Intelligent Property Risk Control System and Method

Abstract

The present invention provides an intelligent property risk control system and method, which relates to the technical field of risk control and includes: collecting images based on preset risk control devices, and screening initial risk points based on the image collection results to obtain a first risk point set; comparing the first images of each first image subset corresponding to each first risk point in the first risk point set with preset risk images to determine the risk causes of each first risk point; combining the risk causes with the first images to evaluate the risk levels of the corresponding risk points, so as to determine the risk coefficients of each risk point; performing risk ranking based on the risk coefficients of each risk point, and sequentially performing risk control based on the risk ranking results. By collecting risk images and comparing and analyzing the risk images of the same risk point, more accurate risk causes and risk coefficients of each risk point can be obtained, so as to realize the orderly control of risk points and make the risk control more detailed and accurate.

Description

Technical Field

[0001] The present invention relates to the technical field of risk control, and particularly to an intelligent property risk control system and method. Background Art

[0002] An intelligent property risk control system is an indispensable part of a modern residential community. A good property risk control system can improve the management level of the community and avoid a large number of risks of people, objects and equipment.

[0003] Currently, the methods of property risk control mostly adopt regular reviews by staff or simply rely on monitoring cameras to shoot monitoring videos. The method of using staff reviews requires a large amount of manpower and cannot conduct risk control in a timely manner, which may lead to the further expansion of the risk situation. And the method of simply relying on monitoring cameras to shoot monitoring videos cannot provide timely information feedback when risks occur, reducing the efficiency of the property's risk control.

[0004] Therefore, the present invention provides an intelligent property risk control system and method. Summary of the Invention

[0005] The present invention provides an intelligent property risk control system and method to solve the defects of low risk identification accuracy and low risk control efficiency in the prior art.

[0006] According to the intelligent property risk control system provided by the present invention, it includes:

[0007] A risk point determination module: used for image acquisition based on a preset risk control device, and initial risk point screening based on the image acquisition result to obtain a first risk point set;

[0008] A risk cause determination module: used for comparing each first image in the first image subset corresponding to each first risk point in the first risk point set with a preset risk image to determine the risk cause of each first risk point;

[0009] A risk coefficient determination module: used for combining the risk cause with the first image to evaluate the risk level of the corresponding risk point, so as to determine the risk coefficient of each risk point;

[0010] A risk control module: used for risk ranking based on the risk coefficient of each risk point, and sequentially performing risk control based on the risk ranking result.

[0011] According to the risk point determination module provided by the present invention, it includes:

[0012] A first acquisition unit: used for obtaining the device number of the preset risk control device and the corresponding device acquisition type;

[0013] The first training unit: used to perform risk training on preset risk control devices based on a risk database to obtain corresponding first risk control devices;

[0014] The second acquisition unit: used to initially acquire risk images within the device control range based on the first risk control device to obtain a first acquired image;

[0015] The first screening unit: used to classify the first acquired image based on the device number of the first risk control device and the corresponding device acquisition type to obtain a first classified acquired image;

[0016] The risk point determination unit: used to determine the corresponding azimuth of the initial risk point based on the first classified acquired image and the device number corresponding to each sub-classified acquired image, thereby obtaining a first risk point set.

[0017] According to the risk cause determination module provided by the present invention, it includes:

[0018] The first image determination unit: used to obtain a first image subset of the current first risk point based on the first classified acquired image corresponding to each risk point in the first risk point set;

[0019] Among them, the first image subset contains an image set acquired by different first risk control devices at the same risk point;

[0020] The reference image determination unit: used to compare the image clarity of each first image in each first image subset, and use the first image with the highest clarity as the reference image of the current first image subset;

[0021] The first comparison unit: used to perform a first comparison between the reference image of each first image subset and a preset risk image;

[0022] The first basis determination unit: used to determine the first similarity between the reference image and each preset risk image, and extract the preset risk image with the highest first similarity to the reference image as the first basis for determining the risk cause of the current risk point;

[0023] The second similarity determination unit: used to perform a second comparison between each remaining first image in the same first image subset except the reference image and the preset risk image, and determine the second similarity between each remaining first image and the preset risk image;

[0024] The second basis determination unit: used to extract the preset risk image with the highest similarity to each first image based on the second similarity as the second basis set for determining the risk cause of the current risk point;

[0025] Initial cause determination unit: used to extract the first risk cause corresponding to the first basis and the second risk causes corresponding to each second basis in the second basis set to obtain a second risk cause set;

[0026] First value determination unit: used to extract the risk causes in the second risk cause set that are the same as the first risk cause, and determine the number of second risk causes in the second risk cause set as the first value;

[0027] First ratio determination unit: used to determine the number of all second risk causes in the second risk cause set as the second value, and determine the ratio of the first value to the second value as the first ratio of the current first risk point;

[0028] Risk cause judgment unit: used to compare the first ratio with a preset minimum ratio;

[0029] If the first ratio is less than the preset minimum ratio, it is determined that the first risk cause is not the risk cause of the current first risk point, and the risk cause is determined again;

[0030] Otherwise, it is determined that the first risk cause is the risk cause of the current first risk point.

[0031] According to the risk cause judgment unit provided by the present invention, it further includes:

[0032] If the first risk cause is not the risk cause of the current first risk point, then compare the first risk cause corresponding to the first basis with the second risk causes of each second basis in the second basis set one by one;

[0033] Extract the risk cause with the most occurrences in the comparison results as the risk cause of the current first risk point.

[0034] According to the risk coefficient determination module provided by the present invention, it includes:

[0035] Comparison image determination unit: used to extract all risk images corresponding to the risk levels of the risk cause of the current first risk point based on the risk database as the first risk comparison image set;

[0036] Comparison image extraction unit: used to extract the first first risk comparison image corresponding to each risk level in the first risk comparison image set as the first comparison image;

[0037] Initial level determination unit: used to sort the first comparison images, and compare them with the reference image one by one based on the sorted first comparison images, so as to determine the initial risk level of the reference image;

[0038] Risk coefficient determination unit: used to obtain each risk image included in the initial risk level, compare it with the reference image, obtain the first risk level of the current first risk point, and use the first risk level as the risk coefficient corresponding to the first risk point, so as to obtain the risk coefficient of each risk point.

[0039] According to the initial level determination unit provided by the present invention, it includes:

[0040] Risk determination subunit: used to determine the first comparison image adjacent to the reference image and the first risk level and the second risk level corresponding to the first comparison image based on the one-by-one comparison result;

[0041] Initial determination subunit: used to compare the first risk level and the second risk level, and use the smaller risk level among the first risk level and the second risk level as the initial risk level of the reference image.

[0042] According to the risk control module provided by the present invention, it includes:

[0043] Solution determination unit: used to determine the risk control solution corresponding to the current first risk point based on the risk coefficient of each first risk point;

[0044] Solution sorting unit: used to perform risk sorting based on the risk coefficient of each first risk point, and sort the corresponding risk control solutions based on the risk sorting result;

[0045] Intelligent control unit: used to perform risk control and optimization on the corresponding risk points from high to low based on the sorting result to achieve intelligent control.

[0046] According to the intelligent property risk control method provided by the present invention, it includes:

[0047] Step 1: Perform image acquisition based on a preset risk control device, and perform initial risk point screening based on the image acquisition result to obtain a first risk point set;

[0048] Step 2: Compare each first image in each first image subset corresponding to each first risk point in the first risk point set with a preset risk image to determine the risk cause of each first risk point;

[0049] Step 3: Combine the risk cause with the first image to evaluate the risk level of the corresponding risk point, so as to determine the risk coefficient of each risk point;

[0050] Step 4: Perform risk sorting based on the risk coefficient of each risk point, and perform risk control in sequence based on the risk sorting result.

[0051] The intelligent property risk control system and method provided by the present invention collect risk images and compare and analyze the risk images of the same risk point, so as to obtain more accurate risk causes and risk coefficients for each risk point, thereby realizing the orderly control of risk points and making the risk control more meticulous and accurate. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0053] Figure 1 is the structural diagram of the intelligent property risk control system provided by the embodiment of the present invention;

[0054] Figure 2 is the flowchart of the intelligent property risk control method provided by the embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0055] In order to make the objectives, technical solutions, and advantages of the present invention clearer, the following will clearly and completely describe the technical solutions in the present invention in conjunction with the drawings in the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art without creative efforts based on the embodiments of the present invention belong to the scope of protection of the present invention.

[0056] Embodiment 1:

[0057] The embodiment of the present invention provides an intelligent property risk control system, as Figure 1 shown, including:

[0058] A risk point determination module: configured to collect images based on a preset risk control device and perform initial risk point screening based on the image collection result to obtain a first risk point set;

[0059] A risk cause determination module: configured to compare each first image in the first image subset corresponding to each first risk point in the first risk point set with a preset risk image to determine the risk cause of each first risk point;

[0060] A risk coefficient determination module: configured to combine the risk cause with the first image to evaluate the risk level of the corresponding risk point, thereby determining the risk coefficient of each risk point;

[0061] Risk control module: used to perform risk ranking based on the risk coefficients of each risk point, and perform risk control in sequence based on the risk ranking results.

[0062] In this embodiment, the preset risk control device refers to a device that can collect images of devices and people within the risk control scope and perform preliminary identification and judgment on the risk of the collected images. Among them, the preset risk control device can be a sensor, a camera, etc.

[0063] In this embodiment, the initial risk point refers to the risk point determined according to the device type and number of the risk control device corresponding to the risk image after image collection by the preset risk control device. Among them, the determination of the initial risk point refers to determining the relative position of the risk point.

[0064] In this embodiment, the first risk point set refers to the set of relative positions of all risk points within the preset risk control scope obtained by determining risk points based on the collected images of the preset risk control device.

[0065] In this embodiment, the first image refers to the image contained in the first image set corresponding to each first risk point, where one first image subset corresponds to one risk point.

[0066] In this embodiment, the preset risk image is a set of risk images obtained by extracting risk images at all levels of each risk cause from the risk database according to the risk causes that may occur in the target property risk control system.

[0067] In this embodiment, the risk causes include dangerous goods risk, equipment damage risk, dangerous personnel risk, etc. For example, the intelligent property risk control system can identify and handle some fire situations and give early warnings for larger fire situations.

[0068] In this embodiment, the risk level assessment refers to determining the risk situation contained in the first image according to the comparison result between the first image and the preset risk image. Among them, the risk level varies according to different risk causes. For example, the equipment damage risk can be divided into 5 levels.

[0069] In this embodiment, the risk coefficient is the risk coefficient of the current first risk point comprehensively determined according to all first images of the same first risk point. Among them, the greater the risk coefficient, the higher the risk level.

[0070] In this embodiment, the risk ranking refers to ranking different first risk points according to the risk coefficients, and performing risk control or early warning on the first risk points in sequence according to the ranking results.

[0071] The beneficial effects of the above technical solution are as follows: By collecting risk images and comparing and analyzing the risk images of the same risk point, more accurate risk causes and risk coefficients for each risk point can be obtained, so as to achieve orderly control of risk points and make risk control more meticulous and accurate.

[0072] Embodiment 2:

[0073] Based on Embodiment 1, the risk point determination module includes:

[0074] The first acquisition unit: used to obtain the device number of the preset risk control device and the corresponding device acquisition type;

[0075] The first training unit: used to perform risk training on the preset risk control device based on the risk database to obtain the corresponding first risk control device;

[0076] The second acquisition unit: used to initially acquire risk images within the device control range based on the first risk control device to obtain the first acquisition image;

[0077] The first screening unit: used to classify the first acquisition image based on the device number of the first risk control device and the corresponding device acquisition type to obtain the first classified acquisition image;

[0078] The risk point determination unit: used to determine the corresponding orientation of the initial risk point based on the first classified acquisition image and the device number corresponding to each sub-classified acquisition image, so as to obtain the first risk point set.

[0079] In this embodiment, the preset risk control device refers to a device that can collect images of devices and people within the risk control range and initially identify and judge the risk of the collected images. Among them, the preset risk control device can be a sensor, a camera, etc. For example, if the orientation of the camera numbered 01 is the upper left corner of the community gate, then the monitored orientation of the upper left corner of the community gate is the corresponding risk point.

[0080] In this embodiment, risk training refers to training the initial risk model according to the risk images that may appear due to various risk causes, so that the preset risk control device can initially judge the risk images, thereby reducing the number of risk points that need to be analyzed and improving the analysis efficiency.

[0081] In this embodiment, the first risk control device refers to the risk control device obtained after model training of the initial risk model corresponding to the preset risk control device.

[0082] In this embodiment, the first acquisition image refers to the acquisition image obtained by collecting risk images within the device control range based on the first risk control device.

[0083] In this embodiment, the first classified acquisition image is obtained by classifying the first acquisition image according to the device number of the first risk control device and the corresponding device acquisition type.

[0084] In this embodiment, the initial risk point refers to the risk point determined according to the device number and device acquisition type of the first risk control device corresponding to the first classified acquisition image.

[0085] In this embodiment, the first risk point set refers to the risk point set composed of the risk points that can be acquired within the risk control range and the corresponding orientations.

[0086] The beneficial effects of the above technical solutions are as follows: By classifying the acquisition images of different devices, the risk point orientations and the corresponding images of each risk point can be obtained, and comparative analysis can be performed based on the corresponding images, so that risk control is more detailed and accurate.

[0087] Embodiment 3:

[0088] Based on Embodiment 2, the risk cause determination module includes:

[0089] The first image determination unit: used to obtain the first image subset of the current first risk point based on the first classified acquisition image corresponding to each risk point in the first risk point set;

[0090] Among them, the first image subset contains the image set acquired by different first risk control devices at the same risk point;

[0091] The reference image determination unit: used to compare the image clarity of each first image in each first image subset, and use the first image with the highest clarity as the reference image of the current first image subset;

[0092] The first comparison unit: used to perform a first comparison between the reference image of each first image subset and the preset risk image;

[0093] The first basis determination unit: used to determine the first similarity between the reference image and each preset risk image, and extract the preset risk image with the highest first similarity to the reference image as the first basis for determining the risk cause of the current risk point;

[0094] The second similarity determination unit: used to perform a second comparison between each remaining first image in the same first image subset and the preset risk image one by one to determine the second similarity between each remaining first image and the preset risk image;

[0095] The second basis determination unit: used to extract the preset risk image with the highest similarity to each first image based on the second similarity as the second basis set for determining the risk cause of the current risk point;

[0096] Initial cause determination unit: used to extract the first risk cause corresponding to the first basis and the second risk causes corresponding to each second basis in the second basis set to obtain a second risk cause set;

[0097] First value determination unit: used to extract the risk causes in the second risk cause set that are the same as the first risk cause, and determine the number of second risk causes in the second risk cause set as the first value;

[0098] First ratio determination unit: used to determine the number of all second risk causes in the second risk cause set as the second value, and determine the ratio of the first value to the second value as the first ratio of the current first risk point;

[0099] Risk cause judgment unit: used to compare the first ratio with a preset minimum ratio;

[0100] If the first ratio is less than the preset minimum ratio, it is determined that the first risk cause is not the risk cause of the current first risk point, and the risk cause is determined again;

[0101] Otherwise, it is determined that the first risk cause is the risk cause of the current first risk point.

[0102] In this embodiment, the first image subset is an image set composed of images collected at the same risk point by different first risk control devices.

[0103] In this embodiment, image clarity means that there are many factors that may cause image blurring during image acquisition, transmission, and processing. The image with the minimum image blur degree is extracted from the first image subset as the reference image.

[0104] In this embodiment, the reference image refers to the image with the highest image clarity in the first image subset.

[0105] In this embodiment, the preset risk images are risk image sets obtained by extracting risk images at all levels of each risk cause from the risk database according to the risk causes that may occur in the target property risk control system.

[0106] In this embodiment, the first comparison refers to comparing the image similarity between the reference image and each image in the preset risk images.

[0107] In this embodiment, the first similarity refers to the image similarity between the reference image and each image in the preset risk images, where the value range of the first similarity is [0, 1).

[0108] In this embodiment, the first basis refers to extracting, from the preset risk images, the risk cause corresponding to the preset risk image with the highest first similarity to the reference image as the first basis, and the second basis set refers to obtaining the second basis set by extracting, from the preset risk images, the risk causes corresponding to the preset risk images with the highest second similarity to each of the remaining first images in the same first image subset as the reference image.

[0109] In this embodiment, the second similarity refers to the image similarity between each of the remaining first images in the same first image subset as the reference image and each image in the preset risk images.

[0110] In this embodiment, the first value refers to the number of risk causes in the second risk causes of the second risk cause set that are the same as the first risk cause, where the first value is a positive integer.

[0111] In this embodiment, the second value refers to the number of second risk causes in the second risk cause set, and the first ratio is the ratio of the first value to the second value, where the value range of the first ratio is (0, 1].

[0112] The beneficial effect of the above technical solution is that by comprehensively judging the risk causes of the risk points, the judgment of the risk causes of the risk points can be made more accurate, so as to achieve precise control of the corresponding risk points.

[0113] Embodiment 4:

[0114] Based on Embodiment 3, the risk cause judgment unit further includes:

[0115] If the first risk cause is not the risk cause of the current first risk point, then compare one by one the first risk cause corresponding to the first basis with the second risk causes of each second basis in the second basis set;

[0116] Extract the risk cause with the most occurrences in the comparison results as the risk cause of the current first risk point.

[0117] The beneficial effect of the above technical solution is that by comprehensively judging the risk causes of the risk points, the judgment of the risk causes of the risk points can be made more accurate, so as to achieve precise control of the corresponding risk points.

[0118] Embodiment 5:

[0119] Based on Embodiment 3, the risk coefficient determination module includes:

[0120] Comparison image determination unit: used to extract, based on the risk database, the risk images corresponding to all risk levels of the risk cause of the current first risk point as the first risk comparison image set;

[0121] Comparison image extraction unit: used to extract the first first-risk comparison image corresponding to each risk level in the first set of risk comparison images as the first comparison image;

[0122] Initial level determination unit: used to sort the first comparison images and compare them one by one with the reference image based on the sorted first comparison images, so as to determine the initial risk level of the reference image;

[0123] Risk coefficient determination unit: used to obtain each risk image included in the initial risk level, compare it with the reference image, obtain the first risk level of the current first risk point, and use the first risk level as the risk coefficient corresponding to the first risk point, so as to obtain the risk coefficients of each risk point.

[0124] In this embodiment, the risk level refers to determining the risk situation included in the first image according to the comparison result between the first image and the preset risk image. Among them, the risk levels are different according to different risk reasons. For example, the equipment damage risk can be divided into 5 levels.

[0125] In this embodiment, the first set of risk comparison images is a set composed of risk images corresponding to all risk levels included in the first risk reason corresponding to the current first risk point extracted from the risk database. For example, if the risk reason is equipment fire, then the risk images of equipment fire at all risk levels are extracted from the risk database.

[0126] In this embodiment, the first comparison image is obtained by extracting the first first-risk comparison image corresponding to each risk level in the first set of risk comparison images. For example, when the risk reason is equipment fire and the equipment level includes a total of 5 levels, the first first-risk comparison image corresponding to the minimum fire degree of the 4th-level fire is the first comparison image.

[0127] In this embodiment, the initial risk level is determined according to the risk level corresponding to the first comparison image.

[0128] In this embodiment, the risk coefficient is the risk coefficient of the current first risk point comprehensively determined according to all first images of the same first risk point. Among them, the greater the risk coefficient, the higher the risk degree.

[0129] The beneficial effects of the above technical solutions are: by comparing the reference image with the first risk comparison images, the initial risk level of the reference image is obtained, and the risk coefficients of the corresponding first risk points are more accurately determined according to each first risk comparison image in the initial risk level, so that the risk points can be more accurately controlled.

[0130] Embodiment 6:

[0131] Based on Embodiment 5, the initial level determination unit includes:

[0132] A risk determination subunit: configured to determine a first comparison image adjacent to a reference image, and a first risk level and a second risk level corresponding to the first comparison image based on the one-by-one comparison results;

[0133] An initial determination subunit: configured to compare the first risk level and the second risk level, and use the smaller risk level of the first risk level and the second risk level as the initial risk level of the reference image.

[0134] In this embodiment, the first risk level and the second risk level refer to determining the risk levels corresponding to the first comparison image adjacent to the reference image as the first risk level and the second risk level according to the comparison results between the reference image and the first comparison image. Among them, the initial risk level of the reference image is between the first risk level and the second risk level.

[0135] In this embodiment, the initial risk level is obtained by comparing the first risk level and the second risk level, and using the smaller risk level of the first risk level and the second risk level as the initial risk level of the reference image.

[0136] The beneficial effects of the above technical solution are: By comparing images, the initial risk level of the first risk point can be obtained, and it can be optimized according to the initial risk level to obtain a more accurate risk level, so as to better achieve precise control of the risk point.

[0137] Embodiment 7:

[0138] Based on Embodiment 5, a risk control module includes:

[0139] A solution determination unit: configured to determine a risk control solution corresponding to the current first risk point based on the risk coefficient of each first risk point;

[0140] A solution sorting unit: configured to perform risk sorting based on the risk coefficient of each first risk point, and sort the corresponding risk control solutions based on the risk sorting results;

[0141] An intelligent control unit: configured to perform risk control and optimization on the corresponding risk points from high to low based on the sorting results to achieve intelligent control.

[0142] In this embodiment, the risk control solution refers to a risk control solution for the corresponding first risk point determined according to the risk coefficient of the first risk point and the corresponding risk cause. For example, if the risk cause of the first risk point is equipment fire and the risk coefficient is 4, the risk control solution can be to report the location of the risk point to the staff and manually extinguish the equipment fire.

[0143] In this embodiment, the risk sorting refers to sorting the first risk points according to the risk coefficient of each first risk point, so as to perform risk handling on the risk points in order.

[0144] The beneficial effects of the above technical solution are as follows: By determining the risk control plan for each risk point based on the risk coefficient and executing the risk control plans in sequence according to the risk coefficient ranking results, the control of risk points can be made more timely and effective, and accurate control of risk points can also be achieved.

[0145] Example 8:

[0146] The embodiment of the present invention provides an intelligent property risk control method, as Figure 2 shown, including:

[0147] Step 1: Perform image acquisition based on a preset risk control device, and perform initial risk point screening based on the image acquisition result to obtain a first risk point set;

[0148] Step 2: Compare each first image in the first image subset corresponding to each first risk point in the first risk point set with a preset risk image to determine the risk cause of each first risk point;

[0149] Step 3: Combine the risk cause with the first image to evaluate the risk level of the corresponding risk point, so as to determine the risk coefficient of each risk point;

[0150] Step 4: Perform risk ranking based on the risk coefficient of each risk point, and perform risk control in sequence based on the risk ranking result.

[0151] The beneficial effects of the above technical solution are as follows: By collecting risk images and comparing and analyzing the risk images of the same risk point, more accurate risk causes and risk coefficients of each risk point can be obtained, so as to achieve orderly control of risk points, and risk control can be made more meticulous and accurate.

[0152] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements on some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. Intelligent property risk management system, characterized by: include: Risk point determination module: used to collect images based on the preset risk control equipment, and to screen initial risk points based on the image collection results to obtain a first risk point set; A risk cause determination module: used to compare each first image in the first image subset corresponding to each first risk point in the first risk point set with a preset risk image to determine the risk cause of each first risk point; Risk coefficient determination module: used for combining the risk cause with the first image to evaluate the risk level of the corresponding risk point, so as to determine the risk coefficient of each risk point; Risk management and control module: used to sort risks based on the risk coefficient of each risk point, and perform risk management and control in turn based on the risk sorting results; Among them, the risk point determination module includes: The first collection unit is used to obtain the device number of the preset risk control device and the corresponding device collection type; A first training unit: used to perform risk training on a preset risk management and control device based on a risk database to obtain a corresponding first risk management and control device; A second acquisition unit: configured to initially acquire a risk image within a device control range based on the first risk control device to obtain a first acquired image; A first screening unit: used for classifying the first collected image based on the device number of the first risk control device and the corresponding device collection type to obtain a first classified collected image; A risk point determination unit is used to determine the corresponding position of the initial risk point based on the first classification acquisition image and the device number corresponding to each sub-classification acquisition image, so as to obtain a first risk point set; Among them, the risk cause determination module includes: A first image determination unit: configured to obtain a first image subset of the current first risk point based on a first classified acquired image corresponding to each risk point in the first risk point set; The first image subset includes a set of images collected by different first risk management and control devices at the same risk point; A reference image determination unit: used for comparing the image clarity of each first image in each first image subset, and taking the first image with the highest clarity as the reference image of the current first image subset; A first comparison unit: configured to perform a first comparison between a reference image in each first image subset and a preset risk image; A first basis determination unit: used to determine a first similarity between the reference image and each preset risk image, and extract the preset risk image with the highest first similarity to the reference image as a first basis for determining the risk cause of the current risk point; A second similarity determination unit is used to perform a second comparison between the remaining first images in the same first image subset except the reference image and the preset risk image one by one, and determine a second similarity between each remaining first image and the preset risk image; A second basis determination unit: configured to extract, based on the second similarity, a preset risk image having the highest similarity to each first image as a second basis set for determining the risk cause of the current risk point; An initial cause determination unit: used for extracting a first risk cause corresponding to the first basis and a second risk cause corresponding to each second basis in the second basis set to obtain a second risk cause set; A first value determination unit: used for extracting risk causes consistent with the first risk cause from the second risk cause set, and determining the number of second risk causes extracted from the second risk cause set as the first value; A first ratio determination unit: used to determine the number of all second risk causes in the second risk cause set as a second value, and determine a ratio of the first value to the second value as a first ratio of the current first risk point; A risk cause determination unit: used for comparing the first ratio with a preset minimum ratio; If the first ratio is less than the preset minimum ratio, it is determined that the first risk cause is not the risk cause of the current first risk point, and the risk cause is determined again; Otherwise, the first risk cause is judged to be the risk cause of the current first risk point.

2. The intelligent property risk management and control system according to claim 1, characterized in that: The risk cause judgment unit also includes: If the first risk reason is not the risk reason of the current first risk point, then comparing the first risk reason corresponding to the first basis with the second risk reason of each second basis in the second basis set one by one; The risk cause that appears most frequently in the comparison results is extracted as the risk cause of the current first risk point.

3. The intelligent property risk management and control system according to claim 1, characterized in that: Risk factor determination module, including: A comparison image determination unit: configured to extract risk images corresponding to all risk levels of the risk cause corresponding to the current first risk point based on the risk database as a first risk comparison image set; A comparison image extraction unit: used for extracting the first first risk comparison image corresponding to each risk level in the first risk comparison image set as the first comparison image; An initial level determination unit: used for sorting the first comparison images, and comparing the sorted first comparison images with the reference images one by one, so as to determine the initial risk level of the reference image; Risk coefficient determination unit: used to obtain each risk image contained in the initial risk level, and compare it with the reference image to obtain the first risk level of the current first risk point, and use the first risk level as the risk coefficient corresponding to the first risk point, thereby obtaining the risk coefficient of each risk point.

4. The intelligent property risk management and control system according to claim 3 is characterized in that: Initial grade determination units, including: Risk determination subunit: used for determining a first comparison image adjacent to the reference image and a first risk level and a second risk level corresponding to the first comparison image based on the comparison results one by one; Initial determination subunit: used for comparing the first risk level and the second risk level, and taking the smaller risk level between the first risk level and the second risk level as the initial risk level of the reference image.

5. The intelligent property risk management and control system according to claim 3 is characterized in that: Risk management module, including: A scheme determining unit: used to determine a risk control scheme corresponding to a current first risk point based on a risk coefficient of each first risk point; Scheme ranking unit: used to perform risk ranking based on the risk coefficient of each first risk point, and to sort the corresponding risk control schemes based on the risk ranking result; Intelligent management and control unit: used to perform risk management and optimization of corresponding risk points from high to low based on the sorting results to achieve intelligent management and control.

6. The smart property risk management method is characterized by: include: Step 1: Perform image acquisition based on a preset risk control device, and perform initial risk point screening based on the image acquisition results to obtain a first risk point set; Step 2: Compare each first image in the first image subset corresponding to each first risk point in the first risk point set with a preset risk image to determine the risk cause of each first risk point; Step 3: combining the risk cause with the first image to evaluate the risk level of the corresponding risk point, thereby determining the risk coefficient of each risk point; Step 4: Rank the risks based on the risk coefficient of each risk point, and perform risk management and control in turn based on the risk ranking results; Wherein, image acquisition is performed based on a preset risk control device, and initial risk points are screened based on the image acquisition results to obtain a first risk point set, including: The first collection unit is used to obtain the device number of the preset risk control device and the corresponding device collection type; A first training unit: used to perform risk training on a preset risk management and control device based on a risk database to obtain a corresponding first risk management and control device; A second acquisition unit: configured to initially acquire a risk image within a device control range based on the first risk control device to obtain a first acquired image; A first screening unit: used for classifying the first collected image based on the device number of the first risk control device and the corresponding device collection type to obtain a first classified collected image; A risk point determination unit is used to determine the corresponding position of the initial risk point based on the first classification acquisition image and the device number corresponding to each sub-classification acquisition image, so as to obtain a first risk point set; The step of comparing each first image in the first image subset corresponding to each first risk point in the first risk point set with a preset risk image to determine the risk cause of each first risk point includes: A first image determination unit: configured to obtain a first image subset of the current first risk point based on a first classified acquired image corresponding to each risk point in the first risk point set; The first image subset includes a set of images collected by different first risk management and control devices at the same risk point; A reference image determination unit: used for comparing the image clarity of each first image in each first image subset, and taking the first image with the highest clarity as the reference image of the current first image subset; A first comparison unit: configured to perform a first comparison between a reference image in each first image subset and a preset risk image; A first basis determination unit: used to determine a first similarity between the reference image and each preset risk image, and extract the preset risk image with the highest first similarity to the reference image as a first basis for determining the risk cause of the current risk point; A second similarity determination unit is used to perform a second comparison between the remaining first images in the same first image subset except the reference image and the preset risk image one by one, and determine a second similarity between each remaining first image and the preset risk image; A second basis determination unit: configured to extract, based on the second similarity, a preset risk image having the highest similarity to each first image as a second basis set for determining the risk cause of the current risk point; An initial cause determination unit: used for extracting a first risk cause corresponding to the first basis and a second risk cause corresponding to each second basis in the second basis set to obtain a second risk cause set; A first value determination unit: used for extracting risk causes consistent with the first risk cause from the second risk cause set, and determining the number of second risk causes extracted from the second risk cause set as the first value; A first ratio determination unit: used to determine the number of all second risk causes in the second risk cause set as a second value, and determine a ratio of the first value to the second value as a first ratio of the current first risk point; A risk cause determination unit: used for comparing the first ratio with a preset minimum ratio; If the first ratio is less than the preset minimum ratio, it is determined that the first risk cause is not the risk cause of the current first risk point, and the risk cause is determined again; Otherwise, the first risk cause is judged to be the risk cause of the current first risk point.

Images