An intelligent inspection management method and system

Abstract

The present invention relates to the field of data processing, and specifically to a smart inspection management method and system. When an inspection user conducts an inspection, the pre-constructed reference information is provided to the inspection personnel for reference, so that the inspection personnel can understand the reference range and inspection time of each inspection point of each inspection item. This helps the inspection personnel who are not familiar with the project quickly understand the inspection project. In addition, the present application determines the priority of each inspection point by using the environmental parameters collected in real time by the sensors set on the construction site project and the real-time positioning of the inspection personnel. When the inspection personnel are performing the inspection task, the priority and reference information are used to guide and supervise the inspection personnel. The present application can effectively guide and supervise the inspection process of the inspection personnel, and help the inspection personnel improve the inspection efficiency and inspection quality.

Description

Technical Field

[0001] The present invention relates to the field of data processing, and specifically to a smart inspection management method and system. Background Art

[0002] The inspection of construction sites is an important part of construction project management. Through regular inspections, problems that occur during the construction process can be discovered in a timely manner, such as improper use of materials, substandard workmanship, etc., so as to take measures to correct them and ensure that the project is carried out in accordance with the design requirements and relevant standards. The inspection can check the safety conditions of the construction site, including but not limited to whether the safety facilities are in place and whether the workers comply with the safety operation procedures. This helps to prevent the occurrence of safety accidents and protect the lives and physical health of the workers, etc.

[0003] The existing construction site inspection technology basically still relies on manual management. The inspection personnel sign in and then conduct the inspection, and record the problems in the inspection record after the inspection is completed. However, this management method depends on the experience and subjectivity of the inspection personnel, and the existing technology cannot effectively guide and supervise the inspection process of the inspection personnel. Summary of the Invention

[0004] In view of this, the purpose of the present invention is to provide a smart inspection management method and system to solve the problems in the background art.

[0005] To achieve the above purpose, the present invention adopts the following technical solutions:

[0006] A smart inspection management method of the present invention includes the steps of:

[0007] When receiving an inspection request from an inspection personnel, obtaining reference information of the inspection items corresponding to the inspection request, wherein the reference information includes multiple inspection points, reference ranges of the multiple inspection points, and reference inspection duration ranges of the multiple inspection points, and the reference information is generated based on historical inspection information;

[0008] Sending the reference information to the inspection personnel, and obtaining the real-time inspection information of the inspection personnel and environmental data collected by sensors at multiple points of the construction site, wherein the real-time inspection information includes real-time positioning;

[0009] Determining the inspection priority of each inspection point based on the real-time inspection information of the inspection personnel and the environmental data collected by sensors at multiple points of the construction site;

[0010] Conducting inspection guidance management for the inspection personnel based on the inspection priority of each inspection point and the reference ranges of the multiple inspection points, and conducting inspection supervision management for the inspection personnel based on the reference ranges of the multiple inspection points and the reference inspection duration ranges of the multiple inspection points.

[0011] In one embodiment of the present application, the method for generating reference information of the inspection items includes:

[0012] Obtain historical inspection data generated during multiple inspections of the inspection items in the first target time period, where the historical inspection data includes historical inspection positions at multiple time points , where represents a time point, and the target time period is a time period of a target duration before the current time point;

[0013] Calculate the distance between the historical inspection positions of any two adjacent time points in the historical inspection data ;

[0014] Based on the distances between multiple adjacent time points Construct a time-series displacement sequence;

[0015] Perform sliding filtering on the time-series displacement sequence to obtain a time-series displacement filtering sequence;

[0016] And slide along the time direction of the time-series displacement filtering sequence based on a pre-constructed sliding window, and calculate the average distance of the time-series displacement filtering sequence within the sliding window each time of sliding ;

[0017] Take the section corresponding to the sliding window with an average distance less than the preset distance threshold as the target section, merge adjacent target sections, and extract the slow-down duration and multiple historical inspection positions ;

[0018] Calculate the average position of multiple historical inspection positions of the merged target section, take the average position of each merged target section as a candidate inspection point, and construct inspection point reference data for each historical inspection data based on the candidate inspection points and slow-down duration of each merged target section ;

[0019] Based on the inspection point reference data of the multiple historical inspection data Construct the reference information of the inspection items.

[0020] In one embodiment of the present application, based on the inspection point reference data of the multiple historical inspection data Constructing the reference information of the inspection items includes:

[0021] Based on the coordinates of the candidate inspection points, for the inspection point reference data of the multiple historical inspection data Perform density clustering to obtain multiple clusters;

[0022] Take the clusters with the amount of data within the cluster greater than a preset threshold as intermediate clusters, calculate the average coordinates of all candidate inspection points within the intermediate clusters, and based on the average coordinates, screen out the deviation points within the intermediate clusters to obtain target clusters;

[0023] Calculate the average coordinates of all candidate inspection points within the target clusters to obtain the inspection point reference coordinates representing the inspection points ; Based on the inspection point reference coordinates Calculate the variance of the abscissas of all candidate inspection points within the target clusters and the variance of the ordinates and the covariance of the abscissas and ordinates ;

[0024] Based on the variance of the abscissas and the variance of the ordinates and the covariance of the abscissas and ordinates Construct the covariance matrix of the target clusters The covariance matrix has the following mathematical expression:

[0025]

[0026] Construct the calculation formula of the covariance matrix The calculation formula is to obtain the first eigenvalue and the second eigenvalue where represents the eigenvalue, is the identity matrix;

[0027] Based on the first eigenvalue and the second eigenvalue respectively construct the major axis and the minor axis where , , is the range adjustment parameter;

[0028] Based on the major axis and the minor axis Construct a range ellipse and use the range ellipse as the reference range of the inspection points;

[0029] Calculate the average duration and the standard deviation of the duration within the target clusters, and based on the average duration and the standard deviation of the duration, construct the reference inspection duration range.

[0030] In an embodiment of the present application, determining the inspection priority of each inspection point based on the real-time inspection information of the inspection personnel and the environmental data collected by sensors at multiple points on the construction site includes:

[0031] Obtain the current location of the inspection personnel , and the values of the environmental parameters of multiple sensors in the target time period;

[0032] Calculate the distance between each inspection point and the current location , and determine the abnormal risk value of each monitoring point based on the values of the environmental parameters of multiple sensors in the target time period , where the abnormal risk value is determined by the value-taking risk, the fluctuation risk, and the trend risk, is the serial number of the inspection point, is the serial number of the monitoring point;

[0033] Take the abnormal risk value of the monitoring point as the abnormal risk value of the inspection point within the coverage range of the corresponding sensor , and based on the distance between each inspection point and the current location , the abnormal risk value of the inspection point calculate the priority score of each inspection point , where the mathematical expression of the priority score is:

[0034]

[0035] In the formula, is the first weight, is the second weight, is the normalization function;

[0036] Based on the priority scores of multiple inspection points determine the priorities of multiple inspection points.

[0037] In an embodiment of the present application, determining the abnormal risk value of each monitoring point based on the values of the environmental parameters of multiple sensors in the target time period includes:

[0038] Compare the values of the environmental parameters at multiple time points in the second target time period with a preset reference range to obtain a value-taking risk value , where when the value of the environmental parameter at any time point in the target time period does not fall within the preset reference range, , otherwise, ;

[0039] Moving average is performed on the values of the environmental parameters at multiple time points in the second target time period based on a pre-constructed sliding window to obtain the average values of the environmental parameters in multiple sections extracted by the sliding window , and when the average values of the environmental parameters in any two adjacent sections satisfy , or , it is determined that there is a one-way change trend in the values of the environmental parameters at multiple time points in the target time period; when there is an upward trend in the values of the environmental parameters at multiple time points in the target time period, the value of the environmental parameter at the current time point is compared with the set upward warning line, and when the value of the environmental parameter at the current time point is greater than the upward warning line, the trend risk value , otherwise ; when there is a downward trend in the values of the environmental parameters at multiple time points in the target time period, the value of the environmental parameter at the current time point is compared with the set downward warning line, and when the value of the environmental parameter at the current time point is less than the upward warning line, the trend risk value , otherwise ;

[0040] When there is no one-way change trend in the values of the environmental parameters at multiple time points in the target time period, calculate the variance of the values of the environmental parameters at multiple time points in the target time period, and compare the variance with a preset variance range to obtain a fluctuation risk value , where when the variance does not fall within the preset variance range , otherwise ;

[0041] Based on the value risk value and the trend risk value construct an abnormal risk value , ; or; based on the value risk value and the fluctuation risk value construct an abnormal risk value , , where is the third weight is the fourth weight is the fifth weight

[0042] In an embodiment of the present application, based on the inspection priority of each inspection point, inspection guidance management is performed on the inspection personnel, including:

[0043] Obtain the current location of the inspection personnel;

[0044] When the duration that the current location of the inspection personnel is within the reference range of one of the inspection points exceeds the target duration, it is determined that the inspection personnel are performing inspections at the current inspection point, and the inspection priorities of all inspection points are updated at the current location of the inspection personnel, and the next inspection point with the highest inspection priority is sent to the inspection personnel to complete the guidance management.

[0045] In an embodiment of the present application, the inspection and supervision management of the inspection personnel is carried out based on the reference ranges of multiple inspection points and the reference inspection duration ranges of multiple inspection points, including:

[0046] Statistically calculate the inspection duration and inspection path of the inspection personnel within the reference range of each inspection point, where the inspection path is composed of multiple positions of the inspection personnel within the reference range;

[0047] Compare the inspection duration with the reference inspection duration range, and when the inspection duration is less than the lower limit value of the reference inspection duration range, give a prompt to the inspection personnel;

[0048] Statistically calculate the number of grids passed by the inspection path within the reference range, calculate the passing grid ratio based on the number of passed grids and the total number of grids within the reference range, compare the passing grid ratio with a preset ratio threshold, and when the passing grid ratio is less than the preset ratio threshold, give a prompt to the inspection personnel, where the reference range is evenly divided in advance to obtain multiple grids within the reference range.

[0049] In an embodiment of the present application, it further includes:

[0050] When giving a prompt to the inspection personnel, mark the inspection point, and remove the mark until the inspection duration is greater than or equal to the lower limit value of the reference inspection duration range, or the passing grid ratio is greater than or equal to the preset ratio threshold.

[0051] In an embodiment of the present application, the historical inspection data is data located within the defined range of the inspection project, where the address and defined range of the inspection project are established in advance.

[0052] The present application also provides an intelligent inspection management system, including:

[0053] An acquisition module, configured to acquire reference information of an inspection item corresponding to the inspection request when receiving an inspection request from an inspector, where the reference information includes a plurality of inspection points, reference ranges of the plurality of inspection points, and reference inspection duration ranges of the plurality of inspection points, and the reference information is generated based on historical inspection information;

[0054] A detection module, configured to send the reference information to the inspector, and acquire real-time inspection information of the inspector and environmental data collected by sensors at multiple points on the construction site, where the real-time inspection information includes real-time positioning;

[0055] A priority determination module, configured to determine the inspection priority of each inspection point based on the real-time inspection information of the inspector and the environmental data collected by sensors at multiple points on the construction site;

[0056] A management module, configured to manage the inspection guidance for the inspector based on the inspection priority of each inspection point and the reference ranges of the plurality of inspection points, and manage the inspection supervision for the inspector based on the reference ranges of the plurality of inspection points and the reference inspection duration ranges of the plurality of inspection points.

[0057] The beneficial effects of the present invention are as follows: For a smart inspection management method and system of the present invention, when an inspection user conducts an inspection, the pre-constructed reference information is used to provide reference for the inspector, so that the inspector can understand the reference ranges and inspection times of each inspection point of each inspection item. This helps inspectors who are not familiar with the project quickly understand the inspection items. In addition, the present application determines the priority of each inspection point by using the environmental parameters collected in real time by sensors set on the construction site project and the real-time positioning of the inspector. When the inspector is performing an inspection task, the priority and reference information are used to guide and supervise the inspector. The present application can effectively guide and supervise the inspection process of the inspector, and help the inspector improve the inspection efficiency and quality. Description of the Drawings

[0058] The present invention will be further described below in conjunction with the drawings and embodiments:

[0059] Figure 1 is an application scenario diagram of a smart inspection management method shown in an embodiment of the present application;

[0060] Figure 2 is a flowchart of a smart inspection management method shown in an embodiment of the present application;

[0061] Figure 3 is a schematic diagram of project information upload in an embodiment of the present application;

[0062] Figure 4Schematic diagram of the priorities of multiple inspection points in an embodiment of the present application;

[0063] Figure 5 Schematic diagram of the grid and inspection path within the reference range in an embodiment of the present application;

[0064] Figure 6 Structural diagram of an intelligent inspection management system shown in an embodiment of the present application. Detailed implementation manners

[0065] The following uses specific specific examples to illustrate the implementation manners of the present invention. Those skilled in the art can easily understand other advantages and effects of the present invention from the content disclosed in this specification. The present invention can also be implemented or applied through different specific implementation manners. Various details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of the present invention. It should be noted that, without conflict, the following embodiments and the features in the embodiments can be combined with each other.

[0066] It should be noted that the diagrams provided in the following embodiments only illustrate the basic concept of the present invention in a schematic manner. Therefore, only the layers related to the present invention are shown in the diagrams, rather than being drawn according to the number, shape, and size of the layers in actual implementation. The type, quantity, and ratio of each layer in actual implementation can be arbitrarily changed, and the layer layout type may also be more complex.

[0067] In the following description, a large number of details are explored to provide a more thorough explanation of the embodiments of the present invention. However, it is obvious to those skilled in the art that the embodiments of the present invention can be implemented without these specific details.

[0068] All relevant information involved in the present application has been obtained with full consent and authorization, and the collection, use, and processing of relevant information need to comply with relevant laws, regulations, and standards of relevant countries and regions.

[0069] Figure 1 It is an application scenario diagram of an intelligent inspection management method shown in an embodiment of the present application. As Figure 1 shown, the intelligent inspection management method in the present application is based on the server 110 and the handheld intelligent terminal 120. The handheld intelligent terminal 120 is carried by the inspection personnel and is used to provide guidance and reference information for the inspection personnel, and at the same time collect the real-time location of the inspection personnel. The handheld intelligent terminal 120 sends the real-time location to the server 110, and the server 110 determines the priorities of the inspection points, provides dynamic guidance, and conducts inspection supervision based on the real-time location and the environmental data uploaded by the sensors.

[0070] Figure 2It is a flowchart of an intelligent patrol management method shown in an embodiment of the present application. As Figure 2 shown, an intelligent patrol management method in this embodiment may include the steps:

[0071] S210, when receiving a patrol request from a patrol personnel, obtain reference information of the patrol items corresponding to the patrol request, where the reference information includes multiple patrol points, reference ranges of the multiple patrol points, and reference patrol duration ranges of the multiple patrol points, and the reference information is generated based on historical patrol information;

[0072] In the present application, when a patrol personnel is performing a patrol task, the patrol request is uploaded to the server through a handheld intelligent terminal, and the server automatically responds, so as to return the positioning and range corresponding to the patrol items in the patrol task to the patrol personnel.

[0073] In the present application, since there are patrol personnel who are not familiar with the project, and as the construction progress of the project advances, the patrol points will also change, so a fixed patrol point map cannot be provided. Therefore, the present application constructs reference information through historical patrol data to help patrol personnel understand the points to be patrolled, the reference ranges of the points, and the reference patrol duration of each patrol point.

[0074] The construction process of the reference information is as follows:

[0075] (1) Obtain historical patrol data generated when the patrol project is patrolled multiple times in a first target time period, where the historical patrol data includes historical patrol positions at multiple time points , where represents a time point, and the target time period is a time period of a target duration before the current time point;

[0076] Considering that as the construction progress of the construction site project advances, the patrol points will change. For example: in the basic construction stage, the patrol may focus on foundation treatment and underground facilities; while in the structural construction stage, more attention is paid to the quality inspection of processes such as concrete pouring and steel bar binding. As the building or infrastructure gradually takes shape, potential safety hazards will also change accordingly. In the initial stage, the risks of earth excavation and slope stability may be relatively large, and in the later stage, the risks in aspects such as high-altitude operations and hoisting operations may increase.

[0077] Therefore, when constructing the reference information, take the historical patrol data of the target duration before the current time period to adapt to the changing patrol points. The target duration is not fixed. For example, in the rapid construction period, the changes in the project will be relatively large, so take a shorter duration, such as 15 days, while in the construction stage where there is no rapid change, take a longer duration, such as 2 months.

[0078] Historical inspection data can be sampled from the inspection data of some experienced inspectors. In addition, the historical inspection data is inspection data located within the defined scope of the inspection items, where the addresses and defined scopes of the inspection items are established in advance. The addresses and defined scopes of the inspection items are uploaded to the server in advance. Figure 3 It is a schematic diagram of project information upload in an embodiment of the present application. The process of information upload is as Figure 3 shown.

[0079] (2) Calculate the distance between the historical inspection positions at any two adjacent time points in the historical inspection data ;

[0080] For the historical inspection data generated by each inspection task, the present application needs to extract the intervals where the inspector stays or moves slowly, and use the positions in this interval as the candidate inspection point positions. Therefore, the present application first calculates the distance between the historical inspection positions between adjacent time points to find the intervals where the inspector stays or moves slowly.

[0081] (3) Construct a time series displacement sequence based on the distances between multiple adjacent time points ;

[0082] (4) Perform sliding filtering on the time series displacement sequence to obtain a time series displacement filtered sequence;

[0083] Since the positioning information itself is prone to fluctuations, the present application performs sliding filtering on the time series displacement sequence to remove the mutation points therein and obtain a smoother time series displacement filtered sequence curve.

[0084] (5) And slide along the time direction of the time series displacement filtered sequence based on a pre-constructed sliding window, and calculate the distance mean value of the time series displacement filtered sequence within the sliding window each time it slides ;

[0085] In this embodiment, a sliding window is used to calculate the displacement average values of multiple sections of the time series displacement filtered sequence. The displacement average value within the window reflects the displacement level of the inspector within the corresponding time section.

[0086] (6) Take the section corresponding to the sliding window with a distance mean value less than the preset distance threshold as the target section, merge adjacent target sections, and extract the slow travel duration and multiple historical inspection positions;

[0087] For the distance mean value calculated by the sliding window, if they are adjacent sliding windows, it means they are within the same time interval, so they are merged.

[0088] (7) Calculate the average position of multiple historical inspection positions of the merged target section of the merged target section, and use the average position of each merged target section as a candidate inspection point, and construct inspection point reference data for each historical inspection data based on the candidate inspection points of each merged target section and the slow travel duration ; For each merged target section, all the positioning points within the target section are screened out through the historical inspection data in the previous text, and the average value is calculated to obtain candidate inspection points. Since there are various reasons for the inspector to slow down or stay during the inspection, the candidate inspection points cannot be directly used as inspection points and further screening is required, as follows: ;

[0089] For each merged target section, all the positioning points within the target section are screened out through the historical inspection data in the previous text, and the average value is calculated to obtain candidate inspection points. Since there are various reasons for the inspector to slow down or stay during the inspection, the candidate inspection points cannot be directly used as inspection points and further screening is required, as follows:

[0090] (8) Perform density clustering on the inspection point reference data of the multiple historical inspection data based on the coordinates of the candidate inspection points to obtain multiple clusters;

[0091] For each candidate inspection point extracted from each historical inspection, the present application performs density clustering on it, so as to cluster the inspection point reference data with similar position characteristics together to obtain multiple clusters.

[0092] (9) Use the clusters with the data volume within the cluster greater than the preset threshold as intermediate clusters, calculate the average coordinates of all candidate inspection points within the intermediate clusters, and screen out the deviation points within the intermediate clusters based on the average coordinates to obtain target clusters;

[0093] If the number of clusters obtained by clustering is large, it means that there are a large number of candidate inspection points with similar positions within this cluster, then it is judged that the inspection points within this cluster are the positions where the inspector is likely to perform the inspection task during the inspection. For other clusters with a small number, it means that the candidate inspection points within the cluster are formed accidentally. It may be the positioning generated when the inspector is performing accidental events, such as resting, making a phone call, etc., and slowing down or staying in the inspection area. Since it is an accidental event, the positioning is not fixed, so these data points are removed.

[0094] In the present application, each selected target cluster represents an inspection point. Each target cluster is a set of positioning points generated when inspecting the inspection point in the historical inspection data.

[0095] (10) Calculate the average coordinates of all candidate inspection points within the target cluster to obtain the inspection point reference coordinates representing the inspection point ; Based on the inspection point reference coordinates Calculate the variance of the abscissas of all candidate inspection points within the target cluster , the variance of the ordinates , and the covariance of the abscissas and ordinates ;

[0096] Since the target cluster has been screened out in the previous text, only the reference range and the reference duration need to be extracted from the target cluster, and then the reference information for the inspection personnel can be constructed.

[0097] In this embodiment, first calculate the average coordinates of all candidate inspection points within the target cluster as the standard positioning point of the inspection point position.

[0098] Then calculate the variance of the abscissas of all candidate inspection points within the target cluster , the variance of the ordinates , and the covariance of the abscissas and ordinates to reflect the distribution characteristics of the data points within the target cluster.

[0099] Among them, the variance of the abscissas , the variance of the ordinates , and the covariance of the abscissas and ordinates have the following mathematical expressions respectively:

[0100]

[0101] Among them, is the total number of positioning points within the target cluster, is the coordinate of the th positioning point within the target cluster, is the coordinate mean of all positioning points within the target cluster , is the coordinate mean of all positioning points within the target cluster.

[0102] Based on the variance of the abscissas , the variance of the ordinates , and the covariance of the abscissas and ordinates , construct the covariance matrix of the target cluster. The mathematical expression of the covariance matrix is:

[0103]

[0104] Construct the calculation formula of the covariance matrix . The calculation formula is , and obtain the first eigenvalue and the second eigenvalue . Among them, represents the eigenvalue is the identity matrix;

[0105] (12)Based on the first eigenvalue and the second eigenvalue construct the major axis and the minor axis respectively, where , , is the range adjustment parameter;

[0106] (13)Based on the major axis and the minor axis construct a range ellipse, and use the range ellipse as the reference range for the inspection points;

[0107] In this embodiment, the covariance matrix is constructed, then the covariance matrix is solved to obtain eigenvalues, and finally the eigenvalues are used to construct the major axis and minor axis of the ellipse, so as to construct a range ellipse reflecting the general inspection range of the inspection points. The shape of the range ellipse is related to the characteristics of the inspection target. For example, when the inspection target is a long equipment, the major axis of the constructed range ellipse will be much larger than the minor axis.

[0108] (14)Calculate the average duration and the standard deviation of the duration within the target cluster, and construct a reference inspection duration range based on the average duration and the standard deviation of the duration.

[0109] Finally, use the average duration and the standard deviation of the duration within the target cluster to construct a duration reference range that satisfies 3 times the standard deviation. Combining with the range ellipse of the inspection points, the reference information can be constructed.

[0110] When the inspection personnel perform the inspection task, the reference information can be sent to the inspection personnel to prompt the inspection personnel to perform the inspection according to the reference information.

[0111] S220, send the reference information to the inspection personnel, and obtain the real-time inspection information of the inspection personnel and the environmental data collected by sensors at multiple points on the construction site. Among them, the real-time inspection information includes real-time positioning;

[0112] In this embodiment, the inspected construction project is a smart construction site, and generally multiple sensors are set, such as temperature and humidity sensors, dust concentration sensors, noise sensors, harmful gas sensors, etc. The data collected by these sensors are returned to the background device, and the background device then transmits them to the server through the Internet.

[0113] S230, determine the inspection priority of each inspection point based on the real-time inspection information of the inspection personnel and the environmental data collected by sensors at multiple points on the construction site;

[0114] In this application, when the inspection personnel conduct inspections, they need to preferentially select areas with abnormalities or abnormal risks to quickly locate and discover the problems. However, the inspection routes of the inspection personnel also need to be considered to avoid a large number of detours. Therefore, this application first determines the priority of each inspection point to perform inspection route planning and guidance using the priority.

[0115] The process of determining the priority is as follows:

[0116] S231. Obtain the current location of the inspection personnel , and the values of the environmental parameters of multiple sensors in the target time period;

[0117] In this application, dynamic priority is adopted, that is, the priority of multiple inspection points is determined according to the current position of the inspection personnel. The advantage of determining the priority in this way is that it is more flexible and more reasonable. Therefore, it is necessary to obtain the location of the inspection personnel through a handheld intelligent terminal. In addition, the set sensors also collect the values of the environmental parameters of the monitoring points in real time.

[0118] S232. Calculate the distance between each inspection point and the current location , and determine the abnormal risk value of each monitoring point based on the values of the environmental parameters of multiple sensors in the target time period , where the abnormal risk value is determined by the value-taking risk, fluctuation risk, and trend risk, is the inspection point serial number, is the monitoring point serial number;

[0119] In this application, the value-taking risk reflects whether there is an abnormality at the monitoring point, while the fluctuation risk and trend risk reflect whether there is an abnormal risk at the monitoring unit.

[0120] Specifically, the process of determining the abnormal risk value is as follows:

[0121] S2321. Compare the values of the environmental parameters at multiple time points in the second target time period with a preset reference range to obtain a value-taking risk value , where when the value of the environmental parameter at any time point in the target time period does not fall within the preset reference range, otherwise, ;

[0122] For the judgment of abnormal value-taking, the environmental parameters such as temperature and humidity, dust concentration, noise level, and harmful gas concentration are compared with the corresponding reference ranges. If it exceeds the range, it means that the environmental parameter is abnormal. At this time, the parameter value with abnormal value-taking is assigned 1, indicating the existence of value-taking risk.

[0123] Among them, the second target time period can be a time period of 1 - 2 hours before the current time point.

[0124] S2322. Based on the pre - constructed sliding window, perform a moving average on the values of the environmental parameters at multiple time points in the second target time period to obtain the average values of the environmental parameters in multiple sections extracted by the sliding window , and when the average values of the environmental parameters in any two adjacent sections satisfy , or , it is determined that there is a one - way change trend in the values of the environmental parameters at multiple time points in the target time period;

[0125] When analyzing potential risks, first perform a trend analysis on the values of multiple sensors in the second target time period (that is, the time period of 1 - 2 hours before the current time point).

[0126] In this application, the moving average method is used to extract the average values of the environmental parameters in multiple time sections, and the average values of multiple time sections are used to analyze the overall value trend, so as to determine whether there is a one - way change trend in the values. If there is a one - way change trend for a continuous duration, it is very likely that there will be an abnormal value at a future time point.

[0127] S2323. When there is an upward trend in the values of the environmental parameters at multiple time points in the target time period, compare the value of the environmental parameter at the current time point with the set upward warning line, and when the value of the environmental parameter at the current time point is greater than the upward warning line, the trend risk value , otherwise, ; when there is a downward trend in the values of the environmental parameters at multiple time points in the target time period, compare the value of the environmental parameter at the current time point with the set downward warning line, and when the value of the environmental parameter at the current time point is less than the upward warning line, the trend risk value, otherwise, ;

[0128] If there is a one - way change trend, this application compares the value at the current time point with the preset warning line. If it has exceeded the warning line, it means that there is already an abnormal risk, and at this time the trend risk value .

[0129] S2324. When there is no one - way change trend in the values of the environmental parameters at multiple time points in the target time period, calculate the variance of the values of the environmental parameters at multiple time points in the target time period, and compare the variance with the preset variance range to obtain the fluctuation risk value , where when the variance does not fall within the preset variance range, , otherwise, ;

[0130] If there is no unidirectional change trend, it is also necessary to analyze whether there are abnormal fluctuations in the values, because if there are abnormal fluctuations, it means that there are some abnormal scenarios currently, resulting in abnormal changes in environmental parameters. This is also an abnormal situation that requires inspection. Therefore, in this embodiment, variance is used to analyze the volatility. If there are abnormal fluctuations, the fluctuation risk value is assigned a value of 1.

[0131] S2325, based on the value risk value and the trend risk value construct an abnormal risk value , ; or; based on the value risk value and the fluctuation risk value construct an abnormal risk value , , where is the third weight, is the fourth weight, is the fifth weight.

[0132] Finally, use the preset weights to perform weighted summation on value anomalies, trend risks, and fluctuation risks to obtain the overall abnormal risk value. The abnormal risk value can reflect anomalies in multiple dimensions.

[0133] Specifically, , .

[0134] S233, use the abnormal risk value of the monitoring point as the abnormal risk value of the inspection points within the coverage range of the corresponding sensor , and based on each inspection point and the current location the distance between them, the abnormal risk value of the inspection point, calculate the priority score of each inspection point , where the mathematical expression of the priority score is:

[0135]

[0136] In the formula, is the first weight, is the second weight, is the normalization function;

[0137] The purpose of the normalization function is to uniformly measure the risks or distances of multiple inspection points, and then perform weighted summation.

[0138] By using the abnormal risk and distance for weighting, the priorities of multiple inspection points at the current position of the inspector can be obtained, thus helping the inspector evaluate the priority of the next inspection point from two dimensions of point risk and distance.

[0139] S234, based on multiple inspection points of the priority score determine the priorities of multiple inspection points of.

[0140] Figure 4 This is a schematic diagram of the priorities of multiple inspection points in an embodiment of the present application. As Figure 4 shown, the present application adopts a dynamic priority method, which can provide the optimal path for each single inspection for the inspector.

[0141] S240, based on the inspection priority of each inspection point and the reference ranges of multiple inspection points, perform inspection guidance management on the inspector, and, based on the reference ranges of multiple inspection points and the reference inspection duration ranges of multiple inspection points, perform inspection supervision management on the inspector.

[0142] After constructing the priorities and reference information, the priorities and reference information can be used to perform guidance management and supervision management on the inspector. The steps of guidance management include:

[0143] S2401, obtain the current position of the inspector;

[0144] S2402, when the duration of the current position of the inspector within the reference range of one of the inspection points exceeds the target duration, determine that the inspector is performing inspection at the current inspection point, update the inspection priorities of all inspection points at the current position of the inspector, and send the next inspection point with the highest inspection priority to the inspector to complete the guidance management.

[0145] If the residence duration of the inspector within the reference range of a certain inspection point exceeds the preset target duration (i.e., it is considered that the inspector has performed an inspection task at this point), the system confirms that the inspector is performing an inspection task at the current inspection point. This kind of guidance can help the inspector complete all inspection tasks according to the optimal path and sequence, improve work efficiency and ensure that all key points are inspected in a timely manner.

[0146] When performing guidance management, it is necessary to update the inspection priorities of all inspection points based on dynamic priorities, and send the next inspection point with the highest inspection priority to the inspector, so as to help the inspector achieve optimal path planning.

[0147] The process of supervision and management includes:

[0148] S2411, statistically calculate the inspection duration and inspection path of the inspector within the reference range of each inspection point, where the inspection path is composed of multiple positions of the inspector within the reference range;

[0149] For each inspection point, the system needs to calculate the residence time of the inspector within the reference range of this point. This is usually achieved by recording the timestamps when the inspector enters and leaves the reference range.

[0150] The inspection path is composed of a series of positioning points within the reference range. These positioning points can come from GPS or other positioning technologies. The system needs to collect this positioning data and concatenate them to form the inspection path.

[0151] S2412, compare the inspection duration with the reference inspection duration range, and when the inspection duration is less than the lower limit value of the reference inspection duration range, give a prompt to the inspector;

[0152] The inspection path is composed of a series of positioning points within the reference range. These positioning points can come from GPS or other positioning technologies. The system needs to collect this positioning data and concatenate them to form the inspection path.

[0153] S2413, statistically calculate the number of grids passed by the inspection path within the reference range, calculate the passing grid ratio based on the number of passed grids and the total number of grids within the reference range, compare the passing grid ratio with a preset ratio threshold, and when the passing grid ratio is less than the preset ratio threshold, give a prompt to the inspector, where the reference range is uniformly divided in advance to obtain multiple grids within the reference range.

[0154] Figure 5 Schematic diagram of the grids within the reference range and the inspection path in an embodiment of the present application, as Figure 5 shown, in the present application, first the inspection area is uniformly divided to generate multiple small grids. The advantage of doing this is that the inspection coverage can be evaluated more precisely. Statistically calculate the number of grids passed by the inspection path. Here, only the grids actually reached by the inspection path are considered. Calculate the ratio based on the number of passed grids and the total number of grids, that is . Compare the calculated passing grid ratio with a pre-set ratio threshold. If it is lower than the threshold, it indicates insufficient inspection coverage, and the system will also prompt the inspection personnel. This mechanism helps to ensure the quality and efficiency of the inspection work, helps the inspection personnel identify potential problem areas through real-time monitoring and feedback, and improves the comprehensiveness and accuracy of the inspection work. At the same time, it can also provide quantitative basis for the management level, facilitating subsequent performance evaluation and decision-making.

[0155] In addition, when prompting the inspection personnel, mark the inspection points until the inspection duration is greater than or equal to the lower limit of the reference inspection duration range, or the passing grid ratio is greater than or equal to the preset ratio threshold, and then remove the marks. This is convenient for the inspection personnel to use the handheld intelligent terminal to view the inspection tasks and check if there are any points with insufficient inspections.

[0156] A smart inspection management method of the present invention, when an inspection user conducts an inspection, uses the pre-constructed reference information to provide reference to the inspection personnel, so that the inspection personnel can understand the reference range and inspection time of each inspection point of each inspection item. It helps the inspection personnel who are not familiar with the project to quickly understand the inspection project. In addition, this application uses the environmental parameters collected in real time by the sensors set on the construction site project and the real-time positioning of the inspection personnel to determine the priority of each inspection point. When the inspection personnel are performing the inspection task, use the priority and reference information to guide and supervise the inspection personnel. This application can effectively guide and supervise the inspection process of the inspection personnel, and help the inspection personnel improve the inspection efficiency and inspection quality.

[0157] As Figure 6 shown, this application also provides a smart inspection management system, including:

[0158] An acquisition module, used to acquire the reference information of the inspection project corresponding to the inspection request when receiving an inspection request from the inspection personnel, where the reference information includes multiple inspection points, the reference range of multiple inspection points, and the reference inspection duration range of multiple inspection points, and the reference information is generated based on historical inspection information;

[0159] A detection module, used to send the reference information to the inspection personnel, and acquire the real-time inspection information of the inspection personnel and the environmental data collected by the sensors at multiple points on the construction site, where the real-time inspection information includes real-time positioning;

[0160] A priority determination module, used to determine the inspection priority of each inspection point based on the real-time inspection information of the inspection personnel and the environmental data collected by the sensors at multiple points on the construction site;

[0161] A management module for guiding and managing the inspection personnel based on the inspection priorities of each inspection point and the reference ranges of multiple inspection points, and for supervising and managing the inspection personnel based on the reference ranges of multiple inspection points and the reference inspection duration ranges of multiple inspection points.

[0162] A smart inspection management system according to the present invention, when an inspection user conducts an inspection, uses pre-constructed reference information to provide reference to the inspection personnel, so that the inspection personnel can understand the reference ranges and inspection times of each inspection point of each inspection item. It helps inspection personnel who are not familiar with the project quickly understand the inspection project. In addition, the present application determines the priority of each inspection point by using the environmental parameters collected in real time by sensors installed on the construction site project and the real-time positioning of the inspection personnel. When the inspection personnel are performing the inspection task, the priority and reference information are used to guide and supervise the inspection personnel. The present application can effectively guide and supervise the inspection process of the inspection personnel, and help the inspection personnel improve the inspection efficiency and inspection quality.

[0163] This embodiment also provides an electronic terminal, including: a processor and a memory;

[0164] The memory is used to store a computer program, and the processor is used to execute the computer program stored in the memory, so that the terminal executes any method in this embodiment.

[0165] For the computer-readable storage medium in this embodiment, those of ordinary skill in the art can understand that all or part of the steps of implementing the above method embodiments can be completed by hardware related to the computer program. The aforementioned computer program can be stored in a computer-readable storage medium. When this program is executed, it executes the steps including the above method embodiments; and the aforementioned storage medium includes: various media such as ROM, RAM, magnetic disk or optical disk that can store program codes.

[0166] The electronic terminal provided in this embodiment includes a processor, a memory, a transceiver, and a communication interface. The memory and the communication interface are connected to the processor and the transceiver and complete communication with each other. The memory is used to store a computer program, the communication interface is used for communication, and the processor and the transceiver are used to run the computer program, so that the electronic terminal executes each step of the above method.

[0167] In this embodiment, the memory may include a random access memory (Random Access Memory, abbreviated as RAM), and may also include a non-volatile memory, such as at least one disk memory.

[0168] The above-mentioned processor may be a general-purpose processor, including a central processing unit (CPU for short), a network processor (NP for short), etc.; it may also be a digital signal processor (DSP for short), an application specific integrated circuit (ASIC for short), a field-programmable gate array (FPGA for short), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

[0169] In the above embodiments, although the present invention has been described in conjunction with specific embodiments of the present invention, many alternatives, modifications, and variations of these embodiments will be apparent to those of ordinary skill in the art in light of the foregoing description. The embodiments of the present invention are intended to cover all such alternatives, modifications, and variations that fall within the broad scope of the appended claims.

[0170] The above embodiments are only illustrative of the principles and effects of the present invention and are not intended to limit the present invention. Any person familiar with this technology can modify or change the above embodiments without departing from the spirit and scope of the present invention. Therefore, all equivalent modifications or changes made by those with ordinary knowledge in the technical field without departing from the spirit and technical idea disclosed by the present invention should still be covered by the claims of the present invention.

Claims

1. A smart inspection management method, characterized in that, Including steps: When receiving an inspection request from an inspection personnel, obtain the reference information of the inspection items corresponding to the inspection request, where the reference information includes multiple inspection points, the reference ranges of the multiple inspection points, and the reference inspection duration ranges of the multiple inspection points, and the reference information is generated based on historical inspection information; the method for generating the reference information of the inspection items includes: obtaining historical inspection data generated during multiple inspections of the inspection items in a first target time period, where the historical inspection data includes historical inspection positions at multiple time points , where represents a time point, and the target time period is the time period of a target duration before the current time point; calculate the distance between the historical inspection positions of any two adjacent time points in the historical inspection data ; based on the distances between multiple adjacent time points construct a time series displacement sequence; perform sliding filtering on the time series displacement sequence to obtain a time series displacement filtering sequence; and slide along the time direction of the time series displacement filtering sequence based on a pre-constructed sliding window, and calculate the distance mean of the time series displacement filtering sequence within the sliding window each time it slides ; use the section corresponding to the sliding window with a distance mean less than a preset distance threshold as the target section, merge adjacent target sections, and extract the slow travel duration and multiple historical inspection positions ; calculate the average position of the multiple historical inspection positions of the merged target section, use the average position of each merged target section as a candidate inspection point, and construct the inspection point reference data of each historical inspection data based on the candidate inspection points and slow travel duration of each merged target section ; construct the reference information of the inspection items based on the inspection point reference data of multiple historical inspection data ; Sending the reference information to the inspection personnel, and obtaining the real-time inspection information of the inspection personnel and the environmental data collected by sensors at multiple points on the construction site. Among them, the real-time inspection information includes real-time positioning; Determining the inspection priority of each inspection point based on the real-time inspection information of the inspection personnel and the environmental data collected by sensors at multiple points on the construction site; Managing the inspection guidance for the inspection personnel based on the inspection priority of each inspection point and the reference range of multiple inspection points, and managing the inspection supervision for the inspection personnel based on the reference range of multiple inspection points and the reference inspection duration range of multiple inspection points.

2. The intelligent patrol management method according to claim 1, characterized in that Reference data for inspection points based on the multiple historical inspection data Construct the reference information for the inspection items, including: Inspection point reference data of the multiple historical inspection data based on the coordinates of candidate inspection points Perform density clustering to obtain multiple clusters; Taking the cluster with the data volume in the cluster greater than the preset threshold as the intermediate cluster, calculating the average coordinates of all candidate inspection points in the intermediate cluster, and screening out the deviation points in the intermediate cluster based on the average coordinates to obtain the target cluster; Calculate the average coordinates of all candidate inspection points within the target cluster to obtain an inspection point reference coordinate representing the inspection point position ; Based on the inspection point reference coordinate Calculate the abscissa variance of all candidate inspection points within the target cluster , ordinate variance and abscissa-ordinate covariance ; Based on the variance of the abscissa , the variance of the ordinate and the covariance of the abscissa and ordinate construct the covariance matrix of the target cluster , and the mathematical expression of the covariance matrix is as follows: Construct a covariance matrix and its calculation formula. The calculation formula is to obtain the first eigenvalue and the second eigenvalue , where represents the eigenvalue and is the identity matrix; Based on the first eigenvalue and the second eigenvalue construct the major axis and the minor axis respectively, where , , is a range adjustment parameter; Based on the major axis and the minor axis a range ellipse is constructed, and the range ellipse is used as the reference range for the inspection points; Calculating the average duration and duration standard deviation in the target cluster, and constructing the reference inspection duration range based on the average duration and the duration standard deviation.

3. A smart inspection management method according to claim 1, characterized in that, Determining the inspection priority of each inspection point based on the real-time inspection information of the inspection personnel and the environmental data collected by sensors at multiple points on the construction site, including: Obtain the current location of the inspection personnel and the values of the environmental parameters of multiple sensors during the target time period; Calculate each inspection point and the current location to determine the distance between them, and determine the abnormal risk value of each monitoring point based on the environmental parameter values of multiple sensors during the target time period where the abnormal risk value is determined by the value risk, fluctuation risk, and trend risk is the serial number of the inspection point is the serial number of the monitoring point Take the abnormal risk value of the monitoring point as the abnormal risk value of the inspection point within the coverage of the corresponding sensor , and based on each inspection point and the current location calculate the distance between , the abnormal risk value of the inspection point to calculate the priority score of each inspection point , where the mathematical expression of the priority score is as follows: ​ In the formula, is the first weight, is the second weight, is the normalization function; Based on the priority scores of multiple inspection points to determine the priorities of multiple inspection points Based on the priority scores of multiple inspection points to determine the priorities of multiple inspection points 4. The intelligent inspection management method according to claim 3, wherein, Determining the abnormal risk value of each monitoring point based on the values of the environmental parameters of multiple sensors in the target time period, including: Compare the values of the environmental parameters at multiple time points in the second target time period with a preset reference range to obtain a value risk , where when the value of the environmental parameter at any time point in the second target time period does not fall within the preset reference range, , otherwise, ; Moving average is performed on the values of the environmental parameters at multiple time points in the second target time period based on a pre-constructed sliding window to obtain the average values of the environmental parameters in multiple sections extracted by the sliding window , and when the average values of the environmental parameters in any two adjacent sections satisfy , or , it is determined that there is a one-way change trend in the values of the environmental parameters at multiple time points in the second target time period; when there is an upward trend in the values of the environmental parameters at multiple time points in the second target time period, the value of the environmental parameter at the current time point is compared with the set upward warning line, and when the value of the environmental parameter at the current time point is greater than the upward warning line, the trend risk value , otherwise ; when there is a downward trend in the values of the environmental parameters at multiple time points in the second target time period, the value of the environmental parameter at the current time point is compared with the set downward warning line, and when the value of the environmental parameter at the current time point is less than the upward warning line, the trend risk value , otherwise ; When there is no unidirectional change trend in the values of the environmental parameters at multiple time points within the second target time period, calculate the variance of the values of the environmental parameters at multiple time points within the second target time period, and compare the variance with a preset variance range to obtain a fluctuation risk value , where when the variance does not fall within the preset variance range , otherwise ; Based on the said value-taking risk value and the said trend risk value construct an abnormal risk value , ; or; based on the said value-taking risk value and the volatility risk value construct an abnormal risk value , , where is the third weight is the fourth weight is the fifth weight 5. A smart inspection management method according to claim 1, characterized in that, Managing the inspection guidance for the inspection personnel based on the inspection priority of each inspection point, including: Obtaining the current position of the inspection personnel; When the duration of the current position of the inspection personnel within the reference range of one of the inspection points exceeds the target duration, it is determined that the inspection personnel are performing inspections at the current inspection point, and the inspection priorities of all inspection points are updated at the current position of the inspection personnel, and the next inspection point with the highest inspection priority is sent to the inspection personnel to complete the guidance management.

6. A smart patrol management method according to claim 1, characterized in that Managing the inspection supervision for the inspection personnel based on the reference range of multiple inspection points and the reference inspection duration range of multiple inspection points, including: Counting the inspection duration and inspection path of the inspection personnel within the reference range of each inspection point, where the inspection path is composed of multiple positions of the inspection personnel within the reference range; Comparing the inspection duration with the reference inspection duration range, and giving a prompt to the inspection personnel when the inspection duration is less than the lower limit value of the reference inspection duration range; Counting the number of grid cells passed by the inspection path within the reference range, calculating the passing grid cell ratio based on the number of passed grid cells and the total number of grid cells within the reference range, comparing the passing grid cell ratio with the preset ratio threshold, and giving a prompt to the inspection personnel when the passing grid cell ratio is less than the preset ratio threshold. Among them, the reference range is evenly divided in advance to obtain multiple grid cells within the reference range.

7. The intelligent patrol management method according to claim 6, wherein It also includes: When giving a prompt to the inspection personnel, marking the inspection points, and removing the marks until the inspection duration is greater than or equal to the lower limit value of the reference inspection duration range, or the passing grid cell ratio is greater than or equal to the preset ratio threshold.

8. A smart inspection management method according to claim 1, characterized in that, The historical inspection data is data located within the defined range of the inspection item, wherein the address and the defined range of the inspection item are established in advance.

9. A smart inspection management system, characterized in that, Including: An acquisition module is used to acquire reference information of an inspection item corresponding to the inspection request when receiving an inspection request from an inspection personnel. The reference information includes multiple inspection points, reference ranges of multiple inspection points, and reference inspection duration ranges of multiple inspection points. The reference information is generated based on historical inspection information. The method for generating the reference information of the inspection item includes: acquiring historical inspection data generated during multiple inspections of the inspection item in a first target time period, where the historical inspection data includes historical inspection positions at multiple time points, where the target time period is a time period with a target duration before the current time point; calculating the distance between the historical inspection positions of any two adjacent time points in the historical inspection data , where represents a time point, and the target time period is a time period with a target duration before the current time point; calculating the distance between the historical inspection positions of any two adjacent time points in the historical inspection data ; based on the distances between multiple adjacent time points construct a time series displacement sequence; perform sliding filtering on the time series displacement sequence to obtain a time series displacement filtered sequence; and slide a pre-constructed sliding window along the time direction of the time series displacement filtered sequence, and calculate the average distance of the time series displacement filtered sequence within the sliding window each time it slides ; take the section corresponding to the sliding window with an average distance less than a preset distance threshold as the target section, merge adjacent target sections, and extract the slow-down duration and multiple historical inspection positions ; calculate the average position of the multiple historical inspection positions of the merged target section, take the average position of each merged target section as a candidate inspection point, and construct inspection point reference data for each historical inspection data based on the candidate inspection points and slow-down durations of each merged target section ; construct the reference information of the inspection item based on the inspection point reference data of multiple historical inspection data ; A detection module, configured to send the reference information to the inspection personnel, and obtain the real-time inspection information of the inspection personnel and the environmental data collected by sensors at multiple points on the construction site, wherein the real-time inspection information includes real-time positioning; A priority determination module, configured to determine the inspection priority of each inspection point based on the real-time inspection information of the inspection personnel and the environmental data collected by sensors at multiple points on the construction site; A management module, configured to manage the inspection guidance of the inspection personnel based on the inspection priority of each inspection point and the reference range of multiple inspection points, and manage the inspection supervision of the inspection personnel based on the reference range of multiple inspection points and the reference inspection duration range of multiple inspection points.

Images