Post-disaster decision scheme generation method based on case reasoning

Abstract

The invention discloses a case reasoning-based post-disaster decision scheme generation method, and relates to the technical field of disaster relief emergency decision. Comprising the following steps: establishing a historical case data and quantitative decision scheme library, establishing a post-disaster decision scheme framework, matching target cases by applying a case reasoning technology, selecting similar historical cases, and adopting the similar historical cases to quantify an emergency decision scheme. According to the method, response can be quickly started according to the decision framework, similar historical cases can be matched based on disaster information and disaster situation information, a targeted comprehensive decision scheme is further generated, decision scheme suggestions can be efficiently and accurately provided for decision makers, decision time is shortened, decision cost is reduced, and guidance is provided for post-disaster emergency management.

Description

Technical Field

[0001] The present invention relates to the technical field of disaster prevention and relief emergency decision-making, and more particularly to a method for generating a post-disaster decision-making plan based on case reasoning. Background Art

[0002] As China's urbanization rate gradually increases and the permanent urban population grows, disasters pose a greater threat to urban safety. Disasters not only threaten people's lives but also have a serious impact on economic development and social stability. In the face of sudden disasters, swift and effective emergency response, rational allocation of rescue forces, and efficient use of supplies are crucial to minimizing casualties and economic losses.

[0003] However, existing post-disaster decision-making techniques often rely on emergency response plans. These plans typically include qualitative descriptions of organizational systems, disaster classifications, and operational mechanisms, but lack in-depth analysis of historical cases. They also lack quantitative indicators in areas such as "team support," "material reserves and shelters," and "funding," limiting their application in emergency decision-making. A small number of researchers have employed case-based reasoning techniques to identify historical cases similar to target cases, but these techniques only address case matching. Research on how to systematically develop emergency response plans and extract detailed emergency response measures from historical cases for application in target cases remains inadequate. Improving the efficiency of emergency decision-making and the feasibility of decision-making plans are key issues that need to be addressed in post-disaster decision-making.

[0004] Therefore, it is an urgent problem for those skilled in the art to propose a method for generating post-disaster decision-making solutions based on case-based reasoning to solve the difficulties existing in the existing technology. Summary of the Invention

[0005] In view of this, the present invention provides a post-disaster decision-making plan generation method based on case reasoning, which is used to solve the problems of low emergency response efficiency and insufficiently detailed decision-making plans after a disaster. The method relies on the MATLAB computer system. First, historical disaster cases that have occurred in various countries and regions in the world in the past three decades are collected and summarized to form a historical case data and quantitative decision-making plan library; disaster emergency plans issued by national, provincial, prefectural and county governments are summarized to build a post-disaster decision-making plan framework; after a disaster occurs, the response level is judged according to the framework, and the responsibilities of different administrative levels are clarified; the historical case with the highest similarity to the target case is selected to obtain quantitative decision-making plans for personnel deployment, material allocation, and financial appropriation, thereby realizing the generation of post-disaster decision-making plans that integrate qualitative and quantitative plans, thereby improving rescue efficiency.

[0006] In order to achieve the above object, the present invention provides the following technical solutions:

[0007] A method for generating a post-disaster decision plan based on case-based reasoning includes the following steps:

[0008] S1. Summarize and aggregate historical case information and emergency decision-making plans, build a library of historical case data and quantitative decision-making plans, and store them in a table format in a storage module of the MATLAB computer system;

[0009] S2. Summarize and integrate the existing national, provincial, prefectural, and county-level disaster emergency plans and special plans, build a post-disaster decision-making plan framework, and store the post-disaster decision-making plan framework in the storage module of the MATLAB computer system;

[0010] S3. After a disaster occurs, based on population density and direct economic losses, the analysis and calculation module of the MATLAB computer system is used to call the disaster response level part of the post-disaster decision-making plan framework of the storage module to analyze and judge the disaster level and determine the response level;

[0011] S4, inputting the six attribute indicators of disaster intensity, disaster occurrence time, population density of the disaster area, number of injured, affected population and economic losses into the analysis and calculation module of the MATLAB computer system to perform similarity calculation;

[0012] S5. Enter the decision module and, based on the response level, initiate a Level I response, Level II response, Level III response, or Level IV response, calling the corresponding qualitative emergency response measures at different levels in the post-disaster decision-making plan framework of the storage module; based on the similarity calculation results, retrieve the historical case with the highest similarity to the target case from the historical case data and quantitative decision-making plan library of the storage module; revise the plan based on the situation of the target disaster and the experience of the decision-maker to form a comprehensive post-disaster decision-making plan that combines qualitative and quantitative methods, and output the comprehensive post-disaster decision-making plan in text form in the computer system;

[0013] S6. Enter the system update module to store and update the case information and quantitative decision-making plan of the target case to the historical case data and quantitative decision-making plan library in S1.

[0014] Optionally, the specific content of S1 is:

[0015] Collect disaster case information from various countries or regions over the past 30 years on the Global Disaster Information Platform, conduct web searches for historical cases, summarize quantitative decision-making solutions, and integrate the above information to build a historical case data and quantitative decision-making solution library;

[0016] The historical case data and quantitative decision-making solution library includes six types of disaster data: disaster intensity, disaster occurrence time, population density in the disaster area, number of injured, affected population and economic losses, as well as three types of quantitative decision-making data: personnel deployment, material allocation, and financial appropriation.

[0017] Optionally, personnel deployment is divided into dispatching experts, rescue personnel, and medical personnel; material allocation is divided into transporting tents, cotton-padded quilts, and folding beds; financial appropriations are divided into national appropriations and local appropriations; historical case data and quantitative decision-making solution libraries are stored in the storage module of the MATLAB computer system in tabular form.

[0018] Optionally, the specific content of S2 is:

[0019] Collect and integrate national, provincial, prefectural and county-level disaster emergency plans through the Ministry of Emergency Management and official government platforms to build a framework for post-disaster decision-making plans.

[0020] Optional, the specific content of S3 is:

[0021] When a disaster occurs, enter the number of casualties and direct economic losses in the MATLAB workspace, call the disaster response level part of the post-disaster decision-making plan framework in the storage module for analysis and judgment, and initiate Level I response, Level II response, Level III response, or Level IV response.

[0022] Optionally, the specific content of S4 is:

[0023] The six indicators are divided into numerical and non-numerical types. Formula (1) is used to calculate the similarity of numerical indicators, formula (2) is used to calculate the similarity of non-numerical indicators, and formula (3) is used to calculate the overall similarity.

[0024]

[0025] in, is the i-th attribute index of target case 0, is the i-th attribute index of historical case j, is the value of the i-th attribute index of target case 0, is the value of the attribute index of the i-th historical case j, max(i) is the maximum value of the index i in the current case and the historical case, min(i) is the minimum value of the index i in the current case and the historical case, Y0 is the target case 0, Y j For historical case j, ω i is the weight coefficient of the i-th attribute index, which is determined by the hierarchical analysis method.

[0026] Optionally, the specific content of S5 is:

[0027] Among them, emergency preparedness and support for Level I response include: team support, material reserves and shelter support, financial support, technical support, transportation and infrastructure support, and communication support;

[0028] Based on the similarity calculation results, the historical case with the highest similarity is selected in the MATLAB computer system, and the quantitative decision-making data of the historical case with the highest similarity is retrieved from the storage module. Personnel deployment is included in the team support aspect of the response measures, material allocation is included in the material reserve and shelter support aspect, and financial appropriation is included in the funding support aspect. According to the situation of the target disaster and the experience of decision makers, the plan is revised to form a comprehensive post-disaster decision-making plan that combines qualitative and quantitative methods, and the post-disaster comprehensive decision-making plan is output in text form in the MATLAB computer system.

[0029] Optionally, the specific content of S6 is:

[0030] Enter the system update module, save and update the case information and quantitative decision-making plan of the target case in a table format to the historical case data and quantitative decision-making plan library, ensure that the data in the historical case data and quantitative decision-making plan library are continuously updated and comprehensive, and provide database support for subsequent decision-making.

[0031] It can be seen from the above technical solutions that, compared with the prior art, the present invention discloses a method for generating a post-disaster decision-making solution based on case-based reasoning, which has the following beneficial effects:

[0032] 1) The present invention builds a post-disaster decision-making framework by extensively collecting disaster emergency plans and historical disaster cases. Based on case-based reasoning technology, similar historical cases are selected and quantitative decision-making plans are supplemented in the framework. A weight coefficient determination method based on the analytic hierarchy process is adopted to rationalize the attribute weight coefficients. A computer operating system is built to enable the computer to execute the functions of a post-disaster decision-making plan generation method based on case-based reasoning.

[0033] 2) This method not only takes into account the disposal measures of local emergency plans, but also refers to similar historical case decision-making plans based on disaster information and disaster situation information, so as to generate detailed disposal measures from the aspects of "team support, material reserves and shelter support, and financial support", assisting decision makers to initiate emergency response, reasonably allocate rescue forces, and efficiently activate materials, thereby reducing decision-making time and reducing decision-making costs, and solving the problems of low emergency response efficiency and insufficiently detailed decision-making plans after disasters. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are merely embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0035] Figure 1A flowchart of a method for generating a post-disaster decision-making plan based on case-based reasoning provided by the present invention;

[0036] Figure 2 A classification diagram of quantitative decision data provided by the present invention;

[0037] Figure 3 This is the architecture diagram of the decision-making system provided by the present invention. DETAILED DESCRIPTION

[0038] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0039] See also Figure 1 As shown, the present invention discloses a method for generating a post-disaster decision-making plan based on case-based reasoning, comprising the following steps:

[0040] S1. Summarize and aggregate historical case information and emergency decision-making plans, build a library of historical case data and quantitative decision-making plans, and store them in a table format in a storage module of the MATLAB computer system;

[0041] S2. Summarize and integrate the existing national, provincial, prefectural, and county-level disaster emergency plans and special plans, build a post-disaster decision-making plan framework, and store the post-disaster decision-making plan framework in the storage module of the MATLAB computer system;

[0042] S3. After a disaster occurs, based on population density and direct economic losses, the analysis and calculation module of the MATLAB computer system is used to call the disaster response level part of the post-disaster decision-making plan framework of the storage module to analyze and judge the disaster level and determine the response level;

[0043] S4, inputting the six attribute indicators of disaster intensity, disaster occurrence time, population density of the disaster area, number of injured, affected population and economic losses into the analysis and calculation module of the MATLAB computer system to perform similarity calculation;

[0044] S5. Enter the decision module and, based on the response level, initiate a Level I response, Level II response, Level III response, or Level IV response, calling the corresponding qualitative emergency response measures at different levels in the post-disaster decision-making plan framework of the storage module; based on the similarity calculation results, retrieve the historical case with the highest similarity to the target case from the historical case data and quantitative decision-making plan library of the storage module; revise the plan based on the situation of the target disaster and the experience of the decision-maker to form a comprehensive post-disaster decision-making plan that combines qualitative and quantitative methods, and output the comprehensive post-disaster decision-making plan in text form in the computer system;

[0045] S6. Enter the system update module to store and update the case information and quantitative decision-making plan of the target case to the historical case data and quantitative decision-making plan library in S1.

[0046] Furthermore, the specific content of S1 is:

[0047] Collect disaster case information from various countries or regions over the past 30 years on the Global Disaster Information Platform, conduct web searches for historical cases, including emergency management department documents and news reports, compile quantitative decision-making solutions, and integrate this information to build a database of historical case data and quantitative decision-making solutions;

[0048] The historical case data and quantitative decision-making solution library includes six types of disaster data: disaster intensity, disaster occurrence time, population density in the disaster area, number of injured, affected population and economic losses, as well as three types of quantitative decision-making data: personnel deployment, material allocation, and financial appropriation.

[0049] For further information, see Figure 2 As shown, personnel allocation is divided into dispatching experts, rescue personnel, and medical personnel; material allocation is divided into transporting tents, cotton-padded quilts, and folding beds; financial appropriations are divided into national appropriations and local appropriations; historical case data and quantitative decision-making solution libraries are stored in the storage module of the MATLAB computer system in tabular form.

[0050] Furthermore, the specific content of S2 is:

[0051] Collect and integrate national, provincial, prefectural and county-level disaster emergency plans through the Ministry of Emergency Management and official government platforms to build a framework for post-disaster decision-making plans.

[0052] Specifically, as shown in Table 1, the decision-making plan framework covers five parts: general principles, organizational command system and main responsibilities, disaster classification response, operating mechanism, and emergency preparedness and support. The general principles include the purpose of compilation, compilation basis, scope of application, and working principles. The organizational command system and main responsibilities include the provincial / municipal disaster relief headquarters and their responsibilities, the local disaster relief headquarters and their responsibilities, and the special working group and their responsibilities. The disaster classification response includes response classification and response classification. The operating mechanism includes monitoring, forecasting and early warning, disaster information reporting, advance disposal, and emergency response measures. Emergency preparedness and support includes team support, material reserves and shelter support, financial support, technical support, transportation and infrastructure support, and communication support.

[0053] Among them, in the disaster classification response, different levels of response will be initiated according to the two indicators of the number of casualties and direct economic losses: Level I response will be initiated when more than 300 casualties are caused or the direct economic losses account for 1% of the disaster area's GDP in the previous year; Level II response will be initiated when more than 50 but less than 300 casualties are caused or the direct economic losses account for 0.5% of the disaster area's GDP in the previous year; Level III response will be initiated when more than 10 but less than 50 casualties are caused or heavy economic losses are caused; Level IV response will be initiated when less than 10 casualties are caused or certain economic losses are caused. The disaster response level judgment method will be written into the MATLAB editor window in the form of code, and the above-mentioned post-disaster decision-making plan framework will be stored in the storage module of the MATLAB computer system.

[0054] Table 1 Decision-making system framework

[0055]

[0056]

[0057] Furthermore, the specific content of S3 is:

[0058] When a disaster occurs, enter the number of casualties and direct economic losses in the MATLAB workspace, call the disaster response level part of the post-disaster decision-making plan framework in the storage module for analysis and judgment, and initiate Level I response, Level II response, Level III response, or Level IV response.

[0059] Furthermore, the specific content of S4 is:

[0060] The six indicators are divided into numerical and non-numerical types. Formula (1) is used to calculate the similarity of numerical indicators, formula (2) is used to calculate the similarity of non-numerical indicators, and formula (3) is used to calculate the overall similarity.

[0061]

[0062] in, is the i-th attribute index of target case 0, is the i-th attribute index of historical case j, is the value of the i-th attribute index of target case 0, is the value of the attribute index of the i-th historical case j, max(i) is the maximum value of the index i in the current case and the historical case, min(i) is the minimum value of the index i in the current case and the historical case, Y0 is the target case 0, Y j For historical case j, ω i is the weight coefficient of the i-th attribute index, which is determined by the hierarchical analysis method.

[0063] Specifically, similarity calculation indicators are determined, namely disaster intensity, occurrence time, population density, number of injured, affected population, and economic losses; the above six indicators are divided into numerical and non-numerical types, among which disaster intensity, population density, number of injured, affected population, and economic losses are numerical indicators, and occurrence time is a non-numerical indicator, among which 8:00-20:00 is daytime, and 20:00-8:00 the next day is nighttime;

[0064] The numerical index uses formula (1) to calculate the similarity, where Y0, Y j represents the target case 0 and the historical case j, max(i) and min(i) represent the maximum and minimum values ​​of indicator i in the current and historical cases; non-numerical indicators are similarity calculated using formula (2), where Y0, Y j Represents target case 0 and historical case j. If the disaster time of target case 0 and historical case j is both during the day or at night, the similarity of the time index is 1. If the disaster time of target case 0 and historical case j is respectively during the day and late at night, the similarity of the time index is 0. The overall similarity between the target case and the historical case is calculated according to formula (3), where ω i The weight coefficient of the i-th attribute indicator is determined by the hierarchical analysis method. The specific process is as follows: the importance of the six attribute indicators is compared pairwise by domain experts, and scored according to the 1-9 scale. Then, a judgment matrix is ​​constructed and its consistency is tested. Then, the eigenvector corresponding to the maximum eigenvalue of the judgment matrix is ​​solved and normalized to obtain the weight coefficient ω of each attribute indicator. i .

[0065] Write formula (1) to formula (3) into the MATLAB editor window in code form. Input six data types of disaster intensity, occurrence time, population density, number of injured, affected population, and economic losses of the target case in the MATLAB workspace. By substituting the formulas and historical case data information for analysis and calculation, the overall similarity between the target case and all historical cases is obtained and output.

[0066] Furthermore, the specific content of S5 is:

[0067] Among them, emergency preparedness and support for Level I response include: team support, material reserves and shelter support, financial support, technical support, transportation and infrastructure support, and communication support;

[0068] Specifically, activate professional emergency rescue teams such as disaster emergency rescue, fire rescue, forest fire fighting, medical and health rescue, traffic rescue, and communication rescue, and equip them with necessary materials, equipment, and equipment; strengthen the construction of emergency material production, storage, allocation, and emergency distribution systems, ensure the production and supply of life relief materials, medical equipment, and medicines required for earthquake emergency work, and sign agreements with relevant production and operation enterprises to ensure the production and supply of emergency materials, daily necessities, and emergency equipment, set up emergency shelters according to local conditions, and make overall arrangements for necessary transportation, communications, water supply, power supply, sewage disposal, environmental protection, material reserves, and other equipment and facilities; local people's governments at or above the county level should include emergency relief funds in the fiscal budget at the same level to ensure them, and improve the emergency relief fund sharing mechanism in accordance with the principle of matching fiscal powers with expenditure responsibilities; build an applicable emergency command system and interconnect it with the superior emergency command system Intercommunication, establish a basic database that can fully reflect local realities, improve information collection and transmission channels, improve daily management systems and information processing methods, establish an emergency communication network system, and equip with satellite phones, walkie-talkies and other emergency communication facilities and equipment; establish a road, railway, aviation, and water transport emergency transportation guarantee system, strengthen unified command and dispatch, take necessary traffic control measures, establish an emergency rescue "green channel" mechanism, ensure that rescue teams, rescue equipment, medical personnel, disaster-stricken people, critically injured people and disaster relief supplies enter and exit the disaster area in a timely manner, strengthen the construction of power infrastructure and power dispatching systems, ensure temporary power supply for emergency equipment at the earthquake site and power supply in the disaster area; ensure smooth communication for disaster emergency rescue work, and immediately activate emergency satellite, shortwave, ultra-shortwave and other wireless communication systems and terminal equipment in extreme cases where basic communication networks and other infrastructure are severely damaged and difficult to repair in a short time.

[0069] Level II, III, and IV will activate some aspects of team support, material reserves and shelter support, financial support, technical support, transportation and infrastructure support, and communications support, and will reduce the requirements of various measures accordingly;

[0070] Based on the similarity calculation results, the historical case with the highest similarity is selected in the MATLAB computer system, and the quantitative decision-making data of the historical case with the highest similarity is retrieved from the storage module. Personnel deployment is included in the team support aspect of the response measures, material allocation is included in the material reserve and shelter support aspect, and financial appropriation is included in the funding support aspect. According to the situation of the target disaster and the experience of decision makers, the plan is revised to form a comprehensive post-disaster decision-making plan that combines qualitative and quantitative methods, and the post-disaster comprehensive decision-making plan is output in text form in the MATLAB computer system.

[0071] Furthermore, the specific content of S6 is:

[0072] Enter the system update module, save and update the case information and quantitative decision-making plan of the target case in a table format to the historical case data and quantitative decision-making plan library, ensure that the data in the historical case data and quantitative decision-making plan library are continuously updated and comprehensive, and provide database support for subsequent decision-making.

[0073] See also Figure 3 The following is the decision-making system architecture diagram.

[0074] In a specific embodiment:

[0075] This example generates an emergency decision-making plan for disaster case Y0. First, historical case information and quantitative decision-making plans are collected. The quantitative decision-making plans in the historical cases are refined according to the three aspects of personnel dispatch, financial appropriation, and material allocation. A historical case data and quantitative decision-making plan library is built and incorporated into the storage module of the computer operating system.

[0076] Furthermore, the disaster emergency plan is summarized to build a post-disaster decision-making framework, and the post-disaster decision-making framework and response level judgment indicators are included in the storage module. After the target disaster occurs, the number of casualties is 120 and the direct economic loss is 52136×10 3USD, according to the response level judgment index in MATLAB, the corresponding level III response is initiated. Further, as shown in Table 2, the six data of disaster level, occurrence time, population density in the disaster area, number of injured, affected population and economic losses are input, and different similarity calculation methods are used to calculate the local similarity of the six attribute indicators. The magnitude similarities between Y0 and historical cases Y1~Y7 are 0.857, 0.714, 0.571, 0.143, 0.857, 0.714, and 0.714. Similarly, the similarities of population density in the disaster area, number of injured, affected population and economic losses are calculated. The time similarities between Y0 and historical cases Y1~Y7 are 1, 1, 1, 1, 0, 1, and 0. According to the hierarchical analysis method, the weights of the six indicators were set as 0.15, 0.15, 0.25, 0.15, 0.15, and 0.15, respectively. The comprehensive similarity calculation method was used, and the overall similarity values ​​of Y0 and historical cases Y1 to Y7 were obtained as 0.886, 0.833, 0.399, 0.709, 0.391, 0.789, and 0.573, respectively. The historical case with the highest similarity between the computer system output and the target case was the magnitude 5.7 earthquake that occurred in Yao'an County, Yunnan Province on July 9, 2009.

[0077] Then, in the decision-making module, based on the Level III response, the provincial earthquake relief headquarters dispatched a working group, coordinated rescue forces to participate in the earthquake relief work, and guided the local government in the disaster area to carry out earthquake relief work. In addition to taking qualitative rescue measures, the most similar historical case quantitative plan was selected: dispatching a 1,000-person medical team, allocating a total of 9,500 tents, 3,000 cotton-padded quilts, and 1,000 pieces of colored cloth, with a central government grant of 38 million yuan and a provincial government grant of 20 million yuan. Based on actual conditions, the above quantitative information was revised and supplemented to the three parts of team support, material reserves and shelter support, and financial support.

[0078] Table 2 Attribute matching information between target cases and historical cases

[0079]

[0080] Finally, the output of the MATLAB decision system is a qualitative + quantitative comprehensive solution as follows:

[0081] Strengthen the development of professional emergency rescue teams, including disaster emergency rescue, fire rescue, forest fire fighting, medical and health rescue, traffic rescue, and communications rescue. Regularly carry out skills training, actively participate in emergency rescue drills, and it is recommended to dispatch 1,000 medical personnel.

[0082] Establish and improve an emergency material reserve network to ensure the production and supply of life-saving supplies, medical equipment, and medicines needed for disaster response. Sign agreements with relevant production and operation enterprises to ensure the production and supply of emergency materials, daily necessities, and emergency equipment. Set up emergency shelters according to local conditions, coordinate the arrangement of necessary transportation, communications, water supply, power supply, sewage disposal, environmental protection, and material reserves, and organize evacuation drills. It is recommended to allocate a total of 9,500 tents, 3,000 cotton-padded quilts, and 1,000 colored cloth strips.

[0083] In accordance with the principle of matching fiscal powers with expenditure responsibilities, the mechanism for sharing emergency relief funds will be improved. Funds for disaster emergency preparedness and emergency drills will be proposed by the emergency departments and included in the annual government fiscal budget after review by the financial departments at the same level. It is recommended that the central government allocate 38 million yuan and the provincial government allocate 20 million yuan.

[0084] The target case information and quantitative decision-making plan are saved and updated in the historical case data and quantitative decision-making plan library to provide database support for subsequent decision-making.

[0085] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.

[0086] The above description of the disclosed embodiments is intended to enable one skilled in the art to implement or use the present invention. Various modifications to these embodiments will be readily apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention is not limited to the embodiments shown herein but is intended to conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for generating post-disaster decision-making solutions based on case-based reasoning, characterized in that: The following steps are involved: S1. Summarize and aggregate historical case information and emergency decision-making plans, build a library of historical case data and quantitative decision-making plans, and store them in a table format in a storage module of the MATLAB computer system; S2. Summarize and integrate the existing national, provincial, prefectural, and county-level disaster emergency plans and special plans, build a post-disaster decision-making plan framework, and store the post-disaster decision-making plan framework in the storage module of the MATLAB computer system; S3. After a disaster occurs, based on population density and direct economic losses, the analysis and calculation module of the MATLAB computer system is used to call the disaster response level part of the post-disaster decision-making plan framework of the storage module to analyze and judge the disaster level and determine the response level; S4, inputting the six attribute indicators of disaster intensity, disaster occurrence time, population density of the disaster area, number of injured, affected population and economic losses into the analysis and calculation module of the MATLAB computer system to perform similarity calculation; S5. Enter the decision module and, based on the response level, initiate a Level I response, Level II response, Level III response, or Level IV response, calling the corresponding qualitative emergency response measures at different levels in the post-disaster decision-making plan framework of the storage module; based on the similarity calculation results, retrieve the historical case with the highest similarity to the target case from the historical case data and quantitative decision-making plan library of the storage module; revise the plan based on the situation of the target disaster and the experience of the decision-maker to form a comprehensive post-disaster decision-making plan that combines qualitative and quantitative methods, and output the comprehensive post-disaster decision-making plan in text form in the computer system; S6. Enter the system update module to store and update the case information and quantitative decision-making plan of the target case to the historical case data and quantitative decision-making plan library in S1.

2. The method for generating a post-disaster decision-making plan based on case-based reasoning according to claim 1, characterized in that: The specific contents of S1 are: Collect disaster case information from various countries or regions over the past 30 years on the Global Disaster Information Platform, conduct web searches for historical cases, summarize quantitative decision-making solutions, and integrate the above information to build a historical case data and quantitative decision-making solution library; The historical case data and quantitative decision-making solution library includes six types of disaster data: disaster intensity, disaster occurrence time, population density in the disaster area, number of injured, affected population and economic losses, as well as three types of quantitative decision-making data: personnel deployment, material allocation, and financial appropriation.

3. The method for generating a post-disaster decision-making plan based on case-based reasoning according to claim 2, characterized in that: Personnel allocation is divided into dispatching experts, rescue personnel, and medical personnel; material allocation is divided into transporting tents, cotton-padded quilts, and folding beds; financial appropriations are divided into national appropriations and local appropriations; historical case data and quantitative decision-making solution libraries are stored in tabular form in the storage module of the MATLAB computer system.

4. The method for generating a post-disaster decision-making plan based on case-based reasoning according to claim 1, characterized in that: The specific contents of S2 are: Collect and integrate national, provincial, prefectural and county-level disaster emergency plans through the Ministry of Emergency Management and official government platforms to build a framework for post-disaster decision-making plans.

5. The method for generating post-disaster decision-making solutions based on case-based reasoning according to claim 1, characterized in that: The specific contents of S3 are: When a disaster occurs, enter the number of casualties and direct economic losses in the MATLAB workspace, call the disaster response level part of the post-disaster decision-making plan framework in the storage module for analysis and judgment, and initiate Level I response, Level II response, Level III response, or Level IV response.

6. The method for generating a post-disaster decision-making plan based on case-based reasoning according to claim 1, characterized in that: The specific contents of S4 are: The six indicators are divided into numerical and non-numerical types. Formula (1) is used to calculate the similarity of numerical indicators, formula (2) is used to calculate the similarity of non-numerical indicators, and formula (3) is used to calculate the overall similarity. in, is the i-th attribute index of target case 0, is the i-th attribute index of historical case j, is the value of the i-th attribute index of target case 0, is the value of the attribute index of the i-th historical case j, max(i) is the maximum value of the index i in the current case and the historical case, min(i) is the minimum value of the index i in the current case and the historical case, Y0 is the target case 0, Y j For historical case j, ω i is the weight coefficient of the i-th attribute index, which is determined by the hierarchical analysis method.

7. The method for generating post-disaster decision-making solutions based on case-based reasoning according to claim 3, characterized in that: The specific contents of S5 are: Among them, emergency preparedness and support for Level I response include: team support, material reserves and shelter support, financial support, technical support, transportation and infrastructure support, and communication support; Based on the similarity calculation results, the historical case with the highest similarity is selected in the MATLAB computer system, and the quantitative decision-making data of the historical case with the highest similarity is retrieved from the storage module. Personnel deployment is included in the team support aspect of the response measures, material allocation is included in the material reserve and shelter support aspect, and financial appropriation is included in the funding support aspect. According to the situation of the target disaster and the experience of decision makers, the plan is revised to form a comprehensive post-disaster decision-making plan that combines qualitative and quantitative methods, and the post-disaster comprehensive decision-making plan is output in text form in the MATLAB computer system.

8. The method for generating post-disaster decision-making solutions based on case-based reasoning according to claim 1, characterized in that: The specific contents of S6 are: Enter the system update module, save and update the case information and quantitative decision-making plan of the target case in a table format to the historical case data and quantitative decision-making plan library, ensure that the data in the historical case data and quantitative decision-making plan library are continuously updated and comprehensive, and provide database support for subsequent decision-making.

Images