Enterprise security risk evaluation method, device and equipment and storage medium

Abstract

The invention provides an enterprise security risk evaluation method and device, equipment and a storage medium, and the method comprises the steps: obtaining a risk factor corresponding to each business system; based on historical data, calculating the probability that the risk factor causes an accident as a probability level; extracting accident data meeting the Haihi proportion from the historical data to obtain a first data set, performing data expansion on the first data set to obtain a second data set, and calculating an efficacy coefficient of the severity of the accident consequence caused by the risk factor based on the second data set; and performing product summation based on the probability level and the efficacy coefficient of the corresponding risk factor under the business system to obtain a safety value corresponding to each business system, and calculating an average value of all the safety values to obtain a risk evaluation result. The method is a multi-service system, data of risk factors of the service system is fully covered, and a one-sidedness evaluation result caused by data singleness is avoided; and the efficiency coefficient is calibrated based on the Haihi, so that the safety evaluation is more accurate.

Description

Technical Field

[0001] The present invention relates to the field of security assessment technology, and in particular to an enterprise security risk assessment method, device, equipment and storage medium. Background Art

[0002] Enterprise risk identification and evaluation is the process of identifying, evaluating and managing the risk scores of accidents that may occur during the operation of the enterprise, which helps the enterprise to formulate effective risk management strategies.

[0003] In related technologies, mechanism models are often used to evaluate safety, and accurate mathematical models are established based on the internal mechanisms of objects or production processes. However, when mechanism models are applied to enterprise safety production scenarios for safety risk assessment, for certain safety production scenarios and management processes, it is difficult to use mechanism models to accurately describe their mathematical expressions, or it is difficult to determine certain coefficients in the expressions; in enterprise safety risk assessments, both data and scenarios are relatively simple, resulting in one-sided evaluation results; in addition, when describing the efficacy factors of indicators that cause the severity of accident consequences, they are usually obtained based on inherent human experience, resulting in large deviations in the evaluation results.

[0004] Based on the above analysis of the development status of this technical field, the existing technology lacks a solution that integrates multiple business systems and optimizes the value of the efficiency factor using Heiligen's law. Summary of the invention

[0005] The purpose of the present invention is to provide an enterprise security risk assessment method, device, equipment and storage medium, aiming to solve the above-mentioned problems in the prior art.

[0006] According to a first aspect of an embodiment of the present invention, there is provided a method for evaluating enterprise security risks, comprising:

[0007] Obtain the corresponding risk factors under each business system;

[0008] Based on historical data, the probability of risk factors causing accidents is calculated as the probability level;

[0009] Extracting accident data satisfying the Heinrich ratio from historical data to obtain a first data set, performing data expansion on the first data set to obtain a second data set, and calculating the efficacy coefficient of the severity of accident consequences caused by the risk factor based on the second data set;

[0010] Based on the probability level and efficacy coefficient of the corresponding risk factors in the business system, the products are summed to obtain the safety value corresponding to each business system, and the average value of all safety values ​​is calculated to obtain the risk assessment result.

[0011] According to a second aspect of an embodiment of the present invention, there is provided an enterprise security risk assessment device, comprising:

[0012] Initial establishment module, used to obtain the corresponding risk factors under each business system;

[0013] The probability level calculation module is used to calculate the probability of the risk factor causing an accident as the probability level based on historical data;

[0014] The efficacy coefficient calculation module is used to extract accident data that meets the Heinrich ratio from historical data to obtain a first data set, perform data expansion on the first data set to obtain a second data set, and calculate the efficacy coefficient of the severity of the accident consequences caused by the risk factor based on the second data set;

[0015] The risk assessment module is used to sum the products based on the probability level and efficacy coefficient of the corresponding risk factors in the business system, obtain the safety value corresponding to each business system, and calculate the average value of all safety values ​​to obtain the risk assessment result.

[0016] According to a third aspect of an embodiment of the present invention, there is provided an electronic device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the computer program is executed by the processor, the steps of the enterprise security risk assessment method provided in the first aspect of the present disclosure are implemented.

[0017] According to a fourth aspect of an embodiment of the present invention, a computer-readable storage medium is provided, on which a program for implementing information transmission is stored. When the program is executed by a processor, the steps of the enterprise security risk assessment method provided in the first aspect of the present disclosure are implemented.

[0018] The technical solution provided by the embodiment of the present invention includes the following beneficial effects: integrating multiple business systems, fully covering the data of risk factors of the business systems, and avoiding one-sided evaluation results caused by the singleness of the data; using probability levels and efficacy coefficients to describe the relationship between risk factors and accidents from two perspectives, namely probability and severity, respectively, and being able to accurately express the calculation formula of the safety value; calibrating the efficacy coefficient based on Heinrich to make the safety evaluation more accurate.

[0019] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate one or more embodiments of this specification or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in this specification. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0021] Figure 1 is a flow chart of a method for evaluating enterprise security risks according to an embodiment of the present invention;

[0022] Figure 2 is a schematic diagram of a security risk assessment framework according to an embodiment of the present invention;

[0023] Figure 3 is a schematic diagram of an enterprise security risk assessment device according to an embodiment of the present invention;

[0024] Figure 4 is a schematic diagram of an electronic device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0025] In order to enable those skilled in the art to better understand the technical solutions in one or more embodiments of this specification, the following will be combined with the drawings in one or more embodiments of this specification to clearly and completely describe the technical solutions in one or more embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this specification, not all of the embodiments. Based on one or more embodiments of this specification, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of this document.

[0026] Method Embodiment

[0027] According to an embodiment of the present invention, a method for evaluating enterprise security risks is provided. Figure 1 is a flow chart of the enterprise security risk assessment method according to an embodiment of the present invention. Figure 1 As shown, the enterprise security risk assessment method according to an embodiment of the present invention specifically includes:

[0028] In step S110, the corresponding risk factors of each business system are obtained, including:

[0029] In the embodiment of the present invention, enterprises in different industries are supported to establish their own security business systems. The integration of the business system makes the security risk assessment more applicable, and under each business system, there are risk factors of comprehensive coverage types. The risk factors are various factors in the security risk assessment.

[0030] The business system includes but is not limited to: risk classification management system, hidden danger investigation and treatment system, special operations management system, etc.

[0031] The data source types corresponding to risk factors include annotated source data such as collection, sharing, basic information, alarm, technology, process, management, environment, fire protection, and scenarios. Multiple types of data sources will provide a more comprehensive assessment of the current status of enterprise security risks and avoid one-sided evaluation results due to data uniformity.

[0032] Under each business system, when selecting the corresponding risk factors, the level of sophistication of the business system evaluation is controlled by setting different numbers of risk factors.

[0033] In step S120, based on historical data, the probability of the risk factor causing the accident is calculated as the probability level, which specifically includes:

[0034] There are great differences between different production and operation enterprises, such as industry characteristics, production processes, generation processes, geographical environments, management scales, etc. Therefore, the probability of the same risk factor causing an accident in different enterprises is different. Therefore, it is necessary to recalculate the current risk assessment instead of using the common experience values ​​in the field;

[0035] Collect historical data of the threshold duration before the current evaluation time node. The historical data includes data of all required risk factors, so that the selected historical data conforms to the current status of the enterprise or project. The threshold duration is determined according to actual needs. The historical data includes normal data and accident data. Perform data preprocessing such as data cleaning and data encoding on the historical data.

[0036] There are four types of labels in the historical data: normal, no personal injury, minor personal injury, and serious personal injury. The last three types can be classified as accidents. At this time, we only need to calculate the probability of the risk factor causing the accident, without considering the severity of the accident. Therefore, the problem of calculating the probability level can be regarded as a binary logistic regression problem.

[0037] Correlation analysis is used to calculate the degree of correlation between risk factors and label results, and the degree of correlation is used as the probability level.

[0038] In step S130, accident data satisfying the Heinrich ratio are extracted from the historical data to obtain a first data set, and the first data set is expanded to obtain a second data set. Based on the second data set, the efficacy coefficient of the severity of the accident consequences caused by the risk factor is calculated, specifically including:

[0039] In the same business system, different risk factors may cause different degrees of severity of accidents. To achieve scientific and accurate calculation of safety risks, it is necessary to calculate the efficacy coefficient. Since the efficacy coefficient focuses on the severity after an accident occurs, this step only requires extracting accident data.

[0040] First, the accident data that occurred continuously are extracted from the historical data. The Heinrich's law is expressed as follows: for every 330 accidents that occur during the production process, 300 of them do not cause personal injury, 29 of them cause minor injuries, and 1 of them causes serious injuries. Since the embodiment of the present invention extracts data continuously, the data extracted initially basically meets the Heinrich ratio. If it does not meet the Heinrich ratio, the label can be adjusted.

[0041] Accident data that meets the Heinrich ratio proves that its label is in line with international standards and can correct the value of the efficacy coefficient to a certain extent, avoiding calculation errors caused by inaccurate labels;

[0042] The amount of accident data extracted is a multiple of 330, and the ratio of the extracted accident data labels conforms to the Heinrich ratio. The ratio of the extracted data labels between no personal injury, slight personal injury and serious personal injury is 300:29:1.

[0043] Through the random oversampling method, the amount of accident data corresponding to each type of risk factor under the expanded business system is equal to improve the accuracy of the efficiency coefficient calculation.

[0044] In step S140, the probability level and efficacy coefficient of the corresponding risk factor are multiplied and summed under the business system to obtain the safety value corresponding to each business system, and the average value of all safety values ​​is calculated to obtain the risk assessment result, which specifically includes:

[0045] Use formula 1 to calculate the security value of each business system:

[0046] S(Ki)=D i1 ×P i1 +D i2 ×P i2 +…D in ×P in Formula 1;

[0047] Among them, S(Ki) represents the security value corresponding to the i-th business system, D ij represents the efficacy coefficient of the jth risk factor under the i-th business system, P ij It represents the probability level of the jth risk factor under the ith business system, and n represents the number of risk factors in the current business system.

[0048] Use formula 2 to calculate the risk assessment results:

[0049] R = {S(K1) + S(K2) + ... + S(KN)} / N Formula 2;

[0050] Among them, R represents the risk assessment result, and N represents the number of business systems.

[0051] The method further comprises:

[0052] In step S150, a safety evaluation report is automatically generated based on the safety value and the risk evaluation result, and it is determined in the safety evaluation report whether each risk factor is controllable, wherein whether it is controllable is output through a pre-trained neural network model.

[0053] Output the safety value of each business system and the overall risk assessment results;

[0054] In addition, it can also automatically determine whether the accident caused by the risk factor is controllable. In the enterprise safety risk assessment, about 88% are unsafe human behaviors, which are controllable, 10% are equipment or other physical unsafe conditions, and 2% are unpreventable; in the domino model, if the accident sequence is represented as a causal chain of events, if a certain risk factor is not operated properly at a certain moment, it will cause a series of subsequent problems. Therefore, judging whether the risk factor is controllable can assist the subsequent management of the enterprise.

[0055] Figure 2 is a schematic diagram of a security risk assessment framework according to an embodiment of the present invention. Figure 2 As shown, a complete framework for enterprise security risk assessment is presented, which integrates risk assessment under multiple business systems and uses Heinrich's law to correct the efficacy coefficient.

[0056] To sum up, in response to the existing problems, this invention proposes an enterprise safety risk assessment method that integrates multiple business systems and fully covers the data of business system risk factors to avoid one-sided evaluation results caused by data uniformity; uses probability levels and efficacy coefficients to describe the relationship between risk factors and accidents from two perspectives, namely probability and severity, and can accurately express the calculation formula of safety values; calculates probability levels and efficacy coefficients in real time during the safety assessment process to avoid directly using empirical data in the field, so that the indicators are more in line with the actual situation of the enterprise; calibrates the efficacy coefficient based on Heinrich to make the safety assessment more accurate; automatically outputs a safety assessment report to visualize the results of the safety risk assessment, and can assist enterprises in optimizing related operations of risk factors.

[0057] Device Embodiment

[0058] According to an embodiment of the present invention, a device for evaluating enterprise security risks is provided. Figure 3 is a schematic diagram of an enterprise security risk assessment device according to an embodiment of the present invention. Figure 3 As shown, the enterprise security risk assessment device according to an embodiment of the present invention specifically includes:

[0059] Initial establishment module 30, used to obtain the corresponding risk factors under each business system;

[0060] The probability level calculation module 32 is used to calculate the probability of the risk factor causing the accident as the probability level based on the historical data;

[0061] The efficacy coefficient calculation module 34 is used to extract accident data that meets the Heinrich ratio from historical data to obtain a first data set, perform data expansion on the first data set to obtain a second data set, and calculate the efficacy coefficient of the severity of the accident consequences caused by the risk factor based on the second data set, specifically for:

[0062] The amount of accident data extracted is a multiple of 330, and the ratio of the extracted accident data labels conforms to the Heinrich ratio. The ratio of the extracted data labels between no personal injury, slight personal injury and serious personal injury is 300:29:1.

[0063] Through the random oversampling method, the amount of accident data corresponding to each type of risk factor in the expanded business system is equal.

[0064] The risk assessment module 36 is used to sum the products based on the probability level and efficacy coefficient of the corresponding risk factor in the business system to obtain the safety value corresponding to each business system, and calculate the average value of all safety values ​​to obtain the risk assessment result, which is specifically used for:

[0065] Use formula 1 to calculate the security value of each business system:

[0066] S(Ki)=D i1 ×P i1 +D i2 ×P i2 +…D in ×P in Formula 1;

[0067] Among them, S(Ki) represents the security value corresponding to the i-th business system, D ij represents the efficacy coefficient of the jth risk factor under the i-th business system, P ij It represents the probability level of the jth risk factor under the ith business system, and n represents the number of risk factors in the current business system.

[0068] Use formula 2 to calculate the risk assessment results:

[0069] R = {S(K1) + S(K2) + ... + S(KN)} / N Formula 2;

[0070] Among them, R represents the risk assessment result, and N represents the number of business systems.

[0071] The device further comprises:

[0072] The report output module 38 is used to automatically generate a safety evaluation report based on the safety value and risk evaluation results, and to determine whether each risk factor is controllable in the safety evaluation report, wherein whether it is controllable is output through a pre-trained neural network model.

[0073] To sum up, in response to the existing problems, this invention proposes an enterprise safety risk assessment device that integrates multiple business systems and fully covers the data of business system risk factors to avoid one-sided evaluation results caused by data uniformity; uses probability levels and efficacy coefficients to describe the relationship between risk factors and accidents from two perspectives, namely probability and severity, and can accurately express the calculation formula of safety values; calculates probability levels and efficacy coefficients in real time during the safety assessment process to avoid directly using empirical data in the field, so that the indicators are more in line with the actual situation of the enterprise; calibrates the efficacy coefficient based on Heinrich to make the safety assessment more accurate; automatically outputs a safety assessment report to visualize the results of the safety risk assessment, and can assist enterprises in optimizing related operations of risk factors.

[0074] Electronic device embodiment

[0075] Figure 4 4 is a schematic diagram of an electronic device according to an embodiment of the present invention. The electronic device 400 may include at least one processor 410 and a memory 420. The processor 410 may execute instructions stored in the memory 420. The processor 410 is connected to the memory 420 through a data bus. In addition to the memory 420, the processor 410 may also be connected to an input device 430, an output device 440, and a communication device 450 through a data bus.

[0076] The processor 410 may be any conventional processor, such as a commercially available CPU. The processor may also include a graphics processor (Graphic Process Unit, GPU), a field programmable gate array (Field Programmable Gate Array, FPGA), a system on chip (System on Chip, SOC), an application specific integrated circuit (Application Specific Integrated Circuit, ASIC) or a combination thereof.

[0077] Memory 420 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0078] In the embodiment of the present disclosure, executable instructions are stored in the memory 420, and the processor 410 can read the executable instructions from the memory 420 and execute the instructions to implement all or part of the steps of any enterprise security risk assessment method in the above exemplary embodiments.

[0079] Computer Readable Storage Medium Embodiments

[0080] In addition to the above-mentioned methods and devices, the exemplary embodiments of the present disclosure may also be a computer program product or a computer-readable storage medium storing the computer program product, wherein the computer product includes computer program instructions that can be executed by a processor to implement all or part of the steps described in any of the enterprise security risk assessment methods in the above-mentioned exemplary embodiments.

[0081] The computer program product may be written in any combination of one or more programming languages ​​to write program codes for performing the operations of the embodiments of the present application, including object-oriented programming languages ​​such as Java, C++, etc., and also conventional procedural programming languages ​​such as "C" language or similar programming languages ​​and scripting languages ​​(e.g., Python). The program code may be executed entirely on the user computing device, partially on the user computing device, as an independent software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0082] Computer readable storage media can adopt any combination of one or more readable media. The readable medium can be a readable signal medium or a readable storage medium. The readable storage medium can include, for example, but is not limited to, a system, device or device of electricity, magnetism, light, electromagnetic, infrared, or semiconductor, or any combination of the above. More specific examples of readable storage media include: a static random access memory (SRAM) with one or more wires electrically connected, an electrically erasable programmable read-only memory (EEPROM), an erasable programmable read-only memory (EPROM), a programmable read-only memory (PROM), a read-only memory (ROM), a magnetic memory, a flash memory, a magnetic disk or an optical disk, or any suitable combination of the above.

[0083] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for evaluating enterprise security risks, characterized in that: include: Obtain the corresponding risk factors under each business system; Based on historical data, the probability of the risk factor causing an accident is calculated as a probability level; Extracting accident data satisfying the Heinrich ratio from the historical data to obtain a first data set, performing data expansion on the first data set to obtain a second data set, and calculating the efficacy coefficient of the severity of accident consequences caused by the risk factor based on the second data set; Based on the probability level and efficacy coefficient of the corresponding risk factors in the business system, the products are summed to obtain the safety value corresponding to each business system, and the average value of all safety values ​​is calculated to obtain the risk assessment result.

2. The method according to claim 1, characterized in that The method further comprises: Based on the safety value and the risk assessment result, a safety assessment report is automatically generated, and in the safety assessment report, it is determined whether each risk factor is controllable, wherein whether the risk factor is controllable is output through a pre-trained neural network model.

3. The method according to claim 1, characterized in that The extracting of accident data satisfying the Heinrich ratio from the historical data specifically includes: The amount of accident data extracted is a multiple of 330, and the ratio of the extracted accident data labels conforms to the Heinrich ratio. The ratio of the extracted data labels between no personal injury, slight personal injury and serious personal injury is 300:29:

1.

4. The method according to claim 1, characterized in that: The data expansion of the first data set specifically includes: expanding the data volume of the accident data corresponding to each type of risk factor in the business system to be equal through a random oversampling method.

5. The method according to claim 1, characterized in that The above-mentioned safety values ​​corresponding to each business system are obtained by multiplying and summing the probability level and efficacy coefficient of the corresponding risk factor under the business system, and specifically include: Use formula 1 to calculate the security value of each business system: S(Ki)=D i1 ×P i1 +D i2 ×P i2 +…D in ×P in Formula 1; Among them, S(Ki) represents the security value corresponding to the i-th business system, D ij represents the efficacy coefficient of the jth risk factor under the i-th business system, P ij It represents the probability level of the jth risk factor under the ith business system, and n represents the number of risk factors in the current business system.

6. The method according to claim 5, characterized in that The risk assessment result obtained by calculating the average value of all safety values ​​specifically includes: Use formula 2 to calculate the risk assessment results: R = {S(K1) + S(K2) + ... + S(KN)} / N Formula 2; Among them, R represents the risk assessment result, and N represents the number of business systems.

7. An enterprise safety risk assessment device, characterized in that: include: Initial establishment module, used to obtain the corresponding risk factors under each business system; A probability level calculation module, used to calculate the probability of the risk factor causing an accident as a probability level based on historical data; an efficacy coefficient calculation module, configured to extract accident data satisfying the Heinrich ratio from the historical data to obtain a first data set, perform data expansion on the first data set to obtain a second data set, and calculate an efficacy coefficient of the severity of accident consequences caused by risk factors based on the second data set; The risk assessment module is used to sum the products based on the probability level and efficacy coefficient of the corresponding risk factors in the business system, obtain the safety value corresponding to each business system, and calculate the average value of all safety values ​​to obtain the risk assessment result.

8. The device according to claim 7, characterized in that The device further comprises: A report output module is used to automatically generate a safety evaluation report based on the safety value and the risk evaluation result, and to determine whether each risk factor is controllable in the safety evaluation report, wherein the controllability is output through a pre-trained neural network model.

9. An electronic device, characterized in that: include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program, when executed by the processor, implements the steps of the enterprise security risk assessment method as described in any one of claims 1 to 6.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores an implementation program for information transmission, and when the program is executed by a processor, the steps of the enterprise security risk assessment method according to any one of claims 1 to 6 are implemented.

Images