An engineering quality detection data tamper-proofing and abnormality early warning method and system

Abstract

The application provides an engineering quality detection data tamper-proofing and abnormal early warning method and system, relates to the technical field of engineering quality detection, and comprises the following steps: obtaining original detection data and tamper-proofing and storing evidence; generating a detection report based on the original data and tamper-proofing and storing evidence; matching a deviation allowable threshold from a dynamic parameter library according to the engineering type, grade and equipment accuracy; comparing the detection report with the original data, comparing the self-inspection data with the sampling inspection data, and obtaining comparison results; constructing a capability portrait based on historical data of a detection institution and performing abnormal scoring by using an unsupervised algorithm; determining an abnormal grade and grading early warning by comprehensively considering the comparison results and the comprehensive abnormal score; and storing evidence by chaining the hash values of the detection report and the original data and generating a verification two-dimensional code. The application realizes multi-source cross verification and can effectively identify data abnormal situations such as inconsistency between report values and original records.

Description

Technical Field

[0001] This invention relates to the field of engineering quality testing technology, and more specifically, to a method and system for preventing tampering and providing early warning of anomalies in engineering quality testing data. Background Technology

[0002] In engineering practice, the authenticity of test data for key indicators such as compaction degree, pavement thickness, subgrade reaction modulus, and material strength directly affects service safety and project durability. However, existing quality inspection management solutions are mostly process management systems, lacking the ability to automatically verify the authenticity of the test data itself. For example, they cannot independently cross-verify whether the test report data is consistent with the original records of the testing machine, cannot dynamically adjust the allowable deviation threshold according to the project type and equipment accuracy, and are difficult to quantitatively assess and continuously monitor the historical behavioral deviations of testing agencies, making it difficult to detect and trace data fraud in a timely manner. Summary of the Invention

[0003] The purpose of this invention is to provide a method, system, device, and readable storage medium for preventing tampering and providing early warning of anomalies in engineering quality inspection data, thereby improving the aforementioned problems. To achieve the above objective, the technical solution adopted by this invention is as follows:

[0004] Firstly, this application provides a method for preventing tampering and providing early warning of anomalies in engineering quality testing data, including:

[0005] Obtain the raw test data from the testing instrument and preserve it in an tamper-proof manner;

[0006] A test report is generated based on the original test data, and the test report is preserved as evidence in an anti-tampering manner.

[0007] Based on the current project type, level, and equipment accuracy, the allowable deviation threshold is matched from the dynamic parameter library;

[0008] Obtain the self-inspection data from the construction party and the random inspection data from the testing agency. Compare the test reports with the original test data and the self-inspection data with the random inspection data to obtain the comparison results.

[0009] Based on the historical testing data of the testing institution, a corresponding capability profile is constructed. An unsupervised anomaly detection algorithm is used to score the abnormal behavior of the testing institution, and a comprehensive anomaly score result is generated based on the score.

[0010] The anomaly level is determined by using various comparison results and comprehensive anomaly score results, and early warning and coordinated handling are carried out according to the anomaly level.

[0011] The hash values ​​of the test report and the original test data are stored on the blockchain for evidence, and a verification QR code is generated in the test report.

[0012] Secondly, this application also provides a system for preventing tampering and providing early warning of anomalies in engineering quality testing data, including:

[0013] The data acquisition module is used to acquire the raw test data of the testing instrument and store it in a tamper-proof manner.

[0014] The report generation and evidence storage module is used to generate a test report based on the original test data and to store the test report data in an anti-tampering manner.

[0015] The dynamic parameter matching module is used to match allowable deviation thresholds from the dynamic parameter library based on the current project type, level, and equipment accuracy.

[0016] The multi-source cross-validation module is used to compare the consistency of the test report data with the original test data, and to compare the deviation of the construction party's self-inspection data with the sampling inspection data of the testing agency to obtain various comparison results;

[0017] The anomaly scoring module is used to construct a capability profile of the testing institution based on its historical testing data, score the abnormal behavior of the testing institution using an unsupervised anomaly detection algorithm, and generate a comprehensive anomaly score result based on the score.

[0018] The anomaly classification and early warning module is used to determine the anomaly level by combining the comparison results of the above items and the comprehensive anomaly score results, and to execute classified early warning and linkage response.

[0019] The verification module is used to store the hash values ​​of the original test data and the test report data on the blockchain for evidence, and to generate a verification QR code on the appendix of the test report.

[0020] Thirdly, this application also provides an engineering quality inspection data anti-tampering and anomaly early warning device, including:

[0021] Memory, used to store computer programs;

[0022] A processor is used to implement the steps of the engineering quality inspection data anti-tampering and anomaly early warning method when executing the computer program.

[0023] Fourthly, this application also provides a readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the above-described method for preventing tampering and providing early warning of anomalies based on engineering quality inspection data.

[0024] The beneficial effects of this invention are as follows:

[0025] 1. This invention achieves end-to-end tamper-proof traceability from the data source to the test report by performing hash calculations on the raw test data at the data acquisition end and uploading it to the blockchain for evidence storage. When the test report is generated, the test values ​​consistent with the original data are automatically filled in and hashed for evidence storage. Simultaneously, by constructing a dynamic parameter library, the allowable deviation threshold is matched layer by layer in three steps according to the project type, project level, and equipment calibration accuracy, avoiding false alarms or missed alarms caused by fixed thresholds.

[0026] 2. This invention achieves multi-source cross-validation by comparing the consistency of the test report values ​​with the original collected values ​​and comparing the deviations between the construction party's self-inspection data and the testing agency's sampling data. It can effectively identify data anomalies such as inconsistencies between the reported values ​​and the original records, and abnormal deviations between self-inspection and sampling data.

[0027] Other features and advantages of the invention will be set forth in the following description, and will be apparent in part from the description, or may be learned by practicing embodiments of the invention. The objects and other advantages of the invention may be realized and obtained by means of the structures particularly pointed out in the written description, claims, and drawings. Attached Figure Description

[0028] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present invention and should not be regarded as a limitation on the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0029] Figure 1 This is a schematic diagram of the process for preventing tampering and providing early warning of anomalies in engineering quality inspection data as described in this embodiment of the invention;

[0030] Figure 2 This is a schematic diagram of the engineering quality inspection data anti-tampering and anomaly early warning system described in this embodiment of the invention;

[0031] Figure 3 This is a schematic diagram of the structure of the engineering quality inspection data anti-tampering and anomaly early warning device described in this embodiment of the invention.

[0032] Marked in the image:

[0033] 800. Equipment for preventing tampering and providing early warning of anomalies in engineering quality inspection data; 801. Processor; 802. Memory; 803. Multimedia components; 804. I / O interface; 805. Communication components. Detailed Implementation

[0034] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. The components of the embodiments of the present invention described and shown in the accompanying drawings can generally be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the claimed invention, but merely to illustrate selected embodiments of the invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without inventive effort are within the scope of protection of the present invention.

[0035] It should be noted that similar reference numerals and letters in the following figures indicate similar items; therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures. Furthermore, in the description of this invention, terms such as "first," "second," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0036] Example 1:

[0037] This embodiment provides a method for preventing tampering and providing early warning of anomalies in engineering quality inspection data, which is particularly suitable for large-scale infrastructure construction projects with stringent requirements for the authenticity of quality inspection data, such as civil aviation, highways, railways, water conservancy, housing construction, and municipal engineering. Specifically, this embodiment is described using a cloud platform.

[0038] See Figure 1 The figure illustrates the flow of the method of the present invention, specifically including steps S100 to S700:

[0039] S100. Obtain the original test data from the testing instrument and store it in a tamper-proof manner;

[0040] In this embodiment, a data acquisition terminal is installed at the data output interface of the test instrument and connected to the instrument via an RS232 or RS485 interface to read real-time raw test data at a frequency of not less than 10Hz.

[0041] Specifically, each piece of raw test data includes load-displacement curves and peak loads of the steel reinforcement's mechanical properties, failure loads and loading rates of concrete's compressive or flexural strength, temperature cycle curves and number of cycles of the freeze-thaw test, and tear strength and tensile strength curves of the geosynthetic materials. Each piece of raw data also includes a timestamp, equipment ID, and operator ID.

[0042] Alternatively, when the testing instrument does not have a data output interface, it can be connected to the testing instrument via RS232, RS485 or Bluetooth interface to identify and parse the data formats of different instruments and collect raw data in real time.

[0043] After collection, the raw test data is subjected to SM3 hash operation to generate a hash value, which is then uploaded to the blockchain node for on-chain notarization. At the same time, the raw test data is stored in a local encrypted database and cannot be deleted.

[0044] Based on the above embodiments, this method further includes:

[0045] S200. Generate a test report based on the original test data, and preserve the test report in an anti-tampering manner;

[0046] In this embodiment, after receiving the original test data, the cloud platform extracts the test values ​​of each test item from the original test data, fills the test values ​​of each test item into a preset test report template, and generates a test report, ensuring that the test values ​​in the test report are consistent with the original data. For example, for the mechanical property testing of steel bars, the converted results of yield load and peak load in the original data are directly filled into the test report, and manual modification is not allowed.

[0047] After the test report is generated, the test report data is subjected to the national cryptographic SM3 hash operation to generate the test report hash value, and then uploaded to the blockchain node for on-chain evidence storage.

[0048] Based on the above embodiments, this method further includes:

[0049] S300. Based on the current project type, level, and equipment accuracy, match the allowable deviation threshold from the dynamic parameter library; simultaneously, use a Bayesian adaptive threshold model to correct instrument accuracy drift in real time. In this embodiment, the dynamic parameter library pre-stores indicator systems, evaluation criteria, and equipment accuracy parameters for different engineering scenarios. The following explanation uses a civil aviation airfield engineering project as an example.

[0050] Specifically, step S300 includes:

[0051] S310. Read the current project type and select the corresponding indicator system and evaluation criteria from the dynamic parameter library. Specifically, the project type includes cement pavement, asphalt pavement, etc.; for example, for cement pavement projects, the indicator system includes indicators such as flatness, texture depth, and height difference between adjacent slabs, and the evaluation criteria corresponding to each indicator are preset according to civil aviation standards such as MH 5007.

[0052] S320. After selecting the indicator system and evaluation criteria, read the current project level and dynamically adjust the acceptable range of each key indicator. The key indicators include at least flexural strength, compaction degree, frost resistance grade, and flatness acceptance rate. For example, the flexural strength of cement concrete is ≥5MPa and ≥4.5MPa according to aviation standards; the compaction degree of the roadbed fill is ≥95% and ≥94% according to aviation standards; the frost resistance grade of cement concrete surface layer is ≥300 and ≥200 according to the construction area; and the surface flatness is ≤3mm and ≤5mm according to the structural layer and construction area. For 4E-level airports, the pavement flatness requirements are stricter than those for 4C-level general aviation airports, and the parameter database automatically narrows or widens the acceptable range accordingly.

[0053] S330. Read the accuracy data from the latest calibration certificate of the currently used testing equipment, perform accuracy compensation based on the qualified range, and obtain the final allowable deviation threshold. Specifically, if the calibration accuracy of the laser flatness tester is ±0.5mm, then the accuracy deviation is added to the flatness acceptable range as the final allowable deviation threshold.

[0054] S340. A Bayesian adaptive threshold model is used to correct instrument accuracy drift. Specifically, online change point detection is performed on the time-series data of the historical self-test-sampling deviation rate of each instrument, and the posterior probability of accuracy drift occurring at the current moment is calculated. ,in, Indicates the first The self-inspection-sampling deviation rate of each event point, i.e. In the past Deviation rate sequence at each time point Below is the probability that the instrument is currently experiencing accuracy drift. When an accuracy drift is detected, i.e. At that time, the standard deviation of the deviation rate during the drift period is automatically calculated. And correct the current comparison threshold based on the standard deviation. :

[0055] ;

[0056] In the formula, The basic permissible error range specified in the instrument calibration certificate. In this embodiment, the tightening factor is... .when At a confidence level of 95%, this is suitable for critical testing instruments or high-level aerospace engineering projects where high data accuracy is required; when... At a confidence level of 99.7%, it is suitable for non-critical testing instruments or low-level aviation transportation engineering where false alarm rates are critical.

[0057] The correction method used in this embodiment can automatically tighten the comparison threshold when the instrument status fluctuates greatly, making the requirements for data consistency more stringent, thereby providing early warning of potential data quality risks caused by instrument aging.

[0058] S400. Obtain the self-inspection data from the construction party and the sampling inspection data from the testing agency, compare the test report with the original test data, and compare the self-inspection data with the sampling inspection data to obtain the comparison results;

[0059] Specifically, step S400 includes:

[0060] S410. Extract the reported values ​​of each test item from the test report, extract the corresponding original collected values ​​from the original test data according to the test item name, and compare the reported values ​​of each test item with the original collected values ​​one by one. When the reported value of any test item exceeds the preset value consistency tolerance range, it is determined that the values ​​are inconsistent, and the inconsistent test item, reported value, and original collected value are recorded.

[0061] In this embodiment, the numerical consistency tolerance range is set comprehensively based on factors such as the accuracy indicators of the testing instrument itself, the regulations on numerical rounding intervals in relevant testing standards (e.g., rounding to even numbers), and the cumulative errors during data acquisition and transmission. For example, for the load value of a pressure testing machine, a relative tolerance of ±0.5% or an absolute tolerance of ±0.1kN can be set. The tolerance range is configurable to adapt to instruments with different accuracy levels and testing requirements of varying severity.

[0062] S420. Comparison of discrepancies between the contractor's self-inspection data and the testing agency's random inspection data. Specifically, for engineering projects... Testing items The values ​​of the tested items in the self-inspection data submitted by the construction company are as follows: The value of this tested item in the sample data obtained by the testing agency through random sampling is... The deviation between the self-inspection data and the sampling inspection data is calculated using the following formula:

[0063] ;

[0064] in, For engineering projects Target Inspection Project Deviation value.

[0065] For each testing item The calculated deviation value Deviation allowable threshold Comparison: When If any discrepancies occur, it is considered an inconsistency. Finally, all test items showing inconsistencies and their corresponding deviation values ​​are recorded.

[0066] S500. Construct a corresponding capability profile based on the historical testing data of the testing institution, use an unsupervised anomaly detection algorithm to score the abnormal behavior of the testing institution, and generate a comprehensive anomaly score result based on the score.

[0067] Specifically, step S500 includes:

[0068] S510. Extract multi-dimensional behavioral features from the historical testing data of the testing institution, wherein the behavioral features include at least:

[0069] Historical pass rate: Distribution of historical pass rates for each testing parameter;

[0070] Missing data rate in test reports: The proportion of key parameters missing in test reports;

[0071] Testing timeliness distribution: The distribution of time intervals from the completion of testing to the issuance of the report;

[0072] It can also include the anomaly reporting rate: the proportion of reports that are returned or questioned;

[0073] Consistency of test results: dimensions such as variance of results among different testers and difference rate with comparison laboratories.

[0074] S520. Normalize the above-mentioned multidimensional behavioral features to eliminate the dimensional differences between the feature dimensions, and obtain the normalized multidimensional behavioral feature vector. Use the normalized multidimensional behavioral features to construct the multidimensional behavioral feature vector of the detection agency, as a capability profile of the detection agency:

[0075] ;

[0076] in, For feature dimension, The value is the normalized value. For feature dimensions The original value, This represents the mean of the feature dimensions across all testing institutions. This represents the standard deviation of the feature dimension across different testing institutions.

[0077] In this embodiment, by normalizing each behavioral feature dimension, the differences between different units such as historical pass rate, detection timeliness, and numerical missing rate can be eliminated, resulting in a normalized multidimensional behavioral feature vector.

[0078] S530. Input the multidimensional behavioral feature vector into an unsupervised anomaly detection algorithm, and the unsupervised anomaly detection algorithm scores the degree of anomaly of the multidimensional behavioral feature vector in each feature dimension.

[0079] Preferably, this embodiment uses the Isolation Forest algorithm, and its anomaly score calculation formula is as follows:

[0080] ;

[0081] in, The abnormal behavior is scored, with a value ranging from 0 to 1. The closer the score is to 1, the more the behavior pattern of the testing agency deviates from the behavior distribution of normal agencies, that is, the higher the degree of abnormality. This represents the multidimensional behavioral feature vector after normalization. Represents sample points The length of the path from the root node to the isolated leaf node in a single isolated tree; Represents sample points Average path length in multiple isolated trees; As the normalization factor, This represents the total number of samples from participating testing institutions. In this embodiment, it refers to the number of isolation trees in an isolated forest. .

[0082] Preferably, the system automatically collects new testing task data from each testing institution at a preset cycle, re-extracts multi-dimensional behavioral features, and updates normalization parameters and the isolation forest model to ensure that the capability profile reflects the latest behavioral trends of the testing institutions.

[0083] This embodiment combines multidimensional behavioral features with the isolated forest algorithm to achieve quantitative anomaly assessment of the behavior of detection agencies without the need for pre-labeled training samples.

[0084] S540. As a preferred embodiment, this embodiment uses Dempster-Shafer evidence theory to fuse two independent evidence sources. The evaluation framework is defined as {credible, untrustworthy}. The anomalous behavior score S of the Isolation Forest algorithm is used. raw Basic probability assignment mapped to the first source of evidence Single data deviation rate With dynamic threshold The ratio is mapped to the basic probability allocation of the second source of evidence. ;in, and Provide the support level for the {untrustworthy} propositions in the evaluation framework. Fusion is achieved through DS composition rules. and A comprehensive anomaly score S is generated. S takes the value [0, 1]. The closer the score is to 1, the more the behavior pattern of the testing agency deviates from that of a normal agency, i.e., the higher the degree of anomaly.

[0085] This embodiment can handle contradictory evidence. For example, if a testing agency has a high historical behavior score, but its current test data has an extremely low deviation rate, a rigid judgment based on a single source of evidence may lead to a misjudgment. However, the comprehensive anomaly score after DS fusion can integrate information from both sides, thereby making a more scientific judgment.

[0086] Based on the above embodiments, this method further includes:

[0087] S600. The anomaly level is determined by combining the comparison results and the comprehensive anomaly score using the DS evidence theory, and an early warning is triggered based on the anomaly level.

[0088] Specifically, this embodiment determines the four-level anomaly level according to the following rules:

[0089] 1) When there are no numerical inconsistencies or deviations, and When deemed reliable, the file is archived normally; among them, The first threshold value is [value]. .

[0090] 2) When there are discrepancies, and If the result is determined to be a mild abnormality, an alert is sent to the testing institution's internal quality management department, and the quality supervision platform records and marks it for attention; among other things, The second threshold is set to a value of [value to be filled in]. .

[0091] 3) When there are discrepancies and inconsistencies, and If the condition is determined to be moderately abnormal, an early warning message will be sent to the construction unit and the supervision unit, and the testing agency's testing qualification for the parameter category stated will be suspended, with a third party entrusted to conduct a review; among these, The third threshold is set to 0.85.

[0092] 4) When there are inconsistent values, or If a serious anomaly is detected, a "Detection Data Anomaly Report" will be automatically generated and pushed to the Civil Aviation Regional Administration's monitoring system via API.

[0093] It should be noted that this embodiment also provides a criterion for determining severe abnormalities, and the specific steps are as follows:

[0094] Extract curve data representing the material's mechanical properties test process from the original test data, and calculate the sample entropy value of the first-order difference sequence of the curve data. ,in, For the embedding dimension, For similarity tolerance, The sequence length is given.

[0095] The absolute value of the difference between the entropy value of each test sample in each test item and the corresponding empirical entropy value threshold is calculated sequentially, and is taken as the entropy value error; in this embodiment, the empirical threshold is 2.5%.

[0096] If the entropy value of any test sample exceeds the preset entropy error allowable threshold, the data source is determined to be abnormal. This indicates that the curve is too smooth and does not conform to the natural fluctuation characteristics of the actual material failure process, suggesting that the original data did not come from a real physical experiment, directly triggering a severe anomaly warning.

[0097] This embodiment, through sample entropy analysis, can effectively identify fraudulent activities by testing personnel, such as using standard test pieces and running instruments without load, to output seemingly reasonable data without conducting real tests, thereby further improving the accuracy and depth of early warning.

[0098] The above judgment logic prioritizes numerical inconsistency as the highest severity level. That is, as long as the value in the test report is inconsistent with the original collected value, it is judged as a severe abnormality regardless of the abnormal behavior score.

[0099] Based on the above embodiments, this method further includes:

[0100] S700. The hash value of the test report and the original test data are stored on the blockchain, and a verification QR code is generated on the test report.

[0101] Specifically, step S700 includes:

[0102] S710. Upload the hash value of the original test data corresponding to the test report and the hash value of the test report data to the blockchain node for on-chain evidence storage. Preferably, in this embodiment, the identity information of the testing personnel is also uploaded to the blockchain node for on-chain evidence storage.

[0103] S720. Obtain the notarization transaction identifier returned by the blockchain when obtaining on-chain notarization.

[0104] S730. Generate a verification QR code based on the evidence storage transaction identifier. The verification QR code contains at least the following information: test report summary information, comparison results between the original test data and the test report, on-chain evidence storage timestamp, identity information of the test personnel, and identity information and qualification status of the testing institution that issued the test report; wherein, the test report summary information includes the report number, project name, and test item.

[0105] S740. The national cryptographic SM2 signature algorithm is used to digitally sign the verification QR code. Specifically, the private key for signing is held by the quality supervision platform, and the supervisor and the construction party can verify the authenticity of the QR code using the corresponding SM2 public key.

[0106] This embodiment provides regulators and construction parties with a means of verifying test data by using blockchain evidence storage and SM2 signature verification QR codes.

[0107] Example 2:

[0108] like Figure 2 As shown, this embodiment provides a system for preventing tampering and providing early warning of anomalies in engineering quality inspection data. The system includes:

[0109] The data acquisition module is used to acquire the raw test data of the testing instrument and store it in a tamper-proof manner.

[0110] The report generation and evidence storage module is used to generate a test report based on the original test data and to store the test report data in an anti-tampering manner.

[0111] The dynamic parameter matching module is used to match allowable deviation thresholds from the dynamic parameter library based on the current project type, level, and equipment accuracy.

[0112] The multi-source cross-validation module is used to compare the consistency of the test report data with the original test data, and to compare the deviation of the construction party's self-inspection data with the sampling inspection data of the testing agency to obtain various comparison results;

[0113] The anomaly scoring module is used to construct a capability profile of the testing institution based on its historical testing data, score the abnormal behavior of the testing institution using an unsupervised anomaly detection algorithm, and generate a comprehensive anomaly score result based on the score.

[0114] The anomaly classification and early warning module is used to determine the anomaly level by combining the comparison results of the above items and the comprehensive anomaly score, and to execute classified early warning and linkage response.

[0115] The verification module is used to store the hash values ​​of the original test data and the test report data on the blockchain for evidence, and to generate a verification QR code on the appendix of the test report.

[0116] Based on the above embodiments, the data acquisition module includes a terminal direct connection unit and an edge gateway unit; wherein:

[0117] The terminal direct connection unit is used to read real-time raw test data from a test instrument with a data interface through a data acquisition terminal installed at the instrument's data output interface, perform a hash operation on the raw test data to generate a unique fingerprint, and upload it to a blockchain node for evidence storage. The raw test data is stored in a local encrypted database and cannot be deleted.

[0118] The edge gateway unit is used to connect to the detection instrument without a data interface through a lightweight edge gateway, parse the data format, collect the raw detection data, and upload it to the cloud platform after adding location and time information. It also supports local caching and resume transmission after network interruption.

[0119] Based on the above embodiments, the report generation and evidence storage module is specifically used for:

[0120] The cloud platform extracts the values ​​of various detection parameters from the original detection data, fills them into the detection report template to generate a detection report, and forces the values ​​of various detection parameters in the detection report to be consistent with the original detection data.

[0121] Based on the above embodiments, the dynamic parameter matching module includes an engineering type matching unit, an engineering level adjustment unit, and an equipment accuracy compensation unit;

[0122] The project type matching unit is used to select the corresponding indicator system and evaluation criteria from the dynamic parameter library according to the project type of the current project.

[0123] The engineering grade adjustment unit is used to dynamically adjust the qualified range of key testing indicators according to the current engineering grade of the project, based on the indicator system and evaluation criteria.

[0124] The equipment accuracy compensation unit is used to perform accuracy compensation on the qualified range based on the latest calibration accuracy data of the currently used testing equipment, based on the qualified range, to obtain the final allowable deviation threshold.

[0125] Based on the above embodiments, the multi-source cross-validation module includes a first validation unit and a second validation unit; wherein:

[0126] The first verification unit is used to extract the name and reported value of each detection parameter from the detection report, match the corresponding original collected value from the original detection data according to the parameter name, compare the reported value of the detection parameter with the original collected value item by item, and determine that the values ​​are inconsistent when the difference between the reported value and the original collected value of any detection parameter exceeds the preset value consistency tolerance range.

[0127] The second verification unit is used to acquire the self-inspection data of the construction party for the target inspection items, and the sampling inspection data of the third-party testing agency for each target inspection item; calculate the absolute value of the difference between the self-inspection data and the sampling inspection data of each parameter in each inspection item in turn to obtain the corresponding deviation value; when the deviation value of any parameter exceeds the allowable deviation threshold, it is determined that the deviation is inconsistent.

[0128] Based on the above embodiments, the capability profiling and anomaly scoring module includes a multi-dimensional feature extraction unit, a normalization processing unit, and an unsupervised anomaly detection unit; wherein:

[0129] The multidimensional feature extraction unit is used to extract multidimensional behavioral features from the historical testing task data of the testing institution according to the historical testing batches of the testing institution. The multidimensional behavioral features include at least: the historical pass rate of each testing parameter, the missing rate of testing report parameters, the distribution of the timeliness of report issuance, and the historical consistency ratio between the testing report value and the corresponding original testing data value.

[0130] The normalization processing unit is used to normalize the behavioral features of each dimension and construct a multi-dimensional behavioral feature vector of the detection agency as a capability profile of the detection agency.

[0131] The unsupervised anomaly detection unit is used to input the multidimensional behavioral feature vector into the unsupervised anomaly detection algorithm, and the unsupervised anomaly detection algorithm scores the degree of anomaly of the multidimensional behavioral feature vector in each feature dimension.

[0132] Based on the above embodiments, the anomaly classification and early warning module includes an archiving unit, a mild handling unit, a moderate handling unit, and a severe handling unit; wherein:

[0133] The archiving unit is used to determine that the data is reliable and archive it when there are no numerical inconsistencies or deviations and the comprehensive anomaly score is less than a first threshold.

[0134] The mild handling unit is used to determine a mild abnormality when there is a deviation inconsistency and the comprehensive abnormality score is greater than or equal to the first threshold and less than the second threshold, and push an early warning to the internal quality management department of the testing institution.

[0135] The moderate handling unit is used to determine a moderate anomaly when there is a discrepancy and the comprehensive anomaly score is greater than or equal to the second threshold and less than the third threshold, and then send an early warning message to the construction unit and the supervision unit.

[0136] When the severe handling unit has inconsistent values ​​or the comprehensive anomaly score is greater than or equal to the third threshold, it determines that the anomaly is severe and generates an anomaly report, which is then sent to the Civil Aviation Regional Administration's monitoring system.

[0137] Based on the above embodiments, the end-to-end evidence storage and verification module includes a hash evidence storage unit, a QR code generation unit, and a signature unit; wherein:

[0138] The hash storage unit is used to upload the hash value of the original test data and the hash value of the test report data to the blockchain node for on-chain storage.

[0139] The QR code generation unit is used to generate a verification QR code based on the on-chain notarized transaction identifier. The information associated with the verification QR code includes: the comparison result between the data in the test report and the original test data, the on-chain notarized timestamp, and the qualification status of the testing institution that issued the test report.

[0140] The signature unit is used to digitally sign the verification QR code using the national cryptographic SM2 signature algorithm.

[0141] It should be noted that the specific methods by which each module performs operations in the system described in the above embodiments have been described in detail in the embodiments related to the method, and will not be elaborated here.

[0142] Example 3:

[0143] Corresponding to the above method embodiments, this embodiment also provides an engineering quality inspection data anti-tampering and anomaly early warning device. The engineering quality inspection data anti-tampering and anomaly early warning device described below and the engineering quality inspection data anti-tampering and anomaly early warning method described above can be referred to in correspondence.

[0144] Figure 3 This is a block diagram illustrating an engineering quality inspection data anti-tampering and anomaly early warning device 800 according to an exemplary embodiment. Figure 3 As shown, the engineering quality inspection data anti-tampering and anomaly early warning device 800 may include: a processor 801 and a memory 802. The engineering quality inspection data anti-tampering and anomaly early warning device 800 may also include one or more of the following: a multimedia component 803, an I / O interface 804, and a communication component 805.

[0145] The processor 801 controls the overall operation of the engineering quality inspection data tamper-proof and anomaly early warning device 800 to complete all or part of the steps in the aforementioned engineering quality inspection data tamper-proof and anomaly early warning method. The memory 802 stores various types of data to support the operation of the engineering quality inspection data tamper-proof and anomaly early warning device 800. This data may include, for example, instructions for any application or method operating on the engineering quality inspection data tamper-proof and anomaly early warning device 800, as well as application-related data, such as contact data, sent and received messages, images, audio, video, etc. The memory 802 can be implemented using any type of volatile or non-volatile storage device or a combination thereof, such as Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read-Only Memory (EPROM), Programmable Read-Only Memory (PROM), Read-Only Memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. The multimedia component 803 may include a screen and an audio component. The screen may be, for example, a touchscreen, and the audio component is used to output and / or input audio signals. For example, the audio component may include a microphone for receiving external audio signals. The received audio signals may be further stored in the memory 802 or transmitted via the communication component 805. The audio component also includes at least one speaker for outputting audio signals. I / O interface 804 provides an interface between processor 801 and other interface modules, such as keyboards, mice, and buttons. These buttons can be virtual or physical. Communication component 805 is used for wired or wireless communication between the engineering quality inspection data tamper-proofing and anomaly early warning device 800 and other devices. Wireless communication includes Wi-Fi, Bluetooth, Near Field Communication (NFC), 2G, 3G, or 4G, or a combination thereof. Therefore, the corresponding communication component 805 may include a Wi-Fi module, a Bluetooth module, and an NFC module.

[0146] In an exemplary embodiment, the engineering quality inspection data anti-tampering and anomaly early warning device 800 may be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to perform the above-described engineering quality inspection data anti-tampering and anomaly early warning method.

[0147] In another exemplary embodiment, a computer-readable storage medium including program instructions is also provided. When executed by a processor, these program instructions implement the steps of the above-described method for preventing tampering and providing early warning of abnormalities in engineering quality inspection data. For example, the computer-readable storage medium may be the memory 802 including the program instructions, which may be executed by the processor 801 of the engineering quality inspection data prevention and abnormality early warning device 800 to complete the above-described method for preventing tampering and abnormalities in engineering quality inspection data.

[0148] Example 4:

[0149] Corresponding to the above method embodiments, this embodiment also provides a readable storage medium. The readable storage medium described below and the method for preventing tampering and providing early warning of anomalies in engineering quality inspection data described above can be referred to in correspondence.

[0150] A readable storage medium storing a computer program, wherein when the computer program is executed by a processor, the steps of the engineering quality inspection data anti-tampering and anomaly early warning method described in the above method embodiment are implemented.

[0151] Specifically, the readable storage medium can be a USB flash drive, a portable hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk, or any other readable storage medium capable of storing program code.

[0152] The above description is merely a preferred embodiment of the present invention and is not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

[0153] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A method for preventing tampering and providing early warning of anomalies in engineering quality inspection data, characterized in that, include: Obtain the raw test data from the testing instrument and preserve it in an tamper-proof manner; A test report is generated based on the original test data, and the test report is protected against tampering and stored as evidence. When the test instrument has a data interface, this includes: A data acquisition terminal is installed at the instrument's data output interface to read the raw test data in real time; A hash value is generated by performing a hash operation on the original detection data; The hash value is uploaded to a blockchain node for evidence storage, so that the original detection data is stored in a local encrypted database and cannot be deleted; Based on the current project type, level, and equipment precision, allowable deviation thresholds are matched from the dynamic parameter library, including: Based on the current project type, select the corresponding indicator system and evaluation criteria from the dynamic parameter library; Based on the indicator system and evaluation criteria, the pass range of key testing indicators is dynamically adjusted according to the current engineering level of the project. Based on the calibration accuracy data of the currently used testing equipment, the acceptable range is compensated for accuracy to obtain the final allowable deviation threshold. Obtain the self-inspection data from the construction party and the random inspection data from the testing agency. Compare the test reports with the original test data and the self-inspection data with the random inspection data to obtain the comparison results. Based on the historical testing data of the testing institution, a corresponding capability profile is constructed. An unsupervised anomaly detection algorithm is used to score the abnormal behavior of the testing institution. A comprehensive anomaly score result is generated based on the score. The unsupervised anomaly detection algorithm is the Isolation Forest algorithm. The anomaly level is determined by using various comparison results and comprehensive anomaly score results, and early warning and coordinated handling are carried out according to the anomaly level. The hash values ​​of the test report and the original test data are stored on the blockchain for evidence, and a verification QR code is generated in the test report.

2. The method for preventing tampering and providing early warning of anomalies in engineering quality inspection data according to claim 1, characterized in that, A test report is generated based on the original test data, including: Extract the values ​​of each detection parameter from the original detection data; The values ​​of each detection parameter are filled into a preset detection report template to generate a detection report, so that the values ​​of each detection parameter in the detection report are consistent with the original detection data.

3. The method for preventing tampering and providing early warning of anomalies in engineering quality inspection data according to claim 1, characterized in that, The test report is compared with the original test data, including: Extract the names and report values ​​of each test parameter from the test report; Extract the corresponding original collected values ​​from the original detection data according to the names of the detection parameters; The reported values ​​of the detection parameters are compared with the original collected values ​​one by one. If the difference between the reported value and the original collected value of any detection parameter exceeds the preset tolerance range for numerical consistency, it is determined that the values ​​are inconsistent.

4. The method for preventing tampering and providing early warning of anomalies in engineering quality inspection data according to claim 1, characterized in that, Compare the self-inspection data with the random inspection data, including: Obtain the construction party's self-inspection data for the target testing items, as well as the sampling inspection data of the third-party testing agency for each target testing item; Calculate the absolute value of the difference between the self-inspection data and the sampling data for each parameter in each test item to obtain the corresponding deviation value; If the deviation value of any parameter exceeds the allowable deviation threshold, it is determined that the deviation is inconsistent.

5. The method for preventing tampering and providing early warning of anomalies in engineering quality inspection data according to claim 1, characterized in that, Based on the historical testing data of the testing institution, a corresponding capability profile is constructed. An unsupervised anomaly detection algorithm is used to score the abnormal behavior of the testing institution, including: Obtain historical testing task data from the testing institution; Multidimensional behavioral features are extracted from the historical testing task data. These multidimensional behavioral features include at least: the historical pass rate of each testing parameter, the missing rate of testing report parameters, and the distribution of report issuance timeliness. The multidimensional behavioral features are normalized respectively, and the normalized multidimensional behavioral features are used to construct the multidimensional behavioral feature vector of the detection agency, which serves as the capability profile of the detection agency. The multidimensional behavioral feature vector is input into an unsupervised anomaly detection algorithm, which scores the degree of anomaly of the multidimensional behavioral feature vector in each feature dimension.

6. The method for preventing tampering and providing early warning of anomalies in engineering quality inspection data according to claim 1, characterized in that, The anomaly level is determined by using various comparison results and a comprehensive anomaly score. Based on the anomaly level, early warnings and coordinated responses are implemented, including: When there are no numerical inconsistencies or deviations, and the overall anomaly score is less than the first threshold, it is deemed reliable and archived. When there is a discrepancy and the comprehensive abnormality score is greater than or equal to the first threshold and less than the second threshold, it is judged as a mild abnormality and an early warning is sent to the internal quality management department of the testing institution. When there is a discrepancy and the comprehensive anomaly score is greater than or equal to the second threshold and less than the third threshold, it is judged as a moderate anomaly and an early warning message is sent to the construction unit and the supervision unit. If there are numerical inconsistencies, or if the comprehensive anomaly score is greater than or equal to the third threshold, it is determined to be a severe anomaly, and an anomaly report is generated and sent to the Civil Aviation Regional Administration's monitoring system.

7. The method for preventing tampering and providing early warning of anomalies in engineering quality inspection data according to claim 1, characterized in that, The hash values ​​of the test report and the original test data are stored on the blockchain for notarization, and a verification QR code is generated in the test report, including: The hash values ​​of the original test data and the test report data corresponding to the test report are uploaded to the blockchain node for on-chain storage and evidence preservation. Obtain the on-chain notarization timestamp and on-chain notarization transaction identifier; A verification QR code is generated based on the on-chain notarized transaction identifier. The information associated with the verification QR code includes: the comparison result between the data in the test report and the original test data, the on-chain notarized timestamp, and the qualification status of the testing institution that issued the test report. The verification QR code is digitally signed using the national cryptographic SM2 signature algorithm.

8. A system for preventing tampering and providing early warning of anomalies in engineering quality inspection data, used in the method for preventing tampering and providing early warning of anomalies in engineering quality inspection data as described in any one of claims 1-7, characterized in that, include: The data acquisition module is used to acquire the raw test data of the testing instrument and store it in a tamper-proof manner. The report generation and evidence storage module is used to generate a test report based on the original test data and to store the test report data in an anti-tampering manner. The dynamic parameter matching module is used to match allowable deviation thresholds from the dynamic parameter library based on the current project type, level, and equipment accuracy. The multi-source cross-validation module is used to compare the consistency of the test report data with the original test data, and to compare the deviation of the construction party's self-inspection data with the sampling inspection data of the testing agency to obtain various comparison results; The anomaly scoring module is used to construct a capability profile of the testing institution based on its historical testing data, score the abnormal behavior of the testing institution using an unsupervised anomaly detection algorithm, and generate a comprehensive anomaly score result based on the score. The anomaly classification and early warning module is used to determine the anomaly level by combining the comparison results of the above items and the comprehensive anomaly score results, and to execute classified early warning and linkage response. The verification module is used to store the hash values ​​of the original test data and the test report data on the blockchain for evidence, and to generate a verification QR code on the appendix of the test report.

Images