set, and the fourth sample set according to the evaluation sample sampling ratio, a fused sample subset is obtained, which can integrate samples from different building types, verified samples, and real-time predicted samples, so that the fused sample subset can comprehensively reflect the damage assessment information of different building types, reflect the real-time target damage assessment information increment of the target building, and reflect the verified target damage assessment information of the target building, so as to ensure the stability, reliability, and accuracy of the confidence threshold after the confidence threshold is updated according to the second damage assessment model, so as to improve the accuracy of damage assessment by the target damage assessment method.

[0147] In some embodiments, the evaluation sample set further includes: generating a sample subset, wherein the generated sample subset has a generated sample number, which is the total number of generated samples; and the fused sample subset has a fused sample number, which is the total number of fused samples. The fused sample number and the generated sample number may be the same or different. That is, the generated sample subset and the fused sample subset are fused in a 1:1 ratio to obtain the evaluation sample set. The second sample set includes at least one positive target building sample and at least one negative target building sample. The positive target building sample indicates that the target building is damaged, while the negative target building sample indicates that the target building is intact.

[0148] See also Figure 7 In some embodiments, step S504 may also include but is not limited to steps S701 to S704:

[0149] Step S701, selecting a target positive sample from the predicted positive samples, the sample building positive samples, and the target building positive samples;

[0150] Step S702: selecting a target negative sample from the predicted negative samples, the sample building negative samples, and the target building negative samples; wherein the target positive sample and the target negative sample come from different sample sets;

[0151] Step S703, linearly adding the target positive sample and the target negative sample according to a preset linear addition ratio to obtain a generated sample;

[0152] Step S704: construct a generated sample subset based on the generated samples.

[0153] In step S701 of some embodiments, a target positive sample may be selected from the predicted positive samples, the sample building positive samples, and the target building positive samples by random sampling.

[0154] In step S702 of some embodiments, a target negative sample may be selected from the predicted negative samples, the sample building negative samples, and the target building negative samples by random sampling. The target positive sample and the target negative sample come from different sample sets to avoid bias in the generated samples due to overly concentrated sample sources.

[0155] In step S703 of some embodiments, a generated sample may be obtained by linearly adding the target positive sample and the target negative sample according to a preset linear addition ratio, wherein the linear addition ratio is used to control whether the generated sample is a positive sample or a negative sample. A specific implementation method of obtaining the generated sample by linearly adding the target positive sample and the target negative sample can be expressed by the following formula:

[0156] ;

[0157] in, Characterize the generated samples, Represent the target positive sample, Characterize the target negative sample, a is the linear addition ratio, and the value range of a is [0.05-0.15] or [0.85-0.95]. If the value range of a is [0.85-0.95], the generated sample is a positive sample, and if the value range of a is [0.05-0.15], the generated sample is a negative sample.

[0158] In some embodiments, the value range of a can be determined based on the number of positive samples and negative samples in the generated sample subset to control the number of positive samples and negative samples in the generated sample subset, so that the ratio of the number of positive samples to the number of negative samples in the evaluation sample set is close to 1:1, that is, the positive and negative samples in the evaluation sample set are balanced, thereby enhancing the feature recognition ability of the second damage assessment model for positive and negative samples, so as to improve the accuracy of damage assessment performed by the target damage assessment method after the confidence threshold of the second damage assessment model is updated.

[0159] In step S704 of some embodiments, a generated sample subset may be constructed based on the generated samples. Specifically, all generated samples may be directly combined into the generated sample subset.

[0160] In steps S701 to S704, as illustrated in the embodiment of the present application, by selecting target positive samples and target negative samples from the first, second, and fourth sample sets and linearly blending the target positive and negative samples to obtain generated samples, multiple samples required for updating the confidence threshold of the second damage assessment model can be quickly generated. This reduces the total number of real samples required for collecting in the assessment sample set, thereby reducing the time cost of collecting real samples, thereby reducing the time cost of updating the confidence threshold of the second damage assessment model and improving the efficiency of updating the confidence threshold of the second damage assessment model. Furthermore, for some special types of buildings, where it is difficult to collect real samples, generating samples by linearly blending the target positive and negative samples can compensate for the shortage of real samples, providing rich and accurate training samples for the confidence threshold of the second damage assessment model, thereby improving the accuracy of the second damage assessment model.

[0161] In step S105 of some embodiments, the target building is the data source for the second sample, used to train the first damage assessment model. Note that the target building's building type is different from that of all sample buildings. The second sample is used to describe at least the target building's actual damage level and sensor data. Therefore, the second sample may include, but is not limited to, second building sensor data and a second damage label. The second building sensor data is sensor data collected from the target building, and the second damage label describes the actual building damage level corresponding to the first building sensor data.

[0162] It should be noted that the type of the second building sensor data is the same as the type of the first building sensor data. For example, if the first building sensor data contains the target temperature, the second building sensor data also needs to contain the target temperature. The type of the second damage label is the same as the type of the first damage label. For example, if the first damage label is a binary label, the second damage label is also a binary label. In addition, the specific embodiment of the second building sensor data can refer to the specific implementation of the first building sensor data. The specific embodiment of the second damage label is similar to the first damage label and can refer to the specific implementation of the first damage label. On this basis, a second sample related to the target building can be obtained. Specifically, a sensor is set on the target building to collect the second building sensor data. The method of collecting the second building sensor data can include but is not limited to: collecting according to a preset sensor data collection instruction or collecting according to a specific period. The specific period can be once a day, once an hour, or once a minute. In addition, since in real life scenarios and scenarios such as building anti-damage capability experiments, buildings are usually complete buildings and the target building can generally only be damaged once, the second damage labels in most second samples will mark the second samples as negative samples.

[0163] In other embodiments, the source of the second sample may also be other buildings of the same building type as the target building, rather than being limited to the target building, so as to improve the collection efficiency of the second sample.

[0164] In other embodiments, the second sample may further describe the building type of the target building. Therefore, the second sample may further include, but is not limited to: a second building type, wherein the second building type is used to describe the building type of the target building.

[0165] In step S106 of some embodiments, the second damage assessment data is used to describe the damage classification type obtained by the first damage assessment model based on the damage assessment of the second building sensor data. The specific implementation of the second damage assessment data is similar to the specific implementation of the first damage assessment data, and reference may be made to the specific implementation of the first damage assessment data, which will not be described in detail in this application. It should be noted that the type of the second damage assessment data is the same as the type of the first damage assessment data. It should be noted that the specific implementation of inputting the second building sensor data into the first damage assessment model for damage assessment to obtain the second damage assessment data is similar to the specific implementation of inputting the first building sensor data into the initial damage assessment model for damage assessment, and the only difference is that the parameters of the first damage assessment model and the initial damage assessment model are different. Therefore, the specific implementation of the second damage assessment data can refer to the specific implementation of the initial damage assessment model, which will not be described in detail in this application.

[0166] In step S107 of some embodiments, a second damage classification loss function is used to describe the difference between the second damage classification data and the second damage label, and can be constructed based on the second damage classification data and the second damage label. It should be noted that the first damage assessment model may include, but is not limited to, a feature extraction module, a target damage classifier, and a target type adversarial classifier. However, since the first damage assessment model is only used to perform damage assessment on the second sample of the target building, that is, it only involves the building type of the target building and not multiple different building types, there is no need to adjust the parameters of the target type adversarial classifier. Therefore, it is only necessary to construct a second damage classification loss function and adjust the parameters of the first damage assessment model based on the second damage classification loss function.

[0167] In step S108 of some embodiments, parameters of the target damage classifier of the first damage assessment model are adjusted based on the second damage classification loss function to obtain a second damage assessment model, which can then be used to perform damage assessment on the target building. A specific implementation of adjusting parameters of the target damage classifier of the first damage assessment model based on the second damage classification loss function may include adjusting the learning rate and performing gradient backpropagation of the first damage assessment model using the Adam method until the second damage classification loss function converges, thereby obtaining the second damage assessment model.

[0168] In some embodiments, a specific implementation of performing damage assessment on a target building using the second damage assessment model includes obtaining target sensor data of the target building and performing damage assessment on the target sensor data using the second damage assessment model to obtain target damage assessment data. It should be noted that since the third building sensor data is continuously collected by sensors deployed on the target building, the second samples can be dynamically updated based on multiple second sample update thresholds, and the second damage classification loss function can be reconstructed based on the dynamically updated second samples, thereby dynamically adjusting the parameters of the second damage assessment model based on the reconstructed second damage classification loss function.

[0169] See also Figure 8 In some embodiments, after step S108, the target damage assessment method may further include but is not limited to steps S801 to S804:

[0170] Step S801: Select an evaluation sample from the evaluation sample set; wherein the evaluation sample includes evaluation building sensor data and verification damage classification labels, and the verification damage classification labels represent the actual damage degree of the evaluation sample;

[0171] Step S802: Input the sensor data of the assessment building into a second damage assessment model to perform damage assessment, thereby obtaining a quality assessment label and an assessment confidence level. The quality assessment label represents the degree of damage obtained by performing damage assessment on the sensor data of the assessment building, and the assessment confidence level is the confidence level of the quality assessment label.

[0172] Step S803, determining a receiver operating characteristic curve of the second damage assessment model based on the quality assessment label, the assessment confidence, and the verification damage classification label;

[0173] Step S804: selecting a target confidence threshold from the receiver operating characteristic curve according to a preset recall rate threshold, and updating the confidence threshold of the second damage assessment model according to the target confidence threshold.

[0174] In step S801 of some embodiments, evaluating the sample includes evaluating building sensor data and verifying that the damage classification label represents the true extent of damage to the sample. Evaluating the building sensor data is used to update the confidence threshold of the second damage assessment model. The specific implementation of evaluating the building sensor data is similar to that of the first building sensor data, and reference may be made to the specific implementation of the first building sensor data. Verifying the damage classification label is used to describe the true extent of damage to the sample. The specific implementation of verifying the damage classification label is similar to that of the first damage label, and reference may be made to the specific implementation of the first damage label.

[0175] In step S802 of some embodiments, the assessment building sensor data is input into a second damage assessment model for damage assessment, resulting in a quality assessment label and an assessment confidence level. The quality assessment label represents the degree of damage obtained from the damage assessment of the assessment building sensor data. Its specific implementation is similar to that of the first damage classification data, and reference can be made to the specific embodiments of the first damage classification data. The assessment confidence level represents the confidence level of the quality assessment label, describing the probability that the quality assessment label is accurate.

[0176] In step S803 of some embodiments, a receiver operating characteristic (ROC) curve of the second damage assessment model can be determined based on the quality assessment label, the assessment confidence, and the verified damage classification label. The receiver operating characteristic (ROC) curve is used to evaluate the performance of the classification model. Specifically, the evaluation samples are first sorted according to the evaluation confidence to obtain an evaluation sample sequence, and a candidate confidence threshold for the second damage assessment model is obtained. The true positive rate of the evaluation samples is then calculated based on each candidate confidence threshold to obtain a candidate true positive rate, and the false positive rate of the evaluation samples is calculated based on each candidate confidence threshold to obtain a candidate false positive rate. Finally, an ROC curve is plotted based on all candidate true positive rates and candidate false positive rates. The true positive rate is also called the recall rate.

[0177] In step S804 of some embodiments, the recall threshold is used to select a target confidence threshold from candidate confidence thresholds. For example, the specific value of the recall threshold can be 80%. On this basis, a target confidence threshold can be selected from the receiver operating characteristic curve based on the preset recall threshold, and the confidence threshold of the second damage assessment model is updated based on the target confidence threshold. Specifically, the recall threshold is first compared with all candidate true positive rates, and the candidate true positive rates greater than the recall threshold are selected as the target true positive rates. Then, the candidate confidence threshold corresponding to the target true positive rate is used as the target confidence threshold. Finally, the target confidence threshold is used to replace the confidence threshold of the second damage assessment model, thereby updating the confidence threshold of the second damage assessment model.

[0178] It should be noted that since the third building sensor data is continuously collected by sensors deployed on the target building, the fourth sample can be dynamically updated based on the third building sensor data collected at different time periods, thereby obtaining a dynamically updated evaluation sample set. The confidence threshold of the second damage assessment model is then dynamically updated based on this dynamically updated evaluation sample set. Furthermore, since the time required to adjust the parameters of the first and second damage assessment models is relatively short after the sensors are deployed on the target building, the confidence threshold of the second damage assessment model is typically updated once or twice.

[0179] In some embodiments, each time after the parameters of the first damage assessment model or the second damage assessment model are adjusted, the confidence threshold of the second damage assessment model can be immediately updated to improve the adaptability of the confidence threshold and parameters of the second damage assessment model, thereby improving the damage assessment accuracy of the second damage assessment model.

[0180] In steps S801 to S804 illustrated in the embodiment of the present application, an evaluation sample is first selected from the evaluation sample set; wherein the evaluation sample includes evaluation building sensor data and verification damage classification labels, and the verification damage classification labels represent the actual damage degree of the evaluation sample. Then, the evaluation building sensor data is input into the second damage assessment model for damage assessment to obtain a quality assessment label and an assessment confidence; wherein the quality assessment label represents the damage degree obtained by performing damage assessment on the evaluation building sensor data, and the assessment confidence is the confidence of the quality assessment label. Finally, the receiver operating characteristic curve of the second damage assessment model is determined based on the quality assessment label, the assessment confidence, and the verification damage classification label, and a target confidence threshold is selected from the receiver operating characteristic curve based on a preset recall rate threshold, so as to update the confidence threshold of the second damage assessment model based on the target confidence threshold. Therefore, the target damage assessment method illustrated in the embodiment of the present application, by determining the target confidence threshold based on the assessment sample and updating the confidence threshold of the second damage assessment model based on the target confidence threshold, can more accurately judge the degree of damage to the target building in subsequent damage assessments by the second damage assessment model, thereby improving the accuracy and reliability of the second damage assessment model.

[0181] See also Figure 9The target damage assessment method illustrated in the embodiment of the present application can be divided into the following four processes: training the initial damage classification model, efficient online training of cross-type models, dynamic adjustment of thresholds in the prediction stage, and deployment and application of the model. In the process of training the initial damage classification model, first, a first sample is obtained from a preset first sample set; wherein the first sample set includes at least two first samples, and the first sample includes first building sensor data and first building type of the sample building, and the first building types of the two first samples are different; then, the first building sensor data is input into the preset initial damage assessment model for damage assessment to obtain first damage assessment data; wherein the first damage assessment data includes: first damage classification data and type classification probability; then, loss is constructed based on the first damage classification data to obtain a first damage classification loss function, and loss is constructed based on the type classification probabilities of at least two sample buildings and the first building type to obtain a building type adversarial loss function; wherein the building type adversarial loss function is used to make at least two sample buildings of different building types approach the same in type classification probability distribution; finally, the initial damage assessment model is trained based on the first damage classification loss function and the building type adversarial loss function to obtain a first damage assessment model. In the efficient online training process for cross-type models, first, sensor data related to the target building is obtained and fed into the first damage assessment model for damage assessment, resulting in a predicted label and prediction confidence. The predicted label represents the degree of damage corresponding to the third building sensor data, and the prediction confidence is the confidence of the predicted label. Then, third samples are selected based on a preset third sample screening threshold, and a third sample set is constructed based on the third samples. Based on this, fourth samples are screened based on a preset fourth sample screening threshold to construct a fourth sample set. Samples are then sampled from the first, second, and fourth sample sets according to a preset evaluation sample sampling ratio to obtain an evaluation sample set. Finally, the second sample set is updated based on the third sample set, and the parameters of the first damage assessment model are adjusted based on the updated second sample set to obtain a second damage assessment model. In the dynamic threshold adjustment process during the prediction phase, evaluation samples are first selected from the evaluation sample set, and then the confidence threshold of the second damage assessment model is updated based on the evaluation samples. In the process of model deployment and application, the second damage assessment model is used to conduct damage assessment on the target building.

[0182] See also Figure 10 The present application also provides a target damage assessment system that can implement the above-mentioned target damage assessment method. The system includes:

[0183] A first sample acquisition module 1001 is configured to acquire a first sample from a preset first sample set; wherein the first sample set includes at least two first samples, each of the first samples including first building sensor data and a first building type of a sample building, and the first building types of the two first samples are different;

[0184] A first damage assessment module 1002 is configured to input the first building sensor data into a preset initial damage assessment model to perform damage assessment and obtain first damage assessment data; wherein the first damage assessment data includes: first damage classification data and type classification probability;

[0185] A first loss construction module 1003 is configured to construct a loss based on the first damage classification data to obtain a first damage classification loss function, and to construct a loss based on the type classification probabilities of at least two sample buildings and the first building type to obtain a building type adversarial loss function. The building type adversarial loss function is configured to ensure that the type classification probability distributions of at least two sample buildings of different building types are close to the same.

[0186] A first training module 1004 is configured to train the initial damage assessment model according to the first damage classification loss function and the building type adversarial loss function to obtain a first damage assessment model;

[0187] A second sample acquisition module 1005 is configured to acquire a second sample related to the target building from a preset second sample set; wherein the second sample includes second building sensor data of the target building;

[0188] A second damage assessment module 1006 is configured to input the second building sensor data into the first damage assessment model to perform damage assessment to obtain second damage assessment data; wherein the second damage assessment data includes second damage classification data;

[0189] A second loss construction module 1007 is configured to construct a loss function based on the second damage classification data to obtain a second damage classification loss function;

[0190] The second training module 1008 is used to adjust the parameters of the target damage classifier of the first damage assessment model according to the second damage classification loss function to obtain a second damage assessment model, so as to perform damage assessment on the target building using the second damage assessment model.

[0191] The specific implementation of the target damage assessment system is basically the same as the specific embodiment of the above-mentioned target damage assessment method, and will not be repeated here.

[0192] The present application also provides an electronic device comprising a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the target damage assessment method. The electronic device can be any smart terminal, such as a tablet computer or an in-vehicle computer.

[0193] See also Figure 11 , Figure 11 The hardware structure of an electronic device according to another embodiment is shown. The electronic device includes:

[0194] The processor 1101 can be implemented as a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of the present application;

[0195] The memory 1102 can be implemented in the form of a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM). The memory 1102 can store an operating system and other application programs. When the technical solutions provided in the embodiments of this specification are implemented through software or firmware, the relevant program code is stored in the memory 1102 and is called by the processor 1101 to execute the target damage assessment method of the embodiments of this application.

[0196] Input / output interface 1103, used to implement information input and output;

[0197] Communication interface 1104, used to implement communication interaction between this device and other devices, which can be achieved through wired means (such as USB, network cable, etc.) or wireless means (such as mobile network, WiFi, Bluetooth, etc.);

[0198] The bus 1105 transmits information between the various components of the device (such as the processor 1101, the memory 1102, the input / output interface 1103 and the communication interface 1104); wherein the processor 1101, the memory 1102, the input / output interface 1103 and the communication interface 1104 realize communication connection with each other within the device through the bus 1105.

[0199] An embodiment of the present application also provides a computer-readable storage medium, which stores a computer program, and when the computer program is executed by a processor, it implements the above-mentioned target damage assessment method. The memory, as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs and non-transitory computer executable programs. In addition, the memory may include a high-speed random access memory, and may also include a non-transitory memory, such as at least one disk storage device, a flash memory device, or other non-transitory solid-state storage device. In some embodiments, the memory may optionally include a memory remotely located relative to the processor, and these remote memories may be connected to the processor via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0200] The target damage assessment method and system, electronic device, and storage medium proposed in the embodiments of the present application use a first damage classification loss function to ensure that the damage classification data output by the first damage assessment model approximates the actual damage level of the building. Furthermore, a building type adversarial loss function is used to ensure that at least two sample buildings of different building types have similar type classification probability distributions. This enables the first damage assessment model to perform damage assessment on the input sensor data based solely on the damage level and not on the building type, thereby improving the damage assessment accuracy of the target damage assessment method for different types of buildings, that is, improving the generalization capability of the target damage assessment method for different types of buildings across scenarios and target types. Furthermore, the target damage assessment method and system, electronic device, and storage medium proposed in this application train an initial damage assessment model based on first samples of different sample buildings to obtain a first damage assessment model, and then train the first damage assessment model using second samples related to the target building to obtain a second damage assessment model. This allows the target damage assessment model to be deployed on a new building type by only collecting a small number of second samples to adjust the parameters of the first damage assessment model to obtain a second damage assessment model with higher accuracy in damage assessment of the target building. This not only allows the target damage assessment method to be quickly and scalably applied to target buildings of new building types, thereby improving the cross-scenario and cross-target type application efficiency of the target damage assessment method, but also shortens the training time of the second damage assessment model, thereby reducing the cost of adapting the target damage assessment method to new building types.

[0201] The embodiments described in the embodiments of this application are intended to more clearly illustrate the technical solutions of the embodiments of this application and do not constitute a limitation on the technical solutions provided by the embodiments of this application. Those skilled in the art will appreciate that with the evolution of technology and the emergence of new application scenarios, the technical solutions provided in the embodiments of this application are also applicable to similar technical problems.

[0202] Those skilled in the art will understand that the technical solutions shown in the figures do not constitute a limitation on the embodiments of the present application, and may include more or fewer steps than shown in the figures, or a combination of certain steps, or different steps.

Claims

1. A target damage assessment method, characterized in that: The method comprises: Obtaining a first sample from a preset first sample set; wherein the first sample set includes at least two first samples, the first sample includes first building sensor data and a first building type of a sample building, and the first building types of the two first samples are different; Inputting the first building sensor data into a preset initial damage assessment model for damage assessment to obtain first damage assessment data; wherein the first damage assessment data includes: first damage classification data and type classification probability; Performing loss construction based on the first damage classification data to obtain a first damage classification loss function, and performing loss construction based on the type classification probabilities of the sample buildings of the at least two first samples and the first building type to obtain a building type adversarial loss function; wherein the building type adversarial loss function is used to ensure that the sample buildings of the at least two first samples of different building types have similar type classification probability distributions; training the initial damage assessment model according to the first damage classification loss function and the building type adversarial loss function to obtain a first damage assessment model; Acquire a second sample related to the target building from a preset second sample set; wherein the second sample includes second building sensor data of the target building; inputting the second building sensor data into the first damage assessment model to perform damage assessment to obtain second damage assessment data; wherein the second damage assessment data includes second damage classification data; Performing loss construction based on the second damage classification data to obtain a second damage classification loss function; The target damage classifier of the first damage assessment model is parameter-adjusted according to the second damage classification loss function to obtain a second damage assessment model, so as to perform damage assessment on the target building using the second damage assessment model.

2. The method according to claim 1, characterized in that Before acquiring the second sample related to the target building from the preset second sample set, the method further includes: Acquiring third building sensor data related to the target building; Inputting the third building sensor data into the first damage assessment model for damage assessment to obtain a prediction label and a prediction confidence; wherein the prediction label represents the damage degree corresponding to the third building sensor data, and the prediction confidence is the confidence of the prediction label; Comparing the prediction confidence with the preset third sample screening threshold to obtain first confidence comparison information; When the first confidence comparison information indicates that the prediction confidence is higher than the third sample screening threshold, selecting the third building sensor data and the prediction label corresponding to the prediction confidence as a third sample; constructing a third sample set according to the third sample; The second sample set is updated according to the third sample set.

3. The method according to claim 2, characterized in that Before updating the second sample set according to the third sample set, the method further includes: Comparing the prediction confidence with the preset fourth sample screening threshold to obtain second confidence comparison information; When the second confidence comparison information indicates that the prediction confidence is higher than the fourth sample screening threshold, selecting the third building sensor data and the prediction label corresponding to the prediction confidence as a fourth sample; constructing a fourth sample set according to the fourth sample; Sample sampling is performed on the first sample set, the second sample set, and the fourth sample set according to a preset evaluation sample sampling ratio to obtain an evaluation sample set.

4. The method according to claim 3, characterized in that The evaluation sample set includes: a fusion sample subset; the first sample set has a first sample number, which is the total number of the first samples; the second sample set has a second sample number, which is the total number of the second samples; the fourth sample set has a fourth sample number, which is the total number of the fourth samples; The step of sampling the first sample set, the second sample set, and the fourth sample set according to a preset evaluation sample sampling ratio to obtain an evaluation sample set includes: Obtaining the first sample number, the second sample number, and the fourth sample number; determining a fifth sample sampling number based on the evaluation sample sampling ratio and the first sample number, determining a sixth sample sampling number based on the evaluation sample sampling ratio and the second sample number, and determining a seventh sample sampling number based on the evaluation sample sampling ratio and the fourth sample number; Collect samples from the first sample set according to the fifth sample sampling number to obtain a fifth sample set; Collect samples from the second sample set according to the sixth sample sampling number to obtain a sixth sample set; Collect samples from the fourth sample set according to the seventh sample sampling number to obtain a seventh sample set; The fifth sample set, the sixth sample set, and the seventh sample set are fused to obtain the fused sample subset.

5. The method according to claim 4, characterized in that The evaluation sample set further includes: generating a sample subset, wherein the fourth sample set includes: at least one predicted positive sample and at least one predicted negative sample, the first sample set includes at least one sample building positive sample and at least one sample building negative sample, and the second sample set includes at least one target building positive sample and at least one target building negative sample; The step of sampling the first sample set, the second sample set, and the fourth sample set according to a preset evaluation sample sampling ratio to obtain an evaluation sample set further includes: Selecting a target positive sample from the predicted positive samples, the sample building positive samples, and the target building positive samples; Selecting a target negative sample from the predicted negative sample, the sample building negative sample, and the target building negative sample; wherein the target positive sample and the target negative sample come from different sample sets; Linearly adding the target positive sample and the target negative sample according to a preset linear addition ratio to obtain a generated sample; The generated sample subset is constructed according to the generated samples.

6. The method according to claim 5, characterized in that After adjusting parameters of the target damage classifier of the first damage assessment model according to the second damage classification loss function to obtain the second damage assessment model, the method further includes: Selecting an evaluation sample from the evaluation sample set; wherein the evaluation sample includes evaluation building sensor data and a verification damage classification label, wherein the verification damage classification label represents the actual damage degree of the evaluation sample; Inputting the sensor data of the assessment building into the second damage assessment model for damage assessment to obtain a quality assessment label and an assessment confidence level; wherein the quality assessment label represents the degree of damage obtained by the damage assessment of the sensor data of the assessment building, and the assessment confidence level is the confidence level of the quality assessment label; determining a receiver operating characteristic curve of the second damage assessment model according to the quality assessment label, the assessment confidence, and the verification damage classification label; A target confidence threshold is selected from the receiver operating characteristic curve according to a preset recall rate threshold, and the confidence threshold of the second damage assessment model is updated according to the target confidence threshold.

7. The method according to claim 1, characterized in that The initial damage assessment model also includes: a feature extraction module and a target type adversarial classifier; The step of inputting the first building sensor data into a preset initial damage assessment model to perform damage assessment to obtain first damage assessment data includes: Performing feature extraction on the first building sensor data by the feature extraction module to obtain a first damage assessment feature; performing target damage classification on the first damage assessment feature by the target damage classifier to obtain the first damage classification data; The first damage assessment feature is subjected to target type adversarial classification by the target type adversarial classifier to obtain the type classification probability.

8. Target damage assessment system, characterized in that: The system comprises: A first sample acquisition module is configured to acquire a first sample from a preset first sample set; wherein the first sample set includes at least two first samples, each of the first samples including first building sensor data and a first building type of a sample building, and the first building types of the two first samples are different; a first damage assessment module, configured to input the first building sensor data into a preset initial damage assessment model for damage assessment to obtain first damage assessment data; wherein the first damage assessment data includes: first damage classification data and type classification probability; a first loss construction module, configured to construct a loss based on the first damage classification data to obtain a first damage classification loss function, and to construct a loss based on the type classification probabilities of the sample buildings of the at least two first samples and the first building type to obtain a building type adversarial loss function; wherein the building type adversarial loss function is configured to ensure that the sample buildings of the at least two first samples of different building types have a similar type classification probability distribution; a first training module, configured to train the initial damage assessment model according to the first damage classification loss function and the building type adversarial loss function to obtain a first damage assessment model; A second sample acquisition module is configured to acquire a second sample related to the target building from a preset second sample set; wherein the second sample includes second building sensor data of the target building; a second damage assessment module, configured to input the second building sensor data into the first damage assessment model for damage assessment to obtain second damage assessment data; wherein the second damage assessment data includes second damage classification data; a second loss construction module, configured to construct a loss function based on the second damage classification data to obtain a second damage classification loss function; The second training module is used to adjust the parameters of the target damage classifier of the first damage assessment model according to the second damage classification loss function to obtain a second damage assessment model, so as to use the second damage assessment model to perform damage assessment on the target building.

9. An electronic device, characterized in that The electronic device includes a memory and a processor, the memory stores a computer program, and the processor implements the target damage assessment method according to any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the target damage assessment method according to any one of claims 1 to 7 is implemented.

Images