A method and system for fusion of tripartite management data based on artificial intelligence

Abstract

The present invention provides a method and system for fusion of tripartite management data based on artificial intelligence, which belongs to the field of data processing technology, and specifically includes: determining the hidden danger historical identification data of different Internet of Things supervision devices based on the observation results of safety hazards, and using the hidden danger historical identification data and a preset AI model to determine the identification reliability coefficients of different Internet of Things supervision devices when performing safety hazard identification processing, based on the setting data of Internet of Things supervision devices of different types of safety hazard points at the construction site, the associated safety hazards of the safety hazard points, and combining the identification reliability coefficients of different Internet of Things supervision devices to determine whether it is necessary to issue a safety supervision hidden danger reminder, thereby ensuring the reliability of construction safety supervision.

Description

Technical Field

[0001] The present invention belongs to the field of data processing technology, and in particular to a method and system for fusion of tripartite management data based on artificial intelligence. Background Art

[0002] Construction safety supervision during the construction process involves multiple roles such as safety supervision departments, construction parties, and project parties. Therefore, how to achieve data integration of safety supervision of the three parties' data and improve the reliability of safety hazard supervision has become a technical problem that needs to be solved urgently. Specifically, in the invention patent application CN201911397791.5 "A safety hazard prediction system based on mathematical model", the setting of the information sending module can realize the intelligent linkage of engineering project construction, effectively solve the problem of information islands, and make construction management perceptible, decision-making, and predictable. However, the existing technical solutions have the following technical problems:

[0003] The existing technical solutions ignore the output of differentiated safety hazard supervision and reminder information based on the analysis results of safety hazards in multiple dimensions by a third party. Specifically, for example, the safety supervision department, as a third party in the construction, not only conducts safety supervision on a single project, but also conducts safety supervision on all construction projects within a certain supervision area. Therefore, if the third-party safety supervision data cannot be used to generate differentiated safety hazard supervision and reminder information for the construction site, the reliability of safety hazard supervision cannot be guaranteed.

[0004] In response to the above technical problems, the present invention provides a method and system for three-party management data fusion based on artificial intelligence. Summary of the invention

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

[0006] According to one aspect of the present invention, a method for fusion of tripartite management data based on artificial intelligence is provided.

[0007] A method for fusion of tripartite management data based on artificial intelligence, specifically comprising:

[0008] S1 uses the analysis results of the third-party data to determine the observation results of safety hazards at different construction sites, and determines the reliable supervision sites among the construction sites through the observation results and the occurrence data of safety accidents;

[0009] S2 obtains the similarity of the distribution data of the safety risk points of different construction sites and the reliable supervision site, and combines the similarity of the different safety risk points with the IoT supervision equipment of the reliable supervision site, and when it is determined that there are no safety supervision risks at the construction site, proceeds to the next step;

[0010] S3 determines the hidden danger historical identification data of different IoT monitoring devices based on the observation results of the hidden dangers, and uses the hidden danger historical identification data and a preset AI model to determine the identification reliability coefficients of different IoT monitoring devices when performing the hidden danger identification process;

[0011] S4 determines whether it is necessary to issue a safety supervision hazard reminder based on the setting data of the Internet of Things monitoring equipment of different types of safety hazard points at the construction site, the associated safety hazards of the safety hazard points, and the identification reliability coefficients of different Internet of Things monitoring equipment.

[0012] The beneficial effects of the present invention are:

[0013] Based on the similarity in the distribution data of safety risk points of reliably supervised construction sites and the similarity in the Internet of Things supervision equipment, it is determined that there are no safety supervision hazards at the construction site. This takes into account both the differences in safety risks caused by the similarity in the distribution of safety risk points at reliably supervised construction sites, and the differences in the supervision reliability of safety risks caused by the differences in the similarity in the Internet of Things supervision equipment. It realizes the determination of the similarity coefficient between the construction site and the reliable supervision reliability from the supervision reliability and the probability of occurrence of safety risks, thereby realizing the screening of construction sites with poor safety supervision reliability, and ensuring the safety and reliability of construction.

[0014] Whether it is necessary to issue a safety supervision hazard reminder is determined by utilizing the setting data of IoT supervision devices at different types of safety hazard points, the associated safety hazards at the safety hazard points, and the identification reliability coefficients of different IoT supervision devices. This determines the real-time safety risk supervision reliability status of the construction site from two perspectives: the identification reliability of IoT supervision devices at safety hazard points and the associated safety hazards. This ensures the reliability of construction sites where the identification reliability of construction safety risks is insufficient, and also lays a foundation for improving construction safety.

[0015] A further technical solution is that the third-party data includes data of an institution, including a safety supervision department, that is responsible for the safety management of multiple construction projects in a certain area.

[0016] A further technical solution is that the observation result of the potential safety hazard includes the number of identifications of different types of potential safety hazards.

[0017] A further technical solution is that the potential safety hazards include falling from height, being hit by objects, mechanical injuries, electric shock, collapse, fire and explosion, poisoning and suffocation.

[0018] A further technical solution is that the safety accident occurrence data includes the number of occurrences of different types of safety accidents.

[0019] A further technical solution is to determine whether it is necessary to issue a safety supervision hazard reminder, including:

[0020] Based on the setting data of the IoT monitoring devices of different types of potential safety hazards at the construction site, the setting types of the IoT monitoring devices of different types of potential safety hazards are determined, and the monitoring reliability coefficients of different types of potential safety hazards are determined by weighting the identification reliability coefficients of the IoT monitoring devices of different setting types;

[0021] Determine the number of associated safety hazard types of the safety hazard point by using associated safety hazards of different types of safety hazard points, and determine the safety hazard coefficient of the safety hazard point by using the number of associated safety hazard types;

[0022] The supervision risk coefficient of the construction site is determined based on the safety hazard coefficients and supervision reliability coefficients of different safety hazard points, and the supervision risk coefficient is used to determine whether it is necessary to issue a safety supervision hazard reminder.

[0023] A further technical solution is that, when the supervision risk coefficient of the construction site does not meet the requirements, it is determined that the construction site needs to issue a safety supervision hazard reminder.

[0024] A further technical solution is that the method for determining the supervision risk coefficient of the construction site is:

[0025] Determine the risk coefficients of different potential safety points by dividing the potential safety coefficients of different potential safety points by the divisors of the supervision reliability coefficients, and determine the risk potential safety points among the potential safety points by the potential safety coefficients;

[0026] The supervision risk coefficient of the construction site is determined based on the number of risk potential points.

[0027] In a second aspect, the present invention provides a computer system comprising: a memory and a processor connected in communication, and a computer program stored in the memory and capable of running on the processor, characterized in that: when the processor runs the computer program, it executes the above-mentioned artificial intelligence-based three-party management data fusion method.

[0028] 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.

[0029] 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

[0030] 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;

[0031] Figure 1 It is a framework diagram of a tripartite management data fusion method based on artificial intelligence;

[0032] Figure 2 It is a flowchart of a method for reliable supervision of a construction site determination;

[0033] Figure 3 is a flow chart of a method for determining whether a safety supervision hazard reminder needs to be issued;

[0034] Figure 4 It is a framework diagram of a computer system. DETAILED DESCRIPTION

[0035] 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.

[0036] As a third party in construction, the safety supervision department not only conducts safety supervision on a single project, but also supervises the safety of all construction projects within a certain supervision area. Therefore, it is necessary to combine the safety supervision data of a third party to generate differentiated supervision reminder information on safety hazards for construction sites to improve the reliability of supervision processing.

[0037] Reliably supervised construction sites: Construction sites where no safety accidents have occurred will be regarded as reliably supervised construction sites.

[0038] Safety supervision hazards at construction sites: Determined by the number of distribution of safety risk points and the IoT supervision devices corresponding to the safety risk points. Specifically, it is determined based on the number of safety risk points where the IoT supervision devices are inconsistent with the settings of reliable supervision sites. For example, when the number of safety risk points where the IoT supervision devices are inconsistent with the settings of reliable supervision sites is 5, the safety supervision hazard is 0.5.

[0039] The recognition reliability coefficient of the Internet of Things supervision device when performing the safety hazard identification process: taking the historical number of hazard identifications of the Internet of Things supervision device and the identification processing time of different historical hazard identification times as input, the recognition reliability coefficient of the Internet of Things supervision device when performing the safety hazard identification process is determined using the output result of the preset AI model, wherein the preset AI model includes convolutional neural network, recurrent neural network, deep neural network, support vector machine, decision tree, and KNN.

[0040] Determine whether it is necessary to issue a safety supervision hidden danger reminder: determine the supervision risk coefficient of the construction site based on the weights of the supervision reliability coefficients of different safety hidden danger points, and use the supervision risk coefficient to determine whether it is necessary to issue a safety supervision hidden danger reminder. Example

[0041] To solve the above problems, according to one aspect of the present invention, Figure 1 As shown, a method for fusion of tripartite management data based on artificial intelligence is provided, which specifically includes:

[0042] S1 uses the analysis results of the third-party data to determine the observation results of safety hazards at different construction sites, and determines the reliable supervision sites among the construction sites through the observation results and the occurrence data of safety accidents;

[0043] Furthermore, the third-party data includes data of institutions responsible for safety management of multiple construction projects in a certain area, including safety supervision departments.

[0044] Specifically, the observation result of the potential safety hazard includes the number of identifications of different types of potential safety hazards.

[0045] It is understandable that the safety hazards include falling from heights, being hit by objects, mechanical injuries, electric shock, collapse, fire and explosion, poisoning and suffocation.

[0046] Furthermore, the safety accident occurrence data includes the number of occurrences of different types of safety accidents.

[0047] In addition, it should be noted that Figure 2 As shown, the method for determining the reliable supervision site in the construction site is:

[0048] Based on the occurrence data of the safety accidents, determine the historical occurrence times of different types of safety accidents, and determine the accident occurrence abnormality coefficient of the construction site according to the total historical occurrence times of safety accidents;

[0049] Determining the number of times different types of safety hazards of the construction site are identified using the observation results of the safety hazards, and determining the identification effectiveness coefficient of the construction site according to the total number of times the safety hazards are identified;

[0050] The reliability of identifying potential safety hazards at the construction site is determined by using the identification validity coefficient and the accident occurrence abnormality coefficient, and whether the construction site is a reliable supervision site is determined using the identification reliability.

[0051] Furthermore, the accident occurrence abnormality coefficient of the construction site is determined according to a preset abnormality coefficient corresponding to the total number of historical occurrences of safety accidents at the construction site.

[0052] It should also be noted that the reliability of identifying the potential safety hazard at the construction site is determined based on the weighted sum of the identification effectiveness coefficient and the accident occurrence abnormality coefficient.

[0053] It can be understood that when the identification reliability of the construction site is not within a preset reliability interval, it is determined that the construction site is not a reliable supervision site.

[0054] In another embodiment, the method for determining the reliable supervision site in the construction site is:

[0055] Based on the occurrence data of the safety accidents, determine the historical number of occurrences of different types of safety accidents, and determine the total number of historical occurrences of the safety accidents according to the historical number of occurrences of different types of safety accidents;

[0056] Determine the number of times different types of safety hazards at the construction site are identified using the observation results of the safety hazards, and determine the total number of times the safety hazards are identified based on the number of times different types of safety hazards are identified;

[0057] The total number of historical occurrences of the safety accidents and the total number of identifications of safety hazards are taken as input quantities, and a preset mapping model is used to determine the reliability of identification of safety hazards at the construction site, and the identification reliability is used to determine whether the construction site is a reliably supervised site.

[0058] S2 obtains the similarity of the distribution data of the safety risk points of different construction sites and the reliable supervision site, and combines the similarity of the different safety risk points with the IoT supervision equipment of the reliable supervision site, and when it is determined that there are no safety supervision risks at the construction site, proceeds to the next step;

[0059] Furthermore, the similarity of the distribution data of the safety risk points of the reliable supervision construction site includes the similarity of the distribution positions of different types of safety risk points and the similarity of the number of safety risk points.

[0060] Specifically, the similarities of the Internet of Things supervision devices include similarities of types of Internet of Things supervision devices corresponding to different types of security risk points and similarities of setting locations.

[0061] Furthermore, it is determined that there are no safety supervision risks at the construction site, including:

[0062] Based on the similarity of the distribution data of the safety risk points of the construction site and the reliable supervision site, determine the number of deviations between the distribution positions of the safety risk points of the construction site and the reliable supervision site, and use it as the number of risk point deviations;

[0063] Determine the number of safety risk points where IoT monitoring equipment is insufficient by comparing different safety risk points with the IoT monitoring equipment of the reliable monitoring site, and use it as the number of risk point monitoring deviations;

[0064] The weight value of the similarity coefficient with the reliable supervision site is determined by the ratio of the number of risk point deviations and the ratio of the number of risk point supervision deviations, and the effectiveness of the supervision of the safety risks of the construction site is determined in combination with the identification reliability of different reliable supervision sites. The effectiveness of the supervision of the safety risks is used to determine whether there are safety supervision risks at the construction site.

[0065] Specifically, when the supervision effectiveness of the safety risk of the construction site is not within a preset effectiveness range, it is determined that there are safety supervision risks at the construction site.

[0066] It is understandable that when there are safety supervision hazards at the construction site, it is determined that a safety supervision hazard reminder needs to be issued.

[0067] It should also be noted that there are no safety supervision risks in the construction site, including:

[0068] Based on the similarity of the distribution data of the safety risk points of the construction site and the reliable supervision site, the number of deviations between the distribution positions of the safety risk points of the construction site and the reliable supervision site is determined, and the deviation is used as the number of risk point deviations, and the similarity coefficient of the risk point distribution with the reliable supervision site is determined according to the number of risk point deviations;

[0069] Determine the number of safety risk points where IoT supervision equipment is in short supply through the similarities between different safety risk points and the IoT supervision equipment of the reliable supervision site, and use it as the number of risk point supervision deviations, and determine the risk point supervision similarity coefficient with the reliable supervision site based on the risk point deviation supervision number;

[0070] The weight value of the similarity coefficient with the reliable supervision site is determined by the risk point distribution similarity coefficient and the risk point supervision similarity coefficient, and the effectiveness of the supervision of the safety risks of the construction site is determined in combination with the identification reliability of different reliable supervision sites. The effectiveness of the supervision of the safety risks is used to determine whether there are safety supervision hazards at the construction site.

[0071] S3 determines the hidden danger historical identification data of different IoT monitoring devices based on the observation results of the hidden dangers, and uses the hidden danger historical identification data and a preset AI model to determine the identification reliability coefficients of different IoT monitoring devices when performing the hidden danger identification process;

[0072] Furthermore, the hidden danger historical identification data of the Internet of Things supervision device includes the number of hidden danger historical identifications of the Internet of Things supervision device and the identification processing time of different hidden danger historical identification times.

[0073] Specifically, the identification processing time is determined according to the interval between the occurrence time and the identification time of the safety hazard under different historical hazard identification times.

[0074] It should be noted that the method for determining the identification reliability coefficient during the safety hazard identification process is:

[0075] The number of historical hidden danger identifications of the Internet of Things supervision device and the identification processing time of different historical hidden danger identification times are used as input quantities, and the output result of a preset AI model is used to determine the identification reliability coefficient of the Internet of Things supervision device when performing the safety hidden danger identification process.

[0076] Furthermore, the value range of the identification reliability coefficient of the Internet of Things supervision device when performing the safety hazard identification process is between 0 and 1, wherein the higher the identification reliability coefficient of the Internet of Things supervision device when performing the safety hazard identification process, the higher the identification reliability of the Internet of Things supervision device when performing the safety hazard identification process.

[0077] It should be noted that the preset AI models include convolutional neural networks, recurrent neural networks, deep neural networks, support vector machines, decision trees, and KNN.

[0078] S4 determines whether it is necessary to issue a safety supervision hazard reminder based on the setting data of the Internet of Things monitoring equipment of different types of safety hazard points at the construction site, the associated safety hazards of the safety hazard points, and the identification reliability coefficients of different Internet of Things monitoring equipment.

[0079] Specifically, Figure 3 As shown, determine whether it is necessary to issue a safety supervision hidden danger reminder, including:

[0080] Based on the setting data of the IoT monitoring devices of different types of potential safety hazards at the construction site, the setting types of the IoT monitoring devices of different types of potential safety hazards are determined, and the monitoring reliability coefficients of different types of potential safety hazards are determined by weighting the identification reliability coefficients of the IoT monitoring devices of different setting types;

[0081] Determine the number of associated safety hazard types of the safety hazard point by using associated safety hazards of different types of safety hazard points, and determine the safety hazard coefficient of the safety hazard point by using the number of associated safety hazard types;

[0082] The supervision risk coefficient of the construction site is determined based on the safety hazard coefficients and supervision reliability coefficients of different safety hazard points, and the supervision risk coefficient is used to determine whether it is necessary to issue a safety supervision hazard reminder.

[0083] Furthermore, when the supervision risk coefficient of the construction site does not meet the requirements, it is determined that the construction site needs to issue a safety supervision hazard reminder.

[0084] It can be understood that the method for determining the supervision risk coefficient of the construction site is:

[0085] Determine the risk coefficients of different potential safety points by dividing the potential safety coefficients of different potential safety points by the divisors of the supervision reliability coefficients, and determine the risk potential safety points among the potential safety points by the potential safety coefficients;

[0086] The supervision risk coefficient of the construction site is determined based on the number of risk potential points. Example

[0087] Second, as Figure 4 As shown, the present invention provides a computer system, comprising: a memory and a processor connected in communication, and a computer program stored in the memory and capable of running on the processor, characterized in that: when the processor runs the computer program, it executes the above-mentioned artificial intelligence-based three-party management data fusion method.

[0088] Specifically, the determination of the reliable supervision site of the construction site includes steps S11-S13, which are specifically:

[0089] S11 determines the historical occurrence times of different types of safety accidents based on the occurrence data of the safety accidents, and determines the accident occurrence abnormality coefficient of the construction site in combination with the accident losses of different types of safety accidents;

[0090] S12: using the observation results of the safety hazards to determine the number of times different types of safety hazards of the construction site are identified, and combining the types of safety accidents associated with the safety hazards to determine the identification effectiveness coefficient of the construction site;

[0091] S13 determines the reliability of identifying the potential safety hazard of the construction site by the average value of the identification validity coefficient and the accident occurrence abnormality coefficient, and uses the identification reliability to determine whether the construction site is a reliable supervision site.

[0092] Specifically, the above step S11 also includes steps S111 to S113, which are specifically:

[0093] S111 determines whether a safety accident with an accident loss that does not meet the requirements has occurred at the construction site based on the occurrence data of the safety accident. If a safety accident with an accident loss that does not meet the requirements has occurred at the construction site, it is determined that the construction site does not belong to a reliable supervision site. If a safety accident with an accident loss that does not meet the requirements has occurred at the construction site, the process directly proceeds to step S112;

[0094] S112 determines the historical occurrence times of different types of safety accidents based on the occurrence data of the safety accidents. When the total historical occurrence times of the safety accidents at the construction site does not meet the requirement, it is determined that the construction site does not belong to a reliable supervision site. When the total historical occurrence times of the safety accidents at the construction site meets the requirement, it directly proceeds to step S113.

[0095] S113 determines the accident occurrence abnormality coefficient of the construction site based on the historical number of occurrences of different types of safety accidents and the accident losses of different types of safety accidents, and proceeds to step S12 if and only if the accident occurrence abnormality coefficient of the construction site meets the requirements. When the accident occurrence abnormality coefficient does not meet the requirements, it is determined that the construction site is not a reliably supervised site.

[0096] Optionally, the above step S12 also includes steps S121 to S123, which are specifically:

[0097] S121 determines the number of identifications of different types of safety hazards of the construction site using the observation results of the safety hazards. When the total number of identifications of the safety hazards of the construction site is less than a preset number, it is directly determined that the construction site does not belong to a reliable supervision site. When the total number of identifications of the safety hazards of the construction site is not less than the preset number, the process proceeds to step S122.

[0098] S122 determines the identification processing time of different identification times based on the identification times of different types of potential safety hazards. When there is no identification number with an identification processing time shorter than the preset processing time, it is directly determined that the construction site does not belong to a reliable supervision site. When there is an identification number with an identification processing time shorter than the preset processing time, the process proceeds to step S123.

[0099] S123 determines the identification effectiveness coefficient of the construction site based on the number of identifications of different types of safety hazards at the construction site, the types of safety accidents associated with the safety hazards, and the identification processing time of different identification times.

[0100] Optionally, determining that there are no safety supervision risks at the construction site specifically includes steps S31-S33, specifically:

[0101] S31 determines the number of deviations in the distribution positions of the safety risk points of the construction site and the reliable supervision site based on the similarity of the distribution data of the safety risk points of the construction site and the reliable supervision site, and uses it as the number of risk point deviations, and determines the risk point distribution similarity coefficient with the reliable supervision site according to the number of risk point deviations;

[0102] S32 determines the number of safety risk points where IoT supervision equipment is in short supply through the similarity between different safety risk points and the IoT supervision equipment of the reliable supervision site, and uses it as the number of risk point supervision deviations, and determines the risk point supervision similarity coefficient with the reliable supervision site according to the risk point deviation supervision number;

[0103] S33 determines the similarity coefficient with the reliable supervision site through the risk point distribution similarity coefficient and the risk point supervision similarity coefficient, determines the similar reference supervision site in the reliable supervision site using the similarity coefficient, and determines the effectiveness of the supervision of the safety risk of the construction site through the recognition reliability of different similar supervision sites, and determines whether there are safety supervision hazards at the construction site through the effectiveness of the supervision of the safety risks.

[0104] Optionally, before entering step S32, it is also necessary to use the risk point distribution similarity coefficient to determine whether there are similarly distributed construction sites among the reliably supervised construction sites. When there are similarly distributed construction sites, proceed to the next step. When there are no similarly distributed construction sites, it is directly determined that there are no safety supervision hazards at the construction site.

[0105] Optionally, in step S22, only the number of risk point supervision deviations and the risk point supervision similarity coefficients between the safety risk points of the construction site with similar distributions and the construction site need to be determined.

[0106] Optionally, before entering step S33, it is also necessary to determine whether there are similar distribution sites whose risk point supervision similarity coefficient meets the requirements. When there are similar distribution sites whose risk point supervision similarity coefficient meets the requirements, go to step S33. When there are no similar distribution sites whose risk point supervision similarity coefficient meets the requirements, it is directly determined that the construction site has safety supervision risks.

[0107] Optionally, the above step S33 also includes steps S331-S333, specifically:

[0108] S331 determines the similarity coefficient with the reliable supervision site through the risk point distribution similarity coefficient and the risk point supervision similarity coefficient. When there is no reliable supervision site with a similarity coefficient that meets the requirements, it is directly determined that the construction site has safety supervision hazards. When there is a reliable supervision site with a similarity coefficient that meets the requirements, enter step S332;

[0109] S332 determines the similar reference supervision site in the reliable supervision site by using the similarity coefficient. When the average value of the identification reliability of the similar reference supervision site does not meet the requirement, it is directly determined that there is a safety supervision hazard in the construction site. When the average value of the identification reliability of the similar reference supervision site meets the requirement, enter step S333;

[0110] S333 determines the effectiveness of the supervision of the safety risks of the construction site through the recognition reliability and similarity coefficient of different similar supervision sites, and determines whether there are safety supervision hazards at the construction site through the effectiveness of the supervision of the safety risks.

[0111] Optionally, determining whether it is necessary to issue a safety supervision potential hazard reminder includes steps S41-S43, specifically:

[0112] S41 determines the setting types of the IoT monitoring devices for different types of potential safety hazards at the construction site based on the setting data of the IoT monitoring devices for different types of potential safety hazards, and determines the monitoring reliability coefficients of different types of potential safety hazards based on the weights of the identification reliability coefficients of the IoT monitoring devices for different setting types;

[0113] S42 determines the regulatory risk potential point among the safety potential points according to the regulatory reliability coefficient, and determines the number of associated safety potential types of the regulatory risk potential point through the associated safety potential of the regulatory risk potential point, and determines the safety potential coefficient of the regulatory risk potential point by using the number of associated safety potential types;

[0114] S43 determines the risk factor coefficients of different regulatory risk potential points based on the safety risk coefficients and regulatory reliability coefficients of different regulatory risk potential points, determines the regulatory risk coefficient of the construction site according to the risk factor coefficients of different regulatory risk potential points, and uses the regulatory risk coefficient to determine whether it is necessary to issue a safety regulatory hazard reminder.

[0115] Optionally, before entering step S42, it is also necessary to determine whether the supervision reliability coefficients of different types of safety hazard points all meet the requirements. When the supervision reliability coefficients of different types of safety hazard points all meet the requirements, it can be directly determined that there is no need to issue a safety supervision hazard reminder. If and only if there is a safety hazard point whose supervision reliability coefficient does not meet the requirements, enter step S42.

[0116] Optionally, the above step S42 includes steps S421-S423, specifically:

[0117] S421 determines the regulatory risk potential points among the safety potential points according to the regulatory reliability coefficient. When the number of regulatory risk potential points does not meet the requirement, it is directly determined that a safety regulatory potential warning needs to be issued. When the number of regulatory risk potential points meets the requirement, the process proceeds to step S422;

[0118] S422 determines the number of safety hazard types associated with the regulatory risk potential point through the safety hazards associated with the regulatory risk potential point. When the total number of safety hazard types associated with the regulatory risk potential point does not meet the requirement, it is directly determined that a safety regulatory hazard reminder needs to be issued. When the total number of safety hazard types associated with the regulatory risk potential point meets the requirement, the process proceeds to step S423;

[0119] S423 uses the number of associated safety hazard types to determine the safety hazard coefficient of the regulatory risk hazard point. When the number of regulatory risk hazard points whose safety hazard coefficient does not meet the requirement does not meet the requirement, it is directly determined that a safety regulatory hazard reminder needs to be issued. When the number of regulatory risk hazard points whose safety hazard coefficient does not meet the requirement meets the requirement, step S43 is entered.

[0120] It should be noted that before determining the regulatory risk coefficient in the above step S43, when the number of regulatory risk potential points whose risk coefficients do not meet the requirements is greater than the preset number of risk potential points, it is directly determined that a safety regulatory hazard reminder needs to be issued; when the number of regulatory risk potential points whose risk coefficients do not meet the requirements is not greater than the preset number of risk potential points, the regulatory risk coefficient is determined.

[0121] 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.

[0122] The above is a description of a specific embodiment of the 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.

[0123] 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 method for fusion of tripartite management data based on artificial intelligence, characterized in that: Specifically include: Utilize the analysis results of third-party data to determine the observation results of safety hazards at different construction sites, and determine reliable supervision sites among the construction sites through the observation results and the occurrence data of safety accidents; Obtaining the similarity of the distribution data of the safety risk points of different construction sites and the reliable supervision site, and combining the similarity of the different safety risk points with the IoT supervision equipment of the reliable supervision site, when it is determined that there are no safety supervision risks at the construction site, proceed to the next step; Determine the hidden danger historical identification data of different IoT monitoring devices based on the observation results of the hidden dangers, and use the hidden danger historical identification data and a preset AI model to determine the identification reliability coefficients of different IoT monitoring devices when performing the hidden danger identification process; Based on the setting data of the IoT monitoring devices of different types of potential safety hazards at the construction site, the associated potential safety hazards at the potential safety hazards, and combined with the identification reliability coefficients of different IoT monitoring devices, it is determined whether a potential safety hazard reminder needs to be issued; Determine whether it is necessary to issue a safety supervision hazard reminder, including: Based on the setting data of the IoT monitoring devices of different types of potential safety hazards at the construction site, the setting types of the IoT monitoring devices of different types of potential safety hazards are determined, and the monitoring reliability coefficients of different types of potential safety hazards are determined by weighting the identification reliability coefficients of the IoT monitoring devices of different setting types; Determine the number of associated safety hazard types of the safety hazard point by using associated safety hazards of different safety hazard points, and determine the safety hazard coefficient of the safety hazard point by using the number of associated safety hazard types; Determine the supervision risk coefficient of the construction site based on the safety hazard coefficients and supervision reliability coefficients of different safety hazard points, and use the supervision risk coefficient to determine whether it is necessary to issue a safety supervision hazard reminder; When the supervision risk coefficient of the construction site does not meet the requirements, it is determined that the construction site needs to issue a safety supervision hazard reminder.

2. The method for fusion of data of three parties based on artificial intelligence as claimed in claim 1, characterized in that: The third-party data includes data of institutions responsible for safety management of multiple construction projects in a certain area, including safety supervision departments.

3. The method for fusion of data of three parties based on artificial intelligence as claimed in claim 1, characterized in that: The safety hazard observation results include the identification times of different types of safety hazards.

4. The method for fusion of data of three parties based on artificial intelligence as claimed in claim 1, characterized in that: The safety hazards mentioned include falling from heights, being hit by objects, mechanical injuries, electric shock, collapse, fire and explosion, poisoning and suffocation.

5. The method for fusion of data of three parties based on artificial intelligence as claimed in claim 1, characterized in that: The method for determining the reliable supervision site in the construction site is: Based on the occurrence data of the safety accidents, determine the historical occurrence times of different types of safety accidents, and determine the accident occurrence abnormality coefficient of the construction site according to the total historical occurrence times of safety accidents; Determining the number of times different types of safety hazards of the construction site are identified using the observation results of the safety hazards, and determining the identification effectiveness coefficient of the construction site according to the total number of times the safety hazards are identified; The reliability of identifying potential safety hazards at the construction site is determined by using the identification validity coefficient and the accident occurrence abnormality coefficient, and whether the construction site is a reliable supervision site is determined using the identification reliability.

6. The method for fusion of data of three parties based on artificial intelligence as claimed in claim 5, characterized in that: The accident occurrence abnormality coefficient of the construction site is determined according to the total number of historical occurrences of safety accidents at the construction site corresponding to the preset abnormality coefficient.

7. The method for fusion of data of three parties based on artificial intelligence as claimed in claim 1, characterized in that: The similarity of the distribution data of the safety risk points of the reliable supervision construction site includes the similarity of the distribution positions of different types of safety risk points and the similarity of the number of safety risk points.

8. The method for fusion of data based on artificial intelligence three-party management as claimed in claim 1, characterized in that: The similarities of the Internet of Things supervision devices include similarities of the types of Internet of Things supervision devices corresponding to different types of security risk points and similarities of the setting locations.

9. The method for fusion of data of three parties based on artificial intelligence as claimed in claim 1, characterized in that: Determine that there are no safety supervision risks at the construction site, including: Based on the similarity of the distribution data of the safety risk points of the construction site and the reliable supervision site, determine the number of deviations between the distribution positions of the safety risk points of the construction site and the reliable supervision site, and use it as the number of risk point deviations; Determine the number of safety risk points where IoT monitoring equipment is insufficient by comparing different safety risk points with the IoT monitoring equipment of the reliable monitoring site, and use it as the number of risk point monitoring deviations; The weight value of the similarity coefficient with the reliable supervision site is determined by the ratio of the number of risk point deviations and the ratio of the number of risk point supervision deviations, and the effectiveness of the supervision of the safety risks of the construction site is determined in combination with the identification reliability of different reliable supervision sites. The effectiveness of the supervision of the safety risks is used to determine whether there are safety supervision risks at the construction site.

10. A computer system comprising: A memory and a processor connected in communication, and a computer program stored in the memory and capable of running on the processor, characterized in that: when the processor runs the computer program, an artificial intelligence-based three-party management data fusion method as described in any one of claims 1-9 is executed.

Images