Method and device for evaluating dynamic risk levels of risk events in various regions of an enterprise

Abstract

The present invention discloses a method and device for evaluating the dynamic risk level of risk events in various regions of an enterprise. The method for evaluating the dynamic risk level of risk events in various regions of an enterprise comprises: acquiring risk events in various regions in real time; determining the risk bias of each key point in the risk event according to the risk event, wherein the risk bias includes high risk, low risk and medium risk; determining a feature vector corresponding to each key point according to the risk bias corresponding to the key point; determining a feature representation corresponding to the risk event according to the feature vector; and inputting the feature representation corresponding to the risk event into a trained algorithm model to determine the corresponding risk level.

Description

Technical Field

[0001] The present invention relates to the technical field of safe production management and control, and in particular to a method and device for evaluating the dynamic risk level of risk events in various regions of an enterprise. Background Art

[0002] In recent years, personal injuries caused by personnel risk events have occurred frequently. Inadequate regional safety management is one of the main causes of production safety accidents. Enterprises often need to spend a lot of energy to conduct on-site control, and lack effective means to timely discover and evaluate the safety level of the site before an accident occurs. Therefore, it is often the case that accidents are only realized after they occur, and the cost is heavy.

[0003] The main reason is that the on-site safety management scenarios of enterprises are complex, involving employees, contractors, external visitors, etc. Some personnel have not received enterprise safety training or the training is not in place, and their self-consciousness is not high. Some illegal operations are not corrected after repeated warnings, and on-site safety management is difficult. In order to ensure the safe production of enterprises, some enterprises have equipped safety supervisors to supervise on-site, but there are still cases where safety supervisors are negligent, perfunctory, or even leave their posts without authorization, resulting in a lack of supervision on site. Even if safety supervisors are on duty, some employees and contractors despise safety supervisors and are careless about safety hazards in various areas. Therefore, it is very likely that accidents will occur inadvertently, causing loss of life and property. The manual offline control method adopted by enterprises is often difficult to achieve results, cannot be comprehensive, and the management cost is also very high.

[0004] Risk events of relevant personnel will increase the probability of accidents in the area. In reality, there are usually multiple risk event scenarios in a specific area at the same time or in the same time period, and different risk events have different impacts on the risk of the area. Failure to grasp the risk events of various areas in a timely manner has become a problem in controlling the safety of the area.

[0005] The above contents are only used to assist in understanding the technical solution of the present invention and do not constitute an admission that the above contents are prior art. Summary of the invention

[0006] The main purpose of the present invention is to provide a method and device for evaluating the dynamic risk level of risk events in various regions of an enterprise, aiming to solve the technical problem in the prior art that risk events in various regions cannot be grasped in a timely manner.

[0007] To achieve the above object, the present invention provides a method for evaluating the dynamic risk level of risk events in various regions of an enterprise, which is characterized by comprising:

[0008] Obtain risk events in each region in real time;

[0009] According to the risk event, determine the risk bias degree of each key point in the risk event, wherein the risk bias degree includes high risk, low risk, and medium risk;

[0010] Determine the characteristic vector corresponding to each key point according to the risk bias degree corresponding to the key point;

[0011] Determining, according to the feature vector, a feature representation corresponding to the risk event;

[0012] Inputting the feature representation corresponding to the risk event into the trained algorithm model to determine the corresponding risk level;

[0013] Among them, the method for determining the risk bias degree of each key point includes:

[0014] According to the formula Calculate the correlation of each key point with other key points in the pre-established high-risk set;

[0015] According to the formula Calculate the correlation of each key point with other key points in the pre-established low-risk set;

[0016] According to the formula Calculate the correlation of each key point with other key points in the pre-established medium risk set;

[0017] Among them, n is the number of key points with high risk concentration;

[0018] m is the number of key points in the low-risk concentration;

[0019] k is the number of critical points in the medium risk concentration;

[0020] r(w, v) is the correlation between the two key points w and v;

[0021] G is the high-risk set;

[0022] H is the low risk set;

[0023] N is the medium risk set;

[0024] ;

[0025] k(w) is the probability of key point w appearing in the risk event;

[0026] k(v) is the probability of key point v appearing in the risk event;

[0027] k(w, v) is the probability that key points w and v appear together in a risk event;

[0028] Calculate the risk bias of each key point, the calculation formula is as follows:

[0029] High-risk bias = correlation between the key point and other key points in the high-risk set - correlation between the key point and other key points in the medium-risk set - correlation between the key point and other key points in the low-risk set;

[0030] Low risk bias = correlation between the key point and other key points in the low risk set - correlation between the key point and other key points in the high risk set - correlation between the key point and other key points in the medium risk set;

[0031] Medium risk bias = the correlation between the key point and other key points in the medium risk set - the correlation between the key point and other key points in the high risk set - the correlation between the key point and other key points in the low risk set.

[0032] Preferably, in the method for evaluating the dynamic risk level of risk events in each region of the enterprise, inputting the feature representation corresponding to the risk event into the trained algorithm model to determine the corresponding risk level includes:

[0033] The feature representation corresponding to the risk event is input into the trained neural network model to determine the corresponding risk level.

[0034] Preferably, in the method for evaluating the dynamic risk level of risk events in each region of the enterprise, inputting the feature representation corresponding to the risk event into the trained algorithm model to determine the corresponding risk level includes:

[0035] The risk event and the preset fitness function are input into a preset genetic algorithm to determine the most suitable risk event level from the population.

[0036] Preferably, in the method for evaluating the dynamic risk level of risk events in each region of the enterprise, after the step of inputting the feature representation corresponding to the risk event into the trained algorithm model to determine the corresponding risk level, the evaluation method further includes:

[0037] Obtain risk events within a preset time period corresponding to each area and the risk level corresponding to the risk events;

[0038] Calculate the risk level of each area using the following formula:

[0039] ;

[0040] is the comprehensive dynamic risk level of region i;

[0041] x1, x2, ..., x n is the risk event level corresponding to risk event 1, risk event 2, ..., risk event n;

[0042] n is the number of risk events within a preset time period in region i.

[0043] f1, f2, ..., f n are x1, x2, ..., x n The corresponding weight.

[0044] Preferably, in the method for evaluating the dynamic risk level of risk events in each region of the enterprise, the step of calculating the risk level of each region further includes:

[0045] Determine the first risk weight of each region according to the pre-established correspondence between the region and the first risk weight;

[0046] Determine the second risk weight corresponding to the corresponding time period according to the time period of the risk event within the preset time period;

[0047] The weights corresponding to the risk events within the preset time period are calculated based on the first risk weight and the second risk weight.

[0048] Preferably, in the method for evaluating the dynamic risk level of risk events in each region of the enterprise, the weight corresponding to the risk event within the preset time period is calculated according to the first risk weight and the second risk weight, and the calculation formula is as follows:

[0049] ;

[0050] f i is the first risk weight of region i;

[0051] f j The weight corresponding to the risk events within the preset time period;

[0052] f ij is the weight of region i in the preset time period.

[0053] Preferably, in the method for evaluating the dynamic risk level of risk events in each region of the enterprise, after the step of calculating the risk level of each region, the evaluation method further includes:

[0054] Send risk warnings to each area based on the risk level of each area.

[0055] In order to achieve the above object, the present invention also provides a device for evaluating the dynamic risk level of risk events in various regions of an enterprise, comprising:

[0056] An acquisition unit is used to acquire risk events in each area in real time;

[0057] A calculation unit, used to determine the risk bias degree of each key point in the risk event according to the risk event, wherein the risk bias degree includes high risk, low risk and medium risk;

[0058] A determination unit, configured to determine a feature vector corresponding to each key point according to the risk bias degree corresponding to each key point;

[0059] A characterization unit, used to determine a feature representation corresponding to the risk event according to the feature vector;

[0060] An output unit, used to input the feature representation corresponding to the risk event into the trained algorithm model to determine the corresponding risk level;

[0061] Wherein, the computing unit is further used for:

[0062] According to the formula Calculate the correlation of each key point with other key points in the pre-established high-risk set;

[0063] According to the formula Calculate the correlation of each key point with other key points in the pre-established low-risk set;

[0064] According to the formula Calculate the correlation of each key point with other key points in the pre-established medium risk set;

[0065] Among them, n is the number of key points with high risk concentration;

[0066] m is the number of key points in the low-risk concentration;

[0067] k is the number of critical points in the medium risk concentration;

[0068] r(w, v) is the correlation between the two key points w and v;

[0069] G is the high-risk set;

[0070] H is the low risk set;

[0071] N is the medium risk set;

[0072] ;

[0073] k(w) is the probability of key point w appearing in the risk event;

[0074] k(v) is the probability of key point v appearing in the risk event;

[0075] k(w, v) is the probability that key points w and v appear together in a risk event;

[0076] Calculate the risk bias of each key point, the calculation formula is as follows:

[0077] High-risk bias = correlation between the key point and other key points in the high-risk set - correlation between the key point and other key points in the medium-risk set - correlation between the key point and other key points in the low-risk set;

[0078] Low risk bias = correlation between the key point and other key points in the low risk set - correlation between the key point and other key points in the high risk set - correlation between the key point and other key points in the medium risk set;

[0079] Medium risk bias = the correlation between the key point and other key points in the medium risk set - the correlation between the key point and other key points in the high risk set - the correlation between the key point and other key points in the low risk set.

[0080] In order to achieve the above object, the present invention further provides a computer device, characterized in that it includes:

[0081] at least one processor; and,

[0082] a memory communicatively connected to the at least one processor; wherein,

[0083] The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the above-mentioned method for evaluating the dynamic risk level of risk events in various regions of the enterprise.

[0084] In order to achieve the above-mentioned purpose, the present invention also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the above-mentioned method for evaluating the dynamic risk level of risk events in various regions of an enterprise.

[0085] The present invention has at least the following beneficial effects:

[0086] The present invention obtains risk events in various areas in real time; determines the risk bias of each key point in the risk event based on the risk event, and the risk bias includes high risk, low risk and medium risk; determines the feature vector corresponding to the key point based on the risk bias corresponding to each key point; determines the feature representation corresponding to the risk event based on the feature vector; inputs the feature representation corresponding to the risk event into a trained algorithm model to determine the corresponding risk level, so that the risk level of the risk event can be determined timely and accurately. BRIEF DESCRIPTION OF THE DRAWINGS

[0087] Figure 1 A schematic diagram of a first implementation of a method for evaluating dynamic risk levels of risk events in various regions of an enterprise provided by the present invention;

[0088] Figure 2A schematic diagram of a device for evaluating the dynamic risk level of risk events in various regions of an enterprise provided by the present invention;

[0089] Figure 3 A schematic diagram of a computer device according to the present invention.

[0090] The purpose, features and advantages of the present invention will be further described with reference to the accompanying drawings in conjunction with the embodiments. DETAILED DESCRIPTION

[0091] The technical solution of the present invention will be clearly and completely described below in conjunction with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all of the embodiments. The present invention will be described in detail below with reference to the accompanying drawings and in conjunction with the embodiments. It should be noted that the embodiments of the present invention and the features in the embodiments can be combined with each other without conflict.

[0092] In the embodiments of the present invention, the term "and / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B may represent three situations: A exists alone, A and B exist at the same time, and B exists alone. The character " / " generally indicates that the associated objects before and after are in an "or" relationship.

[0093] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence.

[0094] In the embodiments of the present invention, the term "plurality" refers to two or more than two, and other quantifiers are similar.

[0095] In the present invention, unless otherwise specified, the directional words used, such as "up, down, top, bottom", usually refer to the directions shown in the drawings, or to the components themselves in the vertical, perpendicular or gravity directions; similarly, for ease of understanding and description, "inside and outside" refer to the inside and outside relative to the outline of each component itself, but the above-mentioned directional words are not used to limit the present invention.

[0096] In order to make the purpose, technical scheme and advantages of the embodiments of the present invention clearer, the embodiments of the present invention will be described in detail below in conjunction with the accompanying drawings. However, it can be understood by those skilled in the art that in the embodiments of the present invention, many technical details are proposed in order to enable the reader to better understand the present invention. However, even without these technical details and various changes and modifications based on the following embodiments, the technical scheme claimed in the present invention can also be implemented. The division of the following embodiments is for the convenience of description and should not constitute any limitation on the specific implementation of the present invention. The various embodiments can be combined and referenced with each other under the premise of no contradiction.

[0097] In order to solve the above problems, the present embodiment relates to a method for evaluating the dynamic risk level of risk events in various regions of an enterprise, which can be applied to computer devices. The computer devices can be electronic devices with data processing capabilities, such as desktop computers, tablet computers, notebooks, etc. In other embodiments, they can also be other electronic devices with data processing capabilities, and no specific restrictions are made here.

[0098] The following is an explanation of the implementation details of the method for evaluating the dynamic risk level of risk events in each region of an enterprise according to the first embodiment of the present invention. The following content is only provided for ease of understanding and is not necessary for the implementation of this solution.

[0099] The specific process of this implementation is as follows: Figure 1 As shown, specifically including:

[0100] Step S100, obtaining risk events in each area in real time;

[0101] It should be understood that there may be one or more risk events in each area. For example, the data obtained at xx:xx on xx / xx / xx that “xx was not wearing a safety helmet when performing hoisting operations in area 1”.

[0102] Step S200, determining the risk bias of each key point in the risk event according to the risk event, wherein the risk bias includes high risk, low risk, and medium risk;

[0103] It should be understood that the key point can be a group of simple phrases, such as "not wearing a safety helmet", or a single word "hoisting". There is no specific limitation here and it can be set as needed.

[0104] The risk bias can be divided into high risk, low risk, and medium risk, and can also be divided into extremely high risk, general high risk, lower risk, general low risk, and medium risk according to needs. The specific division can also be determined based on comprehensive considerations such as assessment accuracy. In other embodiments, it can also be determined based on different risk event scenarios.

[0105] Among them, the method for determining the risk bias degree of each key point includes:

[0106] According to the formula Calculate the correlation of each key point with other key points in the pre-established high-risk set;

[0107] According to the formula Calculate the correlation of each key point with other key points in the pre-established low-risk set;

[0108] According to the formula Calculate the correlation of each key point with other key points in the pre-established medium risk set;

[0109] Among them, n is the number of key points with high risk concentration;

[0110] m is the number of key points in the low-risk concentration;

[0111] k is the number of critical points in the medium risk concentration;

[0112] r(w, v) is the correlation between the two key points w and v;

[0113] G is the high-risk set;

[0114] H is the low risk set;

[0115] N is the medium risk set;

[0116] ;

[0117] k(w) is the probability of key point w appearing in the risk event;

[0118] k(v) is the probability of key point v appearing in the risk event;

[0119] k(w, v) is the probability that key points w and v appear together in a risk event;

[0120] Calculate the risk bias of each key point, the calculation formula is as follows:

[0121] High-risk bias = correlation between the key point and other key points in the high-risk set - correlation between the key point and other key points in the medium-risk set - correlation between the key point and other key points in the low-risk set;

[0122] Low risk bias = correlation between the key point and other key points in the low risk set - correlation between the key point and other key points in the high risk set - correlation between the key point and other key points in the medium risk set;

[0123] Medium risk bias = the correlation between the key point and other key points in the medium risk set - the correlation between the key point and other key points in the high risk set - the correlation between the key point and other key points in the low risk set.

[0124] It should be noted that the high-risk set may include {dangerous goods are placed in the wrong position, ...}; similarly, the low-risk set may also include {no helmet is worn, ...}. In addition, in different areas, the corresponding high-risk set, medium-risk set, and low-risk set may be different. For example, for areas and office areas where more dangerous goods are stored in chemical plants, the risks brought by personnel's operating behaviors are very different. Therefore, the high-risk set, medium-risk set, and low-risk set can be determined by region. When calculating the risk bias of risk events occurring in each area, the corresponding high-risk set, medium-risk set, and low-risk set need to be determined.

[0125] Step S300, determining a feature vector corresponding to each key point according to the risk bias degree corresponding to each key point;

[0126] It should be understood that the construction of the feature vector corresponding to the key point can be to use the risk bias of the key point as the corresponding weight to construct the feature vector of the key point. The dimension of the feature vector can be three-dimensional or other multi-dimensional, which can be determined according to the number of risk bias divisions. For example, if the risk bias includes high risk, low risk, and medium risk, the feature vector can be constructed into at least three dimensions.

[0127] Step S400, determining a feature representation corresponding to the risk event according to the feature vector;

[0128] It should be understood that each risk event is composed of multiple key points, so the feature vectors corresponding to the key points can be combined to form a feature representation corresponding to the risk event.

[0129] Step S500, inputting the feature representation corresponding to the risk event into the trained algorithm model to determine the corresponding risk level;

[0130] Specifically, the feature representation corresponding to the risk event is input into a trained neural network model to determine the corresponding risk level. For example, the feature representation corresponding to the risk event can be input into a trained recurrent neural network model to output the corresponding risk level.

[0131] Alternatively, the risk event and a preset fitness function may be input into a preset genetic algorithm to determine the most suitable risk event level from the population.

[0132] In addition, when there are multiple risk events occurring in the same area at the same time, the comprehensive risk level of the area can be obtained by considering the weights of different risk events. Therefore, after step S500, step S510 and step S520 are also included.

[0133] Step S510, obtaining risk events corresponding to each area within a preset time period and risk levels corresponding to the risk events;

[0134] Step S520, calculate the risk level of each area, the calculation formula is as follows:

[0135] ;

[0136] is the comprehensive dynamic risk level of region i;

[0137] x1, x2, ..., x n is the risk event level corresponding to risk event 1, risk event 2, ..., risk event n;

[0138] n is the number of risk events within a preset time period in region i.

[0139] f1, f2, ..., f n are x1, x2, ..., x n The corresponding weight.

[0140] There is also a situation that, because for different regions, even if it is the same risk event, the corresponding comprehensive risk level will be different, so it is necessary to modify the risk level of the risk event in combination with the specific region, and the modified risk level is used as the comprehensive risk level of the risk event in the region. Therefore, the step S520 also includes:

[0141] S521, determining the first risk weight of each region according to the pre-established correspondence between the region and the first risk weight;

[0142] S522, determining a second risk weight corresponding to a corresponding time period according to the time period of the risk event within the preset time period;

[0143] S523: Calculate the weights corresponding to the risk events within a preset time period according to the first risk weight and the second risk weight.

[0144] Specifically, the calculation formula is as follows:

[0145] ;

[0146] f i is the first risk weight of region i;

[0147] f j The weight corresponding to the risk events within the preset time period;

[0148] f ij is the weight of region i in the preset time period.

[0149] In other embodiments, after step S500, the method further includes: sending risk warnings to each area according to the risk level of each area.

[0150] like Figure 2 As shown, Figure 2 A schematic diagram of the dynamic risk level assessment device for risk events in various regions of an enterprise provided by the present invention is shown, and the dynamic risk level assessment device for risk events in various regions of an enterprise includes an acquisition unit 610, a calculation unit 620, a determination unit 630, a characterization unit 640, and an output unit 650.

[0151] The acquisition unit 610 is used to acquire risk events in each area in real time.

[0152] It should be understood that there may be one or more risk events in each area. For example, the data obtained at xx:xx on xx / xx / xx that “xx was not wearing a safety helmet when performing hoisting operations in area 1”.

[0153] The calculation unit 620 is used to determine the risk bias degree of each key point in the risk event according to the risk event, and the risk bias degree includes high risk, low risk, and medium risk.

[0154] It should be understood that the key point can be a group of simple phrases, such as "not wearing a safety helmet", or a single word "hoisting". There is no specific limitation here and it can be set as needed.

[0155] The risk bias can be divided into high risk, low risk, and medium risk, and can also be divided into extremely high risk, general high risk, lower risk, general low risk, and medium risk according to needs. The specific division can also be determined based on comprehensive considerations such as assessment accuracy. In other embodiments, it can also be determined based on different risk event scenarios.

[0156] It should be noted that the high-risk set may include {dangerous goods are placed in the wrong position, ...}; similarly, the low-risk set may also include {no helmet is worn, ...}. In addition, in different areas, the corresponding high-risk set, medium-risk set, and low-risk set may be different. For example, for areas and office areas where more dangerous goods are stored in chemical plants, the risks brought by personnel's operating behaviors are very different. Therefore, the high-risk set, medium-risk set, and low-risk set can be determined by region. When calculating the risk bias of risk events occurring in each area, the corresponding high-risk set, medium-risk set, and low-risk set need to be determined.

[0157] The determination unit 630 is used to determine the feature vector corresponding to each key point according to the risk bias degree corresponding to each key point.

[0158] It should be understood that the construction of the feature vector corresponding to the key point can be to use the risk bias of the key point as the corresponding weight to construct the feature vector of the key point. The dimension of the feature vector can be three-dimensional or other multi-dimensional, which can be determined according to the number of risk bias divisions. For example, if the risk bias includes high risk, low risk, and medium risk, the feature vector can be constructed into at least three dimensions.

[0159] The characterization unit 640 is used to determine the feature representation corresponding to the risk event according to the feature vector.

[0160] It should be understood that each risk event is composed of multiple key points, so the feature vectors corresponding to the key points can be combined to form a feature representation corresponding to the risk event.

[0161] The output unit 650 is used to input the feature representation corresponding to the risk event into the trained algorithm model to determine the corresponding risk level.

[0162] Specifically, the feature representation corresponding to the risk event is input into a trained neural network model to determine the corresponding risk level. For example, the feature representation corresponding to the risk event can be input into a trained recurrent neural network model to output the corresponding risk level.

[0163] Alternatively, the risk event and a preset fitness function may be input into a preset genetic algorithm to determine the most suitable risk event level from the population.

[0164] The calculation unit 620 is further used for:

[0165] According to the formula Calculate the correlation of each key point with other key points in the pre-established high-risk set;

[0166] According to the formula Calculate the correlation of each key point with other key points in the pre-established low-risk set;

[0167] According to the formula Calculate the correlation of each key point with other key points in the pre-established medium risk set;

[0168] Among them, n is the number of key points with high risk concentration;

[0169] m is the number of key points in the low-risk concentration;

[0170] k is the number of critical points in the medium risk concentration;

[0171] r(w, v) is the correlation between the two key points w and v;

[0172] G is the high-risk set;

[0173] H is the low risk set;

[0174] N is the medium risk set;

[0175] ;

[0176] k(w) is the probability of key point w appearing in the risk event;

[0177] k(v) is the probability of key point v appearing in the risk event;

[0178] k(w, v) is the probability that key points w and v appear together in a risk event;

[0179] Calculate the risk bias of each key point, the calculation formula is as follows:

[0180] High-risk bias = correlation between the key point and other key points in the high-risk set - correlation between the key point and other key points in the medium-risk set - correlation between the key point and other key points in the low-risk set;

[0181] Low risk bias = correlation between the key point and other key points in the low risk set - correlation between the key point and other key points in the high risk set - correlation between the key point and other key points in the medium risk set;

[0182] Medium risk bias = the correlation between the key point and other key points in the medium risk set - the correlation between the key point and other key points in the high risk set - the correlation between the key point and other key points in the low risk set.

[0183] In order to achieve the above object, the present invention also provides a computer device, such as Figure 3 As shown, the cleaning base station includes at least one processor 701; and a memory 702 that is communicatively connected to the at least one processor 701; wherein the memory 702 stores instructions that can be executed by the at least one processor 701, and the instructions are executed by the at least one processor 701 so that the at least one processor 701 can execute the above-mentioned method for evaluating the dynamic risk level of risk events in various areas of an enterprise based on endoscopic images.

[0184] The memory 702 and the processor 701 are connected in a bus manner, and the bus may include any number of interconnected buses and bridges, and the bus connects various circuits of one or more processors 701 and the memory 702 together. The bus can also connect various other circuits such as peripheral devices, voltage regulators, and power management circuits, which are well known in the art and are therefore not further described herein. The bus interface provides an interface between the bus and the transceiver. The transceiver can be one element or multiple elements, such as multiple receivers and transmitters, providing a unit for communicating with various other devices on a transmission medium. The data processed by the processor 701 is transmitted on a wireless medium via an antenna, and further, the antenna also receives data and transmits the data to the processor 701.

[0185] The processor 701 is responsible for managing the bus and general processing, and can also provide various functions, including timing, peripheral interfaces, voltage regulation, power management and other control functions. The memory 702 can be used to store data used by the processor 701 when performing operations.

[0186] In order to achieve the above-mentioned purpose, the present invention provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the above-mentioned method for evaluating the dynamic risk level of risk events in various regions of an enterprise.

[0187] That is, those skilled in the art can understand that all or part of the steps in the above-mentioned implementation method can be completed by instructing the relevant hardware through a program, and the program is stored in a storage medium, including several instructions to enable a device (which can be a single-chip microcomputer, chip, etc.) or a processor to execute all or part of the steps of the method described in each implementation of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0188] Obviously, the embodiments described above are only some embodiments of the present invention, rather than all embodiments. Based on the embodiments of the present invention, ordinary technicians in this field can make other different forms of changes or modifications without creative work, which should fall within the scope of protection of the present invention.

Claims

1. A method for evaluating the dynamic risk level of risk events in each region of an enterprise, characterized in that: include: Obtain risk events in each region in real time; According to the risk event, determine the risk bias degree of each key point in the risk event, wherein the risk bias degree includes high risk, low risk, and medium risk; Determine the characteristic vector corresponding to each key point according to the risk bias degree corresponding to the key point; Determining, according to the feature vector, a feature representation corresponding to the risk event; Inputting the characteristic representation corresponding to the risk event into the trained algorithm model to determine the corresponding risk level, including inputting the risk event and the preset fitness function into a preset genetic algorithm to determine the most suitable risk event level from the population; Among them, the method for determining the risk bias degree of each key point includes: According to the formula Calculate the correlation of each key point with other key points in the pre-established high-risk set; According to the formula Calculate the correlation of each key point with other key points in the pre-established low-risk set; According to the formula Calculate the correlation of each key point with other key points in the pre-established medium risk set; Among them, n is the number of key points with high risk concentration; m is the number of key points in the low-risk concentration; k is the number of critical points in the medium risk concentration; r(w, v) is the correlation between the two key points w and v; G is the high-risk set; H is the low risk set; N is the medium risk set; ； k(w) is the probability of key point w appearing in the risk event; k(v) is the probability of key point v appearing in the risk event; k(w, v) is the probability that key points w and v appear together in a risk event; Calculate the risk bias of each key point, the calculation formula is as follows: High-risk bias = correlation between the key point and other key points in the high-risk set - correlation between the key point and other key points in the medium-risk set - correlation between the key point and other key points in the low-risk set; Low risk bias = correlation between the key point and other key points in the low risk set - correlation between the key point and other key points in the high risk set - correlation between the key point and other key points in the medium risk set; Medium risk bias = the correlation between the key point and other key points in the medium risk set - the correlation between the key point and other key points in the high risk set - the correlation between the key point and other key points in the low risk set.

2. The method for evaluating the dynamic risk level of risk events in each region of an enterprise according to claim 1, characterized in that: The step of inputting the feature representation corresponding to the risk event into the trained algorithm model to determine the corresponding risk level includes: The feature representation corresponding to the risk event is input into the trained neural network model to determine the corresponding risk level.

3. The method for evaluating the dynamic risk level of risk events in each region of an enterprise according to claim 1, characterized in that: After the step of inputting the feature representation corresponding to the risk event into the trained algorithm model to determine the corresponding risk level, the evaluation method further includes: Obtain risk events within a preset time period corresponding to each area and the risk level corresponding to the risk events; Calculate the risk level of each area using the following formula: ； is the comprehensive dynamic risk level of region i; x1, x2, ..., x n is the risk event level corresponding to risk event 1, risk event 2, ..., risk event n; n is the number of risk events within a preset time period in region i; f1, f2, ..., f n are x1, x2, ..., x n The corresponding weight.

4. The method for evaluating the dynamic risk level of risk events in each region of an enterprise as claimed in claim 3, characterized in that: The step of calculating the risk level of each area also includes: Determine the first risk weight of each region according to the pre-established correspondence between the region and the first risk weight; Determine the second risk weight corresponding to the corresponding time period according to the time period of the risk event within the preset time period; The weights corresponding to the risk events within the preset time period are calculated based on the first risk weight and the second risk weight.

5. The method for evaluating the dynamic risk level of risk events in each region of an enterprise as claimed in claim 4, characterized in that: In calculating the weight corresponding to the risk event within the preset time period according to the first risk weight and the second risk weight, the calculation formula is as follows: ； f i is the first risk weight of region i; f j The weight corresponding to the risk events within the preset time period; f ij is the weight of region i in the preset time period.

6. The method for evaluating the dynamic risk level of risk events in each region of an enterprise as claimed in claim 3, characterized in that: After the step of calculating the risk level of each area, the assessment method further includes: Send risk warnings to each area based on the risk level of each area.

7. A device for evaluating the dynamic risk level of risk events in each area of ​​an enterprise, characterized in that: include: An acquisition unit is used to acquire risk events in each area in real time; A calculation unit, used to determine the risk bias degree of each key point in the risk event according to the risk event, wherein the risk bias degree includes high risk, low risk and medium risk; A determination unit, configured to determine a feature vector corresponding to each key point according to the risk bias degree corresponding to each key point; A characterization unit, used to determine a feature representation corresponding to the risk event according to the feature vector; An output unit, used to input the feature representation corresponding to the risk event into a trained algorithm model to determine the corresponding risk level, including inputting the risk event and a preset fitness function into a preset genetic algorithm to determine the most suitable risk event level from the population; Wherein, the computing unit is further used for: According to the formula Calculate the correlation of each key point with other key points in the pre-established high-risk set; According to the formula Calculate the correlation of each key point with other key points in the pre-established low-risk set; According to the formula Calculate the correlation of each key point with other key points in the pre-established medium risk set; Among them, n is the number of key points with high risk concentration; m is the number of key points in the low-risk concentration; k is the number of critical points in the medium risk concentration; r(w, v) is the correlation between the two key points w and v; G is the high-risk set; H is the low risk set; N is the medium risk set; ； k(w) is the probability of key point w appearing in the risk event; k(v) is the probability of key point v appearing in the risk event; k(w, v) is the probability that key points w and v appear together in a risk event; Calculate the risk bias of each key point, the calculation formula is as follows: High-risk bias = correlation between the key point and other key points in the high-risk set - correlation between the key point and other key points in the medium-risk set - correlation between the key point and other key points in the low-risk set; Low risk bias = correlation between the key point and other key points in the low risk set - correlation between the key point and other key points in the high risk set - correlation between the key point and other key points in the medium risk set; Medium risk bias = the correlation between the key point and other key points in the medium risk set - the correlation between the key point and other key points in the high risk set - the correlation between the key point and other key points in the low risk set.

8. A computer device, characterized in that: include: at least one processor; as well as, a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the method for evaluating the dynamic risk level of risk events in various regions of an enterprise as described in any one of claims 1 to 6.

9. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, it implements the method for evaluating the dynamic risk level of risk events in each area of ​​an enterprise as described in any one of claims 1 to 6.

Images