Building safety data acquisition method and device and storage medium

Abstract

The invention discloses a building safety data acquisition method and device and a storage medium, and relates to the technical field of data processing, and the method comprises the steps: carrying out the analysis and preprocessing of a sensor communication signal when it is detected that the sensor communication signal exists in a base station coverage area, and obtaining initial safety detection data; determining detection sub-regions based on the position coordinates of the sensor, and dividing the initial security detection data according to the detection sub-regions to obtain sub-region security detection data corresponding to each detection sub-region; the sub-region security detection data are packaged into data blocks, and each piece of sub-region security detection data corresponds to one data block; and adding the target data block passing the verification to the block chain of the network node. The method can be adapted to large-scale data expansion, when a sensor is newly added or a detection sub-region is newly added, the corresponding data can be directly packaged into a new block to be chained, an existing data storage structure does not need to be changed, and the building safety data collection efficiency is improved.

Description

Technical Field

[0001] This application relates to the field of data processing technology, and in particular to a method, device and storage medium for collecting building safety data. Background Technology

[0002] In existing safety data acquisition methods, safety detection sensor nodes are typically deployed in each detection area. These sensors collect building structure and environmental safety data in real time and upload the data to a local server deployed on-site via wired transmission or short-range wireless communication technology. The local server adopts a static storage architecture based on file directories, creating independent root directories according to the detection area name, and categorizing the data uploaded by sensors in the corresponding area into these directories. Simultaneously, manual configuration of data naming conventions is required, embedding data type identifiers, collection timestamps, and other information into filenames to achieve initial data differentiation and management.

[0003] When new sensors are deployed or the detection sub-area needs to be expanded, maintenance personnel must log in to the local server and manually perform directory creation operations, adding a root directory corresponding to the sub-area or a data sub-directory corresponding to the sensor. Simultaneously, the server storage partition quota allocation must be adjusted, and the offline data classification rule document must be updated. Each time a new device or expanded area is added, the existing storage directory structure, partition configuration, and classification rules must be manually adapted and adjusted. This lack of dynamic adaptive capability makes it difficult to meet the expansion needs of a large-scale increase in the number of sensors and a continuously expanding detection range. Summary of the Invention

[0004] The main purpose of this application is to provide a method, device and storage medium for collecting building safety data, aiming to solve the technical problem of how to improve the efficiency of building safety data collection.

[0005] To address the aforementioned problems, this application provides a method for collecting building safety data, which includes: When a sensor communication signal is detected within the base station coverage area, the sensor communication signal is parsed and preprocessed to obtain initial security detection data; Based on the sensor position coordinates, a detection sub-region is determined, and the initial security detection data is divided according to the detection sub-region to obtain the sub-region security detection data corresponding to each detection sub-region. The sub-region security detection data is encapsulated into data blocks, wherein each sub-region security detection data corresponds to one data block; The target data block that passes verification will be added to the blockchain of the network node.

[0006] In one embodiment, the step of obtaining security detection data stored in the blockchain through the query interface based on blockchain nodes includes: When human activity is detected, or when the preset collection period is reached, the sensor is controlled to collect data and obtain analog signals. The analog signal is converted into a digital signal, and initial security detection data is generated based on the digital signal, sensor identifier, acquisition timestamp, and acquisition location coordinates.

[0007] In one embodiment, the method for collecting building safety data further includes: Time-series data is generated based on timestamps and historical security detection data. The time series data is input into a preset prediction model to predict future security detection data and obtain the prediction trend; The collection period is adjusted based on the predicted trend.

[0008] In one embodiment, the step of encapsulating the sub-region security detection data into data blocks includes: A block header is generated based on the block number, the hash value of the previous block, and the data digest block generation timestamp; and a block body is generated based on the sub-region security detection data. The data block is generated by combining the block header and the block body.

[0009] In one embodiment, after the step of adding the verified target data block to the blockchain of the network node, the method for collecting building security data further includes: Based on the query interface of the blockchain node, obtain the security detection data of the sub-region stored in the blockchain; Based on the timestamp and sensor type identifier, determine the total regional geomorphic stability score, total climate impact coefficient, and building compliance rate for each region from the security detection data; The total score of topographic stability, the total coefficient of climate influence, and the building compliance rate are input into a preset building assessment model to conduct building assessments for each of the regions, and the assessment results are obtained.

[0010] In one embodiment, the step of determining the total regional geomorphic stability score, total climate impact coefficient, and building compliance rate for each region from the security detection data based on the timestamp and sensor type identifier includes: Based on the timestamp and the geomorphological sensor type identifier, soil moisture, surface vibration frequency, first foundation settlement, and terrain slope are obtained; The soil moisture, the surface vibration frequency, the first foundation settlement, and the terrain slope are matched with preset soil stability scoring rules to determine the total geomorphic stability score of the region. Based on the timestamp and climate sensor type identifier, obtain rainfall, temperature variation, and wind speed; The total climate impact coefficient is determined by matching the rainfall, temperature variation, and wind force level with a preset climate impact coefficient determination rule. Based on the timestamp and the building structure sensor type identifier, the wall crack width, beam and column tilt angle, and second foundation settlement are obtained. The building compliance rate is determined based on the width of the wall cracks, the inclination angle of the beams and columns, and the settlement of the second foundation.

[0011] In one embodiment, the building assessment model is a pre-trained random forest model. The step of inputting the total landform stability score, the total climate impact coefficient, and the building compliance rate into the preset building assessment model to conduct building assessments for each of the regions and obtain assessment results includes: The total score of landform stability, the total coefficient of climate influence, and the building compliance rate are normalized, and an input feature vector is generated based on the normalization result. The input feature vector is input into the random forest model, and the input feature vector is split layer by layer according to the preset splitting rules to obtain the initial classification result and initial regression value of a single decision tree; The classification result that appears most frequently is determined as the target classification result, and the mean of the initial regression values ​​is determined as the evaluation score.

[0012] In one embodiment, after the step of inputting the total geomorphic stability score, the total climate impact coefficient, and the building compliance rate into a preset building assessment model to conduct building assessments for each of the regions and obtain assessment results, the method for collecting building safety data further includes: The initial template is obtained by matching the judgment level corresponding to the evaluation result with the preset suggestion template; The building assessment report is obtained by filling the placeholders in the initial template with the total score of topographic stability, the total coefficient of climate influence, and the building compliance rate.

[0013] In addition, to achieve the above objectives, this application also proposes a building safety data acquisition device, the device comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the building safety data acquisition method described above.

[0014] In addition, to achieve the above objectives, this application also proposes a storage medium, which is a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, it implements the steps of the building safety data acquisition method described above.

[0015] This application provides a method for collecting building safety data. It obtains effective initial safety detection data by parsing and preprocessing sensor communication signals. Data is divided into detection sub-regions based on sensor location coordinates, and the data from each sub-region is encapsulated into independent data blocks. Signal preprocessing and sub-region division ensure data accuracy and spatial correlation, enabling precise data management and differentiated analysis. Furthermore, the block encapsulation and blockchain storage features ensure independent traceability and tamper-proof data, enhancing data security and reliability. Real-time cross-entity data sharing is achieved through blockchain node synchronization, optimizing collaboration efficiency. It also adapts to large-scale data expansion; when adding sensors or detection sub-regions, the corresponding data can be directly encapsulated into new blocks and uploaded to the blockchain without changing the existing data storage structure, improving scalability. Attached Figure Description

[0016] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0017] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 A first flowchart illustrating the method for collecting building safety data in this application; Figure 2 A second flowchart illustrating the method for collecting building safety data in this application; Figure 3 This is a schematic diagram of the hardware operating environment involved in the building safety data collection method in this application embodiment.

[0019] The purpose, features, and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0020] It should be understood that the specific embodiments described herein are merely illustrative of the technical solutions of this application and are not intended to limit this application.

[0021] To better understand the technical solution of this application, a detailed description will be provided below in conjunction with the accompanying drawings and specific implementation methods.

[0022] To achieve the above objectives, this application proposes a method for collecting building safety data. The method includes: when a sensor communication signal is detected within the coverage area of ​​a base station, parsing and preprocessing the sensor communication signal to obtain initial safety detection data; determining detection sub-regions based on sensor location coordinates, dividing the initial safety detection data according to the detection sub-regions to obtain sub-region safety detection data corresponding to each detection sub-region; encapsulating the sub-region safety detection data into data blocks, wherein each sub-region safety detection data corresponds to one data block; and adding the verified target data block to the blockchain of the network node.

[0023] In existing safety data acquisition methods, safety detection sensor nodes are typically deployed in each detection area. These sensors collect building structure and environmental safety data in real time and upload the data to a local server deployed on-site via wired transmission or short-range wireless communication technology. The local server adopts a static storage architecture based on file directories, creating independent root directories according to the detection area name, and categorizing the data uploaded by sensors in the corresponding area into these directories. Simultaneously, manual configuration of data naming conventions is required, embedding data type identifiers, collection timestamps, and other information into filenames to achieve initial data differentiation and management.

[0024] When new sensors are deployed or the detection sub-area needs to be expanded, maintenance personnel must log in to the local server and manually perform directory creation operations, adding a root directory corresponding to the sub-area or a data sub-directory corresponding to the sensor. Simultaneously, the server storage partition quota allocation must be adjusted, and the offline data classification rule document must be updated. Each time a new device or expanded area is added, the existing storage directory structure, partition configuration, and classification rules must be manually adapted and adjusted. This lack of dynamic adaptive capability makes it difficult to meet the expansion needs of a large-scale increase in the number of sensors and a continuously expanding detection range.

[0025] This application provides a method for collecting building safety data. It obtains effective initial safety detection data by parsing and preprocessing sensor communication signals. Data is divided into detection sub-regions based on sensor location coordinates, and the data from each sub-region is encapsulated into independent data blocks. Signal preprocessing and sub-region division ensure data accuracy and spatial correlation, enabling precise data management and differentiated analysis. Furthermore, the block encapsulation and blockchain storage features ensure independent traceability and tamper-proof data, enhancing data security and reliability. Real-time cross-entity data sharing is achieved through blockchain node synchronization, optimizing collaboration efficiency and adapting to large-scale data expansion. When adding sensors or detection sub-regions, the corresponding data can be directly encapsulated into new blocks and uploaded to the blockchain without changing the existing data storage structure, improving scalability.

[0026] It should be noted that the executing entity in this embodiment can be a computing service device with network communication and program execution functions, such as a tablet computer, personal computer, or mobile phone, or an electronic device or apparatus capable of performing the above functions. The following description uses a building safety data acquisition device as an example to illustrate this embodiment and the subsequent embodiments.

[0027] Based on this, the embodiments of this application provide a method for collecting building safety data, referring to... Figure 1 , Figure 1 This is a flowchart illustrating the first embodiment of the building safety data collection method of this application.

[0028] In this embodiment, the method for collecting building safety data includes steps S10 to S30: Step S10: When a sensor communication signal is detected within the base station coverage area, the sensor communication signal is parsed and preprocessed to obtain initial security detection data.

[0029] In this embodiment, the base station serves as the communication hub between the sensors in the area and the cloud. It is responsible for receiving data from the scattered sensors and performing preliminary cleaning to remove invalid data, thereby reducing the transmission and processing pressure on the cloud while ensuring the integrity and consistency of the data.

[0030] The base station, based on a preset communication protocol, detects the communication signals of all registered sensors within its coverage area in real time. It receives raw sensor data according to the binding relationship between the sensor identifier and the base station. The base station's local database stores a sensor-base station binding table with fields including: sensor_id (unique sensor identifier), bind_base_id (bound base station ID), bind_status (1 = bound, 0 = not bound), and last_comm_time (last communication time). The communication module monitors wireless signals within its coverage area in real time and performs the following operations on received signal frames: parsing the frame header and extracting the first 16 bytes of the sensor_id from the signal frame; For binding verification, the sensor and base station binding table is queried. If the bind_base_id corresponding to sensor_id is consistent with the current base station ID and bind_status=1, it is determined to be a valid signal, and the signal frame is stored in the receive buffer; if the binding does not match or is not bound, it is discarded directly and the log is recorded. For legitimate signal frames, the base station verifies data integrity using CRC32. After successful verification, it parses the data according to the defined JSON format, extracts core fields such as sensor_id, collect_timestamp, and location, and stores them in a local temporary table. The base station preprocesses the data, first verifying data integrity by checking for missing key fields such as sensor ID, timestamp, and core detection indicators, and removing data with missing fields; then verifying data validity based on preset threshold ranges, such as a reasonable range for crack width of 0-5mm and a reasonable range for soil moisture of 0-100%, removing abnormal data exceeding the thresholds to obtain the initial security detection data from the sensors.

[0031] Step S20: Determine the detection sub-region based on the sensor position coordinates, and divide the initial security detection data according to the detection sub-region to obtain the sub-region security detection data corresponding to each detection sub-region.

[0032] In this embodiment, the base station reads a preset area division rule, such as: latitude 30.12-30.13°, longitude 120.56-120.57° corresponding to area ID: 003, and performs data division. The latitude and longitude of each data point are extracted, and the corresponding area ID is calculated using an interval mapping algorithm. Data is grouped by area ID, and all valid data within each group is aggregated to generate sub-area security detection data, including area identifier, base station identifier, aggregation time, and data list.

[0033] Step S30: Encapsulate the sub-region security detection data into a data block, wherein each sub-region security detection data corresponds to one data block.

[0034] Step S40: Add the target data block that has passed verification to the blockchain of the network node.

[0035] In this embodiment, the base station locally stores the RSA public key issued by the cloud, reads the JSON-formatted aggregation file corresponding to the generated security detection data, and converts the file content into a binary data stream. It then calls the OpenSSL encryption library, uses the RSA public key to encrypt the binary data stream, and generates a transmission data packet containing the base station ID, area ID, encrypted ciphertext, encryption timestamp, and a SHA-256 hash value signature of the ciphertext using the base station's private key.

[0036] The base station connects to the public network via Ethernet or a 4G module, and uses the HTTPS protocol to send data packets to a designated interface in the cloud. During transmission, the cloud server returns an SSL certificate, which the base station verifies to ensure its validity, checking the certificate authority, validity period, and domain name matching. If the base station does not receive a successful reception response from the cloud within 30 seconds, it automatically retransmits the data packet, up to a maximum of 3 times. If all 3 retransmissions fail, the data packet is stored in the local retry_upload directory, and the attempt is repeated after a 10-minute interval, while simultaneously logging the failure.

[0037] After receiving data packets transmitted from the base station, the cloud uses the base station's public key to verify the `sign` field. If verification fails, the signature and hash value do not match, the data packet is discarded, and an invalid signature response is returned. The cloud's RSA private key is used to decrypt `encrypt_data`, restoring it to the generated JSON format aggregated data. The CRC32 value of the decrypted JSON data is calculated and compared with the CRC32 value in the data packet. If they do not match, a data corruption response is returned; if they match, the data proceeds to the blockchain storage stage.

[0038] Specifically, step S30 may include: generating a block header based on the block number, the hash value of the previous block, and the data digest block generation timestamp; generating a block body based on the sub-region security detection data; and generating the data block by combining the block header and the block body.

[0039] The block number is incremented sequentially based on the data reception order, with the initial block number being 1. The SHA-256 hash value of the last block in the blockchain ledger is read. The hash value of the block preceding the initial block is "0000000000000000000000000000000000". The SHA-256 hash value of the decrypted JSON data is calculated to obtain a data digest, used for quick verification of data tampering. A block generation timestamp is generated based on the current time.

[0040] The blocks are assembled according to a block structure, which consists of a block header and a block body. The block header contains the block number, the hash value of the previous block, the data digest, the timestamp, and the random number; the block body contains complete security detection data.

[0041] A blockchain network comprises multiple nodes, such as five nodes, deployed on different physical servers. Each node competes for the right to record a block by calculating a hash value that has the first N bits set to 0. The first node to calculate a hash value that meets these conditions becomes the recording node. The recording node then broadcasts the generated complete block to all other nodes in the blockchain network. After receiving the block, other nodes verify whether the hash value of the previous block matches the hash value of the last block in their local ledger, and whether the data digest matches the hash value of the block body data. If all verifications pass, the block is added to the local blockchain ledger and stored in a LevelDB or RocksDB database. When more than 50% of the nodes have completed block storage, the cloud sends a storage success response to the base station and updates its local block index table, thus obtaining the regional sensor data block stored in the blockchain network.

[0042] In this embodiment, the sensor data stored on the blockchain possesses the characteristics of being immutable, having a complete time sequence, and being traceable in origin. Based on this, factors influencing building construction are extracted, ensuring the authenticity of the data source and preventing human tampering or data forgery. Furthermore, by combining historical and real-time data, the long-term changing patterns and current state of the regional environment can be reflected. Valid initial security detection data is obtained by parsing and preprocessing sensor communication signals. Data is divided into detection sub-regions based on sensor location coordinates, and each sub-region's data is encapsulated into independent data blocks. Signal preprocessing and sub-region division ensure data accuracy and spatial correlation, enabling precise data management and differentiated analysis. The block encapsulation and blockchain storage characteristics ensure independent traceability and immutability of data, improving data security and credibility. Real-time cross-entity data sharing is achieved through blockchain node synchronization, optimizing collaborative efficiency and adapting to large-scale data expansion. When adding sensors or detection sub-regions, the corresponding data can be directly encapsulated into new blocks and uploaded to the blockchain without changing the existing data storage structure, improving scalability.

[0043] Based on the first embodiment of this application, in the second embodiment of this application, the content that is the same as or similar to that in the first embodiment described above can be referred to the above description and will not be repeated hereafter. Furthermore, before step S10, steps S01 to S02 may also be included: Step S01: When human activity is detected, or when the preset acquisition period is reached, the sensor is controlled to acquire data and obtain an analog signal.

[0044] In this embodiment, the sensor has a built-in trigger control module that reads preset trigger condition parameters. The trigger condition can be a timed trigger cycle, such as every hour; or it can be an event trigger, such as infrared sensing of human activity or vibration sensor detecting shaking exceeding a threshold. When any trigger condition is met, the sensor starts data acquisition: it detects physical quantities of building structural safety indicators, such as wall crack width, beam and column tilt angle, and foundation settlement, as well as environmental impact indicators, such as surrounding soil moisture, surface vibration frequency, and regional rainfall, to obtain analog signals such as voltage and current.

[0045] For timed trigger detection, the current time is read from the RTC (Real-Time Clock), and the difference between this time and the previous acquisition time is calculated. If the difference is greater than or equal to the preset acquisition period, a timed trigger signal is generated. For event-triggered detection, analog signals from various event sensors, such as the voltage signal from the infrared sensor and the acceleration signal from the vibration sensor, are acquired in real time via an ADC (Analog-to-Digital Converter). These analog signals are converted to digital values ​​and compared with preset event trigger thresholds. For example, if the infrared sensor outputs a voltage of 3.3V when it detects a human body, corresponding to a distance ≤ 5 meters, and this voltage value persists for more than 200ms, an event trigger signal is generated. If both timed and event trigger conditions are met, the event trigger signal has higher priority by default, triggering only one acquisition cycle to avoid repeated acquisition.

[0046] When the trigger control module generates any trigger signal, it sends a data acquisition command to the sensors, initiating multi-sensor collaborative data acquisition. For structural safety indicators, a laser displacement sensor is used to emit a laser beam to the surface of wall cracks, receive the reflected light signal, and convert the optical path difference into an analog voltage signal through the sensor's internal signal processing circuit to obtain the wall crack width. A MEMS tilt sensor is used to acquire analog signals of the X / Y axis tilt angles. The acquired data is filtered using a Kalman filter algorithm to remove errors caused by vibration, yielding the beam and column tilt angles. A vibrating wire displacement sensor is used, sending a sine wave signal to the sensor through an excitation circuit, receiving the frequency signal fed back by the sensor, and converting the frequency signal into a corresponding displacement value to obtain the foundation settlement.

[0047] For environmental impact indicators, a capacitive soil moisture sensor is used to collect the analog voltage corresponding to soil moisture, thus obtaining the surrounding soil moisture. A piezoelectric vibration sensor is used to collect the analog signal of surface vibration acceleration. The time-domain signal is converted into a frequency-domain signal through Fourier transform, and the main vibration frequency values ​​are extracted to obtain the surface vibration frequency. A tipping bucket rain gauge is used, triggering a pulse signal every 0.1 mm of rainfall. The number of pulses during the collection period is recorded by a counter and converted into a rainfall value to obtain the regional rainfall.

[0048] Step S02: Convert the analog signal into a digital signal, and generate initial security detection data based on the digital signal, sensor identifier, acquisition timestamp, and acquisition location coordinates.

[0049] In this embodiment, the detected analog signals such as voltage and current are converted into digital signals using a built-in AD converter. Each analog signal is sampled a preset number of times to obtain multiple digital values. The calibrated digital value is calculated by averaging the values ​​after removing the maximum and minimum values. Pre-stored calibration coefficients in the microcontroller are called, such as the voltage and width calibration formula for crack width: crack_width=(ADC_value×5) / 4095, where 4095 is the maximum value of the 12-bit ADC. This converts the calibrated digital value into a physical quantity value. Simultaneously, a unique sensor identifier, acquisition timestamp, and acquisition location coordinates are added to generate the original sensor data.

[0050] In this embodiment, a combination of timed triggering and event triggering ensures the real-time nature and effectiveness of sensor data acquisition, avoids redundant invalid data, and covers both routine monitoring and abnormal scenario monitoring needs. Timed triggering covers routine monitoring needs and ensures data continuity; event triggering focuses on abnormal scenarios, such as collecting structural data when someone approaches a building or capturing anomalies in real time when vibration exceeds limits, avoiding invalid data caused by continuous 24 / 7 data collection.

[0051] In one feasible implementation, the method further includes: generating time-series data based on timestamps and historical security detection data; inputting the time-series data into a preset prediction model to predict future security detection data and obtain a prediction trend; and adjusting the collection period according to the prediction trend.

[0052] In this embodiment, historical security detection data containing timestamps and corresponding detection indicators are extracted from data sources such as security detection systems and sensor devices. The data is then sorted by timestamp to ensure that the data is arranged in chronological order. The sorted data is converted into a standard time-series data format, with time as the index and detection indicators as the columns, forming a two-dimensional time-series dataset. If there is data with missing timestamps, interpolation methods such as linear interpolation or spline interpolation are used to complete the data, ensuring the continuity of the time-series data.

[0053] Select a time series forecasting model, such as ARIMA, LSTM, or Prophet; use 70%-80% of the historical time series data as the training set and the remaining data as the test set to train and validate the model, optimizing prediction accuracy by adjusting model parameters. Input the preprocessed time series data into the trained forecasting model, set the prediction step size, and the model outputs the predicted values ​​and trends of each detection indicator within the corresponding time period, such as growth, stability, or decline. Preset the grading criteria for the prediction trend, classifying the trend level according to the magnitude and rate of change of the detection indicators; formulate collection cycle adjustment rules for different trend levels. Match the predicted trend output by the model with the grading rules to determine the current trend level; calculate the new collection cycle according to the adjustment rules. For example, preset trend grading and adjustment rules: monthly average settlement increase ≥0.1mm, indicating rapid deterioration, the collection cycle is shortened from 3 months to 1 month; monthly average settlement increase 0.05-0.1mm, indicating slow change, the collection cycle remains at 3 months; monthly average settlement increase <0.05mm, indicating stability, the collection cycle is extended to 6 months.

[0054] Based on the first embodiment of this application, in the third embodiment of this application, the content that is the same as or similar to that in the first embodiment described above can be referred to the above description, and will not be repeated hereafter. Based on this, please refer to... Figure 2 After step S40, steps A10 to A30 may also be included: Step A10: Based on the query interface of the blockchain node, obtain the sub-region security detection data stored in the blockchain.

[0055] In this embodiment, the cloud initiates a data query request through the smart contract query interface or node API of the blockchain network, filtering data by region, time range, and data type. When retrieving data, the continuity of the block hash chain is verified, checking whether the hash value of the previous block matches the hash of the previous block to ensure the data has not been tampered with; simultaneously, the legitimacy of the sensor ID and base station ID is verified and compared with the pre-registered device list to exclude forged data blocks. Block data from the same region but different time periods are sorted by timestamp to form a complete data sequence in terms of region and time.

[0056] Step A20: Based on the timestamp and sensor type identifier, determine the total regional topographic stability score, total climate impact coefficient, and building compliance rate for each region from the security detection data.

[0057] In this embodiment, for each region, topographic data, climate data, and safety data of existing buildings are extracted from the integrated sensor data, and a topographic stability score is calculated through a quantitative model.

[0058] Correlation indicators for geomorphological data include soil moisture, surface vibration frequency, foundation settlement, and topographic slope. Data from the past year is divided into quarters, and the mean for each quarter is calculated before being aggregated into an annual mean to avoid the influence of short-term anomalies on the overall assessment. The 3σ principle is used to remove extreme outliers, retaining only valid data that conforms to a normal distribution.

[0059] In one feasible implementation, step A20 may include steps A21 to A26: Step A21: Based on the timestamp and the geomorphological sensor type identifier, obtain soil moisture, surface vibration frequency, first foundation settlement and terrain slope.

[0060] Step A22: Match the soil moisture, the surface vibration frequency, the first foundation settlement, and the terrain slope with the preset soil stability scoring rules to determine the total geomorphic stability score of the area.

[0061] In this embodiment, based on the preset soil stability scoring rules, the weighted calculation of sub-indicators determines the range in which soil moisture, surface vibration frequency, foundation settlement and topographic slope fall, and the corresponding score is determined according to the corresponding range. For example, a soil moisture average of 30%-60% is considered reasonable, earning 80-100 points (30% = 80 points, 60% = 100 points), with linear calculations in between. For soil moisture averages <30% or >60%, deduct 10 points for every 5% deviation, up to a maximum deduction of 0.5%. A surface vibration frequency average ≤5Hz is considered safe, earning 100 points; deduct 20 points for every 1Hz exceeding this range, up to a maximum deduction of 0.5mm / year. Foundation settlement average ≤0.5mm / year earns 100 points; deduct 10 points for every 0.1mm / year exceeding this range, up to a maximum of 0.5mm / year. Topographic slope average ≤5° is considered suitable, earning 100 points; average slope average of 5°-10° earns 60-80 points, decreasing linearly; average slope average >10° earns 0 points. The scores for these four items are added together according to preset weights to obtain the total score for regional geomorphological stability.

[0062] Step A23: Based on the timestamp and climate sensor type identifier, obtain the rainfall, temperature change range, and wind force level.

[0063] Step A24: Match the rainfall, temperature change range, and wind force level with the preset climate impact coefficient determination rules to determine the total climate impact coefficient.

[0064] Long-term statistical indicators are extracted from regional climate sensor data to generate a climate impact coefficient, ranging from 0 to 1.0. A higher coefficient indicates a smaller negative impact of climate on housing construction. Climate indicators include rainfall, temperature variation, and wind force. The average annual rainfall over the past 5 years is calculated; the maximum values ​​of the highest and lowest temperatures for each month of the year are obtained to determine the extreme temperature difference; the maximum wind force recorded throughout the year is determined as the annual maximum wind force; and the proportion of rainfall during the flood season (June-August) to the total annual rainfall is calculated to obtain the rainfall concentration.

[0065] In this embodiment, based on preset rules for determining climate impact coefficients, the ranges within which the aforementioned data fall are determined, and the corresponding basic climate impact coefficients are determined according to these ranges. For example, annual average rainfall of 500-1500 mm corresponds to a basic coefficient of 0.4; annual average rainfall of 300-500 mm or 1500-2000 mm corresponds to a basic coefficient of 0.3; annual average rainfall <300 mm or >2000 mm corresponds to a basic coefficient of 0.2. Extreme temperature difference ≤30℃ corresponds to a basic coefficient of 0.3; extreme temperature difference of 30-40℃ corresponds to a basic coefficient of 0.25; extreme temperature difference >40℃ corresponds to a basic coefficient of 0.2. Annual maximum wind force ≤6 corresponds to a basic coefficient of 0.3; annual maximum wind force 7-8 corresponds to a basic coefficient of 0.25; annual maximum wind force ≥9 corresponds to a basic coefficient of 0.2. The three basic coefficients are added together to obtain the total climate impact coefficient.

[0066] Optionally, the total climate impact coefficient can be corrected based on the rainfall concentration. If the rainfall concentration is greater than the preset rainfall concentration threshold, the corresponding preset value is deducted from the base coefficient. If there are records of extreme weather such as rainstorms and strong winds, such as ≥3 times per year, the corresponding preset value is deducted from the base coefficient to ensure that the coefficient reflects the extreme climate risk.

[0067] Step A25: Based on the timestamp and the building structure sensor type identifier, obtain the wall crack width, beam and column tilt angle, and second foundation settlement.

[0068] Step A26: Determine the building compliance rate based on the width of the wall cracks, the inclination angle of the beams and columns, and the settlement of the second foundation.

[0069] In this embodiment, the detection data of structural sensors in the area are extracted. Safety indicators include: wall crack width, beam and column tilt angle, and foundation settlement. The indicators are grouped by building, and the average value of each building is calculated. These are then aggregated into the overall average value for the area. The calculated regional average value is compared with national building safety standards, such as the "Code for Design of Concrete Structures" GB 50010-2010, to determine whether compliance is achieved. The compliance rate is calculated as (number of compliant buildings / total number of buildings within the statistical range) × 100%.

[0070] Step A30: Input the total score of landform stability, the total coefficient of climate influence, and the building compliance rate into the preset building assessment model to conduct a building assessment for each of the regions and obtain the assessment results.

[0071] In one feasible implementation, the building assessment model can be trained based on the Gradient Boosting Tree (XGBoost) algorithm. The model has been optimized using historical data and can output a total building suitability score and a suitability level probability based on topographic stability score, climate influence coefficient, and the average structural safety of existing buildings. For example, the probability of being highly suitable is 85%. Input features are normalized to avoid the influence of dimensional differences on model calculations. Default weights are preset and adjusted according to the region type, increasing the weights corresponding to topographic features in mountainous areas. For example, the default weights are automatically adjusted to topographic stability 0.4, climate influence 0.3, and existing building safety compliance rate 0.3, while for mountainous areas they are automatically adjusted to topographic stability 0.5, climate influence 0.2, and existing building safety compliance rate 0.25. The preprocessed input features are substituted into the assessment model, and the total score is calculated using the following formula: Total Score = (Standardized Topographic Stability Score × First Weight 1) + (Climate Influence Coefficient × Second Weight) + (Standardized Safety Compliance Rate × Third Weight). Suitability levels are determined based on the total score, and the reliability is verified by the level probabilities output by the model.

[0072] In one feasible implementation, the building assessment model can be a large-scale model trained on top of existing models, such as an industry-wide model based on the Transformer architecture. By combining structured indicators such as the total score of topographic stability, the total coefficient of climate impact, and the building compliance rate with the pre-trained knowledge of the large-scale model, such as building codes, geological engineering knowledge, and a regional building case library, the assessment results are output.

[0073] In this embodiment, step A30 may include steps A31 to A33: Step A31: Normalize the total score of landform stability, the total coefficient of climate influence, and the building compliance rate, and generate an input feature vector based on the normalization result.

[0074] The random forest model is trained by using bootstrap sampling (sampling with replacement) to extract independent samples from the training set for each decision tree. Based on the extracted sample set, each tree undergoes feature splitting according to the principle of minimizing the Gini coefficient, such as prioritizing the total terrain stability score as the root node splitting feature, and dividing it into left and right subtrees with a threshold of 0.8. After all decision trees are trained, the model performance is validated using a validation set, and hyperparameters (such as the number of decision trees and maximum depth) are adjusted to ensure that the classification accuracy is greater than or equal to the preset classification accuracy threshold. After training, the model structure is stored as a binary file (e.g., .pkl format) for use during the inference phase.

[0075] The total geomorphic stability score, climate influence coefficient, and building compliance rate are extracted and normalized. The total geomorphic stability score and building compliance rate are converted into the 0-1 interval. The conversion formula is: normalized value = original value / 100. This eliminates the influence of differences in the dimensions of different features on the model inference. The three normalized features are integrated to form a feature vector that can be directly input into the model.

[0076] Step A32: Input the input feature vector into the random forest model, and split the input feature vector layer by layer according to the preset splitting rules to obtain the initial classification result and initial regression value of a single decision tree.

[0077] Step A33: The classification result that appears most frequently is determined as the target classification result, and the mean of the initial regression values ​​is determined as the evaluation score.

[0078] A single decision tree, based on the splitting rules determined during the training phase, splits the input feature vector layer by layer. Starting from the root node, it determines the category of the input feature value based on the splitting feature and threshold specified by the current node, and enters the corresponding left or right subtree. This process is repeated until a leaf node is reached, where the pre-stored classification results and regression values ​​are read. The regression values ​​are the preliminary predicted values ​​for the total evaluation score. For example, the root node specifies the splitting feature as the normalized value of landform stability and the splitting threshold as 0.8; the normalized value of landform stability in the input feature vector is 0.85 > 0.8, so it enters the right subtree. The second-level node specifies the splitting feature as the normalized value of building compliance rate and the splitting threshold as 0.9; the normalized value of building compliance rate in the input feature is 0.92 > 0.9, so it enters the right subtree. The third-level node specifies the splitting feature as the climate impact coefficient and the splitting threshold as 0.85; the climate impact coefficient in the input feature is 0.9 > 0.85, so it enters the right subtree. After reaching a leaf node, the classification results and regression values ​​stored in that node are read.

[0079] The trained random forest model file is used to perform parallel inference on the input feature vector. Since each decision tree is independent, inference calculations can be performed simultaneously, and each decision tree outputs its own classification result and regression value. After the inference is completed, the output results of all decision trees are collected to form a set of classification results and a set of regression values.

[0080] A voting mechanism is used to merge the classification results of multiple decision trees. The frequency of each classification result is counted, and the classification result with the highest frequency is selected as the final classification result. A pre-defined suitability level mapping table is used to convert the final classification result into a suitability level. An arithmetic mean method is used to merge the regression values ​​of multiple decision trees. The sum of all regression values ​​is calculated and then divided by the total number of decision trees to obtain the final evaluation score, thereby reducing the prediction bias of individual decision trees and improving the accuracy of the overall score. The evaluation score is a quantitative comprehensive score of the suitability of the area for housing construction by the random forest model. It represents the comprehensive adaptability of the area's natural conditions and existing housing safety foundation to new housing. The higher the score, the more suitable the area is for housing construction, and the lower the construction risk.

[0081] The confidence level is calculated based on the proportion of the most frequent codes in the classification results. The more frequently the most frequent codes appear, the more reliable the evaluation results. Confidence level = (number of most frequent classification results / total number of decision trees) × 100%. Confidence level is a quantitative indicator of the reliability and credibility of the evaluation results. It represents the degree of confidence that the random forest model has in the current evaluation conclusion. The higher the confidence level, the more reliable the evaluation results are and the better they reflect the actual housing suitability in the region.

[0082] In one feasible implementation, after step A30, the method may further include: matching the judgment level corresponding to the assessment result with a preset suggestion template to obtain an initial template; filling the placeholders in the initial template according to the total score of landform stability, the total coefficient of climate influence, and the building compliance rate to obtain a building assessment report.

[0083] In this embodiment, a structured mapping database is pre-established, using the building assessment level as the key and the corresponding preset suggestion template as the value. Each level's preset suggestion template includes core modules such as building type, structural design, supporting measures, and monitoring requirements. Each module contains placeholders associated with specific indicators, such as: {Geomorphological features}, {Climate adaptation measures}, {Compliance rate reference suggestions}. Based on the assessment level, a precise search is performed in the mapping database to extract the corresponding preset suggestion template, which becomes the initial template. If the assessment level is "highly suitable," the template corresponding to "highly suitable" is extracted from the mapping database as the initial template. For the various placeholders in the initial template, pre-defined mapping rules are established for their correspondence with the total score for landform stability, the total coefficient of climate impact, and the building compliance rate. These rules must clearly define the content to be filled in for different indicator ranges. For example, the content to be filled in for the {landform feature} corresponding to the total score range for landform stability is: high score (≥80 points) for high-stability soil, medium score (60-79 points) for medium-stability soil, and low score (<60 points) for low-stability soil. Range determination is performed for the total score for landform stability, the total coefficient of climate impact, and the building compliance rate, and the corresponding content is matched based on the determination results. The matched content replaces the corresponding placeholders in the initial template one by one. After completing the template filling, the content of each module is integrated, combined with information such as regional identifiers, total assessment score, and indicator details, to generate a complete building assessment report.

[0084] This application provides a building safety data acquisition device, including: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform the building safety data acquisition method of the above embodiment 1.

[0085] The following is for reference. Figure 3 The diagram illustrates a structural schematic of a building safety data acquisition device suitable for implementing embodiments of this application. The building safety data acquisition device in these embodiments may include, but is not limited to, mobile terminals such as mobile phones, laptops, personal digital assistants (PDAs), tablet computers (PADs), and in-vehicle terminals (e.g., in-vehicle navigation terminals), as well as fixed terminals such as digital TVs and desktop computers. Figure 3 The building safety data acquisition device shown is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of this application.

[0086] like Figure 3As shown, the building safety data acquisition device may include a processing unit 1001 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 1002 or a program loaded from a storage device 1003 into a random access memory (RAM) 1004. The RAM 1004 also stores various programs and data required for the operation of the building safety data acquisition device. The processing unit 1001, the read-only memory 1002, and the RAM 1004 are interconnected via a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to I / O interface 1006: input devices 1007 including, for example, touchscreens, touchpads, keyboards, mice, image sensors, microphones, accelerometers, gyroscopes, etc.; output devices 1008 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 1003 including, for example, magnetic tapes, hard disks, etc.; and communication devices 1009. Communication device 1009 allows the building safety data acquisition equipment to communicate wirelessly or wiredly with other devices to exchange data. Although the figure shows a building safety data acquisition equipment with various systems, it should be understood that it is not required to implement or possess all the systems shown. More or fewer systems can be implemented alternatively.

[0087] Specifically, according to the embodiments disclosed in this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments disclosed in this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device, or installed from storage device 1003, or installed from read-only memory 1002. When the computer program is executed by processing device 1001, it performs the functions defined in the methods of the embodiments disclosed in this application.

[0088] The building safety data acquisition device provided in this application, employing the building safety data acquisition method described in the above embodiments, can solve the technical problem of how to improve the efficiency of building safety data acquisition. Compared with the prior art, the beneficial effects of the building safety data acquisition device provided in this application are the same as those of the building safety data acquisition method provided in the above embodiments, and other technical features of the building safety data acquisition device are the same as those disclosed in the previous embodiment method, and will not be repeated here.

[0089] It should be understood that the various parts disclosed in this application can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any suitable manner in one or more embodiments or examples.

[0090] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

[0091] This application provides a computer-readable storage medium having computer-readable program instructions (i.e., a computer program) stored thereon, which are used to execute the building safety data acquisition method in the above embodiments.

[0092] The computer-readable storage medium provided in this application may be, for example, a USB flash drive, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems or devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system or device. The program code contained on the computer-readable storage medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, radio frequency (RF), etc., or any suitable combination thereof.

[0093] The aforementioned computer-readable storage medium may be included in a building safety data acquisition device; or it may exist independently and not assembled into a building safety data acquisition device. The aforementioned computer-readable storage medium carries one or more programs that, when executed by the building safety data acquisition device, cause the building safety data acquisition device to: when a sensor communication signal is detected within the base station coverage area, parse and preprocess the sensor communication signal to obtain initial safety detection data; determine detection sub-regions based on sensor location coordinates, divide the initial safety detection data according to the detection sub-regions, and obtain sub-region safety detection data corresponding to each detection sub-region; encapsulate the sub-region safety detection data into data blocks, wherein each sub-region safety detection data corresponds to one data block; and add the verified target data block to the blockchain of the network node.

[0094] Computer program code for performing the operations of this application can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the client computer, partially on the client computer, as a standalone software package, partially on the client computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the client computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0095] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0096] The modules described in the embodiments of this application can be implemented in software or hardware. The names of the modules do not necessarily limit the functionality of the unit itself.

[0097] The readable storage medium provided in this application is a computer-readable storage medium that stores computer-readable program instructions (i.e., a computer program) for executing the above-described building safety data acquisition method, thereby solving the technical problem of how to improve the efficiency of building safety data acquisition. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in this application are the same as the beneficial effects of the building safety data acquisition method provided in the above embodiments, and will not be repeated here.

[0098] The above descriptions are merely some embodiments of this application and do not limit the patent scope of this application. Any equivalent structural transformations made based on the technical concept of this application and the content of this specification and drawings, or direct / indirect applications in other related technical fields, are included within the patent protection scope of this application. Similarly, applications in other related technical fields are also included within the patent processing scope of this application.

Claims

1. A method of collecting building security data, characterized by, The building safety data collection method comprises: When a sensor communication signal is detected in the base station coverage area, the sensor communication signal is parsed and preprocessed to obtain initial safety detection data; Based on the sensor position coordinates, a detection sub-area is determined, and the initial safety detection data is divided according to the detection sub-area to obtain sub-area safety detection data corresponding to each detection sub-area; The sub-area safety detection data is encapsulated as a data block, wherein each sub-area safety detection data corresponds to a data block; The target data block that passes the verification is added to the block chain of the network node.

2. The method of claim 1, wherein the building security data is collected by a plurality of sensors. After the step of adding the target data block that passes the verification to the block chain of the network node, the building safety data collection method further comprises: Based on the query interface of the block chain node, the sub-area safety detection data stored in the block chain is obtained; According to the time stamp and the sensor type identifier, the total score of the regional landform stability, the total coefficient of the climate influence, and the building compliance rate corresponding to each region are determined from the safety detection data; The total score of the landform stability, the total coefficient of the climate influence, and the building compliance rate are input into a preset building evaluation model to evaluate each region to obtain an evaluation result.

3. The method of claim 2, wherein the building security data is collected by a plurality of sensors. The step of determining the total score of the regional landform stability, the total coefficient of the climate influence, and the building compliance rate corresponding to each region from the safety detection data according to the time stamp and the sensor type identifier comprises: According to the time stamp and the landform sensor type identifier, the soil moisture, surface vibration frequency, first foundation settlement, and terrain slope are obtained; The soil moisture, surface vibration frequency, first foundation settlement, and terrain slope are matched with a preset soil stability scoring rule to determine the total score of the regional landform stability; According to the time stamp and the climate sensor type identifier, the rainfall, temperature variation amplitude, and wind grade are obtained; The rainfall, temperature variation amplitude, and wind grade are matched with a preset climate influence coefficient determination rule to determine the total coefficient of the climate influence; According to the time stamp and the building structure sensor type identifier, the wall crack width, beam column inclination angle, and second foundation settlement are obtained; According to the wall crack width, beam column inclination angle, and second foundation settlement, the building compliance rate is determined.

4. The method of claim 2, wherein the building security data is collected by a plurality of sensors. The building evaluation model is a pre-trained random forest model, and the step of inputting the total score of the landform stability, the total coefficient of the climate influence, and the building compliance rate into the preset building evaluation model to evaluate each region to obtain an evaluation result comprises: The total score of the landform stability, the total coefficient of the climate influence, and the building compliance rate are normalized, and an input feature vector is generated according to the normalization result; The input feature vector is input into the random forest model, and the input feature vector is split layer by layer according to a preset splitting rule to obtain an initial classification result and an initial regression value of a single decision tree; The classification result with the highest frequency is determined as a target classification result, and the mean value of the initial regression value is determined as an evaluation score.

5. The method of claim 2, wherein the building security data is collected by a plurality of sensors. After the step of inputting the geomorphic stability total score, the climate influence total coefficient, and the building compliance rate into a preset building evaluation model to evaluate the building of each region and obtaining an evaluation result, the building safety data collection method further comprises: The evaluation result corresponding determination level and the preset suggestion template are matched to obtain an initial template; The geomorphic stability total score, the climate influence total coefficient, and the building compliance rate are filled in the placeholder in the initial template to obtain a building evaluation report.

6. The method of claim 1, wherein the building security data is collected by a plurality of sensors. Before the step of detecting the sensor communication signal in the base station coverage area, analyzing and preprocessing the sensor communication signal to obtain initial safety detection data, the building safety data collection method further comprises: When human activity is detected, or the preset collection period is reached, the sensor is controlled to collect data to obtain an analog signal; The analog signal is converted into a digital signal, and initial safety detection data is generated according to the digital signal, a sensor identifier, a collection time stamp, and a collection position coordinate.

7. The method of claim 6, wherein the building security data is collected by a plurality of sensors. The building safety data collection method further comprises: Time sequence data is generated based on the time stamp and historical safety detection data; The prediction trend is obtained by inputting the time sequence data into a preset prediction model to predict future safety detection data; The collection period is adjusted according to the prediction trend.

8. The method of claim 1, wherein the building security data is collected by a plurality of sensors. The step of encapsulating the sub-region safety detection data into a data block comprises: The block header is generated based on the block number, the previous block hash value, and the data digest block generation time stamp, and the block body is generated according to the sub-region safety detection data; The block header and the block body are used to generate the data block.

9. A building security data collection device, characterized by The building safety data collection device comprises a memory, a processor, and a computer program stored on the memory and executable on the processor, and the computer program is configured to implement the steps of the building safety data collection method according to any one of claims 1 to 8.

10. A storage medium, characterized by The storage medium is a computer readable storage medium, and the computer readable storage medium stores a computer program, and the computer program is executed by the processor to implement the steps of the building safety data collection method according to any one of claims 1 to 8.

Images