Concealed project acceptance management system for client

Abstract

The invention discloses a hidden project acceptance management system for a client. According to the technical scheme, the hidden project acceptance management system is characterized by comprising data acquisition and processing; a structure analysis module; an online acceptance module; a quality monitoring module; a cloud storage and report generation module; a cross-platform integration and authority management module; the data acquisition and processing comprises a data acquisition module which is used for acquiring physical parameter data of a hidden engineering site through a high-precision sensor; the equipment integration module is used for connecting the sensor with remote control equipment, and the equipment can collect and transmit the physical parameter data in real time; full-process intelligent acceptance and management are realized, the system realizes full-process closed-loop management from data acquisition, preprocessing, analysis, auditing, report generation to storage, and low efficiency and errors caused by manual intervention are eliminated; and utilizing a deep learning model to extract potential rules and abnormal features from complex hidden engineering data, and discovering hidden dangers which are difficult to perceive manually.

Description

Technical Field

[0001] The present invention relates to the technical field of acceptance management systems, and in particular to a concealed project acceptance management system for a client. Background Art

[0002] Concealed works are a crucial component of construction projects. These typically include pipeline laying, waterproofing, structural reinforcement, and other items that are concealed during subsequent construction and difficult to inspect. The quality of these works directly impacts the safety, durability, and performance of a building. To address the technical challenges of concealed work acceptance, a client-side concealed work acceptance management system has emerged. Leveraging data collection, real-time analysis, and an automated acceptance process, it effectively addresses the inefficiencies, management difficulties, and issue tracking inherent in traditional methods, providing a new intelligent solution for quality assurance and optimized management of concealed works. This system not only meets the demands of modern projects for efficient and high-quality acceptance, but also drives the digital and intelligent transformation of the construction industry.

[0003] However, the traditional acceptance method of concealed projects mainly relies on manual inspection and paper records. There are also problems such as that the project acceptance data is mostly stored in paper or simple electronic documents, which makes data integration difficult and lacks systematic records and analysis. Since concealed projects are difficult to re-inspect once completed, the discovery and cause tracing of subsequent problems often require a lot of additional costs and may even lead to technical problems that may pose safety hazards. For this reason, we propose Summary of the Invention

[0004] In view of the deficiencies in the prior art, the present invention provides a concealed engineering acceptance management system for a client, which solves the technical problems mentioned in the above background technology.

[0005] The above technical objectives of the present invention are achieved through the following technical solutions:

[0006] A concealed engineering acceptance management system for a client, comprising:

[0007] Data acquisition and processing; structure analysis module; online acceptance module; quality monitoring module; cloud storage and report generation module; cross-platform integration and rights management module;

[0008] The data collection and processing includes:

[0009] Data acquisition module, used to collect physical parameter data of concealed engineering sites through high-precision sensors;

[0010] A device integration module, used to connect the sensor to a remote control device, so that the device can collect and transmit the physical parameter data in real time;

[0011] A data input module, used to input the collected physical parameter data into the system through a user terminal device, wherein the user terminal device is a mobile terminal device or other smart device;

[0012] A data uploading module is used to transmit the collected physical parameter data to a cloud storage system via a wireless communication protocol;

[0013] A data cleaning module is used to pre-process the collected physical parameter data, including data denoising and verification, to ensure the accuracy and consistency of the data;

[0014] The real-time monitoring module is used to track the changing trends of collected data in real time, automatically generate alarm information when an abnormality occurs, and remind relevant personnel through push notifications;

[0015] Data visualization module generates visual charts or reports of real-time data through user terminal devices, so that users can intuitively understand and process data;

[0016] Data verification module, used to automatically verify the collected data to ensure the accuracy and completeness of the data;

[0017] The data segmentation module is used to segment the collected data according to the size or timestamp of the data so as to upload them in batches and reduce the burden of network transmission;

[0018] The data upload module communicates with the cloud storage system through a security protocol to ensure that the data is encrypted and securely protected during the upload process to prevent data leakage or tampering;

[0019] The data filtering module filters the collected data according to preset rules or algorithms, removes invalid or abnormal data, and improves the accuracy and effectiveness of uploaded data;

[0020] The transmission monitoring module is used to monitor the data upload process, ensure the integrity and real-time nature of the data upload, and automatically retry or issue an alarm notification when an error occurs during the upload process;

[0021] Data integration module, used to uniformly format and integrate data from different sensors or devices for subsequent processing and analysis;

[0022] The data acquisition module includes:

[0023] A sensor module includes at least one sensor for collecting ambient temperature, humidity, pressure, displacement or other physical quantities;

[0024] The location calibration module is used to calibrate the data collected by the sensor according to the geographical location of the project site for subsequent data processing and analysis;

[0025] The device integration module includes a wireless communication interface that supports at least one wireless communication protocol, including but not limited to Bluetooth, WiFi, ZigBee or LoRa, for transmitting collected data to a user terminal device or a cloud storage system;

[0026] The data upload module supports edge computing function, performs preliminary data processing when collecting data, reduces the data load during transmission, and improves data transmission efficiency;

[0027] The data upload module adopts the IoT protocol and uses the MQTT protocol or HTTP protocol to ensure the real-time and high reliability of the data upload process.

[0028] The data cleaning module includes a denoising function for eliminating abnormal noise in the collected data to ensure the validity of the data.

[0029] Preferably, the structure analysis module includes:

[0030] Deep learning models, based on convolutional neural networks or the Mask R-CNN algorithm, identify key features of hidden structures, including the location, quantity, and distribution of steel bars;

[0031] Data comparison module, used to automatically compare analysis results with engineering design drawings to detect deviations or non-compliance;

[0032] The online acceptance module includes:

[0033] Electronic form generation module, quickly generating acceptance forms through pre-filled templates;

[0034] Data input unit, used by acceptance personnel to upload site photos, record key indicators and submit acceptance reports;

[0035] Intelligent audit module, which uses artificial intelligence technology to automatically verify the integrity of the acceptance process and data accuracy;

[0036] The quality monitoring module includes:

[0037] Real-time monitoring unit, used to track and analyze changing trends during data collection and uploading;

[0038] The alarm generation module automatically sends alarm notifications to relevant personnel when data anomalies or deviations from standards are found;

[0039] The problem recording module is used to record problems found during the acceptance process and support tracking and processing.

[0040] Preferably, the cloud storage and report generation module includes:

[0041] Cloud database, used to store collected data, analysis results and acceptance records, supports data storage and backup in multiple formats;

[0042] Automatic report generation module, based on the acceptance process data and analysis results, generates an acceptance report containing construction deviations, suggested improvement plans and charts;

[0043] The cross-platform integration and rights management module includes:

[0044] Platform adaptation module, supporting cross-platform operation of the system on mobile, PC and web terminals;

[0045] The permission control module assigns access rights based on user roles to ensure that only authorized personnel can view, modify or export sensitive data;

[0046] Encrypted communication module ensures data transmission security through TLS or HTTPS protocol.

[0047] Preferably, the data denoising is a process of removing random noise or erroneous data values in the collected data. For each data point, the mean value of the data points in its neighborhood is used to replace the original value. The formula is as follows:

[0048]

[0049] In this formula is the data point after filtering;

[0050] In this formula x j is the original data point;

[0051] In this formula, N is the window size, which is usually 2k+1;

[0052] In this formula, k is the window range;

[0053] The goal of the data verification module is to check the integrity, consistency and logical rationality of the collected data and whether the data is within a reasonable physical range. The formula is as follows:

[0054] x min ≤x i ≤x max

[0055] In this formula x min is the minimum value allowed;

[0056] In this formula x max is the maximum value allowed;

[0057] In this formula x i The original data collected;

[0058] If the data is outside the range, mark it as an outlier.

[0059] Preferably, the data segmentation module adopts a fixed window segmentation algorithm, and the formula is as follows:

[0060] D={d i |t0+n·Δt≤t i <t0+(n+1)·Δt}

[0061] In this formula d i is the i-th data point;

[0062] In this formula t i is the data collection time;

[0063] In this formula, Δt is the time interval of the segment;

[0064] The data module includes low-pass filtering and Kalman filtering. The low-pass filtering is used to remove high-frequency noise, and the Kalman filtering is used for dynamic data optimization. The low-pass filtering algorithm formula is as follows:

[0065] Y(f)=H(f)·X(f)

[0066] In this formula, H(f) is the filter transfer function;

[0067] In this formula, X(f) and Y(f) are the frequency spectra of the input and output signals;

[0068] The Kalman filter algorithm formula is as follows:

[0069]

[0070] In this formula For the current valuation, is the measured value, K k is the Kalman gain.

[0071] Preferably, the transmission data integrity check in the transmission monitoring module adopts a cyclic redundancy check, and the formula is as follows:

[0072] T(x)=M(x)·x k +R(x)

[0073] The receiving end verification formula is:

[0074] T(x)mod G(x)=0

[0075] Where M(x) generates the check digit R(x);

[0076] Where x k is the offset in polynomial form;

[0077] Where R(x) is the check code;

[0078] Where G(x) is the generating polynomial;

[0079] The deep learning model algorithm adopts the convolutional neural network algorithm, and the formula is as follows:

[0080]

[0081] In this formula, I is the input image and K is the convolution kernel.

[0082] Preferably, the data comparison module is based on a comparison algorithm of cosine similarity and Euclidean distance, and the cosine similarity formula is as follows:

[0083]

[0084] Where A and B are vectors;

[0085] The Euclidean distance formula is as follows:

[0086]

[0087] Preferably, the real-time monitoring unit uses a moving average and anomaly detection algorithm based on data time series analysis. The moving average algorithm formula is as follows:

[0088]

[0089] The anomaly detection algorithm formula is as follows:

[0090]

[0091] Where μ is the mean and σ is the standard deviation.

[0092] In summary, the present invention mainly has the following beneficial effects:

[0093] The system implements full-process intelligent acceptance and management, realizing closed-loop management of the entire process from data collection, preprocessing, analysis, review, report generation to storage, eliminating inefficiency and errors caused by manual intervention. Through electronic form generation and intelligent review modules, the system automatically standardizes the concealed project acceptance process to avoid process non-compliance issues caused by inconsistent operations. It uses deep learning models to extract potential patterns and abnormal features from complex concealed project data and discover hidden dangers that are difficult for humans to detect.

[0094] Data is uploaded, cleaned, monitored and analyzed in real time, and acceptance results can be fed back immediately, reducing waiting time and greatly improving acceptance efficiency. Intelligent modules automatically discover and record hidden dangers or deviations, reducing manual investigation time and ensuring that problems can be quickly located and tracked. The system uses distributed storage and cloud computing technologies to process massive amounts of data, support parallel management of multiple projects, and adapt to complex engineering environments.

[0095] During the data collection phase, segmentation, filtering and other algorithms are used to ensure that the collected data is clean and complete; during the data analysis phase, deep learning models and comparison algorithms are used to further optimize the accuracy of the results. The system automatically performs complex verification, calculation and comparison processes to avoid misjudgments or omissions caused by human oversight and subjective judgment.

[0096] The real-time monitoring module can monitor the dynamics of project quality at any time, trigger an alarm immediately when an anomaly is found, improve response speed, and prevent the spread of problems; the problem recording module, combined with the cloud database, can quickly locate the time, location and cause of historical problems, facilitating responsibility tracing and the formulation of improvement measures; based on the analysis of deep learning and data integration modules, the system can evaluate project quality from multiple dimensions and form a basis for scientific decision-making.

[0097] Through the platform adaptation module, the system supports seamless integration of different hardware devices (such as mobile phones, tablets, PCs) and operating systems, improving the efficiency of multi-party collaboration; the system integrates multi-source data into a unified visual report, making it convenient for project teams, acceptance personnel and managers to view key indicators and conduct real-time communication and adjustments; through electronic forms and automatic report generation modules, project acceptance data can be quickly shared, reducing the transfer time in traditional paper workflows.

[0098] Based on cloud architecture, the system can process data from multiple projects simultaneously, and is particularly suitable for the synchronous acceptance management of multiple projects in large enterprises or government projects; the modular design makes the system easy to expand, and can add new functional modules according to specific needs or support more complex hidden engineering scenarios. BRIEF DESCRIPTION OF THE DRAWINGS

[0099] Figure 1 It is a data flow diagram of the present invention. DETAILED DESCRIPTION

[0100] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0101] refer to Figure 1 , a concealed engineering acceptance management system for a client, comprising:

[0102] Data acquisition and processing; structure analysis module; online acceptance module; quality monitoring module; cloud storage and report generation module; cross-platform integration and rights management module;

[0103] Data collection and processing include:

[0104] Data acquisition module, used to collect physical parameter data of concealed engineering sites through high-precision sensors;

[0105] Device integration module, used to connect sensors to remote control devices, enabling the device to collect and transmit physical parameter data in real time;

[0106] The data input module is used to input the collected physical parameter data into the system through the user terminal device, which is a mobile terminal device or other smart device;

[0107] Data upload module, used to transmit the collected physical parameter data to the cloud storage system through wireless communication protocol;

[0108] Data cleaning module, used to pre-process the collected physical parameter data, including data denoising and verification, to ensure data accuracy and consistency;

[0109] The real-time monitoring module is used to track the changing trends of collected data in real time, automatically generate alarm information when an abnormality occurs, and remind relevant personnel through push notifications;

[0110] Data visualization module generates visual charts or reports of real-time data through user terminal devices, so that users can intuitively understand and process data;

[0111] Data verification module, used to automatically verify the collected data to ensure the accuracy and completeness of the data;

[0112] The data segmentation module is used to segment the collected data according to the size or timestamp of the data so as to upload them in batches and reduce the burden of network transmission;

[0113] The data upload module communicates with the cloud storage system through a secure protocol to ensure that data is encrypted and securely protected during the upload process to prevent data leakage or tampering;

[0114] The data filtering module filters the collected data according to preset rules or algorithms, removes invalid or abnormal data, and improves the accuracy and effectiveness of uploaded data;

[0115] The transmission monitoring module is used to monitor the data upload process, ensure the integrity and real-time nature of the data upload, and automatically retry or issue an alarm notification when an error occurs during the upload process;

[0116] Data integration module, used to uniformly format and integrate data from different sensors or devices for subsequent processing and analysis;

[0117] The data acquisition module includes:

[0118] A sensor module includes at least one sensor for collecting ambient temperature, humidity, pressure, displacement or other physical quantities;

[0119] The location calibration module is used to calibrate the data collected by the sensor according to the geographical location of the project site for subsequent data processing and analysis;

[0120] The device integration module includes a wireless communication interface that supports at least one wireless communication protocol, including but not limited to Bluetooth, WiFi, ZigBee or LoRa, for transmitting collected data to a user terminal device or a cloud storage system;

[0121] The data upload module supports edge computing functions, performs preliminary data processing when collecting data, reduces the data load during transmission, and improves data transmission efficiency;

[0122] The data upload module adopts the IoT protocol and uses the MQTT protocol or HTTP protocol to ensure the real-time and high reliability of the data upload process.

[0123] The data cleaning module includes: denoising processing function, which is used to eliminate abnormal noise in the collected data and ensure the validity of the data.

[0124] The structure analysis module includes:

[0125] Deep learning models, based on convolutional neural networks or the Mask R-CNN algorithm, identify key features of hidden structures, including the location, quantity, and distribution of steel bars;

[0126] Data comparison module, used to automatically compare analysis results with engineering design drawings to detect deviations or non-compliance;

[0127] The online acceptance module includes:

[0128] Electronic form generation module, quickly generating acceptance forms through pre-filled templates;

[0129] Data input unit, used by acceptance personnel to upload site photos, record key indicators and submit acceptance reports;

[0130] Intelligent audit module, which uses artificial intelligence technology to automatically verify the integrity of the acceptance process and data accuracy;

[0131] The quality monitoring module includes:

[0132] Real-time monitoring unit, used to track and analyze changing trends during data collection and uploading;

[0133] The alarm generation module automatically sends alarm notifications to relevant personnel when data anomalies or deviations from standards are found;

[0134] The problem recording module is used to record problems found during the acceptance process and support tracking and processing.

[0135] The cloud storage and report generation module includes:

[0136] Cloud database, used to store collected data, analysis results and acceptance records, supports data storage and backup in multiple formats;

[0137] Automatic report generation module, based on the acceptance process data and analysis results, generates an acceptance report containing construction deviations, suggested improvement plans and charts;

[0138] Cross-platform integration and rights management modules include:

[0139] Platform adaptation module, supporting cross-platform operation of the system on mobile, PC and web terminals;

[0140] The permission control module assigns access rights based on user roles to ensure that only authorized personnel can view, modify or export sensitive data;

[0141] Encrypted communication module ensures data transmission security through TLS or HTTPS protocol.

[0142] Data denoising is the process of removing random noise or erroneous data values from collected data. For each data point, the mean value of the data points in its neighborhood is used to replace the original value. The formula is as follows:

[0143]

[0144] In this formula is the data point after filtering;

[0145] In this formula x j is the original data point;

[0146] In this formula, N is the window size, which is usually 2k+1;

[0147] In this formula, k is the window range;

[0148] The goal of the data verification module is to check the integrity, consistency, and logical rationality of the collected data, and to check whether the data is within a reasonable physical range. The formula is as follows:

[0149] x min ≤x i ≤x max

[0150] In this formula x min is the minimum value allowed;

[0151] In this formula x max is the maximum value allowed;

[0152] In this formula x i The original data collected;

[0153] If the data is outside the range, mark it as an outlier.

[0154] The data segmentation module uses a fixed window segmentation algorithm, the formula is as follows:

[0155] D={d i |t0+n·Δt≤t i <t0+(n+1)·Δt}

[0156] In this formula d i is the i-th data point;

[0157] In this formula t i is the data collection time;

[0158] In this formula, Δt is the time interval of the segment;

[0159] The data module includes low-pass filtering and Kalman filtering. Low-pass filtering is used to remove high-frequency noise, and Kalman filtering is used for dynamic data optimization. The low-pass filtering algorithm formula is as follows:

[0160] Y(f)=H(f)·X(f)

[0161] In this formula, H(f) is the filter transfer function;

[0162] In this formula, X(f) and Y(f) are the frequency spectra of the input and output signals;

[0163] The Kalman filter algorithm formula is as follows:

[0164]

[0165] In this formula For the current valuation, is the measured value, K k is the Kalman gain.

[0166] The transmission data integrity check in the transmission monitoring module adopts cyclic redundancy check, and the formula is as follows:

[0167] T(x)=M(x)·x k +R(x)

[0168] The receiving end verification formula is:

[0169] T(x)mod G(x)=0

[0170] Where M(x) generates the check digit R(x);

[0171] Where xk is the offset in polynomial form;

[0172] Where R(x) is the check code;

[0173] Where G(x) is the generating polynomial;

[0174] The deep learning model algorithm uses the convolutional neural network algorithm, and the formula is as follows:

[0175]

[0176] In this formula, I is the input image and K is the convolution kernel.

[0177] The data comparison module is based on the cosine similarity and Euclidean distance comparison algorithm. The cosine similarity formula is as follows:

[0178]

[0179] Where A and B are vectors;

[0180] The Euclidean distance formula is as follows:

[0181]

[0182] The real-time monitoring unit uses moving average and anomaly detection algorithms based on data time series analysis. The moving average algorithm formula is as follows:

[0183]

[0184] The anomaly detection algorithm formula is as follows:

[0185]

[0186] Where μ is the mean and σ is the standard deviation.

[0187] While embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions, and variations may be made to these embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the appended claims and their equivalents.

Claims

1. A concealed engineering acceptance management system for a client, characterized in that: include: Data collection and processing; Structural analysis module; Online acceptance module; Quality monitoring module; Cloud storage and report generation modules; Cross-platform integration and rights management module; The data collection and processing include: Data acquisition module, used to collect physical parameter data of concealed engineering sites through high-precision sensors; A device integration module, used to connect the sensor to a remote control device, so that the device can collect and transmit the physical parameter data in real time; A data input module, used to input the collected physical parameter data into the system through a user terminal device, wherein the user terminal device is a mobile terminal device or other smart device; A data uploading module is used to transmit the collected physical parameter data to a cloud storage system via a wireless communication protocol; A data cleaning module is used to pre-process the collected physical parameter data, including data denoising and verification, to ensure the accuracy and consistency of the data; The real-time monitoring module is used to track the changing trends of collected data in real time, automatically generate alarm information when an abnormality occurs, and remind relevant personnel through push notifications; Data visualization module generates visual charts or reports of real-time data through user terminal devices, so that users can intuitively understand and process data; Data verification module, used to automatically verify the collected data to ensure the accuracy and completeness of the data; The data segmentation module is used to segment the collected data according to the size or timestamp of the data so as to upload them in batches and reduce the burden of network transmission; The data upload module communicates with the cloud storage system through a security protocol to ensure that the data is encrypted and securely protected during the upload process to prevent data leakage or tampering; The data filtering module filters the collected data according to preset rules or algorithms, removes invalid or abnormal data, and improves the accuracy and effectiveness of uploaded data; The transmission monitoring module is used to monitor the data upload process, ensure the integrity and real-time nature of the data upload, and automatically retry or issue an alarm notification when an error occurs during the upload process; Data integration module, used to uniformly format and integrate data from different sensors or devices for subsequent processing and analysis; The data acquisition module includes: A sensor module includes at least one sensor for collecting ambient temperature, humidity, pressure, displacement or other physical quantities; The location calibration module is used to calibrate the data collected by the sensor according to the geographical location of the project site for subsequent data processing and analysis; The device integration module includes a wireless communication interface that supports at least one wireless communication protocol, including but not limited to Bluetooth, WiFi, ZigBee or LoRa, for transmitting collected data to a user terminal device or a cloud storage system; The data upload module supports edge computing function, performs preliminary data processing when collecting data, reduces the data load during transmission, and improves data transmission efficiency; The data upload module adopts the IoT protocol and uses the MQTT protocol or HTTP protocol to ensure the real-time and high reliability of the data upload process. The data cleaning module includes a denoising function for eliminating abnormal noise in the collected data to ensure the validity of the data.

2. A concealed engineering acceptance management system for a client according to claim 1, characterized in that: The structure analysis module includes: Deep learning models, based on convolutional neural networks or the Mask R-CNN algorithm, identify key features of hidden structures, including the location, quantity, and distribution of steel bars; Data comparison module, used to automatically compare analysis results with engineering design drawings to detect deviations or non-compliance; The online acceptance module includes: Electronic form generation module, quickly generating acceptance forms through pre-filled templates; Data input unit, used by acceptance personnel to upload site photos, record key indicators and submit acceptance reports; Intelligent audit module, which uses artificial intelligence technology to automatically verify the integrity of the acceptance process and data accuracy; The quality monitoring module includes: Real-time monitoring unit, used to track and analyze changing trends during data collection and uploading; The alarm generation module automatically sends alarm notifications to relevant personnel when data anomalies or deviations from standards are found; The problem recording module is used to record problems found during the acceptance process and support tracking and processing.

3. A concealed engineering acceptance management system for a client according to claim 1, characterized in that: The cloud storage and report generation module includes: Cloud database, used to store collected data, analysis results and acceptance records, supports data storage and backup in multiple formats; Automatic report generation module, based on the acceptance process data and analysis results, generates an acceptance report containing construction deviations, suggested improvement plans and charts; The cross-platform integration and rights management module includes: Platform adaptation module, supporting cross-platform operation of the system on mobile, PC and web terminals; The permission control module assigns access rights based on user roles to ensure that only authorized personnel can view, modify or export sensitive data; Encrypted communication module ensures data transmission security through TLS or HTTPS protocol.

4. A concealed engineering acceptance management system for a client according to claim 1, characterized in that: Data denoising is the process of removing random noise or erroneous data values from the collected data. Mean filtering is used to replace the original value of each data point with the mean of the data points in its neighborhood. The formula is as follows: In this formula is the data point after filtering; In this formula x j is the original data point; In this formula, N is the window size, which is usually 2k+1; In this formula, k is the window range; The goal of the data verification module is to check the integrity, consistency and logical rationality of the collected data and whether the data is within a reasonable physical range. The formula is as follows: x min ≤x i ≤x max In this formula x min is the minimum value allowed; In this formula x max is the maximum value allowed; In this formula x i The original data collected; If the data is outside the range, mark it as an outlier.

5. A concealed engineering acceptance management system for a client according to claim 1, characterized in that: The data segmentation module adopts a fixed window segmentation algorithm, and the formula is as follows: D={d i |t0+n·Δt≤t i <t0+(n+1)·Δt} In this formula d i is the i-th data point; In this formula t i is the data collection time; In this formula, Δt is the time interval of the segment; The data module includes low-pass filtering and Kalman filtering. The low-pass filtering is used to remove high-frequency noise, and the Kalman filtering is used for dynamic data optimization. The low-pass filtering algorithm formula is as follows: Y(f)=H(f)·X(f) In this formula, H(f) is the filter transfer function; In this formula, X(f) and Y(f) are the frequency spectra of the input and output signals; The Kalman filter algorithm formula is as follows: In this formula For the current valuation, is the measured value, K k is the Kalman gain.

6. A concealed engineering acceptance management system for a client according to claim 1, characterized in that: The transmission data integrity check in the transmission monitoring module adopts cyclic redundancy check, and the formula is as follows: T(x)=M(x)·x k +R(x) The receiving end verification formula is: T(x)modG(x)=0 Where M(x) generates the check digit R(x); Where x k is the offset in polynomial form; Where R(x) is the check code; Where G(x) is the generating polynomial; The deep learning model algorithm adopts the convolutional neural network algorithm, and the formula is as follows: In this formula, I is the input image and K is the convolution kernel.

7. A concealed engineering acceptance management system for a client according to claim 1, characterized in that: The data comparison module is based on the cosine similarity and Euclidean distance comparison algorithm. The cosine similarity formula is as follows: Where A and B are vectors; The Euclidean distance formula is as follows:

8. A concealed engineering acceptance management system for a client according to claim 1, characterized in that: The real-time monitoring unit uses a moving average and anomaly detection algorithm based on the data time series analysis. The moving average algorithm formula is as follows: The anomaly detection algorithm formula is as follows: Where μ is the mean and σ is the standard deviation.

Images