Big data intelligent decision analysis method and system based on machine learning

Abstract

The present invention relates to the technical field of data analysis, and specifically relates to a big data intelligent decision analysis method and system based on machine learning. The system comprises an interaction layer, an analysis layer, and a decision layer. Real-time position information of users and building parameters of an area where the users are located are captured by the interaction layer, and seismic information is synchronously collected by the interaction layer in real time; and the analysis layer receives the seismic information collected by the interaction layer in real time. In the present invention, on the basis of the real-time position information of the users and the seismic information, a better earthquake risk mitigation and maintenance effect is brought to the users, so as to ensure that an unorganized user population, when an earthquake strikes, can more orderly evacuate from a building on the basis of data provided by the system, thereby effectively improving the escape probability of indoor users when an earthquake strikes; and moreover, when indoor users cannot escape, data support is provided for rescue personnel in a position information feedback mode, so that rescue work can be carried out more efficiently, and a safety guarantee is further provided for the users.

Description

A big data intelligent decision analysis method and system based on machine learning Technical Field

[0001] The present invention relates to the field of data analysis technology, and in particular to a big data intelligent decision analysis method and system based on machine learning. Background Art

[0002] Earthquakes, also known as ground motions or seismic vibrations, are natural phenomena that generate seismic waves during the rapid release of energy from the earth's crust.

[0003] Earthquakes are often accompanied by the collapse of houses, which poses a great threat to the lives of residents inside. With the development of technology, earthquake prediction technology has been developed to assist residents in evacuating in advance, but:

[0004] (1) When escaping, some residents may lose or reduce their ability to distinguish directions and correctly determine the escape target area due to tension and emotional excitement, which will affect the residents' escape probability to a certain extent when an earthquake occurs;

[0005] (2) Residents who were unable to escape were buried by the collapsed walls of houses caused by the earthquake. When waiting for rescue, most of them relied on passive search and rescue by search and rescue dogs or scientific and technological equipment. The trapped residents did not have the conditions to actively seek help. Technical issues

[0006] In response to the above-mentioned shortcomings of the prior art, the present invention provides a big data intelligent decision analysis method and system based on machine learning, which solves the technical problems raised in the above-mentioned background technology. Technical Solutions

[0007] To achieve the above objectives, the present invention is implemented through the following technical solutions:

[0008] First, a big data intelligent decision analysis system based on machine learning, including an interaction layer, an analysis layer, and a decision layer;

[0009] The user's real-time location information and building parameters in the user's area are captured through the interaction layer. Earthquake information is collected synchronously based on the interaction layer in real time. The analysis layer receives the real-time earthquake information collected by the interaction layer and triggers the operation of analyzing the safety zone based on the building parameters in the user's area based on the earthquake information. The decision layer receives the safety zone analyzed by the analysis layer in real time, further configures the safety zone based on the user's real-time location information captured by the interaction layer, and then feeds back the configured safety zone coordinates to the interaction layer.

[0010] The analysis layer includes a receiving module, a setting module and an analysis module. The receiving module is used to receive the user's real-time location information, building parameters of the user's area and earthquake information collected in real time in the interaction layer. The setting module is used to set a trigger threshold, apply the trigger threshold and compare it with the earthquake information received by the receiving module. The analysis module is triggered to run based on the comparison result. The analysis module is used to obtain the building parameters of the user's area received by the receiving module and analyze the safe area based on the building parameters of the user's area.

[0011] The analysis module is provided with a safety zone analysis logic. During the operation phase of the analysis module, the module identifies open areas based on regional building parameters, further applies the safety zone analysis logic to analyze each identified open area, and then uses the analysis results to confirm the safety area in the identified open areas.

[0012] Among them, the safety area confirmed in the analysis module is fed back to the decision-making layer in real time, and when feeding back to the decision-making layer, the specification parameters of the safety area and the mutual configuration of the corresponding safety area are synchronously fed back to the decision-making layer.

[0013] Furthermore, the interaction layer includes a capture module, an acquisition module, and a storage module. The capture module is used to capture the user's real-time location information and the building parameters of the user's area. The acquisition module is used to collect earthquake information in real time. The storage module is used to receive the user's real-time location information and the building parameters of the user's area captured by the capture module, build a regional building model based on the building parameters of the user's area, and store the captured user's real-time location information and regional building model.

[0014] Among them, the capture module and the collection module are installed in the format of a software APP in the mobile device held by each user of the system service. The collection module collects earthquake information in real time through the network in the mobile device held by the user. The earthquake information includes: earthquake source, earthquake source magnitude, estimated magnitude, earthquake arrival time, and earthquake end time. The estimated magnitude is the magnitude when the vibration generated by the earthquake source is transmitted to the user's location.

[0015] Furthermore, after obtaining the real-time location information of the user, the capture module confirms the user's area based on the location information of all users, and further captures the building parameters within the user's area. The building parameters include: the building's location coordinates, the building's interconnected road coordinates, the building's facade length, width and height, and the building's load-bearing structure material. When constructing the regional building model, the storage module applies the building's location coordinates, the building's interconnected road coordinates, and the building's facade length, width and height to complete the construction of the regional building model. The acquisition module runs to continuously obtain the user's real-time location information, and further performs the expansion of the regional building model based on the user's real-time location information. The user's real-time location information stored in the storage module only stores the latest captured user's real-time location information before the decision layer runs. After the decision layer runs, the user's real-time location information continuously captured by the capture module is continuously stored.

[0016] Furthermore, among the user's real-time location information, building parameters of the user's area, and earthquake information received by the receiving module, the user's real-time location information is derived from the storage module, the building parameters of the user's area are replaced by the building model of the area stored in the storage module, the earthquake information is derived from the acquisition module in the interaction layer, the trigger threshold set in the setting module is the safe magnitude, and when the trigger threshold applied in the setting module is compared with the earthquake information received by the receiving module, the earthquake information received by the receiving module applied is the estimated magnitude;

[0017] The trigger threshold is expressed as: , x is the safety magnitude. If the estimated magnitude is not within the trigger threshold, the analysis module will be triggered to run. Otherwise, the receiving module will be jumped to run.

[0018] Furthermore, during the operation phase of the analysis module, the building parameters of the user's area are obtained. When analyzing the safety zone based on the building parameters of the user's area, the regional building model is simultaneously applied instead of the building parameters of the user's area. The safety zone analysis logic set in the analysis module is expressed as follows: Where: Safety points for open areas; It is a collection of adjacent buildings in an open area; is a constant; is the facade area of ​​the i-th building adjacent to the open area; is the length of the ground edge of the facade of the i-th building adjacent to the open area; Relatively in open areas Maximum span in parallel direction; is the maximum span of the open area; is the total number of adjacent buildings in the open area; is the total amount of adjacent roads in the open area; is the safety factor of the i-th building adjacent to the open area;

[0019] Among them, the constant The value range is: , and the higher the adjacent building in the open area, the constant The larger the value, the smaller the constant The smaller the value, the setting logic is that the building safety factor is set based on the building's load-bearing structural material. The better the seismic performance of the building's load-bearing structural material, the larger the building safety factor value. Conversely, the smaller the building safety factor value. The range of building safety factor values ​​is: , open area safety points The higher the value, the less safe the open area is, and vice versa.

[0020] Furthermore, in the open area identification stage, the analysis module traverses the regional building model, identifies all road areas and building areas in the regional building model, further segments and discards all road areas and building areas in the regional building model, and the remaining area is the open area identified by the analysis module;

[0021] The analysis module sets a safety zone determination threshold, an open area safety threshold, and After obtaining the safety zone threshold and the open area safety classification threshold, Comparison is performed to determine whether each open area is a safe area based on a safe area determination threshold. The specification parameters of the safe area are obtained from the regional building model. The specification parameters of the safe area include: safe area boundary coordinates and safe area area.

[0022] Furthermore, the decision layer includes a configuration module, a transmission module, and a positioning module. The configuration module is used to receive the security zone and security zone specification parameters analyzed by the analysis layer, and the real-time user location information stored in the storage module in the interaction layer, set the security zone and user configuration ratio, and complete the user and security zone configuration based on the security zone and user configuration ratio. The transmission module is used to receive the user and security zone configuration results from the configuration module and feed the configuration results back to the mobile device held by the user. The positioning module is used to obtain the user location information captured by the interaction layer in real time.

[0023] The ratio of the security area and user configuration set in the configuration module is expressed as: , It represents q users placed in every y square meters. When the configuration module performs user and security area configuration based on the security area to user configuration ratio, the security area specification parameters and the security area to user configuration ratio are applied to calculate the total number of configurable users in the security area. The users are further configured in the security area based on the real-time location information of the users and the total number of configurable users in the security area. When configuring users in the security area based on the real-time location information of the users, the closer the users are to the security area, the higher the configuration priority.

[0024] Furthermore, the positioning module receives earthquake information collected in the interactive layer in real time, obtains the earthquake end time in the earthquake information, refreshes the system operation after the earthquake end time arrives, controls the capture module in the interactive layer of the system to run, and compares the user's real-time location information captured by the capture module with the user and safety zone configuration results in the configuration module;

[0025] For users whose real-time location information is not in the safe area, the real-time location information is acquired and stored in the capture module by the positioning module in real time; for users whose real-time location information is in the safe area, the real-time location information is acquired and stored in the capture module by the positioning module after the capture module is controlled by the positioning module to capture the real-time location information, and the process ends.

[0026] Furthermore, the receiving module is interactively connected to the storage module through a wireless network, the storage module is electrically connected to the acquisition module and the capture module through a medium, the receiving module is electrically connected to the setting module and the analysis module through a medium, the analysis module is interactively connected to the configuration module through a wireless network, and the configuration module is electrically connected to the transmission module and the positioning module through a medium.

[0027] In a second aspect, a big data intelligent decision analysis method based on machine learning comprises the following steps:

[0028] S1: Obtain the user's real-time location information, set the user's area based on the user's real-time location information, capture the building parameters in the user's area, and build a regional building model based on the building parameters in the user's area;

[0029] S2: Applying the regional building model to identify safe areas in the user’s area;

[0030] S21: the stage of setting the security zone identification logic in the user's area;

[0031] S3: Collect earthquake information and configure a safe zone for users based on their real-time location information when an earthquake occurs;

[0032] S31: configuration logic setting stage for mutual configuration between users and security zones;

[0033] S4: Determine whether the user has reached a safe area based on the user's real-time location information;

[0034] S5: If the result of S4 is yes, the user's real-time location information is obtained and stored;

[0035] S6: If the determination result of S4 is no, the user's real-time location information is continuously acquired and stored.

[0036] Compared with the known public technology, the technical solution provided by the present invention has the following beneficial effects:

[0037] 1. The present invention provides a big data intelligent decision-making analysis system based on machine learning. During operation, the system can combine the user's real-time location information and earthquake information to bring better earthquake risk avoidance maintenance effects to users, ensuring that unorganized user groups can use the data provided by the system to evacuate from the house in a more orderly manner when an earthquake occurs, effectively ensuring the escape probability of users in the house when an earthquake occurs, and when the users in the house cannot escape, the system provides data support to rescue personnel in the form of location information feedback, so as to facilitate more efficient rescue work and provide further safety protection for users.

[0038] 2. During operation, the system of the present invention is less affected by the user group and can continuously expand the system's operational functionality based on the expansion of the user group, ensuring that the system can provide centralized earthquake response strategies and safety maintenance for more users. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] 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 only some embodiments of the present invention. Those skilled in the art can also derive other drawings based on these drawings without inventive effort.

[0040] Figure 1 is a schematic diagram of the structure of a big data intelligent decision analysis system based on machine learning;

[0041] FIG2 is a flow chart of a method for intelligent decision-making analysis based on big data using machine learning;

[0042] FIG3 is a schematic diagram of parameter value sources in the security zone analysis logic used in the present invention;

[0043] The numbers in the figure represent: 1. Adjacent buildings in the open area; 2. The open area; 3. The facades of buildings and the open area are close to each other; 4. The length of the side touching the ground; 5. The maximum span in the open area in the direction parallel to the line corresponding to the length of the side touching the ground; 6. The maximum span in the open area. Modes for Carrying Out the Invention

[0044] To make the purpose, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. 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 any creative efforts shall fall within the scope of protection of the present invention.

[0045] The present invention will be further described below with reference to the embodiments.

[0046] Example 1

[0047] A big data intelligent decision analysis system based on machine learning in this embodiment, as shown in FIG1 , includes an interaction layer, an analysis layer, and a decision layer;

[0048] The user's real-time location information and building parameters in the user's area are captured through the interaction layer. Earthquake information is collected synchronously based on the interaction layer in real time. The analysis layer receives the real-time earthquake information collected by the interaction layer and triggers the operation of analyzing the safety zone based on the building parameters in the user's area based on the earthquake information. The decision layer receives the safety zone analyzed by the analysis layer in real time, further configures the safety zone based on the user's real-time location information captured by the interaction layer, and then feeds back the configured safety zone coordinates to the interaction layer.

[0049] The analysis layer includes a receiving module, a setting module, and an analysis module. The receiving module is used to receive the user's real-time location information, building parameters of the user's area, and earthquake information collected in real time in the interaction layer. The setting module is used to set a trigger threshold, apply the trigger threshold to compare with the earthquake information received by the receiving module, and trigger the analysis module to run based on the comparison result. The analysis module is used to obtain the building parameters of the user's area received by the receiving module and analyze the safe area based on the building parameters of the user's area.

[0050] The analysis module is equipped with a safety zone analysis logic. During the operation phase of the analysis module, the module identifies open areas based on regional building parameters, and then applies the safety zone analysis logic to analyze each identified open area. The analysis results are then used to confirm the safety zone within the identified open areas.

[0051] The safety zones confirmed in the analysis module are fed back to the decision-making layer in real time. When feeding back to the decision-making layer, the specification parameters of the safety zones and the corresponding safety zone configurations are also fed back to the decision-making layer synchronously.

[0052] The interaction layer includes a capture module, an acquisition module, and a storage module. The capture module is used to capture the user's real-time location information and the building parameters of the user's area. The acquisition module is used to collect earthquake information in real time. The storage module is used to receive the user's real-time location information and the building parameters of the user's area captured by the capture module, build a regional building model based on the building parameters of the user's area, and store the captured user's real-time location information and regional building model.

[0053] Among them, the capture module and the collection module are installed in the mobile device held by each user of the system service in the format of a software APP. The collection module collects earthquake information in real time through the network on the mobile device held by the user. The earthquake information includes: earthquake source, earthquake source magnitude, estimated magnitude, earthquake arrival time, and earthquake end time. The estimated magnitude is the magnitude of the earthquake when the vibration generated by the earthquake source is transmitted to the user's location;

[0054] During the analysis module operation phase, the building parameters of the user's area are obtained. When analyzing the safety zone based on the building parameters of the user's area, the regional building model is simultaneously applied instead of the building parameters of the user's area. The safety zone analysis logic set in the analysis module is expressed as follows:

[0055] Where: Safety points for open areas; It is a collection of adjacent buildings in an open area; is a constant; is the facade area of ​​the i-th building adjacent to the open area; is the length of the ground edge of the facade of the i-th building adjacent to the open area; Relatively in open areas Maximum span in parallel direction; is the maximum span of the open area; is the total number of adjacent buildings in the open area; is the total amount of adjacent roads in the open area; is the safety factor of the i-th building adjacent to the open area;

[0056] Among them, the constant The value range is: , and the higher the adjacent building in the open area, the constant The larger the value, the smaller the constant The smaller the value, the setting logic is that the building safety factor is set based on the building's load-bearing structural material. The better the seismic performance of the building's load-bearing structural material, the larger the building safety factor value. Conversely, the smaller the building safety factor value. The range of building safety factor values ​​is: , open area safety points The higher the value, the less safe the open area is, and vice versa.

[0057] The decision-making layer includes a configuration module, a transmission module, and a positioning module. The configuration module is used to receive the security zones and security zone specification parameters analyzed by the analysis layer, as well as the real-time user location information stored in the storage module of the interaction layer, set the security zone and user configuration ratio, and complete the user and security zone configuration based on the security zone and user configuration ratio. The transmission module is used to receive the user and security zone configuration results from the configuration module and feed the configuration results back to the mobile device held by the user. The positioning module is used to obtain the user location information captured by the interaction layer in real time.

[0058] The ratio of the security area set in the configuration module to the user configuration is expressed as: , =q represents the number of users placed per y square meters. When the configuration module performs user and security zone configuration based on the security zone to user configuration ratio, it applies the security zone specification parameters and the security zone to user configuration ratio to calculate the total number of users that can be configured in the security zone. Furthermore, based on the user's real-time location information and the total number of users that can be configured in the security zone, users are configured in the security zone. When configuring users in the security zone based on the user's real-time location information, users who are closer to the security zone are given higher priority.

[0059] The receiving module is interactively connected to the storage module through a wireless network, the storage module is electrically connected to the acquisition module and the capture module through a medium, the receiving module is electrically connected to the setting module and the analysis module through a medium, the analysis module is interactively connected to the configuration module through a wireless network, and the configuration module is electrically connected to the transmission module and the positioning module through a medium.

[0060] In this embodiment, the capture module operates to capture the user's real-time location information and building parameters of the user's area. The acquisition module synchronously collects earthquake information in real time. The storage module is subsequently operated to receive the user's real-time location information and building parameters of the user's area captured by the capture module, construct a regional building model based on the building parameters of the user's area, and store the captured user's real-time location information and regional building model. The receiving module then receives the user's real-time location information, building parameters of the user's area, and earthquake information collected in real time in the interaction layer. The setting module synchronously sets a trigger threshold, compares the trigger threshold with the earthquake information received by the receiving module, and triggers the analysis module to operate based on the comparison result. The analysis module further obtains the building parameters of the user's area received by the receiving module, analyzes the safety area based on the building parameters of the user's area, and finally receives the safety area and safety area specification parameters analyzed in the analysis layer and the user's real-time location information stored in the storage module in the interaction layer through the configuration module. The safety area and user configuration ratio are set, and the user and safety area configuration is completed based on the safety area and user configuration ratio. The transmission module receives the user and safety area configuration results from the configuration module in real time and feeds the configuration results back to the mobile device held by the user. The positioning module obtains the user's location information captured in the interaction layer in real time.

[0061] The above system effectively protects the life safety of residents in the house when an earthquake occurs, and provides designated escape areas for residents, greatly reducing the safety threats caused by earthquakes to residents.

[0062] See Figure 3, which further illustrates the safety zone analysis logic set in the analysis module. In the specific application stage, the source of the parameters used in the logic further ensures that the analysis logic is stably implemented in the system.

[0063] Example 2

[0064] At the implementation level, based on Example 1, this example further illustrates a big data intelligent decision analysis system based on machine learning in Example 1 with reference to FIG1 :

[0065] After obtaining the user's real-time location information, the capture module confirms the user's area based on the location information of all users, and further captures the building parameters within the user's area. The building parameters include: the building's location coordinates, the coordinates of the roads connecting the buildings, the length, width and height of the building's facade, and the building's load-bearing structure material. When constructing the regional building model, the storage module applies the building's location coordinates, the coordinates of the roads connecting the buildings, and the length, width and height of the building's facade to complete the construction of the regional building model. The acquisition module runs to continuously obtain the user's real-time location information, and further executes the expansion of the regional building model based on the user's real-time location information. The user's real-time location information stored in the storage module only stores the latest captured user's real-time location information before the decision layer runs. After the decision layer runs, the user's real-time location information continuously captured by the capture module is continuously stored.

[0066] Through the above settings, the interactive layer in the system can be further operated according to the specified operating logic to ensure the stable operation of the interactive layer in the system and provide necessary data support for the operation of the analysis layer and decision-making layer in the system.

[0067] As shown in Figure 1, among the user's real-time location information, building parameters of the user's area, and earthquake information received by the receiving module, the user's real-time location information comes from the storage module, the building parameters of the user's area are replaced by the building model of the area stored in the storage module, the earthquake information comes from the acquisition module in the interaction layer, the trigger threshold set in the setting module is the safe magnitude, and when the trigger threshold applied in the setting module is compared with the earthquake information received by the receiving module, the earthquake information received by the receiving module is the estimated magnitude;

[0068] The trigger threshold is expressed as: , x is the safety magnitude. If the estimated magnitude is not within the trigger threshold, the analysis module will be triggered to run. Otherwise, the receiving module will be jumped to run;

[0069] During the open area identification phase, the analysis module traverses the regional building model and identifies all road areas and building areas in the regional building model. All road areas and building areas in the regional building model are further segmented and discarded. The remaining area is the open area identified by the analysis module.

[0070] The analysis module sets a safety zone determination threshold and an open area safety classification threshold. After obtaining the safety zone threshold and the open area safety classification threshold, Comparison is performed to determine whether each open area is a safe area based on the safe area determination threshold. The specification parameters of the safe area are obtained from the regional building model. The specification parameters of the safe area include: safe area boundary coordinates and safe area area.

[0071] Through the above settings, the trigger threshold set by the setting module in the analysis layer is provided with setting logic limitations, ensuring that the analysis layer in the system provides the linkage conditions of the upper and lower operation layers with the specified trigger logic, making the system operation more stable.

[0072] As shown in Figure 1, the positioning module receives the earthquake information collected in the interactive layer in real time, obtains the earthquake end time in the earthquake information, refreshes the system operation after the earthquake end time arrives, and controls the capture module operation in the interactive layer of the system to compare the user's real-time location information captured by the capture module with the user and safety zone configuration results in the configuration module;

[0073] For users whose real-time location information is not in the safe area, the real-time location information is acquired and stored in the capture module by the positioning module in real time; for users whose real-time location information is in the safe area, the real-time location information is acquired and stored in the capture module by the positioning module after the capture module is controlled by the positioning module to capture the real-time location information, and the process ends.

[0074] By limiting the operating logic of the positioning module, further user data support is provided on the system side, so that users who have not completed earthquake evacuation based on the system can still provide efficient rescue operation conditions for rescue personnel based on the location information fed back by the system operation.

[0075] Example 3

[0076] At the implementation level, based on Example 1, this embodiment further specifically illustrates a big data intelligent decision analysis system based on machine learning in Example 1 with reference to FIG2 :

[0077] A big data intelligent decision analysis method based on machine learning includes the following steps:

[0078] S1: Obtain the user's real-time location information, set the user's area based on the user's real-time location information, capture the building parameters in the user's area, and build a regional building model based on the building parameters in the user's area;

[0079] S2: Applying the regional building model to identify safe areas in the user’s area;

[0080] S21: the stage of setting the security zone identification logic in the user's area;

[0081] S3: Collect earthquake information and configure a safe zone for users based on their real-time location information when an earthquake occurs;

[0082] S31: configuration logic setting stage for mutual configuration between users and security zones;

[0083] S4: Determine whether the user has reached a safe area based on the user's real-time location information;

[0084] S5: If the result of S4 is yes, the user's real-time location information is obtained and stored;

[0085] S6: If the determination result of S4 is no, the user's real-time location information is continuously acquired and stored.

[0086] In summary, in the above embodiment, the system can combine the user's real-time location information and earthquake information during operation to bring better earthquake risk avoidance and maintenance effects to users, ensuring that unorganized user groups can use the data provided by the system to evacuate from the house in a more orderly manner when an earthquake occurs, effectively ensuring the escape probability of users in the house when an earthquake occurs, and when users in the house cannot escape, the system provides data support to rescue personnel in the form of location information feedback, so as to carry out rescue work more efficiently and provide further safety protection for users; and during the operation of this system, it is less affected by the user group and can continuously expand the system operation functionality based on the expansion of the user group, ensuring that the system can bring centralized earthquake response strategies and safety maintenance to more users.

[0087] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements will not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A big data intelligent decision-making analysis system based on machine learning, characterized in that, It includes an interaction layer, an analysis layer, and a decision-making layer; The real-time location information of the user and the building parameters of the area where the user is located are captured through the interaction layer. The earthquake information synchronization is based on the real-time collection through the interaction layer. The analysis layer receives the earthquake information collected in real time by the interaction layer, and triggers the operation of analyzing the safe area in the building parameters of the area where the user is located based on the earthquake information. The decision-making layer receives the safe area analyzed in the analysis layer in real time, further configures the safe area based on the real-time location information of the user captured in the interaction layer, and then feeds back to the interaction layer with the coordinates of the configured safe area; The analysis layer includes a receiving module, a setting module, and an analysis module. The receiving module is used to receive the real-time location information of the user, the building parameters of the area where the user is located, and the earthquake information collected in real time by the interaction layer. The setting module is used to set a trigger threshold, compare the trigger threshold with the earthquake information received by the receiving module, and trigger the operation of the analysis module based on the comparison result. The analysis module is used to obtain the building parameters of the area where the user is located received by the receiving module, and analyze the safe area based on the building parameters of the area where the user is located; A safe area analysis logic is set in the analysis module. During the operation of the analysis module, the open area is identified based on the area building parameters, and then the safe area analysis logic is further applied to analyze each identified open area, and then the safe area in the identified open areas is confirmed with the analysis result; Among them, the safe area confirmed in the analysis module is fed back to the decision-making layer in real time, and when feeding back to the decision-making layer, the specification parameters of the safe area are synchronously fed back to the decision-making layer in mutual configuration with the corresponding safe area.

2. The big data intelligent decision-making analysis system based on machine learning according to claim 1, characterized in that, The interaction layer includes a capture module, a collection module, and a storage module. The capture module is used to capture the real-time location information of the user and the building parameters of the area where the user is located. The collection module is used to collect earthquake information in real time. The storage module is used to receive the real-time location information of the user captured by the capture module and the building parameters of the area where the user is located, construct a regional building model based on the building parameters of the area where the user is located, and store the captured real-time location information of the user and the regional building model; Among them, the capture module and the collection module are installed in the mobile devices held by each user of the system service in the format of a software APP. The collection module collects earthquake information in real time through the network in the mobile device held by the user. The earthquake information includes: earthquake source, earthquake source magnitude, estimated magnitude, earthquake arrival time, earthquake end time, and the estimated magnitude is the magnitude when the vibration generated by the earthquake source propagates to the location where the user is located.

3. The big data intelligent decision analysis system based on machine learning according to claim 2, characterized in that, After obtaining the user's real-time location information, the capture module confirms the area range where the user is located based on the location information of all users, and further captures the building parameters within the area where the user is located. The building parameters include: the coordinates of the building's location, the coordinates of the roads connecting the buildings, the length, width, and height of the building's exterior facade, and the material of the building's load-bearing structure. When constructing the regional building model, the storage module uses the coordinates of the building's location, the coordinates of the roads connecting the buildings, and the length, width, and height of the building's exterior facade to complete the construction of the regional building model. The acquisition module runs continuously to obtain the user's real-time location information, and further expands the regional building model based on the user's real-time location information. Before the decision-making layer runs, only the latest captured user real-time location information is stored in the storage module. After the decision-making layer runs, the user real-time location information continuously captured by the capture module is continuously stored.

4. A big data intelligent decision-making analysis system based on machine learning according to claim 1, characterized in that, Among the user's real-time location information, the building parameters of the area where the user is located, and the earthquake information received by the receiving module, the user's real-time location information comes from the storage module, the building parameters of the area where the user is located are replaced by the regional building model stored in the storage module, and the earthquake information comes from the acquisition module in the interaction layer. The trigger threshold set in the setting module is the safe earthquake magnitude. When comparing the trigger threshold with the earthquake information received by the receiving module, the earthquake information received by the receiving module used is the estimated earthquake magnitude; Among them, the trigger threshold is expressed as: , where x is the safe earthquake magnitude. If the estimated earthquake magnitude is not within the trigger threshold, the analysis module is triggered to run; otherwise, the receiving module is jumped to run.

5. A big data intelligent decision-making analysis system based on machine learning according to claim 1, characterized in that, During the operation phase of the analysis module, when obtaining the building parameters of the user's location area and analyzing the safe area based on the building parameters of the user's location area, the building model of the application area is synchronously used to replace the building parameters of the user's location area. The safe area analysis logic set in the analysis module is expressed as: Where: is the safety score of the open area; is the set of adjacent buildings in the open area; is a constant; is the area of the similar outer facade between the i-th adjacent building in the open area and the open area; is the ground-touching side length of the similar outer facade between the i-th adjacent building in the open area and the open area; is the relative in the open area is the maximum span in the parallel direction; is the maximum span of the open area; is the total number of adjacent buildings in the open area; is the total number of adjacent roads in the open area; is the safety factor of the i-th adjacent building in the open area; Among them, the constant The value range is: , and it follows that the higher the adjacent building in the open area, the constant The larger the value, conversely, the constant For the setting logic with a smaller value, the building safety factor is set based on the material of the building's load-bearing structure. The better the seismic performance of the building's load-bearing structure material, the larger the value of the building safety factor; conversely, the smaller the value of the building safety factor. The value range of the building safety factor is: , safety score for open areas The higher it is, the less safe the open area is; conversely, the safer the open area is.

6. A big data intelligent decision-making analysis system based on machine learning according to claim 1, characterized in that, In the stage where the analysis module identifies the open area, it traverses the regional building model, identifies all the areas where the roads are located and the areas where the buildings are located in the regional building model, and further divides and discards all the areas where the roads are located and the areas where the buildings are located in the regional building model. The remaining area is the open area identified by the analysis module; Among them, a safety area determination threshold is set in the analysis module, and the safety score of the open area After obtaining, further apply the safety area determination threshold and the safety score of the open area Compare, and determine whether each open area is a safe area based on the safe area determination threshold. The specification parameters of the safe area are obtained from the regional building model. The specification parameters of the safe area include: the boundary coordinates of the safe area and the area of the safe area.

7. An intelligent big data decision analysis system based on machine learning according to claim 1, characterized in that The decision-making layer includes a configuration module, a transmission module, and a positioning module. The configuration module is used to receive the safe areas and the specification parameters of the safe areas analyzed in the analysis layer, and the user's real-time location information stored in the storage module in the interaction layer, set the configuration ratio of the safe area and the user, and complete the configuration of the user and the safe area based on the configuration ratio of the safe area and the user. The transmission module is used to receive the configuration result of the user and the safe area in the configuration module and feedback the configuration result to the mobile device held by the user. The positioning module is used to obtain the user's location information captured in the interaction layer in real time; Among them, the security area and user configuration ratio set in the configuration module are expressed as: ， It represents q users placed per y square meters. When the configuration module performs the configuration of users and safety areas based on the safety area and the user configuration ratio, it calculates the total number of users that can be configured in the safety area by applying the safety area specification parameters and the safety area and user configuration ratio. Further, based on the real-time location information of the users and the total number of users that can be configured in the safety area, it configures users for the safety area. And when configuring users for the safety area based on the real-time location information of the users, it follows the principle that the closer the user is to the safety area, the higher the priority for configuration.

8. An intelligent decision-making analysis system for big data based on machine learning according to claim 7, characterized in that, The positioning module runs to receive the earthquake information collected in the interaction layer in real time, obtains the earthquake end time in the earthquake information, refreshes the system operation after the earthquake end time arrives, and controls the operation of the capture module in the interaction layer of the system to compare the real-time location information of the users captured by the operation of the capture module with the configuration result of the users and the safety area in the configuration module; For the users corresponding to the real-time location information of the users not in the safety area, the real-time location information is obtained and stored in real time by the positioning module in the capture module; for the users corresponding to the real-time location information of the users in the safety area, after the real-time location information is captured by the operation of the capture module controlled by the positioning module, the real-time location information is obtained and stored by the positioning module in the capture module, and then it ends.

9. An intelligent decision-making analysis system for big data based on machine learning according to claim 1, characterized in that, The receiving module is connected to a storage module through wireless network interaction. The storage module is electrically connected to a collection module and a capture module through a medium. The receiving module is electrically connected to a setting module and an analysis module through a medium. The analysis module is connected to a configuration module through wireless network interaction. The configuration module is electrically connected to a transmission module and a positioning module through a medium.

10. A big data intelligent decision-making analysis method based on machine learning, which is an implementation method of a big data intelligent decision-making analysis system based on machine learning as described in any one of claims 1-9, characterized in that, It includes the following steps: S1: Obtain the real-time location information of the users, set the area where the users are located based on the real-time location information of the users, capture the building parameters in the area where the users are located, and construct a regional building model based on the building parameters in the area where the users are located; S2: Apply the regional building model to identify the safety areas in the area where the users are located; S21: The setting stage of the safety area identification logic in the area where the users are located; S3: Collect earthquake information, and when an earthquake occurs, configure a safety area for the users based on the real-time location information of the users; S31: The setting stage of the configuration logic for the mutual configuration of users and safety areas; S4: Determine whether the users reach the safety area based on the real-time location information of the users; S5: If the determination result of S4 is yes, obtain and store the real-time location information of the users; S6: If the determination result of S4 is no, continuously obtain and store the real-time location information of the users.

Images