Nuclear emergency decision support method and device based on accident scene

Abstract

The invention relates to a nuclear emergency decision support method and device based on an accident scene. The method comprises the following steps: acquiring a historical accident scene; based on the historical accident scenes and the accident attributes, an accident database is constructed, and the accident database at least comprises the historical accident scenes and multiple solution strategies; under the condition that the accident attributes comprise the effective dose equivalent, based on the effective dose equivalent, the accident database is divided into two types, and two types of data sets are obtained; based on historical accident scenes, the two types of data sets are clustered respectively, and two accident scene libraries corresponding to the two types of data sets respectively are obtained; acquiring a current accident scene; performing similarity analysis based on the current accident scene and the accident scenes in the two accident scene libraries to obtain global similarity; and determining a target solution strategy corresponding to the current accident scene based on the global similarity. According to the invention, the current accident scene can be described without acquiring complete monitoring data of the accident scene, so that the technical effect of determining the corresponding coping strategy is achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of nuclear emergency, and in particular to a nuclear emergency decision support method and device based on accident scenarios. Background Art

[0002] Existing nuclear accident emergency decision support technologies often require multiple emergency evaluation results such as on-site core damage, release source estimation, and accident consequence evaluation as a basis to describe the current accident scenario, and provide nuclear emergency decision support in combination with relevant nuclear emergency regulations and emergency plans. These emergency evaluations all require a large amount of on-site monitoring data as support.

[0003] However, in the early stages of a nuclear accident, it is often difficult or even impossible to obtain monitoring data from the accident site and describe the accident scenario in detail, which may cause the nuclear emergency condition evaluation and auxiliary decision support methods to be paralyzed and unable to provide strong support for emergency preparedness and response.

[0004] The above problems need to be solved urgently. Summary of the invention

[0005] The invention discloses a nuclear emergency decision support method and device based on accident scenarios, aiming to solve the technical problems existing in the prior art.

[0006] The present invention adopts the following technical solutions:

[0007] On the one hand, the present invention provides a nuclear emergency decision support method based on accident scenarios, which comprises: obtaining historical accident scenarios, wherein the historical accident scenarios include accident attributes; constructing an accident database based on the historical accident scenarios and the accident attributes, wherein the accident database at least includes the historical accident scenarios and a plurality of solution strategies corresponding to the historical accident scenarios; when the accident attributes include effective dose equivalents, dividing the accident database into two categories based on the effective dose equivalent to obtain two categories of data sets; clustering the two categories of data sets respectively based on the historical accident scenarios to obtain two accident scenario libraries corresponding to the two categories of data sets, wherein the two accident scenario libraries each include at least accident scenarios and a plurality of solution strategies corresponding to the accident scenarios; obtaining a current accident scenario; performing similarity analysis based on the current accident scenario and the accident scenarios in the two accident scenario libraries to obtain a global similarity; and determining a target solution strategy corresponding to the current accident scenario based on the global similarity.

[0008] Optionally, in the case that the historical accident scenarios include multiple ones, constructing an accident database based on the historical accident scenarios and the accident attributes includes: constructing a case binary function based on any one of the multiple historical accident scenarios, wherein the case binary function is used to indicate the relationship between the historical accident scenario, the direction range of the historical accident scenario, and the accident attributes corresponding to the historical accident scenario; constructing a strategy model based on the case binary function, wherein the strategy model is used to indicate the response strategy corresponding to the direction of the historical accident scenario; performing a possibility analysis on the historical accident scenarios and the strategy model generation strategy to determine the historical accident scenarios with a possibility higher than a preset threshold and the corresponding generation strategy; determining the historical accident scenarios with a possibility higher than a preset threshold and the corresponding generation strategy to construct the accident database.

[0009] Optionally, based on any one of the multiple historical accident scenarios, a case binary function is constructed, including: dividing the multiple historical accident scenarios into multiple stages according to the timeline, wherein each of the historical accident scenarios corresponds to the multiple stages, and the multiple stages include at least a pre-radioactive release stage, a radioactive release stage, a radioactive transport stage, and a long-term post-accident stage; based on the interaction of the multiple stages, a plurality of accident cases are obtained, wherein the multiple accident cases are used to indicate the direction of the accident after changes occur in any of the multiple stages; based on any one of the multiple accident cases, a case binary function is constructed, wherein the case binary function is used to indicate the relationship between the accident case, the direction range of the accident case, and the accident attributes corresponding to the accident case.

[0010] Optionally, constructing a strategy model based on the case binary function includes: constructing an accident description model based on the case binary function, wherein the accident description model is used to indicate the chronological trend of the accident case; determining multiple actions to resolve the accident case based on the accident description model; sorting the multiple actions of the accident case to obtain multiple solution strategies; and constructing a strategy model based on the multiple solution strategies.

[0011] Optionally, the possibility analysis of the historical accident scenarios and the strategy model generation strategy is performed to determine the historical accident scenarios with a possibility higher than a preset threshold and the corresponding generation strategy, including: determining the possibility of the occurrence of the multiple accident cases to obtain a first possibility; when the first possibility is greater than the preset threshold, determining the possibilities corresponding to the multiple solution strategies generated by the strategy model based on the accident cases to obtain a second possibility; when the second possibility is greater than the preset threshold, determining the historical accident scenarios with a possibility higher than the preset threshold and the corresponding generation strategy.

[0012] Optionally, when the accident attributes include an effective dose equivalent, the accident database is divided into two categories based on the effective dose equivalent to obtain two types of data sets, including: one of the two types of data sets is that the effective dose equivalent is greater than or equal to 50 millisieverts, and the other is that the effective dose equivalent is less than 50 millisieverts.

[0013] Optionally, in the case where the historical accident scenarios include multiple ones, the two types of data sets are clustered separately based on the historical accident scenarios to obtain two accident scenario libraries corresponding to the two types of data sets, respectively, including: based on data mining, selecting any historical accident scenarios in turn from the multiple historical accident scenarios corresponding to the two types of data sets; based on the arbitrary historical accident scenarios, clustering the two types of data sets separately using the mean shift method; wherein the mean shift method clusters the two types of data sets separately by determining the center of mass and radius of the arbitrary historical accident scenarios.

[0014] Optionally, the similarity analysis is performed based on the current accident scenario and the accident scenarios in the two accident scenario libraries to obtain the global similarity, including: obtaining the accident attributes corresponding to the current accident scenario and the accident attributes included in the two accident scenario libraries; calculating the local similarities between the accident attributes corresponding to the current accident scenario and the accident attributes included in the two accident scenario libraries; and integrating the local similarities based on preset weight values ​​to obtain the global similarity.

[0015] Optionally, determining the target solution strategy corresponding to the current accident scenario based on the global similarity includes: determining that the current accident scenario belongs to one of the two accident scenario libraries based on the global similarity; determining that the current accident scenario corresponds to a historical accident scenario in the accident scenario library based on the local similarity; determining a plurality of initial solution strategies corresponding to historical accident scenarios similar to the current accident scenario based on the global similarity and the local similarity; performing feasibility analysis on the plurality of initial solution strategies to obtain a feasibility ranked list of the plurality of initial solution strategies; and determining the target solution strategy corresponding to the current accident scenario based on the feasibility ranked list.

[0016] Optionally, the method further includes: when the global similarity is lower than a preset similarity, storing the current accident scenario as a historical accident scenario in a corresponding accident scenario library of the two accident scenario libraries.

[0017] According to another aspect of an embodiment of the present invention, a nuclear emergency decision support device based on accident scenarios is also provided, comprising: a historical acquisition module, used to acquire historical accident scenarios, wherein the historical accident scenarios include accident attributes; an accident database construction module, used to construct an accident database based on the historical accident scenarios and the accident attributes, wherein the accident database at least includes the historical accident scenarios and a plurality of solution strategies corresponding to the historical accident scenarios; a data set differentiation module, used to divide the accident database into two categories based on the effective dose equivalent when the accident attributes include an effective dose equivalent, so as to obtain two categories of data sets; an accident scenario library construction module, used to cluster the two categories of data sets respectively based on the historical accident scenarios, so as to obtain two accident scenario libraries corresponding to the two categories of data sets, wherein both of the two accident scenario libraries at least include accident scenarios and a plurality of solution strategies corresponding to the accident scenarios; a current acquisition module, used to acquire a current accident scenario; a similarity analysis module, used to perform similarity analysis based on the current accident scenario and the accident scenarios in the two accident scenario libraries, so as to obtain a global similarity; and a strategy determination module, used to determine a target solution strategy corresponding to the current accident scenario based on the global similarity.

[0018] According to another aspect of an embodiment of the present invention, a non-volatile storage medium is provided, wherein the non-volatile storage medium stores a plurality of instructions, wherein the instructions are suitable for being loaded by a processor and executing any one of the accident scenario-based nuclear emergency decision support methods.

[0019] According to another aspect of an embodiment of the present invention, there is also provided a computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the steps of any one of the accident scenario-based nuclear emergency decision support methods are implemented.

[0020] The technical solution adopted by the present invention can achieve at least one of the following beneficial effects:

[0021] In an embodiment of the present invention, historical accident scenarios are obtained, wherein the historical accident scenarios include accident attributes; based on the historical accident scenarios and the accident attributes, an accident database is constructed, wherein the accident database at least includes the historical accident scenarios and a plurality of solution strategies corresponding to the historical accident scenarios; when the accident attributes include effective dose equivalents, the accident database is divided into two categories based on the effective dose equivalent to obtain two types of data sets; based on the historical accident scenarios, the two types of data sets are clustered respectively to obtain two accident scenario libraries corresponding to the two types of data sets, wherein each of the two accident scenario libraries at least includes accident scenarios and a plurality of solution strategies corresponding to the accident scenarios; the current accident scenario is obtained; based on the The current accident scenario is analyzed for similarity with the accident scenarios in the two accident scenario libraries to obtain a global similarity; based on the global similarity, the target solution strategy corresponding to the current accident scenario is determined, thereby achieving the goal of constructing two types of accident scenario libraries, based on the data obtained from the current accident scenario that is insufficient to support the description of the accident scenario, a similarity analysis is performed with the accident scenario library to determine the current accident scenario and obtain the solution strategy purpose, thereby achieving the technical effect of describing the current accident scenario without obtaining complete monitoring data of the accident site, thereby determining the corresponding response strategy, and further solving the technical problem that the accident scenario cannot be described in detail due to the inability to obtain comprehensive monitoring data of the accident site, thereby making it impossible to make corresponding decisions on emergency conditions. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments, which constitute a part of the present invention. The exemplary embodiments of the present invention and their descriptions explain the present invention and do not constitute improper limitations on the present invention. In the drawings:

[0023] Figure 1 is a flow chart of a nuclear emergency decision support method based on accident scenarios in Example 1 of the present invention;

[0024] Figure 2 It is a schematic diagram of the flow structure of a nuclear emergency decision support method based on accident scenarios in Example 1 of the present invention;

[0025] Figure 3is a similarity analysis flow chart of a nuclear emergency decision support method based on accident scenarios in Example 1 of the present invention;

[0026] Figure 4 It is a structural schematic diagram of a nuclear emergency decision support device based on accident scenarios in Example 2 of the present invention. DETAILED DESCRIPTION

[0027] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the specific embodiments of the present invention and the corresponding drawings. In the description of the present invention, it should be noted that the term "or" is usually used in the sense of including "and / or", unless the content clearly indicates otherwise.

[0028] In the description of the present invention, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or a magnetic connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal connection of two elements. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances. In addition, in the description of this application, the terms "first", "second", etc. are only used to distinguish the description, and cannot be understood as indicating or implying relative importance. In the description of the present invention, the meaning of "multiple" is at least two, such as two, three or more, etc., unless otherwise clearly and specifically limited.

[0029] Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0030] First, to facilitate understanding of the embodiments of the present invention, some terms or nouns involved in the present invention are explained below:

[0031] An accident scenario refers to a combination of specific conditions or circumstances that may lead to an accident or emergency. It describes various situations before, during and after an accident, including possible triggering factors, the development process of the accident, the scope of impact and possible consequences.

[0032] A binary function is a mathematical function with two independent variables.

[0033] The effective dose equivalent refers to the sum of the equivalent dose of the irradiated tissue or organ multiplied by the corresponding tissue weighting factor when the whole body is subjected to non-uniform irradiation.

[0034] In order to solve the problems existing in the prior art, the embodiments of the present application provide a nuclear emergency decision support method and device based on accident scenarios.

[0035] Example 1

[0036] This embodiment provides a nuclear emergency decision support method based on accident scenarios, such as Figure 1 and Figure 2 As shown, Figure 1 is a flow chart of a nuclear emergency decision support method based on accident scenarios in Example 1 of the present invention, Figure 2 1 is a schematic diagram of a flow structure of a nuclear emergency decision support method based on an accident scenario in Embodiment 1 of the present invention, the method comprising:

[0037] Step S102, obtaining historical accident scenarios, wherein the historical accident scenarios include accident attributes;

[0038] Optionally, the historical accident scenario is a historical event that occurred before the current period. Representative historical events can be selected, or multiple events can be virtually constructed as historical accident scenarios. Based on the historical accident scenarios as initial data, they are collated and analyzed to lay the foundation for the subsequent determination of support strategies.

[0039] Step S104, constructing an accident database based on historical accident scenarios and accident attributes, wherein the accident database at least includes historical accident scenarios and multiple solution strategies corresponding to the historical accident scenarios;

[0040] In some preferred embodiments, when there are multiple historical accident scenarios, an accident database is constructed based on the historical accident scenarios and accident attributes, including: constructing a case binary function based on any one of the multiple historical accident scenarios, wherein the case binary function is used to indicate the historical accident scenario, the trend range of the historical accident scenario, and the relationship between the accident attributes corresponding to the historical accident scenario; constructing a strategy model based on the case binary function, wherein the strategy model is used to indicate the response strategy corresponding to the trend of the historical accident scenario; performing a possibility analysis on the historical accident scenarios and the strategy model generation strategy, determining the historical accident scenarios with a possibility higher than a preset threshold and the corresponding generation strategy; determining the historical accident scenarios with a possibility higher than a preset threshold and the corresponding generation strategy, and constructing an accident database.

[0041] Optionally, in order to construct an accident database, multiple historical accident scenarios are required as data set support. For each of the multiple historical accident scenarios, a binary function is constructed, and the same eigenvalues ​​are found based on the constructed multiple binary functions. Based on the same eigenvalues, it can be determined that multiple historical accident scenarios have similar scenario trends. According to the above scenario trends, multiple strategies corresponding to the scenario trends are determined, and multiple strategies can solve the corresponding historical accident scenarios. However, some strategies may not be feasible, or some strategies may not solve the historical accident scenarios well. Therefore, it is necessary to determine whether the strategy is feasible based on possibility analysis, remove the infeasible strategies, and retain the strategies with a possibility higher than the preset threshold, and finally form historical accident scenarios and corresponding strategies to construct an accident database.

[0042] In some preferred embodiments, based on any one of a plurality of historical accident scenarios, a case binary function is constructed, including: dividing the plurality of historical accident scenarios into a plurality of stages according to a timeline, wherein each historical accident scenario corresponds to a plurality of stages, and the plurality of stages include at least a pre-radioactive release stage, a radioactive release stage, a radioactive transport stage, and a long-term post-accident stage; based on the interaction of a plurality of stages, a plurality of accident cases are obtained, wherein the plurality of accident cases are used to indicate the direction of the accident after a change occurs in any one of the plurality of stages; based on any one of the plurality of accident cases, a case binary function is constructed, wherein the case binary function is used to indicate the relationship between the accident case, the direction range of the accident case, and the accident attributes corresponding to the accident case.

[0043] Optionally, the multiple historical accident scenarios obtained are divided into two major stages, including the emergency action stage and the post-accident stage. The emergency action stage refers to the stage where protection decisions need to be made urgently when the accident is occurring, and the post-accident stage refers to the stage of protective measures that need to be taken after the accident occurs. The emergency action stage and the post-accident stage are further divided into more small stages. Specifically, the two major stages are roughly divided into four main small stages, namely: the pre-radioactive release stage, the radioactive release stage, the radioactive transport stage, and the long-term post-accident stage. It should be noted that the stage division can be divided according to the actual situation and application scenario. In addition to the above four main small stages, multiple other stages can also be divided. The above four small stages are divided by the release state, the type and urgency of the decision options, the type and availability of emergency resources, and the relevance of the exposure pathway. Among them, the release state, the type and urgency of the decision options, the type and availability of emergency resources, and the relevance of the exposure pathway are all accident attributes in the historical accident scenario.

[0044] Optionally, the historical accident scenario will change with the passage of time, that is, when the historical accident scenario first occurs, the equipment may work slowly, and after a period of time, the historical accident scenario becomes that the equipment cannot operate, and after a period of time, the historical accident scenario becomes that the equipment explodes and other dangerous phenomena. There may also be other development trends, that is, when the historical accident scenario first occurs, a small amount of sparks appear on the equipment, and as time goes by, the equipment stops running, and then as time goes by, the equipment explodes and other dangerous phenomena. Therefore, the same equipment may have different accident causes or accident trends over time before the same result occurs, that is, in the above four major stages, if any one or more stages have accident changes, different accident trends may occur. Therefore, under the above four major stages, one or more stages can be arbitrarily changed to form an accident case, that is, the above four major stages are changed in a permutation and combination manner to obtain multiple accident cases.

[0045] Optionally, based on the obtained multiple accident cases, a binary function is constructed for each accident case. The specific binary function is as follows:

[0046] A=(A name ,dom(A))

[0047] Among them, A name is the characteristic label of the accident case, dom(A) is the definition domain of the possible development direction of the accident case, and A is the accident attribute of the accident case.

[0048] In some preferred embodiments, a strategy model is constructed based on a case binary function, including: constructing an accident description model based on the case binary function, wherein the accident description model is used to indicate the chronological trend of the accident cases; determining multiple actions to resolve the accident cases based on the accident description model; sorting the multiple actions of the accident cases to obtain multiple resolution strategies; and constructing a strategy model based on the multiple resolution strategies.

[0049] Optionally, based on the above determined two-tuple function, an accident description model is constructed. The specific accident description model is as follows:

[0050] D=(A1,…,A n ),n>0

[0051] Among them, D is the accident description model, A n is the accident attribute of the nth accident case.

[0052] Optionally, based on the accident description model, multiple actions (L1, ..., L k ), L kFor the kth action, for example, there is an accident case of equipment combustion. The seven actions to solve the accident case may include: pick up a bucket of water, walk to the water pipe, place the bucket under the water pipe, open the water pipe, close the water pipe after it is full, move to the equipment with the bucket full of water, and sprinkle the water in the bucket on the equipment. Based on the above-determined multiple actions to solve the accident case, multiple solution strategies are formed. Among them, the above seven actions are randomly arranged and combined to obtain 5040 solution strategies, that is, P(7,7)=7! / (7-7)! =7! =7×6×5×4×3×2×1=5040.

[0053] Optional, the specific strategy model is as follows:

[0054] L=((L1,…,L k ),S),k>0

[0055] Among them, L is the policy model, (L1,…,L k ) are multiple actions, and S are multiple solution strategies formed.

[0056] Optionally, multiple solution strategies consist of a collection of multiple actions and an order in which the multiple actions are executed. The functions corresponding to the specific multiple solution strategies are as follows:

[0057] S=(M,E)

[0058] Among them, M is a set including management options (multiple actions), target pointing options (pointers to one of the multiple actions) and more information about the option (the pointed action), and E is the execution order of the management options (the execution order of multiple actions).

[0059] M={(M1,…,M v )|v>0}

[0060] Among them, M v is the vth action being pointed to.

[0061]

[0062] Among them, to arrange the execution order of multiple actions, you can only select and arrange from multiple actions.

[0063] Optionally, for each policy s, it is a two-tuple defined as follows:

[0064] s=(m,e)

[0065] m i ={(m i1 ,…,m iv )|m ir ∈dom(M r),r∈[1,v],i∈N +}

[0066]

[0067] Among them, dom(M r ) is the domain of possible actions, v is the number of actions, and it should be noted that dom(M r ),r∈[1,v] contains the empty set.

[0068] Optional, define For the strategy space under nuclear emergency conditions (accident cases), the binary structure of the case model is constructed as follows:

[0069] C=(D,L)=((A1,…,A n ),((L1,…,L k ),S))

[0070] Among them, C is the feature label of the accident case, D is the accident description model, and L is the strategy model.

[0071] For a single accident case, the tuple of its case model is as follows:

[0072] c=(d,l)=((a1,…,a n ),((l1,…,l k ),s))

[0073] in,

[0074] In some preferred embodiments, a possibility analysis is performed on historical accident scenarios and strategy model generation strategies to determine historical accident scenarios with a probability higher than a preset threshold and corresponding generation strategies, including: determining the probability of occurrence of multiple accident cases to obtain a first possibility; when the first possibility is greater than the preset threshold, determining the probabilities corresponding to the multiple solution strategies generated by the strategy model based on the accident case to obtain a second possibility; when the second possibility is greater than the preset threshold, determining historical accident scenarios with a probability higher than the preset threshold and corresponding generation strategies.

[0075] Optionally, there may be a possibility that the above multiple accident cases will not occur. For example, if a bucket of water is used to extinguish the burning of the equipment at the beginning of the burning, the subsequent risk of equipment explosion will not exist, and the possibility of equipment explosion in the subsequent stage will be reduced to less than 50%. At the same time, there are also situations where multiple solution strategies are not in line with reality. For example, if the faucet is turned on after the bucket is filled with water, the strategy is not feasible. For the above parts of the stage where the possibility of occurrence is small and the solution strategy is not feasible, the content is screened to obtain effective cases.

[0076] Optionally, the specific screening method is to determine the possibility of occurrence of multiple accident cases and obtain a first possibility; when the first possibility is greater than a preset threshold, it indicates that the probability of the accident case occurring is relatively high, and a solution strategy is determined for the possible accident case, and the accident cases with a lower possibility of occurrence are deleted from the database. When the first possibility is greater than the preset threshold, the possibilities corresponding to the multiple solution strategies generated by the strategy model based on the accident case are determined to obtain a second possibility; when the second possibility is greater than the preset threshold, the historical accident scenarios with possibilities higher than the preset threshold and the corresponding generation strategies are determined. It should be noted that the preset threshold for the first possibility comparison may be different from the preset threshold for the second possibility comparison.

[0077] Step S106, when the accident attribute includes effective dose equivalent, the accident database is divided into two categories based on the effective dose equivalent to obtain two types of data sets;

[0078] In some preferred embodiments, when the accident attributes include effective dose equivalent, the accident database is divided into two categories based on the effective dose equivalent, and two types of data sets are obtained, including: one of the two types of data sets is an effective dose equivalent greater than or equal to 50 millisieverts, and the other is an effective dose equivalent less than 50 millisieverts.

[0079] Optionally, in the field of radiological medicine and radiation protection, effective dose equivalent is used to measure the radiation dose received by patients undergoing radiological examinations or treatments. At the same time, environmental monitoring agencies also regularly measure radiation levels in the environment, including radioactive substances in the air, water, and soil. An effective dose equivalent greater than or equal to 50 millisieverts indicates that the radiation dose corresponding to the historical accident scenario in the data set exceeds the standard, and there is a risk of harming human health. The solution strategy adopted will increase protection; the other type is an effective dose equivalent less than 50 millisieverts, indicating that the radiation dose corresponding to the historical accident scenario in the data set does not exceed the standard, and the risk of harming human health is small, and the response will be reduced protection when the solution strategy is adopted.

[0080] Step S108, based on the historical accident scenarios, clustering the two types of data sets respectively to obtain two accident scenario libraries corresponding to the two types of data sets, wherein both accident scenario libraries at least include accident scenarios and multiple solution strategies corresponding to the accident scenarios;

[0081] In some preferred embodiments, when there are multiple historical accident scenarios, two types of data sets are clustered separately based on the historical accident scenarios to obtain two accident scenario libraries corresponding to the two types of data sets, including: based on data mining, selecting any historical accident scenarios in turn from multiple historical accident scenarios corresponding to the two types of data sets; based on any historical accident scenario, clustering the two types of data sets separately using the mean shift method; wherein the mean shift method clusters the two types of data sets separately by determining the center of mass and radius of any historical accident scenario.

[0082] Optionally, a data mining process is used instead of random sampling to cluster the data sets in each category, and the clustering process uses the mean shift method (MSN). Starting from the accident scenario space in one of the data sets, each historical accident scenario x in the accident scenario space is clustered with a bandwidth of radius h. The specific clustering result g(x) is calculated as follows:

[0083]

[0084] The clustering method considers all points within a sphere with a radius of h, that is, considers all historical accident scenarios in the accident scenario space, and determines the centroid m (S A ), where the center of mass m(S A ) is calculated as follows:

[0085]

[0086] Where I is the total number of multiple historical accident scenarios, S A One of the data sets.

[0087] Get the first centroid m(S A ), since multiple historical accident scenarios change on the timeline, the centroid will be updated, and the above calculation method will be repeated for the centroid until the deviation between the new centroid and the centroid of the previous step is less than a certain limit, and the calculation is stopped. In the process of continuous updating of the above centroid, the clustering of historical accident scenarios x can be obtained, and finally the clustered accident scenario library is obtained.

[0088] Step S110, obtaining the current accident scenario;

[0089] Optionally, some available accident attributes in the current accident scenario are obtained, and based on the two accident scenario libraries obtained above (one is where the radiation level exceeds the standard, and the other is where the radiation level does not exceed the standard), some accident attributes of the current accident scenario are analyzed for similarity with the attributes in the accident scenario library, thereby obtaining historical accident scenarios similar to the current accident scenario, and based on similar historical accident scenarios, the possible accident trends of the current accident scenario are inferred, thereby determining a solution strategy. This effectively solves the technical problem that the accident scenario cannot be described in detail due to the inability to obtain comprehensive monitoring data at the accident site, thereby making it impossible to make corresponding decisions on emergency conditions.

[0090] Step S112, performing similarity analysis based on the current accident scenario and the accident scenarios in the two accident scenario libraries to obtain a global similarity;

[0091] In some preferred embodiments, a similarity analysis is performed based on the current accident scenario and the accident scenarios in the two accident scenario libraries to obtain a global similarity, including: obtaining the accident attributes corresponding to the current accident scenario and the accident attributes included in the two accident scenario libraries; calculating the local similarities between the accident attributes corresponding to the current accident scenario and the accident attributes included in the two accident scenario libraries; based on a preset weight value, integrating the local similarities to obtain a global similarity.

[0092] Optionally, in nuclear and radiological accidents, before calculating the global similarity, it is necessary to consider the factors of the accident stage, radiation target and radionuclide, and eliminate inappropriate decision options. In particular, it is necessary to consider the local similarity function of the radiation target and radionuclide, allowing the deviation of the accident attributes within a certain range to still point to the appropriate strategy, and it is necessary to classify according to the number of people affected (the number of people present at the time of the accident), the size of the affected area, the amount of radioactive material released, and the scale of the accident. Secondly, since the release time and weather are important factors affecting the deposition of radioactive aerosols, comparable targets, released materials, accident scale, time and meteorological conditions should be considered when searching for reusable strategies. Finally, social, environmental, decision-making effectiveness and psychological impact restrictions may further limit possible solutions, which need to be used as additional information for decision support.

[0093] Optionally, the retrieval task is divided into two small steps, first selecting the candidate objects (the current accident scenario and the two accident scenario libraries), and then determining the similarities between the candidate objects. It should be noted that since the accident stage restricts the possible appropriate decision options, accident cases that do not belong to the same accident stage cannot be analyzed for similarity.

[0094] For similarity analysis, accident attributes need to be indexed to exclude information that is useful but cannot provide distinguishing capabilities. Due to the different types of accident attributes (feature labels) and the changes in decision-making information requirements at different stages, the representation of nuclear accidents is relatively complex. It is necessary to adopt the local-global principle to decompose the problem into several parts. First, analyze and calculate the local similarity between accident attributes, then assign weights according to the importance of reflecting different accident attributes, and finally aggregate them into global similarity. Based on the global similarity, the historical accident scenario in the accident scenario library that is closest to the current accident scenario can be obtained. The flowchart of the similarity analysis is as follows: Figure 3 As shown, Figure 3 It is a similarity analysis flow chart of a nuclear emergency decision support method based on accident scenarios in Example 1 of the present invention.

[0095] Optionally, similarity analysis is calculated as follows:

[0096] Calculate the local similarity f of accident attribute A A , local similarity f A The calculation of is as follows:

[0097] f A =dom(A)×dom(A)

[0098] Among them, dom(A) is the definition domain of the possible development direction of the accident case, and A is the accident attribute of the accident case.

[0099] The environmental variable q and the accident case c are extracted from the tuple C = (D, L) of the case model of the accident scenario library. The environmental variable is calculated as follows:

[0100] q=(d q ,l q )=((q1,…,q n ),l q )

[0101] Among them, d q is the accident scenario related to the environmental variables, l q For resolution strategies related to environment variables.

[0102] The accident case was determined as follows:

[0103] c=(d c ,l c )=((a1,…,a n ),l c )

[0104] Among them, d q is the accident scenario related to the accident case, l q Provides resolution strategies related to incident cases.

[0105] Define the weight factor vector, the weight factor vector w is as follows:

[0106] w=(w1,…,w n )

[0107] Based on the environmental variable q, the accident case c and the weight factor vector, the global similarity is determined. The global similarity is calculated as follows:

[0108] f G (d q ,d c )=σ(f1(q1,a1),…,f n (q n ,a n ),w)

[0109] Among them, f i is the accident attribute A i The corresponding local similarity, σ is the aggregation function.

[0110] Step S114, based on the global similarity, determine the target solution strategy corresponding to the current accident scenario.

[0111] In some preferred embodiments, based on global similarity, a target solution strategy corresponding to the current accident scenario is determined, including: based on global similarity, determining that the current accident scenario belongs to one of two accident scenario libraries; based on local similarity, determining that the current accident scenario corresponds to a historical accident scenario in the accident scenario library; based on global similarity and local similarity, determining multiple initial solution strategies corresponding to historical accident scenarios similar to the current accident scenario; performing feasibility analysis on multiple initial solution strategies to obtain a feasibility ranked list of multiple initial solution strategies; and determining the target solution strategy corresponding to the current accident scenario based on the feasibility ranked list.

[0112] Optionally, the Jaccard coefficient is selected as a representation value for similarity comparison, and the Jaccard coefficient of accident attribute A is calculated as follows:

[0113]

[0114] Among them, J q is the result variable set after segmentation and processing of environmental variables, J c is the case set (accident scenario library) to be compared with the outcome variable set.

[0115] After the environmental variable q and the accident case c are introduced, the Jaccard coefficient is simplified and calculated as follows:

[0116]

[0117] Where b is the number of categories in dom(A).

[0118] Furthermore, it can be simplified as:

[0119]

[0120] Based on the global similarity and Jaccard coefficient, multiple initial solution strategies are determined. The sorted list of multiple initial solution strategies R = (c1,…,c k ) must meet the following conditions:

[0121] f G (d q ,d ci )≥f G (d q ,d cj ),1≤i<j≤k

[0122] Finally, the sorted lists of various initial solution strategies are filtered for feasibility to obtain a filtered sorted list of feasibility. The feasibility list must meet the following conditions:

[0123] CB F ={c=(d c ,l c )=((a1,…,a n ), c |a i =q i ,i∈J}

[0124] In some preferred embodiments, the method further includes: when the global similarity is lower than a preset similarity, storing the current accident scenario as a historical accident scenario in a corresponding accident scenario library in the two accident scenario libraries.

[0125] Through the above steps S102 to S114, two types of accident scenario libraries are constructed. Based on the data obtained from the current accident scenario that is insufficient to support the description of the accident scenario, a similarity analysis is performed with the accident scenario library to determine the current accident scenario and obtain the purpose of the solution strategy. This achieves the purpose of describing the current accident scenario without obtaining complete monitoring data of the accident site, thereby determining the technical effect of the corresponding response strategy, and further solves the technical problem of being unable to describe the accident scenario in detail due to the inability to obtain comprehensive monitoring data of the accident site, thereby making it impossible to make corresponding decisions on emergency conditions.

[0126] Example 2

[0127] In this embodiment, a nuclear emergency decision support device based on an accident scenario is also provided, which is used to implement the above-mentioned embodiments and preferred implementation modes, and the descriptions that have been made will not be repeated. As used below, the terms "module" and "device" can implement a combination of software and / or hardware for a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0128] According to an embodiment of the present invention, there is also provided an apparatus embodiment for implementing the above-mentioned nuclear emergency decision support method based on accident scenarios. Figure 4 is a schematic diagram of the structure of a nuclear emergency decision support device based on an accident scenario in Example 2 of the present invention, such as Figure 4 As shown, the above-mentioned nuclear emergency decision support device based on accident scenarios includes: a history acquisition module 401, an accident database construction module 402, a data set distinction module 403, an accident scenario library construction module 404, a current acquisition module 405, a similarity analysis module 406 and a strategy determination module 407, wherein:

[0129] A history acquisition module 401 is used to acquire historical accident scenarios, wherein the historical accident scenarios include accident attributes;

[0130] The accident database construction module 402 is connected to the history acquisition module 401 and is used to construct an accident database based on historical accident scenarios and accident attributes, wherein the accident database at least includes historical accident scenarios and multiple solution strategies corresponding to the historical accident scenarios;

[0131] A data set differentiation module 403, connected to the accident database construction module 402, is used for, when the accident attribute includes an effective dose equivalent, dividing the accident database into two categories based on the effective dose equivalent to obtain two types of data sets;

[0132] The accident scenario library building module 404 is connected to the data set differentiation module 403 and is used to cluster the two types of data sets based on the historical accident scenarios to obtain two accident scenario libraries corresponding to the two types of data sets, wherein both accident scenario libraries at least include accident scenarios and multiple solution strategies corresponding to the accident scenarios;

[0133] The current acquisition module 405 is connected to the accident scenario library building module 404 and is used to acquire the current accident scenario;

[0134] A similarity analysis module 406, connected to the current acquisition module 405, is used to perform similarity analysis based on the current accident scenario and the accident scenarios in the two accident scenario libraries to obtain a global similarity;

[0135] The strategy determination module 407 is connected to the similarity analysis module 406 and is used to determine the target solution strategy corresponding to the current accident scenario based on the global similarity.

[0136] It should be noted that the above modules can be implemented by software or hardware. For example, for the latter, it can be implemented in the following ways: the above modules can be located in the same processor; or the above modules can be located in different processors in any combination.

[0137] It should be noted that the above-mentioned historical acquisition module 401, accident database construction module 402, data set distinction module 403, accident scenario library construction module 404, current acquisition module 405, similarity analysis module 406 and strategy determination module 407 correspond to steps S102 to S114 in the embodiment, and the examples and application scenarios implemented by the above-mentioned modules and corresponding steps are the same, but are not limited to the contents disclosed in the above-mentioned embodiment. It should be noted that the above-mentioned modules can be run in a computer terminal as part of the device.

[0138] It should be noted that the optional or preferred implementation of this embodiment can refer to the relevant description in the embodiment, which will not be repeated here.

[0139] The above-mentioned nuclear emergency decision support device based on accident scenarios may also include a processor and a memory. The above-mentioned history acquisition module 401, accident database construction module 402, data set differentiation module 403, accident scenario library construction module 404, current acquisition module 405, similarity analysis module 406 and strategy determination module 407 are all stored in the memory as program modules, and the processor executes the above-mentioned program modules stored in the memory to realize corresponding functions.

[0140] The processor includes a kernel, which retrieves the corresponding program module from the memory. The kernel may be one or more. The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. The memory includes at least one memory chip.

[0141] According to an embodiment of the present application, an embodiment of a non-volatile storage medium is also provided. Optionally, in this embodiment, the non-volatile storage medium includes a stored program, wherein when the program is running, the device where the non-volatile storage medium is located is controlled to execute any of the above-mentioned nuclear emergency decision support methods based on accident scenarios.

[0142] Optionally, in this embodiment, the non-volatile storage medium may be located in any computer terminal in a computer terminal group in a computer network, or in any mobile terminal in a mobile terminal group, and the non-volatile storage medium includes a stored program.

[0143] Optionally, when the program is running, the device where the non-volatile storage medium is located is controlled to perform the following functions: obtaining historical accident scenarios, wherein the historical accident scenarios include accident attributes; constructing an accident database based on the historical accident scenarios and the accident attributes, wherein the accident database at least includes historical accident scenarios and a variety of solution strategies corresponding to the historical accident scenarios; when the accident attributes include effective dose equivalents, the accident database is divided into two categories based on the effective dose equivalent to obtain two types of data sets; based on the historical accident scenarios, the two types of data sets are clustered respectively to obtain two accident scenario libraries corresponding to the two types of data sets, wherein both accident scenario libraries include at least accident scenarios and a variety of solution strategies corresponding to the accident scenarios; obtaining the current accident scenario; performing similarity analysis between the current accident scenario and the accident scenarios in the two accident scenario libraries to obtain a global similarity; based on the global similarity, determining the target solution strategy corresponding to the current accident scenario.

[0144] According to an embodiment of the present application, an embodiment of a processor is also provided. Optionally, in this embodiment, the processor is used to run a program, wherein when the program is run, any one of the above-mentioned nuclear emergency decision support methods based on accident scenarios is executed.

[0145] According to an embodiment of the present application, an embodiment of a computer program product is also provided. Optionally, in this embodiment, the computer program product includes a computer program, which, when executed by a processor, implements any of the steps of the nuclear emergency decision support method based on accident scenarios.

[0146] Optionally, the above-mentioned computer program product, when executed on a data processing device, is suitable for executing a program that initializes the following method steps: obtaining historical accident scenarios, wherein the historical accident scenarios include accident attributes; constructing an accident database based on the historical accident scenarios and accident attributes, wherein the accident database at least includes historical accident scenarios and a variety of solution strategies corresponding to the historical accident scenarios; when the accident attributes include effective dose equivalents, dividing the accident database into two categories based on the effective dose equivalent to obtain two types of data sets; based on the historical accident scenarios, clustering the two types of data sets respectively to obtain two accident scenario libraries corresponding to the two types of data sets, wherein both accident scenario libraries include at least accident scenarios and a variety of solution strategies corresponding to the accident scenarios; obtaining the current accident scenario; performing similarity analysis between the current accident scenario and the accident scenarios in the two accident scenario libraries to obtain a global similarity; and determining the target solution strategy corresponding to the current accident scenario based on the global similarity.

[0147] An embodiment of the present invention provides an electronic device, which includes a processor, a memory, and a program stored in the memory and executable on the processor, wherein the processor implements the following steps when executing the program: obtaining historical accident scenarios, wherein the historical accident scenarios include accident attributes; constructing an accident database based on the historical accident scenarios and the accident attributes, wherein the accident database at least includes historical accident scenarios and a plurality of solution strategies corresponding to the historical accident scenarios; when the accident attributes include an effective dose equivalent, dividing the accident database into two categories based on the effective dose equivalent to obtain two types of data sets; clustering the two types of data sets based on the historical accident scenarios to obtain two accident scenario libraries corresponding to the two types of data sets, wherein both accident scenario libraries at least include accident scenarios and a plurality of solution strategies corresponding to the accident scenarios; obtaining a current accident scenario; performing similarity analysis between the current accident scenario and the accident scenarios in the two accident scenario libraries to obtain a global similarity; and determining a target solution strategy corresponding to the current accident scenario based on the global similarity.

[0148] The above sequence of the embodiments of the present invention is for description only and does not represent the superiority or inferiority of the embodiments.

[0149] In the above embodiments of the present invention, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0150] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of the above modules can be a logical function division. There may be other division methods in actual implementation, such as multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, modules or indirect coupling or communication connection of modules, which can be electrical or other forms.

[0151] The modules described above as separate components may or may not be physically separated, and the components shown as modules may or may not be physical modules, that is, they may be located in one place or distributed on multiple modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the present embodiment.

[0152] In addition, each functional module in each embodiment of the present invention may be integrated into one processing module, or each module may exist physically separately, or two or more modules may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of software functional modules.

[0153] If the above-mentioned integrated module is implemented in the form of a software function module and sold or used as an independent product, it can be stored in a computer-readable non-volatile storage medium. Based on this understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a non-volatile storage medium, including a number of instructions to enable a computer device (which can be a personal computer, server or network device, etc.) to perform all or part of the steps of the various embodiments of the present invention. The aforementioned non-volatile storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, magnetic disk or optical disk and other media that can store program codes.

[0154] The above are only preferred embodiments of the present invention. It should be pointed out that, for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A nuclear emergency decision support method based on accident scenarios, characterized in that: include: Acquire historical accident scenarios, wherein the historical accident scenarios include accident attributes; Based on the historical accident scenarios and the accident attributes, construct an accident database, wherein the accident database at least includes the historical accident scenarios and a plurality of solution strategies corresponding to the historical accident scenarios; In the case where the accident attribute includes an effective dose equivalent, the accident database is divided into two categories based on the effective dose equivalent to obtain two types of data sets; Based on the historical accident scenarios, clustering the two types of data sets respectively to obtain two accident scenario libraries corresponding to the two types of data sets respectively, wherein the two accident scenario libraries each include at least accident scenarios and multiple solution strategies corresponding to the accident scenarios; Get the current accident scenario; Performing similarity analysis based on the current accident scenario and the accident scenarios in the two accident scenario libraries to obtain a global similarity; Based on the global similarity, a target resolution strategy corresponding to the current accident scenario is determined.

2. The nuclear emergency decision support method based on accident scenarios according to claim 1 is characterized in that: In the case where the historical accident scenarios include multiple ones, constructing an accident database based on the historical accident scenarios and the accident attributes includes: Based on any one of the plurality of historical accident scenarios, constructing a case binary function, wherein the case binary function is used to indicate the relationship between the historical accident scenario, the direction range of the historical accident scenario, and the accident attribute corresponding to the historical accident scenario; Based on the case binary function, a strategy model is constructed, wherein the strategy model is used to indicate the response strategy corresponding to the trend of the historical accident scenario; Performing a possibility analysis on the historical accident scenarios and the strategy model generation strategy, and determining the historical accident scenarios with a possibility higher than a preset threshold and the corresponding generation strategy; The historical accident scenarios with a probability higher than a preset threshold and the corresponding generation strategies are determined to construct the accident database.

3. The nuclear emergency decision support method based on accident scenarios according to claim 2 is characterized in that: Based on any one of the multiple historical accident scenarios, a case binary function is constructed, including: The multiple historical accident scenarios are divided into multiple stages according to the timeline, wherein each of the historical accident scenarios corresponds to the multiple stages, and the multiple stages at least include a stage before radioactive release, a stage of radioactive release, a stage of radioactive transport, and a long-term stage after the accident; Based on the interaction of the multiple stages, multiple accident cases are obtained, wherein the multiple accident cases are used to indicate the accident occurrence trend obtained after any stage of the multiple stages changes; Based on any one of the multiple accident cases, a case binary function is constructed, wherein the case binary function is used to indicate the relationship between the accident case, the trend range of the accident case, and the accident attribute corresponding to the accident case.

4. The nuclear emergency decision support method based on accident scenarios according to claim 2 is characterized in that: The constructing of a strategy model based on the case binary function includes: Based on the case binary function, an accident description model is constructed, wherein the accident description model is used to indicate the trend of the accident cases in chronological order; Based on the accident description model, determining a plurality of actions to resolve the accident case; Sorting multiple actions of the accident case to obtain multiple solution strategies; Build a strategic model based on multiple solution strategies.

5. The nuclear emergency decision support method based on accident scenarios according to claim 3 is characterized in that: The possibility analysis of the historical accident scenarios and the strategy model generation strategy to determine the historical accident scenarios with a possibility higher than a preset threshold and the corresponding generation strategy includes: Determine the probability of occurrence of the multiple accident cases to obtain a first probability; When the first possibility is greater than the preset threshold, determining the possibilities corresponding to the multiple solution strategies generated by the strategy model based on the accident case, and obtaining a second possibility; When the second possibility is greater than a preset threshold, a historical accident scenario with a possibility higher than the preset threshold and a corresponding generation strategy are determined.

6. The nuclear emergency decision support method based on accident scenarios according to claim 1 is characterized in that: In the case where the accident attribute includes an effective dose equivalent, the accident database is divided into two categories based on the effective dose equivalent to obtain two types of data sets, including: One of the two types of data sets is that the effective dose equivalent is greater than or equal to 50 millisieverts, and the other is that the effective dose equivalent is less than 50 millisieverts.

7. The nuclear emergency decision support method based on accident scenarios according to claim 1 is characterized in that: In the case where the historical accident scenarios include multiple ones, clustering the two types of data sets based on the historical accident scenarios to obtain two accident scenario libraries corresponding to the two types of data sets respectively includes: Based on data mining, any historical accident scenarios are selected in sequence from the plurality of historical accident scenarios corresponding to the two types of data sets; Based on the arbitrary historical accident scenario, the two types of data sets are clustered respectively using the mean shift method; The mean shift method clusters the two types of data sets respectively by determining the centroid and radius of the arbitrary historical accident scenario.

8. The nuclear emergency decision support method based on accident scenarios according to claim 1 is characterized in that: The similarity analysis based on the current accident scenario and the accident scenarios in the two accident scenario libraries is performed to obtain a global similarity, including: Acquire the accident attributes corresponding to the current accident scenario and the accident attributes included in the two accident scenario libraries; Calculating the local similarity between the accident attribute corresponding to the current accident scenario and the accident attributes included in the two accident scenario libraries; Based on a preset weight value, the local similarities are integrated to obtain the global similarity.

9. The nuclear emergency decision support method based on accident scenarios according to claim 8, characterized in that: Determining a target solution strategy corresponding to the current accident scenario based on the global similarity includes: Based on the global similarity, determining that the current accident scenario belongs to one of the two accident scenario libraries; Based on the local similarity, determining that the current accident scenario corresponds to a historical accident scenario in an accident scenario library; Based on the global similarity and the local similarity, determining a plurality of initial solution strategies corresponding to historical accident scenarios similar to the current accident scenario; Performing feasibility analysis on the multiple initial solution strategies to obtain a feasibility ranking list of the multiple initial solution strategies; Based on the feasibility ranked list, a target resolution strategy corresponding to the current accident scenario is determined.

10. The nuclear emergency decision support method based on accident scenarios according to claim 1, characterized in that: The method further comprises: When the global similarity is lower than a preset similarity, the current accident scenario is taken as a historical accident scenario and stored in a corresponding accident scenario library of the two accident scenario libraries.

11. A nuclear emergency decision support device based on accident scenarios, characterized in that: include: A history acquisition module, used to acquire historical accident scenarios, wherein the historical accident scenarios include accident attributes; An accident database construction module is used to construct an accident database based on the historical accident scenarios and the accident attributes, wherein the accident database at least includes the historical accident scenarios and multiple solution strategies corresponding to the historical accident scenarios; a data set differentiation module, used for, when the accident attribute includes an effective dose equivalent, dividing the accident database into two categories based on the effective dose equivalent to obtain two categories of data sets; Constructing an accident scenario library module, which is used to cluster the two types of data sets respectively based on the historical accident scenarios to obtain two accident scenario libraries corresponding to the two types of data sets, wherein the two accident scenario libraries each include at least accident scenarios and multiple solution strategies corresponding to the accident scenarios; The current acquisition module is used to obtain the current accident scenario; A similarity analysis module, used to perform similarity analysis based on the current accident scenario and the accident scenarios in the two accident scenario libraries to obtain a global similarity; A strategy determination module is used to determine a target solution strategy corresponding to the current accident scenario based on the global similarity.

12. A non-volatile storage medium, characterized in that: The non-volatile storage medium stores a plurality of instructions, and the instructions are suitable for being loaded by a processor and executing a nuclear emergency decision support method based on an accident scenario as described in any one of claims 1 to 10.

13. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of a nuclear emergency decision support method based on an accident scenario as described in any one of claims 1 to 10 are implemented.

Images