Visual security and protection data processing method and system

Abstract

Disclosed in the present invention are a visual security and protection data processing method and system. The method comprises: acquiring sensing data and user operation data in a target security and protection region; on the basis of the sensing data, determining the number of personnel corresponding to each sub-region of the target security and protection region; on the basis of the number of personnel corresponding to each sub-region and a preset correspondence among the number of personnel, device types and device operation parameters, determining a device operation reference parameter corresponding to each sub-region, and calculating an operation difference between the user operation data and the device operation reference parameter; and displaying, on a regional security and protection display interface, the sensing data, the user operation data, the number of personnel and the operation difference that correspond to each sub-region. It can be seen that the present invention can visually present situations in a security and protection region and effectively monitor security and protection situations in sub-regions, such that a user can visually and efficiently perform security and protection monitoring on the region.

Description

Visual security data processing method and system Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a visual security data processing method and system. Background Art

[0002] As processing facilities become increasingly large and complex, and driven by the trend of intelligent manufacturing, the number of equipment and safety hazards in processing plants or assembly lines are also increasing. How to conduct effective security monitoring is an important issue.

[0003] However, when implementing security monitoring, existing technologies do not consider the use of real-time sensor data and user operation data, and the use of algorithm prediction and other methods to improve the visualization and accuracy of security monitoring. Therefore, it is obvious that existing technologies have defects that need to be solved urgently. Summary of the Invention

[0004] The technical problem to be solved by the present invention is to provide a visual security data processing method and system, which can visually display the situation in the security area and effectively monitor the security situation of the sub-area, so that users can intuitively and efficiently monitor the security of the area.

[0005] In order to solve the above technical problems, the first aspect of the present invention discloses a visual security data processing method, the method comprising:

[0006] Acquire sensing data of multiple security sensors and user operation data of multiple security working devices within the target security area;

[0007] Determining the number of personnel corresponding to each sub-area of ​​the target security area based on the sensor data and a prediction algorithm;

[0008] Determining the device operation reference parameters corresponding to each sub-area based on the number of personnel corresponding to each sub-area and the preset correspondence between the number of personnel, device type, and device operation parameters, and calculating the operation difference between the user operation data and the device operation reference parameters in each sub-area;

[0009] The sensor data, the user operation data, the number of personnel and the operation difference corresponding to each sub-area are displayed on the regional security display interface corresponding to the target security area.

[0010] As an optional embodiment, in the first aspect of the present invention, the sensor data includes image sensor data, infrared sensor data and sound sensor data; and / or, the device type of the security work equipment is cooling pump equipment, cooling tower equipment, computer equipment, valve equipment or access control equipment.

[0011] As an optional embodiment, in the first aspect of the present invention, determining the number of personnel corresponding to each sub-area of ​​the target security area based on the sensor data and a prediction algorithm includes:

[0012] Determining the sensing data acquired by all the security sensors in each sub-area of ​​the target security area;

[0013] For each of the sub-areas, grouping all the sensor data corresponding to the sub-area according to the sensor location rule to obtain an entry and exit area sensor data group, a stay area sensor data group, and an intersection area sensor data group corresponding to the sub-area;

[0014] According to the entry and exit area sensor data group, the stay area sensor data group and the intersection area sensor data group corresponding to the sub-area, the number of people corresponding to the sub-area is determined based on the neural network prediction algorithm.

[0015] As an optional embodiment, in the first aspect of the present invention, grouping all the sensor data corresponding to the sub-area according to the sensor location rule to obtain the entry and exit area sensor data group, the stay area sensor data group, and the intersection area sensor data group corresponding to the sub-area includes:

[0016] The sensing data acquired by all the security sensors in the intersection area of ​​the sub-area that has a passage without access control with other sub-areas are grouped as an intersection area sensing data group;

[0017] Classifying the sensing data acquired by all the security sensors in the entry and exit area with access control in the sub-area as an entry and exit area sensing data group;

[0018] For all other sensor data in the sub-area except the intersection area sensor data group and the entry and exit area sensor data group, calculating the distance between the sensor position of each other sensor data and the position of the center of people gathering corresponding to the sub-area;

[0019] All other sensing data whose position distance is less than a preset distance threshold are classified as a stay area sensing data group.

[0020] As an optional embodiment, in the first aspect of the present invention, determining the number of people corresponding to the sub-area based on the entry and exit area sensor data group, the stay area sensor data group, and the intersection area sensor data group corresponding to the sub-area based on a neural network prediction algorithm includes:

[0021] Inputting the entry and exit sensor data set corresponding to the sub-area into a trained number prediction neural network model to obtain a first number of people predicted for the sub-area; the number prediction neural network is trained using a training data set including a plurality of training sensor data and corresponding number of people annotated;

[0022] Inputting the stay area sensor data group corresponding to the sub-area into the number of people prediction neural network model to obtain a second person prediction value corresponding to the sub-area;

[0023] Inputting the intersection area sensor data group corresponding to the sub-area into the number of people prediction neural network model to obtain a third person prediction value corresponding to the sub-area;

[0024] Calculate the weighted average of the first personnel prediction value, the second personnel prediction value, and the third personnel prediction value to obtain the number of people corresponding to the sub-area; wherein the weights of the first personnel prediction value, the second personnel prediction value, and the third personnel prediction value decrease in sequence, the weight of the first personnel prediction value is inversely proportional to the amount of data in the entry and exit area sensor data group, the weight of the second personnel prediction value is proportional to the amount of data in the stay area sensor data group, and the weight of the third personnel prediction value is inversely proportional to the area ratio of the intersection area to the total area of ​​the sub-area.

[0025] As an optional embodiment, in the first aspect of the present invention, determining the device operation reference parameters corresponding to each sub-area based on the number of personnel corresponding to each sub-area and the preset correspondence between the number of personnel, device type, and device operation parameters includes:

[0026] For each of the sub-areas, the number of personnel corresponding to the sub-area is input into a parameter prediction neural network prediction model corresponding to different equipment operating parameters of different equipment types, so as to obtain a plurality of predicted equipment operating parameters corresponding to all equipment types in the sub-area; the parameter prediction neural network prediction model is trained using a training data set including a plurality of training personnel numbers corresponding to the equipment types and the corresponding equipment operating parameters;

[0027] The multiple predicted device operation parameters are determined as device operation reference parameters corresponding to the sub-area; the device operation parameters and the predicted device operation parameters both include at least one of device operation frequency, device operation type, and device operation speed.

[0028] As an optional embodiment, in the first aspect of the present invention, the method further comprises:

[0029] When the operation difference corresponding to any of the sub-regions is greater than a preset difference threshold, the prominence of the display parameters of the sub-region is increased, and an alarm is issued for the sub-region; the prominence includes at least one of color prominence, brightness prominence, size prominence, and position prominence;

[0030] When the operation difference corresponding to multiple sub-areas is greater than the difference threshold, when there are multiple sub-areas that meet the continuous area rule among the multiple sub-areas, the prominence of the display parameters corresponding to the multiple sub-areas that meet the continuous area rule is adjusted to be higher than that of other sub-areas, and the alarm level corresponding to the multiple sub-areas that meet the continuous area rule is determined to be higher than that of other sub-areas.

[0031] A second aspect of the present invention discloses a visual security data processing system, the system comprising:

[0032] An acquisition module is used to acquire sensing data of multiple security sensors and user operation data of multiple security working devices in the target security area;

[0033] a determination module, configured to determine the number of personnel corresponding to each sub-area of ​​the target security area based on the sensor data and a prediction algorithm;

[0034] a calculation module, configured to determine the device operation reference parameters corresponding to each sub-area based on the number of personnel corresponding to each sub-area and the preset correspondence between the number of personnel, device type, and device operation parameters, and calculate the operation difference between the user operation data in each sub-area and the device operation reference parameters;

[0035] The display module is used to display the sensor data, the user operation data, the number of personnel and the operation difference corresponding to each sub-area on the regional security display interface corresponding to the target security area.

[0036] As an optional embodiment, in the second aspect of the present invention, the sensor data includes image sensor data, infrared sensor data and sound sensor data; and / or, the device type of the security work equipment is cooling pump equipment, cooling tower equipment, computer equipment, valve equipment or access control equipment.

[0037] As an optional embodiment, in the second aspect of the present invention, the specific manner in which the determination module determines the number of personnel corresponding to each sub-area of ​​the target security area based on the sensor data and a prediction algorithm includes:

[0038] Determining the sensing data acquired by all the security sensors in each sub-area of ​​the target security area;

[0039] For each of the sub-areas, grouping all the sensor data corresponding to the sub-area according to the sensor location rule to obtain an entry and exit area sensor data group, a stay area sensor data group, and an intersection area sensor data group corresponding to the sub-area;

[0040] According to the entry and exit area sensor data group, the stay area sensor data group and the intersection area sensor data group corresponding to the sub-area, the number of people corresponding to the sub-area is determined based on the neural network prediction algorithm.

[0041] As an optional embodiment, in the second aspect of the present invention, the specific manner in which the determination module groups all the sensor data corresponding to the sub-area according to the sensor location rule to obtain the entry and exit area sensor data group, the stay area sensor data group, and the intersection area sensor data group corresponding to the sub-area includes:

[0042] The sensing data acquired by all the security sensors in the intersection area of ​​the sub-area that has a passage without access control with other sub-areas are grouped as an intersection area sensing data group;

[0043] Classifying the sensing data acquired by all the security sensors in the entry and exit area with access control in the sub-area as an entry and exit area sensing data group;

[0044] For all other sensor data in the sub-area except the intersection area sensor data group and the entry and exit area sensor data group, calculating the distance between the sensor position of each other sensor data and the position of the center of people gathering corresponding to the sub-area;

[0045] All other sensing data whose position distance is less than a preset distance threshold are classified as a stay area sensing data group.

[0046] As an optional embodiment, in the second aspect of the present invention, the specific method for the determination module to determine the number of people corresponding to the sub-area based on the neural network prediction algorithm according to the entry and exit area sensor data group, the stay area sensor data group, and the intersection area sensor data group corresponding to the sub-area includes:

[0047] Inputting the entry and exit sensor data set corresponding to the sub-area into a trained number prediction neural network model to obtain a first number of people predicted for the sub-area; the number prediction neural network is trained using a training data set including a plurality of training sensor data and corresponding number of people annotated;

[0048] Inputting the stay area sensor data group corresponding to the sub-area into the number of people prediction neural network model to obtain a second person prediction value corresponding to the sub-area;

[0049] Inputting the intersection area sensor data group corresponding to the sub-area into the number of people prediction neural network model to obtain a third person prediction value corresponding to the sub-area;

[0050] Calculate the weighted average of the first personnel prediction value, the second personnel prediction value, and the third personnel prediction value to obtain the number of people corresponding to the sub-area; wherein the weights of the first personnel prediction value, the second personnel prediction value, and the third personnel prediction value decrease in sequence, the weight of the first personnel prediction value is inversely proportional to the amount of data in the entry and exit area sensor data group, the weight of the second personnel prediction value is proportional to the amount of data in the stay area sensor data group, and the weight of the third personnel prediction value is inversely proportional to the area ratio of the intersection area to the total area of ​​the sub-area.

[0051] As an optional embodiment, in the second aspect of the present invention, the calculation module determines the specific manner of the device operation reference parameter corresponding to each sub-area based on the number of personnel corresponding to each sub-area and the preset correspondence between the number of personnel, device type, and device operation parameter, including:

[0052] For each of the sub-areas, the number of personnel corresponding to the sub-area is input into a parameter prediction neural network prediction model corresponding to different equipment operating parameters of different equipment types, so as to obtain a plurality of predicted equipment operating parameters corresponding to all equipment types in the sub-area; the parameter prediction neural network prediction model is trained using a training data set including a plurality of training personnel numbers corresponding to the equipment types and the corresponding equipment operating parameters;

[0053] The multiple predicted device operation parameters are determined as device operation reference parameters corresponding to the sub-area; the device operation parameters and the predicted device operation parameters both include at least one of device operation frequency, device operation type, and device operation speed.

[0054] As an optional implementation, in the second aspect of the present invention, the display module is further configured to perform the following steps:

[0055] When the operation difference corresponding to any of the sub-regions is greater than a preset difference threshold, the prominence of the display parameters of the sub-region is increased, and an alarm is issued for the sub-region; the prominence includes at least one of color prominence, brightness prominence, size prominence, and position prominence;

[0056] When the operation difference corresponding to multiple sub-areas is greater than the difference threshold, when there are multiple sub-areas that meet the continuous area rule among the multiple sub-areas, the prominence of the display parameters corresponding to the multiple sub-areas that meet the continuous area rule is adjusted to be higher than that of other sub-areas, and the alarm level corresponding to the multiple sub-areas that meet the continuous area rule is determined to be higher than that of other sub-areas.

[0057] A third aspect of the present invention discloses another visual security data processing system, the system comprising:

[0058] a memory storing executable program code;

[0059] a processor coupled to the memory;

[0060] The processor calls the executable program code stored in the memory to execute part or all of the steps in the visual security data processing method disclosed in the first aspect of the present invention.

[0061] 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 visual security data processing method disclosed in the first aspect of the present invention.

[0062] Compared with the prior art, the present invention has the following beneficial effects:

[0063] The present invention can determine the number of people and the degree of difference in equipment operation in a sub-area based on sensor data and user operation data, and further display them on the interface, thereby being able to visually display the situation in the security area and effectively monitor the security situation of the sub-area, so that users can intuitively and efficiently monitor the security of the area. BRIEF DESCRIPTION OF THE DRAWINGS

[0064] 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.

[0065] FIG1 is a flow chart of a method for processing visual security data according to an embodiment of the present invention;

[0066] FIG2 is a schematic diagram of the structure of a visual security data processing system disclosed in an embodiment of the present invention;

[0067] FIG3 is a schematic structural diagram of another visual security data processing system disclosed in an embodiment of the present invention. DETAILED DESCRIPTION

[0068] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings of 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. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0069] The terms "first," "second," and so on, in the description and claims of the present invention and the accompanying drawings are used to distinguish between different items, not to describe a specific order. Furthermore, the terms "including," "having," and any variations thereof, are intended to cover non-exclusive inclusions. For example, a process, method, system, product, or end comprising a series of steps or elements is not limited to the listed steps or elements but may optionally include steps or elements not listed, or may optionally include other steps or elements inherent to the process, method, product, or end.

[0070] References herein to "embodiments" mean that a particular feature, structure, or characteristic described in connection with the embodiments may be included in at least one embodiment of the present invention. The appearance of this phrase in various places in the specification does not necessarily refer to the same embodiment, nor does it constitute a separate or alternative embodiment that is mutually exclusive of other embodiments. It is understood, both explicitly and implicitly, by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0071] The present invention discloses a visual security data processing method and system that can determine the number of people and the degree of equipment operation differences within a sub-area based on sensor data and user operation data, and further display them on the interface. This enables a visual display of the situation within the security area and effectively monitors the security status of the sub-area, allowing users to intuitively and efficiently monitor the security of the area. Detailed descriptions are given below.

[0072] Example 1

[0073] Please refer to Figure 1, which is a flow chart of a method for processing visual security data disclosed in an embodiment of the present invention. The method described in Figure 1 can be applied to corresponding data processing devices, data processing terminals, and data processing servers. The server can be a local server or a cloud server, and the present invention is not limited thereto. As shown in Figure 1, the method for processing visual security data can include the following operations:

[0074] 101. Acquire sensing data of multiple security sensors and user operation data of multiple security working devices within a target security area.

[0075] Optionally, the sensor data includes image sensor data, infrared sensor data and sound sensor data.

[0076] Optionally, the device type of the security work equipment is cooling pump equipment, cooling tower equipment, computer equipment, valve equipment or access control equipment.

[0077] 102. Based on the sensor data and prediction algorithm, determine the number of personnel corresponding to each sub-area of ​​the target security area.

[0078] 103. Determine the device operation reference parameters corresponding to each sub-area based on the number of personnel corresponding to each sub-area and the correspondence between the preset number of personnel, device type, and device operation parameters, and calculate the operation difference between the user operation data of each sub-area and the device operation reference parameters.

[0079] Specifically, the operation difference can be determined by vectorizing the user operation data and the device reference parameters and then calculating the vector distance.

[0080] 104. Display the sensor data, user operation data, number of personnel, and operation difference corresponding to each sub-area on the regional security display interface corresponding to the target security area.

[0081] It can be seen that the method described in the embodiment of the present invention can determine the number of people and the degree of difference in equipment operation in the sub-area based on sensor data and user operation data, and further display them on the interface, so as to realize the visual display of the situation in the security area and effectively monitor the security situation of the sub-area, so that users can monitor the security of the area intuitively and efficiently.

[0082] As an optional embodiment, in the above step, determining the number of personnel corresponding to each sub-area of ​​the target security area based on the sensor data and a prediction algorithm includes:

[0083] Determining sensor data acquired by all security sensors in each sub-area of ​​the target security area;

[0084] For each sub-area, all sensor data corresponding to the sub-area are grouped according to the sensor location rule to obtain the entry and exit area sensor data group, the stay area sensor data group, and the intersection area sensor data group corresponding to the sub-area;

[0085] According to the entry and exit area sensor data group, the stay area sensor data group and the intersection area sensor data group corresponding to the sub-area, the number of people corresponding to the sub-area is determined based on the neural network prediction algorithm.

[0086] Through the above embodiment, all sensor data corresponding to the sub-area can be grouped according to the sensor location rules to obtain the entry and exit area sensor data group, the stay area sensor data group and the intersection area sensor data group corresponding to the sub-area, and the number of people corresponding to the sub-area can be determined based on the neural network prediction algorithm, so that the number of people can be determined more accurately, which is convenient for the subsequent visualization of the situation in the security area and the effective monitoring of the security situation of the sub-area, so that users can monitor the security of the area intuitively and efficiently.

[0087] As an optional embodiment, in the above step, all sensor data corresponding to the sub-area are grouped according to the sensor location rule to obtain the entry and exit area sensor data group, the stay area sensor data group, and the intersection area sensor data group corresponding to the sub-area, including:

[0088] The sensor data acquired by all security sensors in the intersection area of ​​the sub-area that has a passage without access control with other sub-areas are classified into the intersection area sensor data group;

[0089] The sensor data acquired by all security sensors in the entry and exit area with access control in the sub-area are classified into the entry and exit area sensor data group;

[0090] For all other sensor data in the sub-area except the intersection area sensor data group and the entry and exit area sensor data group, calculate the distance between the sensor position of each other sensor data and the position of the center of the gathering of people corresponding to the sub-area;

[0091] All other sensor data with a location distance less than a preset distance threshold are classified as a stay area sensor data group.

[0092] Through the above embodiment, all sensor data corresponding to the sub-area can be grouped according to the sensor location rules to obtain the entry and exit area sensor data group, the stay area sensor data group and the intersection area sensor data group corresponding to the sub-area, so that the number of people can be determined more accurately in the future, which facilitates the subsequent visualization of the situation in the security area and the effective monitoring of the security situation of the sub-area, so that users can monitor the security of the area intuitively and efficiently.

[0093] As an optional embodiment, in the above step, determining the number of people corresponding to the sub-area based on the neural network prediction algorithm according to the entry and exit area sensor data group, the stay area sensor data group, and the intersection area sensor data group corresponding to the sub-area includes:

[0094] Inputting the entry and exit sensor data set corresponding to the sub-area into a trained number prediction neural network model to obtain a first number of people predicted for the sub-area; the number prediction neural network is trained using a training data set including a plurality of training sensor data and corresponding number of people annotated;

[0095] Inputting the stay area sensor data group corresponding to the sub-area into the number of people prediction neural network model to obtain a second person prediction value corresponding to the sub-area;

[0096] Inputting the intersection area sensor data group corresponding to the sub-area into the number of people prediction neural network model to obtain a third person prediction value corresponding to the sub-area;

[0097] Calculate the weighted average of the first person prediction value, the second person prediction value, and the third person prediction value to obtain the number of people corresponding to the sub-area; wherein the weights of the first person prediction value, the second person prediction value, and the third person prediction value decrease in sequence, the weight of the first person prediction value is inversely proportional to the amount of data in the sensor data group of the entry and exit area, the weight of the second person prediction value is proportional to the amount of data in the sensor data group of the stay area, and the weight of the third person prediction value is inversely proportional to the area ratio of the intersection area to the total area of ​​the sub-area.

[0098] Specifically, the above-mentioned weight determination is a rule determined by the operator based on the prediction results when actually implementing the technical solution of the present invention. Specifically, the prediction accuracy of the sensor data of the entry and exit area is greater than that of the stay area and the intersection area. When the number of people entering and exiting the area is too many, the prediction accuracy of the sensor data decreases. On the contrary, the more people stay in the stay area, the higher the prediction accuracy of the sensor data. In addition, the prediction accuracy of the sensor data in the intersection area is the lowest because people can move freely. The larger the area of ​​the intersection area, the lower the prediction accuracy of the sensor data.

[0099] Optionally, the neural network models in the present invention can all be neural network models with CNN structure, RNN structure or LTSM structure, and are trained until convergence through corresponding gradient descent algorithm and loss function. The operator can choose according to the specific implementation scenario and data characteristics, and the present invention does not limit it.

[0100] Through the above embodiment, the entry and exit area sensor data group, the stay area sensor data group and the intersection area sensor data group can be respectively input into the neural network model for prediction and weighted calculation can be performed based on the regional characteristics to more accurately determine the number of people, so as to facilitate the subsequent visualization of the situation in the security area and effectively monitor the security situation of the sub-area, so that users can monitor the security of the area intuitively and efficiently.

[0101] As an optional embodiment, in the above steps, determining the equipment operation reference parameters corresponding to each sub-area based on the number of personnel corresponding to each sub-area and the preset correspondence between the number of personnel, equipment type, and equipment operation parameters includes:

[0102] For each sub-region, the number of personnel corresponding to the sub-region is input into a parameter prediction neural network prediction model corresponding to different equipment operating parameters of different equipment types, so as to obtain multiple predicted equipment operating parameters corresponding to all equipment types in the sub-region; the parameter prediction neural network prediction model is trained using a training data set including a plurality of training personnel numbers corresponding to the equipment types and the corresponding equipment operating parameters.

[0103] A plurality of predicted device operating parameters are determined as device operating reference parameters corresponding to the sub-region; the device operating parameters and the predicted device operating parameters both include at least one of a device operating frequency, a device operating type, and a device operating speed.

[0104] Through the above embodiment, the number of personnel corresponding to the sub-area can be input into the parameter prediction neural network prediction model corresponding to different device operation parameters of different device types to obtain multiple predicted device operation parameters corresponding to all device types in the sub-area, so that the operation difference corresponding to the sub-area can be calculated in the future to accurately measure the degree of operation abnormality in the sub-area, which is convenient for the subsequent visualization of the situation in the security area and effective monitoring of the security situation of the sub-area, so that users can monitor the security of the area intuitively and efficiently.

[0105] As an optional embodiment, in the above steps, the method further includes:

[0106] When the difference in operation corresponding to any sub-region is greater than a preset difference threshold, the prominence of the display parameters of the sub-region is increased and an alarm is issued for the sub-region; the prominence includes at least one of color prominence, brightness prominence, size prominence, and position prominence;

[0107] When the operation difference corresponding to multiple sub-areas is greater than the difference threshold, when there are multiple sub-areas that meet the continuous area rule among the multiple sub-areas, the prominence of the display parameters corresponding to the multiple sub-areas that meet the continuous area rule is adjusted to be higher than that of other sub-areas, and the alarm level corresponding to the multiple sub-areas that meet the continuous area rule is determined to be higher than that of other sub-areas.

[0108] Optionally, any two adjacent sub-regions in the multiple sub-regions that meet the continuous region rule have at least one intersection region, thereby being able to effectively characterize the movement trajectory of hackers, saboteurs, or sabotage sources.

[0109] Through the above embodiment, the prominence of the display parameters corresponding to multiple sub-areas that meet the continuous area rule can be adjusted to be higher than that of other sub-areas, and the alarm level corresponding to multiple sub-areas that meet the continuous area rule can be determined to be higher than that of other sub-areas, so that the movement trajectory of possible sources of destruction can be highlighted and alarmed intuitively and efficiently, so that users can monitor the security of the area intuitively and efficiently.

[0110] Example 2

[0111] Please refer to Figure 2, which is a schematic diagram of the structure of a visual security data processing system disclosed in an embodiment of the present invention. The system described in Figure 2 can be applied to corresponding data processing equipment, data processing terminals, and data processing servers. The server can be a local server or a cloud server, which is not limited in the embodiment of the present invention. As shown in Figure 2, the system may include:

[0112] An acquisition module 201 is configured to acquire sensing data of multiple security sensors and user operation data of multiple security working devices within a target security area;

[0113] A determination module 202 is configured to determine the number of personnel corresponding to each sub-area of ​​the target security area based on the sensor data and a prediction algorithm;

[0114] Calculation module 203, configured to determine the device operation reference parameters corresponding to each sub-area based on the number of personnel corresponding to each sub-area and the preset correspondence between the number of personnel, device type, and device operation parameters, and calculate the operation difference between the user operation data of each sub-area and the device operation reference parameters;

[0115] The display module 204 is used to display the sensor data, user operation data, number of personnel and operation difference corresponding to each sub-area on the regional security display interface corresponding to the target security area.

[0116] As an optional embodiment, the sensor data includes image sensor data, infrared sensor data and sound sensor data; and / or, the device type of the security work equipment is cooling pump equipment, cooling tower equipment, computer equipment, valve equipment or access control equipment.

[0117] As an optional embodiment, the specific method for determining the number of personnel corresponding to each sub-area of ​​the target security area by the determination module 202 based on the sensor data and the prediction algorithm includes:

[0118] Determining sensor data acquired by all security sensors in each sub-area of ​​the target security area;

[0119] For each sub-area, all sensor data corresponding to the sub-area are grouped according to the sensor location rule to obtain the entry and exit area sensor data group, the stay area sensor data group, and the intersection area sensor data group corresponding to the sub-area;

[0120] According to the entry and exit area sensor data group, the stay area sensor data group and the intersection area sensor data group corresponding to the sub-area, the number of people corresponding to the sub-area is determined based on the neural network prediction algorithm.

[0121] As an optional embodiment, the determination module 202 groups all sensor data corresponding to the sub-area according to the sensor location rule to obtain the entry and exit area sensor data group, the stay area sensor data group, and the intersection area sensor data group corresponding to the sub-area, including:

[0122] The sensor data acquired by all security sensors in the intersection area of ​​the sub-area that has a passage without access control with other sub-areas are classified into the intersection area sensor data group;

[0123] The sensor data acquired by all security sensors in the entry and exit area with access control in the sub-area are classified into the entry and exit area sensor data group;

[0124] For all other sensor data in the sub-area except the intersection area sensor data group and the entry and exit area sensor data group, calculate the distance between the sensor position of each other sensor data and the position of the center of the gathering of people corresponding to the sub-area;

[0125] All other sensor data with a location distance less than a preset distance threshold are classified as a stay area sensor data group.

[0126] As an optional embodiment, the determination module 202 determines the number of people corresponding to the sub-area based on the entry and exit area sensor data group, the stay area sensor data group, and the intersection area sensor data group corresponding to the sub-area using a neural network prediction algorithm, including:

[0127] Inputting the entry and exit sensor data set corresponding to the sub-area into a trained number prediction neural network model to obtain a first number of people predicted for the sub-area; the number prediction neural network is trained using a training data set including a plurality of training sensor data and corresponding number of people annotated;

[0128] Inputting the stay area sensor data group corresponding to the sub-area into the number of people prediction neural network model to obtain a second person prediction value corresponding to the sub-area;

[0129] Inputting the intersection area sensor data group corresponding to the sub-area into the number of people prediction neural network model to obtain a third person prediction value corresponding to the sub-area;

[0130] Calculate the weighted average of the first person prediction value, the second person prediction value, and the third person prediction value to obtain the number of people corresponding to the sub-area; wherein the weights of the first person prediction value, the second person prediction value, and the third person prediction value decrease in sequence, the weight of the first person prediction value is inversely proportional to the amount of data in the sensor data group of the entry and exit area, the weight of the second person prediction value is proportional to the amount of data in the sensor data group of the stay area, and the weight of the third person prediction value is inversely proportional to the area ratio of the intersection area to the total area of ​​the sub-area.

[0131] As an optional embodiment, the calculation module 203 determines the specific manner of the device operation reference parameter corresponding to each sub-area based on the number of personnel corresponding to each sub-area and the preset correspondence between the number of personnel, device type, and device operation parameter, including:

[0132] For each sub-region, the number of personnel corresponding to the sub-region is input into a parameter prediction neural network prediction model corresponding to different equipment operating parameters of different equipment types, so as to obtain multiple predicted equipment operating parameters corresponding to all equipment types in the sub-region; the parameter prediction neural network prediction model is trained using a training data set including a plurality of training personnel numbers corresponding to the equipment types and the corresponding equipment operating parameters.

[0133] A plurality of predicted device operating parameters are determined as device operating reference parameters corresponding to the sub-region; the device operating parameters and the predicted device operating parameters both include at least one of a device operating frequency, a device operating type, and a device operating speed.

[0134] As an optional embodiment, the display module 204 is further configured to perform the following steps:

[0135] When the difference in operation corresponding to any sub-region is greater than a preset difference threshold, the prominence of the display parameters of the sub-region is increased and an alarm is issued for the sub-region; the prominence includes at least one of color prominence, brightness prominence, size prominence, and position prominence;

[0136] When the operation difference corresponding to multiple sub-areas is greater than the difference threshold, when there are multiple sub-areas that meet the continuous area rule among the multiple sub-areas, the prominence of the display parameters corresponding to the multiple sub-areas that meet the continuous area rule is adjusted to be higher than that of other sub-areas, and the alarm level corresponding to the multiple sub-areas that meet the continuous area rule is determined to be higher than that of other sub-areas.

[0137] The module details and technical effects in the embodiment of the present invention can be referred to the description in the first embodiment and will not be repeated here.

[0138] Example 3

[0139] Please refer to Figure 3, which is a schematic diagram of the structure of another visual security data processing system disclosed in an embodiment of the present invention. As shown in Figure 3, the system may include:

[0140] A memory 301 storing executable program code;

[0141] a processor 302 coupled to the memory 301;

[0142] The processor 302 calls the executable program code stored in the memory 301 to execute part or all of the steps in the visual security data processing method disclosed in the first embodiment of the present invention.

[0143] Example 4

[0144] An embodiment 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 visual security data processing method disclosed in the first embodiment of the present invention.

[0145] The system embodiments described above are merely illustrative. The modules described as separate components may or may not be physically separate, and the components shown as modules may or may not be physical modules, i.e., they may be located in one place or distributed across multiple network modules. Some or all of the modules may be selected based on actual needs to achieve the objectives of the present embodiment. Persons of ordinary skill in the art will be able to understand and implement the present embodiment without inventive effort.

[0146] Through the detailed description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus the necessary general hardware platform, or of course, by means of hardware. Based on this understanding, the above technical solution, in essence, or the portion that contributes to the prior art, can be embodied in the form of a software product, which can be stored in a computer-readable storage medium, including a read-only memory (ROM), a random access memory (RAM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), a one-time programmable read-only memory (OTPROM), an electronically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disk storage, magnetic disk storage, magnetic tape storage, or any other computer-readable medium capable of carrying or storing data.

[0147] Finally, it should be noted that the visual security data processing method and system disclosed in the embodiments of the present invention are only preferred embodiments of the present invention, and are only used to illustrate the technical solutions of the present invention, rather than to limit them. 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 can still be modified, or some of the technical features therein can be replaced 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 visual security data processing method, characterized in that: The method comprises: Acquire sensing data of multiple security sensors and user operation data of multiple security working devices in the target security area; Determine the number of personnel corresponding to each sub-area of ​​the target security area based on the sensor data and a prediction algorithm; According to the number of personnel corresponding to each of the sub-areas, and the correspondence between the number of personnel, the type of equipment, and the equipment operation parameters, the equipment operation reference parameters corresponding to each of the sub-areas are determined, and the operation difference between the user operation data of each of the sub-areas and the equipment operation reference parameters is calculated; The sensor data, the user operation data, the number of personnel and the operation difference corresponding to each of the sub-areas are displayed on the regional security display interface corresponding to the target security area.

2. The visual security data processing method according to claim 1, characterized in that: The sensor data includes image sensor data, infrared sensor data and sound sensor data; and / or, the device type of the security work equipment is cooling pump equipment, cooling tower equipment, computer equipment, valve equipment or access control equipment.

3. The visual security data processing method according to claim 2, characterized in that: The step of determining the number of personnel corresponding to each sub-area of ​​the target security area based on the sensor data and a prediction algorithm includes: Determine the sensing data acquired by all the security sensors in each sub-area of ​​the target security area; For each of the sub-areas, grouping all the sensor data corresponding to the sub-area according to the sensor position rule to obtain an entry-exit area sensor data group, a stay area sensor data group and an intersection area sensor data group corresponding to the sub-area; According to the entry and exit area sensor data group, the stay area sensor data group and the intersection area sensor data group corresponding to the sub-area, based on the neural network prediction algorithm, the number of people corresponding to the sub-area is determined.

4. The visual security data processing method according to claim 3 is characterized in that: The step of grouping all the sensing data corresponding to the sub-area according to the sensing position rule to obtain the entry and exit area sensing data group, the stay area sensing data group and the intersection area sensing data group corresponding to the sub-area includes: Classify the sensing data acquired by all the security sensors in the intersection area of ​​the sub-area that has a passageway without access control with other sub-areas as an intersection area sensing data group; Classify the sensing data acquired by all the security sensors in the entry and exit area with access control in the sub-area as an entry and exit area sensing data group; For all other sensor data in the sub-area except the intersection area sensor data group and the entry and exit area sensor data group, calculate the distance between the sensor position of each other sensor data and the position of the center of personnel gathering corresponding to the sub-area; All other sensing data whose position distance is less than a preset distance threshold are classified as a stay area sensing data group.

5. The visual security data processing method according to claim 4, characterized in that: The method of determining the number of people corresponding to the sub-area based on the entry and exit area sensor data group, the stay area sensor data group and the intersection area sensor data group corresponding to the sub-area and based on a neural network prediction algorithm includes: Inputting the in-and-out area sensor data group corresponding to the sub-area into a trained population prediction neural network model to obtain a first population prediction value corresponding to the sub-area; the population prediction neural network is trained by a training data set including a plurality of training sensor data and corresponding personnel quantity annotations; Inputting the stay area sensor data group corresponding to the sub-area into the number of people prediction neural network model to obtain a second person prediction value corresponding to the sub-area; Inputting the intersection area sensor data group corresponding to the sub-area into the number of people prediction neural network model to obtain a third person prediction value corresponding to the sub-area; Calculate the weighted average of the first personnel prediction value, the second personnel prediction value and the third personnel prediction value to obtain the number of people corresponding to the sub-area; wherein the weights of the first personnel prediction value, the second personnel prediction value and the third personnel prediction value decrease in sequence, the weight of the first personnel prediction value is inversely proportional to the amount of data in the entry and exit area sensor data group, the weight of the second personnel prediction value is directly proportional to the amount of data in the stay area sensor data group, and the weight of the third personnel prediction value is inversely proportional to the area ratio of the intersection area to the total area of ​​the sub-area.

6. The visual security data processing method according to claim 1, characterized in that: Determining the equipment operation reference parameters corresponding to each of the sub-areas according to the number of personnel corresponding to each of the sub-areas and the preset correspondence between the number of personnel and the equipment type and the equipment operation parameters includes: For each of the sub-areas, the number of personnel corresponding to the sub-area is respectively input into the parameter prediction neural network prediction model corresponding to different equipment operation parameters of different equipment types, so as to obtain a plurality of predicted equipment operation parameters corresponding to all equipment types in the sub-area; the parameter prediction neural network prediction model is trained by a training data set including a plurality of training personnel numbers corresponding to the equipment types and the corresponding equipment operation parameters. The multiple predicted device operation parameters are determined as device operation reference parameters corresponding to the sub-area; the device operation parameters and the predicted device operation parameters both include at least one of device operation frequency, device operation type and device operation speed.

7. The visual security data processing method according to claim 6, characterized in that: The method further comprises: When the operation difference corresponding to any of the sub-regions is greater than a preset difference threshold, the prominence of the display parameters of the sub-region is increased, and an alarm is issued for the sub-region; the prominence includes at least one of color prominence, brightness prominence, size prominence and position prominence; When the operation difference corresponding to multiple sub-areas is greater than the difference threshold, when there are multiple sub-areas that meet the continuous area rule among the multiple sub-areas, the prominence of the display parameters corresponding to the multiple sub-areas that meet the continuous area rule is adjusted to be higher than that of the other sub-areas, and the alarm level corresponding to the multiple sub-areas that meet the continuous area rule is determined to be higher than that of the other sub-areas.

8. A visual security data processing system, characterized in that: The system comprises: An acquisition module, used to acquire sensing data of multiple security sensors and user operation data of multiple security working devices in a target security area; A determination module, configured to determine the number of personnel corresponding to each sub-area of ​​the target security area based on the sensor data and a prediction algorithm; a calculation module, configured to determine the device operation reference parameters corresponding to each of the sub-areas according to the number of personnel corresponding to each of the sub-areas and the correspondence between the preset number of personnel, device type and device operation parameters, and calculate the operation difference between the user operation data of each of the sub-areas and the device operation reference parameters; The display module is used to display the sensor data, the user operation data, the number of personnel and the operation difference corresponding to each sub-area on the regional security display interface corresponding to the target security area.

9. A visual security data processing system, 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 visual security data processing method as described in any one of claims 1-7.

10. A computer storage medium, characterized in that: The computer storage medium stores computer instructions, and when the computer instructions are called, they are used to execute the visual security data processing method as described in any one of claims 1-7.

Images