Fire emergency management method and system

Abstract

The invention provides a fire-fighting emergency management method and system, and the method comprises the steps: carrying out the feature extraction of multi-modal data of a fire-fighting supervision region, and obtaining fire abnormality feature data; calculating a rule similarity between the fire anomaly feature data and feature data of a preset rule base to obtain at least one regular fire protection scheme; calculating case similarity between the fire anomaly feature data and feature data of a historical case library to obtain at least one case fire-fighting scheme; analyzing the at least one regular fire-fighting scheme and the at least one case fire-fighting scheme to obtain a plurality of candidate fire-fighting schemes; and on the basis of an NSGA-II algorithm, under a preset constraint condition, performing optimization solution on the plurality of candidate fire-fighting schemes to obtain a target fire-fighting scheme, thereby realizing a hybrid reasoning mechanism based on a historical case library and a rule library, enabling the obtained target fire-fighting scheme to be more accurate and reliable, improving rescue efficiency, and reducing a resource waste phenomenon.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent fire protection, and particularly to a fire emergency management method and system. Background Art

[0002] With the acceleration of the urbanization process and the increase in the density of various buildings, fire safety has become an important link that cannot be ignored in urban management.

[0003] Traditional pre - plan libraries rely on manually preset plans and cannot dynamically adapt to complex fire situation changes. That is, most traditional fire protection plans still remain at the level of static pre - plans and simple data collection, lacking dynamic analysis of environmental data. In this way, when a fire occurs, it is impossible to accurately formulate a fire protection plan, resulting in low rescue efficiency and resource waste. Summary of the Invention

[0004] The present invention provides a fire emergency management method and system to solve the defects of low rescue efficiency and resource waste in the prior art.

[0005] On the one hand, the present invention provides a fire emergency management method, which includes: Extract features from the multi - modal data of the fire supervision area to obtain fire anomaly feature data; Calculate the rule similarity between the fire anomaly feature data and the feature data of the preset rule library to obtain at least one rule - based fire protection plan; Calculate the case similarity between the fire anomaly feature data and the feature data of the historical case library to obtain at least one case - based fire protection plan; Analyze the at least one rule - based fire protection plan and the at least one case - based fire protection plan to obtain multiple candidate fire protection plans; Based on the NSGA - II algorithm, under the preset constraint conditions, perform optimization solution on the multiple candidate fire protection plans to obtain the target fire protection plan.

[0006] According to the fire emergency management method provided by the present invention, analyzing the at least one rule - based fire protection plan and the at least one case - based fire protection plan to obtain multiple candidate fire protection plans includes: Detect whether there is a conflict between the i - th rule - based fire protection plan and the j - th case - based fire protection plan; i = 1, 2, …, n, j = 1, 2, …, m, where n is the total number of rule - based fire protection plans and m is the total number of case - based fire protection plans; If there is a conflict, determine the weight of the i-th rule fire protection plan and the weight of the j-th case fire protection plan according to the rule similarity of the i-th rule fire protection plan, the timeliness of the i-th rule fire protection plan, the case similarity of the j-th case fire protection plan, the timeliness of the j-th case fire protection plan, the success rate of the j-th case fire protection plan, and the scene information of the fire supervision area; If the weight of the i-th rule fire protection plan is greater than the weight of the j-th case fire protection plan, use the i-th rule fire protection plan as a candidate fire protection plan; If the weight of the i-th rule fire protection plan is less than or equal to the weight of the j-th case fire protection plan, use the j-th case fire protection plan as a candidate fire protection plan.

[0007] According to a fire emergency management method provided by the present invention, the scene information of the fire supervision area includes scene complexity and scene flexibility; Determine the weight of the i-th rule fire protection plan and the weight of the j-th case fire protection plan according to the rule similarity of the i-th rule fire protection plan, the timeliness of the i-th rule fire protection plan, the case similarity of the j-th case fire protection plan, the timeliness of the j-th case fire protection plan, the success rate of the j-th case fire protection plan, and the scene information of the fire supervision area, including: Calculate the first product of the rule similarity of the i-th rule fire protection plan and the timeliness of the i-th rule fire protection plan; Calculate the second product of the case similarity of the j-th case fire protection plan, the timeliness of the j-th case fire protection plan, and the success rate of the j-th case fire protection plan; Calculate the first ratio of the first product to the second product, and the second ratio of the second product to the first product; Calculate the third product of the scene complexity and the complexity coefficient, and the fourth product of the scene flexibility and the flexibility coefficient; Use the sum of the first ratio and the third product as the weight of the i-th rule fire protection plan; Use the sum of the second ratio and the fourth product as the weight of the j-th case fire protection plan.

[0008] According to a fire emergency management method provided by the present invention, it further includes: If there is no conflict, use the i-th rule fire protection plan as a candidate fire protection plan among the multiple candidate fire protection plans, and use the j-th case fire protection plan as a candidate fire protection plan among the multiple candidate fire protection plans; Based on the i-th rule fire protection plan and the j-th case fire protection plan, amplify p candidate fire protection plans.

[0009] A fire emergency management method provided by the present invention, based on the i-th rule-based fire protection plan and the j-th case-based fire protection plan, amplifies p candidate fire protection plans, including: Determine the different fire protection means between the i-th rule-based fire protection plan and the j-th case-based fire protection plan; Taking the i-th rule-based fire protection plan as the amplification benchmark, add the different fire protection means one by one to obtain the p candidate fire protection plans.

[0010] A fire emergency management method provided by the present invention further includes: Compare the p candidate fire protection plans with other rule-based fire protection plans and other case-based fire protection plans to obtain a comparison result; If the comparison result indicates that they are all different, retain the p candidate fire protection plans; If the comparison result indicates that there are q identical fire protection plans, retain r candidate fire protection plans, where r is the difference between p and q.

[0011] A fire emergency management method provided by the present invention further includes: Based on the digital twin model of the fire supervision area, use the target fire protection plan to conduct fire drills to obtain a drill result; If the accuracy rate of the drill result is greater than a preset threshold, send the target fire protection plan to the terminal of the fire supervision personnel.

[0012] A fire emergency management method provided by the present invention further includes: If the accuracy rate of the drill result is less than or equal to the preset threshold, adjust the target fire protection plan until the accuracy rate of the drill result is greater than the preset threshold to obtain a final fire protection plan, and send the final fire protection plan to the terminal of the fire supervision personnel.

[0013] On the other hand, the present invention also provides a fire emergency management system, which includes: An extraction module, configured to fuse and extract features from multi-modal data in the fire supervision area to obtain fire anomaly feature data; A calculation module, configured to calculate the rule similarity between the fire anomaly feature data and the feature data in the preset rule library to obtain at least one rule-based fire protection plan; and calculate the case similarity between the fire anomaly feature data and the feature data in the historical case library to obtain at least one case-based fire protection plan; An analysis module, configured to analyze the at least one rule-based fire protection plan and the at least one case-based fire protection plan to obtain a plurality of candidate fire protection plans; An optimization solution module, configured to perform optimization solution on the multiple candidate fire protection plans under preset constraint conditions based on the NSGA-II algorithm to obtain a target fire protection plan.

[0014] On the other hand, the present invention further provides an electronic device, which includes a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the program, the fire emergency management method described in any one of the above is implemented.

[0015] On the other hand, the present invention further provides a non-transitory computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the fire emergency management method described in any one of the above is implemented.

[0016] On the other hand, the present invention further provides a computer program product, including a computer program. When the computer program is executed by a processor, the fire emergency management method described in any one of the above is implemented.

[0017] The fire emergency management method and system provided by the present invention extract features from multi-modal data in a fire supervision area to obtain fire anomaly feature data; calculate the rule similarity between the fire anomaly feature data and the feature data in a preset rule library to obtain at least one rule fire protection plan; calculate the case similarity between the fire anomaly feature data and the feature data in a historical case library to obtain at least one case fire protection plan; analyze the at least one rule fire protection plan and the at least one case fire protection plan to obtain multiple candidate fire protection plans; perform optimization solution on the multiple candidate fire protection plans under preset constraint conditions based on the NSGA-II algorithm to obtain a target fire protection plan, realizing a hybrid reasoning mechanism based on a historical case library and a rule library, making the obtained target fire protection plan more accurate and reliable, improving the rescue efficiency, and reducing the phenomenon of resource waste. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following will briefly introduce the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings in the following description are some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0019] Figure 1 is a flowchart of the fire emergency management method provided by an embodiment of the present invention; Figure 2 is a flowchart of determining candidate fire protection plans in an embodiment of the present invention; Figure 3 is a structural diagram of the fire emergency management system provided by an embodiment of the present invention; Figure 4 It is a schematic structural diagram of an electronic device provided by an embodiment of the present invention. Specific embodiments

[0020] To make the objectives, technical solutions and advantages of the present invention clearer, the technical solutions in the present invention will be clearly and completely described below with reference to the accompanying drawings in the present invention. Apparently, the described embodiments are some but not all of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in the present invention without making creative efforts shall fall within the protection scope of the present invention.

[0021] Figure 1 It is a schematic flowchart of a fire emergency management method provided by an embodiment of the present invention.

[0022] As Figure 1 shown, the execution subject of the fire emergency management method provided by an embodiment of the present invention may be an electronic device, and the method mainly includes the following steps: 101. Extract features from the multi-modal data of the fire supervision area to obtain fire abnormal feature data; In a specific implementation process, various sensors, third-party platforms, etc. obtain the multi-modal data of the fire supervision area, such as fire detection data, equipment status data, meteorological station data, etc. After obtaining this multi-modal data, the multi-modal data of the fire supervision area can be subjected to feature extraction to obtain fire abnormal feature data.

[0023] 102. Calculate the rule similarity between the fire abnormal feature data and the feature data in the preset rule library to obtain at least one rule fire protection plan; In a specific implementation process, in order to improve the accuracy of the fire protection plan decided, a rule library and a historical case library are preset in this embodiment. Among them, the rule library is a set of fire protection plans set based on expert experience, etc., and the historical case library is a set of case fire protection plans formed based on the fire protection plans adopted in historical fires. In this way, the reliability of the decision-making can be improved by combining case-based reasoning and rule-based reasoning.

[0024] Specifically, similarity algorithms such as cosine similarity can be used to calculate the rule similarity between the fire abnormal feature data and the feature data in the preset rule library to obtain at least one rule fire protection plan. Among them, a first similarity threshold can be set, and the fire protection plans greater than the first similarity threshold are selected as the rule fire protection plans.

[0025] 103. Calculate the case similarity between the fire abnormal feature data and the feature data in the historical case library to obtain at least one case fire protection plan; In a specific implementation process, similarity algorithms such as cosine similarity can also be used to calculate the case similarity between the fire anomaly feature data and the feature data in the historical case library, and at least one case fire protection plan is obtained. Among them, a second similarity threshold can be set, and the fire protection plans greater than the second similarity threshold are selected as the case fire protection plans. The second similarity threshold and the first similarity threshold can be the same or different, and the two similarity thresholds can be adjusted according to actual needs.

[0026] 104. Analyze the at least one rule-based fire protection plan and the at least one case fire protection plan to obtain multiple candidate fire protection plans; In a specific implementation process, after obtaining at least one rule-based fire protection plan and at least one case fire protection plan, although these plans are similar to the fire anomaly feature data in the fire supervision area, there may be some redundant plans, and the plans included may not be comprehensive enough, resulting in a relatively low accuracy rate when selecting the target fire protection plan subsequently. Therefore, in order to improve the accuracy rate of the target fire protection plan, the following technical solutions are provided in this embodiment: Specifically, it can be achieved through Figure 2 to implement step 104. Figure 2 is a schematic flowchart of the process for determining candidate fire protection plans in an embodiment of the present invention. As Figure 2 shown, the method may include the following steps: 201. Detect whether there is a conflict between the i-th rule-based fire protection plan and the j-th case fire protection plan; In a specific implementation process, semantic analysis and other technologies can be used to perform semantic recognition on the i-th rule-based fire protection plan and the j-th case fire protection plan, and based on the recognition results, determine whether there is a conflict between the i-th rule-based fire protection plan and the j-th case fire protection plan. Among them, i = 1, 2,... n, j = 1, 2,... m, n is the total number of rule-based fire protection plans, and m is the total number of case fire protection plans.

[0027] For example, if the i-th rule-based fire protection plan requires that drones are prohibited from taking off when the wind speed > 10 m / s, and the j-th case fire protection plan uses drones to drop bombs at low altitude when the wind speed is 12 m / s, in this case, it indicates that there is a conflict between the two. If the i-th rule-based fire protection plan requires that drones are prohibited from taking off when the wind speed > 10 m / s, and the j-th case fire protection plan does not use drones to drop bombs at low altitude when the wind speed is 12 m / s, in this case, it indicates that there is no conflict between the two.

[0028] 202. If there is a conflict, determine the weight of the \(i\)-th rule-based fire protection plan and the weight of the \(j\)-th case-based fire protection plan according to the rule similarity of the \(i\)-th rule-based fire protection plan, the timeliness of the \(i\)-th rule-based fire protection plan, the case similarity of the \(j\)-th case-based fire protection plan, the timeliness of the \(j\)-th case-based fire protection plan, the success rate of the \(j\)-th case-based fire protection plan, and the scene information of the fire supervision area. In a specific implementation process, if there is a conflict between the \(i\)-th rule-based fire protection plan and the \(j\)-th case-based fire protection plan, it indicates the existence of redundant plans. At this time, the weight of the \(i\)-th rule-based fire protection plan and the weight of the \(j\)-th case-based fire protection plan can be determined according to the rule similarity of the \(i\)-th rule-based fire protection plan, the timeliness of the \(i\)-th rule-based fire protection plan, the case similarity of the \(j\)-th case-based fire protection plan, the timeliness of the \(j\)-th case-based fire protection plan, the success rate of the \(j\)-th case-based fire protection plan, and the scene information of the fire supervision area. Among them, the similarity of various fire protection plans mentioned above can measure the degree of coincidence between the current fire situation characteristics and the triggering conditions, the timeliness of various fire protection plans can measure the practicality and universality of fire protection, and the success rate of various fire protection plans can reflect the accuracy of the fire protection plan. Among them, the timeliness of various fire protection plans can be determined by the time tag of each fire protection plan, calculate the time from the current moment, and then use the ratio of 1 to this time as the timeliness.

[0029] In a specific implementation process, the scene information of the fire supervision area includes scene complexity and scene flexibility. Among them, scene complexity can include multiple dimensions such as the risk level of the scene, environmental constraints, and information uncertainty. Each dimension has corresponding indicators. For example, the indicators of the risk level include the fire level, potential number of casualties, etc., the indicators of environmental constraints can include space tightness, terrain complexity, etc., and the indicators of information uncertainty can include the speed of fire spread, unknownness of hazard sources, etc. Scene flexibility reflects the degree of tolerance of the scene to case adjustment and innovation. It can include dimensions such as environmental openness, resource deployability, and rule flexibility. Each dimension also includes its own indicators. For example, the indicators of environmental openness can include external interference factors (such as weather, traffic, etc.), space tightness, etc., the indicators of resource deployability can include equipment redundancy rate (such as the number of fire trucks), human flexibility (such as the number of personnel, personnel functions, etc.), and the indicators of rule flexibility can include the allowable trial-and-error space, etc. The scene complexity and scene flexibility can be obtained by weighted summation of various indicators.

[0030] In a specific implementation process, this step can be implemented in the following way: a1. Calculate the first product of the rule similarity of the \(i\)-th rule-based fire protection plan and the timeliness of the \(i\)-th rule-based fire protection plan; In a specific implementation process, the first product of the rule similarity of the \(i\)-th rule fire protection plan and the timeliness of the \(i\)-th rule fire protection plan can be calculated, and this first product can reflect the comprehensive matching degree of the \(i\)-th rule fire protection plan with the current scenario.

[0031] b1. Calculate the second product of the case similarity of the \(j\)-th case fire protection plan, the timeliness of the \(j\)-th case fire protection plan, and the success rate of the \(j\)-th case fire protection plan; In a specific implementation process, the second product of the case similarity of the \(j\)-th case fire protection plan, the timeliness of the \(j\)-th case fire protection plan, and the success rate of the \(j\)-th case fire protection plan can be calculated, and this first product can reflect the comprehensive matching degree of the \(j\)-th case fire protection plan with the current scenario.

[0032] c1. Calculate the first ratio of the first product to the second product, and the second ratio of the second product to the first product; Among them, the numerator of the first ratio highlights the advantages of the \(i\)-th rule fire protection plan itself and can balance the influence of the \(j\)-th case fire protection plan. The numerator of the second ratio highlights the advantages of the \(j\)-th case fire protection plan itself and can balance the influence of the \(i\)-th rule fire protection plan.

[0033] d1. Calculate the third product of the scenario complexity and the complexity coefficient, and the fourth product of the scenario flexibility and the flexibility coefficient; By calculating the third product of the scenario complexity and the complexity coefficient, the influence of the scenario complexity on the weight of the \(i\)-th rule fire protection plan can be amplified or reduced. By calculating the fourth product of the scenario flexibility and the flexibility coefficient, the influence of the scenario flexibility on the weight of the \(j\)-th case fire protection plan can be amplified or reduced. Among them, the complexity coefficient and the flexibility coefficient can be set according to actual needs.

[0034] e1. Take the sum value of the first ratio and the third product as the weight of the \(i\)-th rule fire protection plan; f1. Take the sum value of the second ratio and the fourth product as the weight of the \(j\)-th case fire protection plan.

[0035] Specifically, the above steps a1 to f1 can be implemented through the rule weight calculation formula (1) and the case weight calculation formula (2): (1) Among them, represents the weight of the \(i\)-th rule fire protection plan, represents the rule similarity of the \(i\)-th rule fire protection plan, represents the timeliness of the \(i\)-th rule fire protection plan, Denote the case similarity of the fire protection plan for the j-th case. Denote the timeliness of the fire protection plan for the j-th case. Denote the success rate of the fire protection plan for the j-th case. Denote the complexity coefficient. Denote the scenario complexity.

[0036] (2) Wherein, Denote the flexibility coefficient. Denote the scenario flexibility.

[0037] 203. Detect whether the weight of the fire protection plan of the i-th rule is greater than the weight of the fire protection plan of the j-th case. If so, execute step 20 five; if not, execute step 20 five. 204. Take the fire protection plan of the i-th rule as a candidate fire protection plan. In a specific implementation process, if the weight of the fire protection plan of the i-th rule is greater than the weight of the fire protection plan of the j-th case, then take the fire protection plan of the i-th rule as the standard and take the fire protection plan of the i-th rule as a candidate fire protection plan.

[0038] 205. Take the fire protection plan of the j-th case as a candidate fire protection plan.

[0039] If the weight of the fire protection plan of the i-th rule is less than the weight of the fire protection plan of the j-th case, then take the fire protection plan of the j-th case and take the fire protection plan of the j-th case as a candidate fire protection plan.

[0040] In this embodiment, through the above process, the conflicting rule fire protection plan and case fire protection plan can be detected, and by calculating the weights of the two, the fire protection plan with the larger weight is retained as the candidate fire protection plan, and the fire protection plan with the smaller weight is eliminated, so as to realize the cleaning of redundant fire protection plans.

[0041] In a specific implementation process, if there is no conflict between the fire protection plan of the i-th rule and the fire protection plan of the j-th case, then the fire protection plan of the i-th rule can be taken as a candidate fire protection plan among the multiple candidate fire protection plans, and, the fire protection plan of the j-th case can be taken as a candidate fire protection plan among the multiple candidate fire protection plans. In order to select the target fire protection plan more comprehensively, in this embodiment, p candidate fire protection plans are also amplified based on the fire protection plan of the i-th rule and the fire protection plan of the j-th case.

[0042] Specifically, through semantic recognition technology, the different fire-fighting means between the i-th rule fire-fighting plan and the j-th case fire-fighting plan can be determined; taking the i-th rule fire-fighting plan as the amplification benchmark, the different fire-fighting means are added one by one to obtain the p candidate fire-fighting plans. That is to say, the different fire-fighting means in the j-th case fire-fighting plan can be merged with the i-th rule fire-fighting plan one by one to obtain more candidate fire-fighting plans.

[0043] It should be noted that it is also possible to take the j-th case fire-fighting plan as the amplification benchmark, and add the different fire-fighting means one by one to obtain p candidate fire-fighting plans.

[0044] In a specific implementation process, when amplifying the fire-fighting plan by the above means, there may be cases where it is the same as other rule fire-fighting plans and other case fire-fighting plans. Therefore, the p candidate fire-fighting plans can also be compared with other rule fire-fighting plans and other case fire-fighting plans to obtain a comparison result; if the comparison result indicates that they are all different, the p candidate fire-fighting plans are retained; if the comparison result indicates that there are q identical fire-fighting plans, r candidate fire-fighting plans are retained, and r is the difference between p and q.

[0045] Through the amplification and comparison of the above methods, the candidate fire-fighting plans can be made more comprehensive, so that a more accurate target fire-fighting plan can be selected.

[0046] 105. Based on the NSGA-II algorithm, under the preset constraint conditions, optimize and solve the multiple candidate fire-fighting plans to obtain the target fire-fighting plan.

[0047] In a specific implementation process, the following constraint conditions can be set: Hard constraint: Personnel are not allowed to enter the fire spread area, that is, construct an objective function for maximizing personnel safety.

[0048] Soft constraint: Timeliness of each link, that is, construct an objective function for the shortest total fire-fighting duration.

[0049] Dynamic constraint: Real-time correction of equipment working parameters, that is, construct an objective function for the safe and reliable operation of the equipment.

[0050] Under this preset constraint condition, based on the NSGA-II algorithm, the multiple candidate fire-fighting plans can be optimized and solved to obtain the target fire-fighting plan. Among them, the process of solving by the NSGA-II algorithm can refer to the existing relevant technologies and will not be elaborated here.

[0051] The fire emergency management method of this embodiment extracts features from multi-modal data in the fire supervision area to obtain fire anomaly feature data; calculates the rule similarity between the fire anomaly feature data and the feature data in the preset rule library to obtain at least one rule fire fighting plan; calculates the case similarity between the fire anomaly feature data and the feature data in the historical case library to obtain at least one case fire fighting plan; analyzes the at least one rule fire fighting plan and the at least one case fire fighting plan to obtain multiple candidate fire fighting plans; and based on the NSGA-II algorithm, under the preset constraint conditions, optimizes and solves the multiple candidate fire fighting plans to obtain the target fire fighting plan, realizing a hybrid reasoning mechanism based on the historical case library and the rule library, making the obtained target fire fighting plan more accurate and reliable, improving the rescue efficiency, and reducing the phenomenon of resource waste.

[0052] In a specific implementation process, it is also possible to perform fire drills based on the digital twin model of the fire supervision area, using the target fire fighting plan, to obtain drill results; if the accuracy rate of the drill results is greater than the preset threshold, send the target fire fighting plan to the terminal of the fire supervision personnel; if the accuracy rate of the drill results is less than or equal to the preset threshold, adjust the target fire fighting plan until the accuracy rate of the drill results is greater than the preset threshold to obtain the final fire fighting plan, and send the final fire fighting plan to the terminal of the fire supervision personnel.

[0053] That is to say, it is possible to use digital twin technology to implement the drill of the target fire fighting plan, so as to provide a more reliable fire fighting plan for firefighters and improve the fire fighting efficiency.

[0054] Based on the same general inventive concept, the present invention also protects a fire emergency management system. The fire emergency management system provided by the present invention will be described below. The fire emergency management system described below can be mutually corresponding and referred to the fire emergency management method described above.

[0055] Figure 3 It is a schematic structural diagram of the fire emergency management system provided by the embodiment of the present invention. As Figure 3 shown, the fire emergency management system of this embodiment includes an extraction module 31, a calculation module 32, an analysis module 33, and an optimization and solution module 34.

[0056] Among them, the extraction module 31 is used to fuse and extract features from multi-modal data in the fire supervision area to obtain fire anomaly feature data; The calculation module 32 is used to calculate the rule similarity between the fire anomaly feature data and the feature data in the preset rule library to obtain at least one rule fire fighting plan; and calculate the case similarity between the fire anomaly feature data and the feature data in the historical case library to obtain at least one case fire fighting plan; An analysis module 33, configured to analyze the at least one regular fire protection plan and the at least one case fire protection plan to obtain a plurality of candidate fire protection plans; An optimization and solution module 34, configured to perform optimization and solution on the plurality of candidate fire protection plans under preset constraint conditions based on the NSGA-II algorithm to obtain a target fire protection plan.

[0057] Figure 4 FIG. is a schematic structural diagram of an electronic device provided by an embodiment of the present invention. The fire emergency management system may include: a processor 410, a communication interface 420, a memory 430, and a communication bus 440. Among them, the processor 410, the communication interface 420, and the memory 430 complete mutual communication through the communication bus 440. The processor 410 may call logic instructions in the memory 430 to execute the fire emergency management method.

[0058] In addition, when the logic instructions in the above-mentioned memory 430 are implemented in the form of software functional units and sold or used as an independent product, they may be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the present invention, in essence, or the part that makes a contribution to the prior art, or a part of this technical solution, may be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present invention. The foregoing storage medium includes: various media such as a USB flash drive, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a magnetic disk, or an optical disc that can store program codes.

[0059] On the other hand, the present invention also provides a computer program product. The computer program product includes a computer program. The computer program can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the fire emergency management method provided by the above-mentioned various methods.

[0060] On yet another aspect, the present invention also provides a non-transitory computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, it is implemented to execute the fire emergency management method provided by the above-mentioned various methods.

[0061] It should be noted that the relevant information that may be involved in the embodiments of the present application is all processed based on the legitimate, proper and necessary principles in strict accordance with the requirements of laws and regulations, for the reasonable purpose of the business scenario, and is related information actively provided by the user during the use of the product / service or generated due to the use of the product / service, as well as the relevant information obtained with the user's authorization.

[0062] The relevant information processed by this application will vary depending on the specific product / service scenario. It is subject to the specific scenario of the user's use of the product / service and may involve the user's account information, device information or other relevant information. This application will treat the user's personal information and its processing with a high degree of diligence. [[ID=%]]

[0063] This application attaches great importance to the security of relevant information and has taken security protection measures that meet industry standards and are reasonable and feasible to protect relevant information and prevent it from being accessed, publicly disclosed, used, modified, damaged or lost without authorization.

[0064] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. A person of ordinary skill in the art can understand and implement it without creative labor.

[0065] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a necessary general hardware platform, and of course also by hardware. Based on this understanding, the essence of the above technical solution, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0066] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit them. Although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments or equivalently replace some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A fire emergency management method, characterized in that, Including: Performing feature extraction on multi-modal data of a fire supervision area to obtain fire anomaly feature data; Calculating the rule similarity between the fire anomaly feature data and the feature data in a preset rule library to obtain at least one rule-based fire fighting plan; Calculating the case similarity between the fire anomaly feature data and the feature data in a historical case library to obtain at least one case-based fire fighting plan; Analyzing the at least one rule-based fire fighting plan and the at least one case-based fire fighting plan to obtain multiple candidate fire fighting plans; Based on the NSGA-II algorithm, under preset constraint conditions, performing optimization solution on the multiple candidate fire fighting plans to obtain a target fire fighting plan.

2. The fire emergency management method according to claim 1, wherein, Analyzing the at least one rule-based fire fighting plan and the at least one case-based fire fighting plan to obtain multiple candidate fire fighting plans, including: Detecting whether there is a conflict between the i-th rule-based fire fighting plan and the j-th case-based fire fighting plan; i = 1, 2, …, n, j = 1, 2, …, m, where n is the total number of rule-based fire fighting plans and m is the total number of case-based fire fighting plans; If there is a conflict, determining the weight of the i-th rule-based fire fighting plan and the weight of the j-th case-based fire fighting plan according to the rule similarity of the i-th rule-based fire fighting plan, the timeliness of the i-th rule-based fire fighting plan, the case similarity of the j-th case-based fire fighting plan, the timeliness of the j-th case-based fire fighting plan, the success rate of the j-th case-based fire fighting plan, and the scene information of the fire supervision area; If the weight of the i-th rule-based fire fighting plan is greater than the weight of the j-th case-based fire fighting plan, taking the i-th rule-based fire fighting plan as a candidate fire fighting plan; If the weight of the i-th rule-based fire fighting plan is less than or equal to the weight of the j-th case-based fire fighting plan, taking the j-th case-based fire fighting plan as a candidate fire fighting plan.

3. The fire emergency management method according to claim 2, characterized in that, The scene information of the fire supervision area includes scene complexity and scene flexibility; Determining the weight of the i-th rule-based fire fighting plan and the weight of the j-th case-based fire fighting plan according to the rule similarity of the i-th rule-based fire fighting plan, the timeliness of the i-th rule-based fire fighting plan, the case similarity of the j-th case-based fire fighting plan, the timeliness of the j-th case-based fire fighting plan, the success rate of the j-th case-based fire fighting plan, and the scene information of the fire supervision area, including: Calculating the first product of the rule similarity of the i-th rule-based fire fighting plan and the timeliness of the i-th rule-based fire fighting plan; Calculating the second product of the case similarity of the j-th case-based fire fighting plan, the timeliness of the j-th case-based fire fighting plan, and the success rate of the j-th case-based fire fighting plan; ​ ​ ​ ​ 4. The fire emergency management method according to claim 2, characterized in that, ​ If there is no conflict, the i-th rule-based fire protection plan is used as one of the multiple candidate fire protection plans, and the j-th case-based fire protection plan is used as one of the multiple candidate fire protection plans; Based on the i-th rule-based fire protection plan and the j-th case-based fire protection plan, p candidate fire protection plans are amplified.

5. The fire emergency management method according to claim 4, characterized in that, Based on the i-th rule-based fire protection plan and the j-th case-based fire protection plan, amplifying p candidate fire protection plans includes: Determine the different fire protection means between the i-th rule-based fire protection plan and the j-th case-based fire protection plan; Taking the i-th rule-based fire protection plan as the amplification benchmark, add the different fire protection means one by one to obtain the p candidate fire protection plans.

6. The fire emergency management method according to claim 4 or 5, characterized in that It also includes: Compare the p candidate fire protection plans with other rule-based fire protection plans and other case-based fire protection plans to obtain a comparison result; If the comparison result indicates that they are all different, retain the p candidate fire protection plans; If the comparison result indicates that there are q identical fire protection plans, retain r candidate fire protection plans, where r is the difference between p and q.

7. The fire emergency management method according to any one of claims 1 to 5, characterized in that, It also includes: Based on the digital twin model of the fire supervision area, use the target fire protection plan to conduct fire drills to obtain drill results; If the accuracy rate of the drill results is greater than the preset threshold, send the target fire protection plan to the terminal of the fire supervision personnel.

8. The fire emergency management method according to claim 7, characterized in that It also includes: If the accuracy rate of the drill results is less than or equal to the preset threshold, adjust the target fire protection plan until the accuracy rate of the drill results is greater than the preset threshold to obtain the final fire protection plan, and send the final fire protection plan to the terminal of the fire supervision personnel.

9. A fire emergency management system, characterized in that, It includes: An extraction module for fusing and extracting features from the multi-modal data of the fire supervision area to obtain fire anomaly feature data; A calculation module for calculating the rule similarity between the fire anomaly feature data and the feature data of the preset rule library to obtain at least one rule-based fire protection plan; and calculating the case similarity between the fire anomaly feature data and the feature data of the historical case library to obtain at least one case-based fire protection plan; An analysis module for analyzing the at least one rule-based fire protection plan and the at least one case-based fire protection plan to obtain multiple candidate fire protection plans; An optimization and solution module for optimizing and solving the multiple candidate fire protection plans based on the NSGA-II algorithm under the preset constraint conditions to obtain the target fire protection plan.

10. An electronic device, characterized in that, It includes a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the program, it implements the fire emergency management method according to any one of claims 1-8.

Images