Security risk determination method and device, computer equipment and readable storage medium

Abstract

The embodiment of the invention provides a safety risk determination method and device, computer equipment and a readable storage medium, and belongs to the technical field of safety production. The method comprises the steps of obtaining real-time sensing data, collected by a plurality of sensors, of a plurality of dangerous sources in a target area; classifying the real-time sensing data according to a preset rule; determining a corresponding dangerous source state according to the early warning data; determining the sensing risk of the target area according to all the dangerous source states; collecting images of a plurality of danger sources in a first preset time range; determining an image risk of the target area by using the image; and determining the security risk of the target area by using the sensing risk and the image risk. According to the method, the sensing risk is determined based on the real-time sensing data of the multiple hazard sources in the target area, the image risk is determined based on the images of the multiple hazard sources, and the safety risk of the target area is comprehensively determined based on the sensing risk and the image risk, so that the accuracy of the safety risk is improved, and a guarantee is provided for stable and safe operation of an enterprise.

Description

Technical Field

[0001] The present application relates to the field of production safety technology, and in particular to a method, device, computer equipment and readable storage medium for determining safety risks. Background Art

[0002] At present, the following methods are usually used for immediate warning of major hazards in enterprises:

[0003] Construct an information system platform for early warning and prevention of production safety of hazardous chemical production enterprises, pre-store static information such as basic information of hazardous chemical production enterprises and information on major hazard sources (quantity, distribution, hazard level) within the jurisdiction, and display the distribution area of ​​production enterprises, the number of major hazard sources, etc. in combination with GIS system maps;

[0004] Deploy enterprise major hazard source data collection systems in hazardous chemical production enterprises to collect monitoring data of major hazard sources (such as pressure vessels, reactors, process tanks, etc.) and report them to the information system platform via the Internet;

[0005] The enterprise production safety risk warning model algorithm is used on the information system platform to calculate the enterprise's current risk level based on the pre-stored major hazard source information and the monitoring data actually reported by the production enterprise, to assist in decision-making analysis.

[0006] However, this processing method only collects monitoring data of hazardous sources, which leads to inaccurate determination of safety risks. Summary of the invention

[0007] In view of this, the purpose of the embodiments of the present application is to provide a security risk determination method, apparatus, computer device and readable storage medium, which can solve the problem of inaccurate security risk determination in the existing environment.

[0008] In order to solve the above technical problems, this application is implemented as follows:

[0009] In a first aspect, an embodiment of the present application provides a method for determining a security risk, including:

[0010] Acquire real-time sensor data of multiple hazard sources within a target area collected by multiple sensors;

[0011] Classifying the real-time sensor data according to preset rules, wherein the preset rules include whether the real-time sensor data is normal and whether the state of the hazard source corresponding to the real-time sensor data is normal, and the categories of the real-time sensor data include warning data and normal data;

[0012] Determine the corresponding hazard source status according to the warning data;

[0013] Determining the sensing risk of the target area according to all the states of the hazard sources;

[0014] Collect images of the plurality of danger sources within a first preset time range;

[0015] determining an image risk of the target area using the image;

[0016] The security risk of the target area is determined using the sensed risk and the image risk.

[0017] According to a specific embodiment disclosed in the present application, the method further includes:

[0018] Verifying the normal data;

[0019] When the state of the danger source corresponding to the normal data is abnormal, the corresponding state of the danger source is corrected to normal using the verified normal data.

[0020] According to a specific embodiment disclosed in the present application, the method further includes:

[0021] Verifying the early warning data;

[0022] Determining the corresponding danger source status according to the early warning data includes:

[0023] The corresponding hazard source status is determined based on the verified warning data.

[0024] According to a specific implementation manner disclosed in the present application, before classifying the real-time sensor data according to a preset rule, the method further includes:

[0025] The real-time sensing data is pre-processed and subjected to data quality processing, wherein the data quality processing is used to confirm the credibility of the real-time sensing data.

[0026] According to a specific implementation method disclosed in the present application, the data quality processing of the real-time sensor data includes:

[0027] Comparing the real-time sensing data with the corresponding preset standard range, and marking the real-time sensing data that is outside the preset standard range;

[0028] Marking the real-time sensing data that has not changed within a second preset time range;

[0029] For the real-time sensing data of the switch type, marking the real-time sensing data whose jump times exceed a preset number within a third preset time range;

[0030] For the real-time sensor data of cumulative value type, marking the real-time sensor data that is opposite to the preset configuration trend;

[0031] The method further comprises:

[0032] The marked real-time sensing data is discarded.

[0033] According to a specific embodiment disclosed in the present application, the method further includes:

[0034] If the state of the hazard source corresponding to any one of the real-time sensing data changes repeatedly within a fourth preset time range, the hazard source state change information of the real-time sensing data within the fourth preset time range is merged.

[0035] According to a specific implementation method disclosed in the present application, the determining the image risk by using the image includes:

[0036] Using an artificial intelligence algorithm to identify the image to obtain an identification result, wherein the identification result includes whether there is any dangerous behavior in the image;

[0037] The image risk is determined according to the recognition result.

[0038] In a second aspect, an embodiment of the present application provides a security risk determination device, including:

[0039] An acquisition module, used to acquire real-time sensor data of multiple hazard sources in a target area collected by multiple sensors;

[0040] A classification module, used to classify the real-time sensor data according to preset rules, wherein the preset rules include whether the real-time sensor data is normal and whether the state of the hazard source corresponding to the real-time sensor data is normal, and the categories of the real-time sensor data include warning data and normal data;

[0041] A hazard source status determination module, used to determine the corresponding hazard source status according to the warning data;

[0042] A sensor risk determination module, used to determine the sensor risk of the target area according to the states of all the hazard sources;

[0043] An image acquisition module, used for acquiring images of the plurality of danger sources within a first preset time range;

[0044] An image risk determination module, used to determine the image risk of the target area using the image;

[0045] A security risk determination module is used to determine the security risk of the target area by using the sensing risk and the image risk.

[0046] In a third aspect, an embodiment of the present application provides a computer device, including a processor and a memory, wherein the memory stores a program or instruction, and when the program or instruction is executed by the processor, the steps of the method described in the first aspect are implemented.

[0047] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, on which a program or instruction is stored, and when the program or instruction is executed by a processor, the steps of the method described in the first aspect are implemented.

[0048] The above-mentioned embodiments of the present application provide a safety risk determination method, apparatus, computer equipment and readable storage medium, which determine the sensor risk based on the real-time sensor data of multiple hazardous sources in the target area, determine the image risk based on the images of the multiple hazardous sources, and then determine the safety risk of the target area based on the sensor risk and the image risk, thereby improving the accuracy of the safety risk and providing guarantee for the smooth and safe operation of the enterprise.

[0049] Other features and advantages of the embodiments of the present invention will be described in detail in the subsequent detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] In order to more clearly illustrate the technical solution of the present application, the following is a brief introduction to the drawings required for use in the embodiments. It should be understood that the following drawings only illustrate certain embodiments of the present application and should not be regarded as limiting the scope of protection of the present application. In each of the drawings, similar components are numbered similarly.

[0051] Figure 1 A flow chart of a security risk determination method provided by an embodiment of the present application is shown;

[0052] Figure 2 A schematic structural diagram of a security risk determination device provided in an embodiment of the present application is shown. DETAILED DESCRIPTION

[0053] The technical solutions in the embodiments of the present application will be described clearly and completely below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments.

[0054] The components of the embodiments of the present application generally described and shown in the drawings herein may be arranged and designed in various configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the application claimed for protection, but merely represents the selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without making creative work belong to the scope of protection of the present application.

[0055] Hereinafter, the terms "including", "having" and their cognates, which may be used in various embodiments of the present application, are intended only to indicate specific features, numbers, steps, operations, elements, components, or combinations of the foregoing items, and should not be understood as first excluding the existence of one or more other features, numbers, steps, operations, elements, components, or combinations of the foregoing items or adding the possibility of one or more features, numbers, steps, operations, elements, components, or combinations of the foregoing items.

[0056] Furthermore, the terms “first”, “second”, “third”, etc. are merely used for distinguishing descriptions and are not to be understood as indicating or implying relative importance.

[0057] Unless otherwise defined, all terms (including technical terms and scientific terms) used herein have the same meanings as those generally understood by those skilled in the art to which the various embodiments of the present application belong. The terms (such as those defined in generally used dictionaries) will be interpreted as having the same meanings as the contextual meanings in the relevant technical field and will not be interpreted as having idealized meanings or overly formal meanings unless clearly defined in the various embodiments of the present application.

[0058] See also Figure 1 , Figure 1 A flow chart of a method for determining security risks provided by an embodiment of the present application is shown. Figure 1 As shown, the method includes steps 110-170:

[0059] Step 110: Acquire real-time sensor data of multiple hazard sources in the target area collected by multiple sensors.

[0060] Specifically, the target area usually refers to the area where the enterprise is located, which can be the entire enterprise or a part of it. Sensors can be set within the preset range of the target area according to actual needs to realize the collection of real-time sensor data of hazardous sources. Real-time sensor data of hazardous sources include but are not limited to: real-time pressure, temperature, liquid level, flammable and explosive gas leakage concentration and toxic gas concentration; corresponding sensors include but are not limited to: pressure sensors, temperature sensors, liquid level sensors, flammable and explosive gas concentration sensors, and toxic gas concentration sensors.

[0061] Step 120: classify the real-time sensor data according to preset rules, wherein the preset rules include whether the real-time sensor data is normal and whether the state corresponding to the real-time sensor data is normal, and the categories of the real-time sensor data include warning data and normal data.

[0062] Specifically, when the real-time sensor data is normal and the state corresponding to the real-time sensor data is normal, the real-time sensor data is classified as normal data; in other cases, that is, when the real-time sensor data is abnormal and the state corresponding to the real-time sensor data is normal, when the real-time sensor data is normal and the state corresponding to the real-time sensor data is abnormal, when the real-time sensor data is abnormal and the state corresponding to the real-time sensor data is abnormal, the real-time sensor data is classified as warning data. In other words, if either the real-time sensor data or the state corresponding to the real-time sensor data is abnormal, it means that there may be a warning situation that needs to be processed, so it is classified as warning data.

[0063] Different types of real-time sensor data use different rules to determine whether they are abnormal. For example, real-time sensor data such as real-time pressure, temperature, and liquid level usually use the first and second level thresholds for judgment, that is, when it is less than or equal to the first level threshold, it is judged to be normal; when it is greater than the first level threshold and less than or equal to the second level threshold, it is judged to be possibly abnormal; when it is greater than the second level threshold, it is judged to be abnormal. Real-time sensor data of toxic gases is a switch type of data, which only needs to be judged based on a single condition of presence or absence to determine whether it is abnormal.

[0064] Step 130: Determine the corresponding hazard source status according to the warning data.

[0065] Specifically, based on the warning data in the above three different situations, the corresponding hazard source status can be determined.

[0066] In the embodiment of the present application, the early warning data includes alarm data, repeated alarm data and alarm elimination data. When the real-time sensor data is abnormal and the state corresponding to the real-time sensor data is normal, the early warning data is alarm data, and the corresponding state of the dangerous source changes from normal to abnormal; when the real-time sensor data is normal and the state corresponding to the real-time sensor data is abnormal, the early warning data is alarm elimination data, and the corresponding state of the dangerous source changes from abnormal to normal; when the real-time sensor data is abnormal and the state corresponding to the real-time sensor data is abnormal, the early warning data is repeated alarm data, and the corresponding state of the dangerous source remains abnormal.

[0067] Step 140: Determine the sensing risk of the hazard source according to the status of all the hazard sources.

[0068] Specifically, the risk of each hazard source can be determined according to the state of each hazard source and the corresponding weight, and then the sensing risk of the hazard source can be determined. The weight can be the R value of the hazard source. The R value of the hazard source can be understood as the degree of hazard of the hazard source, which is one of the important indicators for the hazard level rating of the hazard source.

[0069] It is understandable that a danger source in a normal state may not be involved in the determination of the sensing risk. In addition, the setting of the sensing risk and the determination logic can be set according to actual needs, and the embodiments of the present application are not limited to this. For example, the sensing risk may include particularly significant impact, significant impact, relatively large impact, general impact, and very small impact.

[0070] Step 150: Collect images of the multiple danger sources within a first preset time range.

[0071] Specifically, after obtaining the sensor risk of the target area based on the real-time sensor data, images of the hazard source within the first preset time range can also be collected, so as to make a comprehensive judgment using the real-time sensor data and the images. It is understandable that if the state of the hazard source is normal, the image of the hazard source may not be collected.

[0072] The first preset time range can be the time range before and after the collection time of the sensor data corresponding to the sensor risk. For example, if the collection time of the sensor data corresponding to the sensor risk is 7 o'clock, the first preset time range can be set to 10 minutes before and after 7 o'clock, that is, the time range from 6:50 to 7:10. It can be understood that the first preset time range and the first preset threshold can be set according to actual needs, and the embodiment of the present application does not limit this.

[0073] Step 160: Determine the image risk of the target area using the image.

[0074] Specifically, after the image of the target area is collected, the image risk of the target area can be determined using the image. The present application provides an image recognition based on an artificial intelligence algorithm to determine the image, and then, in an optional implementation, step 160 includes:

[0075] Using an artificial intelligence algorithm to identify the image to obtain an identification result, wherein the identification result includes whether there is any dangerous behavior in the image;

[0076] The image risk is determined according to the recognition result.

[0077] It is understandable that the artificial intelligence algorithm can be set according to actual needs, including but not limited to: Fourier fast transform, Kalman filter, Gaussian filter algorithm, artificial neural network.

[0078] It should be noted that dangerous behaviors include but are not limited to: not being the target operator, not wearing a helmet, not wearing a reflective vest, the presence of fireworks, working at height, using mobile phones and other electronic devices, smoking, and not wearing a mask. It can also identify whether the area where the dangerous behavior occurs is a preset dangerous area. It is understandable that when the dangerous behavior occurs in a dangerous area, the corresponding image risk level is higher.

[0079] Step 170: Determine the security risk of the target area using the sensor risk and the image risk.

[0080] Specifically, different weights can be configured for the sensor risk and the image risk, respectively, and then the safety risk of the target area can be determined by weighted sum. The safety risk of the target area can also be determined based on the ratio of the sensor risk to the image risk. It is understandable that the specific determination method can be set according to actual needs, and the embodiments of the present application do not limit this.

[0081] The safety risk determination method provided in the embodiment of the present application determines the sensor risk based on the real-time sensor data of multiple hazardous sources in the target area, determines the image risk based on the images of the multiple hazardous sources, and then determines the safety risk of the target area based on the sensor risk and the image risk, thereby improving the accuracy of the safety risk and providing guarantee for the smooth and safe operation of the enterprise.

[0082] In an optional implementation manner, the method further includes:

[0083] Verifying the normal data;

[0084] When the state of the danger source corresponding to the normal data is abnormal, the corresponding state of the danger source is corrected to normal using the verified normal data.

[0085] Specifically, the normal data needs to be further verified to ensure the accuracy of the data. A first verification result is generated based on the verification. The verification result can refer to Table 1.

[0086] Table 1

[0087] Error Code Error Description 4001 Normal data quality stamp abnormal 4002 Numerical errors in normal data 4003 Hazard source code does not exist 4004 The normal data collection time is wrong

[0088] For example, error code 4001 indicates that the quality stamp of real-time data collection is abnormal; error code 4002 indicates that the numerical value of normal data is wrong, such as the numerical value does not exist or is null; error code 4003 indicates that the hazard source coding is wrong, such as the coding does not exist or is null; error code 4004 indicates that the collection time of normal data is wrong, such as it does not exist or is null or the time format is incorrect.

[0089] Under normal circumstances, the logic of processing according to the safety risk determination method provided in the embodiment of the present application is to assume that the normal data range of a certain hazardous source is [-100, 100]. First, the real-time sensor data of 110 is collected. At this time, the hazardous source state is determined to be abnormal; then the real-time sensor data of 90 is collected. At this time, since the real-time sensor data is normal and the corresponding hazardous source state is abnormal, the real-time sensor data of 90 is classified as early warning data, and further, it is alarm elimination data, and the corresponding hazardous source state changes from abnormal to normal; then, the real-time sensor data of 80 is collected again. At this time, since the real-time sensor data is normal and the corresponding hazardous source state is normal, the real-time sensor data of 80 is classified as normal data, and the hazardous source state remains normal.

[0090] It should be noted that data loss may occur during the data transmission process. Continuing with the above example, if the real-time sensor data 90 is lost, then the state of the hazardous source does not change and remains abnormal, and when the normal data 80 is received, the state of the hazardous source does not change. In view of this, the embodiment of the present application also provides a method for correcting the state of the hazardous source using normal data to prevent data loss from affecting data accuracy. If the state of the hazardous source corresponding to the normal data is abnormal at this time, the corresponding state of the hazardous source is corrected to normal using the verified normal data.

[0091] In an optional implementation manner, the method further includes:

[0092] Verifying the early warning data;

[0093] Step 130 includes:

[0094] Specifically, the corresponding hazard source status is determined based on the verified warning data.

[0095] Before using the early warning data to determine the state of the hazard source, the early warning data may be verified first to ensure the accuracy of subsequent processing. Based on the verification, a second verification result is generated. The second verification result can refer to Table 2.

[0096] Table 2

[0097]

[0098]

[0099] For example, error code 4005 indicates an incorrect alarm type; error code 4006 indicates duplicate alarm data; error code 4007 indicates invalid alarm elimination data, for example, alarm elimination data is encountered when the hazardous source status is normal, or there will be no alarm information for special hazardous sources; error code 4008 indicates an invalid gas alarm, for example, a gas lower limit or lower-lower limit alarm; error code 4009 indicates that the collection time of the alarm data is earlier than the collection time of the previous related data; error code 4010 indicates that the collection time of the alarm data is equal to the collection time of the previous related data.

[0100] In an optional implementation manner, before step 120, the method further includes:

[0101] The real-time sensing data is pre-processed and subjected to data quality processing, wherein the data quality processing is used to confirm the credibility of the real-time sensing data.

[0102] Specifically, the real-time sensor data can be preprocessed and the data quality processed to improve the accuracy of the subsequent use of real-time sensor data to execute other steps of the security risk determination method provided by the embodiment of the present application. Preprocessing can be understood as converting the real-time sensor data collected by the sensor into data that can be read by the corresponding computer. For example, the pressure represented by the current value of 4-20mA must be fitted in the manner of y=ax+b after collection before the current value can be converted into a pressure value. For another example, a pressure value needs to be obtained from multiple registers in the sensor, and then combined according to the weight relationship to obtain a complete value. For another example, when data is transmitted through protocols such as Modbus, all data collected by the sensors will be packaged in one frame of data, and the data needs to be restored according to the actual topological relationship after receipt.

[0103] Data quality processing is used to confirm the credibility of the real-time sensor data. The embodiment of the present application provides a variety of data quality processing methods. It is understandable that all data quality processing methods should be traversed to improve the credibility of the real-time sensor data. Therefore, further, in an optional implementation, the data quality processing of the raw sensor data includes:

[0104] Comparing the real-time sensing data with the corresponding preset standard range, and marking the real-time sensing data that is outside the preset standard range;

[0105] Marking the real-time sensing data that has not changed within a second preset time range;

[0106] For the real-time sensing data of the switch type, marking the real-time sensing data whose jump times exceed a preset number within a third preset time range;

[0107] For the real-time sensor data of cumulative value type, marking the real-time sensor data that is opposite to the preset configuration trend;

[0108] The method further comprises:

[0109] The marked real-time sensing data is discarded.

[0110] Specifically, the range is the measurement range of the measuring tool (a sensor in the embodiment of the present application), which is determined by the minimum measurement value and the maximum measurement value of the measuring tool. It is understandable that different real-time sensor data have different preset standard ranges. When the sensor itself fails or the error code of the communication signal may generate data outside the range, the real-time sensor data outside the preset standard range is marked.

[0111] If the real-time sensor data does not change within the second preset time range, it means that there may be a situation where the data is not collected or collected incorrectly, resulting in low credibility of the real-time sensor data, so it needs to be marked. It is understandable that the operator can be notified to check and confirm at this time.

[0112] For real-time sensor data of the switch type, if the number of jumps exceeds the preset number within the third preset time range, it means that there are repeated jumps, resulting in low credibility of the real-time sensor data, so it needs to be marked. It is understandable that the operator can be notified to check and confirm at this time.

[0113] For real-time sensor data of the cumulative value type, if it is contrary to the preset configuration trend, the credibility is low, so it needs to be marked. It is understandable that the operator can be notified to check and confirm at this time.

[0114] In an optional implementation manner, the method further includes:

[0115] If the state of the hazard source corresponding to any one of the real-time sensing data changes repeatedly within a fourth preset time range, the hazard source state change information of the real-time sensing data within the fourth preset time range is merged.

[0116] Specifically, the application provides that the abnormal state of the danger source may include: high high report (hh), high report (hi), low report (lo), and low low report (ll). Assuming that the normal data range of a certain danger source is [-100, 100], then the real-time sensor data of 180 can be a high high report, the real-time sensor data of 110 can be a high report, the real-time sensor data of -110 can be a low report, and the real-time sensor data of -180 can be a low low report.

[0117] Assuming that the first preset time range is 30 minutes, hazardous source A generates a high alarm at 8:00, a high-high alarm at 8:10, a high alarm at 8:15, and the alarm is extinguished at 8:30. These four abnormal records are ultimately reflected in one record in the alarm record table: the alarm time of hazardous source A is 8:00, the initial state is high alarm, the worst state is high-high alarm, the current state is extinguished, and the most recent state change time is 8:30.

[0118] It can be understood that, thereby, the hazardous source status change information corresponding to multiple warning conditions is integrated, and the update rules for alarm and alarm elimination are defined.

[0119] Corresponding to the above method embodiment, see Figure 2 , Figure 2 A schematic diagram of the structure of a security risk determination device provided in an embodiment of the present application is shown in FIG. Figure 2 As shown, the security risk determination device 1000 includes:

[0120] An acquisition module 1001 is used to acquire real-time sensor data of multiple danger sources in a target area collected by multiple sensors;

[0121] A classification module 1002 is used to classify the real-time sensor data according to preset rules, wherein the preset rules include whether the real-time sensor data is normal and whether the state of the hazard source corresponding to the real-time sensor data is normal, and the categories of the real-time sensor data include warning data and normal data;

[0122] A hazard source status determination module 1003 is used to determine the corresponding hazard source status according to the warning data;

[0123] A sensor risk determination module 1004, configured to determine the sensor risk of the target area according to the states of all the hazard sources;

[0124] An image acquisition module 1005 is used to acquire images of the plurality of danger sources within a first preset time range;

[0125] An image risk determination module 1006, configured to determine the image risk of the target area using the image;

[0126] The security risk determination module 1007 is configured to determine the security risk of the target area by using the sensing risk and the image risk.

[0127] The early warning device provided in the embodiment of the present application can implement each process of the early warning method in the method embodiment and can achieve the same technical effect. To avoid repetition, it will not be described here.

[0128] Optionally, an embodiment of the present application also provides a computer device, including a processor and a memory, wherein the memory stores programs or instructions, and when the program or instructions are executed by the processor, the various processes of the above-mentioned early warning method embodiment are implemented, and the same technical effect can be achieved. To avoid repetition, they are not repeated here.

[0129] Optionally, an embodiment of the present application also provides a computer-readable storage medium, on which a program or instruction is stored. When the program or instruction is executed by a processor, the various processes of the above-mentioned early warning method embodiment are implemented and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.

[0130] The processor is a processor in the computer device described in the above embodiment. The readable storage medium includes a computer readable storage medium, such as a computer read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0131] Optionally, an embodiment of the present application further provides a computer program product which, when executed on a data processing device, is suitable for executing a program that initializes the various steps of the above-mentioned early warning method embodiment.

[0132] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt 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 include computer-usable program code.

[0133] The present application 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 the present application. 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 generate 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.

[0134] 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 including 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.

[0135] 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.

[0136] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0137] The memory may include non-permanent memory in a computer-readable storage 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 storage medium.

[0138] Computer-readable storage 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 tape 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 storage media does not include temporary computer-readable media (transitory media), such as modulated data signals and carrier waves.

[0139] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included within the scope of the claims of the present application.

Claims

1. A method for determining security risks, characterized in that: include: Acquire real-time sensor data of multiple hazard sources within a target area collected by multiple sensors; Classifying the real-time sensor data according to preset rules, wherein the preset rules include whether the real-time sensor data is normal and whether the state of the hazard source corresponding to the real-time sensor data is normal, and the categories of the real-time sensor data include warning data and normal data; Determine the corresponding hazard source status according to the warning data; Determining the sensing risk of the target area according to all the states of the hazard sources; Collect images of the plurality of danger sources within a first preset time range; determining an image risk of the target area using the image; The security risk of the target area is determined using the sensed risk and the image risk.

2. The security risk determination method according to claim 1, characterized in that: The method further comprises: verifying the normal data; When the state of the danger source corresponding to the normal data is abnormal, the corresponding state of the danger source is corrected to normal using the verified normal data.

3. The security risk determination method according to claim 1, characterized in that: The method further comprises: Verifying the early warning data; Determining the corresponding danger source status according to the early warning data includes: The corresponding hazard source status is determined based on the verified warning data.

4. The method for determining security risks according to claim 1, characterized in that: Before classifying the real-time sensor data according to the preset rules, the method further includes: The real-time sensing data is pre-processed and subjected to data quality processing, wherein the data quality processing is used to confirm the credibility of the real-time sensing data.

5. The method for determining security risks according to claim 4, characterized in that: The performing data quality processing on the real-time sensing data comprises: Compare the real-time sensing data with the corresponding preset standard range, and mark the real-time sensing data that is outside the preset standard range; Marking the real-time sensing data that has not changed within a second preset time range; For the real-time sensing data of the switch type, marking the real-time sensing data whose jump times exceed a preset number within a third preset time range; For the real-time sensor data of cumulative value type, marking the real-time sensor data that is opposite to the preset configuration trend; The method further comprises: The marked real-time sensing data is discarded.

6. The method for determining security risks according to claim 1, characterized in that: The method further comprises: If the state of the hazard source corresponding to any one of the real-time sensing data changes repeatedly within a fourth preset time range, the hazard source state change information of the real-time sensing data within the fourth preset time range is merged.

7. The method for determining security risks according to claim 1, characterized in that: The determining the image risk by using the image comprises: Using an artificial intelligence algorithm to identify the image to obtain an identification result, wherein the identification result includes whether there is any dangerous behavior in the image; The image risk is determined according to the recognition result.

8. A security risk determination device, characterized in that: include: An acquisition module, used to acquire real-time sensor data of multiple hazard sources in a target area collected by multiple sensors; A classification module, used to classify the real-time sensor data according to preset rules, wherein the preset rules include whether the real-time sensor data is normal and whether the state of the hazard source corresponding to the real-time sensor data is normal, and the categories of the real-time sensor data include warning data and normal data; A hazard source status determination module, used to determine the corresponding hazard source status according to the warning data; A sensor risk determination module, used to determine the sensor risk of the target area according to the states of all the hazard sources; An image acquisition module, used for acquiring images of the plurality of danger sources within a first preset time range; An image risk determination module, used to determine the image risk of the target area using the image; A security risk determination module is used to determine the security risk of the target area by using the sensing risk and the image risk.

9. A computer device, characterized in that: It comprises a processor and a memory, wherein the memory stores a program or instruction, and when the program or instruction is executed by the processor, the steps of the early warning method as described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a program or instruction, and when the program or instruction is executed by the processor, the steps of the early warning method according to any one of claims 1 to 7 are implemented.

Images