New risk assessment method, device and equipment based on cloud feature parameters and cloud image

Abstract

The application discloses a novel risk assessment method and device based on cloud feature parameters and cloud maps, and relates to the technical field of novel risk assessment, and comprises the following steps: in the case that a risk scene belongs to a novel risk scene, a scene library is established based on a plurality of events occurring in the risk scene in a same time period at different positions or regions; a plurality of evaluation standard clouds are drawn according to preset score intervals; a historical event evaluation cloud map and an expert evaluation cloud map are drawn based on historical evaluation cloud feature parameters and expert evaluation cloud feature parameters; the similarity of the historical event evaluation cloud map and the expert evaluation cloud map is calculated based on a cloud drop distance method, and a comprehensive evaluation cloud of a single event is obtained according to the historical event evaluation cloud map and the expert evaluation cloud map. The application proposes a scene evaluation method with universality, considers the overall risk of a scene and the risk of a single event of the scene, further introduces an uncertainty parameter, expands expert evaluation data, and enhances the consideration of uncertainty of novel risks.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of new risk assessment, in particular to a new risk assessment method and device based on cloud feature parameters and cloud images. BACKGROUND

[0002] In recent years, the concept of emerging risk has begun to rise in the field of risk research at home and abroad, and has gradually attracted the attention of the theoretical circle and decision makers. Major changes in scientific and technological level or economic and social system level may trigger emerging risks.

[0003] Emerging risks have characteristics such as high uncertainty and dynamic change, and currently there is a small sample size, lacking sufficient data support, while existing risk assessment methods, such as the comprehensive risk element method, although easy to apply, need to further improve the applicability of the indicators, and adopt a more intuitive and practical risk representation method.

[0004] Therefore, how to identify and evaluate emerging risks has become a problem to be solved.

[0005] The above content is only used to assist in understanding the technical solutions of the present application, and does not represent the acknowledgement of the above content as prior art. SUMMARY

[0006] The main purpose of the present application is to provide a new risk assessment method, device and equipment based on cloud feature parameters and cloud images, aiming to solve the technical problem of how to identify and evaluate emerging risks.

[0007] To achieve the above purpose, the present application provides a new risk assessment method based on cloud feature parameters and cloud images, which comprises:

[0008] In the case of a risk scenario belonging to a new risk scenario, a scenario library is established based on a plurality of events occurring in the same time period in different positions or regions of the risk scenario;

[0009] According to the preset score interval, a plurality of evaluation standard clouds are drawn;

[0010] Based on the historical scores of each event, a plurality of historical evaluation cloud feature parameters are obtained, and a historical event evaluation cloud image is drawn;

[0011] Based on the expert scores of each event and the corresponding uncertainty parameters, a plurality of expert evaluation cloud feature parameters are obtained, and an expert evaluation cloud image is drawn;

[0012] Based on the cloud droplet distance method, the similarity between the historical event evaluation cloud image and the expert evaluation cloud image is calculated, and the similarity is taken as reference data for adjusting the control strength of emerging risks;

[0013] According to the historical event evaluation cloud and the expert evaluation cloud, a comprehensive evaluation cloud of a single event is obtained;

[0014] According to the historical event evaluation cloud, the expert evaluation cloud and the comprehensive evaluation cloud, membership degrees of each evaluation standard cloud are determined;

[0015] According to the membership degrees, risk levels of the historical event evaluation cloud, the expert evaluation cloud and the comprehensive evaluation cloud are determined.

[0016] In an embodiment, when the risk scenario belongs to a new type of risk scenario, before the scenario library is established based on a plurality of events of the risk scenario occurring in a same time period in different locations or regions, the method further comprises:

[0017] The risk scenario meeting the condition is disassembled into at least urban safety basic elements including a risk source, a hazard-affected body and a disaster mitigation force;

[0018] When the risk source is related to new information technology, new energy, new industry forms and new material fields, it is determined that the risk scenario is a new type of risk scenario;

[0019] and / or

[0020] When the hazard-affected body is related to a new urban structure or system form, it is determined that the risk scenario is a new type of risk scenario;

[0021] and

[0022] When the disaster mitigation force is in an unknown state, it is determined that the risk scenario is a new type of risk scenario.

[0023] In an embodiment, the scenario library is established based on a plurality of events of the risk scenario occurring in a same time period in different locations or regions, comprising:

[0024] Investigating a plurality of events of the risk scenario occurring in a same time period in different locations or regions;

[0025] Establishing a scenario library according to the plurality of events.

[0026] In an embodiment, the historical evaluation cloud feature parameters are obtained based on historical scores of each event, and a historical event evaluation cloud is drawn, comprising:

[0027] According to a preset score interval, each event is scored according to a historical event description consequence severity, to obtain a plurality of historical scores;

[0028] According to the historical score of each type of event, a plurality of historical evaluation cloud feature parameters are obtained, wherein the historical evaluation cloud feature parameters include a historical evaluation expectation value, a historical evaluation entropy and a historical evaluation hyper entropy.

[0029] According to each of the historical evaluation cloud feature parameters, a historical event evaluation cloud map is drawn.

[0030] In an embodiment, the expert evaluation cloud feature parameters are obtained based on the expert scores of each of the events and the corresponding uncertainty parameters, and an expert evaluation cloud map is drawn, including:

[0031] According to a preset score interval, each of the events is evaluated by a fixed number of experts to obtain a plurality of initial scores and corresponding uncertainty parameters;

[0032] According to each of the initial scores and the corresponding uncertainty parameters of each type of event, a plurality of expert scores are obtained;

[0033] According to each of the expert scores of each type of event, a corresponding expert evaluation mean and expert evaluation variance are calculated;

[0034] According to the expert evaluation mean, the expert evaluation variance and the expert score of each type of event, a plurality of expert evaluation cloud feature parameters are obtained, wherein the expert evaluation cloud feature parameters include an expert evaluation expectation value, an expert evaluation entropy and an expert evaluation hyper entropy;

[0035] According to each of the expert evaluation cloud feature parameters, an expert evaluation cloud map is drawn.

[0036] In an embodiment, the expert scores are obtained based on each of the initial scores and the corresponding uncertainty parameters of each type of event, including:

[0037] An event is selected as a to-be-expanded event, and each of the initial scores and the corresponding uncertainty parameters of the to-be-expanded event are obtained;

[0038] The maximum value and the minimum value in a preset score interval are obtained;

[0039] For a to-be-expanded event, a first expansion value and a second expansion value are obtained according to the maximum value, the minimum value, the initial score and the corresponding uncertainty parameter;

[0040] If the first expansion value is less than the minimum value, the minimum value is taken as the first expansion value;

[0041] If the second expansion value is greater than the maximum value, the maximum value is taken as the second expansion value;

[0042] The first expansion value, the initial score and the second expansion value are taken as the expert score.

[0043] In an embodiment, the step of obtaining the comprehensive evaluation cloud of a single event according to the historical event evaluation cloud and the expert evaluation cloud comprises:

[0044] obtaining the target event, the historical event weight and the expert evaluation weight, wherein the sum of the historical event weight and the expert evaluation weight is a fixed value;

[0045] obtaining the comprehensive cloud feature parameter of the target event according to the historical event weight, the expert evaluation weight, the historical evaluation cloud feature parameter of the target event and the expert evaluation cloud feature parameter, wherein the comprehensive cloud feature parameter comprises a target expected value, a target entropy and a target hyper entropy;

[0046] iterating each event to execute the above steps until the comprehensive cloud feature parameters of all events are obtained;

[0047] obtaining the comprehensive evaluation cloud of a single event based on the comprehensive cloud feature parameters of each event.

[0048] In an embodiment, after the step of obtaining the comprehensive evaluation cloud of a single event according to the historical event evaluation cloud and the expert evaluation cloud, the method further comprises:

[0049] obtaining the occurrence frequency of each event, and taking the occurrence frequency as the weight of each event;

[0050] selecting the historical event evaluation cloud feature parameter, the expert evaluation cloud feature parameter or the comprehensive cloud feature parameter as the reference cloud feature parameter;

[0051] obtaining the scene evaluation cloud feature parameter according to the weight corresponding to each event and the reference cloud feature parameter;

[0052] drawing a scene evaluation cloud map according to the scene evaluation cloud feature parameter.

[0053] In addition, to achieve the above object, the application further provides a novel risk assessment device based on cloud feature parameters and cloud maps, which comprises:

[0054] a scene construction module, configured to establish a scene library based on a plurality of events occurring in a same time period in different positions or regions of a risk scene in a case that the risk scene is a novel risk scene;

[0055] a standard establishment module, configured to draw a plurality of evaluation standard clouds according to a preset score interval;

[0056] a historical evaluation module, configured to obtain a plurality of historical evaluation cloud feature parameters based on historical scores of each event, and draw a historical event evaluation cloud map;

[0057] An expert evaluation module is configured to obtain a plurality of expert evaluation cloud feature parameters based on expert scores of the events and corresponding uncertainty parameters, and draw an expert evaluation cloud map;

[0058] A difference analysis module is configured to calculate a similarity between the historical event evaluation cloud map and the expert evaluation cloud map based on a cloud droplet distance method, and take the similarity as reference data for adjusting new risk management and control strength;

[0059] An event synthesis module is configured to obtain a comprehensive evaluation cloud of a single event based on the historical event evaluation cloud map and the expert evaluation cloud map.

[0060] A risk evaluation module is configured to determine membership degrees of the evaluation standard clouds based on the historical event evaluation cloud map, the expert evaluation cloud map and the comprehensive evaluation cloud, and determine risk levels of the historical event evaluation cloud map, the expert evaluation cloud map and the comprehensive evaluation cloud based on the membership degrees.

[0061] In addition, to achieve the above-mentioned purposes, the present application further provides a new risk evaluation device based on cloud feature parameters and cloud maps, which comprises a memory, a processor and a computer program stored in the memory and executable on the processor, and the computer program is configured to implement the steps of the new risk evaluation method based on cloud feature parameters and cloud maps as described above.

[0062] In addition, to achieve the above-mentioned purposes, the present application further provides a storage medium, which is a computer readable storage medium, and the storage medium stores a computer program, and the computer program is executed by a processor to implement the steps of the new risk evaluation method based on cloud feature parameters and cloud maps as described above.

[0063] In addition, to achieve the above-mentioned purposes, the present application further provides a computer program product, which comprises a computer program, and the computer program is executed by a processor to implement the steps of the new risk evaluation method based on cloud feature parameters and cloud maps as described above.

[0064] The one or more technical solutions provided by the present application have at least the following technical effects:

[0065] In a case where the risk scenario belongs to a new type of risk scenario, a scenario library is established based on a plurality of events of the risk scenario occurring in different locations or regions within a same time period; a plurality of evaluation standard clouds are drawn according to preset score intervals; a plurality of historical evaluation cloud feature parameters are obtained based on historical scores of the events, and a historical event evaluation cloud map is drawn; a plurality of expert evaluation cloud feature parameters are obtained based on expert scores of the events and corresponding uncertainty parameters, and an expert evaluation cloud map is drawn; similarity between the historical event evaluation cloud map and the expert evaluation cloud map is calculated based on a cloud droplet distance method, and the similarity is taken as reference data for adjusting new type of risk control strength; a comprehensive evaluation cloud of a single event is obtained according to the historical event evaluation cloud map and the expert evaluation cloud map; membership degrees of the historical event evaluation cloud map, the expert evaluation cloud map and the comprehensive evaluation cloud to each of the evaluation standard clouds are calculated according to a membership degree calculation method, and levels in which the historical event evaluation cloud map, the expert evaluation cloud map and the comprehensive evaluation cloud are located are judged. The application proposes a scenario evaluation method with universality for new type of risks, considers both overall risks of scenarios and risks of single events of scenarios, and also introduces uncertainty parameters to expand expert evaluation data due to cognitive uncertainty of new type of risks, constructs an evaluation method based on a cloud model, and enhances consideration of uncertainty of new type of risks. BRIEF DESCRIPTION OF DRAWINGS

[0066] The accompanying drawings, which are incorporated herein and form a part of the specification, illustrate embodiments consistent with the present application and, together with the description, further serve to explain the principles of the application.

[0067] To make the technical solutions of the embodiments of the application or the prior art clearer, below a brief introduction is given to the drawings needed to be used in the embodiments or the prior art description. Obviously, for those of ordinary skill in the art, other drawings can also be obtained from these drawings without any creative effort.

[0068] Figure 1 A flowchart is provided for the new type of risk evaluation method based on cloud feature parameters and cloud maps according to the first embodiment of the application;

[0069] Figure 2 A new type of risk performance form is provided for the new type of risk evaluation method based on cloud feature parameters and cloud maps according to the first embodiment of the application;

[0070] Figure 3 A flowchart is provided for the new type of risk evaluation method based on cloud feature parameters and cloud maps according to the second embodiment of the application;

[0071] Figure 4 A module structure diagram is provided for the new type of risk evaluation device based on cloud feature parameters and cloud maps according to the embodiment of the application.

[0072] Figure 5 A device structure schematic diagram of a hardware running environment involved in a new risk assessment method based on cloud feature parameters and cloud maps in embodiments of the present application.

[0073] The object implementation, functional features and advantages of the present application will be further described with reference to the embodiments and the accompanying drawings. DETAILED DESCRIPTION

[0074] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application, and are not used to limit the present application.

[0075] In order to better understand the technical solutions of the present application, the following will be described in detail in combination with the drawings and specific embodiments of the specification.

[0076] The main solution of the embodiments of the present application is: in the case that the risk scene belongs to a new type of risk scene, a scene library is established based on a plurality of events occurring in the same time period in different positions or regions of the risk scene;

[0077] Based on the historical scores of each event, a plurality of historical evaluation cloud feature parameters are obtained, and a historical event evaluation cloud map is drawn;

[0078] Based on the expert scores of each event and the corresponding uncertainty parameters, a plurality of expert evaluation cloud feature parameters are obtained, and an expert evaluation cloud map is drawn;

[0079] Based on the cloud drop distance method, the similarity of the historical event evaluation cloud map and the expert evaluation cloud map is calculated, and the similarity is taken as reference data for adjusting the new risk control strength;

[0080] According to the historical event evaluation cloud map and the expert evaluation cloud map, a comprehensive evaluation cloud of a single event is obtained.

[0081] Because the new type of risk has characteristics such as high uncertainty and dynamic change, and the sample size is small at present, there is a lack of sufficient data support, and the existing risk assessment methods, such as the method of comprehensive risk elements, although easy to apply, need to further improve the applicability of the indicators, and adopt more intuitive and practical risk representation method. Therefore, how to identify and evaluate the new type of risk has become a problem to be solved.

[0082] The application provides a solution, in the case that a risk scenario belongs to a new type of risk scenario, a scenario library is established based on a plurality of events of the risk scenario occurring in a same time period in different positions or regions; a plurality of evaluation standard clouds are drawn according to preset score intervals; a plurality of historical evaluation cloud feature parameters are obtained based on historical scores of the events, and a historical event evaluation cloud map is drawn; a plurality of expert evaluation cloud feature parameters are obtained based on expert scores of the events and corresponding uncertainty parameters, and an expert evaluation cloud map is drawn; similarity of the historical event evaluation cloud map and the expert evaluation cloud map is calculated based on a cloud droplet distance method, and the similarity is taken as reference data for adjusting the new type of risk control strength; a comprehensive evaluation cloud of a single event is obtained according to the historical event evaluation cloud map and the expert evaluation cloud map; membership degrees of the historical event evaluation cloud map, the expert evaluation cloud map and the comprehensive evaluation cloud to each of the evaluation standard clouds are calculated according to a membership calculation method, and levels of the historical event evaluation cloud map, the expert evaluation cloud map and the comprehensive evaluation cloud are judged. The application proposes a scenario evaluation method with universality for new types of risks, which considers both overall risks of scenarios and risks of single events of scenarios, and since there is cognitive uncertainty for new types of risks, an uncertainty parameter is introduced to expand expert evaluation data, an evaluation method is constructed based on a cloud model, and consideration of uncertainty of new types of risks is enhanced.

[0083] It should be noted that the execution subject of the embodiment can be a computing service device with data processing, network communication and program running functions, such as a tablet computer, a personal computer, a mobile phone, etc., or an electronic device capable of realizing the above functions. The embodiment and the following embodiments will be described below taking a computer as an example.

[0084] Based on this, the embodiment of the application provides a new type of risk evaluation method based on cloud feature parameters and cloud maps, referring to Figure 1 , Figure 1 The flowchart of the first embodiment of the new type of risk evaluation method based on cloud feature parameters and cloud maps of the application is shown in the figure.

[0085] In the embodiment, the new type of risk evaluation method based on cloud feature parameters and cloud maps includes steps S10-S80:

[0086] Step S10, in the case that a risk scenario belongs to a new type of risk scenario, a scenario library is established based on a plurality of events of the risk scenario occurring in a same time period in different positions or regions;

[0087] It should be noted that the risk scenario includes three basic elements of urban safety, i.e. risk source, disaster-bearing body and disaster mitigation force. The risk source can be a risk factor causing urban safety problems. The disaster-bearing body can be a city life composed of people and three-dimensional space (physical space, social space and information space) serving people, which is the carrier affected by disasters. The disaster mitigation force can be an element that can play a role in disaster prevention, mitigation and rescue before, during and after disasters. In risk assessment, an event can be a series of situations or activities that occur in a risk scenario and affect the organization in achieving its goals. The scenario library can be composed of events occurring in different regions or locations at the same time period based on a risk scenario.

[0088] Specifically, first, the risk scenario is disassembled into risk source, disaster-bearing body and disaster mitigation force, and it is judged whether it belongs to a new type of risk. The manifestation of the new type of risk is described as a "new" risk source acting on a "traditional" or "new" disaster-bearing body, or a "traditional" risk source acting on a "new" disaster-bearing body, and there is a situation where the disaster mitigation force is unknown (such as Figure 2 ). It is judged whether the risk source is "new", i.e. whether it involves new information technology, new energy, new industry, new materials, etc.; whether the disaster-bearing body is "new", i.e. whether it involves new urban structure or system form, etc., such as the deepening development of urban building system; whether the disaster mitigation force is "unknown", i.e. whether it involves lack of laws and regulations, unclear governance system, etc. For a type of risk scenario, investigate and obtain such risk scenarios in different locations or regions, multiple events occurring in the same time period, record the specific circumstances of these events, and establish a scenario library for this type of risk scenario according to these events.

[0089] It can be understood that, since the number of samples of the new type of risk scenario is small, step S10 can avoid the risk assessment losing effectiveness due to insufficient data, so as to make the conclusion of the risk assessment have wider applicability and universality.

[0090] In step S20, a plurality of evaluation standard clouds are drawn according to a preset scoring interval.

[0091] It should be noted that the preset scoring interval can be divided according to the severity of the event consequences, for example, it can include low (0-1), lower (1-2), medium (2-3), higher (3-4), and high (4-5) 5 levels. The evaluation standard cloud can be used to measure the condition of the new type of risk scenario.

[0092] It can be understood that by setting the preset scoring interval, a unified scoring standard is provided for subsequent historical event scoring and expert scoring.

[0093] In an embodiment, step S20 can include dividing a plurality of score intervals according to the event consequence severity, obtaining a plurality of standard expected values and a plurality of standard entropies according to upper and lower limit values of each of the score intervals, setting a hyper-entropy standard value as a constant, obtaining a plurality of standard cloud feature parameters according to the standard expected values, the standard entropies and the hyper-entropy standard value corresponding to each of the score intervals, and drawing a plurality of evaluation standard clouds according to the standard cloud feature parameters.

[0094] It should be noted that the expected value is a concept in probability theory and statistics, which represents the average value or long-term average value of a random variable, the concept of entropy is used to quantify the uncertainty and randomness of a risk scenario, and the hyper-entropy (He) is used to measure the uncertainty of the entropy.

[0095] For example, the event consequence severity evaluation standard is established, i.e., low (0-1), lower (1-2), medium (2-3), higher (3-4), and high (4-5) five levels. The evaluation standard cloud feature parameters are obtained according to the following formula, five standard clouds are generated, and k is 0.005, wherein Q max represents the upper limit value of the score interval, Q min represents the lower limit value of the score interval, k is a constant, represents the standard expected value, represents the standard entropy, represents the hyper-entropy standard value.

[0096]

[0097] The above is only one embodiment of step S20 provided by the embodiment, and the embodiment does not specifically limit the specific embodiments of step S20.

[0098] Step S30, obtaining a plurality of historical evaluation cloud feature parameters based on historical scores of each of the events, and drawing a historical event evaluation cloud map;

[0099] It should be noted that the historical score can be scored according to the historical event description consequence severity when an event occurs, the historical event description consequence severity can reflect the cognition of people at that time on the new type of risk, the historical evaluation cloud feature parameters can include historical evaluation expected value, historical evaluation entropy and historical evaluation hyper-entropy, all of which can be any real number, and the historical event evaluation cloud map is drawn based on the cloud model according to the historical evaluation cloud feature parameters of each event.

[0100] It can be understood that scoring according to the historical event description consequence severity and then calculating the historical evaluation cloud feature parameters can reflect the cognition of people at that time on the new type of risk scenario, and ensure the data quality and integrity.

[0101] In one possible implementation, step S30 can include, according to a preset scoring interval, scoring the consequence severity of each of the events according to historical event descriptions to obtain a plurality of historical scores; and obtaining a plurality of historical evaluation cloud feature parameters according to the historical scores of each of the events.

[0102] It should be noted that the historical evaluation cloud feature parameters include a historical evaluation expected value, a historical evaluation entropy and a historical evaluation hyper entropy, and the historical scores, the historical evaluation mean value, the historical evaluation variance, the historical evaluation expected value, the historical evaluation entropy and the historical evaluation hyper entropy can all be represented by any real number.

[0103] For example, the consequence severity of events occurring in the scene library is scored according to a preset scoring interval (which can be divided into five levels, with scores of 1-5 respectively), and the score mean value and variance of different events are calculated. Taking event A 1 for example, there are γ events in the scene library, and let the consequence severity of event A 1 is determined, with scores of The mean value is calculated as The variance is According to the formula, the historical evaluation expected value (Ex), the historical entropy (En) and the historical hyper entropy (He) are calculated according to the mean value and the variance, and the historical event evaluation cloud chart is drawn according to the cloud model and the historical evaluation cloud feature parameters.

[0104]

[0105] In the historical event evaluation process, Ex1 represents the historical evaluation expected value, En1 represents the historical evaluation entropy, and He1 represents the historical evaluation hyper entropy; n represents the number of events, x represents the historical score of each event, represents the mean value, and S 2 represents the variance.

[0106] The above is only one possible implementation of step S30 provided by the embodiment, and the embodiment does not specifically limit the specific implementation of step S30.

[0107] Step S40, based on the expert scores of each of the events and the corresponding uncertainty parameters, obtains a plurality of expert evaluation cloud feature parameters, and draws an expert evaluation cloud chart.

[0108] It should be noted that the expert score can be the most likely consequence severity of the scene after the event is judged by experts in the field according to the risk source, disaster bearing body and disaster mitigation body involved in the scene, and the score is scored according to the preset score interval, the uncertainty parameter can be a number from 0 to 1, which represents the degree of certainty of the expert for the score given by himself, the expert evaluation cloud feature parameter can include expert evaluation expectation value, expert evaluation entropy and expert evaluation hyper entropy, all of which can be represented by any real number, and the expert evaluation cloud map is drawn based on the cloud model according to the expert evaluation cloud feature parameter of each event.

[0109] It can be understood that the most likely consequence severity of the risk scene after the event is judged by experts in the field according to the risk source, disaster bearing body and disaster mitigation body involved in the risk scene, and the most likely consequence severity is scored according to the preset score interval, and then the expert evaluation cloud feature parameter is calculated, which is helpful to form a scientific decision support and enhance the objectivity and accuracy of risk assessment.

[0110] In a feasible implementation, step S40 can include: scoring each event by a fixed number of experts according to a preset score interval to obtain a plurality of initial scores and corresponding uncertainty parameters; obtaining a plurality of expert scores according to each of the initial scores and the corresponding uncertainty parameters of each event; calculating the corresponding expert evaluation mean and expert evaluation variance according to each of the expert scores of each event; obtaining a plurality of expert evaluation cloud feature parameters according to the expert evaluation mean, the expert evaluation variance and the expert score of each event, wherein the expert evaluation cloud feature parameters include expert evaluation expectation value, expert evaluation entropy and expert evaluation hyper entropy; and drawing an expert evaluation cloud map according to each of the expert evaluation cloud feature parameters.

[0111] It should be noted that the expert evaluation cloud feature parameter includes the expert evaluation expectation value, the expert evaluation entropy and the expert evaluation entropy, and the expert score, the expert evaluation mean, the expert evaluation variance, the expert evaluation expectation value, the expert evaluation entropy and the expert evaluation hyper entropy can be represented by any real number.

[0112] Exemplarily, Z experts in the relevant field are selected, the most likely consequence severity of the scene after the event is judged according to the risk source, disaster bearing body and disaster mitigation body involved in the scene, and the uncertainty parameter θ (θ ∈ [0, 1]) of this judgment is given.

[0113] According to the uncertainty parameter, data is added in the original evaluation data (initial score). The method is as follows: for a certain event, assuming that the minimum value in the preset score interval is H min , and the maximum value is H maxFor example, if the preset scoring range is [1, 5], then 1 is the minimum value and 5 is the maximum value. When the severity scores of the consequences assessed by Z experts are {H1, H2, ..., H...}, the scores are... Z The uncertainty parameters are {θ1, θ2, ..., θ}. z Then, the two augmented values ​​are calculated according to the following formula:

[0114]

[0115] At the same time, if Then H min It is added to the initial score data as the first augmentation value; if Then H max This is added as a second augmentation value to the initial scoring data. The augmented data is represented as H = {H′1, H′2, ..., H′}. 3Z For the expanded data, calculate the mean and variance. Taking event A as an example... 1 For example, let's assume the expanded data is... The mean and variance can be expressed as follows: variance is

[0116] Then, according to the following formula, calculate the three characteristic parameters of expert evaluation: expected value (Ex), expert entropy (En), and expert hyperentropy (He). Draw the expert evaluation cloud map based on the cloud model and the characteristic parameters of the expert evaluation cloud.

[0117]

[0118] In the expert evaluation process, i = 2, Ex2 represents the expected value of the expert evaluation, En2 represents the entropy of the expert evaluation, and He2 represents the hyperentropy of the expert evaluation; n represents the number of events, and x represents the expert score for each event. S represents the mean of the expert ratings. 2 The variance represents the expert ratings.

[0119] The above is only one feasible implementation of step S40 provided in this embodiment. This embodiment does not specifically limit the specific implementation of step S40.

[0120] Step S50: Based on the cloud droplet distance method, calculate the similarity between the historical event evaluation cloud map and the expert evaluation cloud map, and use the similarity as reference data to adjust the intensity of new risk management.

[0121] It should be noted that the cloud drop distance method is a similarity measurement method based on a cloud model, which represents the similarity between two cloud models by generating cloud drops and calculating the values of the cloud drops, and the cloud drop is a basic unit of the cloud model and represents a random implementation of a qualitative concept. In the cloud model theory, the cloud drop is an individual element constituting a "cloud" and reflects the overall characteristics of a certain qualitative concept in the domain.

[0122] It can be understood that by evaluating the cloud map and the expert evaluation cloud map for the historical event and calculating the similarity based on the existing cloud drop distance method, the difference between the current cognition of the new type of risk and the actual occurrence can be compared and analyzed, which is beneficial to the management personnel to adjust the control strength of the new type of risk.

[0123] In step S60, a comprehensive evaluation cloud of a single event is obtained according to the historical event evaluation cloud map and the expert evaluation cloud map.

[0124] It should be noted that the comprehensive evaluation cloud of a single event can reflect the uncertainty of a single event in a direct number.

[0125] It can be understood that since the evolution law of the new type of risk is unknown, the uncertainty is high, and the sample size is small at present, the size of the new type of risk can be described by combining historical evaluation and expert scoring, which can enhance the flexibility of the evaluation method.

[0126] In a feasible implementation, step S60 includes obtaining a target event, a historical event weight and an expert evaluation weight, wherein the sum of the historical event weight and the expert evaluation weight is a fixed value; obtaining a comprehensive cloud feature parameter of the target event according to the historical event weight, the expert evaluation weight, a historical evaluation cloud feature parameter of the target event and an expert evaluation cloud feature parameter, wherein the comprehensive cloud feature parameter includes a target expected value, a target entropy and a target hyper entropy; traversing each event, executing the above steps until the comprehensive cloud feature parameters of all events are obtained; and obtaining a comprehensive evaluation cloud of a single event based on the comprehensive cloud feature parameters.

[0127] Exemplarily, it is assumed that the historical event weight is w1 and the expert evaluation weight is w2, the values of which can be assigned according to the cognition of the scene to be evaluated, the sample size of the historical event, etc., and w1+w2=1, Ex1 represents a historical evaluation expected value, En1 represents a historical evaluation entropy, He1 represents a historical evaluation hyper entropy, Ex2 represents an expert evaluation expected value, En2 represents an expert evaluation entropy, and He2 represents an expert evaluation hyper entropy; and the comprehensive cloud feature parameter of a single event is as follows.

[0128]

[0129] Step S70, according to the historical event evaluation cloud, the expert evaluation cloud and the comprehensive evaluation cloud, the membership of each evaluation standard cloud is determined.

[0130] It should be noted that the membership can be used to describe the degree to which an element belongs to a fuzzy set. In the fuzzy set, the membership of the element is no longer absolute "yes" or "no", but can be any value between 0 and 1, indicating the strength of the membership degree, which can be calculated by the membership calculation method. The membership of the historical event evaluation cloud, the expert evaluation cloud and the comprehensive evaluation cloud to each evaluation standard cloud is calculated.

[0131] It can be understood that by calculating the membership of the historical event evaluation cloud, the expert evaluation cloud and the comprehensive evaluation cloud to each evaluation standard cloud, the membership relationship between the historical score, the expert score and the evaluation standard can be more accurately expressed, so as to realize the accurate processing and decision of fuzzy problems.

[0132] Step S80, according to the membership, the risk level of the historical event evaluation cloud, the expert evaluation cloud and the comprehensive evaluation cloud is determined.

[0133] It should be noted that the risk level can reflect the relative position of the evaluation object in all evaluation objects, such as the positioning in the evaluation grades of excellent, good, medium and poor.

[0134] It can be understood that according to the membership, the level of the historical event evaluation cloud, the expert evaluation cloud and the comprehensive evaluation cloud is determined, which can reflect the performance of the risk scene on each evaluation index, such as which index is excellent and which index needs to be improved.

[0135] The embodiment provides a new risk assessment method based on cloud feature parameters and cloud diagrams. In the case that a risk scene belongs to a new risk scene, a scene library is established based on a plurality of events of the risk scene occurring in a same time period in different positions or regions; a plurality of evaluation standard clouds are drawn according to preset score intervals; a plurality of historical evaluation cloud feature parameters are obtained based on historical scores of the events, and a historical event evaluation cloud diagram is drawn; a plurality of expert evaluation cloud feature parameters are obtained based on expert scores of the events and corresponding uncertainty parameters, and an expert evaluation cloud diagram is drawn; similarity of the historical event evaluation cloud diagram and the expert evaluation cloud diagram is calculated based on a cloud drop distance method, and the similarity is taken as reference data for adjusting new risk control strength; a comprehensive evaluation cloud of a single event is obtained according to the historical event evaluation cloud diagram and the expert evaluation cloud diagram; membership degrees of the historical event evaluation cloud diagram, the expert evaluation cloud diagram and the comprehensive evaluation cloud to each of the evaluation standard clouds are calculated according to a membership calculation method, and levels of the historical event evaluation cloud diagram, the expert evaluation cloud diagram and the comprehensive evaluation cloud are judged. The application proposes a universal scene assessment method for new risks, considers both overall risks of scenes and risks of single events of scenes, and introduces an uncertainty parameter to expand expert evaluation data because of cognitive uncertainty of new risks, constructs an evaluation method based on a cloud model, and enhances consideration of uncertainty of new risks.

[0136] Based on the first embodiment, in the second embodiment, the same or similar contents as the above-mentioned first embodiment can be referred to the above description, and the subsequent will not be repeated. On this basis, please refer to Figure 3 , after step S70, the new risk assessment method based on cloud feature parameters and cloud diagrams further includes steps S71-S74:

[0137] In step S71, the occurrence frequencies of the events are obtained, and the occurrence frequencies are taken as weights of the events.

[0138] It should be noted that the occurrence frequency can be a proportion of a single event to all events.

[0139] In step S72, a historical event evaluation cloud feature parameter, an expert evaluation cloud feature parameter or a comprehensive cloud feature parameter is selected as a reference cloud feature parameter.

[0140] In step S73, a scene evaluation cloud feature parameter is obtained according to the weights of the events and the reference cloud feature parameter.

[0141] Ex = p * (Ex1 + He1) / (En1 + He1) En = p * (En1 + He1) / (En1 + He1) He = p * (He1 + He1) / (En1 + He1) Ex1 = (Ex + He) / 2 En1 = (En + He) / 2 He1 = (He + He) / 2

[0142]

[0143] Step S74, according to the scene evaluation cloud feature parameters, a scene evaluation cloud map is drawn.

[0144] It should be noted that the scene evaluation cloud feature parameters include the scene evaluation expected value, the scene evaluation entropy and the scene evaluation hyper entropy.

[0145] The embodiment integrates the scene evaluation cloud feature parameters by taking the frequency of each event of the scene as the weight of each scene, draws the scene evaluation cloud, combines the possibility of the events of the scene in the scene library, comprehensively judges the risk, integrates the scene evaluation cloud generated by all events of a scene, and realizes the evaluation of the new risk scene risk.

[0146] It should be noted that the above examples are only used for understanding the present application and do not constitute a limitation on the new risk evaluation method based on the cloud feature parameters and the cloud map of the present application. More forms of simple transformation based on the technical concept are within the protection scope of the present application.

[0147] The present application also provides a new risk evaluation device based on the cloud feature parameters and the cloud map, please refer to Figure 4 The new risk evaluation device based on the cloud feature parameters and the cloud map comprises:

[0148] The scene construction module 10 is configured to, in the case that the risk scene is a new risk scene, establish a scene library based on a plurality of events of the risk scene occurring in a same time period in different positions or regions;

[0149] The standard establishment module 20 is configured to draw a plurality of evaluation standard clouds according to a preset score interval;

[0150] The historical evaluation module 30 is configured to obtain a plurality of historical evaluation cloud feature parameters based on historical scores of the events, and draw a historical event evaluation cloud map;

[0151] The expert evaluation module 40 is configured to obtain a plurality of expert evaluation cloud feature parameters based on expert scores of the events and corresponding uncertainty parameters, and draw an expert evaluation cloud map;

[0152] The difference analysis module 50 is configured to calculate the similarity between the historical event evaluation cloud chart and the expert evaluation cloud chart based on the cloud drop distance method, and take the similarity as reference data for adjusting the new risk control strength.

[0153] The event synthesis module 60 is configured to obtain a single event comprehensive evaluation cloud according to the historical event evaluation cloud chart and the expert evaluation cloud chart.

[0154] The risk evaluation module 70 is configured to determine the membership degrees of each evaluation standard cloud according to the historical event evaluation cloud chart, the expert evaluation cloud chart and the comprehensive evaluation cloud, and determine the risk levels of the historical event evaluation cloud chart, the expert evaluation cloud chart and the comprehensive evaluation cloud according to the membership degrees.

[0155] The new risk evaluation device based on cloud feature parameters and cloud charts provided in the application adopts the new risk evaluation method based on cloud feature parameters and cloud charts in the above embodiments, and can solve the technical problem of new risk evaluation based on cloud feature parameters and cloud charts. Compared with the prior art, the new risk evaluation device based on cloud feature parameters and cloud charts provided in the application has the same beneficial effects as the new risk evaluation method based on cloud feature parameters and cloud charts provided in the above embodiments, and other technical features in the new risk evaluation device based on cloud feature parameters and cloud charts are the same as the features disclosed in the above method embodiments, which will not be repeated here.

[0156] The scenario construction module 10 is further configured to decompose the risk scenario meeting the condition into at least urban safety basic elements including a risk source, a disaster-bearing body and a disaster mitigation force; determine the risk scenario as a new risk scenario if the risk source is related to new information technology, new energy, new industry form and new material field; and / or determine the risk scenario as a new risk scenario if the disaster-bearing body is related to a new urban structure or system form; and / or determine the risk scenario as a new risk scenario if the disaster mitigation force is in an unknown state.

[0157] The standard establishment module 20 is further configured to divide a plurality of score intervals according to the event consequence severity; obtain a plurality of standard expected values and a plurality of standard entropies according to the upper limit value and the lower limit value of each score interval; set a hyper-entropy standard value as a constant; obtain a plurality of standard cloud feature parameters according to each standard expected value, each standard entropy and the hyper-entropy standard value corresponding to each score interval; and draw a plurality of evaluation standard clouds according to each standard cloud feature parameter.

[0158] The historical evaluation module 30 is further configured to score each of the events according to a preset score interval and a consequence severity of the event, to obtain a plurality of historical scores; obtain a plurality of historical evaluation cloud feature parameters according to the historical score of each event, wherein the historical evaluation cloud feature parameters include a historical evaluation expectation value, a historical evaluation entropy and a historical evaluation hyper entropy; and draw a historical event evaluation cloud map according to the historical evaluation cloud feature parameters.

[0159] The expert evaluation module 40 is further configured to evaluate each of the events by a fixed number of experts according to a preset score interval, to obtain a plurality of initial scores and corresponding uncertainty parameters; obtain a plurality of expert scores according to each of the initial scores and the corresponding uncertainty parameters of each event; calculate a corresponding expert evaluation mean and an expert evaluation variance according to each of the expert scores of each event; obtain a plurality of expert evaluation cloud feature parameters according to the expert evaluation mean, the expert evaluation variance and the expert score of each event, wherein the expert evaluation cloud feature parameters include an expert evaluation expectation value, an expert evaluation entropy and an expert evaluation hyper entropy; and draw an expert evaluation cloud map according to the expert evaluation cloud feature parameters.

[0160] The expert evaluation module 40 is further configured to select an event as an event to be expanded, obtain each of the initial scores and the corresponding uncertainty parameters of the event to be expanded; obtain a maximum value and a minimum value in the preset score interval; obtain a first expansion value and a second expansion value according to the maximum value, the minimum value, the initial score and the corresponding uncertainty parameter for an event to be expanded; if the first expansion value is less than the minimum value, the minimum value is taken as the first expansion value; if the second expansion value is greater than the maximum value, the maximum value is taken as the second expansion value; and take the first expansion value, the initial score and the second expansion value as the expert score.

[0161] The event synthesis module 60 is further configured to obtain a target event, a historical event weight and an expert evaluation weight, wherein the sum of the historical event weight and the expert evaluation weight is a fixed value; obtain a comprehensive cloud feature parameter of the target event according to the historical event weight, the expert evaluation weight, the historical evaluation cloud feature parameter and the expert evaluation cloud feature parameter of the target event, wherein the comprehensive cloud feature parameter includes a target expectation value, a target entropy and a target hyper entropy; traverse each of the events, perform the above steps until the comprehensive cloud feature parameters of all events are obtained; and obtain a comprehensive evaluation cloud of a single event based on the comprehensive cloud feature parameters.

[0162] The event synthesis module 60 is further configured to acquire the occurrence frequency of each event, take the occurrence frequency as the weight of each event, select the historical event evaluation cloud feature parameter, the expert evaluation cloud feature parameter or the comprehensive cloud feature parameter as the reference cloud feature parameter, obtain the scene evaluation cloud feature parameter according to the weight corresponding to each event and the reference cloud feature parameter, and draw a scene evaluation cloud image according to the scene evaluation cloud feature parameter.

[0163] The application provides a novel risk assessment device based on cloud feature parameters and cloud images. The novel risk assessment device based on cloud feature parameters and cloud images comprises at least one processor and a memory in communication connection with the at least one processor. The memory stores instructions executable by the at least one processor. The instructions are executed by the at least one processor to enable the at least one processor to perform the novel risk assessment method based on cloud feature parameters and cloud images in the above embodiment one.

[0164] Reference will be made to the following description of the embodiments of the application. Figure 5 The novel risk assessment device based on cloud feature parameters and cloud images shown in the structural diagram is suitable for implementing the embodiments of the application. The novel risk assessment device based on cloud feature parameters and cloud images in the embodiments of the application can include, but is not limited to, mobile terminals such as mobile phones, notebook computers, digital broadcast receivers, PDAs (Personal Digital Assistant), PADs (Portable Application Description), PMPs (Portable Media Player), vehicle-mounted terminals (for example, vehicle-mounted navigation terminals) and the like, and fixed terminals such as digital TVs, desktop computers and the like. Figure 5 The novel risk assessment device based on cloud feature parameters and cloud images shown is only an example and should not bring any limitation to the functions and use range of the embodiments of the application.

[0165] As Figure 5As shown, the new risk assessment device based on cloud feature parameters and cloud images can include a processing device 1001 (e.g., a central processing unit, a graphics processing unit, etc.) that can perform various appropriate actions and processes according to programs stored in a read-only memory (ROM) 1002 or loaded from a storage device 1003 into a random access memory (RAM) 1004. In the RAM 1004, various programs and data required for the operation of the new risk assessment device based on cloud feature parameters and cloud images are also stored. The processing device 1001, the ROM 1002, and the RAM 1004 are connected to each other through a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Generally, the following systems can be connected to the I / O interface 1006: input devices 1007 including, for example, a touch screen, a touch pad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; output devices 1008 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; the storage device 1003 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 1009. The communication device 1009 can allow the new risk assessment device based on cloud feature parameters and cloud images to communicate with other devices wirelessly or by wire to exchange data. Although the new risk assessment device based on cloud feature parameters and cloud images with various systems is shown in the figure, it should be understood that all the systems shown are not required to be implemented or possessed. More or fewer systems can be alternatively implemented or possessed.

[0166] In particular, according to embodiments of the present disclosure, the processes described above with reference to the flowcharts can be implemented as a computer software program. For example, embodiments of the present disclosure include a computer program product comprising a computer program carried on a computer readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network through a communication device, or installed from the storage device 1003, or installed from the ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the methods of the embodiments of the present disclosure are performed.

[0167] The new risk assessment device based on the cloud feature parameter and the cloud picture provided in the application adopts the new risk assessment method based on the cloud feature parameter and the cloud picture in the above embodiment, and can solve the technical problem of the new risk assessment based on the cloud feature parameter and the cloud picture. Compared with the prior art, the beneficial effects of the new risk assessment device based on the cloud feature parameter and the cloud picture provided in the application are the same as those of the new risk assessment method based on the cloud feature parameter and the cloud picture provided in the above embodiment, and other technical features in the new risk assessment device based on the cloud feature parameter and the cloud picture are the same as those disclosed in the previous embodiment method, which will not be repeated here.

[0168] It should be understood that parts of the present application can be realized by hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0169] The above is merely specific implementation of the present application, but the protection scope of the present application is not limited thereto, any person skilled in the art can easily think of changes or replacements within the technical range disclosed in the present application, which should be covered in the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

[0170] The present application provides a computer readable storage medium having computer readable program instructions (i.e. computer programs) stored thereon, the computer readable program instructions being used to execute the new risk assessment method based on the cloud feature parameter and the cloud picture in the above embodiment.

[0171] The computer readable storage medium provided in the application may be, for example, a U disk, but is not limited to an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, system or device, or any combination thereof. More specific examples of the computer readable storage medium may include, but are not limited to, an electrical connection with one or more conductive wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In the present embodiment, the computer readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, system or device. The program code contained on the computer readable storage medium can be transmitted by any suitable medium, including but not limited to an electrical wire, an optical cable, an RF (Radio Frequency), etc., or any suitable combination thereof.

[0172] The computer readable storage medium described above may be contained in the new risk assessment device based on cloud feature parameters and cloud maps, or may exist independently without being assembled into the new risk assessment device based on cloud feature parameters and cloud maps.

[0173] The computer readable storage medium described above carries one or more programs, which, when executed by the new risk assessment device based on cloud feature parameters and cloud maps, cause the new risk assessment device based on cloud feature parameters and cloud maps to: in the case that a risk scenario belongs to a new risk scenario, establish a scenario library based on a plurality of events of the risk scenario occurring in different locations or regions within the same time period; draw a plurality of evaluation standard clouds according to a preset scoring interval; obtain a plurality of historical evaluation cloud feature parameters based on historical scores of each of the events, and draw a historical event evaluation cloud map; obtain a plurality of expert evaluation cloud feature parameters based on expert scores of each of the events and corresponding uncertainty parameters, and draw an expert evaluation cloud map; calculate the similarity between the historical event evaluation cloud map and the expert evaluation cloud map based on a cloud droplet distance method, and take the similarity as reference data for adjusting the new risk control strength; obtain a comprehensive evaluation cloud of a single event according to the historical event evaluation cloud map and the expert evaluation cloud map; determine the membership degree of each of the evaluation standard clouds according to the historical event evaluation cloud map, the expert evaluation cloud map and the comprehensive evaluation cloud; and determine the risk level in which the historical event evaluation cloud map, the expert evaluation cloud map and the comprehensive evaluation cloud are located according to the membership degree.

[0174] Computer program code for carrying out operations of the present application can be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C++ or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code can execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or the connection can be made to an external computer (for example, through the Internet using an Internet Service Provider).

[0175] The computer program instructions can also be loaded onto a computer, other programmable data processing apparatus, or other devices to cause a series of operational steps to be performed on the computer, other programmable apparatus or other devices to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide processes for implementing the functions / acts specified in the flowchart and / or block diagram block or blocks.

[0176] The modules involved in the embodiments of the present application can be implemented in the form of software or hardware. In some cases, the name of the module does not constitute a limitation on the module itself.

[0177] The readable storage medium provided by the application is a computer readable storage medium, and the computer readable storage medium stores computer readable program instructions (i.e. computer programs) for executing the new risk assessment method based on the cloud feature parameters and the cloud image, and can solve the technical problem of the new risk assessment based on the cloud feature parameters and the cloud image. Compared with the prior art, the beneficial effects of the computer readable storage medium provided by the application are the same as those of the new risk assessment method based on the cloud feature parameters and the cloud image provided by the above-mentioned embodiments, and will not be repeated here.

[0178] The application also provides a computer program product comprising a computer program, which, when executed by a processor, implements the steps of the new risk assessment method based on the cloud feature parameters and the cloud image as described above.

[0179] The computer program product provided by the application can solve the technical problem of the new risk assessment based on the cloud feature parameters and the cloud image. Compared with the prior art, the beneficial effects of the computer program product provided by the application are the same as those of the new risk assessment method based on the cloud feature parameters and the cloud image provided by the above-mentioned embodiments, and will not be repeated here.

[0180] The above-mentioned is only part of the embodiments of the application, and does not limit the patent scope of the application, and any equivalent structural transformation, direct / indirect application in other related technical fields made by using the content of the application specification and drawings under the technical concept of the application are included in the patent protection scope of the application.

Claims

1. A novel risk assessment method based on cloud feature parameters and cloud maps, characterized in that, The method includes: In cases where the risk scenario is a novel risk scenario, a scenario library is established based on multiple events that occur in the same time period in different locations or regions within the risk scenario. Based on the preset scoring range, draw multiple evaluation standard clouds; Based on the historical scores of each event, multiple historical evaluation cloud feature parameters are obtained, and a historical event evaluation cloud map is drawn. Based on the expert scores for each event and the corresponding uncertainty parameters, multiple expert evaluation cloud feature parameters are obtained, and an expert evaluation cloud map is drawn. Based on the cloud droplet distance method, the similarity between the historical event evaluation cloud map and the expert evaluation cloud map is calculated, and the similarity is used as reference data for adjusting the intensity of new risk management. Based on the historical event evaluation cloud map and the expert evaluation cloud map, a comprehensive evaluation cloud for a single event is obtained; The membership degree of each evaluation standard cloud is determined based on the historical event evaluation cloud map, the expert evaluation cloud map, and the comprehensive evaluation cloud. The risk levels of the historical event evaluation cloud map, the expert evaluation cloud map, and the comprehensive evaluation cloud map are determined based on the membership degree. Based on the historical scores of each event, multiple historical evaluation cloud feature parameters are obtained, and a historical event evaluation cloud map is drawn, including: According to the preset scoring range, each historical event is scored sequentially based on the severity of its consequences, resulting in multiple historical scores. Based on the historical score of each event, multiple historical evaluation cloud feature parameters are obtained, including historical evaluation expectation value, historical evaluation entropy, and historical evaluation hyper-entropy. Based on the historical evaluation cloud characteristic parameters described above, draw historical event evaluation cloud maps; Based on the expert scores for each event and the corresponding uncertainty parameters, multiple expert evaluation cloud feature parameters are obtained, and an expert evaluation cloud map is drawn, including: According to a preset scoring range, each event is evaluated by a fixed number of experts to obtain multiple initial scores and corresponding uncertainty parameters; Based on the initial score and corresponding uncertainty parameters for each event, multiple expert scores are obtained; Based on the expert scores for each event, multiple expert evaluation cloud feature parameters are obtained, including expert evaluation expectation value, expert evaluation entropy, and expert evaluation hyperentropy. Based on the characteristic parameters of the expert evaluation cloud, draw the expert evaluation cloud map; The process involves obtaining multiple expert scores based on the initial scores and corresponding uncertainty parameters for each event, including: Select an event as the event to be expanded, and obtain the initial scores and corresponding uncertainty parameters of the event to be expanded; Get the maximum and minimum values ​​within a preset scoring range; For a given event to be expanded, a first expanded value and a second expanded value are obtained based on the maximum value, the minimum value, the initial score, and the corresponding uncertainty parameter. If the first augmented value is less than the minimum value, then the minimum value is used as the first augmented value; If the second augmented value is greater than the maximum value, then the maximum value is used as the second augmented value; The first augmented value, the initial score, and the second augmented value are used as the expert score.

2. The method as described in claim 1, characterized in that, Before establishing a scenario library based on multiple events occurring in different locations or regions within the same time period, when the risk scenario is a novel risk scenario, the method further includes: The risk scenarios that meet the conditions are broken down into the basic elements of urban safety, which include at least the risk source, the disaster-bearing body, and the disaster reduction capacity. If the risk source involves new information technology, new energy, new business models, and new materials, then the risk scenario is identified as a new type of risk scenario. and / or If the disaster-bearing body involves a new urban structure or system form, then the risk scenario is determined to be a new type of risk scenario. and If the disaster mitigation capability is in an unknown state, then the risk scenario is determined to be a new type of risk scenario.

3. The method as described in claim 1, characterized in that, The process involves drawing multiple evaluation standard clouds based on preset scoring intervals, including: The scoring range is divided according to the severity of the consequences of the event; Based on the upper and lower limits of each scoring interval, multiple standard expected values ​​and multiple standard entropies are obtained; Set the standard value of hyperentropy to a constant; According to the standard expected value, standard entropy and hyperentropy standard value corresponding to each of the scoring intervals, multiple standard cloud feature parameters are obtained; Multiple evaluation standard clouds are drawn based on the characteristic parameters of each standard cloud.

4. The method as described in claim 1, characterized in that, The process of obtaining a comprehensive evaluation cloud for a single event based on the historical event evaluation cloud map and the expert evaluation cloud map includes: Obtain the target event, historical event weights, and expert evaluation weights, wherein the sum of the historical event weights and expert evaluation weights is a fixed value; Based on the historical event weights, the expert evaluation weights, the historical evaluation cloud feature parameters of the target event, and the expert evaluation cloud feature parameters, the comprehensive cloud feature parameters of the target event are obtained, wherein the comprehensive cloud feature parameters include the target expected value, the target entropy, and the target hyper-entropy. Iterate through each of the events and perform the above steps until the comprehensive cloud feature parameters of all events are obtained; Based on the comprehensive cloud feature parameters described above, a comprehensive evaluation cloud for a single event is obtained.

5. The method as described in claim 1, characterized in that, After obtaining the comprehensive evaluation cloud for a single event based on the historical event evaluation cloud map and the expert evaluation cloud map, the method further includes: Obtain the occurrence frequency of each event, and use the occurrence frequency as the weight of each event; Choose historical event evaluation cloud feature parameters, expert evaluation cloud feature parameters, or comprehensive cloud feature parameters as reference cloud feature parameters; Based on the weights corresponding to each event and the reference cloud feature parameters, the scene evaluation cloud feature parameters are obtained; Based on the scene evaluation cloud feature parameters, draw a scene evaluation cloud map.

6. A novel risk assessment device based on cloud feature parameters and cloud maps, characterized in that, The device includes: The scenario building module is used to build a scenario library based on multiple events that occur in different locations or regions within the same time period when the risk scenario is a new type of risk scenario. The standard creation module is used to draw multiple evaluation standard clouds based on preset scoring ranges; The historical evaluation module is used to obtain multiple historical evaluation cloud feature parameters based on the historical scores of each event, and to draw a historical event evaluation cloud map. The expert evaluation module is used to obtain multiple expert evaluation cloud feature parameters based on the expert scores and corresponding uncertainty parameters of each event, and to draw an expert evaluation cloud map. The difference analysis module is used to calculate the similarity between the historical event evaluation cloud map and the expert evaluation cloud map based on the cloud droplet distance method, and use the similarity as reference data to adjust the intensity of new risk management. The event synthesis module is used to obtain a comprehensive evaluation cloud for a single event based on the historical event evaluation cloud map and the expert evaluation cloud map. The risk assessment module is used to determine the membership degree of each of the evaluation standard clouds based on the historical event evaluation cloud map, the expert evaluation cloud map, and the comprehensive evaluation cloud; and to determine the risk level of the historical event evaluation cloud map, the expert evaluation cloud map, and the comprehensive evaluation cloud based on the membership degree. The historical evaluation module is further configured to score each event sequentially according to the severity of the consequences described in the historical event description, based on a preset scoring range, to obtain multiple historical scores; to obtain multiple historical evaluation cloud feature parameters based on the historical scores of each event, wherein the historical evaluation cloud feature parameters include historical evaluation expected value, historical evaluation entropy, and historical evaluation hyperentropy; and to draw a historical event evaluation cloud map based on each of the historical evaluation cloud feature parameters. The expert evaluation module is further configured to evaluate each event according to a preset scoring range by a fixed number of experts, obtaining multiple initial scores and corresponding uncertainty parameters; obtain multiple expert scores based on each initial score and corresponding uncertainty parameter for each event; obtain multiple expert evaluation cloud feature parameters based on each expert score for each event, wherein the expert evaluation cloud feature parameters include expert evaluation expectation value, expert evaluation entropy, and expert evaluation hyperentropy; and draw an expert evaluation cloud map based on each expert evaluation cloud feature parameter. The expert evaluation module is further configured to select an event as the event to be expanded, obtain the initial scores and corresponding uncertainty parameters of the event to be expanded; obtain the maximum and minimum values ​​in a preset score range; for a given event to be expanded, obtain a first expanded value and a second expanded value based on the maximum value, the minimum value, the initial score, and the corresponding uncertainty parameters; if the first expanded value is less than the minimum value, then the minimum value is used as the first expanded value; if the second expanded value is greater than the maximum value, then the maximum value is used as the second expanded value; and use the first expanded value, the initial score, and the second expanded value as the expert score.

7. A novel risk assessment device based on cloud feature parameters and cloud maps, characterized in that, The device includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the novel risk assessment method based on cloud feature parameters and cloud maps as described in any one of claims 1 to 5.

Images