Engineering monitoring project automatic report generation method and system

Abstract

The invention discloses an engineering monitoring project automatic report generation method and system. The method comprises the following steps: establishing a standardized report template library taking the type of a measuring instrument as a benchmark; a multi-dimensional analysis model established based on an analytic hierarchy process and a fuzzy comprehensive evaluation method is utilized to carry out automatic safety risk grade evaluation on actual monitoring data; a safety risk assessment grade result is automatically extracted, early warning statistics and early warning disposal suggestions are generated, and trend prediction is carried out on monitoring data; and integrating the acquired actual monitoring data and the processing result, and automatically filling a corresponding standardized report template to generate a complete structured report. According to the invention, automation and intelligentization of the whole process from collection, processing and analysis of monitoring data to report generation are realized, informatization construction management can be effectively guided, security risk dynamic control and grading early warning decision based on real-time data are supported, and report generation efficiency, data analysis accuracy and security management intelligentization level are significantly improved.

Description

Technical Field

[0001] This invention relates to the field of engineering monitoring data processing technology, specifically to an automated report generation method and system for engineering monitoring projects. Background Technology

[0002] Engineering safety monitoring plays an increasingly important role in ensuring construction safety and preventing accidents. By deploying various sensors and measuring instruments, engineering monitoring acquires key parameters such as deformation, stress, and water level of engineering structures in real time, providing data support for engineering safety assessments and risk warnings. However, existing data analysis methods have the following problems:

[0003] (1) Low efficiency in report production: Traditional engineering monitoring reports mainly rely on manual compilation. Monitoring personnel need to export raw data from various instruments, then organize, calculate, and plot the data in software such as Excel, and finally write the report in Word. The whole process is time-consuming and involves a lot of repetitive work. It often takes 3-4 hours to compile a monitoring report, which is difficult to meet the real-time requirements of engineering monitoring information.

[0004] (2) Insufficient depth of data analysis: Most existing monitoring reports only perform simple statistical and comparative analysis of monitoring data, such as maximum value, minimum value, and change, and lack in-depth exploration of the inherent laws of monitoring data. There is insufficient analysis on the correlation between multiple monitoring items, the spatiotemporal evolution characteristics of monitoring data, and the comprehensive evaluation of potential risk factors, resulting in limited guiding value of monitoring reports.

[0005] (3) The risk warning mechanism is too simplistic: Current warning methods are mainly based on a simple comparison between a single indicator and a warning threshold. An alarm is triggered when the monitored value exceeds the warning threshold. This method fails to comprehensively consider factors such as the rate of change, the trend of change, and the scope of impact, which can easily lead to false alarms or missed alarms. The accuracy and timeliness of the warning need to be improved. At the same time, the warning information is often independent of the monitoring reports and is not organically integrated, which affects the efficiency of decision-making.

[0006] (4) Human error is hard to avoid: In the process of manually compiling reports, problems such as data entry errors, calculation mistakes, and non-standard chart drawing often occur, affecting the accuracy and authority of the monitoring reports. In addition, there are significant differences in the format, content, and depth of reports compiled by different monitoring personnel, which lack standardization and normalization.

[0007] (5) Inability to predict trends: Existing monitoring reports mainly analyze and summarize monitoring data that has already occurred, lacking the ability to predict future development trends. Construction management personnel cannot know potential risks in advance and can only respond passively, which is not conducive to proactive safety management of the project.

[0008] (6) Low data utilization: A large amount of monitoring data is only used for simple report compilation, and the deeper value of the data is not fully explored. Valuable information such as the correlation between monitoring data, evolution patterns, and anomaly patterns are ignored, resulting in a waste of data resources.

[0009] (7) The report format is monotonous: Traditional monitoring reports are mostly static Word or PDF documents, lacking interactivity and visualization effects, making it difficult to intuitively display the spatial distribution and temporal evolution characteristics of monitoring data, which is not conducive to understanding and use by non-professionals.

[0010] Based on the above problems, there is an urgent need to develop an intelligent and automated method for generating monitoring reports, so as to realize rapid processing, in-depth analysis and risk warning of monitoring data, improve the efficiency and quality of monitoring work, and provide more reliable technical support for engineering safety management. Summary of the Invention

[0011] This application provides an automated report generation method and system for engineering monitoring projects to solve the technical problems of long production cycles, high reliance on manual labor, insufficient depth of data analysis, and delayed risk warning in traditional monitoring reports, thereby enabling rapid generation of monitoring reports, intelligent analysis of monitoring data, and dynamic assessment of engineering safety risks.

[0012] According to the first aspect, one embodiment provides a method for automatically generating reports for engineering monitoring projects, the method comprising:

[0013] The various monitoring items in engineering monitoring projects are classified, and a standardized report template library based on the type of measuring instrument is established. Based on the standardized report templates, the standardized collection, storage and retrieval of monitoring data for different items are realized.

[0014] Based on a pre-established set of evaluation indicators, and using a multi-dimensional analysis model based on the analytic hierarchy process and fuzzy comprehensive evaluation method, an automated safety risk level assessment is performed on the actual monitoring data to obtain the safety risk level assessment results.

[0015] Automatically extract safety risk assessment results, generate early warning statistics and early warning handling suggestions, and perform trend prediction on monitoring data;

[0016] The system integrates the collected actual monitoring data, safety risk level assessment results, early warning statistics and early warning handling suggestions, and monitoring data trend prediction results, and automatically fills them into the corresponding standardized report templates to generate complete structured reports.

[0017] Furthermore, the various monitoring items in the engineering monitoring project are categorized, specifically including:

[0018] The monitoring items include displacement monitoring, stress-strain monitoring, water level monitoring, and settlement monitoring.

[0019] Furthermore, a standardized report template library based on the type of measuring instrument will be established, specifically including:

[0020] The measuring instruments are classified according to their type, which includes inclinometers, strain gauges, water level gauges, total stations, and levels.

[0021] Define a data field structure for each instrument type and create standardized report templates for different measuring instrument types. The standardized report templates include a header and a body, where the header contains basic information about the measurement items and the body contains monitoring data of the monitoring points and related data processing results.

[0022] Establish report display formats corresponding to each instrument type, including data table styles, chart types, and analysis indicators.

[0023] Furthermore, based on a pre-established set of evaluation indicators and using a multi-dimensional analysis model established using the analytic hierarchy process (AHP) and fuzzy comprehensive evaluation method, an automated safety risk level assessment is performed on the actual monitoring data to obtain the safety risk level assessment results, specifically including:

[0024] Determine the set of evaluation indicators , n≥6, where u1 is the size of the monitored value, u2 is the rate of change, u3 is the cumulative change, u4 is the proximity of the warning threshold, u5 is the number of alarm points, and u6 is the dispersion of the monitored data;

[0025] Construct a judgment matrix, and use the 1-9 scaling method to compare each evaluation index pairwise, thereby calculating the weight vector set of each evaluation index. ;

[0026] Perform a consistency test and calculate the consistency ratio CR. When CR < 0.1, the judgment matrix is ​​considered to have satisfactory consistency.

[0027] Establish evaluation level set These correspond to four levels: safe, basically safe, warning, and dangerous.

[0028] Establish a single-factor evaluation matrix R and determine the membership degree of each evaluation indicator to each evaluation level;

[0029] Perform fuzzy synthesis operation to calculate the comprehensive evaluation vector B=W·R, where W is the weight vector and R is the single-factor evaluation matrix;

[0030] The safety risk level of the project is determined based on the principle of maximum membership.

[0031] Furthermore, trend prediction is performed on the monitoring data, specifically including:

[0032] Establish a time series model based on historical monitoring data;

[0033] The LSTM model is used to predict future monitoring values;

[0034] By comparing the forecast results with the early warning threshold, potential risks can be identified in advance;

[0035] The trend prediction results are integrated into the monitoring reports in the form of curves.

[0036] Furthermore, the collected actual monitoring data, safety risk level assessment results, early warning statistics and early warning handling suggestions, and monitoring data trend prediction results are integrated and automatically filled into the corresponding standardized report templates to generate complete structured reports, specifically including:

[0037] The final complete report includes a project cover, project overview, monitoring plan introduction, data summary information, detailed information for each monitoring item, comprehensive safety assessment, risk warning prompts and handling suggestions. The detailed information for each monitoring item includes data curves, comparative analysis, and anomaly annotations.

[0038] Furthermore, the specific items in the complete report include:

[0039] The cover page includes the project name, report number, report period, preparation date, and preparing organization;

[0040] Project overview, including project location, project scale, surrounding environment, and geological conditions;

[0041] A brief overview of the monitoring plan, including monitoring objectives, monitoring items, monitoring point layout, and monitoring frequency;

[0042] Data summary information includes statistical tables of monitoring data for each measurement item, a summary of alarm situations, and an overview of changing trends;

[0043] Detailed information for each measurement item, including a specific plan of measurement point layout, monitoring data tables, time history curves, cumulative change bar charts, rate of change curves, and annotations of abnormal data;

[0044] Comprehensive safety assessment, including safety risk level assessment results and analysis of various assessment indicators;

[0045] Risk warning prompts include a list of alarm monitoring points, risk area identification, and warning level;

[0046] Recommendations for handling situations, including recommendations for engineering measures to address the warning situation.

[0047] Furthermore, the method also includes:

[0048] It supports multiple report output formats, including PDF, Word, and Excel, and also supports custom report configuration and batch generation.

[0049] According to a second aspect, one embodiment provides an automated report generation system for engineering monitoring projects, the system comprising:

[0050] The report template creation module is used to classify various monitoring items in engineering monitoring projects and establish a standardized report template library based on the type of measuring instrument. Based on the standardized report templates, the standardized collection, storage and retrieval of monitoring data for different items can be realized.

[0051] The safety risk assessment module is used to automatically assess the safety risk level of actual monitoring data based on a pre-established set of evaluation indicators and a multi-dimensional analysis model based on the analytic hierarchy process and fuzzy comprehensive evaluation method, and obtain the safety risk level assessment results.

[0052] The security risk information integration module is used to automatically extract security risk assessment results, generate early warning statistics and early warning handling suggestions, and perform trend prediction on monitoring data;

[0053] The automatic report generation module integrates the collected actual monitoring data, safety risk level assessment results, early warning statistics and early warning handling suggestions, and monitoring data trend prediction results, and automatically fills them into the corresponding standardized report templates to generate complete structured reports.

[0054] According to a third aspect, one embodiment provides an electronic device, the device comprising: a processor and a memory;

[0055] The memory is used to store one or more program instructions;

[0056] The processor is configured to run one or more program instructions to perform the steps of an automated report generation method for engineering monitoring projects as described in any of the preceding claims.

[0057] According to a fourth aspect, one embodiment provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of an automated report generation method for engineering monitoring projects as described in any of the preceding claims.

[0058] This application provides a method and system for automatically generating reports for engineering monitoring projects, which has the following advantages:

[0059] 1. Significantly improve report generation efficiency: By establishing a standardized report template library and an automated data processing workflow, the time for generating monitoring reports has been reduced from the traditional 3-4 hours to just a few minutes, improving efficiency by over 90%. Monitoring personnel only need to import monitoring data, and the system can automatically complete all tasks such as data processing, chart creation, analysis and evaluation, and report output, greatly reducing their workload.

[0060] 2. Achieve in-depth data analysis: By adopting the analytic hierarchy process (AHP) and fuzzy comprehensive evaluation method, a multi-dimensional analysis model is established. This model comprehensively considers multiple factors such as monitored values, rate of change, cumulative change, proximity of warning thresholds, number of alarm points, and data dispersion, to deeply mine the monitoring data. This enables a more scientific and comprehensive assessment of the safety status of the project, making up for the shortcomings of traditional methods in terms of analysis depth.

[0061] 3. Construct an intelligent early warning mechanism: Establish a safety risk assessment method based on multi-factor coupling, which not only considers the relationship between monitored values ​​and thresholds, but also factors such as changing trends, scope of impact, and data stability, significantly improving the accuracy and timeliness of early warnings. The tiered early warning mechanism enables progressive warnings from normal to dangerous levels, providing sufficient time for construction management to respond.

[0062] 4. Eliminate human error: Automated data processing and report generation workflows avoid data entry errors, calculation mistakes, and non-standard chart drawing issues that may occur during manual operations, ensuring the accuracy and reliability of monitoring reports. Standardized report templates ensure consistent report format and complete content.

[0063] 5. Trend Prediction: Based on the LSTM deep learning model, future monitoring values ​​are predicted, transforming monitoring from post-event analysis to pre-event prediction, and from passive response to proactive prevention. Construction managers can be aware of potential risks in advance, adjust construction plans or take reinforcement measures in a timely manner, significantly improving the initiative in project safety management.

[0064] 6. Enhance the value of data utilization: Through in-depth analysis and trend prediction, fully explore the intrinsic value of monitoring data, transform the originally simple data records into valuable engineering safety information, and provide a scientific basis for construction decisions.

[0065] 7. Supports multiple output formats: Supports multiple output formats such as PDF, Word, and Excel to meet the needs of different scenarios. Supports custom report configuration and batch generation, further improving the system's flexibility and usability. Attached Figure Description

[0066] Figure 1 A flowchart illustrating an automated report generation method for engineering monitoring projects, as provided in one embodiment of the present invention;

[0067] Figure 2 A detailed flowchart of the classification of monitoring items and template establishment in an automated report generation method for engineering monitoring projects provided in an embodiment of the present invention;

[0068] Figure 3 A flowchart of a method for automatically generating reports for engineering monitoring projects, provided in one embodiment of the present invention, is shown for assessing the safety risk level.

[0069] Figure 4 An alarm statistics chart is provided in an automated report generation method for engineering monitoring projects according to an embodiment of the present invention.

[0070] Figure 5 This is a schematic diagram of the report cover page in an automated report generation method for engineering monitoring projects provided in one embodiment of the present invention;

[0071] Figure 6 This is a schematic diagram of a report summary page in an automated report generation method for engineering monitoring projects provided in one embodiment of the present invention;

[0072] Figure 7 This is a schematic diagram of the total station measurement items in an automated report generation method for engineering monitoring projects provided in one embodiment of the present invention;

[0073] Figure 8 This is a schematic diagram of the inclinometer measurement item in an automated report generation method for engineering monitoring projects provided in one embodiment of the present invention. Detailed Implementation

[0074] The present invention will now be described in further detail with reference to specific embodiments and accompanying drawings. Similar elements in different embodiments are referred to by associated similar element reference numerals. In the following embodiments, many details are described to facilitate a better understanding of this application. However, those skilled in the art will readily recognize that some features may be omitted in different situations, or may be replaced by other elements, materials, or methods. In some cases, certain operations related to this application are not shown or described in the specification. This is to avoid obscuring the core parts of this application with excessive description. For those skilled in the art, detailed description of these related operations is not necessary; they can fully understand the related operations based on the description in the specification and general technical knowledge in the art.

[0075] Furthermore, the features, operations, or characteristics described in the specification can be combined in any suitable manner to form various embodiments. At the same time, the steps or actions in the method description can be rearranged or adjusted in a manner obvious to those skilled in the art. Therefore, the various orders in the specification and drawings are only for the clear description of a particular embodiment and do not imply a necessary order, unless otherwise stated that a particular order must be followed.

[0076] The first embodiment of this invention provides a method for automatically generating reports for engineering monitoring projects. The following is a description of this method in conjunction with... Figure 1 Please provide a detailed explanation.

[0077] like Figure 1 As shown, in step S100, various monitoring items in the engineering monitoring project are classified, and a standardized report template library based on the type of measuring instrument is established. Based on the standardized report templates, the standardized collection, storage and retrieval of monitoring data for different items are realized.

[0078] In this embodiment, as Figure 2 As shown, a standardized report template library is established based on the type of measuring instrument to achieve standardized collection, storage, and retrieval of data for different measurement items. Specifically, the measuring instruments are classified according to their type. Common types of measuring instruments include: ① Inclinometer: used to measure deep horizontal displacement of walls or soil; ② Strain gauge: used to measure axial force of concrete supports, axial force of steel supports, etc.; ③ Water level gauge: used to monitor changes in groundwater level; ④ Total station: used in conjunction with a prism to measure changes in the horizontal displacement of structures; ⑤ Level: used for monitoring the vertical displacement of structures.

[0079] Define a unified data field structure for each instrument type, including measurement point number, measurement point location notes, measurement time, measured value, initial value, cumulative change, current change, and rate of change. Establish report display formats corresponding to each instrument type, including data table styles, chart types (time history curves, bar charts, contour maps, etc.), and analysis indicators (maximum value, minimum value, average value, standard deviation, etc.).

[0080] Taking the monitoring items including the horizontal displacement of the top of the diaphragm wall, the deep horizontal displacement, the axial force of the concrete support, the axial force of the steel support, the groundwater level, the surrounding surface settlement, and the vertical displacement of the top of the wall as an example; the horizontal displacement of the top of the diaphragm wall is monitored using a total station and a prism, the deep horizontal displacement is monitored using an inclinometer, the axial force of the concrete support is monitored using a steel bar gauge, the groundwater level is monitored using a water level gauge, and the surface settlement and the vertical displacement of the top of the wall are monitored using a level.

[0081] The report templates for corresponding monitoring items are divided into two parts: a header and a main body. The header mainly includes information such as the monitoring item name, project name, and instrument number. The main body mainly displays the monitoring data of the monitoring points. For monitoring items using a total station, a report template based on the total station is created. Its main body includes the monitoring point number, initial value, previous measurement, current measurement, current change, cumulative change, rate of change, rate alarm value, cumulative alarm value, warning level, remarks, and data analysis charts. For monitoring items using an inclinometer, a report template based on the inclinometer is created. Its main body includes depth information, previous cumulative value, current cumulative value, current change, rate of change, rate alarm value, cumulative alarm value, warning level, and data analysis charts. For monitoring items using a rebar gauge, a report template based on the rebar gauge is created. Its main body includes the monitoring point number, previous measurement, current measurement, and current measurement. The report template should include the following information: For items monitored using a water level gauge, a water level gauge-based report template should be created. The main content of this template includes the measuring point number, initial value, previous measurement, current measurement, current change, cumulative change, rate of change, rate alarm value, cumulative alarm value, warning level, remarks, and data analysis charts. For items monitored using a level instrument, a level instrument-based report template should be created. The main content of this template includes the measuring point number, initial value, previous measurement, current measurement, current change, cumulative change, rate of change, rate alarm value, cumulative alarm value, warning level, remarks, and data analysis charts.

[0082] like Figure 1 As shown, in step S200, based on the pre-established set of evaluation indicators and using a multi-dimensional analysis model established based on the analytic hierarchy process and fuzzy comprehensive evaluation method, an automated safety risk level assessment is performed on the actual monitoring data to obtain the safety risk level assessment result.

[0083] In this embodiment, a multi-dimensional analysis model based on actual monitoring data is constructed to address the spatiotemporal distribution characteristics of the monitoring data. This model comprehensively considers multiple influencing factors, including: ① the magnitude of the monitored value: reflecting the absolute amount of current deformation or stress; ② the rate of change: reflecting the speed of deformation or stress development; ③ the cumulative change: reflecting the total change since the start of construction; ④ the proximity of the warning threshold: reflecting the proximity of the current state to a dangerous state; ⑤ the number of alarm points: reflecting the size of the alarm range; and ⑥ the dispersion of the monitoring data: reflecting the stability and reliability of the data.

[0084] The Analytic Hierarchy Process (AHP) was used to determine the weights of each factor: ① A hierarchical model was constructed, decomposing the complex evaluation problem into target, criterion, and alternative layers; ② A judgment matrix was constructed, and pairwise comparisons of each indicator were performed using the 1-9 scaling method; ③ The weight vector was calculated. The eigenvalue method or geometric mean method is usually used; ④ Perform a consistency test and calculate the consistency ratio CR. When CR < 0.1, the judgment matrix is ​​considered to have satisfactory consistency; otherwise, the judgment matrix needs to be adjusted.

[0085] Data mining analysis using fuzzy comprehensive evaluation method: ① Establish evaluation level set ① The evaluation indicators correspond to four levels: safety, basic safety, early warning, and danger, respectively; ② Establish a single-factor evaluation matrix R and determine the membership degree of each evaluation indicator to each level; ③ Perform fuzzy synthesis operation to calculate the comprehensive evaluation vector B=W·R; ④ Determine the engineering safety risk level according to the principle of maximum membership degree.

[0086] Establishing a method for assessing and predicting engineering safety risk levels under multi-factor coupling conditions can more scientifically and objectively evaluate the safety status of engineering projects.

[0087] like Figure 3 As shown, the operation example is as follows:

[0088] (1) Determine the evaluation index set. Based on the characteristics of the engineering monitoring project, determine the evaluation index set. Where: ①u1: magnitude of the monitored value, ②u2: rate of change, ③u3: cumulative change, ④u4: proximity of the warning threshold, ⑤u5: number of alarm points, ⑥u6: dispersion of the monitored data.

[0089] (2) Constructing the judgment matrix and calculating the weights: Based on the monitoring standards, the 1-9 scaling method is used to compare each indicator pairwise to construct the judgment matrix A:

[0090]

[0091] The weight vector is calculated using the geometric mean method, and the geometric mean of the i-th index is:

[0092]

[0093] Normalization yields the weights:

[0094]

[0095] The weight vector W = {0.26, 0.16, 0.10, 0.26, 0.16, 0.10} is calculated. A consistency test is performed, the maximum eigenvalue λmax = 6.05 is calculated, the consistency index CI = (λmax - n) / (n - 1) = 0.01 is calculated, the random consistency index RI = 1.24 is obtained from the table, and the consistency ratio CR = CI / RI = 0.008 < 0.1 is calculated. The consistency test is passed, and the weight vector is valid.

[0096] (3) Establish an evaluation level set. These correspond to: v1: Safe (green), v2: Basically Safe (yellow), v3: Warning (orange), v4: Danger (red).

[0097] (4) Establish a single-factor evaluation matrix. Based on monitoring standards and engineering experience, establish the membership functions of each indicator to each level, forming a single-factor evaluation matrix R. Taking the monitoring value u1 as an example, let its membership function be:

[0098]

[0099] Assume that the evaluation values ​​of each indicator during a certain monitoring period are: u1 = 0.75 (monitored value has reached 75% of the warning threshold), u2 = 1.5 (rate of change is 1.5 times the historical average), u3 = 30 mm (cumulative change of 30 mm), u4 = 0.75 (close to the warning threshold of 75%), u5 = 0.15 (15% of monitoring points are at warning level), and u6 = 0.08 (coefficient of variation 0.08, data is relatively stable). Based on the membership function calculation, the single-factor evaluation matrix R is obtained:

[0100]

[0101] (5) Fuzzy comprehensive evaluation

[0102]

[0103] B = [0.26, 0.16, 0.10, 0.26, 0.16, 0.10] × R = [0.48, 0.43, 0.09, 0]

[0104] Based on the principle of maximum membership, the safety level for this monitoring period is rated as "safe." However, it should be noted that the membership degree for "basically safe" is also relatively high (0.43), requiring continued close monitoring. If a weighted average method is used to calculate the overall score:

[0105]

[0106] Therefore, the score is between 1 and 2, corresponding to the "safe" to "basically safe" range, which is consistent with the result of the maximum membership degree method.

[0107] like Figure 1 As shown, in step S300, the safety risk assessment level results are automatically extracted, early warning statistics and early warning handling suggestions are generated, and trend prediction is performed on the monitoring data.

[0108] In this embodiment, key information such as the safety risk assessment results, trend prediction information, and early warning suggestions obtained through intelligent analysis are automatically extracted and formatted. The system automatically identifies alarm-exceeding detection points, counts the number and distribution of alarm points, analyzes the changing trends, and proposes targeted handling suggestions. Specifically:

[0109] ① Risk assessment results: mainly monitoring the overall safety level of the project (safe, basic safe, early warning, dangerous), measuring the project's risk score, the weight of each factor, and score details;

[0110] ② Trend prediction information: For each monitoring item, based on the historical monitoring data of the previous 20 periods, the monitoring value of the next 3 periods is predicted using an LSTM model. The prediction process using the LSTM model is shown in the following formula;

[0111] First, the monitoring data is normalized and scaled to the [0,1] interval:

[0112]

[0113] in For the normalized data, This is the raw monitoring data. and These represent the minimum and maximum values ​​of the data, respectively. Then, a sliding window method is used to construct training samples. Let the time window length be... (Usually 10-20 issues are taken), then the first The training samples are:

[0114]

[0115]

[0116] in, Given an input sequence containing consecutive... The monitoring value at each moment, The target output is the monitored value at the next time step. Then, the mean squared error (MSE) is used as the loss function for model training.

[0117]

[0118] in: The number of training samples. For the true value, These are the predicted values. The parameters are then updated using the Adam optimizer.

[0119]

[0120]

[0121]

[0122]

[0123] in, For a moment gradient, and First-order and second-order moment estimates, respectively. and This is the exponential decay rate, typically taken as 0.9 or 0.999. The learning rate is typically set to 0.001. To minimize division by zero errors, it is usually taken as a very small constant. , These are the model parameters.

[0124] Predicting the future The monitoring values ​​at each moment (in this invention) or ): Recursive prediction strategy adopted: Step 1: Prediction Step 2: Add the input sequence and predict. ; and so on, until the prediction is made. .

[0125] ③ Alarm statistics, the statistical format is as follows: Figure 4 As shown.

[0126] ④ Based on the monitoring results, identify the monitoring points that require special attention and make recommendations for subsequent monitoring work.

[0127] like Figure 1 As shown, in step S400, the collected actual monitoring data, safety risk level assessment results, early warning statistics and early warning handling suggestions, and monitoring data trend prediction results are integrated and automatically filled into the corresponding standardized report templates to generate a complete structured report.

[0128] Specifically, based on the report template library established in step S100, the security risk information and monitoring data from step S300 are automatically integrated to generate a complete structured monitoring report. The report includes the following:

[0129] ①Cover page: Project name, report number, report period, preparation date, preparing unit, reviewer, approver, etc.

[0130] ② Project Overview: Project location, project scale, foundation pit depth, surrounding environment, geological conditions, hydrological conditions, etc.

[0131] ③ Monitoring Plan Overview: Monitoring objectives, monitoring basis, monitoring items, monitoring point layout, monitoring methods, monitoring frequency, early warning standards, etc.

[0132] ④ Data summary information: Statistical tables of monitoring data for each measurement item, summary of alarm situations, overview of change trends, key points of concern in this period, etc.

[0133] ⑤ Detailed information for each measurement item: Ⅰ Measurement point layout diagram: clearly marking the location and number of measurement points; Ⅱ Monitoring data table: including measurement point number, measurement time, measured value, cumulative change, current change, rate of change, etc.; Ⅲ Time series curve graph: showing the change pattern of monitoring values ​​over time; Ⅳ Cumulative change bar chart: comparing the cumulative change of each measurement point; Ⅴ Rate of change curve: showing the change of the rate of change over time; Ⅵ Abnormal data annotation: highlighting data exceeding the warning level or abnormal data.

[0134] ⑥ Comprehensive safety assessment: Based on the safety level assessment results of fuzzy comprehensive evaluation, the weight and score of each influencing factor, and the comprehensive evaluation conclusion.

[0135] ⑦ Risk warning prompts: list of alarm monitoring points, risk area identification, warning level (blue, yellow, orange, red), and risk description.

[0136] ⑧ Recommendations for handling the situation: Suggestions for engineering measures to address the early warning situation, such as increasing the monitoring frequency, adding monitoring points, adjusting the construction plan, and taking reinforcement measures.

[0137] The detailed information for each monitoring item includes data curves, comparative analysis, and anomaly annotations, which can intuitively and clearly reflect the changing patterns and safety status of the monitoring data.

[0138] The report generation module supports three output formats: PDF, Word, and Excel. PDF is suitable for printing and archiving and is not easily modified; Word is easy to edit and supplement; and Excel facilitates further data processing and analysis. It also supports custom report configurations, allowing users to select the report content, chart types, page layout, and more as needed. Furthermore, it supports batch generation, enabling the generation of reports for multiple monitoring periods at once, significantly improving work efficiency.

[0139] In this embodiment, the system automatically generates a complete monitoring report based on the report template library, such as... Figure 5-8The image shows the report templates used in the report generation process, including the cover page, summary page, total station measurement items, and inclinometer measurement items. During program execution, data will be filled into the corresponding positions in the report. During rendering, the system automatically inserts page breaks between each page and automatically switches the page orientation based on the template attributes. This allows the report to achieve alternating horizontal and vertical layouts within a single file, satisfying both the requirements for displaying the point map and ensuring the readability of the monitoring data tables.

[0140] This invention discloses an automated method for generating monitoring reports for engineering monitoring projects. It employs a standardized template library based on measuring instrument types and a multi-dimensional intelligent analysis framework to achieve unified management and automated report output for various types of monitoring data. By establishing an instrument type template library, it achieves standardized management of monitoring data from total stations, inclinometers, strain gauges, water level gauges, and levels. A multi-dimensional analysis model is constructed using the analytic hierarchy process (AHP) and fuzzy comprehensive evaluation, comprehensively considering factors such as monitored values, rate of change, cumulative change, proximity of warning thresholds, number of alarm points, and data dispersion, to achieve scientific assessment and intelligent early warning of engineering safety risks. An LSTM deep learning model is used for trend prediction, realizing a shift from passive response to proactive prevention. An automated report engine quickly generates structured reports containing complete content such as a cover page, project overview, data summary, measurement details, safety evaluation, risk warning, and disposal suggestions, supporting multiple output formats including PDF, Word, and Excel. It supports various monitoring types such as diaphragm wall displacement, deep displacement, support axial force, groundwater level, surface settlement, and building settlement, and features automatic data processing, intelligent risk assessment, trend prediction, template configuration, and batch generation functions. Through standardized, intelligent, and automated design, this invention reduces report generation time from 3-4 hours to just a few minutes, improving efficiency by over 90%. It eliminates data entry errors and calculation mistakes caused by manual operation, significantly enhancing monitoring data processing efficiency and risk warning accuracy. This invention is applicable to various engineering monitoring fields, including foundation pits, tunnels, slopes, bridges, and subways, providing an efficient and reliable digital solution for engineering safety monitoring, and possesses significant application value and promising prospects for wider adoption.

[0141] Corresponding to the above-disclosed method for automatically generating reports for engineering monitoring projects, this invention also discloses an automated report generation system for engineering monitoring projects, which specifically includes:

[0142] The report template creation module is used to classify various monitoring items in engineering monitoring projects and establish a standardized report template library based on the type of measuring instrument. Based on the standardized report templates, the standardized collection, storage and retrieval of monitoring data for different items can be realized.

[0143] The safety risk assessment module is used to automatically assess the safety risk level of actual monitoring data based on a pre-established set of evaluation indicators and a multi-dimensional analysis model based on the analytic hierarchy process and fuzzy comprehensive evaluation method, and obtain the safety risk level assessment results.

[0144] The security risk information integration module is used to automatically extract security risk assessment results, generate early warning statistics and early warning handling suggestions, and perform trend prediction on monitoring data;

[0145] The automatic report generation module integrates the collected actual monitoring data, safety risk level assessment results, early warning statistics and early warning handling suggestions, and monitoring data trend prediction results, and automatically fills them into the corresponding standardized report templates to generate complete structured reports.

[0146] It should be noted that for a detailed description of the automated report generation system for engineering monitoring projects provided in the embodiments of the present invention, please refer to the relevant description of the automated report generation method for engineering monitoring projects provided in the embodiments of this application, which will not be repeated here.

[0147] In addition, embodiments of the present invention also provide an electronic device, the device comprising: a processor and a memory; the memory being used to store one or more program instructions; the processor being used to execute one or more program instructions to perform the steps of an automated report generation method for engineering monitoring projects as described in any of the preceding embodiments.

[0148] It should be noted that for a detailed description of the electronic device provided in the embodiments of the present invention, please refer to the relevant description of the automated report generation method for engineering monitoring projects provided in the embodiments of this application, which will not be repeated here.

[0149] In addition, embodiments of the present invention also provide a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the automated report generation method for engineering monitoring projects as described in any of the preceding embodiments.

[0150] It should be noted that for a detailed description of the computer-readable storage medium provided in the embodiments of the present invention, please refer to the relevant description of the automated report generation method for engineering monitoring projects provided in the embodiments of this application, which will not be repeated here.

[0151] Those skilled in the art will understand that all or part of the functions of the various methods in the above embodiments can be implemented by hardware or by computer programs. When all or part of the functions in the above embodiments are implemented by computer programs, the program can be stored in a computer-readable storage medium, which may include: read-only memory, random access memory, disk, optical disk, hard disk, etc., and the program is executed by a computer to achieve the above functions. For example, the program can be stored in the memory of a device, and when the program in the memory is executed by the processor, all or part of the above functions can be achieved. In addition, when all or part of the functions in the above embodiments are implemented by computer programs, the program can also be stored in a server, another computer, disk, optical disk, flash drive, or external hard drive, etc., and can be downloaded or copied to the memory of a local device, or the system of the local device can be updated. When the program in the memory is executed by the processor, all or part of the functions in the above embodiments can be achieved.

[0152] The above examples illustrate the present invention only to aid in understanding it and are not intended to limit the scope of the invention. Those skilled in the art can make various simple deductions, modifications, or substitutions based on the principles of this invention.

Claims

1. A method for automatically generating reports for engineering monitoring projects, characterized in that, The method includes: The various monitoring items in engineering monitoring projects are classified, and a standardized report template library based on the type of measuring instrument is established. Based on the standardized report templates, the standardized collection, storage and retrieval of monitoring data for different items are realized. Based on a pre-established set of evaluation indicators, and using a multi-dimensional analysis model based on the analytic hierarchy process and fuzzy comprehensive evaluation method, an automated safety risk level assessment is performed on the actual monitoring data to obtain the safety risk level assessment results. Automatically extract safety risk assessment results, generate early warning statistics and early warning handling suggestions, and perform trend prediction on monitoring data; The system integrates the collected actual monitoring data, safety risk level assessment results, early warning statistics and early warning handling suggestions, and monitoring data trend prediction results, and automatically fills them into the corresponding standardized report templates to generate complete structured reports.

2. The method for automatically generating reports for engineering monitoring projects as described in claim 1, characterized in that, The various monitoring items in engineering monitoring projects are categorized, specifically including: The monitoring items include displacement monitoring, stress-strain monitoring, water level monitoring, and settlement monitoring.

3. The method for automatically generating reports for engineering monitoring projects as described in claim 1, characterized in that, Establish a standardized report template library based on the type of measuring instrument, specifically including: The measuring instruments are classified according to their type, which includes inclinometers, strain gauges, water level gauges, total stations, and levels. Define a data field structure for each instrument type and create standardized report templates for different measuring instrument types. The standardized report templates include a header and a body, where the header contains basic information about the measurement items and the body contains monitoring data of the monitoring points and related data processing results. Establish report display formats corresponding to each instrument type, including data table styles, chart types, and analysis indicators.

4. The method for automatically generating reports for engineering monitoring projects as described in claim 1, characterized in that, Based on a pre-established set of evaluation indicators and using a multi-dimensional analysis model based on the analytic hierarchy process (AHP) and fuzzy comprehensive evaluation method, an automated safety risk level assessment is performed on the actual monitoring data to obtain the safety risk level assessment results, which specifically include: Determine the set of evaluation indicators , n≥6, where u1 is the size of the monitored value, u2 is the rate of change, u3 is the cumulative change, u4 is the proximity of the warning threshold, u5 is the number of alarm points, and u6 is the dispersion of the monitored data; Construct a judgment matrix, and use the 1-9 scaling method to compare each evaluation index pairwise, thereby calculating the weight vector set of each evaluation index. ; Perform a consistency test and calculate the consistency ratio CR. When CR < 0.1, the judgment matrix is ​​considered to have satisfactory consistency. Establish evaluation level set These correspond to four levels: safe, basically safe, warning, and dangerous. Establish a single-factor evaluation matrix R and determine the membership degree of each evaluation indicator to each evaluation level; Perform fuzzy synthesis operation to calculate the comprehensive evaluation vector B=W·R, where W is the weight vector and R is the single-factor evaluation matrix; The safety risk level of the project is determined based on the principle of maximum membership.

5. The method for automatically generating reports for engineering monitoring projects as described in claim 1, characterized in that, Trend prediction of monitoring data includes: Establish a time series model based on historical monitoring data; The LSTM model is used to predict future monitoring values; By comparing the forecast results with the early warning threshold, potential risks can be identified in advance; The trend prediction results are integrated into the monitoring reports in the form of curves.

6. The method for automatically generating reports for engineering monitoring projects as described in claim 1, characterized in that, The system integrates the collected actual monitoring data, safety risk level assessment results, early warning statistics and early warning handling suggestions, and monitoring data trend prediction results, and automatically fills them into the corresponding standardized report templates to generate complete structured reports, specifically including: The final complete report includes a project cover, project overview, monitoring plan introduction, data summary information, detailed information for each monitoring item, comprehensive safety assessment, risk warning and handling suggestions. The detailed information for each monitoring item includes data curves, comparative analysis, and anomaly annotations.

7. The method for automatically generating reports for engineering monitoring projects as described in claim 6, characterized in that, The complete report includes the following items: The cover page includes the project name, report number, report period, preparation date, and preparing organization; Project overview, including project location, project scale, surrounding environment, and geological conditions; A brief overview of the monitoring plan, including monitoring objectives, monitoring items, monitoring point layout, and monitoring frequency; Data summary information includes statistical tables of monitoring data for each measurement item, a summary of alarm situations, and an overview of changing trends; Detailed information for each measurement item, including a specific plan of measurement point layout, monitoring data tables, time history curves, cumulative change bar charts, rate of change curves, and annotations of abnormal data; Comprehensive safety assessment, including safety risk level assessment results and analysis of various assessment indicators; Risk warning prompts include a list of alarm monitoring points, risk area identification, and warning level; Recommendations for handling situations, including recommendations for engineering measures to address the warning situation.

8. The method for automatically generating reports for engineering monitoring projects as described in claim 6, characterized in that, The method further includes: It supports multiple report output formats, including PDF, Word, and Excel, and also supports custom report configuration and batch generation.

9. An automated report generation system for engineering monitoring projects, characterized in that, The system includes: The report template creation module is used to classify various monitoring items in engineering monitoring projects and establish a standardized report template library based on the type of measuring instrument. Based on the standardized report templates, the standardized collection, storage and retrieval of monitoring data for different items can be realized. The safety risk assessment module is used to automatically assess the safety risk level of actual monitoring data based on a pre-established set of evaluation indicators and a multi-dimensional analysis model based on the analytic hierarchy process and fuzzy comprehensive evaluation method, and obtain the safety risk level assessment results. The security risk information integration module is used to automatically extract security risk assessment results, generate early warning statistics and early warning handling suggestions, and perform trend prediction on monitoring data; The automatic report generation module integrates the collected actual monitoring data, safety risk level assessment results, early warning statistics and early warning handling suggestions, and monitoring data trend prediction results, and automatically fills them into the corresponding standardized report templates to generate complete structured reports.

10. An electronic device, characterized in that, The device includes: a processor and a memory; The memory is used to store one or more program instructions; The processor is configured to run one or more program instructions to perform the steps of the automated report generation method for engineering monitoring projects as described in any one of claims 1 to 8.

Images