Fire-fighting three-dimensional visualization and emergency deduction method and device based on CIM technology, equipment and medium

Abstract

The invention discloses a fire-fighting three-dimensional visualization and emergency deduction method and device based on a CIM technology, equipment and a medium, and belongs to the technical field of computers. The method comprises the following steps: acquiring a basic CIM three-dimensional model, fire-fighting exclusive real-time data and building structure basic data; fusing the basic CIM model and the fire-fighting exclusive real-time data through a dynamic fire-fighting attribute mapping algorithm to obtain a fire-fighting CIM model; quantifying the fire-fighting CIM model and the building structure data in combination with a weight algorithm, generating regional fire risk data, and visualizing the regional fire risk data through a thermodynamic diagram; real-time environment and surrounding fire-fighting resource data are obtained, and through fire simulation and resource matching, optimization suggestions are generated in linkage with a historical case library, and an emergency deduction result is obtained; and building a multi-view interaction channel, and synchronizing the frontline marking data and a command center fire-fighting CIM model. According to the technical scheme, fire-fighting data fusion and risk visualization can be realized, the deduction scientificity is improved, and the emergency rescue efficiency is greatly improved.

Description

Technical Field

[0001] This application belongs to the field of computer technology, specifically relating to a method, device, equipment and medium for fire protection three-dimensional visualization and emergency simulation based on CIM technology. Background Technology

[0002] The topic of digital urban management is receiving increasing attention. With the rise of high-rise buildings and complex commercial complexes, the safety hazards posed by fires are becoming more and more serious. Traditional fire emergency response relies on map data, on-site reconnaissance, and human experience, and its simulation methods are not advanced enough to cope with real-world complex scenarios.

[0003] In existing technologies, fire information is mostly presented as theoretical data. Rescuers need to use data calculations to determine the unobstructed capacity of fire lanes and the availability of fire-fighting supplies. Furthermore, historical fire cases are only archived in document form, failing to provide reliable references. For command centers and frontline personnel, information transmission is often delayed and inaccurate, leading to a disconnect between command decisions and the actual situation on the ground. These problems result in inaccurate risk assessment, low rescue efficiency, and safety hazards for the general public. Summary of the Invention

[0004] The purpose of this application is to provide a method, device, equipment, and medium for fire protection 3D visualization and emergency simulation based on CIM technology. This application aims to address the technical problems of outdated traditional fire emergency simulation methods, poor practicality of fire information presentation, low efficiency due to reliance on manual calculation for fire lane clearing and material deployment judgments, inability to effectively reference historical cases, and the disconnect between command center and frontline information transmission due to delays and inaccuracies leading to a lack of on-site decision-making. The goal is to achieve the technical effects of realizing fire data visualization and fusion, improving the accuracy of risk prediction and emergency simulation, ensuring real-time linkage between command and frontline, improving rescue efficiency, and reducing safety hazards.

[0005] In a first aspect, embodiments of this application provide a method for fire-fighting 3D visualization and emergency simulation based on CIM technology, the method comprising: Acquire basic CIM 3D model, fire protection-specific real-time data, and basic building structure data; wherein, the fire protection-specific real-time data includes fire protection facility status data, passageway access data, and evacuation load data; Based on the basic CIM 3D model and the fire-specific real-time data, a fire-fighting CIM model is obtained through data fusion processing using a dynamic fire-fighting attribute mapping algorithm. Based on the fire protection CIM model and the basic building structure data, the risk level is quantified using a weighting algorithm to obtain fire risk level data for each area, and a heat map is used to visualize the risk based on the fire risk level data for each area. Acquire real-time environmental data and surrounding fire-fighting resource data. Based on the fire-fighting CIM model, the real-time environmental data, and the surrounding fire-fighting resource data, perform fire simulation and resource matching processing. Link with the historical case library to generate optimization suggestions through similarity matching to obtain complete emergency simulation results. A multi-view interactive channel is established to obtain front-line view marker data. Based on the front-line view marker data, the fire protection CIM model is updated in real time to synchronize the view of the command center.

[0006] Furthermore, based on the basic CIM 3D model and the fire-specific real-time data, a data fusion process is performed using a dynamic fire attribute mapping algorithm to obtain a fire-fighting CIM model, including: The fire-specific real-time data is standardized to convert unstructured data into key-value pair structured data. Extract the spatial coordinate parameters of the building components in the basic CIM 3D model, and establish a coordinate mapping table between the structured data and the corresponding building components; According to the coordinate mapping table, the structured data is mounted to the corresponding spatial position of the basic CIM 3D model, and the fire protection CIM model is output after the mounting is completed.

[0007] Furthermore, before performing format standardization processing on the fire-specific real-time data to convert unstructured data into key-value pair format structured data, the method further includes: Obtain standardized, real-time fire-specific data and detect the percentage of missing values ​​in each data field; If the percentage of missing values ​​in a certain data field is greater than a set threshold, linear interpolation will be used to fill in the missing values ​​in that field. Identify outliers in the data and replace them with the average value of the corresponding field.

[0008] Furthermore, based on the fire protection CIM model and the building structure foundation data, a weighted algorithm is used to quantify the risk level, resulting in fire risk level data for each area, including: By combining the fire protection facility status data and real-time personnel density data in the fire protection CIM model, the weighting coefficients of the fire resistance rating data, facility status data, and the real-time personnel density data are determined; wherein, the basic building structure data includes the building structure fire resistance rating data; According to the preset scoring criteria, the fire resistance rating data, facility status data, and real-time personnel density data are respectively quantified and scored. The scores for each region are calculated using a preset weighting formula, and the fire risk level data for each region is determined based on the scores.

[0009] Furthermore, fire simulation is performed based on the fire protection CIM model, the real-time environmental data, and the surrounding fire protection resource data, including: Real-time environmental data is input into the fire protection CIM model to simulate the fire spread path and smoke diffusion range based on the thermal conductivity characteristics of building components; wherein, the real-time environmental data includes wind direction, temperature and humidity data; Acquire surrounding fire-fighting resource data, and calculate the optimal rescue route, resource arrival time, and evacuation route capacity limit by combining the fire spread path and the smoke diffusion range; wherein, the surrounding fire-fighting resource data includes fire truck location, water source distribution, number of rescue personnel, and equipment parameters; Based on the load-bearing capacity of evacuation routes and real-time personnel density data, the evacuation success rate is calculated, and the fire simulation results are obtained.

[0010] Furthermore, by linking with the historical case database and generating optimization suggestions through similarity matching, a complete emergency simulation result is obtained, including: Key feature parameters of each case are extracted from the historical case database. These key feature parameters include: fire type, building structure type, floor where the fire started, and successful rescue measures. A case feature matrix is ​​then constructed. Extract key feature parameters of the current simulation scenario to form a scenario feature vector; The cosine similarity algorithm is used to calculate the matching degree between the scene feature vector and each vector in the case feature matrix, and the successfully matched cases are selected. Extract successful rescue measures from matching case studies and generate suggestions for optimizing the simulation strategy.

[0011] Furthermore, a multi-view interactive channel is established to acquire front-line view marker data. Based on this front-line view marker data, real-time linkage and update processing is performed between the data and the fire protection CIM model, including: A multi-view interactive channel is built based on the 5G network to convert global data from the command center, AR perspective data from the front line, and analysis data from the expert group into a unified transmission format. Acquire fire point data marked by frontline firefighters using AR devices, wherein the fire point data includes at least one of precise coordinates, on-site photos, and text descriptions; The fire location data is synchronized to the corresponding coordinates of the fire protection CIM model, generating dynamic early warning indicators, which are then pushed to the expert group's perspective.

[0012] Secondly, embodiments of this application provide a fire-fighting 3D visualization and emergency simulation device based on CIM technology, the device comprising: The data acquisition module is used to acquire basic CIM 3D model, fire protection-specific real-time data, and basic building structure data; wherein, the fire protection-specific real-time data includes fire protection facility status data, passageway data, and evacuation load data; The model building module is used to perform data fusion processing based on the basic CIM 3D model and the fire-specific real-time data through a dynamic fire attribute mapping algorithm to obtain a fire CIM model. The visualization rendering module is used to quantify the risk level based on the fire protection CIM model and the building structure basic data, combined with a weighting algorithm, to obtain fire risk level data for each area, and to perform risk visualization rendering using a heat map based on the fire risk level data for each area. The emergency simulation module is used to acquire real-time environmental data and surrounding fire-fighting resource data. Based on the fire-fighting CIM model, the real-time environmental data, and the surrounding fire-fighting resource data, it performs fire simulation and resource matching processing. It also links with the historical case library to generate optimization suggestions through similarity matching, and obtains complete emergency simulation results. The data synchronization module is used to establish a multi-view interaction channel, acquire front-line view marker data, and perform real-time linkage and update processing with the fire protection CIM model based on the front-line view marker data to synchronize the view of the command center.

[0013] Thirdly, embodiments of this application provide an electronic device, which includes a processor, a memory, and a program or instructions stored in the memory and executable on the processor, wherein the program or instructions, when executed by the processor, implement the steps of the method described in the first aspect.

[0014] Fourthly, embodiments of this application provide a readable storage medium on which a program or instructions are stored, which, when executed by a processor, implement the steps of the method described in the first aspect.

[0015] Fifthly, embodiments of this application provide a chip, the chip including a processor and a communication interface, the communication interface being coupled to the processor, the processor being used to run programs or instructions to implement the method as described in the first aspect.

[0016] The technical solution provided in this application embodiment acquires a basic CIM 3D model, fire-specific real-time data, and basic building structure data. The fire-specific real-time data includes fire facility status data, passageway data, and evacuation capacity data. Based on the basic CIM 3D model and the fire-specific real-time data, a dynamic fire attribute mapping algorithm is used for data fusion processing to obtain a fire CIM model. Based on the fire CIM model and the basic building structure data, a weighted algorithm is used for risk level quantification to obtain fire risk level data for each area. A heat map is used to visualize the risk based on the fire risk level data for each area. Real-time environmental data and surrounding fire resource data are acquired. Fire simulation and resource matching are performed based on the fire CIM model, the real-time environmental data, and the surrounding fire resource data. A historical case library is linked to generate optimization suggestions through similarity matching, resulting in a complete emergency simulation result. A multi-view interactive channel is established to acquire frontline view marker data. The frontline view marker data and the fire CIM model are updated in real-time to synchronize the command center's view. This technical solution can realize the visualization and integration of fire protection data and accurate risk prediction, improve the scientific nature of emergency simulation, ensure real-time linkage between command and front line, improve rescue efficiency, and reduce safety hazards. Attached Figure Description

[0017] Figure 1 This is a flowchart illustrating the fire protection 3D visualization and emergency simulation method based on CIM technology provided in Embodiment 1 of this application; Figure 2 This is a schematic diagram of the fire protection 3D visualization and emergency simulation device based on CIM technology provided in Embodiment 3 of this application; Figure 3 This is a schematic diagram of the structure of the electronic device provided in Embodiment 4 of this application. Detailed Implementation

[0018] To make the objectives, technical solutions, and advantages of this application clearer, specific embodiments of this application will be described in further detail below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are merely for explaining this application and not for limiting it. It should also be noted that, for ease of description, only the parts relevant to this application are shown in the drawings, not all of them. Before discussing exemplary embodiments in more detail, it should be mentioned that some exemplary embodiments are described as processes or methods depicted as flowcharts. Although the flowcharts describe operations (or steps) as sequential processes, many of these operations can be performed in parallel, concurrently, or simultaneously. Furthermore, the order of the operations can be rearranged. The process can be terminated when its operation is completed, but may also have additional steps not included in the drawings. The process can correspond to a method, function, procedure, subroutine, subroutine, etc.

[0019] The technical solutions of the embodiments of this application will be clearly described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application are within the scope of protection of this application.

[0020] The terms "first," "second," etc., used in the specification and claims of this application are used to distinguish similar objects and not to describe a specific order or sequence. It should be understood that such use of data can be interchanged where appropriate so that embodiments of this application can be implemented in orders other than those illustrated or described herein, and the objects distinguished by "first," "second," etc., are generally of the same class and the number of objects is not limited; for example, a first object can be one or more. Furthermore, in the specification and claims, "and / or" indicates at least one of the connected objects, and the character " / " generally indicates that the preceding and following objects are in an "or" relationship.

[0021] The following description, in conjunction with the accompanying drawings, details the fire protection 3D visualization and emergency simulation method, device, equipment, and medium based on CIM technology provided in this application through specific embodiments and application scenarios.

[0022] Example 1 Figure 1 This is a flowchart illustrating the fire-fighting 3D visualization and emergency simulation method based on CIM technology provided in Embodiment 1 of this application. Figure 1 As shown, the specific steps include the following: S101, acquire the basic CIM 3D model, fire protection-specific real-time data, and basic building structure data; wherein, the fire protection-specific real-time data includes fire protection facility status data, passageway data, and evacuation load data.

[0023] Among them, the basic CIM 3D model can be a special application model of City Information Modeling (CIM) in the field of fire protection, which includes basic spatial information such as the three-dimensional spatial structure and component distribution of the building. For example, a 3D model is formed after the BIM (Building Information Modeling) data of a commercial complex is exported and converted into a format.

[0024] Real-time data specific to fire protection can be a collection of dynamic data directly related to fire emergencies, specifically including fire protection facility status data, passageway access data, and evacuation capacity data.

[0025] Fire protection facility status data can be real-time operating parameters of various fire protection equipment, such as real-time water pressure of fire hydrants, valve on / off status of sprinkler systems, power level and alarm signals of smoke detectors, etc.

[0026] Access data can be real-time accessibility data for critical passageways such as fire lanes and evacuation staircases. For example, the real-time width of a fire lane on the first floor of a building, whether there are obstacles, and the area occupied by obstacles.

[0027] Evacuation carrying capacity data can be the personnel carrying capacity limit data of each evacuation area and evacuation route in a building, such as the maximum number of people standing safely per square meter in an office building's evacuation staircase, or the upper limit of the number of people passing through an evacuation corridor per unit time.

[0028] Basic building structural data can be fundamental information reflecting the fire resistance characteristics of a building structure, such as the building's fire resistance rating, component materials, floor slab thickness, and load-bearing wall distribution.

[0029] This solution can obtain a basic CIM 3D model by connecting to the city's CIM platform database, collect real-time fire-specific data through Internet of Things (IoT) sensors for fire protection facilities, and retrieve basic building structural data through a building file management system. For example, the data analysis server downloads the 3D model file of the target building from the city's CIM management platform via an HTTP interface and receives real-time status data uploaded by smoke detectors via the LoRa (Long Range Radio) communication protocol.

[0030] S102, Based on the basic CIM 3D model and the fire-specific real-time data, a fire-fighting CIM model is obtained by performing data fusion processing through a dynamic fire-fighting attribute mapping algorithm.

[0031] The dynamic fire protection attribute mapping algorithm is an algorithm used to establish the spatial coordinate association between fire protection-specific data and CIM model, enabling dynamic matching and updating of data and model.

[0032] Data fusion processing can be the process of linking and integrating scattered fire-specific real-time data with basic CIM 3D models, so that the model not only contains spatial information but also carries fire-fighting functional attributes.

[0033] Fire protection CIM models can be integrated models that combine spatial form with real-time fire protection data. For example, in a 3D model of a commercial complex, clicking on the fire hydrant icon on a certain floor can display information such as real-time water pressure and maintenance records.

[0034] This solution first converts the format of real-time fire protection data, then uses an algorithm to establish a coordinate mapping relationship between the data and model components, ultimately completing the data mounting. For example, the server runs a mapping algorithm script written in Python to match the latitude and longitude coordinates of fire hydrants with the spatial coordinates of their corresponding locations in the model, thus achieving data mounting.

[0035] S103. Based on the fire protection CIM model and the building structure basic data, the risk level is quantified using a weighting algorithm to obtain fire risk level data for each area, and a heat map is used to visualize the risk based on the fire risk level data for each area.

[0036] A weighted algorithm is an algorithm that assigns weights to different influencing factors and calculates a comprehensive result. This algorithm can quantify the comprehensive degree of fire risk in various regions.

[0037] Risk level quantification can be the process of converting qualitative and quantitative data affecting fire risk into comparable quantitative scores and determining the risk level.

[0038] Fire risk level data for each area can be the quantitative results of fire risk in different areas of a building, such as offices, power distribution rooms, evacuation routes, etc., and are usually divided into different levels such as high, medium and low.

[0039] A heat map is a visual chart that uses different shades of color to intuitively show the distribution and intensity of data. In this method, it is used to show the level of fire risk in each area.

[0040] This solution first extracts facility status data and basic building structure data from the fire protection CIM model, then calculates the risk score for each area using a weighted algorithm, and finally generates a heat map and overlays it onto the 3D model. For example, the system sets the basic score for an area with a fire resistance rating of Level 1 to 80 points. If a smoke detector in that area malfunctions, 30 points are deducted. Finally, the risk level is determined based on the comprehensive score, and the corresponding color is rendered.

[0041] S104. Acquire real-time environmental data and surrounding fire-fighting resource data. Based on the fire-fighting CIM model, the real-time environmental data, and the surrounding fire-fighting resource data, perform fire simulation and resource matching processing. Link with the historical case library to generate optimization suggestions through similarity matching to obtain complete emergency simulation results.

[0042] Real-time environmental data can be dynamic environmental parameters of the fire scene and its surroundings, including data such as wind direction, temperature, and humidity. For example, the real-time wind speed at the fire scene is 3 meters per second and the ambient temperature is 28°C.

[0043] Surrounding fire resources data can be information on available fire and rescue resources around the fire scene, including the location of fire trucks, distribution of water sources, number of rescue personnel, and equipment parameters. For example, there are 3 water tanker fire trucks 2 kilometers away from the scene, or 1 municipal fire hydrant.

[0044] A historical case database can be a database that stores information on past fire accidents and rescue operations, including the type of fire, rescue measures, and the effectiveness of the response, such as the rescue case of an electrical fire in an office building in 2023.

[0045] A complete emergency simulation result can be a comprehensive report that includes fire development simulation, resource allocation plan, rescue suggestions, etc., providing a comprehensive reference for fire command.

[0046] This solution first collects real-time environmental and fire resource data, then simulates fire development based on a fire CIM model, and simultaneously calls upon a historical case database for similarity matching. Finally, it integrates the simulation results and optimization suggestions. For example, based on environmental data of a level 3 northerly wind, the server simulates the path of a fire spreading northward and matches it with rescue suggestions from similar cases, such as "prioritizing the blocking of the north-facing passage."

[0047] S105, establish a multi-view interactive channel, obtain front-line view marker data, and perform real-time linkage and update processing based on the front-line view marker data and the fire protection CIM model to synchronize the view of the command center.

[0048] The multi-view interactive channel can be a communication and data transmission channel connecting the command center, front-line rescue personnel, and rear expert groups, supporting real-time communication of multiple perspectives and data.

[0049] Frontline perspective data can be key information marked by frontline rescuers at the scene, including the location of the fire, the location of the facility failure, the location of the trapped people, etc. For example, marking "the fire started in the office on the east side of the 15th floor, and there are 2 people trapped".

[0050] Real-time linkage and update processing can be the process of quickly synchronizing front-line marked data to the fire protection CIM model and updating the displayed content on each terminal, ensuring that the information in the command center is consistent with that in the front line.

[0051] This solution can establish a high-speed interactive channel via 5G network to receive marker data uploaded by frontline AR (Augmented Reality) devices and synchronously update the 3D model in the command center. For example, frontline firefighters can mark the coordinates of a fire point using AR glasses, and the fire CIM model in the command center can display a dynamic marker of that fire point within one second.

[0052] The technical solution provided in this embodiment solves the problem of traditional data dispersion by fusing multi-source fire protection data. The fire protection CIM model is displayed in an integrated manner, improving the efficiency of data use. In addition, risk quantification and heat map rendering make fire risks intuitive, allowing commanders to quickly locate high-risk areas and significantly improving the accuracy of risk identification. This solution combines real-time data dynamic simulation to make fire simulation and resource matching more accurate. Historical case linkage provides scientific reference for decision-making, and provides multi-perspective collaborative channels to ensure real-time synchronization of information between the command center and the front line, solving the problem of information lag. Overall, it improves the efficiency and accuracy of rescue decision-making and effectively reduces the risk of casualties and property losses.

[0053] In one feasible embodiment, optionally, a fire protection CIM model is obtained by performing data fusion processing based on the basic CIM 3D model and the fire protection-specific real-time data through a dynamic fire protection attribute mapping algorithm, including: The fire-specific real-time data is standardized to convert unstructured data into key-value pair structured data. Extract the spatial coordinate parameters of the building components in the basic CIM 3D model, and establish a coordinate mapping table between the structured data and the corresponding building components; According to the coordinate mapping table, the structured data is mounted to the corresponding spatial position of the basic CIM 3D model, and the fire protection CIM model is output after the mounting is completed.

[0054] Format standardization is the process of converting real-time fire protection data in different formats into a unified format, ensuring that the data is compatible with the CIM model.

[0055] Unstructured data can be data without a fixed format, such as videos of fire lane congestion taken by firefighters on the scene, or verbal descriptions of facility malfunctions.

[0056] Key-value pair structured data can be a data format consisting of attribute names and attribute values, such as fire hydrant number-101 and real-time pressure-0.8MPa.

[0057] Spatial coordinate parameters can be based on the three-dimensional coordinate information of each building component in the CIM three-dimensional model. For example, the spatial coordinates of a fire hydrant are (longitude value, latitude value, and height value).

[0058] A coordinate mapping table can be a table that records the correspondence between structured data and the spatial coordinates of building components, clearly defining the model location to which each data point should be attached.

[0059] This solution first uses natural language processing to convert unstructured data into key-value pairs, then extracts the coordinates of model components to establish a mapping table, and finally attaches the data to the corresponding locations according to the table. For example, after converting the verbal information about insufficient pressure in fire hydrant No. 101 into key-value pairs, it is attached to the fire hydrant component with that coordinate in the model through the mapping table.

[0060] This technical solution achieves the integration of fire protection data and CIM model through standardized processing and coordinate mapping, avoiding data misalignment issues, improving the data accuracy of the fire protection CIM model, and providing data support for subsequent risk assessment and simulation.

[0061] In one feasible embodiment, optionally, before performing format standardization processing on the fire-specific real-time data to convert the unstructured data into key-value pair format structured data, the method further includes: Obtain standardized, real-time fire-specific data and detect the percentage of missing values ​​in each data field; If the percentage of missing values ​​in a certain data field is greater than a set threshold, linear interpolation will be used to fill in the missing values ​​in that field. Identify outliers in the data and replace them with the average value of the corresponding field.

[0062] Missing value percentage can be the proportion of missing data in a certain data field to the total amount of data in that field. For example, if there are 8 missing data in 100 fire hydrant pressure data, the missing value percentage is 8%.

[0063] Setting a threshold can be a pre-defined critical value for determining whether missing data needs to be filled in. Specifically, it can be set to 5%, meaning that when the proportion of missing values ​​exceeds 5%, filling in the missing data is performed.

[0064] Linear interpolation is a mathematical method that uses known data points to extrapolate missing data. For example, based on the pressure data of 0.9 MPa and 0.7 MPa one hour before and after a fire hydrant, the missing pressure data in the middle can be filled in as 0.8 MPa.

[0065] Outliers can be values ​​that deviate from the normal range of data. For example, most fire hydrant pressures are between 0.6 and 1.0 MPa, so a data point of 1.8 MPa would be an outlier.

[0066] Specifically, you can first calculate the percentage of missing values ​​in each data field, then use linear interpolation to fill in the missing values ​​in fields that exceed the threshold, and finally identify outliers and replace them with the average value. For example, if a value of 500% is detected in the power data of a smoke detector, it is determined to be an outlier and replaced with the average value of that field, which is 85%.

[0067] This technical solution improves the completeness and accuracy of real-time fire protection data by filling in missing values ​​and correcting outliers, avoiding the impact of poor-quality data on model quality and ensuring the reliability of subsequent data fusion and risk assessment results.

[0068] In one feasible embodiment, optionally, based on the fire protection CIM model and the building structure foundation data, a weighted algorithm is used to quantify the risk level to obtain fire risk level data for each area, including: By combining the fire protection facility status data and real-time personnel density data in the fire protection CIM model, the weighting coefficients of the fire resistance rating data, facility status data, and the real-time personnel density data are determined; wherein, the basic building structure data includes the building structure fire resistance rating data; According to the preset scoring criteria, the fire resistance rating data, facility status data, and real-time personnel density data are respectively quantified and scored. The scores for each region are calculated using a preset weighting formula, and the fire risk level data for each region is determined based on the scores.

[0069] The weighting coefficient can be a numerical value that measures the degree of contribution of each influencing factor to the fire risk. It is set according to the importance of the factor. Specifically, the weight of fire resistance rating data can be set to 40%, facility status data to 35%, and real-time personnel density data to 25%.

[0070] Preset scoring criteria can be quantitative scoring rules set for each data point. For example, a fire resistance rating of Level 1 is worth 100 points, Level 2 is worth 80 points, normal fire protection facilities are worth 100 points, and minor malfunctions are worth 50 points.

[0071] Score quantification is the process of converting qualitative data into quantitative scores. For example, "fire resistance rating level 2" is converted into 80 points, and "personnel density 0.8 people / ㎡" is converted into 60 points.

[0072] The preset weighting formula can be a formula for calculating the overall risk score, specifically: ; Specifically, we can first set the weighting coefficients and scoring standards for each data point, then quantify the data into scores, and finally calculate the comprehensive score and determine the risk level using a weighted formula. For example, if an area has a fire resistance rating of 80 points, normal facilities of 100 points, and population density of 60 points, the comprehensive score would be: The score corresponds to an orange risk level.

[0073] This technical solution achieves accurate calculation of fire risk through clear weight allocation and quantification rules, avoids the subjectivity of traditional risk assessment, makes the risk levels of different areas more comparable and credible, and provides a clear basis for key fire prevention and control.

[0074] In one feasible embodiment, optionally, fire simulation is performed based on the fire protection CIM model, the real-time environmental data, and the surrounding fire protection resource data, including: Real-time environmental data is input into the fire protection CIM model to simulate the fire spread path and smoke diffusion range based on the thermal conductivity characteristics of building components; wherein, the real-time environmental data includes wind direction, temperature and humidity data; Acquire surrounding fire-fighting resource data, and calculate the optimal rescue route, resource arrival time, and evacuation route capacity limit by combining the fire spread path and the smoke diffusion range; wherein, the surrounding fire-fighting resource data includes fire truck location, water source distribution, number of rescue personnel, and equipment parameters; Based on the load-bearing capacity of evacuation routes and real-time personnel density data, the evacuation success rate is calculated, and the fire simulation results are obtained.

[0075] The thermal conductivity of building components refers to their ability to transfer heat. Different materials have different properties; for example, the thermal conductivity of concrete is 1.74 W / (m·K), while that of wood is 0.12 W / (m·K).

[0076] The fire spread path can be the route in which a fire spreads within a building. It is affected by factors such as building structure, materials, and wind direction. For example, in a northerly wind environment, a fire may spread from the south side of a building to the north side.

[0077] The smoke diffusion range can be the area in which smoke generated by a fire spreads within a building, and is related to environmental factors such as passageways, whether windows are open, and temperature.

[0078] Equipment parameters can be the performance indicators of fire and rescue equipment, such as a water tanker fire truck having a water capacity of 15 tons and a water gun range of 30 meters.

[0079] Evacuation success rate is the probability of successful evacuation of people inside a building. It is calculated by combining the carrying capacity of the evacuation route and the population density. For example, if the evacuation route can carry 1,000 people per hour and there are 500 people on site, the success rate is 100%.

[0080] This solution first inputs real-time environmental data into the model, simulates fire and smoke diffusion based on the thermal conductivity characteristics of components, and then calculates rescue parameters and evacuation success rate by combining fire resource data. For example, based on environmental data of a level 2 southerly wind and a temperature of 30°C, simulating the spread of fire to the south-facing stairwell, the solution calculates that the nearest fire truck will arrive in 5 minutes, and the evacuation success rate is 95%.

[0081] This technical solution can take into account the impact of environmental factors and building characteristics on fire, achieve accurate simulation of fire development and rescue effectiveness, provide a scientific basis for rescue route planning and resource allocation, and improve the practicality of emergency simulation.

[0082] In one feasible embodiment, optionally, the historical case database is linked to generate optimization suggestions through similarity matching to obtain complete emergency simulation results, including: Key feature parameters of each case are extracted from the historical case database. These key feature parameters include: fire type, building structure type, floor where the fire started, and successful rescue measures. A case feature matrix is ​​then constructed. Extract key feature parameters of the current simulation scenario to form a scenario feature vector; The cosine similarity algorithm is used to calculate the matching degree between the scene feature vector and each vector in the case feature matrix, and the successfully matched cases are selected. Extract successful rescue measures from matching case studies and generate suggestions for optimizing the simulation strategy.

[0083] Key characteristic parameters can be parameters that reflect the core characteristics of a fire scene, including fire type, such as electrical fire or gas fire; building structure type, such as frame structure or shear wall structure; floor where the fire started; and successful rescue measures.

[0084] A case feature matrix can be a matrix of key feature parameters of historical cases arranged according to preset rules, such as arranging the feature parameters of 100 historical cases into a 100-row, 4-column matrix.

[0085] Scene feature vectors can be vector data formed by converting the key feature parameters of the current scenario into a vector. The number of columns in the vector vector is the same as that in the case feature matrix. For example, the current scene feature vector may include fire type, building structure, location, presence or absence of personnel, such as [electrical fire, frame structure, 10 floors, empty].

[0086] The cosine similarity algorithm is an algorithm for calculating the similarity between two vectors. The value range is [-1, 1]. The closer the value is to 1, the higher the similarity. Specifically, a similarity threshold of 0.75 can be set. If the value exceeds this value, the match is successful.

[0087] This solution first extracts feature parameters from a historical case database to construct a matrix, then extracts current scene features to form a vector, calculates the matching degree using a cosine similarity algorithm, and finally extracts successful measures from the matching cases. For example, if the current electrical fire scenario has a similarity of 0.82 with an electrical fire case in an office building in 2023, the optimization suggestion of "prioritizing power cut-off and using dry powder fire extinguishers" from that case can be extracted.

[0088] The technical effects of this claim are as follows: Through standardized feature extraction and similarity calculation, the accurate reuse of historical rescue experience can be achieved, providing targeted optimization suggestions for current emergency simulations, solving the problem of lack of experience support in traditional simulations, and improving the scientificity and feasibility of rescue strategies.

[0089] In one feasible embodiment, optionally, a multi-view interaction channel is established to acquire front-line view marker data, and real-time linkage and update processing is performed based on the front-line view marker data and the fire protection CIM model, including: A multi-view interactive channel is built based on the 5G network to convert global data from the command center, AR perspective data from the front line, and analysis data from the expert group into a unified transmission format. Acquire fire point data marked by frontline firefighters using AR devices, wherein the fire point data includes at least one of precise coordinates, on-site photos, and text descriptions; The fire location data is synchronized to the corresponding coordinates of the fire protection CIM model, generating dynamic early warning indicators, which are then pushed to the expert group's perspective.

[0090] 5G networks are characterized by high speed and low latency, with transmission latency controllable to within 20 milliseconds.

[0091] A unified transmission format can be a unified data format set for data from multiple terminals, such as using JSON (JavaScript Object Notation) format, to ensure that data can be exchanged between the command center, the front line, and the expert group.

[0092] AR devices can be terminal devices using Augmented Reality (AR) technology, such as AR glasses and AR helmets, which can overlay and display on-site images and virtual information.

[0093] Dynamic warning signs can be dynamic prompt icons displayed in the fire protection CIM model, such as marking the fire point with a flashing red dot, with the text "Fire point: 15th floor east office" displayed next to it.

[0094] This solution can be based on a 5G network to build a channel, convert data from all terminals into a unified format, receive the labeled data uploaded by AR devices, synchronize it to the model, and push it to the expert group. For example, if a frontline firefighter uses AR glasses to mark "12th floor sprinkler system malfunction," this information will be synchronized to the command center model and pushed to the terminal of the fire experts at the rear within 1 second.

[0095] This technical solution utilizes 5G and AR technologies to achieve high-speed and precise linkage of information across multiple terminals, ensuring real-time synchronization of information between the command center, the front line, and the expert group. This solves the problem of information asymmetry in traditional rescue operations and improves the collaborative efficiency and accuracy of rescue command.

[0096] Example 2 In order to enable those skilled in the art to better understand the technical solution of this application, this application also provides a preferred embodiment. It should be understood that this preferred embodiment is intended to illustrate a specific implementation method and is not intended to limit the technical solution of this application.

[0097] Currently, fire rescue in high-rise complexes and large commercial buildings faces significant challenges. Traditional firefighting relies entirely on paper drawings, on-site reconnaissance, and manual experience. Data is scattered across different systems; retrieving critical data such as fire hydrant pressure, sprinkler status, and passageway access takes more than five minutes, making real-time synchronization impossible. Furthermore, fire spread paths and smoke diffusion ranges are estimated based on experience, often with deviations exceeding 30%. Moreover, existing solutions lack a unified 3D model platform, resulting in vague risk assessments and failing to meet the precise, rapid, and collaborative needs of modern firefighting. This is the core reason for developing this technology in this solution.

[0098] (a) Data Acquisition Layer; Basic model acquisition: Directly connect to the city's CIM (City Information Modeling) platform to download the target building's basic 3D model in FBX format. The model's coordinate accuracy reaches ±0.1 meters and includes core information such as the dimensions, materials, and spatial locations of building components.

[0099] Real-time data acquisition: 126 LoRa (Long Range Radio) sensors are deployed to collect real-time data on fire hydrant water pressure, sprinkler system valve status, smoke detector power levels, and alarm signals at a frequency of 5 seconds per acquisition. Laser rangefinders are installed at fire lane entrances to collect real-time data on lane width and obstruction area. High-definition surveillance cameras combined with the YOLOv5 target detection algorithm are used to identify population density in each area, with an identification error ≤0.05 people / ㎡.

[0100] Basic data retrieval: Extract basic building structure data from the building completion archives, focusing on the building structure fire resistance rating, such as Class I for office buildings and Class II for shopping malls, as well as information on component materials, and input them into the system database in a standardized manner.

[0101] (ii) Data fusion layer; Data cleaning: Write a data processing script in Python. First, identify outliers using the 3σ principle and replace them with the average value of the corresponding field. Then, check the percentage of missing values ​​in each data field and set a threshold of 5%. If the percentage of missing values ​​in a field exceeds 5%, use linear interpolation to complete the data to ensure that the data accuracy is ≥95%.

[0102] Format standardization: Cleaned unstructured data, such as fault photos taken on-site and verbal descriptions, are converted into key-value pair structured data with device number, attribute name, and attribute value using the NLTK natural language processing library.

[0103] Model fusion: Develop a dynamic fire protection attribute mapping algorithm to extract the three-dimensional coordinate parameters of each building component in the basic CIM model, establish a mapping relationship table between structured data and component coordinates, accurately mount the data to the corresponding position in the model according to the table, with a mounting deviation of ≤0.5 meters, and finally generate a fire protection CIM model of about 2.8GB.

[0104] (III) Analysis and Processing Layer; Risk level quantification: Set weighting coefficients, with building structure fire resistance rating accounting for 40%, fire protection facility status accounting for 35%, and personnel density accounting for 25%.

[0105] The scoring criteria are as follows: fire resistance rating: Level 1 100 points, Level 2 80 points; normal fire protection facilities: 100 points, minor malfunctions: 50 points, serious malfunctions: 20 points; personnel density: ≤0.5 people / ㎡ 30 points, 0.5-1 person / ㎡ 60 points, >1 person / ㎡ 100 points; the score for each area is calculated using the formula "risk quantification score = sum of quantification values ​​of each data point × corresponding weights", and the risk is divided into four levels: red (>90 points), orange (70-90 points), yellow (50-70 points), and green (<50 points).

[0106] Visual rendering: Using WebGL technology, risk level data is overlaid on the fire protection CIM model in the form of a heat map. It supports mouse zoom (1:100 to 1:1) and click query. The rendering refresh rate is 10 seconds / time, and the command personnel can intuitively view high-risk areas.

[0107] Emergency simulation: Fire simulation: Real-time environmental data, such as wind direction, temperature, and humidity, are collected by the rooftop weather station and input into FDS (Fire Dynamics Simulator). Based on the thermal conductivity characteristics of building components, the fire spread path (e.g., when the north wind is at level 3, smoke spreads to the evacuation stairwell 10 minutes after the fire starts on the 15th floor) and the smoke spread range are simulated.

[0108] Resource matching: The optimal rescue route is calculated by combining Dijkstra's algorithm with fire lane access data. For example, it takes 4 minutes and 20 seconds for a fire brigade 1.2 kilometers away to reach the scene. At the same time, the carrying capacity limit of evacuation routes (800 people per hour) and the evacuation success rate are calculated.

[0109] Case matching: Construct a historical case library containing 320 similar fire cases, extract key feature parameters of the current simulation scenario, such as fire type, building structure, and floor where the fire started, and match similar cases using a cosine similarity algorithm to extract successful rescue measures and generate optimization suggestions.

[0110] (iv) Application Interaction Layer; Establish a multi-perspective collaborative channel: Based on the 5G private network, the global data of the command center, the data of the front-line AR equipment, and the analysis data of the expert group are converted into a unified JSON transmission format; front-line firefighters mark the fire point data with AR glasses, including precise coordinates, on-site photos, and text descriptions. The data is synchronized to the 4K large screen of the command center and the tablet of the expert group within 1 second after being uploaded.

[0111] This technical solution innovatively incorporates a real-time GPS coordinate comparison mechanism, resolving the misalignment issue between traditional data and CIM models. It precisely controls the alignment deviation from over 1.2 meters to within 0.5 meters, achieving a unified model construction encompassing spatial form, fire protection functions, and real-time status. The solution optimizes the FDS fire simulation module algorithm, dynamically adjusting simulation parameters based on the thermal conductivity characteristics of building components and real-time environmental data. This reduces the simulation calculation time from 10 minutes to 20 seconds, while ensuring a projection deviation rate of ≤8%. The solution's frontline AR equipment supports one-click marking of fire and fault points, automatically generating structured data with timestamps, precise coordinates, and on-site images, eliminating the need for manual data entry and resolving the issues of information distortion and time consumption in traditional methods, improving operational efficiency by 80%. Furthermore, by comprehensively considering three core factors—building structure, facility status, and personnel density—and using the analytic hierarchy process (AHP) to determine scientific weights, it transforms fuzzy risk assessments into quantifiable scores, increasing risk identification accuracy to over 90%.

[0112] This technical solution has the following technical advantages: Data processing efficiency: The time for integrating multi-source data is reduced from the traditional 20 minutes to 1 minute, data integrity is ≥98%, and the loading speed of the fire protection CIM model is ≤8 seconds, enabling commanders to quickly obtain comprehensive and accurate fire protection information.

[0113] Risk identification capability: The accuracy rate of risk identification reaches 93.5%, which is 40% higher than traditional manual judgment. The visualization of heat maps makes high-risk areas clear at a glance, the targeting of fire prevention and control is improved by 60%, and the efficiency of early detection of hidden dangers is increased by 50%.

[0114] Accuracy of emergency simulation: The deviation rate between fire spread simulation and actual scenario is only 7.1%, the accuracy of rescue route planning is improved by 60%, and the optimization suggestions combined with historical cases greatly improve the scientific nature of decision-making, avoiding resource waste and dispatch delays.

[0115] Collaborative rescue efficiency: Emergency response time has been reduced from the traditional 15 minutes to 4 minutes and 30 seconds, and the synchronization delay between the command center and the front line is ≤1.5 seconds. Overall rescue efficiency has been improved by more than 60%. Based on the estimated pedestrian flow in XX Square, more than 200 people can be evacuated in the event of a fire, greatly reducing the risk of casualties.

[0116] Promotional value: The solution has strong compatibility. It can be adapted to various densely populated places such as hospitals, train stations, and large industrial parks by simply adjusting the model parameters and data interfaces. It has broad market application prospects.

[0117] Example 3 Figure 2 This is a structural schematic diagram of the fire-fighting 3D visualization and emergency simulation device based on CIM technology provided in Embodiment 3 of this application. Figure 2 As shown, the device includes: The data acquisition module 210 is used to acquire the basic CIM 3D model, fire protection-specific real-time data, and basic building structure data; wherein, the fire protection-specific real-time data includes fire protection facility status data, passageway data, and evacuation load data; The model building module 220 is used to perform data fusion processing based on the basic CIM 3D model and the fire-specific real-time data through a dynamic fire attribute mapping algorithm to obtain a fire CIM model. The visualization rendering module 230 is used to perform risk level quantification processing based on the fire protection CIM model and the building structure basic data, combined with a weighting algorithm, to obtain fire risk level data for each area, and to perform risk visualization rendering based on the fire risk level data for each area using a heat map. The emergency simulation module 240 is used to acquire real-time environmental data and surrounding fire-fighting resource data, perform fire simulation and resource matching processing based on the fire-fighting CIM model, the real-time environmental data and the surrounding fire-fighting resource data, and generate optimization suggestions through similarity matching by linking the historical case library to obtain complete emergency simulation results. The data synchronization module 250 is used to establish a multi-view interaction channel, acquire front-line view marker data, and perform real-time linkage and update processing with the fire protection CIM model based on the front-line view marker data to synchronize the view of the command center.

[0118] In this embodiment, the data acquisition module is used to acquire a basic CIM 3D model, fire-specific real-time data, and basic building structure data; wherein, the fire-specific real-time data includes fire-fighting facility status data, passageway data, and evacuation capacity data; the model construction module is used to perform data fusion processing based on the basic CIM 3D model and the fire-specific real-time data using a dynamic fire attribute mapping algorithm to obtain a fire-fighting CIM model; the visualization rendering module is used to perform risk level quantification processing based on the fire-fighting CIM model and the basic building structure data using a weighting algorithm to obtain fire risk level data for each area, and to perform risk visualization rendering using a heat map based on the fire risk level data for each area; the emergency simulation module is used to acquire real-time environmental data and surrounding fire-fighting resource data, perform fire simulation and resource matching processing based on the fire-fighting CIM model, the real-time environmental data, and the surrounding fire-fighting resource data, and generate optimization suggestions through similarity matching by linking with a historical case library to obtain a complete emergency simulation result; the data synchronization module is used to build a multi-view interactive channel, acquire front-line view marker data, and perform real-time linkage update processing based on the front-line view marker data and the fire-fighting CIM model to synchronize the view of the command center. This technical solution addresses the problem of fragmented traditional data by fusing multi-source fire protection data. The fire protection CIM model achieves a multi-dimensional, integrated display, improving data utilization efficiency. Risk quantification and heat map rendering provide a visual representation of fire risks, allowing command personnel to quickly locate high-risk areas and significantly improving risk identification accuracy. Dynamic simulations combined with real-time data enable more precise fire simulation and resource matching, while historical case studies provide scientific references for decision-making. Multi-perspective collaborative channels ensure real-time synchronization of information between the command center and the front lines, resolving information lag issues and comprehensively improving the efficiency and accuracy of rescue decision-making, effectively reducing the risk of casualties and property damage.

[0119] The fire-fighting 3D visualization and emergency simulation device based on CIM technology in this application embodiment can be a device, or it can be a component, integrated circuit or chip in a terminal.

[0120] The device can be a mobile electronic device or a non-mobile electronic device. For example, mobile electronic devices can be mobile phones, tablets, laptops, PDAs, in-vehicle electronic devices, wearable devices, ultra-mobile personal computers (UMPCs), netbooks, or personal digital assistants (PDAs), etc., while non-mobile electronic devices can be servers, network attached storage (NAS), personal computers (PCs), televisions (TVs), ATMs, or self-service machines, etc. The embodiments in this application do not impose specific limitations.

[0121] The fire-fighting 3D visualization and emergency simulation device based on CIM technology in this application embodiment can be a device with an operating system. This operating system can be Android, iOS, or other possible operating systems; this application embodiment does not specifically limit it.

[0122] The fire protection 3D visualization and emergency simulation device based on CIM technology provided in this application embodiment can realize the various processes of the above embodiments. To avoid repetition, it will not be described again here.

[0123] Example 4 like Figure 3 As shown, this application embodiment also provides an electronic device 300, including a processor 301, a memory 302, and a program or instructions stored in the memory 302 and executable on the processor 301. When the program or instructions are executed by the processor 301, they implement the various processes of the above-described embodiment of the fire protection three-dimensional visualization and emergency simulation method based on CIM technology and achieve the same technical effect. To avoid repetition, they will not be described again here.

[0124] It should be noted that the electronic devices in the embodiments of this application include the mobile electronic devices and non-mobile electronic devices described above.

[0125] Example 5 This application also provides a readable storage medium storing a program or instructions. When the program or instructions are executed by a processor, they implement the various processes of the above-described embodiment of the fire protection three-dimensional visualization and emergency simulation method based on CIM technology and achieve the same technical effect. To avoid repetition, they will not be described again here.

[0126] The processor is the processor in the electronic device described in the above embodiments. The readable storage medium includes computer-readable storage media, such as computer read-only memory (ROM), random access memory (RAM), magnetic disk, or optical disk.

[0127] Example 6 This application embodiment also provides a chip, which includes a processor and a communication interface. The communication interface and the processor are coupled. The processor is used to run programs or instructions to implement the various processes of the above-described embodiment of the fire protection three-dimensional visualization and emergency simulation method based on CIM technology, and can achieve the same technical effect. To avoid repetition, it will not be described again here.

[0128] It should be understood that the chip mentioned in the embodiments of this application may also be referred to as a system-on-a-chip, system chip, chip system, or system-on-a-chip, etc.

[0129] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element. Furthermore, it should be noted that the scope of the methods and apparatuses in the embodiments of this application is not limited to performing functions in the order shown or discussed, but may also include performing functions substantially simultaneously or in the reverse order, depending on the functions involved. For example, the described methods may be performed in a different order than described, and various steps may be added, omitted, or combined. Additionally, features described with reference to certain examples may be combined in other examples.

[0130] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a computer software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods described in the various embodiments of this application.

[0131] The embodiments of this application have been described above with reference to the accompanying drawings. However, this application is not limited to the specific embodiments described above. The specific embodiments described above are merely illustrative and not restrictive. Those skilled in the art can make many other forms under the guidance of this application without departing from the spirit and scope of the claims, and all of these forms are within the protection scope of this application.

[0132] The above description is merely a preferred embodiment and the technical principles employed in this application. This application is not limited to the specific embodiments described herein, and various obvious changes, readjustments, and substitutions that can be made by those skilled in the art will not depart from the scope of protection of this application. Therefore, although this application has been described in detail through the above embodiments, this application is not limited to the above embodiments, and may include more other equivalent embodiments without departing from the concept of this application, the scope of which is determined by the scope of the claims.

Claims

1. A fire-fighting 3D visualization and emergency simulation method based on CIM technology, characterized in that, The method includes: Acquire basic CIM 3D model, fire protection-specific real-time data, and basic building structure data; wherein, the fire protection-specific real-time data includes fire protection facility status data, passageway access data, and evacuation load data; Based on the basic CIM 3D model and the fire-specific real-time data, a fire-fighting CIM model is obtained through data fusion processing using a dynamic fire-fighting attribute mapping algorithm. Based on the fire protection CIM model and the basic building structure data, the risk level is quantified using a weighting algorithm to obtain fire risk level data for each area, and a heat map is used to visualize the risk based on the fire risk level data for each area. Acquire real-time environmental data and surrounding fire-fighting resource data. Based on the fire-fighting CIM model, the real-time environmental data, and the surrounding fire-fighting resource data, perform fire simulation and resource matching processing. Link with the historical case library to generate optimization suggestions through similarity matching to obtain complete emergency simulation results. A multi-view interactive channel is established to obtain front-line view marker data. Based on the front-line view marker data, the fire protection CIM model is updated in real time to synchronize the view of the command center.

2. The method according to claim 1, characterized in that, Based on the basic CIM 3D model and the fire-specific real-time data, a fire-fighting CIM model is obtained through data fusion processing using a dynamic fire attribute mapping algorithm, including: The fire-specific real-time data is standardized to convert unstructured data into key-value pair structured data. Extract the spatial coordinate parameters of the building components in the basic CIM 3D model, and establish a coordinate mapping table between the structured data and the corresponding building components; According to the coordinate mapping table, the structured data is mounted to the corresponding spatial position of the basic CIM 3D model, and the fire protection CIM model is output after the mounting is completed.

3. The method according to claim 2, characterized in that, Before standardizing the format of the fire-specific real-time data and converting the unstructured data into key-value pair structured data, the method further includes: Obtain standardized, real-time fire-specific data and detect the percentage of missing values ​​in each data field; If the percentage of missing values ​​in a certain data field is greater than a set threshold, linear interpolation will be used to fill in the missing values ​​in that field. Identify outliers in the data and replace them with the average value of the corresponding field.

4. The method according to claim 1, characterized in that, Based on the fire protection CIM model and the building structure foundation data, a weighted algorithm is used to quantify the risk level, resulting in fire risk level data for each area, including: By combining the fire protection facility status data and real-time personnel density data in the fire protection CIM model, the weighting coefficients of the fire resistance rating data, facility status data, and the real-time personnel density data are determined; wherein, the basic building structure data includes the building structure fire resistance rating data; According to the preset scoring criteria, the fire resistance rating data, facility status data, and real-time personnel density data are respectively quantified and scored. The scores for each region are calculated using a preset weighting formula, and the fire risk level data for each region is determined based on the scores.

5. The method according to claim 1, characterized in that, Fire simulation is performed based on the fire protection CIM model, the real-time environmental data, and the surrounding fire protection resource data, including: Real-time environmental data is input into the fire protection CIM model to simulate the fire spread path and smoke diffusion range based on the thermal conductivity characteristics of building components; wherein, the real-time environmental data includes wind direction, temperature and humidity data; Acquire surrounding fire-fighting resource data, and calculate the optimal rescue route, resource arrival time, and evacuation route capacity limit by combining the fire spread path and the smoke diffusion range; wherein, the surrounding fire-fighting resource data includes fire truck location, water source distribution, number of rescue personnel, and equipment parameters; Based on the load-bearing capacity of evacuation routes and real-time personnel density data, the evacuation success rate is calculated, and the fire simulation results are obtained.

6. The method according to claim 5, characterized in that, By linking with the historical case database and generating optimization suggestions through similarity matching, a complete emergency simulation result is obtained, including: Key feature parameters of each case are extracted from the historical case database. These key feature parameters include: fire type, building structure type, floor where the fire started, and successful rescue measures. A case feature matrix is ​​then constructed. Extract key feature parameters of the current simulation scenario to form a scenario feature vector; The cosine similarity algorithm is used to calculate the matching degree between the scene feature vector and each vector in the case feature matrix, and the successfully matched cases are selected. Extract successful rescue measures from matching case studies and generate suggestions for optimizing the simulation strategy.

7. The method according to claim 1, characterized in that, Establish a multi-view interactive channel to acquire front-line view marker data, and perform real-time linkage and update processing based on the front-line view marker data and the fire protection CIM model, including: A multi-view interactive channel is built based on the 5G network to convert global data from the command center, AR perspective data from the front line, and analysis data from the expert group into a unified transmission format. Acquire fire point data marked by frontline firefighters using AR devices, wherein the fire point data includes at least one of precise coordinates, on-site photos, and text descriptions; The fire location data is synchronized to the corresponding coordinates of the fire protection CIM model, generating dynamic early warning indicators, which are then pushed to the expert group's perspective.

8. A fire-fighting 3D visualization and emergency simulation device based on CIM technology, characterized in that, The device includes: The data acquisition module is used to acquire basic CIM 3D model, fire protection-specific real-time data, and basic building structure data; wherein, the fire protection-specific real-time data includes fire protection facility status data, passageway data, and evacuation load data; The model building module is used to perform data fusion processing based on the basic CIM 3D model and the fire-specific real-time data through a dynamic fire attribute mapping algorithm to obtain a fire CIM model. The visualization rendering module is used to quantify the risk level based on the fire protection CIM model and the building structure basic data, combined with a weighting algorithm, to obtain fire risk level data for each area, and to perform risk visualization rendering using a heat map based on the fire risk level data for each area. The emergency simulation module is used to acquire real-time environmental data and surrounding fire-fighting resource data. Based on the fire-fighting CIM model, the real-time environmental data, and the surrounding fire-fighting resource data, it performs fire simulation and resource matching processing. It also links with the historical case library to generate optimization suggestions through similarity matching, and obtains complete emergency simulation results. The data synchronization module is used to establish a multi-view interaction channel, acquire front-line view marker data, and perform real-time linkage and update processing based on the front-line view marker data and the fire protection CIM model to synchronize the view of the command center.

9. An electronic device, characterized in that, It includes a processor, a memory, and a program or instructions stored in the memory and executable on the processor, wherein when the program or instructions are executed by the processor, they implement the steps of the fire protection three-dimensional visualization and emergency simulation method based on CIM technology as described in any one of claims 1-7.

10. A readable storage medium, characterized in that, The program or instructions are stored on the readable storage medium, and when the program or instructions are executed by the processor, they implement the steps of the fire protection three-dimensional visualization and emergency simulation method based on CIM technology as described in any one of claims 1-7.

Images