Chemical safety risk assessment method and related equipment

Abstract

The invention provides a chemical safety risk assessment method and related equipment, and the method comprises the steps: determining a chemical, determining an assessment index of the chemical through employing a preset assessment index, and carrying out the quantification of the assessment index; determining the volatility and conflict of the evaluation index, determining the information amount of the evaluation index according to the volatility and conflict, and determining the weight of the evaluation index according to the information amount; determining a cloud model, a preset early warning level and a corresponding early warning limit, and determining a standard cloud feature value of the early warning level according to the early warning limit; determining a cloud feature value of the evaluation index by using a cloud model; according to the cloud characteristic value and the weight, determining a comprehensive cloud characteristic value of the chemical; and according to the comprehensive cloud characteristic value and the standard cloud characteristic value, determining the close degree of the comprehensive cloud characteristic value and the standard cloud characteristic value, and according to the close degree, determining the early warning level of the chemical.

Description

Technical Field

[0001] The present application relates to the technical field of risk assessment, and particularly to a chemical safety risk assessment method and related equipment. Background Art

[0002] Hazardous chemicals play an important role in social and economic activities and are involved in many industry categories. For the development of industries, hazardous chemicals have played a unique role. Various chemical reagent hazardous chemicals are applied to physical and chemical detection, research experiments, etc., promoting the research and development of technologies. There are many units involved in the management of hazardous chemicals, among which some units have problems such as incomplete information systems, unclear supervision, unclear responsible entities, and non-standardized control.

[0003] At the same time, the unique nature of hazardous chemical safety management is ignored. Without integrating its unique nature, it is difficult to effectively assess the safety risks of hazardous chemicals. At the same time, there are many types of hazardous chemicals with different characteristics, and data integration also needs to be carried out according to the types and characteristics of hazardous chemicals. Summary of the Invention

[0004] In view of this, the purpose of the present application is to propose a chemical safety risk assessment method and related equipment that overcome the above problems or at least partially solve the above problems.

[0005] Based on the above purpose, in the first aspect of the present application, a chemical safety risk assessment method is provided, including:

[0006] Determine a chemical, determine the evaluation index of the chemical using a preset evaluation index, and quantify the evaluation index;

[0007] Determine the volatility and conflict of the evaluation index, determine the amount of information of the evaluation index according to the volatility and the conflict, and determine the weight of the evaluation index according to the amount of information;

[0008] Determine the cloud model, preset warning levels and their corresponding warning boundaries, determine the standard cloud characteristic values of the warning levels according to the warning boundaries, and determine the standard cloud diagrams of each warning level according to the standard cloud characteristic values and the cloud model;

[0009] Use the cloud model to determine the cloud characteristic values of the evaluation index;

[0010] Determine the comprehensive cloud characteristic value of the chemical according to the cloud characteristic value and the weight, and determine the comprehensive cloud diagram of the chemical according to the comprehensive cloud characteristic value and the cloud model;

[0011] Determine the closeness degree between the comprehensive cloud eigenvalue and the standard cloud eigenvalue based on the comprehensive cloud eigenvalue, the standard cloud eigenvalue, the comprehensive cloud map and the standard cloud map, and determine the early warning level of the chemical according to the closeness degree.

[0012] Optionally, the evaluation indicators include positive indicators and reverse indicators;

[0013] Determine the volatility and correlation of the evaluation indicators, determine the amount of information of the evaluation indicators according to the volatility and the correlation, and determine the weight of the evaluation indicators according to the amount of information, including:

[0014] Determine the matrix of the evaluation indicators, and the matrix of the evaluation indicators is expressed as:

[0015]

[0016] Standardize the evaluation indicators to eliminate the influence of dimensions. The positive indicator is expressed as:

[0017]

[0018] The reverse indicator is expressed as:

[0019]

[0020] The volatility is expressed as:

[0021]

[0022] The conflict is expressed as:

[0023] Where

[0024] The amount of information is expressed as:

[0025] C j =S j ×A j ,

[0026] The weight is expressed as:

[0027]

[0028] Where x ij is the j-th evaluation indicator of the i-th chemical in the matrix of evaluation indicators, min(x j ) is the minimum value of the j-th evaluation indicator column, max(x j ) is the maximum value of the j-th evaluation indicator column, the mean of the j-th evaluation indicator column, x ikThe k-th evaluation index of the i-th chemical The mean of the k-th evaluation index column, r ij The correlation coefficient between the i-th evaluation index and the j-th evaluation index, and R represents the correlation matrix of the evaluation indexes

[0029] Optionally, the standard cloud eigenvalue is expressed as:

[0030]

[0031] He s = L

[0032] where Ex s , En s , He s represent the expected value, entropy and hyperentropy of each warning level respectively, L is a constant, x max and x min represent the maximum and minimum values of the warning limits corresponding to each warning level respectively

[0033] Optionally, the cloud model includes a forward cloud generator

[0034] Determine the standard cloud diagram of each warning level according to the standard cloud eigenvalue and the forward cloud generator, including:

[0035] Determine the expected value, entropy and hyperentropy of each warning level by using the standard cloud eigenvalue

[0036] Use the expected value and entropy as the expected value and variance of the first normal distribution, and determine the first random number according to the expected value and variance of the first normal distribution

[0037] Use the entropy and hyperentropy as the expected value and variance of the second normal distribution, and determine the second random number according to the expected value and variance of the second normal distribution

[0038] Determine the membership degree of the first random number according to the first random number and the second random number Form the first cloud droplet by using the first random number and the membership degree of the first random number

[0039] Repeat multiple times to determine the first random number and the membership degree of the first random number, form multiple first cloud droplets, and form the standard cloud diagram by using multiple first cloud droplets

[0040] where, x i represents the first random number, Ex s represents the expected value of each warning level, En s represents the entropy of each warning level, Eni Represents the second random number, He s Represents the hyper entropy of each warning level.

[0041] Optionally, the cloud model includes an inverse cloud generator;

[0042] Determining the cloud eigenvalue of the evaluation index by using the inverse cloud generator includes:

[0043] Calculating the mean value of the evaluation index;

[0044] Calculating the variance of the evaluation index according to the mean value;

[0045] Determining the expected value of the evaluation index according to the mean value, and using the expected value to represent the certainty measure, which is located at the position of the cloud peak in the cloud diagram;

[0046] Determining the entropy of the evaluation index according to the expected value, and using the entropy to represent the uncertainty measure of the expected value;

[0047] Determining the hyper entropy of the evaluation index according to the variance and the entropy, and using the hyper entropy to represent the uncertainty measure of the entropy.

[0048] Optionally, determining the comprehensive cloud eigenvalue of the chemical according to the cloud eigenvalue and the weight, and determining the comprehensive cloud diagram of the chemical according to the comprehensive cloud eigenvalue and the cloud model, includes:

[0049] Determining the digital matrix of the evaluation index according to the cloud eigenvalue;

[0050] Determining the weight matrix of the evaluation index according to the weight;

[0051] Combining the digital matrix and the weight matrix to determine the comprehensive cloud eigenvalue;

[0052] Determining the expected value, entropy and hyper entropy of the chemical by using the comprehensive cloud eigenvalue;

[0053] Using the expected value and the above of the chemical as the expected value and variance of the first normal distribution, and determining the third random number according to the expected value and variance of the first normal distribution

[0054] Using the entropy and hyper entropy of the chemical as the expected value and variance of the second normal distribution, and determining the fourth random number according to the expected value and variance of the second normal distribution

[0055] Determining the membership degree of the third random number according to the third random number and the fourth random number Forming the second cloud droplet by using the third random number and the membership degree of the third random number;

[0056] Determine the third random number and the membership degree of the third random number multiple times to form multiple second cloud droplets, and form the comprehensive cloud map by using the multiple second cloud droplets.

[0057] Optionally, the evaluation indicators include primary indicators, secondary indicators, and tertiary indicators, where any one of the primary indicators includes at least one of the secondary indicators, and any one of the secondary indicators includes at least one of the tertiary indicators;

[0058] The determination of the digital matrix of the evaluation indicators according to the cloud eigenvalues includes:

[0059] Perform normalization according to the number of the tertiary indicators to determine the digital matrix of the secondary indicators;

[0060] Perform normalization according to the number of the secondary indicators to determine the digital matrix of the primary indicators;

[0061] The comprehensive cloud eigenvalue is expressed as:

[0062]

[0063] where Ex 综合云 , En 综合云 , En 综合云 respectively represent the expected value, entropy, and hyperentropy of the comprehensive cloud, Ex i , En i , He i respectively represent the expected value, entropy, and hyperentropy of the i-th primary indicator, and ω i represents the weight of the i-th primary indicator.

[0064] Optionally, the determination of the closeness between the comprehensive cloud eigenvalue and the standard cloud eigenvalue according to the comprehensive cloud eigenvalue and the standard cloud eigenvalue includes:

[0065]

[0066] where Ex 综合云 represents the comprehensive cloud eigenvalue, Ex s represents the standard cloud eigenvalue of each warning level, and T s represents the closeness between the comprehensive cloud eigenvalue and the standard cloud eigenvalue.

[0067] In the second aspect of the present application, a chemical safety risk assessment device is provided, including:

[0068] A determination module, configured to determine a chemical, determine the evaluation indicators of the chemical by using preset evaluation indicators, and quantify the evaluation indicators;

[0069] A weight module, configured to determine the volatility and conflict of the evaluation indicators, determine the amount of information of the evaluation indicators according to the volatility and the conflict, and determine the weight of the evaluation indicators according to the amount of information;

[0070] A standard cloud module, configured to determine a cloud model, a preset warning level and its corresponding warning limit, determine the standard cloud characteristic value of the warning level according to the warning limit, and determine the standard cloud map of each warning level according to the standard cloud characteristic value and the cloud model;

[0071] A cloud module, configured to determine the cloud characteristic value of the evaluation indicator by using the cloud model;

[0072] A comprehensive cloud module, configured to determine the comprehensive cloud characteristic value of the chemical according to the cloud characteristic value and the weight, and determine the comprehensive cloud map of the chemical according to the comprehensive cloud characteristic value and the cloud model;

[0073] A closeness module, configured to determine the closeness between the comprehensive cloud characteristic value and the standard cloud characteristic value according to the comprehensive cloud characteristic value, the standard cloud characteristic value, the comprehensive cloud map and the standard cloud map, and determine the warning level of the chemical according to the closeness.

[0074] In a third aspect of the present application, there is provided an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor, and when the processor executes the program, the method described in the first aspect is implemented.

[0075] As can be seen from the above, the chemical safety risk assessment method and related equipment provided by the present application pre-analyze the safety risk influencing factors of hazardous chemicals, use the type, risk factors and influence parameters of the chemicals as relevant information respectively, and finally form 22 third-level indicators corresponding to five first-level indicators including personnel factors, item factors, environmental factors and task factors, so as to determine the evaluation indicators of the chemicals through the preset evaluation indicators, further determine the weight of the evaluation indicators by using the volatility and conflict of the evaluation indicators, effectively support the research on chemical risk analysis, further use the preset warning level and its corresponding warning limit to determine the standard cloud characteristic value corresponding to different warning levels, use the standard cloud characteristic value to determine the cloud characteristic value corresponding to each evaluation indicator for the research of hazardous chemicals, use the cloud characteristic value to determine the comprehensive cloud characteristic value of the evaluation indicator, and finally determine the warning level corresponding to the evaluation indicator, that is, the warning level of the chemical, through the closeness between the comprehensive cloud characteristic value and the standard cloud characteristic value. The safety risk of the chemical is effectively warned through the corresponding warning level.

[0076] The above description is only an overview of the technical solution of the present invention. In order to better understand the technical means of the present invention, it can be implemented according to the content of the specification. In order to make the above and other objects, features, and advantages of the present invention more obvious and understandable, the specific embodiments of the present invention are given below. Description of the Drawings

[0077] In order to more clearly illustrate the technical solutions in the present application or related technologies, the following will briefly introduce the drawings required for use in the embodiments or related technology descriptions. Obviously, the drawings in the following description are only the embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0078] Figure 1 It is a flowchart of a chemical safety risk assessment method 100 according to an embodiment of the present application;

[0079] Figure 2 It is a schematic diagram of preset evaluation indicators according to an embodiment of the present application;

[0080] Figure 3 It is a flowchart of the reverse cloud generator method according to an embodiment of the present application;

[0081] Figure 4 It is a schematic diagram of a chemical safety risk assessment device according to an embodiment of the present application;

[0082] Figure 5 It is a schematic diagram of an electronic device according to an embodiment of the present application. Detailed Embodiments

[0083] To make the objectives, technical solutions, and advantages of the present application clearer and more understandable, the following further elaborates on the present application in detail with reference to specific embodiments and the accompanying drawings.

[0084] It should be noted that unless otherwise defined, the technical terms or scientific terms used in the embodiments of the present application should have the ordinary meaning understood by those of ordinary skill in the art to which the present application belongs. The "first", "second", and similar terms used in the embodiments of the present application do not indicate any order, quantity, or importance, but are only used to distinguish different components. The terms such as "including" or "comprising" mean that the elements or objects appearing before this word cover the elements or objects listed after this word and their equivalents, without excluding other elements or objects. The terms such as "connected" or "coupled" are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. The terms such as "upper", "lower", "left", and "right" are only used to represent relative positional relationships. When the absolute position of the object being described changes, the relative positional relationship may also change accordingly.

[0085] In the field of safety management of hazardous chemicals, the unique nature of the safety management of hazardous chemicals is ignored, resulting in the corresponding safety risk assessment technology failing to fully adapt to its particularity. Correspondingly, the safety risk assessment is not accurate enough. At the same time, due to the diversity of types and different characteristics of hazardous chemicals, their dispersion makes it difficult to integrate them, making it difficult to comprehensively and deeply address the complex challenges of hazardous chemicals. Also, due to the large variety and different characteristics, the accuracy and reliability in the construction of the index system, pretreatment, and hazard prediction for hazardous chemicals cannot meet the expectations.

[0086] Based on this, the present application proposes a method for safety risk assessment of hazardous chemicals, referring to Figure 1 As shown, it is a flowchart of a method 100 for safety risk assessment of hazardous chemicals provided by an embodiment of the present application. The method starts from step S100, determining the chemical, using a preset evaluation index to determine at least one evaluation index of the chemical, and quantifying the evaluation index.

[0087] In this step, first determine the preset evaluation index. In order to comprehensively construct the index system of hazardous chemicals, relevant information such as the type, risk factors, and influence parameters of hazardous chemicals is used to construct the preset evaluation index of hazardous chemicals.

[0088] In some embodiments, determining the preset evaluation index includes:

[0089] Predetermine the independent variables of hazardous chemicals and group the independent variables, where the independent variables include at least one of type, risk factors, and influence parameters;

[0090] Determine the weight of the independent variables in each group;

[0091] Determine the information value of the independent variables according to the weight;

[0092] In response to the information value being not less than a preset threshold, determine the independent variable corresponding to the information value as the preset evaluation index.

[0093] In the process of constructing the evaluation index, through the WOE (Weight of Evidence) / IV (Information Value) method, first perform WOE (Weight of Evidence) coding on an independent variable (at least one of type, risk factors, and influence parameters), that is, perform grouping processing or discretization processing (equal-width cutting, equal-height cutting, decision tree cutting) on a certain independent variable. After grouping, for the i-th group:

[0094] WOE i =In(bad i / bad T )-In(good i / good T) Formula (1)

[0095] where bad i represents the number of samples with the management form "bad" corresponding to the i-th group of the selected independent variable, and bad T represents the total number of samples with the management form "bad" in the independent variable samples, and good i represents the number of samples with the management form "good" corresponding to the i-th group of the selected independent variable, and good T represents the total number of samples with the management form "good" in the independent variable samples.

[0096] After performing WOE encoding on the selected independent variable, the IV value is calculated. Specifically, the IV value is an index used to judge and evaluate the quality of the management form and the prediction ability. The higher the IV value, the greater the deviation in the distribution of good and bad management forms in this independent variable, that is, the better the ability of this independent variable to distinguish and predict the management form. The IV value of the independent variable is expressed as:

[0097]

[0098] The purpose of the IV value analysis method is mainly to screen the magnitude of the risk prediction ability of each independent variable for hazardous chemicals.

[0099] In some exemplary embodiments, if the IV value is less than 0.02, it is determined that this independent variable has no correlation with the prediction ability;

[0100] If the IV value is greater than or equal to 0.02 and less than 0.1, it is determined that this independent variable has a weak correlation with the prediction ability;

[0101] If the IV value is greater than or equal to 0.1 and less than 0.3, it is determined that this independent variable has a medium correlation with the prediction ability;

[0102] If the IV value is greater than 0.3, it is determined that this independent variable has a strong correlation with the prediction ability.

[0103] In some embodiments, when the IV value is greater than or equal to 0.02, it is determined that this independent variable is a preset evaluation index.

[0104] Furthermore, a comprehensive preset evaluation index is constructed.

[0105] Combined with the screening and analysis of the evaluation index in the above embodiments, the preset evaluation index is determined.

[0106] The evaluation index includes a first index, a second index, and a third index. The first index includes personnel factors, item factors, environmental factors, management factors, and task factors. Specifically, the evaluation index is as Figure 2 shown.

[0107] To facilitate the determination of at least one evaluation index of a chemical using a preset evaluation index, corresponding index descriptions are preset for the preset evaluation index, as shown in Table 1 below.

[0108] Table 1, Preset Evaluation Index and Index Description

[0109]

[0110]

[0111]

[0112]

[0113] In some embodiments, the preset evaluation index and index description obtain and sort out the standards related to chemical management (national standards, industry standards, international standards), construct a set of hazardous chemical standards, and realize the comprehensive management of the standards. To better support the use and management of the standards, uploading, downloading, and querying of the preset evaluation index and index description can be supported.

[0114] After that, the evaluation index is quantified.

[0115] It can be understood that the evaluation index itself is a language description rather than a quantitative numerical expression. To facilitate the subsequent calculation of the weight of the evaluation index, the evaluation index is initially quantified using the index description.

[0116] In some alternative embodiments, the quantification method can be any one of the following:

[0117] (1) Statistical result quantification method

[0118] Statistical result quantification refers to directly giving a digital task result according to the situation after the task is completed, such as quantification indexes like completion rate, number of times, etc.

[0119] (2) Goal achievement situation quantification method

[0120] Goal achievement situation quantification refers to a method of comparing the result after the task is completed with the pre-expected goal to obtain a measurable result of the difference between the goal and the actual situation. The quantification indexes include achievement rate, implementation rate, etc.

[0121] (3) Frequency quantification method

[0122] The frequency quantification method refers to a method of calculating the result according to the frequency of task completion or the frequency of behavioral performance, and it includes quantification indexes such as timeliness, number of errors, number of completions, turnover speed, etc.

[0123] (4) Balance control quantification method

[0124] Balance control quantification is a method of measuring the work value represented by the remaining amount after a task is completed, such as the budget balance control rate.

[0125] (5) Piecewise assignment quantification method

[0126] Piecewise assignment quantification refers to a method of assigning values to intervals for different levels of task achievement or behavior performance, and directly finding the assessment result scores through the corresponding intervals. When using the piecewise assignment quantification method for index quantification, it is necessary to fully consider the rationality and fairness of the piecewise interval setting and its corresponding score interval setting, and combine the actual situation and characteristics. For some difficult-to-quantify assessment items, such as attitude and ability, the piecewise scoring method can also be used to achieve index quantification.

[0127] (6) Forced percentage quantification method

[0128] Forced percentage quantification refers to a method of forcibly ranking different situations in task completion under the confirmation of the excellent and poor ratio. The forced percentage quantification method is one of the important methods for qualitative index quantification.

[0129] (7) Behaviorally anchored quantification method

[0130] Behaviorally anchored quantification refers to a method of measuring different behaviors in task completion with different level scales, giving the result scores of qualitative things through behavior scales, intuitively reflecting the behavior gaps between departments / employees, and obtaining learning benchmarks through comparison.

[0131] (8) Key behavior quantification method

[0132] Key behavior quantification refers to a method of giving scores from the key actions that directly bring results, giving the result scores of qualitative things by finding the root causes of things, and attaching importance to the significance of details for the success or failure of tasks.

[0133] (9) Time dimension quantification method

[0134] Index quantification can be achieved from the time dimension (i.e., timeliness), such as assessment indicators like completion time, approval time, start time, earliest start time, earliest end time, latest end time, number of days of the deadline, progress, cycle, etc. One of the time quantification methods is progress quantification, which refers to a method of measuring the development of the situation (time stage) during the task completion process, and giving the result scores by calculating the causal relationship between specific time and behavior.

[0135] (10) Result dimension quantification method

[0136] The result quantification method refers to analyzing the purpose of a certain assessment indicator, understanding the ultimate expected result of achieving this assessment indicator, obtaining the sub - quantified assessment indicators of the result performance, so as to quantify the assessment indicator.

[0137] (11) Action dimension quantification method

[0138] The action quantification method refers to a method that starts from analyzing the completion of a certain result, clarifies the actions to be taken, and sets assessment indicators for the actions to be taken for each requirement.

[0139] (12) "Fishbone diagram + Balanced Scorecard" analysis method

[0140] The fishbone diagram can be used to find strategic goals and determine key success factors. According to the key factors, the overall KPI is determined and decomposed to lower - level units until grass - roots units, forming a causal relationship network to support the realization of strategic goals. When using the fishbone diagram for index analysis and quantification, the Balanced Scorecard principle can be combined. The main causes of the indicators are divided into management - type, safety - type, etc. On this basis, secondary causes are determined, and the indicators are decomposed step by step until the indicators are refined and quantified.

[0141] For the above - mentioned preliminary quantification methods, initial scoring and assignment are carried out according to the index description, so as to carry out corresponding quantification.

[0142] After that, in step S102, the volatility and conflict of the evaluation indicators are determined. According to the volatility and conflict, the amount of information of the evaluation indicators is determined, and the weight of the evaluation indicators is determined according to the amount of information.

[0143] In this step, when determining the weight of an indicator, usually the data itself is concerned. However, the magnitude of the volatility between data is also a kind of information, and the magnitude of the correlation between data is also a kind of information. The weight is calculated using the magnitude of data volatility and the magnitude of data correlation.

[0144] In the embodiment of the present application, the CRITIC weight method is an objective weight - assignment method based on data volatility. Its idea lies in two indicators, namely, the volatility (contrast intensity) and conflict (correlation) indicators. The contrast intensity is represented by the standard deviation. The larger the standard deviation, the greater the volatility and the higher the weight. The conflict is represented by the correlation coefficient. The larger the correlation coefficient value, the lower the conflict and the lower the weight. The contrast intensity and the conflict indicator are multiplied and normalized to finally obtain the weight of the evaluation indicator.

[0145] In some embodiments, the evaluation indicators include positive indicators and reverse indicators.

[0146] Specifically, S103 includes: determining the matrix of the evaluation indicators, expressed as:

[0147]

[0148] Standardize the evaluation indicators to eliminate the influence of dimensions. The positive indicators are expressed as:

[0149]

[0150] The negative indicators are expressed as:

[0151]

[0152] The volatility is expressed as:

[0153]

[0154] The correlation matrix of the evaluation indicators is expressed as:

[0155]

[0156] The conflict is expressed as:

[0157]

[0158] The amount of information is expressed as:

[0159] C j = S j × a j Formula (9)

[0160] The weight is expressed as:

[0161]

[0162] Where x ij is the jth evaluation indicator of the ith chemical in the matrix of evaluation indicators, min(x j ) is the minimum value of the jth evaluation indicator column, max(x j ) is the maximum value of the jth evaluation indicator column, is the mean value of the jth evaluation indicator column, x ik is the kth evaluation indicator of the ith chemical, is the mean value of the kth evaluation indicator column, r ij is the correlation coefficient between the ith evaluation indicator and the jth evaluation indicator, and R represents the correlation matrix of the evaluation indicators.

[0163] Then in step S103, determine the cloud model, the preset warning levels and their corresponding warning boundaries, determine the standard cloud characteristic values of the warning levels according to the warning boundaries, and determine the standard cloud diagrams of each warning level according to the standard cloud characteristic values and the cloud model.

[0164] In this step, the cloud model is a conversion model between qualitative language descriptions and quantitative expressions. It can convert qualitative language descriptions into quantitative mathematical expressions and vice versa. For evaluation indicators such as the type of chemical, which is a qualitative language description rather than a quantitative expression, the conversion facilitates the risk assessment of chemicals.

[0165] Determine that U is a quantitative universe represented by precision values;

[0166] Determine that C is a fuzzy qualitative concept on the quantitative universe;

[0167] If x→μ(x), where μ(x) ∈ [0, 1], then the distribution of the random number x in the universe U is called a cloud, and (x, μ(x)) is called a cloud droplet. The mathematical characteristics of the cloud model are represented by the expected value E x , entropy E n , hyperentropy H e . The expected value E x is the point that best represents the quantitative expression and is reflected as the position of the cloud peak in the cloud diagram; the entropy E n is the uncertainty measure of the expected value E x , representing the range of values in the universe U that can be accepted by the quantitative expression, reflecting the randomness and fuzziness of the quantitative expression, and is represented by the width of the cloud in the cloud diagram; the hyperentropy H e is the uncertainty measure of the entropy E n , reflecting the dispersion degree of the cloud droplets, representing the randomness of the appearance of the cloud droplets, and is represented by the thickness of the cloud in the cloud diagram.

[0168] For the safety risk assessment of chemicals, warning levels and warning limits are pre-constructed. The warning levels and warning limits are corresponding as shown in Table 2 below:

[0169] Table 2 Warning Level Table

[0170]

[0171] Warning level Warning threshold Warning degree Meaning Level I (8,10] Severe warning An accident may occur at any time Level II (6,8] Serious warning An accident is likely to occur Level III (4,6] Medium warning The possibility of an accident occurring is average Level IV (2,4] Light warning The possibility of an accident occurring is small Level V [0,2] No warning In a safe state, the risk can be ignored

[0172] According to the warning levels, their corresponding warning limits, and the preset cloud model, determine the standard cloud model, which is expressed as:

[0173]

[0174]

[0175] He s = L, Formula (19)

[0176] where Ex s , Ens , He s respectively represent the expected value, entropy, and hyper-entropy of each warning level, L is a constant, and x max and x min respectively represent the maximum and minimum values of the warning boundaries corresponding to each warning level.

[0177] Here, one or more of the expected value, entropy, and hyper-entropy of each warning level can be used to represent the standard cloud eigenvalue.

[0178] It should be noted that whether it is the standard cloud eigenvalue, the subsequent cloud eigenvalue, or the comprehensive cloud eigenvalue, one or more of their corresponding expected value, entropy, and hyper-entropy can be used to represent them.

[0179] Taking Table 2 as an example, the 5 preset warning levels each have corresponding warning boundaries, that is, each warning level has corresponding standard cloud eigenvalues, namely the expected value, entropy, and hyper-entropy.

[0180] According to the standard cloud eigenvalue and the cloud model, determine the standard cloud diagram of each warning level, including:

[0181] In some embodiments, the cloud model includes a forward cloud generator and a backward cloud generator. The forward cloud generator (FCG) is a process from qualitative language description to quantitative mathematical expression, and the backward cloud generator (BCG) is a process from quantitative mathematical expression to qualitative language description.

[0182] Specifically, use the standard cloud eigenvalue and the forward cloud model to determine the standard cloud diagram of each warning level, including:

[0183] Use the standard cloud eigenvalue to determine the expected value, entropy, and hyper-entropy of each warning level;

[0184] Use the expected value and entropy as the expected value and variance of the first normal distribution, and determine the first random number according to the expected value and variance of the first normal distribution

[0185] Use the entropy and hyper-entropy as the expected value and variance of the second normal distribution, and determine the second random number according to the expected value and variance of the second normal distribution

[0186] According to the first random number and the second random number, determine the membership degree of the first random number Use the first random number and the membership degree of the first random number to form the first cloud droplet;

[0187] Repeat multiple times to determine the first random number and the membership degree of the first random number, form multiple first cloud droplets, and use the multiple first cloud droplets to form the standard cloud diagram;

[0188] where, xi Denote the first random number, Ex s Denote the expected value of each warning level, En s Denote the entropy of each warning level, E ni Denote the second random number, He s Denote the hyperentropy of each warning level.

[0189] Exemplarily, as shown in Table 2, the preset warning levels are 5. Correspondingly, each warning level corresponds to a standard cloud map, and the generated standard cloud map follows a normal distribution, where the peaks of the standard cloud map respectively correspond to the expected values of each warning level.

[0190] Then in step S104, use the cloud model to determine the cloud characteristic value of the evaluation index.

[0191] Refer to Figure 3 shown. Specifically, use the inverse cloud generator to determine the cloud characteristic value of the evaluation index, including:

[0192] S301. Calculate the mean values of the evaluation indexes x1, x2…, x n of.

[0193] The mean value of the preset evaluation index is expressed as:

[0194]

[0195] S302. Calculate the variance of the evaluation index according to the mean value;

[0196] The variance of the evaluation index is expressed as:

[0197]

[0198] S303. Determine the expected value of the evaluation index according to the mean value, and use the expected value to represent the certainty measure;

[0199] The expected value is expressed as:

[0200]

[0201] S304. Determine the entropy of the evaluation index according to the expected value, and use the entropy to represent the uncertainty measure of the expected value;

[0202] The entropy is expressed as:

[0203]

[0204] S305. Determine the hyperentropy of the evaluation index according to the variance and the entropy, and use the hyperentropy to represent the uncertainty measure of the entropy.

[0205] The hyperentropy is expressed as:

[0206]

[0207] In the cloud model, the cloud characteristic values of 22 third-level indicators in the evaluation index are respectively obtained by using the inverse cloud generators shown in formulas (11) to (15).

[0208] After that, in step S105, according to the cloud characteristic values and weights, the comprehensive cloud characteristic value of the chemical is determined, and the comprehensive cloud map of the chemical is determined according to the comprehensive cloud characteristic value and the cloud model.

[0209] In this step, the comprehensive cloud aggregates two or more similar sub-clouds within the same universe of discourse to generate a parent cloud with a higher concept level and broader meaning.

[0210] Specifically, step S105 includes:

[0211] Determine the digital matrix of the evaluation index according to the cloud characteristic values;

[0212] Determine the weight matrix of the evaluation index according to the weights;

[0213] Synthesize the digital matrix and the weight matrix to determine the comprehensive cloud characteristic value;

[0214] Use the comprehensive cloud characteristic value to determine the expected value, entropy, and hyperentropy of the chemical;

[0215] Use the expected value and upper of the chemical as the expected value and variance of the first normal distribution, and determine the third random number according to the expected value and variance of the first normal distribution

[0216] Use the entropy and hyperentropy of the chemical as the expected value and variance of the second normal distribution, and determine the fourth random number according to the expected value and variance of the second normal distribution

[0217] Determine the membership degree of the third random number according to the third random number and the fourth random number Use the third random number and the membership degree of the third random number to form the second cloud droplet;

[0218] Repeat multiple times to determine the third random number and the membership degree of the third random number, form multiple second cloud droplets, and use the multiple second cloud droplets to form the comprehensive cloud map.

[0219] Similarly, the generated comprehensive cloud map follows a normal distribution, where the peaks of the comprehensive cloud map respectively correspond to the expected value of the comprehensive cloud, that is, the expected value corresponding to the chemical.

[0220] In some embodiments, determining the digital matrix of the evaluation index according to the cloud characteristic values includes:

[0221] Perform normalization processing according to the number of third-level indicators to determine the digital matrix of the second-level indicator;

[0222] According to the number of secondary indicators, perform normalization processing to determine the digital matrix of the primary indicators;

[0223] The comprehensive cloud eigenvalue is expressed as:

[0224]

[0225] Among them, Ex 综合云 , En 综合云 , En 综合云 respectively represent the expected value, entropy, and hyperentropy of the comprehensive cloud. Ex i , En i , He i respectively represent the expected value, entropy, and hyperentropy of the i-th primary indicator, and ω i represents the weight of the i-th primary indicator.

[0226] By normalizing the tertiary indicators into the digital matrix of the secondary indicators and normalizing the secondary indicators into the digital matrix of the primary indicators, the calculation quantity of the digital matrix is reduced.

[0227] After that, in step S106, according to the comprehensive cloud eigenvalue, the standard cloud eigenvalue, and the comprehensive cloud map and the standard cloud map, determine the closeness between the comprehensive cloud eigenvalue and the standard cloud eigenvalue, and determine the warning level of the chemical according to the closeness.

[0228] In this step, considering that the safety risk assessment conclusion cannot be accurately determined only from the cloud map of the comprehensive cloud, the calculation method of the closeness between the comprehensive cloud and the standard cloud is adopted. The greater the closeness, the closer the comprehensive cloud is to the standard cloud eigenvalue corresponding to this level, and the one with the maximum closeness is the final warning level.

[0229] The closeness is expressed as:

[0230]

[0231] Among them, Ex 综合云 represents the comprehensive cloud eigenvalue, Ex s represents the standard cloud eigenvalue of each warning level, and T s represents the closeness between the comprehensive cloud eigenvalue and the standard cloud eigenvalue.

[0232] It can be understood that when there are 5 preset warning levels, there are correspondingly 5 standard cloud eigenvalues. Through the above formula (20), 5 closeness values can be obtained. Here, the value with the maximum closeness indicates that the comprehensive cloud eigenvalue is closer to the warning level corresponding to this standard cloud eigenvalue, and the warning level of the chemical is this warning level. For example, under the standard cloud eigenvalue corresponding to level III in Table 2, the obtained closeness T sIf it is the largest, the early warning level of the chemical is level III.

[0233] Here, the expected value of the comprehensive cloud and the expected value of the standard cloud are respectively used as the comprehensive cloud eigenvalue and the standard cloud eigenvalue for the calculation of the fitting degree. At the same time, the standard cloud map and the comprehensive cloud map can be used for intuitive comparison. The peak of the standard cloud map represents the expected value corresponding to each early warning level, and the peak of the comprehensive cloud map represents the expected value corresponding to the chemical. By comparing which peak of the comprehensive cloud map is closer to the peak of the standard cloud map, it indicates a higher degree of closeness, and the corresponding early warning level of the chemical is also determined.

[0234] The chemical safety risk assessment method provided by the embodiments of the present application pre-analyzes the safety risk influencing factors of hazardous chemicals, uses the type, risk factors and influence parameters of the chemicals as relevant information respectively, and finally forms 22 third-level indicators corresponding to five first-level indicators including personnel factors, item factors, environmental factors and task factors, so as to determine the evaluation indicators of the chemicals through the preset evaluation indicators, further determine the weights of the evaluation indicators by using the volatility and conflict of the evaluation indicators, effectively support the research on chemical risk analysis, further use the preset cloud model for the research of hazardous chemicals, use the cloud model to determine the comprehensive cloud eigenvalue of the evaluation indicators, and at the same time use the preset early warning level and the preset cloud model to determine the standard cloud eigenvalue corresponding to different early warning levels. Finally, through the closeness between the comprehensive cloud eigenvalue and the standard cloud eigenvalue, the early warning level corresponding to the evaluation indicator, that is, the early warning level of the chemical, is determined. The safety risk of the chemical is effectively warned through the corresponding early warning level.

[0235] It should be noted that the method of the embodiments of the present application can be executed by a single device, such as a computer or a server. The method of this embodiment can also be applied to a distributed scenario and completed by multiple devices cooperating with each other. In this case of a distributed scenario, one of the multiple devices can only execute one or more steps in the method of the embodiments of the present application, and these multiple devices will interact with each other to complete the described method.

[0236] It should be noted that some embodiments of the present application have been described above. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims can be executed in a different order from that in the above embodiments and still achieve the desired results. Additionally, the processes depicted in the figures do not necessarily require the particular order or sequential order shown to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0237] Based on the same inventive concept, corresponding to the method of any of the above embodiments, the present application also provides a chemical safety risk assessment device.

[0238] Reference Figure 4 , the chemical safety risk assessment device includes:

[0239] A determination module 501, configured to determine a chemical, determine the evaluation index of the chemical by using a preset evaluation index, and quantify the evaluation index;

[0240] A weight module 502, configured to determine the volatility and conflict of the evaluation index, determine the amount of information of the evaluation index according to the volatility and the conflict, and determine the weight of the evaluation index according to the amount of information;

[0241] A standard cloud module 503, configured to determine a cloud model, a preset warning level and its corresponding warning limit, determine the standard cloud characteristic value of the warning level according to the warning limit, and determine the standard cloud map of each warning level according to the standard cloud characteristic value and the cloud model;

[0242] A cloud module 504, configured to determine the cloud characteristic value of the evaluation index by using the cloud model;

[0243] A comprehensive cloud module 505, configured to determine the comprehensive cloud characteristic value of the chemical according to the cloud characteristic value and the weight, and determine the comprehensive cloud map of the chemical according to the comprehensive cloud characteristic value and the cloud model;

[0244] A closeness module 506, configured to determine the closeness between the comprehensive cloud characteristic value and the standard cloud characteristic value according to the comprehensive cloud characteristic value, the standard cloud characteristic value, and the comprehensive cloud map and the standard cloud map, and determine the warning level of the chemical according to the closeness.

[0245] For the convenience of description, the above device is described by dividing it into various modules according to functions. Of course, when implementing the present application, the functions of each module can be implemented in the same or multiple software and / or hardware.

[0246] The device in the above embodiment is used to implement the corresponding chemical safety risk assessment method in any of the foregoing embodiments, and has the beneficial effects of the corresponding method embodiments, which will not be elaborated here.

[0247] Based on the same technical concept, corresponding to the method in any of the above embodiments, the present application further provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor, and the processor implements the chemical safety risk assessment method described in any of the above embodiments when executing the program.

[0248] Figure 5FIG. 0 shows a more specific schematic diagram of the hardware structure of the electronic device provided in this embodiment. The device may include: a processor 1010, a memory 1020, an input / output interface 1030, a communication interface 1040, and a bus 1050. Among them, the processor 1010, the memory 1020, the input / output interface 1030, and the communication interface 1040 are communicatively connected to each other inside the device through the bus 1050.

[0249] The processor 1010 may be implemented in a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, etc., and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this specification.

[0250] The memory 1020 may be implemented in the form of a ROM (Read Only Memory), a RAM (Random Access Memory), a static storage device, a dynamic storage device, etc. The memory 1020 may store an operating system and other application programs. When implementing the technical solutions provided in the embodiments of this specification through software or firmware, the relevant program codes are stored in the memory 1020 and are called and executed by the processor 1010.

[0251] The input / output interface 1030 is used to connect to an input / output module to implement information input and output. The input / output module may be configured as a component in the device (not shown in the figure) or externally connected to the device to provide corresponding functions. Among them, the input device may include a keyboard, a mouse, a touch screen, a microphone, various sensors, etc., and the output device may include a display, a speaker, a vibrator, an indicator light, etc.

[0252] The communication interface 1040 is used to connect to a communication module (not shown in the figure) to implement communication interaction between this device and other devices. Among them, the communication module may implement communication in a wired manner (such as USB, network cable, etc.) or in a wireless manner (such as mobile network, WIFI, Bluetooth, etc.).

[0253] The bus 1050 includes a path for transmitting information between various components of the device (such as the processor 1010, the memory 1020, the input / output interface 1030, and the communication interface 1040).

[0254] It should be noted that although the above device only shows the processor 1010, the memory 1020, the input / output interface 1030, the communication interface 1040, and the bus 1050, in the specific implementation process, the device may also include other components necessary for normal operation. In addition, those skilled in the art can understand that the above device may also only include the components necessary to implement the solution of the embodiments of this specification, and does not necessarily include all the components shown in the figure.

[0255] The electronic device of the above embodiment is used to implement the corresponding chemical safety risk assessment method in any of the foregoing embodiments, and has the beneficial effects of the corresponding method embodiments, which will not be elaborated here.

[0256] Based on the same technical concept, corresponding to the method of any of the above embodiments, the present application also provides a non-transitory computer-readable storage medium, and the non-transitory computer-readable storage medium stores computer instructions, and the computer instructions are used to cause the computer to execute the chemical safety risk assessment method described in any of the foregoing embodiments.

[0257] The computer-readable medium of this embodiment includes permanent and non-permanent, removable and non-removable media, and information storage can be implemented by any method or technology. The information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassette tapes, magnetic tapes, magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device.

[0258] The computer instructions stored in the storage medium of the above embodiment are used to cause the computer to execute the chemical safety risk assessment method described in any of the foregoing embodiments, and have the beneficial effects of the corresponding method embodiments, which will not be elaborated here.

[0259] Based on the same inventive concept, corresponding to the chemical safety risk assessment method described in any of the above embodiments, the present disclosure also provides a computer program product, which includes computer program instructions. In some embodiments, the computer program instructions can be executed by one or more processors of a computer to cause the computer and / or the processor to execute the chemical safety risk assessment method. Corresponding to the execution entities corresponding to the steps in each embodiment of the chemical safety risk assessment method, the processor executing the corresponding steps can belong to the corresponding execution entity.

[0260] The computer program product of the above embodiment is used to cause the computer and / or the processor to execute the chemical safety risk assessment method described in any of the above embodiments, and has the beneficial effects of the corresponding method embodiments, which will not be elaborated here.

[0261] Those of ordinary skill in the art should understand that: The discussion of any of the above embodiments is only exemplary and is not intended to imply that the scope of the present application (including the claims) is limited to these examples; Under the idea of the present application, the technical features in the above embodiments or different embodiments can also be combined, the steps can be implemented in any order, and there are many other variations in different aspects of the embodiments of the present application as described above, and they are not provided in detail for the sake of brevity.

[0262] In addition, for simplicity of explanation and discussion, and in order not to make the embodiments of the present application difficult to understand, the well-known power / ground connections to integrated circuit (IC) chips and other components may or may not be shown in the provided drawings. In addition, the device may be shown in block diagram form in order to avoid making the embodiments of the present application difficult to understand, and this also takes into account the fact that the details of the implementation of these block diagram devices are highly dependent on the platform on which the embodiments of the present application will be implemented (that is, these details should be fully within the understanding of those skilled in the art). In the case where specific details (such as circuits) are set forth to describe the exemplary embodiments of the present application, it will be apparent to those skilled in the art that the embodiments of the present application can be implemented without these specific details or with variations of these specific details. Therefore, these descriptions should be considered illustrative rather than restrictive.

[0263] Although the present application has been described in conjunction with specific embodiments of the present application, many alternatives, modifications, and variations of these embodiments will be apparent to those of ordinary skill in the art based on the foregoing description. For example, other memory architectures (such as dynamic RAM (DRAM)) can be used with the embodiments discussed.

[0264] Embodiments of the present application are intended to cover all such substitutions, modifications, and variations that fall within the broad scope of the appended claims. Therefore, any omissions, modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the embodiments of the present application shall be included within the protection scope of the present application.

Claims

1. A chemical safety risk assessment method, characterized in that Including: Determine chemicals, determine the evaluation indicators of the chemicals using preset evaluation indicators, and quantify the evaluation indicators; Determine the volatility and conflict of the evaluation indicators, determine the amount of information of the evaluation indicators according to the volatility and the conflict, and determine the weight of the evaluation indicators according to the amount of information; Determine the cloud model, the preset warning levels and their corresponding warning boundaries, determine the standard cloud characteristic values of the warning levels according to the warning boundaries, and determine the standard cloud diagrams of each warning level according to the standard cloud characteristic values and the cloud model; Use the cloud model to determine the cloud characteristic values of the evaluation indicators; Determine the comprehensive cloud characteristic values of the chemicals according to the cloud characteristic values and the weights, and determine the comprehensive cloud diagrams of the chemicals according to the comprehensive cloud characteristic values and the cloud model; Determine the closeness between the comprehensive cloud characteristic values and the standard cloud characteristic values according to the comprehensive cloud characteristic values, the standard cloud characteristic values, the comprehensive cloud diagrams and the standard cloud diagrams, and determine the warning level of the chemicals according to the closeness; 2. The method according to claim 1, wherein The evaluation indicators include positive indicators and negative indicators; Determine the volatility and correlation of the evaluation indicators, determine the amount of information of the evaluation indicators according to the volatility and the correlation, and determine the weight of the evaluation indicators according to the amount of information, including: Determine the matrix of the evaluation indicators, and the matrix of the evaluation indicators is expressed as: Standardize the evaluation indicators to eliminate the influence of dimensions, and the positive indicator is expressed as: The negative indicator is expressed as: The volatility is expressed as: The conflict is expressed as: Among them The amount of information is expressed as: C j = S j × A j , The weight is expressed as: where x ij is the j-th evaluation index of the i-th chemical in the matrix of evaluation indices, min(x j ) is the minimum value of the j-th evaluation index column, max(x j ) is the maximum value of the j-th evaluation index column, is the mean value of the j-th evaluation index column, x ik is the k-th evaluation index of the i-th chemical, is the mean value of the k-th evaluation index column, r ij is the correlation coefficient between the i-th evaluation index and the j-th evaluation index, and R represents the correlation matrix of evaluation indices.

3. The method according to claim 1, wherein The standard cloud characteristic value is expressed as: He s = L, Among them, Ex s , En s , He s represent the expected value, entropy, and hyperentropy of each early warning level respectively. L is a constant, x max and x min represent the maximum and minimum values of the early warning thresholds corresponding to each early warning level respectively.

4. The method according to claim 3, characterized in that, The cloud model includes a forward cloud generator; Determine the standard cloud diagrams of each warning level according to the standard cloud characteristic values and the forward cloud generator, including: Use the standard cloud characteristic values to determine the expected value, entropy and hyperentropy of each warning level; Using the expected value and entropy as the expected value and variance of a first normal distribution, a first random number is determined according to the expected value and variance of the first normal distribution Using the entropy and hyperentropy as the expected value and variance of a second normal distribution, a second random number is determined according to the expected value and variance of the second normal distribution Determine the membership degree of the first random number according to the first random number and the second random number Form a first cloud droplet by using the first random number and the membership degree of the first random number Determine the first random number and the membership degree of the first random number multiple times to form multiple first cloud droplets, and form the standard cloud diagram using the multiple first cloud droplets; Among them, x i represents the first random number, Ex s represents the expected value of each warning level, En s represents the entropy of each warning level, E ni represents the second random number, He s represents the hyper-entropy of each warning level.

5. The method according to claim 4, characterized in that, The cloud model includes a reverse cloud generator; Use the reverse cloud generator to determine the cloud characteristic values of the evaluation indicators, including: Calculate the mean value of the evaluation indicators; Calculate the variance of the evaluation indicators according to the mean value; Determine the expected value of the evaluation indicators according to the mean value, and use the expected value to represent the certainty measure; Determine the entropy of the evaluation indicators according to the expected value, and use the entropy to represent the uncertainty measure of the expected value; Determine the hyperentropy of the evaluation indicators according to the variance and the entropy, and use the hyperentropy to represent the uncertainty measure of the entropy; 6. The method according to claim 1, wherein Determine the comprehensive cloud characteristic values of the chemicals according to the cloud characteristic values and the weights, and determine the comprehensive cloud diagrams of the chemicals according to the comprehensive cloud characteristic values and the cloud model, including: Determine the digital matrix of the evaluation indicators according to the cloud characteristic values; Determine the weight matrix of the evaluation indicators according to the weights; Synthesize the digital matrix and the weight matrix to determine the comprehensive cloud characteristic values; Determine the expected value, entropy, and hyper-entropy of the chemical using the comprehensive cloud eigenvalue; Using the expected value of the chemical and the upper value as the expected value and variance of the first normal distribution, determine a third random number based on the expected value and variance of the first normal distribution Using the entropy and super-entropy of the chemical as the expected value and variance of the second normal distribution, determining a fourth random number according to the expected value and variance of the second normal distribution Determine the membership degree of the third random number according to the third random number and the fourth random number Form a second cloud droplet by using the third random number and the membership degree of the third random number Determine the third random number and its membership degree multiple times to form multiple second cloud droplets, and use the multiple second cloud droplets to form the comprehensive cloud diagram.

7. The method according to claim 6, wherein The evaluation indicators include primary indicators, secondary indicators, and tertiary indicators, where any one of the primary indicators includes at least one of the secondary indicators, and any one of the secondary indicators includes at least one of the tertiary indicators; The determination of the digital matrix of the evaluation indicators according to the cloud eigenvalue includes: Perform normalization processing according to the number of the tertiary indicators to determine the digital matrix of the secondary indicators; Perform normalization processing according to the number of the secondary indicators to determine the digital matrix of the primary indicators; The comprehensive cloud eigenvalue is expressed as: Among them, Ex 综合云 , En 综合云 , En 综合云 respectively represent the expected value, entropy, and hyper-entropy of the comprehensive cloud. Ex i , En i , He i respectively represent the expected value, entropy, and hyper-entropy of the i-th first-level index, and ω i represents the weight of the i-th first-level index.

8. The method according to claim 1, characterized in that The determination of the closeness between the comprehensive cloud eigenvalue and the standard cloud eigenvalue according to the comprehensive cloud eigenvalue and the standard cloud eigenvalue includes: Among them, Ex 综合云 represents the comprehensive cloud eigenvalue, Ex s represents the standard cloud eigenvalue for each warning level, and T s represents the closeness between the comprehensive cloud eigenvalue and the standard cloud eigenvalue.

9. A chemical safety risk assessment device, characterized in that, Includes: A determination module for determining a chemical, determining the evaluation indicators of the chemical using a preset evaluation indicator, and quantifying the evaluation indicators; A weight module for determining the volatility and conflict of the evaluation indicators, determining the amount of information of the evaluation indicators according to the volatility and the conflict, and determining the weight of the evaluation indicators according to the amount of information; A standard cloud module for determining a cloud model, a preset warning level and its corresponding warning limit, determining the standard cloud eigenvalue of the warning level according to the warning limit, and determining the standard cloud diagram of each warning level according to the standard cloud eigenvalue and the cloud model; A cloud module for determining the cloud eigenvalue of the evaluation indicator using the cloud model; A comprehensive cloud module for determining the comprehensive cloud eigenvalue of the chemical according to the cloud eigenvalue and the weight, and determining the comprehensive cloud diagram of the chemical according to the comprehensive cloud eigenvalue and the cloud model; A closeness module for determining the closeness between the comprehensive cloud eigenvalue and the standard cloud eigenvalue according to the comprehensive cloud eigenvalue, the standard cloud eigenvalue, and the comprehensive cloud diagram and the standard cloud diagram, and determining the warning level of the chemical according to the closeness; 10. An electronic device, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the method according to any one of claims 1 to 8.

Images