Infrastructure data processing method, platform, device and equipment and readable storage medium

Abstract

The invention relates to an infrastructure data processing method, platform and device, computer equipment, a computer readable storage medium and a computer program product. The method comprises the following steps: acquiring capital construction statistical data for a capital construction site, wherein the capital construction statistical data comprises capital construction progress data and a capital construction image associated with the capital construction progress data; performing image recognition on the capital construction image to obtain an image recognition result; verifying the image recognition result and the capital construction progress data to obtain a progress verification result, and marking the progress verification result in the capital construction statistical data; and receiving sensor detection data sent by a sensor in the capital construction site and third-party data related to the capital construction site and sent by a third-party system, and constructing a data pool according to the sensor detection data, the third-party data and the capital construction statistical data marked with the progress verification result. By adopting the method, the capital construction progress of the capital construction site in the power distribution network can be efficiently and accurately analyzed through the data in the data pool.

Description

Technical Field

[0001] The present application relates to the field of big data processing technology, and in particular to an infrastructure data processing method, platform, device, computer equipment, computer-readable storage medium and computer program product. Background Art

[0002] In the process of modern distribution network construction, due to the complexity of the distribution network architecture and the large number of distribution networks, the infrastructure-related data of the distribution network (that is, the data of various construction projects in the distribution network) has become increasingly complex and diversified.

[0003] In this case, the traditional way of managing distribution network infrastructure-related data, which relies on manual records, paper documents and decentralized digital systems, will lead to serious data island effects and make it difficult to verify the authenticity of the collected infrastructure-related data, thus affecting the efficiency and accuracy of analyzing the infrastructure progress of infrastructure sites in the distribution network. Summary of the invention

[0004] Based on this, it is necessary to provide an infrastructure data processing method, device, computer equipment, computer-readable storage medium and computer program product that are conducive to efficiently and accurately analyzing the infrastructure progress of infrastructure sites in distribution networks in response to the above technical problems.

[0005] In a first aspect, the present application provides an infrastructure data processing method, comprising:

[0006] Acquire infrastructure statistical data for the infrastructure site, the infrastructure statistical data including: infrastructure progress data and infrastructure images associated with the infrastructure progress data;

[0007] Perform image recognition on the infrastructure image to obtain the image recognition result;

[0008] Verify the image recognition results and infrastructure progress data to obtain progress verification results, and mark the progress verification results in infrastructure statistical data;

[0009] Receive sensor detection data sent by sensors in the infrastructure site, and third-party data related to the infrastructure site sent by a third-party system, and build a data pool based on the sensor detection data, third-party data, and infrastructure statistical data with marked progress verification results; the data in the data pool is used to analyze the infrastructure progress of the infrastructure site.

[0010] In one embodiment, performing image recognition on the infrastructure image to obtain an image recognition result includes:

[0011] Performing image preprocessing on the infrastructure image to obtain a preprocessed image;

[0012] Extract features from the preprocessed image and generate a feature map;

[0013] Perform image element recognition on the feature map, determine the target element carried by the infrastructure image, and detect the element information of the target element;

[0014] Perform image scene recognition on the feature map to determine the infrastructure scene corresponding to the infrastructure image;

[0015] The element information of the target element carried by the infrastructure image and the infrastructure scene corresponding to the infrastructure image are taken as the image recognition result.

[0016] In one embodiment, the image recognition result is verified with the infrastructure progress data to obtain a progress verification result, including:

[0017] Get multiple progress verification rules;

[0018] According to multiple progress verification rules, the image recognition results and infrastructure progress data are verified to obtain progress verification results.

[0019] In one embodiment, a data pool is constructed based on sensor detection data, third-party data, and infrastructure statistics with annotated progress verification results, including:

[0020] Extract infrastructure project information from sensor detection data, third-party data, and infrastructure statistics with annotated progress verification results;

[0021] Determine multiple infrastructure projects and the project level of each infrastructure project according to the infrastructure project information;

[0022] According to the determined project level, the initial storage space is layered to obtain a plurality of sub-storage spaces; each sub-storage space has its own corresponding project level;

[0023] For each infrastructure project, the sensor detection data, third-party data and infrastructure statistical data associated with the infrastructure project are used as the project data of the infrastructure project, and the project data of the infrastructure project are stored in the sub-storage space corresponding to the project level of the infrastructure project to build a data pool.

[0024] In one embodiment, the infrastructure data processing method further includes:

[0025] Receive data visualization query requests;

[0026] According to the data visualization query request, the data stored in the data pool is visualized and the visualization processing results are fed back.

[0027] In a second aspect, the present application also provides an infrastructure data processing platform, including a cloud and a client;

[0028] The cloud is used to obtain infrastructure statistical data for infrastructure sites synchronized with the client, and the infrastructure statistical data include: infrastructure progress data and infrastructure images associated with the infrastructure progress data; perform image recognition on infrastructure images to obtain image recognition results; verify the image recognition results with the infrastructure progress data to obtain progress verification results, and mark the progress verification results in the infrastructure statistical data; receive sensor detection data sent by sensors in the infrastructure site, and third-party data related to the infrastructure site sent by a third-party system, and build a data pool based on the sensor detection data, third-party data and infrastructure statistical data with marked progress verification results; the data in the data pool is used to analyze the infrastructure progress of the infrastructure site.

[0029] In a third aspect, the present application further provides an infrastructure data processing device, comprising:

[0030] An infrastructure statistical data acquisition module is used to acquire infrastructure statistical data for infrastructure sites, the infrastructure statistical data including: infrastructure progress data and infrastructure images associated with the infrastructure progress data;

[0031] An image recognition module is used to perform image recognition on infrastructure images to obtain image recognition results;

[0032] A matching verification module is used to verify the image recognition results and the infrastructure progress data, obtain the progress verification results, and mark the progress verification results in the infrastructure statistical data;

[0033] The data pool construction module is used to receive sensor detection data sent by sensors in the infrastructure site and third-party data related to the infrastructure site sent by a third-party system, and to build a data pool based on the sensor detection data, third-party data and infrastructure statistical data with marked progress verification results; the data in the data pool is used to analyze the infrastructure progress of the infrastructure site.

[0034] In a fourth aspect, the present application also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor implements the above-mentioned infrastructure data processing method when executing the computer program.

[0035] In a fifth aspect, the present application also provides a computer-readable storage medium on which a computer program is stored, and when the computer program is executed by a processor, the above-mentioned infrastructure data processing method is implemented.

[0036] In a sixth aspect, the present application also provides a computer program product, including a computer program, which implements the above-mentioned infrastructure data processing method when executed by a processor.

[0037] The above-mentioned infrastructure data processing method, device, computer equipment, computer-readable storage medium and computer program product can first obtain infrastructure statistical data for infrastructure sites, and the infrastructure statistical data include: infrastructure progress data and infrastructure images associated with the infrastructure progress data. Further, the image recognition result and the infrastructure progress data can be verified for authenticity to obtain a progress verification result, and then the progress verification result can be annotated for the infrastructure statistical data. Further, the sensor detection data sent by the sensor in the infrastructure site and the third-party data related to the infrastructure site sent by the third-party system can be received, and a data pool can be constructed based on the sensor detection data, the third-party data and the infrastructure statistical data with the annotated progress verification result, so as to fuse multi-source data to analyze the infrastructure progress of the infrastructure site and avoid the generation of data islands. Based on this, the above-mentioned infrastructure data processing method can be used to verify the authenticity of the data and build a data pool in combination with data from multiple sources to avoid data islands, so that the infrastructure progress of the infrastructure site in the distribution network can be efficiently and accurately analyzed based on the data in the data pool. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the drawings required for use in the embodiments of the present application or related technical descriptions will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0039] FIG1 is a diagram showing an application environment of a method for processing infrastructure data in one embodiment;

[0040] FIG2 is a schematic diagram of a flow chart of a method for processing infrastructure data in one embodiment;

[0041] FIG3 is a schematic diagram of an intelligent identification module deployed in the cloud in one embodiment;

[0042] FIG4 is a schematic diagram of a flow chart of a method for collaboratively processing power distribution network infrastructure data based on cloud computing in one embodiment;

[0043] FIG5 is a structural block diagram of an infrastructure data processing device in one embodiment;

[0044] FIG. 6 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0045] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0046] The infrastructure data processing method provided in the embodiment of the present application can be applied to the application environment shown in FIG1. ​​Among them, the cloud 102 can communicate with the client 104, the sensor 106, and the third-party system 108 through the network. Specifically, the cloud 102 can obtain the infrastructure statistical data for the infrastructure site synchronized by the client 104 by communicating with the client 104, and the infrastructure statistical data includes: infrastructure progress data and infrastructure images associated with the infrastructure progress data. Further, the cloud 102 can perform image recognition on the infrastructure image to obtain the image recognition result, and then verify the image recognition result with the infrastructure progress data to obtain the progress verification result, and mark the progress verification result in the infrastructure statistical data. Further, the cloud 102 can receive the sensor detection data sent by the sensor 106 in the infrastructure site, and the third-party data related to the infrastructure site sent by the third-party system 108, so as to build a data pool according to the sensor detection data, the third-party data and the infrastructure statistical data with the marked progress verification result, so that the infrastructure progress of the infrastructure site can be analyzed according to the data in the data pool. Among them, the cloud 102 can specifically be a cloud server that provides cloud computing services. The client 104 may be, but is not limited to, various personal computers, laptops, smart phones, tablet computers, IoT devices, etc.

[0047] In an exemplary embodiment, as shown in FIG2 , a method for processing infrastructure data is provided, which is described by taking the method applied to the cloud 102 in FIG1 as an example, and includes the following steps 202 to 208 . Among them:

[0048] Step 202: Acquire infrastructure statistical data for the infrastructure site, where the infrastructure statistical data includes: infrastructure progress data and infrastructure images associated with the infrastructure progress data.

[0049] Among them, infrastructure statistics include: infrastructure progress data for infrastructure sites in distribution networks (used to record the infrastructure progress of construction projects in distribution networks), quality inspection data (used to record the quality inspection status of construction projects in distribution networks), and safety management data (used to record the safety management status of construction projects in distribution networks).

[0050] Optionally, the client can respond to the data entry instruction triggered by the user and provide the user with a standardized data entry template to ensure the uniformity of the format of the data entered by the user, and then receive the infrastructure statistics of the distribution network entered by the user according to the data entry template, and synchronize the infrastructure statistics to the cloud. Furthermore, the cloud can obtain infrastructure statistics for the infrastructure sites of the distribution network through communication with the client.

[0051] It should be noted that the data entry templates provided by the client include: infrastructure progress data entry template, quality inspection data entry template, and safety management data entry template. Among them, all data entry templates support uploading images. For example, the infrastructure progress data entry template can also include infrastructure image insertion points, which is convenient for users to configure associated infrastructure images for infrastructure progress data representing special progress nodes as supporting materials for infrastructure progress data. Based on this, the cloud can identify whether the relevant infrastructure progress recorded in the infrastructure progress data is true based on the received images to avoid human false reports.

[0052] Step 204: perform image recognition on the infrastructure image to obtain an image recognition result.

[0053] Optionally, an intelligent image recognition mechanism may be deployed in the cloud to perform image recognition on infrastructure images to identify the type, location, and status of equipment included in the infrastructure image, as well as the infrastructure scene corresponding to the infrastructure image, thereby obtaining image recognition results.

[0054] Step 206, verify the image recognition result and the infrastructure progress data to obtain a progress verification result, and mark the progress verification result in the infrastructure statistical data.

[0055] Among them, infrastructure progress data may include the following: in a certain infrastructure scenario, a certain equipment at a certain location is currently in a certain state (the state may refer to any of the installation state, use state, and intact state).

[0056] Optionally, the cloud can verify the image recognition results and the infrastructure progress data according to preset rules to obtain progress verification results to verify the authenticity of the infrastructure images and the infrastructure progress data, obtain progress verification results, and annotate the progress verification results for the infrastructure statistical data.

[0057] In addition, if the progress verification result indicates that the infrastructure image or infrastructure progress data has not passed the verification, the cloud can mark the corresponding infrastructure image or infrastructure progress data in the infrastructure statistical data as "abnormal" and feedback the abnormality to all parties. If the progress verification result indicates that the infrastructure image or infrastructure progress data has passed the verification, the cloud can determine that the corresponding infrastructure image or infrastructure progress data in the infrastructure statistical data is normal and does not need to be marked as "abnormal".

[0058] Step 208, receiving sensor detection data sent by sensors in the infrastructure site and third-party data related to the infrastructure site sent by a third-party system, and constructing a data pool based on the sensor detection data, the third-party data and the infrastructure statistical data with marked progress verification results; the data in the data pool is used to analyze the infrastructure progress of the infrastructure site.

[0059] Optionally, the cloud can also receive sensor detection data sent by sensors in the infrastructure site, and third-party data related to the infrastructure site sent by a third-party system, and build a data pool based on the sensor detection data, third-party data and infrastructure statistical data with marked progress verification results, to achieve the fusion of infrastructure-related data from three sources (multi-source data fusion), so that the infrastructure progress of the infrastructure site can be accurately analyzed based on the data in the data pool. The data in the data pool also facilitates improving the management efficiency and decision-making ability of infrastructure projects in the distribution network, reducing project delays or quality risks.

[0060] For example, the cloud can collect multi-source data through the following channels:

[0061] (1) Client data reception: The client collects infrastructure statistical data uploaded by users (including infrastructure progress data, related infrastructure images, quality inspection data, and safety management data) through standardized data entry templates and synchronizes them to the cloud, which automatically classifies and archives these data.

[0062] (2) Sensor data reception: Sensors deployed in the infrastructure sites of the distribution network (such as environmental monitoring sensors, equipment operation status monitoring sensors, etc.) can monitor data in real time and access the cloud through a gateway to synchronize the monitored data to the cloud. The cloud can automatically store the sensor detection data and associate the received sensor detection data with relevant infrastructure progress data.

[0063] (3) Receiving data from third-party systems: Data interfaces connected to the cloud can be integrated into third-party systems related to distribution network infrastructure projects (such as ERP, PMS, SCADA, etc.) to synchronize third-party data related to infrastructure progress to the cloud on a regular or real-time basis. These third-party data include but are not limited to: equipment procurement arrival time, project approval status, financial data, etc.

[0064] Furthermore, in order to ensure the uniformity and integrity of the multi-source data received by the cloud, the cloud will standardize and clean the various data received. Including: (1) Data format conversion: convert data from different sources into a unified format, such as JSON, XML or a custom structured format, to ensure the consistency of the data in the subsequent analysis process. (2) Data cleaning: automatically process redundant data, abnormal data and incomplete data, such as removing duplicate records, filling missing values, and marking abnormal data to ensure the accuracy and reliability of the data in the data pool. (3) Data normalization: unify the naming rules, units, timestamp formats, etc. of data from different sources, so that data can be smoothly associated and calculated across systems.

[0065] The above-mentioned infrastructure data processing method can first obtain infrastructure statistical data for the infrastructure site, and the infrastructure statistical data includes: infrastructure progress data and infrastructure images associated with the infrastructure progress data. Further, the image recognition result and the infrastructure progress data can be verified for authenticity to obtain the progress verification result, and then the progress verification result can be annotated for the infrastructure statistical data. Further, the sensor detection data sent by the sensor in the infrastructure site and the third-party data related to the infrastructure site sent by the third-party system can be received. According to the sensor detection data, the third-party data and the infrastructure statistical data with the annotated progress verification result, a data pool is constructed to analyze the infrastructure progress of the infrastructure site by fusing multi-source data to avoid the generation of data islands. Based on this, the above-mentioned infrastructure data processing method can be used to verify the authenticity of the data and construct a data pool in combination with data from multiple sources to avoid data islands, so that the infrastructure progress of the infrastructure site in the distribution network can be efficiently and accurately analyzed based on the data in the data pool.

[0066] In an exemplary embodiment, performing image recognition on an infrastructure image to obtain an image recognition result includes:

[0067] Performing image preprocessing on the infrastructure image to obtain a preprocessed image;

[0068] Extract features from the preprocessed image and generate a feature map;

[0069] Perform image element recognition on the feature map, determine the target element carried by the infrastructure image, and detect the element information of the target element;

[0070] Perform image scene recognition on the feature map to determine the infrastructure scene corresponding to the infrastructure image;

[0071] The element information of the target element carried by the infrastructure image and the infrastructure scene corresponding to the infrastructure image are taken as the image recognition result.

[0072] Optionally, the cloud can perform denoising, enhancement, cropping and adjustment on the infrastructure image through a pre-deployed image pre-processing mechanism, thereby achieving image pre-processing of the infrastructure image, obtaining a pre-processed image, and then using the deployed neural network to extract features from the pre-processed image to generate a feature map. Furthermore, the cloud can perform image element recognition on the feature map based on a pre-deployed target detection algorithm, determine the target element carried by the infrastructure image, generate a bounding box for the target element in the infrastructure image, and detect the element information (type, position, state) of the target element within the bounding box. Furthermore, the cloud can perform image scene recognition on the feature map based on a pre-deployed deep learning model, and determine the infrastructure scene corresponding to the infrastructure image. Finally, the element information of the target element carried by the infrastructure image and the infrastructure scene corresponding to the infrastructure image are used as image recognition results.

[0073] Exemplarily, image preprocessing includes: (1) image denoising: using filters, such as Gaussian filtering, to remove noise from photos and improve image clarity; (2) image enhancement: optimizing images through techniques such as brightness adjustment and contrast enhancement to make key details in the image more prominent; (3) image cropping and adjustment: automatically cropping images to focus on key areas, such as equipment installation areas and construction personnel operation areas, based on the description in the infrastructure progress data.

[0074] Exemplarily, feature extraction of the preprocessed image is specifically performed as follows: a convolutional neural network (CNN) is used to extract features in the image and generate a feature map. The convolutional neural network can extract low-level and high-level features in the image layer by layer, such as edges, textures, shapes, etc., through several convolutional layers and pooling layers, and then generate a series of feature maps through convolution operations to represent different features in the image. These feature maps will serve as the basis for subsequent object detection and scene classification.

[0075] The specific structure of the CNN used is as follows: (1) Input layer: the image size is 224×224×3, where 224×224 is the image resolution and 3 is the RGB channel; (2) The first convolution layer: the convolution kernel size is 3×3, the number of convolution kernels is 64, the step size is 1, the activation function is ReLU, and the output is a 224×224×64 feature map; (3) The first pooling layer: the pooling window is 2×2, the step size is 2, and the output is a 112×112×64 feature map; (4) Second convolution layer: convolution kernel size is 3×3, number of convolution kernels is 128, step size is 1, activation function is ReLU, output is 112×112×128 feature map; (5) Second pooling layer: pooling window is 2×2, step size is 2, output is 56×56×128 feature map; (6) Third convolution layer: convolution kernel size is 3×3, number of convolution kernels is 256, step size is 1, activation function is ReLU, output is 56×56×256 feature map; (7) Third pooling layer: The pooling window is 2×2, the stride is 2, and the output is a feature map of 28×28×256; (8) The fourth convolution layer: the convolution kernel size is 3×3, the number of convolution kernels is 512, the stride is 1, the activation function is ReLU, and the output is a feature map of 28×28×512; (9) The fourth pooling layer: the pooling window is 2×2, the stride is 2, and the output is a feature map of 14×14×512; (10) The fifth convolution layer: the convolution kernel size is 3×3, the number of convolution kernels is 512, the stride is 1, and the activation function is ReLU. The function is ReLU, and the output is a 14×14×512 feature map; (11) The fifth pooling layer: the pooling window is 2×2, the step size is 2, and the output is a 7×7×512 feature map; (12) Fully connected layer 1: the number of units is 4096, and the activation function is ReLU; (13) Fully connected layer 2: the number of units is 4096, and the activation function is ReLU; (14) Fully connected layer 3: the number of units is 1000; (15) Output layer: outputs the probability distribution of different categories for object classification. It should be noted that the above parameters can be adjusted according to the specific application scenario.

[0076] Exemplarily, using a target detection algorithm to perform image element recognition on a feature map may include: using a target detection algorithm (such as YOLO or Faster R-CNN) to locate and identify specific objects or scenes in the infrastructure image based on the feature map, that is, identifying the target element, and then specifically detecting the element information of the target element. For example, if the installation progress of a certain device is captured in the infrastructure image, the target detection algorithm can be used to automatically identify the device (identify the target element), and detect the type, location, shape, whether it is intact, which installation progress it is in, and other information (identify element information) of the device, and generate a bounding box for the identified device to accurately locate the area of ​​the device in the image, and mark the category, location, status, and other information of the device in the infrastructure image. Among them, YOLO is a target detection algorithm based on a single neural network, and Faster R-CNN is a target detection algorithm based on a region-based convolutional neural network.

[0077] In this embodiment, the YOLO algorithm used can be jointly implemented by an input layer, a feature extraction layer, a detection layer, and an output layer. Specifically, (1) Input layer: an RGB image of size 448×448×3 or 416×416×3 can be input, and the specific input size can also be determined according to the YOLO version. The input RGB image can be an infrastructure image containing the equipment installation site, and the input layer can normalize the input infrastructure image to reduce the influence of factors such as lighting and color. (2) Feature extraction layer: The feature extraction part of YOLO usually uses a pre-trained convolutional neural network (CNN) as the backbone network (Backbone), such as Darknet-53, which is the backbone network used in YOLOv3 and contains 53 convolutional layers, which can effectively capture features of different scales. The feature extraction part of YOLO can also include a pooling layer. In this case, multi-layer convolution operations are used to extract low-level and high-level features of the image, including edges, textures, shapes, etc., and the pooling layer can be used to gradually reduce the spatial dimension of the feature map while keeping the key features intact. (3) Detection layer: The feature map output by the feature extraction layer is passed to the detection layer for predicting the bounding box and category probability of each grid. In the detection layer, grid division is performed so that the input image is divided into S×S grids (for example, 13×13), and each grid is responsible for detecting an object in an area of ​​the image. In the detection layer, bounding box prediction can also be performed: B bounding boxes are predicted for each grid (usually B=3), and each bounding box contains 5 regression parameters: center coordinates (x, y), width w, height h, and confidence score. The confidence score indicates the probability that the bounding box contains an object and the accuracy of the bounding box. Furthermore, in the detection layer, category probability prediction can also be performed: for each bounding box, the probability distribution of the C categories to which the object belongs is also predicted. (4) In the output layer, output tensor: The final output is a S×S×(B×5+C) tensor, which contains the bounding box coordinates, confidence, and category probabilities of all grids. Among them, the NMS algorithm (non-maximum suppression algorithm) can be used in the output layer to remove redundant bounding boxes and only retain the boxes with the highest confidence.

[0078] The above YOLO algorithm can help identify the progress of equipment installation in the digital infrastructure of the distribution network, that is, the element information of the target element, such as the installation status of equipment such as transformers, switches, and distribution boxes. The specific application process is as follows: (1) Image input: Input the image of the equipment installation site, and input it into the YOLO network after preprocessing. (2) Feature extraction: Use the above CNN structure (such as Darknet-53) to extract image features and generate feature maps of multiple scales, covering features from low-level to high-level. (3) Object detection: Divide the image into grids, detect the objects in each grid, and predict its bounding box and category probability. It can also identify the location, shape, integrity and other information of the equipment. (4) Output result: YOLO outputs information including bounding box coordinates, confidence scores and category labels. That is, when a specific device (such as a transformer) is detected, YOLO generates a bounding box and marks the device category and location to facilitate subsequent analysis and processing. (5) Post-processing of results: Use the NMS algorithm to remove overlapping bounding boxes to ensure that only one bounding box is generated for each device. The output bounding box will accurately locate the location of the device. Ultimately, the detection results will display information such as the type, location, and installation progress of the device, that is, the element information of the target element in the infrastructure image.

[0079] Exemplarily, a deep learning model is used to perform image scene recognition on the feature map, and then the recognized infrastructure image is matched and verified with the infrastructure progress data, mainly to determine whether the construction scene displayed by the infrastructure image is consistent with the progress description entered by the user in the infrastructure progress data. For example, when classifying the scene, it is determined whether the infrastructure image shows the foundation pit excavation stage or the concrete pouring stage, and then it is matched and verified with the description in the infrastructure progress data. Among them, the deep learning model can use multi-label classification technology to identify multiple related construction stages in the infrastructure image.

[0080] In some embodiments, as shown in FIG3 , an intelligent recognition module may be deployed in the cloud, and the intelligent recognition module may include an image preprocessing submodule, a key element recognition submodule, an object detection submodule, a scene classification submodule, and an anomaly detection submodule. Among them, the image preprocessing submodule is used to perform image preprocessing on the infrastructure image to obtain a preprocessed image; the key element recognition submodule is used to extract features from the preprocessed image and generate a feature map; the object detection submodule is used to perform image element recognition on the feature map, determine the target element carried by the infrastructure image, and detect the element information of the target element; the scene classification submodule is used to perform image scene recognition on the feature map to determine the infrastructure scene corresponding to the infrastructure image; the anomaly detection submodule is used to use the element information of the target element carried by the infrastructure image and the infrastructure scene corresponding to the infrastructure image as the image recognition result. Based on this, the cloud can also integrate the infrastructure statistical data uploaded by the client, the sensor detection data sent by the sensor, and the third-party data generated by the third-party system.

[0081] In this embodiment, a variety of algorithms can be combined to perform intelligent recognition on infrastructure images to obtain image recognition results, thereby ensuring the accuracy of subsequent verification based on the image recognition results.

[0082] In some embodiments, the image recognition result and the infrastructure progress data are verified to obtain a progress verification result, and the progress verification result is marked in the infrastructure statistical data, including:

[0083] Get multiple progress verification rules;

[0084] According to multiple progress verification rules, the image recognition results and infrastructure progress data are verified to obtain progress verification results.

[0085] The multiple progress verification rules may specifically include: construction phase sequence rules, key node completion rules, time progress rules, and image content requirement rules.

[0086] Optionally, the cloud can verify the element information of the target element in the image recognition result (the type, location, and status of the equipment included in the infrastructure image) and the type, location, and status of the equipment recorded in the infrastructure progress data according to multiple progress verification rules, and obtain the progress verification result in percentage form. Among them, the percentage represents: the proportion of passed verification. If the progress verification result is lower than the preset percentage threshold, it is determined that the infrastructure image and infrastructure progress data in the infrastructure statistical data have not passed the verification as a whole, and an abnormality report is automatically generated. The abnormality report includes the abnormality type, specific problem description, related images, and recommended treatment measures, etc., and the abnormality report is fed back to the client of the corresponding project leader for abnormal reminder. It should be noted that there can be multiple infrastructure images. In the case of multiple images, the cloud can average the progress verification results in percentage form corresponding to the multiple infrastructure images, and then determine the final progress verification result based on the comparison result of the averaged percentage value with the preset percentage threshold.

[0087] Exemplarily, the progress verification rules are as follows: (1) Construction progress rules are rules set according to the order of construction phases in the project plan. For example, foundation excavation must be completed before concrete pouring can be carried out, and equipment installation can only be carried out after concrete pouring is completed. If the infrastructure progress data records the later executed phase but not the earlier executed phase, it is determined that this part has not passed the verification. (2) Key node completion rules are rules set based on the completion order of nodes with dependencies in the project plan. For example, foundation construction is completed → equipment arrives → equipment installation is completed. Some nodes may have strong correlations. For example, a certain equipment must arrive on site after the foundation construction is completed. If the cloud detects that the node representing the equipment arrival in the infrastructure progress data has been completed, but does not detect the infrastructure image representing the completion of the foundation construction, then this part of the data will fail to pass the verification. In other words, when it is detected that a node in the infrastructure progress data has been completed, but the node on which the node depends has not been completed, it will be determined that it has not passed the verification. (3) Time progress rules are time window rules for each stage set according to the overall project schedule. For example, if the completion time of a certain stage is N, if the corresponding image content is not identified in the infrastructure image before the end of the time window, or if the relevant content is not recorded in the infrastructure progress data, it is determined that the verification has not been passed. (4) Image content requirement rules are set quality rules for uploading infrastructure images, such as setting parameters such as resolution, clarity, and exposure to ensure that the infrastructure image is clear enough to be accurately identified. If the quality of the infrastructure image is too low, the cloud will also determine that it has not passed the verification and require retransmission.

[0088] Exemplarily, taking the cloud-deployed intelligent recognition module shown in FIG3 as an example, a plurality of progress verification rules may be configured in the anomaly detection submodule. Based on this, the anomaly detection submodule may verify the element information of the target element in the image recognition result (output by the object detection submodule), the infrastructure scene in the image recognition result (output by the scene classification submodule), and the infrastructure progress data according to the plurality of progress verification rules to obtain a progress verification result.

[0089] In this embodiment, multiple progress verification rules can be used to effectively ensure the authenticity of the infrastructure progress reflected by the infrastructure statistical data.

[0090] In one embodiment, a data pool is constructed based on sensor detection data, third-party data, and infrastructure statistics with annotated progress verification results, including:

[0091] Extract infrastructure project information from sensor detection data, third-party data, and infrastructure statistics with annotated progress verification results;

[0092] Determine multiple infrastructure projects and the project level of each infrastructure project according to the infrastructure project information;

[0093] According to the determined project level, the initial storage space is layered to obtain a plurality of sub-storage spaces; each sub-storage space has its own corresponding project level;

[0094] For each infrastructure project, the sensor detection data, third-party data and infrastructure statistical data associated with the infrastructure project are used as the project data of the infrastructure project, and the project data of the infrastructure project are stored in the sub-storage space corresponding to the project level of the infrastructure project to build a data pool.

[0095] The infrastructure project information may include the number, name, and project level of the infrastructure project.

[0096] Optionally, the cloud can manage the storage space in layers. Specifically, first, according to the field names related to the project, the infrastructure project information is extracted from the sensor detection data, third-party data, and infrastructure statistics with marked progress verification results. Then, based on the infrastructure project information, multiple infrastructure projects and the project level of each infrastructure project are determined, so that the initial storage space is layered according to the determined project level to obtain multiple sub-storage spaces. Then, for each infrastructure project, the cloud can use the sensor detection data, third-party data, and infrastructure statistics (including infrastructure progress data, infrastructure images, quality inspection data, and safety management data) associated with the infrastructure project as the project data of the infrastructure project, and store the project data of the infrastructure project in the sub-storage space corresponding to the project level of the infrastructure project to build a data pool.

[0097] Exemplarily, among multiple sub-storage spaces, the top layer may be the entire engineering project, and each engineering project is subdivided into several small projects. The sub-storage space corresponding to each small project stores the infrastructure statistical data of the small project (including the infrastructure progress data, infrastructure images, quality inspection data, safety management data of the small project), sensor detection data and third-party data to form data sets for different small projects.

[0098] Furthermore, security access control measures can be configured in the data pool to protect sensitive information, and hierarchical authority control measures can be adopted to assign access rights according to user roles. Project managers, engineers, and external auditors can access data at different levels and scopes to ensure that the use of data complies with security regulations. In addition, the data in the data pool can also be encrypted and stored to prevent data leakage or tampering, while supporting data backup and recovery functions.

[0099] In this embodiment, the efficiency and accuracy of subsequent analysis of infrastructure conditions based on the data in the data pool can be improved through hierarchical management of multi-source data in the data pool, and security measures can be taken on the data in the data pool to ensure the security of distribution network infrastructure-related data.

[0100] In one embodiment, the infrastructure data processing method further includes:

[0101] Receive data visualization query requests;

[0102] According to the data visualization query request, the data stored in the data pool is visualized and the visualization processing results are fed back.

[0103] Optionally, the client has a visualization function, and the user can send a data visualization query request to the cloud through the client. The cloud can receive the data visualization query request and, based on the data visualization query request, visualize the data stored in the data pool. For example, the data requested by the client is processed into a chart, a Gantt chart, or a dashboard, and the visualization processing result is then fed back to the client, so that the user can have a comprehensive understanding of the infrastructure-related data in the distribution network through the client with visualization function, thereby realizing the monitoring and analysis of the infrastructure situation.

[0104] For example, the cloud can also automatically generate progress reports, quality analysis reports, safety assessment reports, etc. based on the data stored in the data pool to provide support for project decision-making. It can also analyze the progress data in the data pool, combined with historical data and sensor detection information, to provide early warning of potential construction delays or quality problems, and provide visual feedback of progress reports, quality analysis reports, safety assessment reports, early warning prompts, etc. to the user's client.

[0105] In this embodiment, a visualization function of infrastructure-related data can be provided for users, so that users can fully grasp the infrastructure-related data and provide decision-making support for users.

[0106] In a detailed embodiment, as shown in FIG4 , a schematic diagram of a method for collaboratively processing power distribution network infrastructure data based on cloud computing is provided, which mainly includes the following steps:

[0107] Step 402, obtaining infrastructure statistical data for the infrastructure site; the infrastructure statistical data includes: infrastructure progress data and infrastructure images associated with the infrastructure progress data;

[0108] Step 404, performing image preprocessing on the infrastructure image to obtain a preprocessed image;

[0109] Step 406, extracting features from the preprocessed image to generate a feature map;

[0110] Step 408, performing image element recognition on the feature image, determining the target element carried by the infrastructure image, and detecting element information of the target element;

[0111] Step 410, performing image scene recognition on the feature map to determine the infrastructure scene corresponding to the infrastructure image;

[0112] Step 412, taking the element information of the target element carried by the infrastructure image and the infrastructure scene corresponding to the infrastructure image as the image recognition result;

[0113] Step 414, verifying the image recognition result and the infrastructure progress data according to the plurality of progress verification rules, obtaining a progress verification result, and marking the progress verification result in the infrastructure statistical data;

[0114] Step 416, receiving sensor detection data sent by sensors in the infrastructure site, and third-party data related to the infrastructure site sent by a third-party system;

[0115] Step 418, extracting infrastructure project information from sensor detection data, third-party data, and infrastructure statistical data with marked progress verification results;

[0116] Step 420, determining a plurality of infrastructure projects and a project level of each infrastructure project according to the infrastructure project information;

[0117] Step 422, according to the determined project level, the initial storage space is layered to obtain a plurality of sub-storage spaces; each sub-storage space has its own corresponding project level;

[0118] Step 424: for each infrastructure project, the sensor detection data, third-party data and infrastructure statistical data associated with the infrastructure project are used as project data of the infrastructure project, and stored in the sub-storage space corresponding to the project level of the infrastructure project to build a data pool;

[0119] Step 426, receiving a data visualization query request, performing visualization processing on the data stored in the data pool according to the data visualization query request, and feeding back the visualization processing result.

[0120] It should be understood that, although the steps in the flowcharts involved in the above embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps is not strictly limited in order, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above embodiments may include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0121] In a possible implementation, the present application further provides an infrastructure data processing platform, including a cloud and a client, wherein the cloud can be used to execute the various embodiments involved in the above infrastructure data processing method, and the client can be used to collect infrastructure statistical data for the cloud, wherein:

[0122] The cloud is used to obtain infrastructure statistical data for infrastructure sites synchronized with the client, and the infrastructure statistical data includes: infrastructure progress data and infrastructure images associated with the infrastructure progress data; perform image recognition on the infrastructure images to obtain image recognition results; match and verify the image recognition results with the infrastructure progress data to obtain progress verification results of the infrastructure progress data, and annotate the progress verification results for the infrastructure progress data; receive sensor detection data sent by sensors in the infrastructure site, and third-party data related to the infrastructure site sent by a third-party system, and build a data pool based on the sensor detection data, third-party data and infrastructure progress data with annotated progress verification results; the data in the data pool is used to analyze the infrastructure progress of the infrastructure site.

[0123] The above-mentioned infrastructure data processing platform can first obtain infrastructure statistical data for the infrastructure site, and the infrastructure statistical data includes: infrastructure progress data and infrastructure images associated with the infrastructure progress data. Further, the image recognition result and the infrastructure progress data can be verified for authenticity to obtain the progress verification result, and then the progress verification result can be annotated for the infrastructure statistical data. Further, the sensor detection data sent by the sensor in the infrastructure site and the third-party data related to the infrastructure site sent by the third-party system can be received. According to the sensor detection data, the third-party data and the infrastructure statistical data with the annotated progress verification result, a data pool is constructed to analyze the infrastructure progress of the infrastructure site by fusing multi-source data to avoid the generation of data islands. Based on this, the above-mentioned infrastructure data processing method can be used to verify the authenticity of the data and construct a data pool in combination with data from multiple sources to avoid data islands, so that the infrastructure progress of the infrastructure site in the distribution network can be efficiently and accurately analyzed based on the data in the data pool.

[0124] Based on the same inventive concept, the embodiment of the present application also provides an infrastructure data processing device for implementing the infrastructure data processing method involved above. The implementation solution provided by the device to solve the problem is similar to the implementation solution recorded in the above method, so the specific limitations in one or more infrastructure data processing device embodiments provided below can refer to the limitations of the infrastructure data processing method above, and will not be repeated here.

[0125] In an exemplary embodiment, as shown in FIG5 , an infrastructure data processing device is provided, comprising: an infrastructure statistical data acquisition module 502, an image recognition module 504, a matching verification module 506 and a data pool construction module 508, wherein:

[0126] An infrastructure statistical data acquisition module is used to acquire infrastructure statistical data for infrastructure sites, the infrastructure statistical data including: infrastructure progress data and infrastructure images associated with the infrastructure progress data;

[0127] An image recognition module is used to perform image recognition on infrastructure images to obtain image recognition results;

[0128] A matching verification module is used to verify the image recognition results and the infrastructure progress data, obtain the progress verification results, and mark the progress verification results in the infrastructure statistical data;

[0129] The data pool construction module is used to receive sensor detection data sent by sensors in the infrastructure site and third-party data related to the infrastructure site sent by a third-party system, and to build a data pool based on the sensor detection data, third-party data and infrastructure statistical data with marked progress verification results; the data in the data pool is used to analyze the infrastructure progress of the infrastructure site.

[0130] The above-mentioned infrastructure data processing device can first obtain infrastructure statistical data for the infrastructure site, and the infrastructure statistical data includes: infrastructure progress data and infrastructure images associated with the infrastructure progress data. Further, the image recognition result and the infrastructure progress data can be verified for authenticity to obtain a progress verification result, and then the progress verification result can be annotated for the infrastructure statistical data. Further, the sensor detection data sent by the sensor in the infrastructure site and the third-party data related to the infrastructure site sent by the third-party system can be received, and a data pool can be constructed based on the sensor detection data, the third-party data and the infrastructure statistical data with the annotated progress verification result, so as to integrate multi-source data to analyze the infrastructure progress of the infrastructure site and avoid the generation of data islands. Based on this, the above-mentioned infrastructure data processing method can be used to verify the authenticity of the data and build a data pool in combination with data from multiple sources to avoid data islands, so that the infrastructure progress of the infrastructure site in the distribution network can be efficiently and accurately analyzed based on the data in the data pool.

[0131] In one of the embodiments, the image recognition module is also used to: perform image preprocessing on the infrastructure image to obtain a preprocessed image; perform feature extraction on the preprocessed image to generate a feature map; perform image element recognition on the feature map to determine the target element carried by the infrastructure image, and detect the element information of the target element; perform image scene recognition on the feature map to determine the infrastructure scene corresponding to the infrastructure image; and use the element information of the target element carried by the infrastructure image and the infrastructure scene corresponding to the infrastructure image as the image recognition result.

[0132] In one of the embodiments, the matching verification module is further used to: obtain multiple progress verification rules; verify the image recognition results and infrastructure progress data according to the multiple progress verification rules to obtain progress verification results.

[0133] In one of the embodiments, the data pool construction module is also used to: extract infrastructure project information from sensor detection data, third-party data and infrastructure statistical data with marked progress verification results; determine multiple infrastructure projects and the project level of each infrastructure project based on the infrastructure project information; layer the initial storage space according to the determined project level to obtain multiple sub-storage spaces; each sub-storage space has its own corresponding project level; for each infrastructure project, use the sensor detection data, third-party data and infrastructure statistical data associated with the infrastructure project as the project data of the infrastructure project, and store the project data of the infrastructure project in the sub-storage space corresponding to the project level of the infrastructure project to construct a data pool.

[0134] In one of the embodiments, the infrastructure data processing device also includes a visualization processing module, which is used to receive a data visualization query request; according to the data visualization query request, the data stored in the data pool is visualized and the visualization processing result is fed back.

[0135] Each module in the above-mentioned infrastructure data processing device can be implemented in whole or in part by software, hardware or a combination thereof. Each of the above-mentioned modules can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute the operations corresponding to each of the above modules.

[0136] In an exemplary embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be shown in FIG6. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. The processor, the memory and the input / output interface are connected via a system bus, and the communication interface is connected to the system bus via the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store infrastructure data processing data. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a method for processing infrastructure data is implemented.

[0137] Those skilled in the art will understand that the structure shown in FIG. 6 is merely a block diagram of a partial structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different arrangement of components.

[0138] In an exemplary embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above-mentioned method embodiments when executing the computer program.

[0139] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0140] In one embodiment, a computer program product is provided, including a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0141] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0142] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., but are not limited to this.

[0143] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0144] The above embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A method for processing infrastructure data, characterized in that: The method comprises: Acquire infrastructure statistical data for the infrastructure site, the infrastructure statistical data comprising: infrastructure progress data and infrastructure images associated with the infrastructure progress data; Performing image recognition on the infrastructure image to obtain an image recognition result; Verifying the image recognition result and the infrastructure progress data to obtain a progress verification result, and marking the progress verification result in the infrastructure statistical data; Receive sensor detection data sent by sensors in the infrastructure site and third-party data related to the infrastructure site sent by a third-party system, and build a data pool based on the sensor detection data, the third-party data and the infrastructure statistical data marked with the progress verification result; the data in the data pool is used to analyze the infrastructure progress of the infrastructure site.

2. The method according to claim 1, characterized in that The performing image recognition on the infrastructure image to obtain an image recognition result includes: Performing image preprocessing on the infrastructure image to obtain a preprocessed image; Performing feature extraction on the preprocessed image to generate a feature map; Performing image element recognition on the feature image, determining the target element carried by the infrastructure image, and detecting element information of the target element; Performing image scene recognition on the feature map to determine the infrastructure scene corresponding to the infrastructure image; The element information of the target element carried by the infrastructure image and the infrastructure scene corresponding to the infrastructure image are taken as the image recognition result.

3. The method according to claim 1, characterized in that The verifying the image recognition result and the infrastructure progress data to obtain a progress verification result includes: Get multiple progress verification rules; According to the plurality of progress verification rules, the image recognition result and the infrastructure progress data are verified to obtain a progress verification result.

4. The method according to claim 1, characterized in that: The step of constructing a data pool based on the sensor detection data, the third-party data, and the infrastructure statistical data marked with the progress verification results includes: Extracting infrastructure project information from the sensor detection data, the third-party data, and the infrastructure statistical data marked with the progress verification results; Determine, according to the infrastructure project information, a plurality of infrastructure projects and a project level of each of the infrastructure projects; According to the determined project level, the initial storage space is layered to obtain a plurality of sub-storage spaces; each of the sub-storage spaces has a corresponding project level; For each of the infrastructure projects, the sensor detection data, third-party data and infrastructure statistical data associated with the infrastructure project are used as the project data of the infrastructure project, and the project data of the infrastructure project are stored in the sub-storage space corresponding to the project level of the infrastructure project to build a data pool.

5. The method according to claim 1, characterized in that The method further comprises: Receive data visualization query requests; According to the data visualization query request, the data stored in the data pool is visualized and the visualization processing result is fed back.

6. An infrastructure data processing platform, characterized in that: Including cloud and client; The cloud end is used to obtain infrastructure statistical data for the infrastructure site synchronized with the client, the infrastructure statistical data including: infrastructure progress data and infrastructure images associated with the infrastructure progress data; perform image recognition on the infrastructure image to obtain an image recognition result; verify the image recognition result with the infrastructure progress data to obtain a progress verification result, and mark the progress verification result in the infrastructure statistical data; receive sensor detection data sent by sensors in the infrastructure site and third-party data related to the infrastructure site sent by a third-party system, and construct a data pool based on the sensor detection data, the third-party data and the infrastructure statistical data marked with the progress verification result; the data in the data pool is used to analyze the infrastructure progress of the infrastructure site.

7. An infrastructure data processing device, characterized in that: The device comprises: An infrastructure statistical data acquisition module is used to acquire infrastructure statistical data for an infrastructure site, wherein the infrastructure statistical data includes: infrastructure progress data and infrastructure images associated with the infrastructure progress data; An image recognition module is used to perform image recognition on the infrastructure image to obtain an image recognition result; A matching verification module, used for verifying the image recognition result and the infrastructure progress data, obtaining a progress verification result, and marking the progress verification result in the infrastructure statistical data; A data pool construction module is used to receive sensor detection data sent by sensors in the infrastructure site and third-party data related to the infrastructure site sent by a third-party system, and to construct a data pool based on the sensor detection data, the third-party data and the infrastructure statistical data marked with the progress verification results; the data in the data pool is used to analyze the infrastructure progress of the infrastructure site.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 5 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 5 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 5 are implemented.

Images