Intelligent smoke monitoring data processing method and device based on 4G network

Abstract

The invention relates to the technical field of information transmission, and provides an intelligent smoke monitoring data processing method and device based on a 4G network, and the method comprises the steps: obtaining smoke concentration data in a monitoring region, carrying out the time sequence analysis and abnormal point recognition of the smoke concentration data, obtaining an emergency measure, and generating a response suggestion according to the emergency measure and an initial path; and a corresponding control instruction is generated according to the alarm information and the response suggestion, the control instruction is sent to a field response device through a 4G network to execute corresponding measures, an execution result is obtained, and a monitoring report is generated based on the execution result. By collecting and analyzing smoke concentration data in real time and combining a time sequence and an abnormal point identification technology, potential fire disasters can be found and responded in time, and the problem that under the condition that smoke increase occurs in multiple areas at the same time, abnormal point identification and path analysis lack enough accuracy is solved. And a fire source cannot be effectively identified and emergency response measures cannot be timely optimized.

Description

Technical Field

[0001] The present application relates to the technical field of information transmission, and in particular to a method and device for intelligent smoke monitoring data processing based on a 4G network. Background Art

[0002] Intelligent smoke monitoring systems play a vital role in the fields of industrial safety and urban safety. With the rapid development of urbanization and the increase in the density of industrial and residential areas, the prevention and response to fire accidents has become an important task in public safety management. Intelligent smoke monitoring systems effectively improve the speed and accuracy of emergency response by real-time monitoring of the concentration of smoke and other harmful gases, thereby reducing casualties and property losses.

[0003] Among the related technical means, smoke detectors are deployed in the monitoring area and the detected data is transmitted to the central processing system in real time through the 4G network. The central processing system analyzes the received data, detects the trend of smoke concentration changes through algorithms, and identifies whether there is a potential fire risk. The implementation of this technology makes monitoring more extensive and continuous, realizes early warning of potential fires, and greatly improves the efficiency and effectiveness of fire response.

[0004] Regarding the above technical solutions, although real-time data transmission and central processing can provide continuous monitoring and basic trend analysis, they are often limited by data processing capabilities and algorithm limitations when processing large-scale data and identifying complex fire patterns. In particular, when smoke increases in multiple areas at the same time, the identification of abnormal points and path analysis lack sufficient accuracy, making it impossible to effectively identify the source of the fire and timely optimize emergency response measures. Summary of the invention

[0005] In order to improve the problem that when smoke increases in multiple areas at the same time, the identification of abnormal points and path analysis lack sufficient accuracy, and the fire source cannot be effectively identified and emergency response measures cannot be optimized in a timely manner, the present application provides an intelligent smoke monitoring data processing method and device based on a 4G network.

[0006] The present invention provides an intelligent smoke monitoring data processing method based on a 4G network, comprising: acquiring smoke concentration data in a monitoring area, performing time series analysis and abnormal point identification on the smoke concentration data, and obtaining a time trend analysis result and an abnormal monitoring point; evaluating the time trend analysis result to obtain an evaluation result, and performing a comprehensive analysis on the evaluation result and the abnormal monitoring point to obtain a source analysis result; inputting the source analysis result into a preset machine learning model for analysis to obtain an initial path and an emergency response level, using a preset threshold to determine whether the emergency response level triggers an alarm, if an alarm is triggered, generating alarm information based on the emergency response level, performing level mapping on the alarm information to obtain emergency measures, and generating response suggestions based on the emergency measures and the initial path; generating corresponding control instructions based on the alarm information and the response suggestions, sending the control instructions to an on-site response device through a 4G network to execute corresponding measures, obtain execution results, and generate a monitoring report based on the execution results.

[0007] As a preferred solution, the steps of performing time series analysis and abnormal point identification on the smoke concentration data to obtain time trend analysis results and abnormal monitoring points include: performing denoising on the smoke concentration data to obtain purified data, applying a sliding window method to calculate the average smoke concentration of each time window of the purified data to obtain a time average concentration series; identifying abnormally increased time points in the time average concentration series by peak detection technology to obtain a number of abnormal time points; classifying all the abnormal time points by a clustering algorithm to obtain abnormal categories and abnormal frequencies, performing trend analysis on the abnormal categories by time series analysis, identifying the periodicity, trend and random components of the abnormal categories that change with time, and obtaining time trend analysis results; comparing the abnormal frequencies according to historical data to obtain abnormal comparison results, and performing statistical analysis on the abnormal comparison results to obtain abnormal monitoring points.

[0008] As a preferred embodiment, the steps of evaluating the time trend analysis results to obtain evaluation results, and comprehensively analyzing the evaluation results and the abnormal monitoring points to obtain source analysis results include: applying a correlation analysis algorithm to perform source inference on the time trend analysis results to obtain a potential source list, and using multivariate regression analysis based on environmental monitoring data and historical event records to perform a possibility assessment on each potential source in the potential source list to obtain an evaluation result; performing multi-factor comprehensive positioning of the location information of the abnormal monitoring points and the potential sources of the evaluation results to obtain a source analysis result; wherein the environmental monitoring data includes smoke concentration records and related meteorological conditions in the area where the source is located; and the historical event records include the frequency and intensity of similar historical events.

[0009] As a preferred solution, the step of performing multi-factor comprehensive positioning on the location information of the abnormal monitoring points and the potential sources of the evaluation results to obtain source analysis results includes: collecting and integrating the location information of the abnormal monitoring points, the environmental monitoring data and the historical event records to generate a comprehensive data set, calculating a weighted score for each potential source in the comprehensive data set by smoke concentration, meteorological conditions, frequency and intensity of historical events, and obtaining a weighted score list; applying GIS tools to spatially match and analyze the abnormal monitoring points and the potential sources of the evaluation results, identifying the spatial correlation between each source and the abnormal monitoring points, and generating a spatial coordinate mapping diagram; verifying the accuracy of the potential sources in the weighted score list and the potential sources in the spatial coordinate mapping diagram by a reliability analysis method, and calculating the reliability score of each potential source; and performing synchronous analysis in combination with the weighted score list, the spatial coordinate mapping diagram and the reliability score to obtain a source analysis result report.

[0010] As a preferred scheme, the step of using a preset threshold to determine whether the emergency response level triggers an alarm, generating an alarm message based on the emergency response level if an alarm is triggered, performing level mapping on the alarm message to obtain emergency measures, and generating response suggestions based on the emergency measures and the initial path includes: scoring the emergency response level by the Delphi method to obtain an urgency score, comparing the urgency score with a preset threshold, triggering an alarm if the urgency score is greater than the threshold, generating an alarm message, and marking the alarm level of the alarm message; mapping the alarm level with the result corresponding to the preset alarm level to obtain emergency measures, performing route planning on the initial path by a path planning algorithm to obtain an evacuation route, and generating response suggestions based on the evacuation route and the emergency measures.

[0011] As a preferred solution, the step of optimizing the initial path through a path planning algorithm to obtain an evacuation route, and generating response suggestions based on the evacuation route and the emergency measures includes: applying the Dijkstra algorithm to analyze all possible initial evacuation paths in the monitoring area to obtain an optimal evacuation route; formulating an evacuation plan based on the optimal evacuation route, integrating the evacuation plan with the emergency measures, and generating response suggestions.

[0012] As a preferred scheme, the steps of generating corresponding control instructions according to the alarm information and the response suggestions, sending the control instructions to the on-site response equipment through the 4G network to execute corresponding measures, obtaining execution results, and generating a monitoring report based on the execution results include: applying a decision tree analysis method to perform decision analysis on the alarm information and the response suggestions to obtain a control strategy, optimizing the control strategy through a weighted average algorithm to obtain control instructions; using a 4G network to send the control instructions to the on-site response equipment to execute corresponding measures, and monitoring the execution process in real time to obtain execution results; evaluating the execution results through a comparative analysis method to generate a monitoring report.

[0013] The present application also provides an intelligent smoke monitoring data processing device based on a 4G network, including: an acquisition module, used to acquire smoke concentration data in a monitoring area, perform time series analysis and abnormal point identification on the smoke concentration data, and obtain a time trend analysis result and an abnormal monitoring point; an evaluation module, used to evaluate the time trend analysis result, obtain an evaluation result, and perform a comprehensive analysis on the evaluation result and the abnormal monitoring point to obtain a source analysis result; an analysis module, used to input the source analysis result into a preset machine learning model for analysis, obtain an initial path and an emergency response level, use a preset threshold to determine whether the emergency response level triggers an alarm, if an alarm is triggered, generate an alarm message based on the emergency response level, perform level mapping on the alarm message, obtain emergency measures, and generate response suggestions based on the emergency measures and the initial path; a generation module, used to generate corresponding control instructions based on the alarm information and the response suggestions, send the control instructions to the on-site response equipment through the 4G network to execute corresponding measures, obtain execution results, and generate a monitoring report based on the execution results.

[0014] Compared with the prior art, the present application has the following beneficial effects: accurate fire source identification and timely response optimization. By real-time collection and analysis of smoke concentration data, combined with time series and outlier identification technology, potential fires can be discovered and responded to in a timely manner. The location of the fire source and the predicted path of fire spread can be further determined by using evaluation and comprehensive analysis technology. These analysis results are input into the machine learning model, which not only improves the accuracy of the prediction, but also realizes the dynamic emergency response level judgment for specific situations. Through the generation and execution of automated control instructions, fast and effective on-site emergency measures are implemented, which greatly improves the efficiency and effectiveness of fire response, reduces casualties and property losses, and improves the problem of insufficient accuracy in the identification and path analysis of outliers in the case of smoke increase in multiple areas at the same time, and cannot effectively identify the fire source and timely optimize emergency response measures. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0016] The structures, proportions, sizes, etc. illustrated in the drawings of this specification are only used to match the contents disclosed in the specification so as to facilitate understanding and reading by persons familiar with this technology. They are not used to limit the conditions under which the present invention can be implemented, and therefore have no substantive technical significance. Any structural modification, change in proportion or adjustment of size, without affecting the effects and purposes that can be achieved by the present invention, should still fall within the scope of the technical contents disclosed by the present invention.

[0017] Figure 1 It is a flow chart of a method for processing intelligent smoke monitoring data based on a 4G network provided by an embodiment of the present invention; Figure 2 It is a schematic block diagram of the structure of an intelligent smoke monitoring data processing device based on a 4G network provided in an embodiment of the present invention.

[0018] Description of reference numerals: 10. Intelligent smoke monitoring data processing device based on 4G network; 11. Acquisition module; 12. Evaluation module; 13. Analysis module; 14. Generation module. DETAILED DESCRIPTION

[0019] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are 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 creative work are within the scope of protection of the present invention.

[0020] The flowcharts shown in the accompanying drawings are only examples and do not necessarily include all the contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps may also be decomposed, combined or partially merged, so the actual execution order may change according to actual conditions.

[0021] It should also be understood that the terms used in this application specification are only for the purpose of describing specific embodiments and are not intended to limit the application. As used in this application specification and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include plural forms.

[0022] It should be further understood that the term “and / or” used in the specification and appended claims refers to any combination and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0023] The technical solution of the present invention is further described below with reference to the accompanying drawings and through specific implementation methods.

[0024] Embodiment 1: like Figure 1 As shown, the intelligent smoke monitoring data processing method based on 4G network provided in the embodiment of the present application includes steps S100 to S400.

[0025] Step S100: Acquire smoke concentration data in the monitoring area, perform time series analysis and abnormal point identification on the smoke concentration data, and obtain time trend analysis results and abnormal monitoring points.

[0026] In this step, smoke concentration data is automatically collected through sensors deployed in key areas; specifically, data is recorded regularly using highly sensitive smoke sensors, which are then uploaded to the central monitoring system in real time via the 4G network. The central system uses advanced data processing algorithms to perform time series analysis on smoke concentration data in order to observe the changing trends of the data, and uses statistical methods to automatically identify abnormal points.

[0027] For example, inside a large warehouse, sensors collect smoke concentration data once a minute. When the data suddenly rises to more than twice the regular measurement value, the system automatically marks the data point as an abnormal monitoring point and triggers further analysis.

[0028] Step S200: Evaluate the time trend analysis results to obtain evaluation results, and conduct comprehensive analysis on the evaluation results and abnormal monitoring points to obtain source analysis results.

[0029] In this step, the time trend analysis results are evaluated in depth to determine the consistency and speed of smoke concentration increase; specifically, trend lines and pattern recognition techniques are used to evaluate the potential path and speed of smoke diffusion. Combined with the data from abnormal monitoring points, the system conducts a comprehensive analysis to infer the location of the fire source.

[0030] For example, if three consecutive abnormal monitoring points show a similar rapid growth trend, the system connects these points and infers the location of the smoke source, while taking into account wind direction and wind speed information to optimize the location of the source.

[0031] Step S300: Input the source analysis results into the preset machine learning model for analysis to obtain the initial path and emergency response level, use the preset threshold to determine whether the emergency response level triggers an alarm, and if an alarm is triggered, generate alarm information based on the emergency response level, perform level mapping on the alarm information, obtain emergency measures, and generate response suggestions based on the emergency measures and the initial path.

[0032] In this step, the source analysis results are input into a pre-trained machine learning model to predict the initial path of fire spread and the emergency response level; specifically, the model calculates the most likely fire development path based on historical data and current analysis results, and determines the degree of urgency. If the response level output by the model exceeds the preset threshold, the alarm system is automatically triggered, the corresponding alarm information is generated, and mapped to different levels of emergency measures.

[0033] For example, if the model predicts that the fire has an extremely high spread rate and impact area, the system maps the level to the highest emergency response level and generates recommendations for evacuation and firefighting response.

[0034] Step S400: Generate corresponding control instructions according to the alarm information and response suggestions, send the control instructions to the on-site response equipment through the 4G network to execute corresponding measures, obtain the execution results, and generate a monitoring report based on the execution results.

[0035] In this step, the system automatically generates control instructions based on the alarm level and response suggestions, and quickly sends them to the relevant on-site equipment through the 4G network for execution; specifically, it automatically starts the sprinkler system and opens the emergency exit door. The execution results are collected and sent back to the central system to evaluate the actual effect of the emergency response and generate a detailed monitoring report.

[0036] For example, in an actual emergency response, the control system automatically adjusted the ventilation system inside the warehouse to limit the further spread of smoke, and simultaneously activated the automatic sprinkler system to suppress the fire.

[0037] In this embodiment, by obtaining the smoke concentration data in the monitoring area, and then performing time series analysis and abnormal point identification on the smoke concentration data, the time trend analysis results and abnormal monitoring points are obtained. Based on these results, further evaluation is performed, and the evaluation results and abnormal monitoring points obtained are comprehensively analyzed to obtain the source analysis results. This source analysis result is then input into the preset machine learning model to analyze and predict the initial path and emergency response level. The system will determine whether to trigger an alarm based on a preset threshold, and generate an alarm message based on the obtained emergency response level. After level mapping, this alarm information is converted into specific emergency measures, and then a response suggestion is generated. Finally, a control instruction is generated based on the alarm information and the response suggestion, and is sent to the on-site response equipment through the 4G network to execute the corresponding measures, and finally a monitoring report is generated based on the execution results.

[0038] By efficiently integrating the time series analysis and anomaly identification of smoke concentration data, the diffusion trend of smoke and its potential fire source location can be tracked and predicted more accurately, thereby greatly improving the accuracy and timeliness of fire warnings. The use of machine learning models to further analyze the source results not only enhances the depth of data processing, but also improves the level of intelligence of emergency response, making emergency measures more targeted and effective. In addition, the control instructions generated by the system can achieve rapid on-site response, ensuring that effective measures can be taken at the early stage of the fire, effectively reducing the potential damage and risks caused by the fire, and significantly improving the public safety protection capabilities.

[0039] Embodiment 2: In step S100, the steps of performing time series analysis and abnormal point identification on smoke concentration data to obtain time trend analysis results and abnormal monitoring points include: The smoke concentration data is denoised to obtain purified data, and the sliding window method is used to calculate the average smoke concentration in each time window of the purified data to obtain the time average concentration series.

[0040] The original data collected by the sensor is denoised to filter out environmental noise and abnormal fluctuation factors to ensure data accuracy. Specifically, the median filter and wavelet transform method are used to remove noise, and the average concentration value of each time window is calculated by the sliding window method to form a time average concentration series.

[0041] For example, the data collected by sensors located in a factory workshop at different time points are interfered by machine operation and other environmental factors. Median filtering can effectively remove these interferences and obtain purified smoke concentration data.

[0042] The peak detection technology is used to identify the time points of abnormal increase in the time-averaged concentration series, and several abnormal time points are obtained.

[0043] The mutation points in the time series are identified by applying peak detection technology. Specifically, the first-order difference and local extreme value detection methods are used to identify the time points with sudden concentration changes and mark them as abnormal time points.

[0044] For example, in a time series data, the smoke concentration at a certain time point suddenly rises to more than three times the normal value. Peak detection can accurately capture this mutation point and mark it as an abnormal time point.

[0045] Clustering algorithms are used to classify all abnormal time points to obtain abnormal categories and abnormal frequencies. Trend analysis of abnormal categories is performed through time series analysis to identify the periodicity, trend and random components of abnormal categories changing over time, and obtain time trend analysis results.

[0046] All abnormal time points are classified by using the K-means clustering algorithm. Specifically, the abnormal points are clustered according to the feature vector to identify different types of abnormalities and their frequencies. The periodicity and trend of various types of abnormalities are analyzed through time series analysis methods, such as the autoregressive integrated moving average model (ARIMA).

[0047] For example, in the abnormal monitoring data within a year, the categories with abnormally increased occurrence during the summer high temperature period are identified and their periodic changes are analyzed.

[0048] The abnormal frequency is compared with the historical data to obtain the abnormal comparison result, and the abnormal comparison result is statistically analyzed to obtain the abnormal monitoring point.

[0049] By comparing the current abnormal frequency with historical data, specifically, using statistical analysis methods such as the chi-square test, it is evaluated whether the current abnormal frequency is significantly higher than the historical average level, and the monitoring points with significant abnormalities are identified.

[0050] For example, within the same monitoring area, the number of abnormal points in the current month is significantly higher than the average level of the past five years, and the chi-square test confirms that there is an abnormality in that month.

[0051] In step S200, a correlation analysis algorithm is applied to perform source inference on the time trend analysis results to obtain a potential source list, and a multivariate regression analysis is used based on environmental monitoring data and historical event records to perform a possibility assessment on each potential source in the potential source list to obtain an assessment result.

[0052] The Pearson correlation coefficient method is used to infer the source of the time trend analysis results. Specifically, by calculating the correlation coefficient between each potential source and the abnormal time point, the potential sources with high correlation are screened out. Based on environmental monitoring data and historical event records, the multivariate linear regression model is used to evaluate the possibility of each potential source and obtain the evaluation results.

[0053] For example, a correlation analysis was conducted on multiple smoke sources in an industrial area, and it was found that the emission outlet of a factory building had the highest correlation at multiple abnormal time points, and it was evaluated as the source.

[0054] The location information of abnormal monitoring points and the potential sources of assessment results are comprehensively located based on multiple factors to obtain source analysis results; among them, environmental monitoring data include smoke concentration records and related meteorological conditions in the area where the source is located; historical event records include the frequency and intensity of similar historical events.

[0055] A multi-factor comprehensive analysis is conducted on the location information of abnormal monitoring points, environmental monitoring data and historical event records. Specifically, the weighted factor method is used to comprehensively consider factors such as smoke concentration, wind speed and direction, temperature and humidity, and calculate the comprehensive score of each potential source.

[0056] For example, in an industrial park, by analyzing wind speed and direction data, it was found that the abnormal monitoring points of a factory under a specific wind direction highly coincided with its emission period, and its comprehensive score was the highest.

[0057] Among them, the steps of comprehensively locating the location information of abnormal monitoring points and potential sources of assessment results by multiple factors to obtain source analysis results include: The location information of abnormal monitoring points, environmental monitoring data and historical event records are collected and integrated to generate a comprehensive data set. A weighted score is calculated for each potential source in the comprehensive data set based on smoke concentration, meteorological conditions, frequency and intensity of historical events to obtain a weighted score list.

[0058] A comprehensive data set is generated by collecting historical records of smoke concentration, meteorological conditions (such as wind speed, wind direction, temperature, humidity) and similar events in the region over the years. Specifically, a weighted scoring method is used to calculate the weighted scores of each indicator and form a weighted score list of potential sources.

[0059] For example, by integrating and analyzing the data of an industrial zone over the past five years, we can identify the high-frequency emissions of high-pollution sources under specific meteorological conditions and obtain a list of sources with the highest weighted scores.

[0060] GIS tools are used to spatially match and analyze the potential sources of abnormal monitoring points and assessment results, identify the spatial correlation between each source and abnormal monitoring points, and generate a spatial coordinate map.

[0061] By applying geographic information system (GIS) tools, spatial matching analysis is performed on each abnormal monitoring point and potential source. Specifically, the data of the abnormal monitoring point is mapped to geographic coordinates, and the location of the potential source is compared to generate a spatial coordinate mapping diagram.

[0062] For example, the data of outliers and potential sources can be imported into the GIS system to generate a spatial distribution map that visually displays the geographical location relationship between each source and the outliers.

[0063] The accuracy of potential sources in the weighted scoring list and the potential sources in the spatial coordinate mapping diagram was verified by reliability analysis, and the reliability score of each potential source was calculated.

[0064] The accuracy of potential sources was verified through reliability analysis. Specifically, the Bayesian reliability analysis method was used to calculate the reliability score of each potential source and evaluate its reliability as an actual source.

[0065] For example, through Bayesian reliability analysis, high-frequency potential sources are matched with abnormal monitoring points, and their reliability scores are calculated, confirming that the reliability of a factory's emission outlet is the highest.

[0066] Combine the weighted score list, spatial coordinate map and reliability score for synchronous analysis to obtain a source analysis result report.

[0067] A detailed source analysis results report is generated by comprehensively evaluating all analysis results, specifically combining a weighted score list, spatial coordinate mapping diagram and reliability score.

[0068] For example, after combining all the above data and conducting a comprehensive analysis, the report clearly points out that a certain emission outlet is the source of the smoke and provides a detailed chain of evidence.

[0069] In step S300, a preset threshold is used to determine whether the emergency response level triggers an alarm. If an alarm is triggered, an alarm message is generated based on the emergency response level, and the alarm message is level mapped to obtain emergency measures. The steps of generating response suggestions based on the emergency measures and the initial path include: The emergency response level is scored by the Delphi method to obtain an urgency score, which is then compared with a preset threshold. If the urgency score is greater than the threshold, an alarm is triggered, an alarm message is generated, and the alarm level of the alarm message is marked.

[0070] The Delphi method is used to score the urgency of emergency response events. Specifically, the final urgency score is obtained by combining the scoring results of multiple experts. The score is compared with the response threshold preset by the system. If it is greater than the threshold, an alarm is triggered and the corresponding alarm information is generated.

[0071] For example, during the review process, the urgency score of an abnormal concentration increase event was assessed as 8.5, which is higher than the threshold of 7.0, and the system immediately triggered the highest level alarm.

[0072] The alarm level is mapped with the result corresponding to the preset alarm level to obtain the emergency measures, the initial path is planned by the path planning algorithm to obtain the evacuation route, and the response suggestions are generated based on the evacuation route and emergency measures.

[0073] Through the preset emergency plan, different levels of alarm information are mapped to corresponding emergency measures. Specifically, a path planning algorithm such as the A algorithm is used to calculate the optimal evacuation route and generate comprehensive emergency response recommendations.

[0074] For example, in an alarm event, the system maps the third-level alarm to immediate evacuation and activates the fire protection system, and calculates the optimal evacuation route through the A algorithm.

[0075] The steps of optimizing the initial path through a path planning algorithm to obtain an evacuation route and generating response suggestions based on the evacuation route and emergency measures include: The Dijkstra algorithm is used to analyze all possible initial evacuation paths in the monitoring area to obtain the optimal evacuation route.

[0076] All possible evacuation paths are analyzed by applying Dijkstra algorithm in emergency response plan. Specifically, the shortest and safest evacuation route is determined by combining geographic information system (GIS) and real-time monitoring data.

[0077] For example, when a fire occurs in a large shopping mall, the system analyzes the real-time congestion of each exit and passageway and calculates an evacuation route that avoids peak traffic flow and reaches a safe area in the shortest time.

[0078] Develop an evacuation plan based on the optimal evacuation route, integrate the evacuation plan with emergency measures, and generate response recommendations.

[0079] By converting the calculated optimal evacuation route into a specific evacuation plan, specifically, developing detailed evacuation steps, including evacuation instructions and route guidance, and combining it with preset emergency measures, a complete emergency response recommendation is generated.

[0080] For example, the shopping mall management system formulates a detailed evacuation plan based on the optimal evacuation route, prompts customers to evacuate quickly according to the path signs, and activates the broadcasting system to guide the crowd to evacuate in an orderly manner.

[0081] In step S400, a decision tree analysis method is applied to perform decision analysis on the alarm information and the response suggestion to obtain a control strategy, and the control strategy is optimized by a weighted average algorithm to obtain a control instruction.

[0082] A decision tree model is constructed to perform decision analysis on alarm information and response suggestions. Specifically, response measures in different situations are selected and optimized through decision tree nodes, and the final control strategy is adjusted through a weighted average algorithm.

[0083] For example, when faced with different fire levels, the decision tree model selects the corresponding level of water sprinkler system activation and optimizes the spraying range and intensity based on real-time wind direction data.

[0084] Use the 4G network to send control instructions to the on-site response equipment to execute corresponding measures, and monitor the execution process in real time to obtain the execution results.

[0085] The optimized control instructions are quickly sent to the on-site response equipment through the 4G network. Specifically, the fire extinguishers, sprinkler systems and ventilation equipment are automatically started, and their execution is monitored in real time to ensure the effectiveness of the emergency response.

[0086] For example, when a fire breaks out inside a factory, the system promptly activates fire-fighting equipment in each area through the 4G network, and provides feedback on the progress of fire-fighting through a real-time monitoring system.

[0087] Evaluate the implementation results through comparative analysis and generate a monitoring report.

[0088] The execution results of emergency response are evaluated by using comparative analysis method. Specifically, the actual execution results are compared with the expected results, the effectiveness and response speed of emergency measures are analyzed, and a detailed monitoring report is generated.

[0089] For example, after a fire emergency drill, the system evaluates the response time and fire-fighting effectiveness of each device, and the generated monitoring report records in detail the execution effect and improvement suggestions of each step.

[0090] In this embodiment, by comprehensively using a variety of technical means, accurate monitoring and analysis of smoke concentration data in the monitoring area is achieved, and a complete emergency response mechanism is constructed through intelligent algorithm models and real-time network communication systems. In this process, by accurately identifying smoke anomalies and locating the source, the system can respond quickly and provide the best emergency advice, thereby effectively preventing and controlling the occurrence and spread of fires. The system not only improves the accuracy and timeliness of fire warnings, but also significantly reduces the damage to personnel and property caused by fires through intelligent emergency response measures, and improves the overall level of public and industrial safety protection. Through the comprehensive application of these means, it is ensured that actions can be taken quickly and effectively in the early stages of a fire, effectively reducing the potential damage and risks caused by a fire, and significantly improving the public safety protection capabilities.

[0091] Embodiment 3: like Figure 2As shown, the present application also provides an intelligent smoke monitoring data processing device 10 based on a 4G network, including an acquisition module 11, an evaluation module 12, an analysis module 13 and a generation module 14.

[0092] The acquisition module 11 is mainly used to acquire smoke concentration data in the monitoring area, perform time series analysis and abnormal point identification on the smoke concentration data, and obtain time trend analysis results and abnormal monitoring points.

[0093] The evaluation module 12 is mainly used to evaluate the time trend analysis results to obtain the evaluation results, and to conduct a comprehensive analysis of the evaluation results and abnormal monitoring points to obtain the source analysis results.

[0094] The analysis module 13 is mainly used to input the source analysis results into a preset machine learning model for analysis, obtain the initial path and emergency response level, and use the preset threshold to determine whether the emergency response level triggers an alarm. If an alarm is triggered, an alarm message is generated based on the emergency response level, and the alarm information is level-mapped to obtain emergency measures, and response recommendations are generated based on the emergency measures and the initial path.

[0095] The generation module 14 is mainly used to generate corresponding control instructions according to the alarm information and response suggestions, send the control instructions to the on-site response equipment through the 4G network to execute corresponding measures, obtain the execution results, and generate a monitoring report based on the execution results.

[0096] In this embodiment, by integrating multiple functional modules in the intelligent smoke monitoring data processing device, efficient monitoring and processing of smoke concentration data is achieved. The acquisition module 11 is responsible for real-time acquisition of smoke concentration data in the monitoring area, and obtains time trend analysis results and abnormal monitoring points through time series analysis and abnormal point identification technology. The evaluation module 12 comprehensively evaluates the time trend analysis results, combines environmental monitoring data and historical event records, uses multiple regression analysis and correlation analysis methods to evaluate the possibility of potential fire sources, and obtains detailed source analysis results. Through clustering algorithms and abnormal frequency comparison, the periodicity and trend of abnormal categories are evaluated to provide a reliable basis for source location. The analysis module 13 uses a preset machine learning model to further analyze the source analysis results, generate an initial path and emergency response level, and judge whether to trigger an alarm through the Delphi method and threshold comparison. After the alarm is triggered, the generation module 14 generates corresponding control instructions according to the alarm information, sends them to the on-site response equipment through the 4G network, and executes corresponding emergency measures, such as starting the sprinkler system and opening the emergency exit. The generation module 14 is also responsible for real-time monitoring of the execution results, using the weighted average algorithm to optimize the control strategy to ensure the efficiency and accuracy of the emergency response. By comparing and analyzing the execution results, a detailed monitoring report is generated to provide data support for the optimization of subsequent emergency plans.

[0097] It should be noted that technicians in the relevant technical field can clearly understand that for the convenience and conciseness of description, the specific working process of the above-described device and each module can refer to the corresponding process in the aforementioned embodiment of the intelligent smoke monitoring data processing method based on 4G network, and will not be repeated here.

[0098] As described above, 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 the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features thereof may be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. An intelligent smoke monitoring data processing method based on 4G network, characterized in that: include: Acquire smoke concentration data in the monitoring area, perform time series analysis and abnormal point identification on the smoke concentration data, and obtain time trend analysis results and abnormal monitoring points; Evaluate the time trend analysis result to obtain an evaluation result, and comprehensively analyze the evaluation result and the abnormal monitoring point to obtain a source analysis result; Input the source analysis result into a preset machine learning model for analysis to obtain an initial path and an emergency response level, use a preset threshold to determine whether the emergency response level triggers an alarm, if an alarm is triggered, generate alarm information based on the emergency response level, perform level mapping on the alarm information, obtain emergency measures, and generate response suggestions based on the emergency measures and the initial path; Generate corresponding control instructions according to the alarm information and the response suggestion, send the control instructions to the on-site response equipment through the 4G network to execute corresponding measures, obtain execution results, and generate a monitoring report based on the execution results.

2. The intelligent smoke monitoring data processing method based on 4G network according to claim 1 is characterized in that: The step of performing time series analysis and abnormal point identification on the smoke concentration data to obtain time trend analysis results and abnormal monitoring points includes: De-noising the smoke concentration data to obtain purified data, and applying a sliding window method to calculate the average smoke concentration of each time window of the purified data to obtain a time average concentration sequence; Identifying abnormally increased time points in the time-averaged concentration sequence by peak detection technology to obtain a number of abnormal time points; Using a clustering algorithm to classify all the abnormal time points, obtain abnormal categories and abnormal frequencies, perform trend analysis on the abnormal categories through time series analysis, identify the periodicity, trend and random components of the abnormal categories over time, and obtain time trend analysis results; The abnormal frequency is compared with historical data to obtain abnormal comparison results, and the abnormal comparison results are statistically analyzed to obtain abnormal monitoring points.

3. The intelligent smoke monitoring data processing method based on 4G network according to claim 1 is characterized in that: The step of evaluating the time trend analysis result to obtain an evaluation result, and comprehensively analyzing the evaluation result and the abnormal monitoring point to obtain a source analysis result includes: Applying a correlation analysis algorithm to perform source inference on the time trend analysis results to obtain a potential source list, and using a multivariate regression analysis based on environmental monitoring data and historical event records to perform a possibility assessment on each potential source in the potential source list to obtain an assessment result; The location information of the abnormal monitoring point and the potential source of the assessment result are comprehensively located based on multiple factors to obtain the source analysis result; wherein the environmental monitoring data includes the smoke concentration record and related meteorological conditions in the area where the source is located; and the historical event record includes the frequency and intensity of similar historical events.

4. The intelligent smoke monitoring data processing method based on 4G network according to claim 3 is characterized in that: The step of performing multi-factor comprehensive positioning of the location information of the abnormal monitoring point and the potential source of the evaluation result to obtain the source analysis result includes: Collect and integrate the location information of the abnormal monitoring point, the environmental monitoring data and the historical event records to generate a comprehensive data set, calculate a weighted score for each potential source in the comprehensive data set by smoke concentration, meteorological conditions, and the frequency and intensity of historical events, and obtain a weighted score list; Using GIS tools to spatially match and analyze the abnormal monitoring points and potential sources of the assessment results, identify the spatial correlation between each source and the abnormal monitoring points, and generate a spatial coordinate mapping diagram; Verifying the accuracy of the potential sources in the weighted scoring list and the potential sources in the spatial coordinate mapping diagram by a reliability analysis method, and calculating the reliability score of each potential source; The weighted score list, the spatial coordinate map and the reliability score are combined for synchronous analysis to obtain a source analysis result report.

5. The intelligent smoke monitoring data processing method based on 4G network according to claim 1 is characterized in that: The step of using a preset threshold to determine whether the emergency response level triggers an alarm, generating alarm information based on the emergency response level if an alarm is triggered, performing level mapping on the alarm information to obtain emergency measures, and generating response suggestions based on the emergency measures and the initial path includes: The emergency response level is scored by the Delphi method to obtain an urgency score, and the urgency score is compared with a preset threshold value. If the urgency score is greater than the threshold value, an alarm is triggered, an alarm message is generated, and an alarm level of the alarm message is marked; The alarm level is mapped with the result corresponding to the preset alarm level to obtain emergency measures, the initial path is route planned by a path planning algorithm to obtain an evacuation route, and a response suggestion is generated based on the evacuation route and the emergency measures.

6. The intelligent smoke monitoring data processing method based on 4G network according to claim 5 is characterized in that: The step of optimizing the initial path by a path planning algorithm to obtain an evacuation route, and generating a response suggestion based on the evacuation route and the emergency measures comprises: Dijkstra algorithm is used to analyze all possible initial evacuation paths in the monitoring area to obtain the optimal evacuation route; An evacuation plan is formulated according to the optimal evacuation route, and the evacuation plan is integrated with the emergency measures to generate a response recommendation.

7. The intelligent smoke monitoring data processing method based on 4G network according to claim 1 is characterized in that: The step of generating corresponding control instructions according to the alarm information and the response suggestion, sending the control instructions to the on-site response equipment through the 4G network to execute corresponding measures, obtaining execution results, and generating a monitoring report based on the execution results includes: Applying a decision tree analysis method to perform decision analysis on the alarm information and the response suggestion to obtain a control strategy, and optimizing the control strategy through a weighted average algorithm to obtain a control instruction; The control instructions are sent to the on-site response equipment using the 4G network to execute corresponding measures, and the execution process is monitored in real time to obtain the execution results; The execution results are evaluated by comparative analysis and a monitoring report is generated.

8. An intelligent smoke monitoring data processing device based on 4G network, characterized in that: include: An acquisition module is used to acquire smoke concentration data in the monitoring area, perform time series analysis and abnormal point identification on the smoke concentration data, and obtain time trend analysis results and abnormal monitoring points; An evaluation module is used to evaluate the time trend analysis result to obtain an evaluation result, and to comprehensively analyze the evaluation result and the abnormal monitoring point to obtain a source analysis result; An analysis module, used to input the source analysis result into a preset machine learning model for analysis, obtain an initial path and an emergency response level, use a preset threshold to determine whether the emergency response level triggers an alarm, if an alarm is triggered, generate alarm information based on the emergency response level, perform level mapping on the alarm information, obtain emergency measures, and generate response suggestions based on the emergency measures and the initial path; A generation module is used to generate corresponding control instructions according to the alarm information and the response suggestion, send the control instructions to the on-site response equipment through the 4G network to execute corresponding measures, obtain execution results, and generate a monitoring report based on the execution results.

Images