Safety hazard early warning method for construction areas

Abstract

The present application proposes a safety hazard early warning method for a construction area, including: for each sub-area in the construction area, obtaining the first real-time risk association information of the sub-area; determining the safety hazard subject in the sub-area that has a preset association relationship with the first real-time risk association information, and obtaining the individual performance characteristics of the safety hazard subject; based on the individual performance characteristics, determining the target correlation between the first real-time risk association information and the safety hazard subject; if the target correlation reaches a first predetermined threshold, setting the first real-time risk association information to the second real-time risk association information; based on the second real-time risk association information and a preset risk value calculation model, determining the risk assessment parameters of the sub-area; if the risk assessment parameters reach a second predetermined threshold, performing risk early warning processing for the sub-area. The technical solution of the present application improves the compatibility and accuracy of risk early warnings at construction sites.

Description

Technical Field

[0001] The present application relates to the field of engineering safety technology, and in particular to a safety hazard early warning method for a construction area. Background Art

[0002] With the development of science and technology, intelligent early warning functions are generally installed at engineering sites in various fields to provide early warnings after safety problems occur at the engineering sites, notify relevant personnel to deal with safety hazards in a timely manner, and reduce engineering losses.

[0003] However, the existing early warning function is limited by the limited accuracy of sensor data collection, imperfect early warning algorithms, and high costs of manual links, which can easily lead to missed reports and false alarms. At the same time, there are many different projects in various fields, involving different key factors such as environment and construction content. The current early warning function is often customized for a certain type of project, with high customization costs and insufficient compatibility, making it difficult to be widely used, resulting in increased project costs.

[0004] Therefore, providing a real-time early warning system that is accurate and can be widely applied to different engineering sites has become a technical problem that needs to be solved urgently. Summary of the invention

[0005] The embodiment of the present application provides a safety hazard warning method for construction areas, which aims to solve the technical problems in the related art that the engineering site warning method is prone to missed reports, false alarms, high customization costs, and insufficient compatibility.

[0006] In a first aspect, an embodiment of the present application provides a safety hazard early warning method for a construction area, comprising:

[0007] For each sub-area within the construction area, first real-time risk association information of the sub-area is obtained, wherein the first real-time risk association information is used to reflect the performance characteristics associated with the sub-area and having an impact on the safety level of the sub-area;

[0008] Determine a safety hazard subject in the sub-area that has a preset association relationship with the first real-time risk association information, and obtain individual performance characteristics of the safety hazard subject, wherein the preset association relationship refers to the correlation between the first real-time risk association information and the safety level of the safety hazard subject;

[0009] Based on the individual performance characteristics, determining a target correlation between the first real-time risk association information and the safety hazard subject, wherein the target correlation is used to reflect the degree of influence of the first real-time risk association information on the safety level of the safety hazard subject;

[0010] If the target correlation degree reaches a first predetermined threshold, setting the first real-time risk correlation information as second real-time risk correlation information;

[0011] Based on the second real-time risk association information and a preset risk value calculation model, determine the risk assessment parameter of the sub-area, wherein the risk assessment parameter is used to reflect the urgency of the security risk to be dealt with by the sub-area, and the risk value calculation model is used to reflect the association relationship between the second real-time risk association information and the risk assessment parameter;

[0012] If the risk assessment parameter reaches a second predetermined threshold, risk warning processing is performed for the sub-region.

[0013] In a second aspect, an embodiment of the present application provides a potential safety hazard warning device for a construction area, comprising:

[0014] A first association information acquisition unit is used to acquire, for each sub-area in the construction area, first real-time risk association information of the sub-area, wherein the first real-time risk association information is used to reflect the performance characteristics associated with the sub-area and having an impact on the safety level of the sub-area;

[0015] a hidden danger subject determination unit, configured to determine a hidden danger subject in the sub-area that has a preset association relationship with the first real-time risk association information, wherein the preset association relationship refers to a correlation between the first real-time risk association information and a safety level of the hidden danger subject;

[0016] An individual performance characteristic acquisition unit, used to acquire the individual performance characteristics of the potential safety hazard subject;

[0017] a target correlation determination unit, configured to determine a target correlation between the first real-time risk correlation information and the safety hazard subject based on the individual performance characteristics, wherein the target correlation is used to reflect the degree of influence of the first real-time risk correlation information on the safety level of the safety hazard subject;

[0018] A second association information acquisition unit, configured to set the first real-time risk association information as second real-time risk association information if the target association degree reaches a first predetermined threshold;

[0019] a risk assessment parameter determination unit, configured to determine the risk assessment parameter of the sub-area based on the second real-time risk association information and a preset risk value calculation model, wherein the risk assessment parameter is used to reflect the urgency of the security risk to be dealt with by the sub-area, and the risk value calculation model is used to reflect the association relationship between the second real-time risk association information and the risk assessment parameter;

[0020] The risk warning unit is used to perform risk warning processing for the sub-area if the risk assessment parameter reaches a second predetermined threshold.

[0021] In a third aspect, an embodiment of the present application provides a computer device, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are configured to execute the method described in the first aspect above.

[0022] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium storing computer-executable instructions, wherein the computer-executable instructions are used to execute the method described in the first aspect above.

[0023] The above technical solution aims at the technical problems that the engineering site early warning method in the related technology is prone to omissions, false alarms, high customization cost and insufficient compatibility. In order to maximize the accuracy of the real-time early warning of the construction site, a separate real-time early warning judgment is made for each sub-area in the construction area. In this judgment process, the real-time risk-related information related to the safety of the sub-area is screened through the performance of the safety hazard subject, and the screened part of the real-time risk-related information that has sufficient influence on the safety of the sub-area is input into the preset risk value calculation model, so that it outputs the risk assessment parameter as the final judgment basis for whether to perform the risk early warning processing. This technical solution is compatible with various types of construction sites. It only needs to obtain the real-time risk-related information of a certain construction site to accurately judge whether each sub-area in the construction site needs an early warning, which improves the compatibility of the risk early warning of the construction site and reduces the cost of the risk early warning of the construction site. At the same time, the real-time risk-related information related to the safety of the sub-area is screened through the performance of the safety hazard subject, and the information that has insufficient influence on the safety of the sub-area can be eliminated while retaining the judgment basis that has sufficient influence on the safety of the sub-area, which helps to improve the accuracy of the risk early warning. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0025] Figure 1 A flow chart showing a method for early warning of potential safety hazards in a construction area according to an embodiment of the present application is shown;

[0026] Figure 2A flow chart showing a method for calculating target relevance according to an embodiment of the present application is shown;

[0027] Figure 3 A flow chart showing a method for calculating target relevance according to another embodiment of the present application is shown;

[0028] Figure 4 A block diagram of a computer device according to an embodiment of the present application is shown;

[0029] Figure 5 A block diagram of a computer device according to another embodiment of the present application is shown. DETAILED DESCRIPTION

[0030] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0031] Figure 1 A flow chart of a method for early warning of potential safety hazards in a construction area according to an embodiment of the present application is shown.

[0032] like Figure 1 As shown, according to one embodiment of the present application, a safety hazard early warning method for a construction area includes:

[0033] Step 102: For each sub-area in the construction area, first real-time risk association information of the sub-area is obtained.

[0034] The construction area in a project often includes multiple parts that are being constructed simultaneously. Each part, as a separate sub-area, may be different from other parts in terms of construction content, construction progress, and even construction environment. Therefore, in order to maximize the accuracy of real-time warnings at the construction site, separate real-time warning judgments can be made for each sub-area within the construction area.

[0035] Furthermore, the first real-time risk association information of the sub-region is used to reflect the performance characteristics associated with the sub-region and having an impact on the safety level of the sub-region. In other words, the first real-time risk association information of the sub-region is the basis for judging whether the sub-region has a potential safety hazard that requires early warning. Therefore, the first real-time risk association information of the sub-region can be obtained to further judge whether the sub-region has a potential safety hazard that requires early warning.

[0036] Among them, the first real-time risk association information of the sub-area includes various types of data obtained by information acquisition devices such as cameras at various locations set in the area, different types of sensors, etc., and each type of first real-time risk association information has a different degree of impact on the security of the sub-area.

[0037] In a possible design, obtaining the first real-time risk association information of the sub-region includes: obtaining internal performance characteristics of the sub-region and obtaining external environment performance characteristics of the sub-region.

[0038] Among them, the internal performance characteristics of the area include: the overall video of the sub-area, the local video, the number of operators, the operator positions, the operator actions, the operator expressions, the non-operating personnel positions, the non-operating personnel actions, the non-operating personnel expressions, the operating equipment positions, the operating equipment actions, the non-operating equipment positions, the non-operating equipment actions, the abnormal events in the area, and the noise and noise level caused by the abnormal events in the area.

[0039] The external environment performance characteristics include: current weather type, performance level of the current weather type, ambient temperature, perceived temperature, ambient humidity, UV index, water quality information, soil composition information, geological seepage degree, surface inclination, dust concentration and harmful gas concentration.

[0040] Of course, the first real-time risk-related information of the sub-area is not limited to the above examples, and may also be any other feature that has an impact on the safety of the sub-area.

[0041] Step 104: determine the safety hazard subject in the sub-area that has a preset association relationship with the first real-time risk association information, and obtain individual performance characteristics of the safety hazard subject.

[0042] The subject of safety hazard refers to the object in the sub-area that has an impact on the safety of the sub-area, including but not limited to any individual in the sub-area, such as operating personnel, operating equipment, non-operating personnel, non-operating equipment, mobile obstacles, fixed obstacles, etc.

[0043] The individual performance characteristics of the subject of safety hazards refer to the characteristics of the subject of safety hazards that have an impact on the safety of the sub-area. For example, the individual performance characteristics of the operator include: the working hours, error rate, facial expression information and body posture information of the operator under the performance characteristics of the external environment. These individual performance characteristics can reflect the fatigue level of the operator. The higher the fatigue level, the greater the problem of errors in the operator's work, and the greater the threat to the safety of the sub-area.

[0044] Furthermore, each safety hazard subject has different impacts on the safety level of the sub-area due to its different individual performance characteristics. At the same time, each first real-time risk association information also reflects the safety performance of the sub-area in a single dimension. Therefore, the individual performance characteristics of the safety hazard subject are correlated with the first real-time risk association information. In other words, this correlation, that is, the preset correlation relationship, means that the first real-time risk association information is correlated with the safety level of the safety hazard subject.

[0045] In a possible design, each safety hazard subject in a sub-area is associated with part of the first real-time risk association information of the sub-area.

[0046] For example, for the first real-time risk-related information such as the overall video, local video, operator expression, number of operators, operator position or operator action of the sub-area, the corresponding safety hazard subjects include the operators, and the individual performance characteristics of the operators include: the working time, error rate, expression information and body information of the operators under the external environment performance characteristics.

[0047] In a possible design, an association relationship set may be set, in which a plurality of related safety hazard subjects are determined for each first real-time risk association information. Thus, after obtaining the first real-time risk association information of the sub-region, the safety hazard subject corresponding to each first real-time risk association information may be searched in the association relationship set.

[0048] Step 106: Determine the target correlation between the first real-time risk correlation information and the safety hazard subject based on the individual performance characteristics.

[0049] Step 108: If the target correlation degree reaches a first predetermined threshold, the first real-time risk correlation information is set as second real-time risk correlation information.

[0050] Among them, the target correlation degree is used to reflect the influence of the first real-time risk correlation information on the safety level of the safety hazard subject. It can be said that the higher the target correlation degree between the first real-time risk correlation information and the safety hazard subject, the greater the influence of the first real-time risk correlation information on the overall safety of the sub-area. In other words, the target correlation degree reflects the influence of the first real-time risk correlation information on the overall safety of the sub-area.

[0051] Based on this, the target correlation degree can be used as a condition for screening the first real-time risk correlation information that has a sufficiently high impact on the overall safety of the sub-area. The first predetermined threshold refers to the target correlation degree when the impact of the first real-time risk correlation information on the overall safety of the sub-area reaches a decisive condition for using it as a warning.

[0052] In a possible design, the first predetermined threshold refers to the minimum target correlation degree when the influence of the first real-time risk association information on the overall safety of the sub-area reaches a decisive condition for using it as a warning.

[0053] Step 110, based on the second real-time risk association information and a preset risk value calculation model, determine the risk assessment parameters of the sub-area, wherein the risk assessment parameters are used to reflect the urgency of the security risks to be dealt with by the sub-area, and the risk value calculation model is used to reflect the association between the second real-time risk association information and the risk assessment parameters.

[0054] After screening out the second real-time risk association information whose influence on the overall safety of the sub-area reaches the decisive condition for using it as a warning, the second real-time risk association information can be input into a preset risk value calculation model, so that the preset risk value calculation model outputs risk assessment parameters as the final judgment basis for whether to issue a warning or not.

[0055] The risk value calculation model includes but is not limited to any type of model such as logistic regression, decision tree, random forest, support vector machine, neural network, etc. In addition, the prediction performance of the risk value calculation model can be evaluated by using indicators such as binary classification model evaluation, cross validation, AUC, precision, recall rate, etc., so as to adjust the parameters of the risk value calculation model based on the evaluation results of the prediction performance, so that the risk assessment parameters output by the model are more accurate.

[0056] Step 112: If the risk assessment parameter reaches a second predetermined threshold, risk warning processing is performed for the sub-region.

[0057] The second predetermined threshold refers to the minimum risk assessment parameter corresponding to the second real-time risk association information when the safety hazard in the sub-area may bring adverse consequences. In other words, once the risk assessment parameter reaches the second predetermined threshold, it means that the safety hazard in the sub-area may bring adverse consequences and needs to be dealt with urgently. At this time, risk warning processing can be carried out to prompt the engineering operator to solve the safety hazard faced by the sub-area in a timely manner.

[0058] In order to maximize the accuracy of real-time warnings at construction sites, the above technical solution performs a separate real-time warning judgment on each sub-area in the construction area. In this judgment process, the real-time risk-related information related to the safety of the sub-area is screened through the performance of the subject of the safety hazard, and the screened part of the real-time risk-related information that has sufficient influence on the safety of the sub-area is input into the preset risk value calculation model, so that it outputs the risk assessment parameters as the final judgment basis for whether to perform the risk warning process. This technical solution is compatible with various types of construction sites. It only needs to obtain the real-time risk-related information of a certain construction site to accurately judge whether each sub-area in the construction site needs a warning, which improves the compatibility of risk warnings at construction sites and reduces the cost of risk warnings at construction sites. At the same time, by screening the real-time risk-related information related to the safety of the sub-area through the performance of the subject of the safety hazard, the information that has insufficient influence on the safety of the sub-area can be eliminated while retaining the judgment basis that has sufficient influence on the safety of the sub-area, which helps to improve the accuracy of risk warnings.

[0059] In a possible design, a single item of first real-time risk association information is correlated with multiple safety hazard subjects. For the single item of first real-time risk association information, its target correlation with each of the multiple safety hazard subjects can be determined.

[0060] Optionally, if the target correlation degree between a single first real-time risk association information and any safety hazard subject reaches a first predetermined threshold, the first real-time risk association information is set as the second real-time risk association information.

[0061] Optionally, if the target correlation degrees of a single first real-time risk association information with multiple safety hazard subjects all reach a first predetermined threshold, the first real-time risk association information is set as the second real-time risk association information.

[0062] Optionally, the average of the target correlations between a single first real-time risk association information and each of the multiple safety hazard subjects is determined, and if the average reaches a first predetermined threshold, the first real-time risk association information is set as the second real-time risk association information.

[0063] Below through Figure 2 and Figure 3 The specific example of the process of calculating the target correlation degree for a single first real-time risk correlation information is described in detail.

[0064] If the first real-time risk-related information includes multiple pieces of related information in the overall video of the sub-area, the local video, the expressions of the operators, the number of operators, the positions of the operators, and the actions of the operators, the main body of the safety hazard corresponding to the first real-time risk-related information includes the operators, and the individual performance characteristics of the operators include: the working hours, error rate, expression information, and body posture information of the operators under the performance characteristics of the external environment. On this basis, Figure 2 A flow chart of a method for calculating target relevance according to an embodiment of the present application is shown.

[0065] like Figure 2 As shown, the method includes:

[0066] Step 202: Obtain the weights of all external environment performance features of the sub-region.

[0067] The external environment performance characteristics of the sub-area reflect the impact of the environment in which the sub-area is located on the safety level of the sub-area. The weight of each external environment performance characteristic is used to reflect the degree of influence of the external environment performance characteristic on the work content performed by the operator in the sub-area. In other words, when calculating the target correlation between a single first real-time risk association information and a single safety hazard subject, it is necessary to determine the weight of the current external environment performance characteristic in the dimension of the single safety hazard subject.

[0068] Step 204: Determine the first environment participation degree based on all the external environment performance characteristics and their respective weights.

[0069] In general, the first environmental participation reflects the impact of the environment of the sub-area on the workers in the sub-area.

[0070] In a possible design, a weighted average value of all the external environment performance characteristics is determined, and the weighted average value reflects the impact of different external environment performance characteristics on the safety level of the operating personnel in the sub-area as the main body of safety hazards. Therefore, the weighted average value can be used to determine the first environmental participation degree.

[0071] In another possible design, based on all the external environment performance characteristics and their respective weights, a weighted average of all the external environment performance characteristics is determined as a second environmental participation degree. The second environmental participation degree reflects the impact of different external environment performance characteristics on the safety level of the workers in the sub-area, which is the main body of safety hazards, and can be used as one of the conditions for determining the impact of the environment of the sub-area on the workers in the sub-area.

[0072] Next, for each of the multiple pieces of associated information in the overall video, partial video, operator expression, number of operators, operator position, and operator action of the sub-area, the third environment participation degree is determined based on the associated information and the weight of the associated information. The third environment participation degree reflects the degree to which a single piece of associated information is affected by the performance characteristics of the external environment.

[0073] Next, based on the second environment participation level and the third environment participation level, a fourth environment participation level of the associated information is determined.

[0074] Optionally, the average of the second environmental participation degree and the third environmental participation degree may be used as the fourth environmental participation degree of the associated information to highlight the role of the single associated information in the safety situation of the sub-area.

[0075] Optionally, the maximum value of the second environment participation degree and the third environment participation degree may be used as the fourth environment participation degree of the associated information, so as to maximize consideration of the impact of the environment when evaluating whether a risk warning is needed.

[0076] At this point, after obtaining the fourth environment participation degree of each of the plurality of associated information, the first environment participation degree is determined.

[0077] Optionally, the maximum value of the fourth environmental participation degrees of each of the plurality of associated information may be used as the first environmental participation degree, so as to maximize consideration of the impact of the environment when evaluating whether a risk warning is needed.

[0078] Optionally, an average of the fourth environment participation degrees of each of the multiple pieces of the associated information may be used as the first environment participation degree.

[0079] Step 206, based on the working hours, error rate, facial expression information and body posture information of the operator, determine the first initial correlation degree between the first real-time risk association information and the operator.

[0080] Optionally, after normalizing the working hours, the error rate, the expression information and the posture information, an initial correlation matrix is ​​established, and the rank of the initial correlation matrix is ​​used as the first initial correlation. The initial correlation matrix is ​​a matrix with four rows and four columns, and the element in the pth row and qth column of the matrix is ​​the square root of the mean of the normalized values ​​of the pth item and the qth item in the working hours, the error rate, the expression information and the posture information.

[0081] Step 208: Correct the first initial correlation degree using the first environmental participation degree to obtain a target correlation degree.

[0082] Finally, the first environmental participation degree is used as an error caused by the influence of the environment on the result of the correlation calculation, and the first initial correlation degree is corrected to obtain the target correlation degree.

[0083] In a possible design, the difference between the first initial association degree and the first environment participation degree is set as the target association degree.

[0084] It should be noted that in the embodiments of the present application, any content such as the first real-time risk association information, the second real-time risk association information, and the individual performance characteristics are encoded and normalized before the calculation process.

[0085] In a possible design, if the first real-time risk association information includes the location of the operating equipment and / or the operation of the operating equipment, the main body of the safety hazard corresponding to the first real-time risk association information includes the operating equipment, and the individual performance characteristics of the operating equipment include: the maintenance information, inspection information, production data, energy consumption data of the operating equipment, the first operating impact of the ambient temperature on the operating equipment, the second operating impact of the ambient humidity on the operating equipment, and the offset distance between the current position and the initial position of the operating equipment in multiple specified directions, wherein the specified directions include the horizontal direction, the vertical direction, and the relative direction between any safety hazard main body in the sub-area and the operating equipment. On this basis, Figure 3 A flow chart of a method for calculating target relevance according to another embodiment of the present application is shown.

[0086] like Figure 3 As shown, the method includes:

[0087] Step 302: Obtain the weights of all external environment performance features of the sub-region.

[0088] The external environment performance characteristics of the sub-region reflect the impact of the environment in which the sub-region is located on the safety level of the sub-region, and the weight of each external environment performance characteristic is used to reflect the degree of influence of the external environment performance characteristic on the operating level of the operating equipment in the sub-region. In other words, when calculating the target correlation between a single first real-time risk association information and a single safety hazard subject, it is necessary to determine the weight of the current external environment performance characteristics in the dimension of the single safety hazard subject.

[0089] Step 304 : determining, among all the external environment performance features, some performance features whose weights reach a third predetermined threshold.

[0090] The third predetermined threshold refers to the minimum weight of the external environment performance characteristics when the degree of influence of the external environment performance characteristics on the operating level of the operating equipment in the sub-area has a decisive influence on the safety level of the sub-area. Therefore, if the weight of an external environment performance characteristic reaches the third predetermined threshold, it means that the external environment performance characteristic is an important environmental factor involved in the decision-making of the safety level of the sub-area.

[0091] Step 306: determine the fifth environmental participation level corresponding to the first real-time risk association information which is a weighted average of the partial performance characteristics.

[0092] For each important environmental factor involved in the safety level of a decision-making sub-region, the weighted average value is calculated as the fifth environmental participation degree. It can be understood that the fifth environmental participation degree reflects the comprehensive impact of various important environmental factors involved in the safety level of a decision-making sub-region on the safety level of the sub-region.

[0093] Step 308, based on the maintenance information, inspection information, production data, energy consumption data, first operation impact, second operation impact and offset distance of the operating equipment, determine the second initial correlation between the first real-time risk association information and the operating equipment.

[0094] Optionally, a weighted average of the operating equipment's maintenance information, inspection information, production data, energy consumption data, first operating impact, second operating impact and offset distance is used as the second initial correlation between the first real-time risk association information and the operating equipment.

[0095] Optionally, maintenance information, inspection information, production data, energy consumption data, first operation impact, second operation impact and standard deviation of offset distance of the operating equipment are used as the second initial correlation between the first real-time risk association information and the operating equipment.

[0096] Step 310: Correct the second initial correlation degree by using the fifth environmental participation degree to obtain a target correlation degree.

[0097] Finally, the fifth environmental participation degree is used as an error caused by the influence of the environment on the result of the correlation calculation, and the second initial correlation degree is corrected to obtain the target correlation degree.

[0098] In a possible design, the difference between the first initial association degree and the first environment participation degree is set as the target association degree.

[0099] In addition, before determining the risk assessment parameters of the sub-area based on the second real-time risk association information and the preset risk value calculation model, the historical participation times of all the first real-time risk association information of the sub-area can be obtained, and among all the first real-time risk association information, the third real-time risk association information whose historical participation times is greater than the average historical participation times of all the first real-time risk association information can be determined.

[0100] The historical participation times refers to the number of times the first real-time risk association information is selected as the second real-time risk association information in the historical risk assessment records of the construction area or the sub-area. In other words, the higher the historical participation times, the greater the possibility that the first real-time risk association information will affect the safety level of the sub-area. Therefore, the first real-time risk association information with a sufficiently high historical participation times can be screened as the third real-time risk association information as the basis for modifying the input information of the risk value calculation model.

[0101] Next, based on the multiple external environment performance characteristics in the third real-time risk association information, an environmental participation matrix is ​​constructed, wherein the element in the mth row and nth column in the environmental participation matrix is ​​the product of the weighted average of m random features and the weighted average of n random features in the multiple external environment performance characteristics in the third real-time risk association information. It can be known that the environmental participation matrix reflects the influence of the environmental related information in the third real-time risk association information that has a sufficiently large impact on the safety level of the sub-region in the historical assessment on the safety level of the sub-region.

[0102] On this basis, in determining the risk assessment parameters of the sub-region, a risk association matrix can be further constructed based on multiple pieces of the second real-time risk association information of the sub-region, wherein the element in the xth row and yth column of the risk association matrix is ​​the superposition value of the xth information and the yth information when multiple pieces of the second real-time risk association information are arranged from large to small according to the target association degree. The risk association matrix reflects the comprehensive influence of the second real-time risk association information as a decisive condition for early warning on the overall safety of the sub-region.

[0103] Furthermore, based on the risk association matrix and the environmental participation matrix, input information of the risk value calculation model is determined, and based on the input information and the risk value calculation model, risk assessment parameters of the sub-area are determined.

[0104] Based on the input information determined by the risk association matrix and the environmental participation matrix, the second real-time risk association information as the decisive condition for early warning is screened out from all the first real-time risk association information of the sub-area, and the superimposed influence of the external environmental performance characteristics that have a sufficiently large impact on the safety level of the sub-area in the historical risk assessment on the second real-time risk association information is taken into account. In other words, the technical solution is to obtain the input information after comprehensive processing of the real-time risk association information itself, the correlation between the real-time risk association information and the main body of the safety hazard, the external environmental performance characteristics in the real-time risk association information, and some external environmental performance characteristics with high influence in the historical assessment records. As a result, the accuracy of the risk assessment results of each sub-area in the construction area is greatly improved.

[0105] In addition, the embodiment of the present application provides a potential safety hazard warning device for a construction area, comprising:

[0106] A first association information acquisition unit is used to acquire, for each sub-area in the construction area, first real-time risk association information of the sub-area, wherein the first real-time risk association information is used to reflect the performance characteristics associated with the sub-area and having an impact on the safety level of the sub-area;

[0107] a hidden danger subject determination unit, configured to determine a hidden danger subject in the sub-area that has a preset association relationship with the first real-time risk association information, wherein the preset association relationship refers to a correlation between the first real-time risk association information and a safety level of the hidden danger subject;

[0108] An individual performance characteristic acquisition unit, used to acquire the individual performance characteristics of the potential safety hazard subject;

[0109] a target correlation determination unit, configured to determine a target correlation between the first real-time risk correlation information and the safety hazard subject based on the individual performance characteristics, wherein the target correlation is used to reflect the degree of influence of the first real-time risk correlation information on the safety level of the safety hazard subject;

[0110] A second association information acquisition unit, configured to set the first real-time risk association information as second real-time risk association information if the target association degree reaches a first predetermined threshold;

[0111] a risk assessment parameter determination unit, configured to determine the risk assessment parameter of the sub-area based on the second real-time risk association information and a preset risk value calculation model, wherein the risk assessment parameter is used to reflect the urgency of the security risk to be dealt with by the sub-area, and the risk value calculation model is used to reflect the association relationship between the second real-time risk association information and the risk assessment parameter;

[0112] The risk warning unit is used to perform risk warning processing for the sub-area if the risk assessment parameter reaches a second predetermined threshold.

[0113] In one embodiment of the present application, optionally, the first association information acquisition unit includes:

[0114] A first acquisition unit is used to acquire the internal performance characteristics of the sub-region, wherein the internal performance characteristics of the sub-region include: the overall video of the sub-region, the local video, the number of operators, the positions of operators, the actions of operators, the expressions of operators, the positions of non-operators, the actions of non-operators, the expressions of non-operators, the positions of operating equipment, the actions of operating equipment, the positions of non-operating equipment, the actions of non-operating equipment, abnormal events in the region, and multiple items of noise and noise size caused by the abnormal events in the region; and

[0115] The second acquisition unit is used to acquire the external environment performance characteristics of the sub-area, wherein the external environment performance characteristics include: current weather type, performance level of the current weather type, ambient temperature, perceived temperature, ambient humidity, UV index, water quality information, soil composition information, geological seepage degree, surface inclination, dust concentration and multiple items of harmful gas concentration.

[0116] In one embodiment of the present application, optionally, if the first real-time risk association information includes multiple pieces of associated information including the overall video, local video, operator expressions, number of operators, operator positions and operator actions of the sub-area, the safety hazard subject corresponding to the first real-time risk association information includes operators, and the individual performance characteristics of the operators include: the working time, error rate, expression information and body shape information of the operators under the external environment performance characteristics.

[0117] In one embodiment of the present application, optionally, the target relevance determination unit includes:

[0118] A weight acquisition unit, used to acquire the weights of all the external environment performance characteristics of the sub-area, wherein the weight of each external environment performance characteristic is used to reflect the influence of the external environment performance characteristic on the work content performed by the operator in the sub-area;

[0119] A first environment participation degree calculation unit, configured to determine a first environment participation degree based on all of the external environment performance characteristics and their respective weights;

[0120] A first initial correlation calculation unit, configured to determine a first initial correlation between the first real-time risk correlation information and the operator based on the working time, the error rate, the expression information, and the body information;

[0121] The first execution unit is used to correct the first initial correlation degree by using the first environment participation degree to obtain the target correlation degree.

[0122] In one embodiment of the present application, optionally, the first environment participation calculation unit is used to:

[0123] Based on all the external environment performance characteristics and their respective weights, determine a weighted average of all the external environment performance characteristics as the second environment participation; for each of the multiple items of associated information, determine a third environment participation based on the associated information and the weight of the associated information; based on the second environment participation and the third environment participation, determine a fourth environment participation of the associated information; based on the fourth environment participation of each of the multiple items of associated information, determine the first environment participation.

[0124] In one embodiment of the present application, optionally, if the first real-time risk association information includes the location of the operating equipment and / or the operation of the operating equipment, the main body of the safety hazard corresponding to the first real-time risk association information includes the operating equipment, and the individual performance characteristics of the operating equipment include: the maintenance information, inspection information, production data, energy consumption data of the operating equipment, the first operating impact of the ambient temperature on the operating equipment, the second operating impact of the ambient humidity on the operating equipment, and the offset distance between the current position of the operating equipment and the initial position in multiple specified directions, wherein the specified direction includes the horizontal direction, the vertical direction, and the relative direction between any safety hazard main body in the sub-area and the operating equipment.

[0125] In one embodiment of the present application, optionally, the target relevance determination unit includes:

[0126] A weight acquisition unit, used to acquire the weights of all the external environment performance characteristics of the sub-area, wherein the weight of each external environment performance characteristic is used to reflect the influence of the external environment performance characteristic on the operation level of the operating equipment in the sub-area;

[0127] A partial performance feature determination unit, configured to determine, from among all the external environment performance features, the partial performance features whose weights reach a third predetermined threshold;

[0128] a fifth environment participation degree determining unit, configured to determine a weighted average value of the partial performance characteristics as a fifth environment participation degree corresponding to the first real-time risk association information;

[0129] A second initial correlation determination unit is used to determine a second initial correlation between the first real-time risk association information and the operating equipment based on the maintenance information, the inspection information, the production data, the energy consumption data, the first operation impact, the second operation impact and the offset distance;

[0130] The second execution unit is used to correct the second initial correlation degree by using the fifth environmental participation degree to obtain the target correlation degree.

[0131] In one embodiment of the present application, optionally, the device further includes:

[0132] A historical participation number acquisition unit is used to acquire the historical participation number of each of all the first real-time risk association information of the sub-area before determining the risk assessment parameters of the sub-area based on the second real-time risk association information and a preset risk value calculation model, wherein the historical participation number refers to the number of times the first real-time risk association information is selected as the second real-time risk association information in the historical risk assessment record of the construction area or the sub-area;

[0133] A third real-time risk association information acquisition unit is used to determine, from among all the first real-time risk association information, third real-time risk association information whose historical participation times are greater than an average of the historical participation times of all the first real-time risk association information;

[0134] An environmental participation matrix construction unit is used to construct an environmental participation matrix based on multiple external environmental performance characteristics in the third real-time risk association information, wherein the element in the mth row and nth column in the environmental participation matrix is ​​the product of the weighted average of m random features and the weighted average of n random features in the multiple external environmental performance characteristics in the third real-time risk association information;

[0135] The risk assessment parameter determination unit comprises:

[0136] A risk association matrix construction unit, configured to construct a risk association matrix based on the multiple pieces of the second real-time risk association information of the sub-region, wherein the element in the x-th row and y-th column of the risk association matrix is ​​a superposition value of the x-th information and the y-th information when the multiple pieces of the second real-time risk association information are arranged from large to small according to the target association degree;

[0137] An input information processing unit, used to determine input information of the risk value calculation model based on the risk association matrix and the environmental participation matrix;

[0138] The third execution unit is used to determine the risk assessment parameter of the sub-region based on the input information and the risk value calculation model.

[0139] The device uses any one of the solutions described in the above embodiments, and therefore has all the above technical effects, which will not be repeated here.

[0140] In addition, in one embodiment, the present application provides a computer device, which may be a server, and its internal structure diagram may be as follows: Figure 4 As shown. The computer device includes a processor, a memory, a network interface and a database connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile and / or volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external client via a network connection. When the computer program is executed by the processor, the method described in any of the above embodiments can be implemented.

[0141] In one embodiment, the present application further provides a computer device, which may be a client, and its internal structure diagram may be as follows: Figure 5 As shown. The computer device includes a processor, a memory, a network interface, a display screen and an input device connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external server via a network connection. When the computer program is executed by the processor, the method described in any of the above embodiments can be implemented.

[0142] Any of the above-mentioned computer devices in the embodiments of the present application may exist in various forms, including but not limited to:

[0143] (1) Mobile communication devices: These devices are characterized by their mobile communication functions and their main purpose is to provide voice and data communications. These terminals include: smart phones (such as iPhone), multimedia phones, functional phones, and low-end phones.

[0144] (2) Ultra-mobile personal computer devices: These devices fall into the category of personal computers, have computing and processing capabilities, and generally also have mobile Internet access features. These terminals include: PDA, MID and UMPC devices, such as iPad.

[0145] (3) Portable entertainment devices: These devices can display and play multimedia content. They include audio and video players (such as iPods), handheld game consoles, e-books, as well as smart toys, wearable devices, and portable car navigation devices.

[0146] (4) Server: A device that provides computing services. The server consists of a processor, hard disk, memory, system bus, etc. The server is similar to a general computer architecture, but because it needs to provide highly reliable services, it has higher requirements in terms of processing power, stability, reliability, security, scalability, and manageability.

[0147] (5) Other electronic devices with data interaction functions.

[0148] In addition, an embodiment of the present application provides a computer-readable storage medium storing computer-executable instructions, wherein the computer-executable instructions are used to perform the following steps:

[0149] For each sub-area within the construction area, first real-time risk association information of the sub-area is obtained, wherein the first real-time risk association information is used to reflect the performance characteristics associated with the sub-area and having an impact on the safety level of the sub-area;

[0150] Determine a safety hazard subject in the sub-area that has a preset association relationship with the first real-time risk association information, and obtain individual performance characteristics of the safety hazard subject, wherein the preset association relationship refers to the correlation between the first real-time risk association information and the safety level of the safety hazard subject;

[0151] Based on the individual performance characteristics, determining a target correlation between the first real-time risk association information and the safety hazard subject, wherein the target correlation is used to reflect the degree of influence of the first real-time risk association information on the safety level of the safety hazard subject;

[0152] If the target correlation degree reaches a first predetermined threshold, setting the first real-time risk correlation information as second real-time risk correlation information;

[0153] Based on the second real-time risk association information and a preset risk value calculation model, determine the risk assessment parameter of the sub-area, wherein the risk assessment parameter is used to reflect the urgency of the security risk to be dealt with by the sub-area, and the risk value calculation model is used to reflect the association relationship between the second real-time risk association information and the risk assessment parameter;

[0154] If the risk assessment parameter reaches a second predetermined threshold, risk warning processing is performed for the sub-region.

[0155] It should be noted that the above functions or steps that can be implemented by the computer-readable storage medium or computer device can refer to the relevant description in the aforementioned method embodiment. In order to avoid repetition, they will not be described one by one here.

[0156] The technical solution of the present application is described in detail above in conjunction with the accompanying drawings. Through the technical solution of the present application, in order to maximize the accuracy of the real-time warning of the construction site, a separate real-time warning judgment is made for each sub-area in the construction area. In this judgment process, the real-time risk association information related to the safety of the sub-area is screened through the performance of the safety hazard subject, and the screened part of the real-time risk association information that has sufficient influence on the safety of the sub-area is input into the preset risk value calculation model, so that it outputs the risk assessment parameter as the final judgment basis for whether to perform the risk warning process. This technical solution is compatible with various types of construction sites. It only needs to obtain the real-time risk association information of a certain construction site to accurately judge whether each sub-area in the construction site needs an early warning, which improves the compatibility of the risk early warning of the construction site and reduces the cost of the risk early warning of the construction site. At the same time, the real-time risk association information related to the safety of the sub-area is screened through the performance of the safety hazard subject, and the information that has insufficient influence on the safety of the sub-area can be eliminated while retaining the judgment basis that has sufficient influence on the safety of the sub-area, which helps to improve the accuracy of the risk early warning.

[0157] It should be understood that the term "and / or" used in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship.

[0158] It should be understood that although the terms first, second, etc. may be used to describe real-time risk association information in the embodiments of the present application, these real-time risk association information should not be limited to these terms. These terms are only used to distinguish real-time risk association information from each other. For example, without departing from the scope of the embodiments of the present application, the first real-time risk association information may also be referred to as the second real-time risk association information, and similarly, the second real-time risk association information may also be referred to as the first real-time risk association information.

[0159] The word "if" as used herein may be interpreted as "at the time of" or "when" or "in response to determining" or "in response to detecting", depending on the context. Similarly, the phrases "if it is determined" or "if (stated condition or event) is detected" may be interpreted as "when it is determined" or "in response to determining" or "when detecting (stated condition or event)" or "in response to detecting (stated condition or event)", depending on the context.

[0160] The terms used in the embodiments of the present application are only for the purpose of describing specific embodiments, and are not intended to limit the present application. The singular forms "a", "said" and "the" used in the embodiments of the present application and the appended claims are also intended to include plural forms, unless the context clearly indicates other meanings.

[0161] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0162] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0163] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0164] The embodiments described above are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included in the protection scope of the present invention.

Claims

1. A safety hazard early warning method for a construction area, characterized in that: include: For each sub-area within the construction area, first real-time risk association information of the sub-area is obtained, wherein the first real-time risk association information is used to reflect the performance characteristics associated with the sub-area and having an impact on the safety level of the sub-area; Determine a safety hazard subject in the sub-area that has a preset association relationship with the first real-time risk association information, and obtain individual performance characteristics of the safety hazard subject, wherein the preset association relationship refers to the correlation between the first real-time risk association information and the safety level of the safety hazard subject; Based on the individual performance characteristics, determining a target correlation between the first real-time risk association information and the safety hazard subject, wherein the target correlation is used to reflect the degree of influence of the first real-time risk association information on the safety level of the safety hazard subject; If the target correlation degree reaches a first predetermined threshold, setting the first real-time risk correlation information as second real-time risk correlation information; Based on the second real-time risk association information and a preset risk value calculation model, determine the risk assessment parameter of the sub-area, wherein the risk assessment parameter is used to reflect the urgency of the security risk to be dealt with by the sub-area, and the risk value calculation model is used to reflect the association relationship between the second real-time risk association information and the risk assessment parameter; If the risk assessment parameter reaches a second predetermined threshold, performing risk warning processing for the sub-region; If the first real-time risk-related information includes multiple pieces of related information including the overall video of the sub-area, the local video, the expressions of the operators, the number of operators, the positions of the operators, and the actions of the operators, The safety hazard subjects corresponding to the first real-time risk association information include operating personnel, The individual performance characteristics of the operator include: the working time, error rate, expression information and body posture information of the operator under the performance characteristics of the external environment; The determining, based on the individual performance characteristics, a target correlation between the first real-time risk correlation information and the potential safety hazard subject includes: Obtaining the weights of all the external environment performance characteristics of the sub-area, wherein the weight of each external environment performance characteristic is used to reflect the influence of the external environment performance characteristic on the work content performed by the operator in the sub-area; Determining a first environmental participation degree based on all of the external environmental performance characteristics and their respective weights; Based on the working hours, the error rate, the facial expression information and the body information, determine a first initial correlation between the first real-time risk association information and the operator, wherein after the working hours, the error rate, the facial expression information and the body information are normalized, an initial correlation matrix is ​​established, and the rank of the initial correlation matrix is ​​used as the first initial correlation, the initial correlation matrix is ​​a matrix with four rows and four columns, and the element in the p-th row and q-th column of the initial correlation matrix is ​​the square root of the mean of the normalized values ​​of the p-th item and the q-th item in the working hours, the error rate, the facial expression information and the body information; Correcting the first initial correlation degree by using the first environmental participation degree to obtain the target correlation degree; The determining of the first environment participation degree based on all the external environment performance characteristics and their respective weights includes: Based on all the external environment performance characteristics and their respective weights, determining a weighted average of all the external environment performance characteristics as the second environment participation degree; For each of the plurality of pieces of association information, determining a third environment participation degree based on the association information and a weight of the association information; Determining a fourth environment participation level of the associated information based on the second environment participation level and the third environment participation level; The first environment participation degree is determined based on the fourth environment participation degrees of each of the multiple associated information, wherein the maximum value of the fourth environment participation degrees of each of the multiple associated information is used as the first environment participation degree, or the average value of the fourth environment participation degrees of each of the multiple associated information is used as the first environment participation degree.

2. The method according to claim 1, characterized in that The obtaining of the first real-time risk association information of the sub-area includes: Acquire the regional internal performance features of the sub-region, wherein the regional internal performance features include: the overall video of the sub-region, the local video, the number of operators, the positions of operators, the actions of operators, the expressions of operators, the positions of non-operators, the actions of non-operators, the expressions of non-operators, the positions of operating equipment, the actions of operating equipment, the positions of non-operating equipment, the actions of non-operating equipment, abnormal events in the region, and the noise and noise level caused by the abnormal events in the region; and The external environment performance characteristics of the sub-area are obtained, wherein the external environment performance characteristics include: current weather type, performance level of the current weather type, ambient temperature, perceived temperature, ambient humidity, UV index, water quality information, soil composition information, geological seepage degree, surface inclination, dust concentration and multiple items of harmful gas concentration.

3. The method according to claim 2, characterized in that If the first real-time risk-related information includes the location of the operating equipment and / or the operation of the operating equipment, The safety hazard subjects corresponding to the first real-time risk association information include operating equipment, The individual performance characteristics of the operating equipment include: maintenance information, inspection information, production data, energy consumption data of the operating equipment, the first operating impact of the ambient temperature on the operating equipment, the second operating impact of the ambient humidity on the operating equipment, and the offset distance between the current position and the initial position of the operating equipment in multiple specified directions, wherein the specified directions include horizontal directions, vertical directions, and the relative direction between any safety hazard subject in the sub-area and the operating equipment.

4. The method according to claim 3, characterized in that The determining, based on the individual performance characteristics, a target correlation between the first real-time risk correlation information and the potential safety hazard subject includes: Obtaining respective weights of all the external environment performance characteristics of the sub-area, wherein the weight of each external environment performance characteristic is used to reflect the degree of influence of the external environment performance characteristic on the operation level of the operating equipment in the sub-area; Determining, from among all the external environment performance features, some performance features whose weights reach a third predetermined threshold; Determining a weighted average of the partial performance characteristics as a fifth environmental participation degree corresponding to the first real-time risk association information; Determine a second initial correlation between the first real-time risk association information and the operating equipment based on the maintenance information, the inspection information, the production data, the energy consumption data, the first operation impact, the second operation impact, and the offset distance; The second initial correlation degree is corrected by the fifth environmental participation degree to obtain the target correlation degree.

5. The method according to claim 4, characterized in that Before determining the risk assessment parameter of the sub-area based on the second real-time risk association information and a preset risk value calculation model, the method further includes: Obtaining the respective historical participation times of all the first real-time risk association information of the sub-area, wherein the historical participation times refers to the number of times the first real-time risk association information is selected as the second real-time risk association information in the historical risk assessment record of the construction area or the sub-area; Determine, from among all the first real-time risk association information, third real-time risk association information whose historical participation times are greater than an average of the historical participation times of all the first real-time risk association information; Based on the multiple external environment performance characteristics in the third real-time risk association information, an environmental participation matrix is ​​constructed, wherein the element in the mth row and nth column in the environmental participation matrix is ​​the product of the weighted average of m random characteristics and the weighted average of n random characteristics in the multiple external environment performance characteristics in the third real-time risk association information; Then, based on the second real-time risk association information and a preset risk value calculation model, determining the risk assessment parameters of the sub-region includes: Based on the multiple pieces of the second real-time risk association information of the sub-region, a risk association matrix is ​​constructed, wherein the element in the x-th row and the y-th column of the risk association matrix is ​​a superposition value of the x-th information and the y-th information when the multiple pieces of the second real-time risk association information are arranged from large to small according to the target association degree; Determining input information of the risk value calculation model based on the risk association matrix and the environmental participation matrix; Based on the input information and the risk value calculation model, a risk assessment parameter of the sub-region is determined.

6. A computer device, characterized in that: include: at least one processor; and, a memory communicatively coupled to the at least one processor; The memory stores instructions executable by the at least one processor, and the instructions are configured to execute the method according to any one of claims 1 to 5.

7. A computer-readable storage medium, characterized in that: Computer executable instructions are stored, and the computer executable instructions are used to execute the method according to any one of claims 1 to 5.

Images