A building safety monitoring method and system based on sensor data linkage

Abstract

The present invention discloses a building safety monitoring method and system based on sensor data linkage, the method comprising: obtaining a set of sensor data obtained by multiple sensors in multiple escape channel areas of a target building; predicting the probability of crowd gathering corresponding to each escape channel area based on the sensor data set and a neural network algorithm; calculating the probability of sudden danger corresponding to the target building based on the regional parameters of each escape channel area and the probability of crowd gathering; when the probability of sudden danger is greater than a preset probability threshold, sending a warning message to the safety monitoring terminal corresponding to the target building. It can be seen that the present invention can effectively improve the efficiency and accuracy of building safety monitoring, so as to timely discover possible dangers, improve the speed of rescue, and reduce personal injuries.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a building safety monitoring method and system based on sensor data linkage. Background Art

[0002] With the development of intelligent building technology, more and more buildings have begun to deploy a large number of sensors to improve their intelligence, so as to obtain different types of sensor data in the building and monitor the activities of people or fire conditions in specific areas of the building. However, in the prior art, when implementing safety monitoring of the building, the data connection between the sensor data in the escape passage area of ​​the building is not specifically considered to achieve more accurate monitoring of the building safety situation, so its safety monitoring effect is poor. It can be seen that the prior art has defects that need to be solved urgently. Summary of the invention

[0003] The technical problem to be solved by the present invention is to provide a building safety monitoring method and system based on sensor data linkage, which can effectively improve the efficiency and accuracy of building safety monitoring, timely discover possible dangerous situations, increase the rescue speed, and reduce personal injuries.

[0004] In order to solve the above technical problems, the first aspect of the present invention discloses a building safety monitoring method based on sensor data linkage, the method comprising:

[0005] Acquire a set of sensor data acquired by multiple sensors in multiple escape passage areas of a target building;

[0006] According to the sensor data set, based on the neural network algorithm, predict the crowd gathering probability corresponding to each escape channel area;

[0007] Calculate the probability of an emergency situation corresponding to the target building according to the area parameters of each escape passage area and the crowd gathering probability;

[0008] When the probability of the sudden danger is greater than a preset probability threshold, a warning message is sent to the security monitoring terminal corresponding to the target building.

[0009] As an optional implementation, in the first aspect of the present invention, the sensor data set includes image data, infrared ranging data, sound data, video data and infrared thermal imaging data.

[0010] As an optional implementation, in the first aspect of the present invention, the area parameters include the floor where the area is located, the channel number to which the area belongs, and information about institutions near the area.

[0011] As an optional implementation, in the first aspect of the present invention, predicting the crowd gathering probability corresponding to each escape channel area based on the sensor data set and a neural network algorithm includes:

[0012] For each of the escape channel areas, based on a data value elimination rule, the sensor data set corresponding to the escape channel area is cleaned to obtain a cleaned data set;

[0013] The cleaned data set is input into the trained crowd gathering probability prediction neural network to obtain the crowd gathering probability corresponding to the escape passage area.

[0014] As an optional implementation, in the first aspect of the present invention, the cleaning of the sensor data set corresponding to the escape passage area to obtain a cleaned data set based on a data value elimination rule includes:

[0015] For each sensor data in the sensor data set corresponding to the escape passage area, determine the data type corresponding to the sensor data; the data type is image data, infrared ranging data, sound data, video data or infrared thermal imaging data;

[0016] Determine a data reference value corresponding to the data type;

[0017] Calculating a data difference between the data value of the sensing data value and the data reference value;

[0018] Determine an associated data type corresponding to the data type, and determine a plurality of other sensor data belonging to the associated data type from the sensor data set;

[0019] Calculate the average value of the data difference corresponding to each of the other sensor data to obtain the associated data difference;

[0020] Calculating a ratio between the data difference and the associated data difference, and calculating an absolute value of a difference between the ratio and 1, to obtain an offset parameter corresponding to the sensing data;

[0021] All the sensor data whose offset parameters are greater than a preset parameter threshold in the sensor data set are eliminated to obtain a cleaned data set.

[0022] As an optional embodiment, in the first aspect of the present invention, the crowd gathering probability prediction neural network is a neural network with a CNN structure, which is trained by a training data set including multiple training sensor data sets and corresponding crowd gathering annotations, and during the training, the neural network model parameters are optimized based on the L1 loss function and the gradient descent algorithm until convergence.

[0023] As an optional implementation, in the first aspect of the present invention, the calculation of the probability of an emergency corresponding to the target building according to the regional parameters of each of the escape passage areas and the crowd gathering probability includes:

[0024] Grouping all the escape passage areas according to corresponding area parameters to obtain a plurality of associated area sets;

[0025] Calculate the average value of all the crowd gathering probabilities corresponding to each of the associated area sets to obtain the set probability corresponding to each of the associated area sets;

[0026] The weighted sum average of the set probabilities corresponding to all the associated area sets is calculated to obtain the probability of sudden danger corresponding to the target building, wherein the weighted calculation weight corresponding to each set probability is proportional to the number of areas in the corresponding associated area set.

[0027] As an optional implementation, in the first aspect of the present invention, grouping all the escape passage areas according to corresponding area parameters to obtain a plurality of associated area sets includes:

[0028] For any two of the escape passages, calculating the floor difference between the floors of the areas corresponding to the two escape passages;

[0029] Calculate the difference between the channel numbers of the areas corresponding to the two escape channels;

[0030] Calculating the organizational similarity between the organizational information near the area corresponding to the two escape passages;

[0031] Calculate the weighted average of the floor difference, the number difference and the mechanism similarity to obtain the correlation between the two escape passages;

[0032] Based on a clustering algorithm, all the escape channel areas are grouped to obtain a plurality of associated area sets, wherein the degree of association between any two escape channel areas in each associated area set is greater than a preset degree of association threshold.

[0033] A second aspect of an embodiment of the present invention discloses a building safety monitoring system based on sensor data linkage, the system comprising:

[0034] An acquisition module, used to acquire a set of sensor data acquired by multiple sensors in multiple escape passage areas of a target building;

[0035] A prediction module, used for predicting the probability of crowd gathering corresponding to each escape channel area based on the sensor data set and a neural network algorithm;

[0036] A calculation module, used for calculating the probability of an emergency corresponding to the target building according to the regional parameters of each escape passage area and the probability of crowd gathering;

[0037] The alarm module is used to send a warning message to the security monitoring terminal corresponding to the target building when the probability of the sudden dangerous situation is greater than a preset probability threshold.

[0038] As an optional implementation, in the second aspect of the present invention, the sensor data set includes image data, infrared ranging data, sound data, video data and infrared thermal imaging data.

[0039] As an optional implementation, in the second aspect of the present invention, the area parameters include the floor where the area is located, the channel number to which the area belongs, and information about institutions near the area.

[0040] As an optional implementation, in the second aspect of the present invention, the prediction module predicts the crowd gathering probability corresponding to each escape channel area based on the sensor data set and a neural network algorithm, including:

[0041] For each of the escape channel areas, based on a data value elimination rule, the sensor data set corresponding to the escape channel area is cleaned to obtain a cleaned data set;

[0042] The cleaned data set is input into the trained crowd gathering probability prediction neural network to obtain the crowd gathering probability corresponding to the escape passage area.

[0043] As an optional implementation, in the second aspect of the present invention, the prediction module cleans the sensor data set corresponding to the escape passage area based on the data value elimination rule to obtain the cleaned data set, including:

[0044] For each sensor data in the sensor data set corresponding to the escape passage area, determine the data type corresponding to the sensor data; the data type is image data, infrared ranging data, sound data, video data or infrared thermal imaging data;

[0045] Determine a data reference value corresponding to the data type;

[0046] Calculating a data difference between the data value of the sensing data value and the data reference value;

[0047] Determine an associated data type corresponding to the data type, and determine a plurality of other sensor data belonging to the associated data type from the sensor data set;

[0048] Calculate the average value of the data difference corresponding to each of the other sensor data to obtain the associated data difference;

[0049] Calculating a ratio between the data difference and the associated data difference, and calculating an absolute value of a difference between the ratio and 1, to obtain an offset parameter corresponding to the sensing data;

[0050] All the sensor data whose offset parameters are greater than a preset parameter threshold in the sensor data set are eliminated to obtain a cleaned data set.

[0051] As an optional embodiment, in the second aspect of the present invention, the crowd gathering probability prediction neural network is a neural network with a CNN structure, which is trained by a training data set including multiple training sensor data sets and corresponding crowd gathering annotations, and during the training, the neural network model parameters are optimized based on the L1 loss function and the gradient descent algorithm until convergence.

[0052] As an optional implementation, in the second aspect of the present invention, the specific manner in which the calculation module calculates the probability of an emergency situation corresponding to the target building according to the regional parameters of each of the escape passage areas and the crowd gathering probability includes:

[0053] Grouping all the escape passage areas according to corresponding area parameters to obtain a plurality of associated area sets;

[0054] Calculate the average value of all the crowd gathering probabilities corresponding to each of the associated area sets to obtain the set probability corresponding to each of the associated area sets;

[0055] The weighted sum average of the set probabilities corresponding to all the associated area sets is calculated to obtain the probability of sudden danger corresponding to the target building, wherein the weighted calculation weight corresponding to each set probability is proportional to the number of areas in the corresponding associated area set.

[0056] As an optional implementation, in the second aspect of the present invention, the specific manner in which the calculation module groups all the escape passage areas according to corresponding area parameters to obtain a plurality of associated area sets includes:

[0057] For any two of the escape passages, calculating the floor difference between the floors of the areas corresponding to the two escape passages;

[0058] Calculate the difference between the channel numbers of the areas corresponding to the two escape channels;

[0059] Calculating the organizational similarity between the organizational information near the area corresponding to the two escape passages;

[0060] Calculate the weighted average of the floor difference, the number difference and the mechanism similarity to obtain the correlation between the two escape passages;

[0061] Based on a clustering algorithm, all the escape channel areas are grouped to obtain a plurality of associated area sets, wherein the degree of association between any two escape channel areas in each associated area set is greater than a preset degree of association threshold.

[0062] The third aspect of the present invention discloses another building safety monitoring system based on sensor data linkage, the system comprising:

[0063] A memory storing executable program code;

[0064] a processor coupled to the memory;

[0065] The processor calls the executable program code stored in the memory to execute part or all of the steps in the building safety monitoring method based on sensor data linkage disclosed in the first aspect of the present invention.

[0066] The fourth aspect of the present invention discloses a computer storage medium, which stores computer instructions. When the computer instructions are called, they are used to execute some or all of the steps in the building safety monitoring method based on sensor data linkage disclosed in the first aspect of the present invention.

[0067] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:

[0068] The present invention can predict the probability of crowd gathering in each escape channel area according to the sensor data based on the neural network algorithm, and then calculate the probability of sudden dangerous situations corresponding to the building according to the crowd gathering probabilities in multiple escape channel areas, so as to realize the safety monitoring of the building, thereby effectively improving the efficiency and accuracy of the safety monitoring of the building, and timely discovering possible dangerous situations, improving the rescue speed, and reducing personal injuries. BRIEF DESCRIPTION OF THE DRAWINGS

[0069] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0070] Figure 1 It is a flow chart of a building safety monitoring method based on sensor data linkage disclosed in an embodiment of the present invention.

[0071] Figure 2It is a structural schematic diagram of a building safety monitoring system based on sensor data linkage disclosed in an embodiment of the present invention.

[0072] Figure 3 It is a structural schematic diagram of another building safety monitoring system based on sensor data linkage disclosed in an embodiment of the present invention. DETAILED DESCRIPTION

[0073] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only 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.

[0074] The terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, device, product or equipment that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units that are not listed, or may optionally include other steps or units that are inherent to these processes, methods, products or equipment.

[0075] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present invention. The appearance of the phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0076] The present invention discloses a building safety monitoring method and system based on sensor data linkage, which can predict the probability of crowd gathering according to the sensor data of each escape channel area based on a neural network algorithm, and then calculate the probability of sudden dangerous situations corresponding to the building according to the crowd gathering probabilities of multiple escape channel areas, so as to realize the safety monitoring of the building, thereby effectively improving the efficiency and accuracy of the safety monitoring of the building, and timely discovering possible dangerous situations, improving the rescue speed, and reducing personnel injuries. The following are detailed descriptions.

[0077] Embodiment 1

[0078] See also Figure 1 , Figure 1: is a flow chart of a building safety monitoring method based on sensor data linkage disclosed in an embodiment of the present invention. Figure 1 The described building safety monitoring method based on sensor data linkage can be applied to a data processing system / data processing device / data processing server (wherein the server includes a local processing server or a cloud processing server). Figure 1 As shown, the building safety monitoring method based on sensor data linkage may include the following operations:

[0079] 101. Obtain a set of sensor data acquired by multiple sensors in multiple escape passage areas of a target building.

[0080] 102. According to the sensor data set and based on the neural network algorithm, the probability of crowd gathering corresponding to each escape channel area is predicted.

[0081] 103. According to the regional parameters of each escape route area and the probability of crowd gathering, the probability of sudden danger corresponding to the target building is calculated.

[0082] 104. When the probability of an emergency is greater than a preset probability threshold, a warning message is sent to the security monitoring terminal corresponding to the target building.

[0083] It can be seen that the above-mentioned embodiment of the invention can predict the probability of crowd gathering in each escape channel area according to the sensor data based on the neural network algorithm, and then calculate the probability of sudden dangerous situations corresponding to the building according to the crowd gathering probabilities in multiple escape channel areas, so as to realize the safety monitoring of the building, thereby effectively improving the efficiency and accuracy of the safety monitoring of the building, and timely discovering possible dangerous situations, improving the rescue speed, and reducing personal injuries.

[0084] As an optional embodiment, in the above steps, the sensor data set includes image data, infrared ranging data, sound data, video data and infrared thermal imaging data.

[0085] It can be seen that through the above optional embodiments, the type of sensor data is limited to more comprehensively characterize the situation in the escape passage area, facilitate the subsequent accurate prediction of crowd gathering, and assist in improving the efficiency and accuracy of building safety monitoring, so as to timely discover possible dangerous situations, increase the speed of rescue, and reduce personal injuries.

[0086] As an optional embodiment, in the above steps, the area parameters include the floor where the area is located, the channel number to which the area belongs, and information about institutions near the area.

[0087] It can be seen that through the above optional embodiments, the content of the regional parameters is limited to more comprehensively characterize the characteristics of different aspects of the escape route area, facilitate the accurate prediction of the subsequent probability of sudden dangerous situations, and assist in improving the efficiency and accuracy of building safety monitoring, so as to timely discover possible dangerous situations, improve the speed of rescue, and reduce personal injuries.

[0088] As an optional embodiment, in the above steps, predicting the crowd gathering probability corresponding to each escape channel area based on the sensor data set and the neural network algorithm includes:

[0089] For each escape channel area, based on the data value elimination rule, the sensor data set corresponding to the escape channel area is cleaned to obtain a cleaned data set;

[0090] The cleaned data set is input into the trained crowd gathering probability prediction neural network to obtain the crowd gathering probability corresponding to the escape channel area.

[0091] It can be seen that through the above-mentioned optional embodiments, the sensor data set can be cleaned based on the data value elimination rules to obtain more reference data, and then the crowd gathering probability corresponding to the escape channel area can be predicted based on the trained crowd gathering probability prediction neural network, so as to assist in improving the efficiency and accuracy of building safety monitoring, and timely discover possible dangerous situations, improve rescue speed, and reduce personal injuries.

[0092] As an optional embodiment, in the above steps, based on the data value elimination rule, the sensor data set corresponding to the escape passage area is cleaned to obtain a cleaned data set, including:

[0093] For each sensor data in the sensor data set corresponding to the escape passage area, determine the data type corresponding to the sensor data; optionally, the data type is image data, infrared ranging data, sound data, video data or infrared thermal imaging data;

[0094] Determine the data reference value corresponding to the data type;

[0095] Calculating a data difference between a data value of the sensing data value and a data reference value;

[0096] Determine an associated data type corresponding to the data type, and determine a plurality of other sensor data belonging to the associated data type from the sensor data set;

[0097] Calculate the average value of the data difference corresponding to each other sensor data to obtain the associated data difference;

[0098] Calculate the ratio between the data difference and the associated data difference, and calculate the absolute value of the difference between the ratio and 1 to obtain the offset parameter corresponding to the sensor data;

[0099] All sensor data with offset parameters greater than a preset parameter threshold in the sensor data set are eliminated to obtain a cleaned data set.

[0100] It can be seen that through the above optional embodiments, the steps of cleaning the sensor data set according to the data value elimination rules are clarified to eliminate the abnormal sensor data with abnormal deviation degree that cannot be verified with the related data type, so as to obtain more reference data, facilitate the subsequent accurate prediction of the probability of crowd gathering corresponding to the escape channel area, and assist in improving the efficiency and accuracy of safety monitoring of buildings, so as to timely discover possible dangerous situations, improve the rescue speed, and reduce personal injuries.

[0101] As an optional embodiment, in the above steps, the crowd gathering probability prediction neural network is a neural network with a CNN structure, which is trained by a training data set including multiple training sensor data sets and corresponding crowd gathering annotations, and during the training, the neural network model parameters are optimized based on the L1 loss function and the gradient descent algorithm until convergence.

[0102] It can be seen that through the above optional embodiments, the model details and training details of the crowd gathering probability prediction neural network are clarified, so as to accurately predict the crowd gathering probability corresponding to the escape channel area, assist in improving the efficiency and accuracy of building safety monitoring, and timely discover possible dangerous situations, improve rescue speed, and reduce personal injuries.

[0103] As an optional embodiment, in the above steps, calculating the probability of an emergency corresponding to the target building according to the regional parameters of each escape passage area and the probability of crowd gathering includes:

[0104] Grouping all escape passage areas according to corresponding area parameters to obtain multiple associated area sets;

[0105] Calculate the average of all crowd gathering probabilities corresponding to each associated area set to obtain the aggregate probability corresponding to each associated area set;

[0106] The weighted sum average of the set probabilities corresponding to all associated area sets is calculated to obtain the probability of sudden danger corresponding to the target building, where the weighted calculation weight corresponding to each set probability is proportional to the number of areas in the corresponding associated area set.

[0107] It can be seen that through the above-mentioned optional embodiments, all escape channel areas can be grouped based on area parameters to obtain multiple associated area sets, and then the probability of sudden dangerous situations corresponding to the target building can be calculated based on probability average calculation and weighted sum calculation to achieve safety monitoring of the building, which can effectively improve the efficiency and accuracy of safety monitoring of the building, and timely discover possible dangerous situations, improve rescue speed, and reduce personal injuries.

[0108] As an optional embodiment, in the above step, all escape passage areas are grouped according to corresponding area parameters to obtain multiple associated area sets, including:

[0109] For any two escape routes, calculate the floor difference between the floors where the areas corresponding to the two escape routes are located;

[0110] Calculate the difference between the channel numbers of the areas corresponding to the two escape channels;

[0111] Calculate the organizational similarity between organizational information in the vicinity of the areas corresponding to the two escape passages;

[0112] Calculate the weighted average of the floor difference, number difference and organization similarity to obtain the correlation between the two escape routes;

[0113] Based on the clustering algorithm, all escape channel areas are grouped to obtain a plurality of associated area sets, wherein the degree of association between any two escape channel areas in each associated area set is greater than a preset threshold value of the degree of association.

[0114] It can be seen that through the above-mentioned optional embodiments, all escape channel areas can be grouped based on the calculation of the correlation between the area parameters corresponding to the two escape channels, as well as the clustering algorithm and the correlation threshold, to obtain a plurality of sets of associated areas with strong correlations with each other, so as to facilitate the subsequent accurate calculation of the probability of sudden dangerous situations corresponding to the target building, so as to realize the safety monitoring of the building, and can effectively improve the efficiency and accuracy of the safety monitoring of the building, so as to timely discover possible dangerous situations, improve the rescue speed, and reduce personal injuries.

[0115] Embodiment 2

[0116] See also Figure 2 , Figure 2 is a schematic diagram of a building safety monitoring system based on sensor data linkage disclosed in an embodiment of the present invention. Figure 2 The building safety monitoring system based on sensor data linkage described above can be applied to a data processing system / data processing device / data processing server (wherein the server includes a local processing server or a cloud processing server). Figure 2As shown, the building safety monitoring system based on sensor data linkage may include:

[0117] The acquisition module 201 is used to acquire a set of sensor data acquired by multiple sensors in multiple escape passage areas of a target building.

[0118] The prediction module 202 is used to predict the crowd gathering probability corresponding to each escape channel area based on the sensor data set and the neural network algorithm.

[0119] The calculation module 203 is used to calculate the probability of sudden danger corresponding to the target building according to the regional parameters of each escape channel area and the probability of crowd gathering.

[0120] The alarm module 204 is used to send a warning message to the security monitoring terminal corresponding to the target building when the probability of an emergency is greater than a preset probability threshold.

[0121] It can be seen that the above-mentioned embodiment of the invention can predict the probability of crowd gathering in each escape channel area according to the sensor data based on the neural network algorithm, and then calculate the probability of sudden dangerous situations corresponding to the building according to the crowd gathering probabilities in multiple escape channel areas, so as to realize the safety monitoring of the building, thereby effectively improving the efficiency and accuracy of the safety monitoring of the building, and timely discovering possible dangerous situations, improving the rescue speed, and reducing personal injuries.

[0122] As an optional embodiment, the sensor data set includes image data, infrared ranging data, sound data, video data and infrared thermal imaging data.

[0123] It can be seen that through the above optional embodiments, the type of sensor data is limited to more comprehensively characterize the situation in the escape passage area, facilitate the subsequent accurate prediction of crowd gathering, and assist in improving the efficiency and accuracy of building safety monitoring, so as to timely discover possible dangerous situations, increase the speed of rescue, and reduce personal injuries.

[0124] As an optional embodiment, the area parameters include the floor where the area is located, the channel number to which the area belongs, and information about institutions near the area.

[0125] It can be seen that through the above optional embodiments, the content of the regional parameters is limited to more comprehensively characterize the characteristics of different aspects of the escape route area, facilitate the accurate prediction of the subsequent probability of sudden dangerous situations, and assist in improving the efficiency and accuracy of building safety monitoring, so as to timely discover possible dangerous situations, improve the speed of rescue, and reduce personal injuries.

[0126] As an optional embodiment, the prediction module predicts the specific manner of the crowd gathering probability corresponding to each escape channel area based on the sensor data set and the neural network algorithm, including:

[0127] For each escape channel area, based on the data value elimination rule, the sensor data set corresponding to the escape channel area is cleaned to obtain a cleaned data set;

[0128] The cleaned data set is input into the trained crowd gathering probability prediction neural network to obtain the crowd gathering probability corresponding to the escape channel area.

[0129] It can be seen that through the above-mentioned optional embodiments, the sensor data set can be cleaned based on the data value elimination rules to obtain more reference data, and then the crowd gathering probability corresponding to the escape channel area can be predicted based on the trained crowd gathering probability prediction neural network, so as to assist in improving the efficiency and accuracy of building safety monitoring, and timely discover possible dangerous situations, improve rescue speed, and reduce personal injuries.

[0130] As an optional embodiment, the prediction module cleans the sensor data set corresponding to the escape passage area based on the data value elimination rule to obtain the cleaned data set, including:

[0131] For each sensor data in the sensor data set corresponding to the escape passage area, determine the data type corresponding to the sensor data; optionally, the data type is image data, infrared ranging data, sound data, video data or infrared thermal imaging data;

[0132] Determine the data reference value corresponding to the data type;

[0133] Calculating a data difference between a data value of the sensing data value and a data reference value;

[0134] Determine an associated data type corresponding to the data type, and determine a plurality of other sensor data belonging to the associated data type from the sensor data set;

[0135] Calculate the average value of the data difference corresponding to each other sensor data to obtain the associated data difference;

[0136] Calculate the ratio between the data difference and the associated data difference, and calculate the absolute value of the difference between the ratio and 1 to obtain the offset parameter corresponding to the sensor data;

[0137] All sensor data with offset parameters greater than a preset parameter threshold in the sensor data set are eliminated to obtain a cleaned data set.

[0138] It can be seen that through the above optional embodiments, the steps of cleaning the sensor data set according to the data value elimination rules are clarified to eliminate the abnormal sensor data with abnormal deviation degree that cannot be verified with the related data type, so as to obtain more reference data, facilitate the subsequent accurate prediction of the probability of crowd gathering corresponding to the escape channel area, and assist in improving the efficiency and accuracy of safety monitoring of buildings, so as to timely discover possible dangerous situations, improve the rescue speed, and reduce personal injuries.

[0139] As an optional embodiment, the crowd gathering probability prediction neural network is a neural network with a CNN structure, which is trained by a training data set including multiple training sensor data sets and corresponding crowd gathering annotations, and during the training, the neural network model parameters are optimized based on the L1 loss function and gradient descent algorithm until convergence.

[0140] It can be seen that through the above optional embodiments, the model details and training details of the crowd gathering probability prediction neural network are clarified, so as to accurately predict the crowd gathering probability corresponding to the escape channel area, assist in improving the efficiency and accuracy of building safety monitoring, and timely discover possible dangerous situations, improve rescue speed, and reduce personal injuries.

[0141] As an optional embodiment, the specific method of calculating the probability of an emergency situation corresponding to the target building according to the regional parameters of each escape passage area and the probability of crowd gathering by the calculation module includes:

[0142] Grouping all escape passage areas according to corresponding area parameters to obtain multiple associated area sets;

[0143] Calculate the average of all crowd gathering probabilities corresponding to each associated area set to obtain the aggregate probability corresponding to each associated area set;

[0144] The weighted sum average of the set probabilities corresponding to all associated area sets is calculated to obtain the probability of sudden danger corresponding to the target building, where the weighted calculation weight corresponding to each set probability is proportional to the number of areas in the corresponding associated area set.

[0145] It can be seen that through the above-mentioned optional embodiments, all escape channel areas can be grouped based on area parameters to obtain multiple associated area sets, and then the probability of sudden dangerous situations corresponding to the target building can be calculated based on probability average calculation and weighted sum calculation to achieve safety monitoring of the building, which can effectively improve the efficiency and accuracy of safety monitoring of the building, and timely discover possible dangerous situations, improve rescue speed, and reduce personal injuries.

[0146] As an optional embodiment, the specific manner in which the calculation module groups all escape passage areas according to corresponding area parameters to obtain a plurality of associated area sets includes:

[0147] For any two escape routes, calculate the floor difference between the floors where the areas corresponding to the two escape routes are located;

[0148] Calculate the difference between the channel numbers of the areas corresponding to the two escape channels;

[0149] Calculate the organizational similarity between organizational information in the vicinity of the areas corresponding to the two escape passages;

[0150] Calculate the weighted average of the floor difference, number difference and organization similarity to obtain the correlation between the two escape routes;

[0151] Based on the clustering algorithm, all escape channel areas are grouped to obtain a plurality of associated area sets, wherein the degree of association between any two escape channel areas in each associated area set is greater than a preset threshold value of the degree of association.

[0152] It can be seen that through the above-mentioned optional embodiments, all escape channel areas can be grouped based on the calculation of the correlation between the area parameters corresponding to the two escape channels, as well as the clustering algorithm and the correlation threshold, to obtain a plurality of sets of associated areas with strong correlations with each other, so as to facilitate the subsequent accurate calculation of the probability of sudden dangerous situations corresponding to the target building, so as to realize the safety monitoring of the building, and can effectively improve the efficiency and accuracy of the safety monitoring of the building, so as to timely discover possible dangerous situations, improve the rescue speed, and reduce personal injuries.

[0153] Embodiment 3

[0154] See also Figure 3 , Figure 3 It is another building safety monitoring system based on sensor data linkage disclosed in an embodiment of the present invention. Figure 3 The building safety monitoring system based on sensor data linkage is applied to a data processing system / data processing device / data processing server (wherein the server includes a local processing server or a cloud processing server). Figure 3 As shown, the building safety monitoring system based on sensor data linkage may include:

[0155] A memory 301 storing executable program codes;

[0156] a processor 302 coupled to the memory 301;

[0157] The processor 302 calls the executable program code stored in the memory 301 to execute the steps of the building safety monitoring method based on sensor data linkage described in the first embodiment.

[0158] Embodiment 4

[0159] An embodiment of the present invention discloses a computer-readable storage medium storing a computer program for electronic data exchange, wherein the computer program enables a computer to execute the steps of the building safety monitoring method based on sensor data linkage described in the first embodiment.

[0160] Embodiment 5

[0161] An embodiment of the present invention discloses a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to enable a computer to execute the steps of the building safety monitoring method based on sensor data linkage described in Example 1.

[0162] The above describes specific embodiments of the present specification, and 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 accompanying drawings do not necessarily have to be performed in the specific order or sequential order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0163] The systems, devices, modules or units described in the above embodiments may be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, the computer may be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

[0164] For the convenience of description, the above device is described in various units according to their functions. Of course, when implementing this specification, the functions of each unit can be implemented in the same or multiple software and / or hardware.

[0165] Those skilled in the art will appreciate that the embodiments of this specification may be provided as methods, systems, or computer program products. Therefore, the embodiments of this specification may be in the form of complete hardware embodiments, complete software embodiments, or embodiments in combination with software and hardware. Moreover, the embodiments of this specification may be in the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0166] This specification is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of this specification. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0167] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0168] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0169] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0170] The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0171] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0172] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0173] This specification may be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. This specification may also be practiced in distributed computing environments where tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules may be located in local and remote computer storage media, including storage devices.

[0174] 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 system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0175] Finally, it should be noted that the building safety monitoring method and system based on sensor data linkage disclosed in the embodiment of the present invention only discloses the preferred embodiment of the present invention, which is only used to illustrate the technical solution of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, ordinary technicians in this field should understand that it is still possible to modify the technical solutions recorded in the aforementioned embodiments, or to replace some of the technical features therein by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A building safety monitoring method based on sensor data linkage, characterized in that: The method comprises: Acquire a set of sensor data acquired by multiple sensors in multiple escape passage areas of a target building; According to the sensor data set, based on the neural network algorithm, predict the crowd gathering probability corresponding to each escape channel area; According to the regional parameters of each of the escape passage areas and the crowd gathering probability, the probability of sudden danger corresponding to the target building is calculated; the regional parameters include the floor where the area is located, the channel number to which the area belongs, and the information of institutions near the area; according to the regional parameters of each of the escape passage areas and the crowd gathering probability, the probability of sudden danger corresponding to the target building is calculated, including: For any two of the escape passages, calculating the floor difference between the floors of the areas corresponding to the two escape passages; Calculate the difference between the channel numbers of the areas corresponding to the two escape channels; Calculating the organizational similarity between the organizational information near the area corresponding to the two escape passages; Calculate the weighted average of the floor difference, the number difference and the mechanism similarity to obtain the correlation between the two escape passages; Based on a clustering algorithm, all the escape channel areas are grouped to obtain a plurality of associated area sets, wherein the degree of association between any two escape channel areas in each associated area set is greater than a preset degree of association threshold; Calculate the average value of all the crowd gathering probabilities corresponding to each of the associated area sets to obtain the set probability corresponding to each of the associated area sets; Calculate the weighted sum average of the set probabilities corresponding to all the associated area sets to obtain the probability of a sudden danger corresponding to the target building, wherein the weighted calculation weight corresponding to each set probability is proportional to the number of areas in the corresponding associated area set; When the probability of the sudden danger is greater than a preset probability threshold, a warning message is sent to the security monitoring terminal corresponding to the target building.

2. The building safety monitoring method based on sensor data linkage according to claim 1 is characterized in that: The sensor data set includes image data, infrared ranging data, sound data, video data and infrared thermal imaging data.

3. The building safety monitoring method based on sensor data linkage according to claim 1 is characterized in that: The method of predicting the crowd gathering probability corresponding to each escape passage area based on the sensor data set and a neural network algorithm includes: For each of the escape channel areas, based on a data value elimination rule, the sensor data set corresponding to the escape channel area is cleaned to obtain a cleaned data set; The cleaned data set is input into the trained crowd gathering probability prediction neural network to obtain the crowd gathering probability corresponding to the escape passage area.

4. The building safety monitoring method based on sensor data linkage according to claim 3 is characterized in that: The step of cleaning the sensor data set corresponding to the escape passage area based on the data value elimination rule to obtain a cleaned data set includes: For each sensor data in the sensor data set corresponding to the escape passage area, determine the data type corresponding to the sensor data; the data type is image data, infrared ranging data, sound data, video data or infrared thermal imaging data; Determine a data reference value corresponding to the data type; Calculating a data difference between the data value of the sensing data value and the data reference value; Determine an associated data type corresponding to the data type, and determine a plurality of other sensor data belonging to the associated data type from the sensor data set; Calculate the average value of the data difference corresponding to each of the other sensor data to obtain the associated data difference; Calculating a ratio between the data difference and the associated data difference, and calculating an absolute value of a difference between the ratio and 1, to obtain an offset parameter corresponding to the sensing data; All the sensor data whose offset parameters are greater than a preset parameter threshold in the sensor data set are eliminated to obtain a cleaned data set.

5. The building safety monitoring method based on sensor data linkage according to claim 3 is characterized in that: The crowd gathering probability prediction neural network is a neural network with a CNN structure, which is trained by a training data set including multiple training sensor data sets and corresponding crowd gathering annotations, and during the training, the neural network model parameters are optimized based on the L1 loss function and the gradient descent algorithm until convergence.

6. A building safety monitoring system based on sensor data linkage, characterized in that: The system comprises: An acquisition module, used to acquire a set of sensor data acquired by multiple sensors in multiple escape passage areas of a target building; A prediction module, used for predicting the probability of crowd gathering corresponding to each escape channel area based on the sensor data set and a neural network algorithm; A calculation module is used to calculate the probability of sudden danger corresponding to the target building according to the regional parameters of each escape channel area and the probability of crowd gathering; the regional parameters include the floor where the area is located, the channel number to which the area belongs, and the information of institutions near the area; the specific method in which the calculation module calculates the probability of sudden danger corresponding to the target building according to the regional parameters of each escape channel area and the probability of crowd gathering includes: For any two of the escape passages, calculating the floor difference between the floors of the areas corresponding to the two escape passages; Calculate the difference between the channel numbers of the areas corresponding to the two escape channels; Calculating the organizational similarity between the organizational information near the area corresponding to the two escape passages; Calculate the weighted average of the floor difference, the number difference and the mechanism similarity to obtain the correlation between the two escape passages; Based on a clustering algorithm, all the escape channel areas are grouped to obtain a plurality of associated area sets, wherein the degree of association between any two escape channel areas in each associated area set is greater than a preset degree of association threshold; Calculate the average value of all the crowd gathering probabilities corresponding to each of the associated area sets to obtain the set probability corresponding to each of the associated area sets; Calculate the weighted sum average of the set probabilities corresponding to all the associated area sets to obtain the probability of a sudden danger corresponding to the target building, wherein the weighted calculation weight corresponding to each set probability is proportional to the number of areas in the corresponding associated area set; The alarm module is used to send a warning message to the security monitoring terminal corresponding to the target building when the probability of the sudden dangerous situation is greater than a preset probability threshold.

7. A building safety monitoring system based on sensor data linkage, characterized in that: The system comprises: A memory storing executable program code; a processor coupled to the memory; The processor calls the executable program code stored in the memory to execute the building safety monitoring method based on sensor data linkage as described in any one of claims 1-5.

Images