A security detection method, device and cloud server

Abstract

The embodiment of the present invention discloses a security detection method, device and cloud server, which relate to the field of communication technology. In this method, when the security central control device controls the target alarm device to alarm based on the detection information, the cloud server can obtain detection information from the security central control device, and determine whether the security central control device is faulty according to the detection information. In this way, the detection information determined by the security central control device can be verified and re-examined, thereby determining whether the security central control device is faulty and improving the detection accuracy of the security central control device.

Description

Technical Field

[0001] The present invention relates to the field of communication technology, and in particular to a security detection method, device and cloud server. Background Art

[0002] With the development of science and technology, the application of Internet of Things technology is becoming more and more extensive. Nowadays, more and more families benefit from Internet of Things technology, among which the intelligent security technology based on Internet of Things is favored by most families. However, it is difficult to verify the security detection results with existing technology. Summary of the invention

[0003] In view of the above problems, the present invention is proposed to provide a security detection method, device and cloud server that overcome the above problems or at least partially solve the above problems.

[0004] A first aspect of the present invention provides a security detection method, which is applied to a cloud server, and the method comprises:

[0005] When the security central control device controls the target alarm device to alarm based on the detection information, the detection information is obtained from the security central control device; wherein the detection information is determined by the security central control device according to the real-time video uploaded by the target camera;

[0006] Determine whether the security central control device is faulty based on the detection information.

[0007] Optionally, the cloud server pre-stores a plurality of identification groups, wherein each identification group includes an identification of an alarm device and an identification of a camera; the detection information includes a first identification of the target alarm device and a second identification of the target camera; and determining whether the security central control device is faulty according to the detection information includes:

[0008] Searching whether there is a target identification group from the multiple identification groups, wherein the identification of the alarm device in the target identification group is the same as the first identification, and the identification of the camera in the target identification group is the same as the second identification;

[0009] If the target identification group does not exist in the multiple identification groups, it is determined that the security central control device is faulty.

[0010] Optionally, the cloud server pre-stores a portrait library, the detection information includes a target image, the target image is obtained by the security central control device from the real-time video, and the target image includes a portrait to be detected determined by the security central control device; determining whether the security central control device is faulty according to the detection information includes:

[0011] Searching in the portrait database whether the portrait to be detected exists;

[0012] If the portrait to be detected exists in the portrait database, it is determined that the security central control device is faulty.

[0013] Optionally, determining whether the security central control device is faulty according to the detection information includes:

[0014] Obtaining the total number of all human figures in the target image and the number of human figures to be detected in the target image;

[0015] Determine whether the total number is the same as the quantity; if the total number is not the same as the quantity, determine that the security central control device is faulty.

[0016] Optionally, the detection information includes a target image, the target image is obtained by the security central control device from the real-time video, the target image includes a human image to be detected determined by the security central control device, and determining whether the security central control device is faulty according to the detection information includes:

[0017] Obtaining the actual alarm category of the target alarm device when it issues an alarm;

[0018] Analyzing the target image to obtain an analysis result;

[0019] According to a preset condition set, the analysis result is judged to obtain a judgment result;

[0020] Determining the target alarm category of the target alarm device according to the judgment result;

[0021] Determine whether the target alarm category is the same as the actual alarm category. If they are not the same, determine that the security central control device is faulty.

[0022] Optionally, determining the target alarm category of the target alarm device according to the judgment result includes:

[0023] When the judgment result indicates that the analysis result does not satisfy all the preset conditions in the preset condition set, the target alarm category is determined to be a warning; otherwise, the target alarm category is determined to be an alarm;

[0024] Among them, the preset condition set includes one or more combinations of a first preset condition that the portrait to be detected is located within a set area in the target image, a second preset condition that the upload time of the target image is within a set time period, and a third preset condition that the posture of the portrait to be detected is a set posture.

[0025] Optionally, the determining whether the target alarm category is the same as the actual alarm category, and if they are not the same, determining that the security central control device is faulty, includes:

[0026] If the target alarm category is warning and the actual alarm category is alarm, it is determined that the security central control device is faulty;

[0027] If the target alarm category is alarm and the actual alarm category is warning, it is determined that the security central control device is faulty.

[0028] Optionally, the method further comprises:

[0029] Obtaining a parameter configuration request sent by the security central control device;

[0030] According to the parameter configuration request, the setting parameters are sent to the security central control device; wherein the setting parameters are uploaded by the user terminal, and the setting parameters include detection rules, and the detection rules are used by the security central control device when determining the detection information based on the real-time video.

[0031] A second aspect of the present invention provides a security detection device, which is applied to a cloud server, and the device comprises:

[0032] A detection information acquisition module, used to obtain the detection information from the security central control device when the security central control device controls the target alarm device to alarm based on the detection information; wherein the detection information is determined by the security central control device according to the real-time video uploaded by the target camera;

[0033] A fault determination module is used to determine whether the security central control device is faulty based on the detection information.

[0034] Optionally, the cloud server pre-stores a plurality of identification groups, wherein each identification group includes an identification of an alarm device and an identification of a camera; the detection information includes a first identification of the target alarm device and a second identification of the target camera; the fault determination module is used to:

[0035] Searching whether there is a target identification group from the multiple identification groups, wherein the identification of the alarm device in the target identification group is the same as the first identification, and the identification of the camera in the target identification group is the same as the second identification;

[0036] If the target identification group does not exist in the multiple identification groups, it is determined that the security central control device is faulty.

[0037] Optionally, the cloud server pre-stores a portrait library, the detection information includes a target image, the target image is obtained by the security central control device from the real-time video, and the target image includes a portrait to be detected determined by the security central control device; the fault determination module is used to:

[0038] Searching in the portrait database whether the portrait to be detected exists;

[0039] If the portrait to be detected exists in the portrait database, it is determined that the security central control device is faulty.

[0040] Optionally, the fault determination module is used to:

[0041] Obtaining the total number of all human figures in the target image and the number of human figures to be detected in the target image;

[0042] Determine whether the total number is the same as the quantity; if the total number is not the same as the quantity, determine that the security central control device is faulty.

[0043] Optionally, the detection information includes a target image, the target image is obtained by the security central control device from the real-time video, the target image includes a human image to be detected determined by the security central control device, and the fault determination module is used to:

[0044] Obtaining the actual alarm category of the target alarm device when it issues an alarm;

[0045] Analyzing the target image to obtain an analysis result;

[0046] According to a preset condition set, the analysis result is judged to obtain a judgment result;

[0047] Determining the target alarm category of the target alarm device according to the judgment result;

[0048] Determine whether the target alarm category is the same as the actual alarm category. If they are not the same, determine that the security central control device is faulty.

[0049] Optionally, the fault determination module is used to:

[0050] When the judgment result indicates that the analysis result does not satisfy all the preset conditions in the preset condition set, the target alarm category is determined to be a warning; otherwise, the target alarm category is determined to be an alarm;

[0051] Among them, the preset condition set includes one or more combinations of a first preset condition that the portrait to be detected is located within a set area in the target image, a second preset condition that the upload time of the target image is within a set time period, and a third preset condition that the posture of the portrait to be detected is a set posture.

[0052] Optionally, the fault determination module is used to:

[0053] If the target alarm category is warning and the actual alarm category is alarm, it is determined that the security central control device is faulty;

[0054] If the target alarm category is alarm and the actual alarm category is warning, it is determined that the security central control device is faulty.

[0055] Optionally, the device further comprises:

[0056] a parameter configuration module, used to obtain a parameter configuration request sent by the security central control device; according to the parameter configuration request, send the setting parameters to the security central control device; wherein the setting parameters are uploaded by the user terminal, and the setting parameters include detection rules, which are used by the security central control device when determining the detection information according to the real-time video.

[0057] According to a third aspect of the present invention, a computer-readable storage medium is provided, on which a computer program is stored, and when the program is executed by a processor, the steps of the above-mentioned security detection method are implemented.

[0058] According to a fourth aspect of the present invention, a cloud server is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the above-mentioned security detection method when executing the program.

[0059] The technical solution provided in the embodiments of the present application has at least the following technical effects or advantages:

[0060] In the above scheme, when the security central control device controls the target alarm device to alarm based on the detection information, the cloud server can obtain detection information from the security central control device and determine whether the security central control device is faulty based on the detection information. In this way, the detection information determined by the security central control device can be verified and re-audited to determine whether the security central control device is faulty, thereby improving the detection accuracy of the security central control device.

[0061] The above description is only an overview of the technical solution of the present invention. In order to more clearly understand the technical means of the present invention, it can be implemented according to the contents of the specification. In order to make the above and other purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0062] Various other advantages and benefits will become apparent to those of ordinary skill in the art by reading the detailed description of the preferred embodiments below. The accompanying drawings are only for the purpose of illustrating the preferred embodiments and are not to be considered as limiting the present invention. Moreover, the same reference symbols are used throughout the accompanying drawings to represent the same components. In the accompanying drawings:

[0063] Figure 1 A structural block diagram of a security detection system provided according to an embodiment of the present invention is shown.

[0064] Figure 2 A flow chart of a security detection method provided according to an embodiment of the present invention is shown.

[0065] Figure 3 A schematic diagram of a user residence provided according to an embodiment of the present invention is shown.

[0066] Figure 4 A schematic diagram of event triggering provided according to an embodiment of the present invention is shown.

[0067] Figure 5 A module block diagram of a security detection device provided according to an embodiment of the present invention is shown.

[0068] icon:

[0069] 100-security detection system; 101-cloud server; 102-security central control equipment; 103-camera; 104-infrared transmitter; 105-alarm device; 106-user terminal;

[0070] 200-security detection device; 211-detection information acquisition module; 212-fault determination module; 213-parameter setting module;

[0071] 301-yard; 302-residence. DETAILED DESCRIPTION

[0072] The exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

[0073] The embodiments of the present invention provide a security detection method, a device and a cloud server, which are used to improve the technical problem that the existing security detection technology is difficult to verify the security detection results.

[0074] As an optional embodiment, Figure 1 A module block diagram of a security detection system 100 provided according to an embodiment of the present invention.

[0075] Depend on Figure 1 It can be seen that the security detection system 100 includes a cloud server 101, a security central control device 102, a camera 103, an infrared transmitter 104, an alarm device 105 and a user terminal 106.

[0076] In the embodiment of the present application, the security central control device 102 is an independent control device, which is quite different from the existing desktop / laptop computer, smart phone, tablet computer, server, etc. The security central control device 102 can provide a set of smart home security solutions. Externally, it can provide a security detection method to achieve intelligent protection. Internally, it can provide a smart home control method to achieve smart control of the home.

[0077] Please continue reading Figure 1 The security central control device 102 is connected to the camera 103, the infrared transmitter 104 and the alarm device 105 for communication. In this way, the security central control device 102 can obtain real-time monitoring information around the home based on the camera 103 and the infrared transmitter 104, and control the alarm device 105 to sound an alarm based on the real-time monitoring information.

[0078] Furthermore, the security central control device 102 is also communicatively connected with the cloud server 101, so that the security central control device 102 can send the determined detection information to the cloud server 101, and the cloud server 101 can perform asynchronous verification and secondary review on the detection information, so as to determine whether the detection information determined by the security central control device 102 is incorrect, and then determine whether the security central control device 102 fails. In this way, the fault of the security central control device 102 can be discovered in time based on the detection information, and the message of the fault of the security central control device 102 can also be sent to the user terminal 106, so as to avoid the faulty security central control device 102 from continuously outputting incorrect detection information, thereby ensuring the detection accuracy of the security central control device 102.

[0079] Please continue reading Figure 1, the user terminal 106 can communicate with the security central control device 102 through the cloud server 101, or can directly communicate with the security central control device 102. For example, when the user terminal 106 and the security central control device 102 are in the same WIFI local area network, the user terminal 106 can directly communicate with the security central control device 102 to achieve data interaction. For another example, when the user terminal 106 and the security central control device 102 are not in the same WIFI local area network, the user terminal 106 can communicate with the security central control device 102 through the cloud server 101, and achieve data interaction based on the cloud server 101.

[0080] In the embodiment of the present application, the user terminal 106 may be a mobile phone or a tablet. For example, the mobile phone may be indirectly connected to the security central control device 102 through the cloud server 101, and the tablet may be directly connected to the security central control device 102 through a WIFI local area network. It should be understood that in the specific implementation process, it is not limited to the several communication connection methods listed above.

[0081] It can be understood that the cloud server 101 in the above-mentioned security detection system 100 can verify and re-examine the detection information during the security detection process, so as to promptly determine whether the security central control device 102 has a fault, thereby improving the detection accuracy of the security central control device 102.

[0082] Please refer to Figure 2 , is a flow chart of a security detection method provided according to an embodiment of the present invention, the method is applied to Figure 1 The cloud server 101 in the embodiment of the present invention will be described in detail below:

[0083] S21, when the security central control device controls the target alarm device to alarm based on the detection information, the detection information is obtained from the security central control device.

[0084] In the embodiment of the present application, the security central control device 102 determines the detection information according to the real-time video uploaded by the target camera, and controls the target alarm device to alarm based on the detection information. It can be understood that when the security central control device 102 controls the target alarm device to alarm, the cloud server 101 obtains the detection information from the security central control device 102.

[0085] Optionally, when the security central control device 102 controls the target alarm device to sound an alarm, the security central control device 102 may also automatically upload the detection information to the cloud server 101 for verification and secondary review by the cloud server 101 .

[0086] In the embodiment of the present application, the detection information includes a variety of information, including but not limited to the following information:

[0087] 1) A first identification of the target alarm device and a second identification of the target camera;

[0088] 2) target image;

[0089] 3) The actual alarm category of the target alarm device.

[0090] It can be understood that the cloud server 101 can verify and re-examine the detection information of the security central control device 102 based on the above-mentioned information, so as to determine whether the detection information is accurate, and then determine whether the security central control device 102 has a fault. In this way, the detection accuracy and reliability of the security central control device 102 can be improved.

[0091] The entire security detection system 100 is first described below with a specific example:

[0092] Please refer to Figure 3 , multiple infrared transmitters 104 are arranged around the user's yard 301, and two adjacent infrared transmitters 104 form an infrared "detection wall", and an object passing through the "detection wall" can trigger the infrared transmitter 104. In the embodiment of the present application, the number of infrared transmitters 104 can be 4, and more specifically, there are 4 "detection walls" in the embodiment of the present application.

[0093] Furthermore, a plurality of cameras 103 are arranged around the user's residence 302 . In the implementation of the present application, the number of cameras 103 may be 4, and the 4 cameras 103 can monitor the user's yard 301 in real time.

[0094] Furthermore, a plurality of alarm devices 105 are installed around the user's residence 302 .

[0095] In this embodiment, each camera 103 , each infrared transmitter 104 , and each alarm device 105 are connected to the security central control device 102 for communication, thereby realizing security detection of the user's yard 301 and residence 302 .

[0096] Furthermore, the four cameras 103 can shoot their respective areas in real time, obtain real-time video, and then send the real-time video to the security central control device 102.

[0097] For ease of explanation, we will take one of the cameras as an example. For more details, please refer to Figure 3 , the camera 103 that monitors area A is used to illustrate. In the embodiment of the present application, the camera 103 that monitors area A can be understood as a target camera, and the alarm device 105 in area A can be understood as a target alarm device.

[0098] Furthermore, the security central control device 102 receives the real-time video uploaded by the camera 103. It can be understood that the real-time video is the real-time video of area A.

[0099] Furthermore, the security central control device 102 determines detection information based on the real-time video, controls the alarm device 105 to alarm based on the detection information, and sends the detection information to the cloud server 101.

[0100] S22, determining whether the security central control device is faulty based on the detection information.

[0101] It can be understood that when the cloud server 101 obtains the detection information, it will verify the various information in the detection information, and then verify and re-examine the detection information from multiple dimensions to determine whether the security central control device 102 is faulty (whether the detection information determined by the security central control device 102 is incorrect).

[0102] In the embodiment of the present application, the cloud server 101 determines whether the security central control device is faulty according to the detection information, specifically including the following three situations. Of course, in the specific implementation process, it is not limited to the following three situations:

[0103] Case 1: Verify the detection information based on the first identification of the target alarm device and the second identification of the target camera.

[0104] It can be understood that the cameras 103 and the alarm devices 105 in the same area correspond one to one. If the security central control device 102 determines that an alarm is needed based on the real-time video uploaded by the camera 103 in area A, then the security central control device 102 should control the alarm device 105 in area A to alarm. Otherwise, it can be determined that the security central control device 102 is faulty.

[0105] In this case, the detection information includes a first identifier of the target alarm device and a second identifier of the target camera. Furthermore, the cloud server 101 pre-stores a plurality of identifier groups, wherein each identifier group includes an identifier of an alarm device and an identifier of a camera. Figure 3 , the cloud server 101 may include 4 identification groups, each of which includes the identification of the alarm device and the identification of the camera in the same area. For another example, the identification of the alarm device in area A is P A , the camera in area A is marked as C A It can be understood that the four identification groups included in the cloud server 101 can be (P A , C A )、(P B , C B )、(P C , C C ) and (PD , C D ).

[0106] In the embodiment of the present application, the first identifier of the target alarm device is P X , the second identifier of the target camera is C X .

[0107] Specifically, the cloud server 101 determines whether the security central control device 102 is faulty according to the detection information, specifically including:

[0108] Find out whether there is a target identification group among the multiple identification groups. The identification of the alarm device in the target identification group is the same as the first identification, and the identification of the camera in the target identification group is the same as the second identification. If the target identification group does not exist among the multiple identification groups, it is determined that the security central control device is faulty.

[0109] Please refer to Figure 3 , if the first identifier P X P A , the second identifier C X C A , then the target identification group (P A , C A ), and the target identification group exists in multiple identification groups, indicating that the target alarm device and the target camera are located in the same area. It can be determined that the detection information is correct and the security central control device 102 is not faulty.

[0110] For another example, if the first identifier P X P B , the second identifier C X C A , then the target identification group (P B , C A ), and the target identification group does not exist in the multiple identification groups, indicating that the target alarm device and the target camera are not located in the same area. Therefore, it is determined that the detection information is wrong and the security central control device 102 is faulty. Further, the fault of the security central control device 102 can be understood as follows: when the security central control device 102 determines that it needs to control the alarm device in area A to alarm based on the real-time video uploaded by the camera in area A, it mistakenly controls the alarm device in area B to alarm. Therefore, in this case, the cloud server 101 will determine that the security central control device 102 is faulty.

[0111] Case 2: Verify detection information based on target image.

[0112] In this case, the detection information includes a target image, and the target image includes a human portrait to be detected determined by the security central control device 102 . Furthermore, a human portrait library is pre-stored in the cloud server 101 .

[0113] In the embodiment of the present application, the cloud server 101 determines whether the security central control device 102 is faulty based on the detection information, including: searching in the portrait library whether there is a portrait to be detected, and if there is a portrait to be detected in the portrait library, determining that the security central control device 102 is faulty.

[0114] In this embodiment, the portraits in the portrait library are uploaded to the cloud server 101 by the user terminal 106. For example, the user terminal 106 can upload customized portraits to the cloud server 101 for storage. For another example, the user terminal 106 can upload portraits of family members, friends, classmates or colleagues to the cloud server 101 for storage. The cloud server 101 can detect the portraits to be detected in the target image based on the portraits in the portrait library.

[0115] If the cloud server 101 finds the portrait to be detected in the target image in the portrait library, it indicates that the portrait to be detected is recognized (authorized) by the user terminal 106. In this case, the security central control device 102 controls the alarm device 105 to alarm, indicating that a problem occurs in the security central control device 102 during the detection. More specifically, the cloud server 101 can determine that the security central control device 102 has a fault based on the target image in the detection information.

[0116] Optionally, the cloud server 101 determines whether the security central control device 102 is faulty based on the detection information, and also includes: obtaining the total number of all human figures in the target image and the number of human figures to be detected in the target image, and judging whether the total number is the same as the number; if the total number is different from the number, it is determined that the security central control device is faulty.

[0117] In the embodiment of the present application, the security central control device 102 determines the portrait to be detected based on the target image. When determining the portrait to be detected based on the target image, false detection or missed detection may occur. Therefore, the cloud server 101 needs to conduct a second review of the target image to determine whether the portrait recognition algorithm to be detected of the security central control device 102 is accurate.

[0118] In the specific implementation process, the possible misdetection or missed detection of the security central control device 102 can be specifically described by the following two scenarios. Of course, in the specific implementation, it is not limited to the following two scenarios:

[0119] Scenario 1:

[0120] A cat enters area A, triggering the infrared transmitter 104. The security central control device 102 obtains the target image of the cat entering area A and marks the cat. The security central control device 102 mistakenly marks the cat as a human portrait to be detected.

[0121] When the cloud server 101 obtains this target image, it will detect that the object marked in the target image is not a human portrait but a cat. The total number of all human portraits obtained by the cloud server 101 in the target image is 0, while the number of human portraits to be detected in the target image is 1. In this case, the cloud server 101 will determine that the security central control device 102 has a fault. Specifically, the cloud server 101 determines that the security central control device 102 has a fault when identifying the human portrait to be detected in the target image.

[0122] Scenario 2:

[0123] Passersby P1 and P2 enter area A at the same time, and passersby P1 approaches the window in area A. The security central control device 101 obtains the target image of passersby P1 and passersby P2 entering area A, and the target image also shows that passersby P1 approaches the window in area A. When determining the human figure to be detected in the target image, the security central control device 101 may only mark passersby P2, but not passersby P1.

[0124] Furthermore, the cloud server 101 obtains a total of 2 human portraits in the target image, while the number of human portraits to be detected in the target image is 1. At this time, the cloud server 101 determines that a failure occurs in the security central control device 102 when identifying the human portrait to be detected in the target image.

[0125] It can be understood that the cloud server 101 compares the total number of all human figures in the target image and the number of human figures to be detected in the target image, and then determines whether the security central control device 101 is faulty. It can promptly discover the algorithm error of the security central control device 102 in determining the human figures to be detected, so that the algorithm error can be known in time, thereby avoiding false detection and missed detection, thereby improving the detection accuracy of the security central control device 102.

[0126] Case 3: Verify detection information based on the actual alarm category of the target alarm device.

[0127] In this case, the detection information includes a target image, and the target image includes a human image to be detected determined by the security central control device. Further, the cloud server 101 determines whether the security central control device 102 is faulty according to the detection information, specifically including:

[0128] Get the actual alarm category of the target alarm device when it alarms;

[0129] Analyze the target image to obtain the analysis result;

[0130] Judging the analysis result according to the preset condition set to obtain the judgment result;

[0131] According to the judgment result, the target alarm category of the target alarm device is determined;

[0132] Determine whether the target alarm category and the actual alarm category are the same. If they are not the same, determine that the security central control equipment is faulty.

[0133] In the embodiment of the present application, the cloud server 101 determines the target alarm category of the target alarm device according to the judgment result, which specifically includes the following contents:

[0134] When the judgment result indicates that the parsing result does not satisfy all preset conditions in the preset condition set, the target alarm category is determined to be a warning; otherwise, the target alarm category is determined to be an alarm.

[0135] Specifically, the analysis result may include the upload time of the target image, the area where the to-be-detected person portrait in the target image is located, the posture of the to-be-detected person portrait in the target image, and the like.

[0136] Specifically, the preset condition set includes one or more combinations of the following three preset conditions:

[0137] 1) The first preset condition: the person to be detected is located in a set area in the target image;

[0138] 2) The second preset condition: the upload time of the target image is within the set time period;

[0139] 3) The third preset condition: the posture of the portrait to be detected is the set posture.

[0140] In the embodiment of the present application, the set area can be a window or a door. Generally speaking, if the person to be detected is located near the window or in front of the door, it is likely that he is snooping around the house 302, which poses a certain security risk. The set time period can be night or early morning. For example, the set time period can be 00:00:00 to 6:00:00. If the target image is uploaded during this time period, the probability of a security risk is high. The set posture can be climbing a window, prying a door, smashing a window, etc. It can be understood that if the person to be detected has these postures, it can be determined that there is a security risk.

[0141] In the embodiment of the present application, the judgment result may include the following 7 situations:

[0142] Case 1: the judgment result indicates that the analysis result satisfies the first preset condition, the second preset condition and the third preset condition at the same time;

[0143] Case 2: the judgment result indicates that the analysis result satisfies both the first preset condition and the second preset condition, but does not satisfy the third preset condition;

[0144] Case 3: the judgment result indicates that the analysis result satisfies both the first preset condition and the third preset condition, but does not satisfy the second preset condition;

[0145] Case 4: the judgment result indicates that the analysis result satisfies both the second preset condition and the third preset condition, but does not satisfy the first preset condition;

[0146] Case 5: the judgment result indicates that the analysis result only meets the first preset condition;

[0147] Case 6: the judgment result indicates that the analysis result only meets the second preset condition;

[0148] Case 7: The judgment result indicates that the analysis result only satisfies the third preset condition.

[0149] It can be understood that if the judgment result is one of the above 7 situations, the target alarm category is determined to be alarm. If the judgment result is not any of the 7 situations, the target alarm category is determined to be warning.

[0150] It can be understood that the security level of the early warning is lower than the security level of the alarm.

[0151] In the embodiment of the present application, the cloud server 101 determines whether the target alarm category and the actual alarm category are the same. If they are not the same, it is determined that the security central control device is faulty, specifically including:

[0152] If the target alarm category is warning and the actual alarm category is alarm, it is determined that the security central control device 102 is faulty;

[0153] If the target alarm category is alarm and the actual alarm category is warning, it is determined that the security central control device 102 is faulty.

[0154] It can be understood that when the security central control device 102 controls the alarm device 105 to alarm, the actual alarm category and the target alarm category may be different. Through the above method, the cloud server 101 can determine the target alarm category according to the target image, and determine whether the security central control device 102 fails when sending the alarm control instruction to the alarm device 105 based on the actual alarm category. In this way, the detection information can be verified and re-audited, and the failure of the alarm control instruction sending of the security central control device 102 can be determined in time, thereby improving the detection accuracy of the security central control device 102.

[0155] Optionally, the cloud server 101 determines whether the security central control device 102 is faulty according to the detection information, and also includes the following situation:

[0156] Case 4:

[0157] The cloud server 101 verifies the detection information within a period of time, and then determines whether the detection algorithm of the security central control device 102 fails. For example, the cloud server 101 obtains multiple detection information uploaded by the security central control device 102 for area A within a certain period of time, wherein each detection information includes a target image.

[0158] Furthermore, if the same person to be detected exists in each target image, it indicates that during this period of time, the person to be detected has not left the monitoring area of ​​the camera 103 in area A. However, at this time, the cloud server 101 receives multiple detection information, indicating that the security central control device 102 controls the alarm device 105 to sound an alarm multiple times based on the real-time video of the camera 103 in area A. In this case, the cloud server 101 can determine that the security central control device 102 has a failure when executing the detection rules. In this way, the detection rule execution failure of the security central control device 102 can be discovered in time, thereby improving the detection accuracy of the security central control device 102.

[0159] It should be understood that when the cloud server 101 determines whether the security central control device 102 is faulty based on the detection information, as long as it is determined that the security central control device 102 has one of the above four fault conditions, it can be determined that the security central control device 102 has a fault.

[0160] Optionally, the cloud server 101 can also perform device management and rule management on the security central control device 102. Specifically, the cloud server 101 obtains a parameter configuration request sent by the security central control device, and sends the set parameters to the security central control device according to the parameter configuration request.

[0161] In the embodiment of the present application, the setting parameters are uploaded by the user terminal 106, and the setting parameters include detection rules, etc. The detection rules are used by the security central control device 102 when determining the detection information based on the real-time video.

[0162] More specifically, the cloud server 101 can send the setting parameters uploaded by the user terminal 106 to the security central control device 102, so that the security central control device 102 can directly configure the camera 103, infrared transmitter 104 and alarm device 105 based on the setting parameters. In this way, when the security central control device 102 is restarted due to damage or abnormality, it can directly obtain the setting parameters from the cloud server 101, avoiding the user's manual reconfiguration, thereby improving the recoverability and reusability of the security central control device 102.

[0163] Optionally, in the specific implementation process, the security central control device 102 can obtain the target image from the real-time video through a variety of methods. Two methods of obtaining the target image from the real-time video are listed below. Of course, in the specific implementation process, it is not limited to the following two methods.

[0164] The first method of obtaining a target image from a real-time video is that the security central control device 102 obtains the moment when the infrared transmitter 104 sends a trigger signal, obtains the image corresponding to the moment from the real-time video, and determines the image corresponding to the moment as the target image.

[0165] Please refer to Figure 4 For example, when someone Figure 4 When entering the yard 301 from the left, trigger Figure 4 As for the two infrared transmitters 104 on the left, since the security central control device 102 is in communication connection with the two infrared transmitters 104 , the security central control device 102 can obtain the time when the two infrared transmitters 104 send out the alarm signal, for example, the time may be 9:05:16.

[0166] Furthermore, the security central control device 102 obtains the image corresponding to the time 9:05:16 from the real-time video, and determines the image corresponding to the time 9:05:16 as the target image.

[0167] It can be understood that the infrared transmitter 104 is triggered, indicating that an event has been triggered. More specifically, when the security central control device 102 obtains the moment when the two infrared transmitters 104 send out the trigger signal, it can determine that an event has been triggered. At this time, the security central control device 102 obtains the target image from the real-time video uploaded by the camera 103 according to the moment when the event is triggered (the moment when the two infrared transmitters 104 send out the alarm signal).

[0168] The second method of obtaining a target image from a real-time video is that the security central control device 102 detects whether there is a portrait in the current frame image of the real-time video. If there is a portrait in the current frame image, it detects whether the portrait exists in the previous frame image of the current frame image. If the portrait does not exist in the previous frame image, the current frame image is obtained and the current frame image is determined as the target image.

[0169] It can be understood that the real-time video acquired by the security central control device 102 is uploaded by the camera 103 in the form of each frame image. The security central control device 102 can detect the received current frame image to determine whether the current frame image triggers an event, thereby acquiring the target image.

[0170] Specifically, the security central control device 102 detects whether there is a human portrait in the current frame image, and if so, detects whether there is the human portrait in the previous frame image of the current frame image:

[0171] If the portrait does not exist in the previous frame image, it indicates that the current frame image records the situation that the portrait enters area A, indicating the triggering of an event. At this time, the security central control device 102 obtains the current frame image and determines the current frame image as the target image.

[0172] If the portrait exists in the previous frame image, it indicates that the portrait has always been in area A. Then it can be determined that one of the frames before the current frame image has been determined as the target image, and there is no need to determine the current frame image as the target image. More specifically, if a person enters area A and stays in area A, the security control device 102 only uses the image corresponding to the person entering area A captured by the camera 103 as the target image. Furthermore, if a person enters area A, leaves area A, and then enters area A again, the security control device 102 uses the image corresponding to the person entering area A twice captured by the camera 103 as the target image.

[0173] As an optional embodiment, Figure 5 The module block diagram of a security detection device 200 provided according to an embodiment of the present invention is shown, and the security detection device 200 includes:

[0174] The detection information acquisition module 201 is used to obtain the detection information from the security central control device when the security central control device controls the target alarm device to alarm based on the detection information; wherein the detection information is determined by the security central control device according to the real-time video uploaded by the target camera;

[0175] The fault determination module 202 is used to determine whether the security central control device is faulty according to the detection information.

[0176] Furthermore, the fault determination module 202 is used to: search whether there is a target identification group from the multiple identification groups, wherein the identification of the alarm device in the target identification group is the same as the first identification, and the identification of the camera in the target identification group is the same as the second identification; if the target identification group does not exist in the multiple identification groups, determine that the security central control device is faulty.

[0177] Furthermore, the fault determination module 202 is used to: search in the portrait database whether the portrait to be detected exists; if the portrait to be detected exists in the portrait database, determine that the security central control device is faulty.

[0178] Furthermore, the fault determination module 202 is used to: obtain the total number of all human figures in the target image and the number of human figures to be detected in the target image; determine whether the total number is the same as the number, and if the total number is different from the number, determine that the security central control device is faulty.

[0179] Furthermore, the fault determination module 202 is used to: obtain the actual alarm category when the target alarm device sounds an alarm; analyze the target image to obtain an analysis result; judge the analysis result according to a preset condition set to obtain a judgment result; determine the target alarm category of the target alarm device according to the judgment result; judge whether the target alarm category and the actual alarm category are the same, and if not, determine that the security central control device is faulty.

[0180] Further, the fault determination module 202 is used to: when the judgment result represents that the analysis result does not meet all the preset conditions in the preset condition set, determine the target alarm category as warning; otherwise, determine the target alarm category as alarm; wherein the preset condition set includes one or more combinations of a first preset condition that the human portrait to be detected is located within a set area in the target image, a second preset condition that the upload time of the target image is within a set time period, and a third preset condition that the posture of the human portrait to be detected is a set posture.

[0181] Further, the fault determination module 202 is used to: if the target alarm category is warning and the actual alarm category is alarm, determine that the security central control device is faulty; if the target alarm category is alarm and the actual alarm category is warning, determine that the security central control device is faulty.

[0182] Furthermore, the security detection device 200 further includes:

[0183] The parameter configuration module 203 is used to obtain the parameter configuration request sent by the security central control device; according to the parameter configuration request, the setting parameters are sent to the security central control device; wherein the setting parameters are uploaded by the user terminal, and the setting parameters include detection rules, and the detection rules are used by the security central control device when determining the detection information based on the real-time video.

[0184] Based on the same inventive concept as in the aforementioned embodiment, an embodiment of the present invention further provides a computer-readable storage medium on which a computer program is stored, and when the program is executed by a processor, the steps of any of the aforementioned methods are implemented.

[0185] Based on the same inventive concept as in the aforementioned embodiment, an embodiment of the present invention further provides a cloud server, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of any of the aforementioned methods when executing the program.

[0186] The technical solution provided in the embodiments of the present application has at least the following technical effects or advantages:

[0187] According to a security detection method, device and cloud server of the present invention, the cloud server can obtain detection information from the security central control device when the security central control device controls the target alarm device to alarm based on the detection information, and determine whether the security central control device is faulty according to the detection information. In this way, the detection information determined by the security central control device can be verified and re-audited, thereby determining whether the security central control device is faulty and improving the detection accuracy of the security central control device.

[0188] The algorithm and display provided herein are not inherently related to any particular computer, virtual system or other device. Various general purpose systems can also be used together with the teachings based on this. According to the above description, it is obvious that the structure required for constructing such systems. In addition, the present invention is not directed to any specific programming language either. It should be understood that various programming languages ​​can be utilized to realize the content of the present invention described herein, and the description of the above specific languages ​​is for disclosing the best mode of the present invention.

[0189] In the description provided herein, a large number of specific details are described. However, it is understood that embodiments of the present invention can be practiced without these specific details. In some instances, well-known methods, structures and techniques are not shown in detail so as not to obscure the understanding of this description.

[0190] Similarly, it should be understood that in order to streamline the present disclosure and aid in understanding one or more of the various inventive aspects, in the above description of exemplary embodiments of the present invention, various features of the present invention are sometimes grouped together into a single embodiment, figure, or description thereof. However, this disclosed method should not be interpreted as reflecting the intention that the claimed invention requires more features than those explicitly recited in each claim. More specifically, as reflected in the claims below, inventive aspects lie in less than all the features of the individual embodiments disclosed above. Therefore, the claims that follow the specific embodiment are hereby expressly incorporated into the specific embodiment, with each claim itself serving as a separate embodiment of the present invention.

[0191] Those skilled in the art will appreciate that the modules in the devices in the embodiments may be adaptively changed and arranged in one or more devices different from the embodiments. The modules or units or components in the embodiments may be combined into one module or unit or component, and in addition they may be divided into a plurality of submodules or subunits or subcomponents. Except that at least some of such features and / or processes or units are mutually exclusive, all features disclosed in this specification (including the accompanying claims, abstracts and drawings) and all processes or units of any method or device disclosed in this manner may be combined in any combination. Unless otherwise expressly stated, each feature disclosed in this specification (including the accompanying claims, abstracts and drawings) may be replaced by an alternative feature providing the same, equivalent or similar purpose.

[0192] In addition, those skilled in the art will appreciate that, although some embodiments herein include certain features included in other embodiments but not other features, the combination of features of different embodiments is meant to be within the scope of the present invention and form different embodiments. For example, in the claims below, any one of the claimed embodiments may be used in any combination.

[0193] The various component embodiments of the present invention can be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. It should be understood by those skilled in the art that a microprocessor or digital signal processor (DSP) can be used in practice to implement some or all functions of some or all components in a gateway, proxy server, or system according to an embodiment of the present invention. The present invention can also be implemented as a device or apparatus program (e.g., a computer program and a computer program product) for executing part or all of the methods described herein. Such a program implementing the present invention can be stored on a computer-readable medium, or can have the form of one or more signals. Such a signal can be downloaded from an Internet website, or provided on a carrier signal, or provided in any other form.

[0194] It should be noted that the above embodiments illustrate the present invention rather than limit it, and that those skilled in the art may devise alternative embodiments without departing from the scope of the appended claims. In the claims, any reference symbol between brackets shall not be construed as a limitation on the claims. The word "comprising" does not exclude the presence of elements or steps not listed in the claims. The word "one" or "an" preceding an element does not exclude the presence of a plurality of such elements. The present invention may be implemented by means of hardware comprising a number of different elements and by means of a suitably programmed computer. In a unit claim enumerating a number of devices, several of these devices may be embodied by the same hardware item. The use of the words first, second, and third, etc., does not indicate any order. These words may be interpreted as names.

[0195] The present invention discloses:

[0196] A1. A security detection method, characterized in that it is applied to a cloud server, and the method comprises:

[0197] When the security central control device controls the target alarm device to alarm based on the detection information, the detection information is obtained from the security central control device; wherein the detection information is determined by the security central control device according to the real-time video uploaded by the target camera;

[0198] Determine whether the security central control device is faulty based on the detection information.

[0199] A2. The method as claimed in claim A1, characterized in that the cloud server pre-stores a plurality of identification groups, wherein each identification group includes an identification of an alarm device and an identification of a camera; the detection information includes a first identification of the target alarm device and a second identification of the target camera; and determining whether the security central control device is faulty according to the detection information comprises:

[0200] Searching whether there is a target identification group from the multiple identification groups, wherein the identification of the alarm device in the target identification group is the same as the first identification, and the identification of the camera in the target identification group is the same as the second identification;

[0201] If the target identification group does not exist in the multiple identification groups, it is determined that the security central control device is faulty.

[0202] A3. The method as claimed in claim A1, characterized in that the cloud server pre-stores a portrait library, the detection information includes a target image, the target image is obtained by the security central control device from the real-time video, and the target image includes a portrait to be detected determined by the security central control device; the determining whether the security central control device is faulty according to the detection information includes:

[0203] Searching in the portrait database whether the portrait to be detected exists;

[0204] If the portrait to be detected exists in the portrait database, it is determined that the security central control device is faulty.

[0205] A4. The method as claimed in claim A3, characterized in that determining whether the security central control device is faulty according to the detection information comprises:

[0206] Obtaining the total number of all human figures in the target image and the number of human figures to be detected in the target image;

[0207] Determine whether the total number is the same as the quantity; if the total number is not the same as the quantity, determine that the security central control device is faulty.

[0208] A5. The method as claimed in claim A1, characterized in that the detection information includes a target image, the target image is obtained by the security central control device from the real-time video, the target image includes a human image to be detected determined by the security central control device, and the determining whether the security central control device is faulty according to the detection information includes:

[0209] Obtaining the actual alarm category of the target alarm device when it issues an alarm;

[0210] Analyzing the target image to obtain an analysis result;

[0211] According to a preset condition set, the analysis result is judged to obtain a judgment result;

[0212] Determining the target alarm category of the target alarm device according to the judgment result;

[0213] Determine whether the target alarm category is the same as the actual alarm category. If they are not the same, determine that the security central control device is faulty.

[0214] A6. The method according to claim A5, characterized in that the step of determining the target alarm category of the target alarm device according to the judgment result comprises:

[0215] When the judgment result indicates that the analysis result does not satisfy all the preset conditions in the preset condition set, the target alarm category is determined to be a warning; otherwise, the target alarm category is determined to be an alarm;

[0216] Among them, the preset condition set includes one or more combinations of a first preset condition that the portrait to be detected is located within a set area in the target image, a second preset condition that the upload time of the target image is within a set time period, and a third preset condition that the posture of the portrait to be detected is a set posture.

[0217] A7. The method according to claim A6, characterized in that the step of determining whether the target alarm category and the actual alarm category are the same, and if they are not the same, determining that the security central control device is faulty, comprises:

[0218] If the target alarm category is warning and the actual alarm category is alarm, it is determined that the security central control device is faulty;

[0219] If the target alarm category is alarm and the actual alarm category is warning, it is determined that the security central control device is faulty.

[0220] A8. The method according to claim A1, characterized in that the method further comprises:

[0221] Obtaining a parameter configuration request sent by the security central control device;

[0222] According to the parameter configuration request, the setting parameters are sent to the security central control device; wherein the setting parameters are uploaded by the user terminal, and the setting parameters include detection rules, and the detection rules are used by the security central control device when determining the detection information based on the real-time video.

[0223] B9. A security detection device, characterized in that it is applied to a cloud server, and the device comprises:

[0224] A detection information acquisition module, used to obtain the detection information from the security central control device when the security central control device controls the target alarm device to alarm based on the detection information; wherein the detection information is determined by the security central control device according to the real-time video uploaded by the target camera;

[0225] A fault determination module is used to determine whether the security central control device is faulty based on the detection information.

[0226] B10. The device as claimed in claim B9, characterized in that the cloud server pre-stores a plurality of identification groups, wherein each identification group includes an identification of an alarm device and an identification of a camera; the detection information includes a first identification of the target alarm device and a second identification of the target camera; the fault determination module is used to:

[0227] Searching whether there is a target identification group from the multiple identification groups, wherein the identification of the alarm device in the target identification group is the same as the first identification, and the identification of the camera in the target identification group is the same as the second identification;

[0228] If the target identification group does not exist in the multiple identification groups, it is determined that the security central control device is faulty.

[0229] B11. The device as claimed in claim B9, characterized in that the cloud server pre-stores a portrait library, the detection information includes a target image, the target image is obtained by the security central control device from the real-time video, and the target image includes the portrait to be detected determined by the security central control device; the fault determination module is used to:

[0230] Searching in the portrait database whether the portrait to be detected exists;

[0231] If the portrait to be detected exists in the portrait database, it is determined that the security central control device is faulty.

[0232] B12. The device according to claim B11, characterized in that the fault determination module is used to:

[0233] Obtaining the total number of all human figures in the target image and the number of human figures to be detected in the target image;

[0234] Determine whether the total number is the same as the quantity; if the total number is not the same as the quantity, determine that the security central control device is faulty.

[0235] B13. The device as claimed in claim B9, characterized in that the detection information includes a target image, the target image is obtained by the security central control device from the real-time video, the target image includes a human image to be detected determined by the security central control device, and the fault determination module is used to:

[0236] Obtaining the actual alarm category of the target alarm device when it issues an alarm;

[0237] Analyzing the target image to obtain an analysis result;

[0238] According to a preset condition set, the analysis result is judged to obtain a judgment result;

[0239] Determining the target alarm category of the target alarm device according to the judgment result;

[0240] Determine whether the target alarm category is the same as the actual alarm category. If they are not the same, determine that the security central control device is faulty.

[0241] B14. The device according to claim B13, characterized in that the fault determination module is used to:

[0242] When the judgment result indicates that the analysis result does not satisfy all the preset conditions in the preset condition set, the target alarm category is determined to be a warning; otherwise, the target alarm category is determined to be an alarm;

[0243] Among them, the preset condition set includes one or more combinations of a first preset condition that the portrait to be detected is located within a set area in the target image, a second preset condition that the upload time of the target image is within a set time period, and a third preset condition that the posture of the portrait to be detected is a set posture.

[0244] B15. The device according to claim B14, characterized in that the fault determination module is used to:

[0245] If the target alarm category is warning and the actual alarm category is alarm, it is determined that the security central control device is faulty;

[0246] If the target alarm category is alarm and the actual alarm category is warning, it is determined that the security central control device is faulty.

[0247] B16. The device as claimed in claim B9, characterized in that the device also includes:

[0248] A parameter configuration module is used to obtain a parameter configuration request sent by the security central control device; according to the parameter configuration request, the setting parameters are sent to the security central control device; wherein the setting parameters are uploaded by the user terminal, and the setting parameters include detection rules, and the detection rules are used by the security central control device when determining the detection information based on the real-time video.

[0249] C17. A computer-readable storage medium, characterized in that a computer program is stored thereon, and when the program is executed by a processor, the steps of the security detection method described in any one of claims A1 to A8 are implemented.

[0250] D18. A cloud server, characterized in that it comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the steps of the security detection method described in any one of claims A1 to A8 are implemented.

Claims

1. A security detection method, characterized in that: Applied to a cloud server, the method includes: When the security central control device controls the target alarm device to alarm based on the detection information, the detection information is obtained; wherein the detection information is determined by the security central control device according to the real-time video uploaded by the target camera; Determine whether the security central control device is faulty according to the detection information; The cloud server pre-stores a plurality of identification groups, wherein each identification group includes an identification of an alarm device and an identification of a camera; the detection information includes a first identification of the target alarm device and a second identification of the target camera; and determining whether the security central control device is faulty according to the detection information includes: Searching whether there is a target identification group from the multiple identification groups, wherein the identification of the alarm device in the target identification group is the same as the first identification, and the identification of the camera in the target identification group is the same as the second identification; If the target identification group does not exist in the multiple identification groups, it is determined that the security central control device is faulty.

2. The method according to claim 1, characterized in that The detection information includes a target image, which is obtained by the security central control device from the real-time video. The target image includes a human image to be detected determined by the security central control device. The determining whether the security central control device is faulty according to the detection information includes: Obtaining the actual alarm category of the target alarm device when it issues an alarm; Analyzing the target image to obtain an analysis result; According to a preset condition set, the analysis result is judged to obtain a judgment result; Determining the target alarm category of the target alarm device according to the judgment result; Determine whether the target alarm category is the same as the actual alarm category. If they are not the same, determine that the security central control device is faulty.

3. The method according to claim 2, characterized in that Determining the target alarm category of the target alarm device according to the judgment result includes: When the judgment result indicates that the analysis result does not satisfy all the preset conditions in the preset condition set, the target alarm category is determined to be a warning; otherwise, the target alarm category is determined to be an alarm; Among them, the preset condition set includes one or more combinations of a first preset condition that the portrait to be detected is located within a set area in the target image, a second preset condition that the upload time of the target image is within a set time period, and a third preset condition that the posture of the portrait to be detected is a set posture.

4. The method according to claim 3, characterized in that The determining whether the target alarm category is the same as the actual alarm category, and if they are not the same, determining that the security central control device is faulty, includes: If the target alarm category is warning and the actual alarm category is alarm, it is determined that the security central control device is faulty; If the target alarm category is alarm and the actual alarm category is warning, it is determined that the security central control device is faulty.

5. The method according to claim 1, characterized in that The method further comprises: Obtaining a parameter configuration request sent by the security central control device; According to the parameter configuration request, the setting parameters are sent to the security central control device; wherein the setting parameters are uploaded by the user terminal, and the setting parameters include detection rules, and the detection rules are used by the security central control device when determining the detection information based on the real-time video.

6. A security detection device, characterized in that: Applied to a cloud server, the device comprises: A detection information acquisition module, used to acquire the detection information when the security central control device controls the target alarm device to alarm based on the detection information; wherein the detection information is determined by the security central control device based on the real-time video uploaded by the target camera; A fault determination module, used to determine whether the security central control device is faulty according to the detection information; The cloud server pre-stores a plurality of identification groups, wherein each identification group includes an identification of an alarm device and an identification of a camera; the detection information includes a first identification of the target alarm device and a second identification of the target camera; the fault determination module is used to: Searching whether there is a target identification group from the multiple identification groups, wherein the identification of the alarm device in the target identification group is the same as the first identification, and the identification of the camera in the target identification group is the same as the second identification; If the target identification group does not exist in the multiple identification groups, it is determined that the security central control device is faulty.

7. The device according to claim 6, characterized in that The detection information includes a target image, which is obtained by the security central control device from the real-time video. The target image includes a human image to be detected determined by the security central control device. The fault determination module is used to: Obtaining the actual alarm category of the target alarm device when it issues an alarm; Analyzing the target image to obtain an analysis result; According to a preset condition set, the analysis result is judged to obtain a judgment result; Determining the target alarm category of the target alarm device according to the judgment result; Determine whether the target alarm category is the same as the actual alarm category. If they are not the same, determine that the security central control device is faulty.

8. The device according to claim 7, characterized in that The fault determination module is used to: When the judgment result indicates that the analysis result does not satisfy all the preset conditions in the preset condition set, the target alarm category is determined to be a warning; otherwise, the target alarm category is determined to be an alarm; Among them, the preset condition set includes one or more combinations of a first preset condition that the portrait to be detected is located within a set area in the target image, a second preset condition that the upload time of the target image is within a set time period, and a third preset condition that the posture of the portrait to be detected is a set posture.

9. The device according to claim 8, characterized in that The fault determination module is used to: If the target alarm category is warning and the actual alarm category is alarm, it is determined that the security central control device is faulty; If the target alarm category is alarm and the actual alarm category is warning, it is determined that the security central control device is faulty.

10. The device according to claim 6, characterized in that The device also includes: A parameter configuration module is used to obtain a parameter configuration request sent by the security central control device; according to the parameter configuration request, the setting parameters are sent to the security central control device; wherein the setting parameters are uploaded by the user terminal, and the setting parameters include detection rules, and the detection rules are used by the security central control device when determining the detection information based on the real-time video.

11. A computer-readable storage medium, characterized in that: A computer program is stored thereon, and when the program is executed by a processor, the steps of the security detection method described in any one of claims 1 to 5 are implemented.

12. A cloud server, characterized in that: The invention comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the steps of the security detection method described in any one of claims 1 to 5 are implemented.

Images