An artificial intelligence-based smart space governance platform

Abstract

The present invention provides an artificial intelligence-based smart space governance platform, which belongs to the field of safety supervision technology and uses a governance method, which specifically includes: determining the network abnormality probability of the observation data of different observation Internet of Things devices and paying attention to abnormal devices through the analysis results of observation data of different observation Internet of Things devices, determining the probability of quality defects in different observation defect potential risk points based on the types of observation defect potential risk points, generating multiple observation defect potential risk point groups based on the observation defect potential risk points, determining the impact on building safety when quality defects occur at the same time at the observation defect potential risk points in different observation defect potential risk point groups, and using the impact on building safety to output a network governance plan for the area, thereby improving the reliability of quality hazard observation.

Description

Technical Field

[0001] The present invention belongs to the field of security supervision technology, and in particular relates to an artificial intelligence-based smart space governance platform. Background Art

[0002] During the construction process at the construction site, there will inevitably be construction quality problems and construction safety risk problems. This makes how to timely control construction quality problems and construction safety risk problems within the management space area with the construction site as the management space a technical problem that needs to be solved urgently.

[0003] In the existing technical solutions, various types of IoT monitoring devices are often used to realize real-time monitoring of various types of building quality. Specifically, similar technical solutions are given in the invention patent application CN201811087981.2 "A Smart Construction Site Supervision and Approval Platform", etc. However, the above technical solutions all have the following technical problems:

[0004] Due to the large number and dimensions of IoT monitoring devices used for building quality and safety risk management, how to manage IoT monitoring devices to ensure their reliability has become a technical problem that needs to be solved urgently.

[0005] In response to the above technical problems, the present invention provides an artificial intelligence-based smart space governance platform. Summary of the invention

[0006] To achieve the purpose of the present invention, the present invention adopts the following technical solutions:

[0007] According to one aspect of the present invention, there is provided an artificial intelligence-based smart space governance platform.

[0008] An artificial intelligence-based smart space governance platform uses a governance method, specifically including:

[0009] S1 divides the smart space based on the construction site into multiple areas, determines the IoT devices for observing quality risk points in different areas, and determines the network abnormality probability of the observation data of different IoT devices and pays attention to abnormal devices through the analysis results of the observation data of different IoT devices;

[0010] S2 determines the observation equipment combination of the quality potential risk point when the abnormalities of different concerned abnormal equipment occur, and determines the observation reliability and observation defect potential risk points of different quality potential risk points in the area based on the analysis results of the observation data of the quality potential risk point of the observation equipment combination and the probability of occurrence of network abnormalities of the observation equipment combination;

[0011] S3 determines the probability of occurrence of quality defects at different observed defect potential points based on the type of the observed defect potential point;

[0012] S4 generates multiple groups of observed defect hidden danger points based on the observed defect hidden danger points, determines the impact on building safety when quality defects occur simultaneously at the observed defect hidden danger points in different groups of observed defect hidden danger points, and uses the impact on building safety to output a network governance plan for the area.

[0013] The beneficial effects of the present invention are:

[0014] Through the analysis results of the observation data of different observation IoT devices, the network anomaly probability and the abnormal devices of attention of the observation data of different observation IoT devices are determined, so that on the basis of the observation data of the observation IoT devices, the abnormal devices of attention with suspected abnormalities in the network communication status are obtained, which also lays the foundation for further determining the quality potential danger points with defects in observation based on the abnormal devices of attention, and avoids the emergence of technical problems of building safety risks caused by abnormalities in quality potential danger observations.

[0015] By utilizing the impact of simultaneous quality defects at observation defect hidden danger points in different observation defect hidden danger point groups on building safety, the output of regional network governance plans is carried out, avoiding the emergence of technical problems such as an incomplete assessment of the impact of a single observation defect hidden danger point on building safety risks. This achieves a comprehensive assessment of building safety risks based on multiple quality hidden danger points, and also lays a foundation for generating differentiated observation processing plans and improving the observation accuracy of quality hidden danger points.

[0016] A further technical solution is to divide the smart space based on the construction site into multiple areas, including:

[0017] The construction site is divided into a plurality of areas using a preset area.

[0018] A further technical solution is that the quality risk points are determined according to the types of construction projects in the area, and specifically determined according to the construction points in the construction project types where quality risks have occurred.

[0019] A further technical solution is that the observation Internet of Things device determines the Internet of Things device that is associated with the quality defects of the quality risk point based on the observation data.

[0020] A further technical solution is to output a network governance solution for the area using the impact on building safety, specifically including:

[0021] Based on the impact of the observed defect potential point group on building safety, determine the building area corresponding to the observed defect potential point group with building safety risk, and determine the safety impact coefficient of the observed defect potential point group in combination with the defect probabilities of different observed defect potential point groups;

[0022] The safety risk coefficient of the area is determined by the safety impact coefficients of different groups of observed defect potential risk points, and the network governance plan for the area is determined using the safety risk coefficient.

[0023] A further technical solution is that the network management solution includes setting up a network relay device and not setting up a network relay device.

[0024] A further technical solution is that the defect probability of the observed defect potential point group is determined according to the probability of quality defects occurring simultaneously at all the observed defect potential point groups in the observed defect potential point group.

[0025] Other features and advantages will be described in the following description. The objects and other advantages of the present invention are realized and obtained by the structures particularly pointed out in the description and drawings.

[0026] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, preferred embodiments are given below and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] The above and other features and advantages of the present invention will become more apparent by describing in detail exemplary embodiments thereof with reference to the accompanying drawings;

[0028] Figure 1 It is a flow chart of a governance approach;

[0029] Figure 2 is a flow chart of a method for determining a network anomaly probability of observing observation data of an IoT device;

[0030] Figure 3 It is a flow chart of the method for determining the reliability of observation of quality risk points;

[0031] Figure 4 It is a flow chart of a method for determining the probability of occurrence of quality defects at observed defect potential points. DETAILED DESCRIPTION

[0032] In order to enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below in conjunction with the drawings in the embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this specification, not all of the embodiments. Based on the embodiments of this specification, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of this specification.

[0033] Since the number and dimensions of IoT monitoring devices used for building quality and safety risk management are large, it is necessary to manage the IoT monitoring devices to ensure the reliability of their use.

[0034] Network anomaly probability of observation data of observed IoT devices: The network anomaly probability is determined based on the proportion of time that the network in the observation data of observed IoT devices is abnormal. Observed IoT devices with a network anomaly probability greater than 0.3 are regarded as abnormal devices of concern.

[0035] Observation reliability of quality risk points: Determine the observation anomaly coefficient of the quality observation point based on the ratio of the number of abnormalities in the observation data of the quality risk point of the observation equipment combination to the preset number of times and the product of the probability of occurrence of network anomalies of the observation equipment combination. Take the difference between 1 and the observation anomaly coefficient as the observation reliability, and take the quality risk point with an observation reliability less than 0.5 as an observation defect risk point.

[0036] Probability of occurrence of quality defects at observed defect potential point: Based on the type of observed defect potential point, determine the number of occurrences of different types of quality defects at the observed defect potential point; based on the number of occurrences of different types of quality defects, determine the preset occurrence probabilities corresponding to different types of quality defects under the number of occurrences; determine the probability of occurrence of quality defects at the observed defect potential point by the sum of the preset occurrence probabilities corresponding to different types of quality defects.

[0037] Output of network governance plan for the area using impact on building safety:

[0038] Based on the impact of the observed defect and potential danger point groups on building safety, determine the building areas with building safety risks corresponding to the observed defect and potential danger point groups, use the proportion of the total building areas with building safety risks corresponding to the observed defect and potential danger point groups to determine the safety risk coefficient of the region, and use the safety risk coefficient to determine the network governance plan for the region.

[0039] To solve the above problems, according to one aspect of the present invention, Figure 1 As shown, a smart space governance platform based on artificial intelligence is provided, using a governance method, specifically including:

[0040] S1 divides the smart space based on the construction site into multiple areas, determines the IoT devices for observing quality risk points in different areas, and determines the network abnormality probability of the observation data of different IoT devices and pays attention to abnormal devices through the analysis results of the observation data of different IoT devices;

[0041] S2 determines the observation equipment combination of the quality potential risk point when the abnormalities of different concerned abnormal equipment occur, and determines the observation reliability and observation defect potential risk points of different quality potential risk points in the area based on the analysis results of the observation data of the quality potential risk point of the observation equipment combination and the probability of occurrence of network abnormalities of the observation equipment combination;

[0042] S3 determines the probability of occurrence of quality defects at different observed defect potential points based on the type of the observed defect potential point;

[0043] S4 generates multiple groups of observed defect hidden danger points based on the observed defect hidden danger points, determines the impact on building safety when quality defects occur simultaneously at the observed defect hidden danger points in different groups of observed defect hidden danger points, and uses the impact on building safety to output a network governance plan for the area.

[0044] Furthermore, the smart space based on the construction site is divided into multiple areas, including:

[0045] The construction site is divided into a plurality of areas using a preset area.

[0046] Specifically, the quality hidden danger points are determined according to the types of construction projects in the area, and specifically determined according to the construction points in the construction project types where quality hidden dangers have occurred.

[0047] Specifically, the observing Internet of Things device determines the Internet of Things device that is associated with the quality defect of the quality risk point based on the observation data.

[0048] Specifically, Figure 2 As shown, the method for determining the network anomaly probability of the observation data of the IoT device is:

[0049] Based on the analysis results of the observation data of the observed IoT device, the number of times the observation data of the observed IoT device has network anomalies is determined, and the number is used as the number of network anomalies. According to different numbers of network anomalies of the observed IoT devices, the proportion of dates with network anomalies is determined, and based on the date proportion, the abnormal date ratio coefficient of the observation data of the observed IoT device is determined;

[0050] Determine the daily average number of network anomalies based on the number of network anomalies that occur on different dates with network anomalies, and determine the daily average network anomaly coefficient of the observation data of the observed Internet of Things device based on the daily average number of network anomalies;

[0051] The network anomaly probability of the observation data of the observed Internet of Things device is determined by multiplying the anomaly date proportion coefficient of the observation data of the observed Internet of Things device by the daily average network anomaly coefficient.

[0052] Furthermore, the abnormal device of concern is an observed Internet of Things device whose network abnormality probability of observed data is not satisfied.

[0053] It can be understood that the observation combination of the quality observation points is an observation combination of quality observation points constructed by observation Internet of Things devices that do not have network anomalies when a network anomaly occurs in one or more abnormal devices of concern.

[0054] Optional, such as Figure 3 As shown, the method for determining the observation reliability of the quality risk point is:

[0055] Determine, based on the analysis result of the observation data of the quality potential danger point of the observation equipment combination, the recognition accuracy rate of the quality potential danger of the quality potential danger point based on the observation data of the observation equipment combination;

[0056] Determine the recognition reliability coefficients of different observation device combinations based on the recognition accuracy and the product of the network abnormality probability of the concerned abnormal device having a network failure corresponding to the observation device combination;

[0057] The observation reliability of the quality risk point is determined by using the identification reliability coefficients of different observation equipment combinations.

[0058] Furthermore, the observation reliability of the quality risk point is determined based on the weighted sum of the identification reliability coefficients of different observation equipment combinations.

[0059] It can be understood that the recognition accuracy of the quality hazard of the quality hazard point is determined according to the number of historical recognition deviations of the quality hazard under the observation data of the observation equipment combination.

[0060] Furthermore, the observed defect potential point is a quality potential point whose identification reliability is not within a preset reliability interval.

[0061] Specifically, Figure 4 As shown, the method for determining the probability of occurrence of quality defects at the observed defect potential point is:

[0062] Based on the type of the observed defect potential point, determining the number of occurrences of different types of quality defects at the observed defect potential point;

[0063] Based on the number of occurrences of different types of quality defects, determining preset occurrence probabilities corresponding to different types of quality defects under the number of occurrences;

[0064] The probability of occurrence of quality defects at the observed defect potential point is determined by the sum of the preset occurrence probabilities corresponding to different types of quality defects.

[0065] Furthermore, the impact on building safety includes the building area where there is a building safety risk.

[0066] It is understood that the output of the network governance plan for the area is based on the impact on building safety, including:

[0067] Based on the impact of the observed defect potential point group on building safety, determine the building area corresponding to the observed defect potential point group with building safety risk, and determine the safety impact coefficient of the observed defect potential point group in combination with the defect probabilities of different observed defect potential point groups;

[0068] The safety risk coefficient of the area is determined by the safety impact coefficients of different groups of observed defect potential risk points, and the network governance plan for the area is determined using the safety risk coefficient.

[0069] Furthermore, the network management solution includes setting up a network relay device and not setting up a network relay device.

[0070] It should also be noted that the defect probability of the observed defect potential point group is determined based on the probability of quality defects occurring simultaneously at all observed defect potential points in the observed defect potential point group.

[0071] It should be further explained that the above technical solution also includes the following replacement technical solution:

[0072] Optionally, the method for determining the network anomaly probability of the observation data of the observed IoT device is:

[0073] Determine the number of times the observation data of the observed IoT device undergoes network anomalies based on the analysis result of the observation data of the observed IoT device, and use the number as the number of network anomalies, and determine the basic network anomaly probability corresponding to the number of network anomalies based on a preset number interval corresponding to the number of network anomalies;

[0074] Determine the percentage of dates with network anomalies according to the number of network anomalies of different observed IoT devices, and determine the abnormal date ratio coefficient of the observation data of the observed IoT devices based on the date percentage;

[0075] The network anomaly probability of the observation data of the observation Internet of Things device is determined by multiplying the anomaly date ratio coefficient of the observation data of the observation Internet of Things device by the basic network anomaly probability.

[0076] Optionally, the determination of the network anomaly probability of the observation data of the observed IoT device includes steps S11-S33, specifically:

[0077] S31 determines the number of times network anomalies occur in the observation data of the observation Internet of Things device based on the analysis result of the observation data of the observation Internet of Things device, and uses the number of times network anomalies occur in the observation data of the observation Internet of Things device;

[0078] S32 determines the percentage of dates with network anomalies according to the number of network anomalies of different observed IoT devices, and determines the abnormal date ratio coefficient of the observation data of the observed IoT devices based on the date percentage;

[0079] S33 determines the proportion of dates when the number of network anomalies is greater than a preset number, and determines the network anomaly probability of the observation data of the observed Internet of Things device based on the proportion of dates when the number of network anomalies is greater than the preset number, the abnormal date ratio coefficient of the observation data of the observed Internet of Things device, and the number of network anomalies on different dates.

[0080] Optionally, before entering step S32, it is also necessary to determine whether the number of network anomalies of the observation data of the observed IoT device is within a preset interval. If it is within the preset interval, it can be determined that the observed IoT device does not belong to the abnormal device of concern. If and only if it is not within the preset interval, proceed to step S32.

[0081] Optionally, the above step S32 includes steps S321-S323, specifically:

[0082] S321 determines the percentage of dates with network anomalies according to the number of network anomalies of different observed IoT devices. When the percentage of dates with network anomalies meets the requirement, the process proceeds to step S322. When the percentage of dates with network anomalies does not meet the requirement, the process directly proceeds to step S323.

[0083] S322 obtains the number of network anomalies on the date when the number of network anomalies is greater than the preset number. If there is no date when the number of network anomalies is greater than the preset number, it can be determined that the observed IoT device does not belong to the concerned abnormal device. If there is a date when the number of network anomalies is greater than the preset number, proceed to step S323.

[0084] S323 determines the abnormal date ratio coefficient of the observation data of the observed IoT device based on the date proportion, and proceeds to step S33.

[0085] Optionally, the above step S33 also includes steps S331-S332, which are specifically:

[0086] S331 determines the percentage of dates when the number of network anomalies is greater than the preset number. When the percentage of dates when the number of network anomalies is greater than the preset number is less than the preset number, proceed to step S332. When the percentage of dates when the number of network anomalies is greater than the preset number is not less than the preset number, proceed to step S333.

[0087] S332: When the abnormal date ratio coefficient of the observation data of the observed IoT device is within the preset ratio range at the same time, it can be determined that the observed IoT device does not belong to the concerned abnormal device. When the abnormal date ratio coefficient of the observation data of the observed IoT device is not within the preset ratio range, proceed to step S333;

[0088] S333 determines the network anomaly probability of the observation data of the observed Internet of Things device based on the proportion of dates with a number of network anomalies greater than a preset number, the anomaly date ratio coefficient of the observation data of the observed Internet of Things device, and the number of network anomalies on different dates.

[0089] It should be further explained that the method for determining the observation reliability of the quality risk point is:

[0090] Determine, based on the analysis result of the observation data of the quality potential danger point of the observation equipment combination, the recognition accuracy rate of the quality potential danger of the quality potential danger point based on the observation data of the observation equipment combination;

[0091] The reliable observation device combination in the observation device combination is determined by the recognition accuracy, and the observation reliability of the quality risk point is determined by using the sum of the network abnormality probabilities of the abnormal devices of concern that have network failures corresponding to the reliable observation device combination.

[0092] Optionally, the determination of the observation reliability of the quality risk point includes steps S21-S23, specifically:

[0093] S21 determines the number of identification deviations of the quality hazards of the quality hazards of the quality hazards of the combination of observation equipment based on the analysis results of the observation data of the quality hazards of the combination of observation equipment, and determines the identification deviation probabilities of different combinations of observation equipment using the number of identification deviations;

[0094] S22 determines the identification deviation coefficients of different observation device combinations based on the product of the identification deviation probability and the network abnormality probability of the concerned abnormal device with network failure corresponding to the observation device combination;

[0095] S23 determines the observation reliability of the quality risk point based on the identification deviation coefficients of different observation equipment combinations.

[0096] Optionally, the above step S21 also includes steps S211 and S212, which are specifically:

[0097] S211 determines the number of identification deviations of the quality hazards of the quality hazard points based on the observation data of the observation equipment combination based on the analysis results of the observation data of the quality hazard points of the observation equipment combination. When the number of identification deviations of the quality hazards of the quality hazard points of different observation equipment combinations meets the requirements, it is determined that the quality hazard points do not belong to the observation defect hazard points. When there is an observation equipment combination whose number of deviation identifications does not meet the requirements, enter step S212;

[0098] S212 uses the number of identification deviations to determine the identification deviation probabilities of different observation equipment combinations. When there is no observation equipment combination whose identification deviation probability does not meet the requirements, it is determined that the quality risk point does not belong to the observation defect risk point. When there is an observation equipment combination whose identification deviation probability does not meet the requirements, enter step S22.

[0099] Optionally, the above step S22 includes steps S221-S223, specifically:

[0100] S221 regards the observation equipment combination whose identification deviation probability does not meet the requirement as the deviation observation combination. When the network abnormality probability of the concerned abnormal equipment with network failure corresponding to the deviation observation combination is less than the preset probability threshold, it is determined that the quality potential risk point does not belong to the observation defect potential risk point. When the network abnormality probability of the concerned abnormal equipment with network failure corresponding to the deviation observation combination is less than the preset probability threshold, the process proceeds to step S222.

[0101] S222 determines the identification deviation coefficients of different observation equipment combinations based on the product of the identification deviation probability and the network abnormality probability of the abnormal equipment of concern that has a network failure corresponding to the observation equipment combination. When the identification deviation coefficients all meet the requirements, it is determined that the quality risk point does not belong to the observation defect risk point. When there is an observation equipment combination whose identification deviation coefficient does not meet the requirements, enter step S23.

[0102] It should be further explained that the output of the network governance plan for the area using the impact on building safety specifically includes steps S41-S43, specifically:

[0103] S41, based on the impact of the observed defect hidden danger point group on building safety, determining the building area corresponding to the observed defect hidden danger point group with building safety risk, and determining the comprehensive safety risk coefficient of the observed defect hidden danger point group in combination with the risk coefficients of building safety risks in different areas within the building area;

[0104] S42: determining a risk group of the observed defect potential point group based on the comprehensive safety risk coefficient of the observed defect potential point group, and determining the safety impact coefficient of the risk group through the comprehensive safety risk coefficient of the risk group and the defect probability;

[0105] S43 determines the security risk coefficient of the area through the security impact coefficients of different risk groups, and determines the network governance plan of the area using the security risk coefficient.

[0106] It should be noted that the above step S41 includes steps S411 to S412, which are specifically:

[0107] S411 determines the concerned hidden danger point group in the observed defect hidden danger point group based on the defect probability of the observed defect hidden danger point group, determines the building area with building safety risk corresponding to the observed defect hidden danger point group based on the impact of the observed defect hidden danger point group on building safety, and directly determines that a network relay device needs to be set up when the total building area with building safety risk corresponding to the concerned hidden danger point group does not meet the requirements, and enters step S412 when the total building area with building safety risk corresponding to the concerned hidden danger point group meets the requirements;

[0108] S412 determines the building area with building safety risks corresponding to the observed defect hidden danger point group, and determines the comprehensive safety risk coefficient of the observed defect hidden danger point group in combination with the risk coefficients of building safety risks in different areas within the building area. When there is a group of hidden danger points of concern whose comprehensive safety risk coefficient does not meet the requirements, it is directly determined that a network relay device needs to be set up. When there is a group of hidden danger points of concern whose comprehensive safety risk coefficient does not meet the requirements, proceed to step S42.

[0109] It should be further explained that the above step S42 includes steps S421 and S422, which are specifically:

[0110] S421 determines that there is no risk group in the observed defect hidden danger point group based on the comprehensive safety risk coefficient of the observed defect hidden danger point group, then determines that there is no need to set up a network relay device, when there is a risk group in the observed defect hidden danger point group, then directly proceeds to step S422;

[0111] S422 determines the total defect probability of the risk group based on the defect probability of different risk groups. When the total defect probability of the risk group does not meet the requirements, it is determined that a network relay device needs to be set. When the total defect probability of the risk group meets the requirements, it directly proceeds to step S423;

[0112] S423 determines the safety impact coefficient of the risk group through the comprehensive safety risk coefficient and defect probability of the risk group. When there is a risk group whose safety impact coefficient does not meet the requirements, it is determined that a network relay device needs to be set up. If and only if there is no risk group whose safety impact coefficient does not meet the requirements, directly enter step S43.

[0113] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device, equipment, and non-volatile computer storage medium embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0114] The above is a description of a specific embodiment of the present specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0115] The above description is only one or more embodiments of this specification and is not intended to limit this specification. For those skilled in the art, one or more embodiments of this specification may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of one or more embodiments of this specification shall be included in the scope of the claims of this specification.

Claims

1. A treatment method, characterized in that: Specifically include: Divide the smart space based on the construction site into multiple areas, identify the IoT devices for observing quality risk points in different areas, and determine the network anomaly probability of the observation data of different IoT devices and pay attention to abnormal devices through the analysis results of the observation data of different IoT devices; Determine the observation equipment combination of the quality potential risk point when the abnormalities of different concerned abnormal equipment occur, and determine the observation reliability and observation defect potential risk points of different quality potential risk points in the area based on the analysis results of the observation data of the quality potential risk point of the observation equipment combination and the probability of occurrence of network abnormalities of the observation equipment combination; Based on the types of the observed defect potential points, determining the probability of occurrence of quality defects at different observed defect potential points; Based on the observed defect hidden danger points, multiple observed defect hidden danger point groups are generated, and the impact on building safety when quality defects occur at the observed defect hidden danger points in different observed defect hidden danger point groups at the same time is determined, and the network governance plan for the area is outputted using the impact on building safety; The method for determining the network anomaly probability of the observation data of the observed IoT device is: Based on the analysis results of the observation data of the observed IoT device, the number of times the observation data of the observed IoT device has network anomalies is determined, and the number is used as the number of network anomalies. According to different numbers of network anomalies of the observed IoT devices, the proportion of dates with network anomalies is determined, and based on the date proportion, the abnormal date ratio coefficient of the observation data of the observed IoT device is determined; Determine the daily average number of network anomalies based on the number of network anomalies that occur on different dates with the number of network anomalies, and determine the daily average network anomaly coefficient of the observation data of the observed Internet of Things device based on the daily average number of network anomalies; Determine the network anomaly probability of the observation data of the observation Internet of Things device by multiplying the anomaly date ratio coefficient of the observation data of the observation Internet of Things device by the daily average network anomaly coefficient; The concerned abnormal device is an observed IoT device whose network abnormality probability of observed data does not meet the requirements; The observation combination of the quality potential risk points is an observation combination of quality observation points constructed by observation Internet of Things devices that do not have network abnormalities when one or more concerned abnormal devices have network abnormalities; The method for determining the observation reliability of the quality risk point is: Determine, based on the analysis result of the observation data of the quality hidden danger point of the observation equipment combination, the recognition accuracy rate of the quality hidden danger of the quality hidden danger point based on the observation data of the observation equipment combination; Determine the recognition reliability coefficients of different observation device combinations based on the recognition accuracy and the product of the network abnormality probability of the concerned abnormal device having a network failure corresponding to the observation device combination; Determining the observation reliability of the quality risk point through the identification reliability coefficients of different observation equipment combinations; The observed defect potential point is a quality potential point whose identification reliability is not within a preset reliability interval.

2. The treatment method according to claim 1, characterized in that: The smart space based on the construction site is divided into multiple areas, including: The construction site is divided into a plurality of areas using a preset area.

3. The treatment method according to claim 1, characterized in that: The quality hidden danger points are determined according to the types of construction projects in the area, and specifically determined according to the construction points in the construction project types where quality hidden dangers have occurred.

4. The treatment method according to claim 1, characterized in that: The observation Internet of Things device determines the Internet of Things device that is associated with the quality defects of the quality risk point based on the observation data.

5. The treatment method according to claim 1, characterized in that: The observation reliability of the quality risk point is determined based on the weighted sum of the identification reliability coefficients of different observation equipment combinations.

6. The treatment method according to claim 1, characterized in that: The network management solution includes setting up a network relay device and not setting up a network relay device.

Images