Intelligent fire alarm method and system based on Internet

Abstract

The invention belongs to the technical field of fire alarm, and discloses an Internet-based intelligent fire alarm method and system, and the method comprises the following steps: analyzing the temperature, humidity and electrical equipment states, carrying out the real-time data transmission through the Internet, carrying out the data classification, recognizing a fire risk index, and generating an environment risk analysis result; potential fire risks are recognized in time by analyzing temperature, humidity and electrical equipment states, early warning can be carried out at the initial stage of fire formation, potential damage of the fire is remarkably reduced, the response speed and prevention capacity of fire alarm are remarkably improved, and the safety of fire protection is improved. Real-time data transmission ensures that information can be quickly transmitted to a fire fighting center at the initial stage of a fire, an emergency response unit is allowed to prepare in advance, casualties and property losses are effectively reduced, the adaptability to different environment conditions is enhanced, important data are provided for fire post-analysis, and optimization and adjustment of future strategies are facilitated.

Description

Technical Field

[0001] The present invention belongs to the technical field of fire alarm technology, and in particular, relates to an Internet-based intelligent fire alarm method and system. Background Art

[0002] The field of fire alarm technology mainly involves the design, implementation and management of systems for detecting early signs of fire (such as smoke, flames and abnormal temperatures). It has evolved from basic smoke detectors and fire alarms to comprehensive safety solutions that integrate advanced sensing technologies, automatic control systems and real-time data analysis. Modern fire alarm systems can include a variety of sensors, such as photoelectric sensors, ion sensors, thermal sensors and gas detectors, which can be connected to the Internet and perform real-time monitoring and analysis of data through a central monitoring system. They can not only provide a rapid response when a fire occurs, but also help prevent the occurrence of fires through data prediction and trend analysis.

[0003] Among them, the Internet-based smart fire alarm method refers to the use of Internet technology to enhance the function and efficiency of traditional fire alarm systems, and realize remote monitoring, data sharing and intelligent analysis by connecting the fire alarm system to the Internet; the main purpose is to realize real-time monitoring of fire conditions in buildings, and quickly transmit alarm information to fire centers and related emergency response units to reduce casualties and property losses; Internet-based systems can collect and analyze large amounts of data to help optimize firefighting strategies and improve the effectiveness of preventive measures; through intelligent algorithms, they can identify potential fire risks, issue early warnings, and effectively improve the intelligence level of fire safety management.

[0004] Although existing fire alarm technology includes a variety of sensors and real-time monitoring systems, it still has shortcomings in processing complex data and conducting efficient risk assessments. Data analysis relies on post-processing rather than real-time analysis, which limits the system's response speed in emergency situations. The risk assessment in existing technologies does not take into account posterior probability, resulting in insufficient flexibility in responding to environmental changes and the inability to accurately adjust the alarm system to respond to specific risk levels. Static risk assessment models lead to false alarms or missed alarms under changing environmental conditions, affecting the accuracy and reliability of fire alarms. For example, when changes in specific environmental conditions do not reach the preset threshold, the existing system cannot trigger an alarm in time, which increases the risk of fire to a certain extent. Summary of the Invention

[0005] The technical problem to be solved by the present invention is to provide an Internet-based smart fire alarm method and system, which can significantly improve the response speed and prevention capability of fire alarms through the comprehensive application of real-time monitoring and intelligent analysis.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions: An Internet-based intelligent fire alarm method includes the following steps: S1: By analyzing temperature, humidity, and electrical equipment status, using the Internet for real-time data transmission, performing data classification, and identifying fire risk indicators, it generates environmental risk analysis results; S2: Using the environmental risk analysis results, construct a probability update model, calculate the posterior probability under differentiated environmental conditions, analyze the fire risk level using the posterior probability, and obtain a posterior probability update result; S3: Using the posterior probability update result, the fire risk is assessed via the Internet, risk weights are calculated for environmental factors, and the risk level of the environment is analyzed based on the risk weight calculation results to obtain a risk level determination result; S4: Based on the risk level determination result, adjust the trigger parameters of the smart fire alarm, dynamically set the trigger threshold according to the risk level, optimize the timeliness of the alarm triggering, and generate the alarm threshold adjustment result; S5: Implement the alarm threshold adjustment result, monitor environmental data in real time and compare it with the preset threshold, perform real-time fire risk assessment, update the response status of the smart fire alarm, and generate a real-time risk assessment result; S6: Based on the real-time risk assessment results, use the Internet to conduct a smart fire emergency response simulation test, evaluate the implementation effect of the response strategy, and generate a smart fire alarm log.

[0007] The following is a further optimization of the above technical solution by the present invention: The environmental risk analysis results include key temperature indicators, key humidity indicators and fire equipment operation indicators; the posterior probability update results include temperature adjustment probability, humidity adjustment probability and environmental safety probability; the risk level determination results include temperature risk level, humidity risk level and fire risk level; the alarm threshold adjustment results include temperature trigger threshold, humidity trigger threshold and electrical abnormality trigger threshold; the real-time risk assessment results include real-time temperature data, real-time humidity data and electrical data; the smart fire alarm log includes response time records, simulation test evaluation and strategy effect analysis results.

[0008] Further optimization: By analyzing temperature, humidity, and electrical equipment status, using the internet for real-time data transmission, performing data classification, and identifying fire risk indicators, the steps for generating environmental risk analysis results are as follows: S101: By analyzing temperature, humidity, and electrical equipment status, data is uploaded to a central server via the Internet, differentiated data is marked as temperature data, humidity data, and equipment status data, and the data is formatted to obtain real-time environmental data; S102: Based on the real-time environmental data, data classification processing is performed to screen the data, distinguish between data in a normal range and data in an abnormal range, iteratively mark the data in the abnormal range, identify potential abnormal states, and obtain classified state data; S103: Perform fire risk assessment based on the classification status data, calculate the risk value of the differentiated data based on a preset risk assessment threshold, assess the overall fire risk level of the environment, and obtain an environmental risk analysis result.

[0009] Further optimization: Using the environmental risk analysis results, constructing a probability update model, calculating the posterior probability under differentiated environmental conditions, and using the posterior probability to analyze the risk level of the fire, the steps for obtaining the posterior probability update results are as follows: S201: Using the environmental risk analysis results, initialize a comparison model between environmental parameters and historical environmental data, perform data normalization, check whether the compared data is on the target scale, identify the deviation between the real-time environmental parameters and historical data, and obtain environmental change parameters; S202: Based on the environmental change parameters, a parameter adjustment strategy is used to update the posterior probability model, and the model parameters are gradually adjusted to match the new environmental change information. After the parameter update, the model is verified to verify the applicability of the parameter adjustment, and the adjusted posterior probability is obtained. S203: Classify and quantitatively analyze the fire risk levels of the differentiated environments according to the adjusted posterior probability, compare the analysis results with a preset risk level threshold, and obtain an updated posterior probability result.

[0010] Further optimization: Using the posterior probability update result, the fire risk is assessed through the Internet, the risk weight of environmental factors is calculated, and the risk level of the environment is analyzed based on the risk weight calculation result. The specific steps for obtaining the risk level determination result are as follows: S301: Based on the posterior probability update result, synchronize the current fire risk data via the Internet, check the integrity of the data, analyze the cause of the fire risk, and obtain synchronized risk data; S302: Based on the synchronized risk data, weights of environmental factors are assigned, differentiated weight values ​​are set according to the risk contribution of each factor, and the fire risk value of the environmental factors is calculated to obtain a weighted risk score; S303: Assigning differentiated risk levels to environmental factors through the weighted risk scoring, associating each risk level with a risk value within a target range, checking the real-time performance of the fire risk assessment, and obtaining a risk level determination result.

[0011] Further optimization: Based on the risk level determination results, adjust the trigger parameters of the smart fire alarm, dynamically set the trigger threshold according to the risk level, and optimize the timeliness of the alarm trigger. The steps for generating the alarm threshold adjustment results are as follows: S401: Based on the risk level determination result, access the configuration interface via the Internet, query the trigger parameters of the smart fire alarm, record the old trigger thresholds associated with the differentiated risk levels, and obtain real-time threshold records; S402: Based on the real-time threshold record, adjust the smart fire alarm trigger threshold according to the new risk level, check whether the threshold matches the real-time risk level, update the smart fire alarm parameters, and obtain the adjusted trigger parameters; S403: Update the configuration file of the smart fire alarm using the adjusted trigger parameters, reload the configuration to evaluate the effect of the new threshold implementation, test the adjusted response time, and obtain the alarm threshold adjustment result.

[0012] Further optimization: Implement the alarm threshold adjustment results, monitor environmental data in real time and compare it with the preset threshold, conduct real-time fire risk assessment, update the response status of the smart fire alarm, and generate real-time risk assessment results. The specific steps are as follows: S501: Based on the alarm threshold adjustment result, real-time monitoring is performed via the Internet to collect environmental temperature, humidity, and smoke concentration data of differentiated areas in real time, and the data is cyclically monitored and recorded to obtain real-time monitoring data; S502: Based on the real-time monitoring data, the data is compared with the set new trigger threshold to analyze whether the parameters exceed the safety range, identify potential fire risk areas, and perform risk assessment to obtain an early warning risk level; S503: Using the early warning risk level, the alarm response status is updated. If the assessment result exceeds the target risk level, the associated alarm signal is triggered, and the time and area of ​​the alarm activation are recorded to obtain a real-time risk assessment result.

[0013] Further optimization: Based on the real-time risk assessment results, use the Internet to conduct a smart fire emergency response simulation test to evaluate the implementation effect of the response strategy. The specific steps for generating a smart fire alarm log are as follows: S601: Using the real-time risk assessment results, conduct a simulation test of the smart fire alarm via the Internet. Simulate fire responses under differentiated environmental conditions through a network connection, check the activation status of the smart fire alarm and response equipment, verify the response time of the equipment in each simulated scenario, and obtain a simulation test record. S602: Analyze the response time and effect of the smart fire alarm in differentiated test scenarios using a decision tree algorithm based on the simulation test records to obtain a response strategy evaluation result; S603: Based on the response strategy evaluation results, the date, time, response status and adjustment measures of each simulation test are recorded through the Internet, and the time and area of ​​the smart fire alarm are recorded and tracked to obtain a smart fire alarm log.

[0014] Further optimization: The formula of the decision tree algorithm is as follows: ; in, is the weighted Gini impurity, For classification The proportion of samples under For classification The key weight coefficient, For category The total number of .

[0015] An Internet-based smart fire alarm system, the Internet-based smart fire alarm system is used to execute the above-mentioned Internet-based smart fire alarm method, the system comprising: The data collection module transmits data via the Internet based on temperature, humidity, and electrical equipment status, classifies it into environmental data, analyzes and identifies fire risk indicators, and generates environmental risk analysis results; The risk analysis module establishes a probability update model based on the environmental risk analysis results, calculates the posterior probability under differentiated environmental conditions, uses the probability to evaluate the fire risk level, and obtains the posterior probability update result; The risk identification module uses the posterior probability update result to calculate the weight of the environmental risk level through the Internet, analyzes the risk level of differentiated environmental factors, and obtains the risk level determination result; The threshold optimization module uses the risk level determination results to adjust the trigger parameters of the smart fire alarm, dynamically sets the trigger threshold according to the differentiated risk level, optimizes the timeliness of the alarm trigger, and generates the alarm threshold adjustment results; The real-time monitoring module applies the alarm threshold adjustment results, monitors environmental data in real time, and compares it with the preset threshold to assess the real-time risk of fire, update the response status of the smart fire alarm, and generate a smart fire alarm log through simulation testing of the smart fire alarm response.

[0016] The present invention adopts the above technical solution and has the following beneficial effects: In the present invention, through the comprehensive application of real-time monitoring and intelligent analysis, the reaction speed and prevention capability of fire alarms are significantly improved, the temperature, humidity and electrical equipment status are analyzed, potential fire risks are identified in a timely manner, and early warning can be issued in the early stages of fire formation, significantly reducing the potential damage of fire; real-time data transmission ensures that information can be quickly transmitted to the fire center in the early stages of a fire, allowing emergency response units to prepare in advance, effectively reducing casualties and property losses; the application of posterior probability provides more accurate data support in assessing fire risk levels, making it more flexible in dynamically adjusting trigger parameters, enhancing the adaptability to different environmental conditions, providing important data for post-fire analysis, and contributing to the optimization and adjustment of future strategies. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 Schematic diagram of the working process of an embodiment of the present invention; Figure 2 Detailed flowchart of step S1 in an embodiment of the present invention; Figure 3 Detailed flowchart of step S2 in an embodiment of the present invention; Figure 4 Detailed flowchart of step S3 in an embodiment of the present invention; Figure 5 Detailed flowchart of step S4 in an embodiment of the present invention; Figure 6 Detailed flowchart of step S5 in an embodiment of the present invention; Figure 7 Detailed flowchart of step S6 in an embodiment of the present invention; Figure 8 Flowchart of the system in the embodiment of the present invention. DETAILED DESCRIPTION

[0018] Example 1: See also Figure 1 The present invention provides a technical solution, an Internet-based smart fire alarm method, comprising the following steps: S1: By analyzing temperature, humidity, and electrical equipment status, using the internet for real-time data transmission, performing data classification, iteratively marking abnormal data, and identifying fire risk indicators, it generates environmental risk analysis results; S2: Using the environmental risk analysis results, a probability update model is constructed to calculate the posterior probability under differentiated environmental conditions. The posterior probability is used to analyze the fire risk level, and the fire risk level of the differentiated environment is classified and quantitatively analyzed to obtain the posterior probability update results. S3: Based on the posterior probability update results, the fire risk is assessed through the Internet, the risk weights of environmental factors are calculated, and the risk level of the environment is analyzed based on the risk weight calculation results to obtain the risk level determination result; S4: Based on the risk level determination results, adjust the trigger parameters of the smart fire alarm, dynamically set the trigger threshold according to the risk level, optimize the timeliness of the alarm trigger, and generate the alarm threshold adjustment results; S5: Implement the alarm threshold adjustment results, monitor environmental data in real time and compare it with the preset threshold, conduct real-time fire risk assessment, update the response status of the smart fire alarm, and generate real-time risk assessment results; S6: Based on the real-time risk assessment results, use the Internet to conduct smart fire emergency response simulation tests, record the date, time, response status and adjustment measures of each simulation test, evaluate the implementation effect of the response strategy, and generate a smart fire alarm log.

[0019] The results of environmental risk analysis include key temperature indicators, key humidity indicators and fire equipment operation indicators. The results of posterior probability update include temperature adjustment probability, humidity adjustment probability and environmental safety probability. The risk level determination results include temperature risk level, humidity risk level and fire risk level. The alarm threshold adjustment results include temperature trigger threshold, humidity trigger threshold and electrical abnormality trigger threshold. The real-time risk assessment results include real-time temperature data, real-time humidity data and electrical data. The smart fire alarm log includes response time records, simulation test evaluation and strategy effect analysis results.

[0020] See also Figure 2 By analyzing temperature, humidity, and electrical equipment status, using the Internet for real-time data transmission, performing data classification, and identifying fire risk indicators, the steps for generating environmental risk analysis results are as follows: S101: By analyzing temperature, humidity, and electrical equipment status, uploading data to a central server via the Internet, marking the differentiated data as temperature data, humidity data, and equipment status data, and formatting the data, the execution process of obtaining real-time environmental data is as follows; Sub-step S101 analyzes temperature, humidity, and electrical equipment status, deploys multi-point sensors to capture key parameters in real time, and transmits the data to a central server via the Internet. On the server side, the data undergoes preliminary formatting to distinguish between temperature data, humidity data, and equipment status data. Each type of data can be marked and formatted as necessary to facilitate subsequent analysis and processing, including timestamps, data type identifiers, and specific measurement values, providing standardized input for further data analysis and application, and obtaining real-time environmental data.

[0021] S102: Based on the real-time environmental data, data classification processing is performed to screen the data, distinguish between data in the normal range and data in the abnormal range, iteratively mark the data in the abnormal range, identify potential abnormal states, and obtain classified state data. The execution process is as follows; Sub-step S102 classifies the data based on real-time environmental data, sets normal and abnormal threshold standards, and filters and distinguishes the data according to the standards; all data that exceeds the normal operating range is marked as abnormal, and iterative status marking is performed to identify potential abnormal states; classification processing not only helps to quickly identify data within the abnormal range that requires attention, but also makes the response to potential risks more rapid and effective, and obtains classified status data.

[0022] S103: Perform fire risk assessment based on the classified status data, calculate the risk value of the differentiated data based on the preset risk assessment threshold, evaluate the overall fire risk level of the environment, and obtain the environmental risk analysis results. The execution process is as follows; Sub-step S103 conducts a fire risk assessment based on the classified status data and calculates the risk value of the differentiated data based on the preset risk assessment threshold. The calculation takes into account the abnormal frequency, severity, and impact range of various parameters. Based on the calculation, the overall fire risk level of the environment is assessed and a quantitative analysis of the potential fire risk in the building is provided. The risk assessment helps managers take appropriate preventive measures or emergency responses to ensure the safety of the building and residents, and obtains the environmental risk analysis results using the formula: ; in, is the fire hazard level of the environment, It is The weight of the class classification status data, It is The number of class classification status data, is the corresponding risk indicator.

[0023] See also Figure 3 ,Using the results of environmental risk analysis, a probability update model is constructed, the posterior probability under differentiated environmental conditions is calculated, and the risk level of fire is analyzed using the posterior probability. The specific steps to obtain the posterior probability update result are as follows: S201: Using the environmental risk analysis results, initialize the environmental parameter and historical environmental data comparison model. Through data normalization, check whether the compared data is on the target scale, identify the deviation between the real-time environmental parameters and historical data, and obtain the environmental change parameters. The execution process is as follows; Sub-step S201 uses the results of the environmental risk analysis to initialize a model for comparing environmental parameters with historical environmental data. The real-time monitoring data and historical data are normalized to ensure that they are on the same scale when performing comparative analysis. This allows for accurate identification of deviations between real-time environmental parameters and historical data, and a better understanding of environmental trends. After normalization, specific parameters of environmental changes, such as sudden changes or persistently high temperatures and humidity, can be clearly identified. These parameters will be used for subsequent model updates and risk assessments to obtain posterior probability updates using the following formula: ; in, represents the normalized data, is the original data, and are the minimum and maximum values ​​of the data respectively.

[0024] S202: Based on the environmental change parameters, a parameter adjustment strategy is used to update the posterior probability model, gradually adjusting the model parameters to match the new environmental change information. After the parameter update, the model is verified to verify the applicability of the parameter adjustment. The execution process of the adjusted posterior probability is as follows; Sub-step S202 updates the posterior probability model based on the environmental change parameters using a parameter adjustment strategy, which involves gradually adjusting the model parameters to match the new environmental change information; continuously optimizing the model's predictive ability and accuracy through comparative analysis and feedback adjustment; after the parameter update is completed, model validation is performed to confirm the applicability and effectiveness of the parameter adjustment; this includes testing the model's response and prediction accuracy under new environmental conditions to ensure that the model update can reflect changes in the actual environment and improve the reliability of environmental risk assessment. The adjusted posterior probability is obtained using the formula: ; in, is the updated posterior probability, is the original posterior probability, is the adjustment coefficient, is the environmental variation parameter.

[0025] S203: Based on the adjusted posterior probability, the fire risk levels of the differentiated environments are classified and quantitatively analyzed, and the analysis results are compared with the preset risk level threshold to obtain the updated posterior probability results. The execution process is as follows: Sub-step S203 classifies and quantitatively analyzes the fire risk levels of differentiated environments based on the adjusted posterior probabilities; compares the risk levels obtained by analysis with the preset risk level thresholds to assess the fire risk of the current environment, allowing decision makers to understand the changing trends of environmental risks and take appropriate preventive measures or adjust safety strategies; and obtains updated posterior probability results through comparison and analysis.

[0026] See also Figure 4 ,By updating the results of posterior probability, the fire risk is assessed through the Internet, the risk weight of environmental factors is calculated, and the risk level of the environment is analyzed based on the risk weight calculation results. The specific steps to obtain the risk level determination result are as follows: S301: Based on the posterior probability update result, synchronize the current fire risk data via the Internet, check the data integrity, and analyze the cause of the fire risk. The execution process of obtaining the synchronized risk data is as follows; In sub-step S301, based on the posterior probability update results, the current fire risk data is synchronized to the smart fire protection system via the Internet. Ensuring the integrity and security of the data is crucial. After data synchronization, data integrity verification is performed to ensure that all key information has been correctly transmitted and has not been damaged or tampered with. In-depth analysis of the synchronized fire data is conducted to identify and understand the main causes of risk changes, including temperature anomalies, humidity changes, or electrical equipment failures. This not only provides the current risk status, but also provides data support for prevention and response measures. The synchronized risk data is obtained using the formula: ; in, Indicates the correlation between each factor and fire risk, is the observed value of the current environmental factor, is historical data related to fire risk, and are the observed values ​​of environmental factors and the average values ​​of historical data related to fire risk, respectively.

[0027] S302: Based on the synchronized risk data, weights of environmental factors are assigned. Differentiated weights are set based on the risk contribution of each factor. The fire risk value of the environmental factors is calculated to obtain a weighted risk score. The execution process is as follows: In sub-step S302, weights are assigned to environmental factors based on the synchronized risk data. Differentiated weight values ​​are set based on the contribution of each factor to the fire risk. For example, if the data shows that temperature anomalies contribute the most to the fire risk, a higher weight is assigned to the temperature factor. Through weight assignment, the contribution of each environmental factor to the overall fire risk can be more accurately calculated, reflecting the fire risk status under the combined effects of various factors in the environment, and obtaining a weighted risk score using the following formula: ; in, is the risk value of environmental factors, is the weight, It is a predictive risk indicator of environmental factors.

[0028] S303: By weighting the risk scores, differentiated risk levels are assigned to environmental factors. Each risk level is associated with the risk value of the target range. The real-time performance of the fire risk assessment is checked, and the execution process for obtaining the risk level determination result is as follows; Sub-step S303 assigns corresponding risk levels to different environmental factors through weighted risk scoring. Each risk level is associated with a specific range of risk values, ensuring the real-time and accuracy of fire risk assessment. It can quickly identify and respond to potential high-risk areas or conditions, take preventive measures in a timely manner, and effectively guide fire departments or building managers to carry out corresponding risk management and obtain risk level determination results.

[0029] See also Figure 5 According to the risk level determination results, the trigger parameters of the smart fire alarm are adjusted, the trigger threshold is dynamically set according to the risk level, and the timeliness of the alarm trigger is optimized. The specific steps for generating the alarm threshold adjustment results are as follows: S401: Based on the risk level determination result, access the configuration interface through the Internet, query the trigger parameters of the smart fire alarm, record the old trigger thresholds associated with the differentiated risk levels, and obtain the real-time threshold record. The execution process is as follows; Based on the risk level determination result, sub-step S401 accesses the configuration interface through the Internet; in this interface, the smart fire alarm trigger parameters associated with the current risk level are queried and recorded, including the old trigger thresholds; ensuring real-time understanding of the smart fire alarm system, being able to track existing settings and prepare for upcoming adjustments; recording the thresholds is key because it is the basis for evaluating the current system response and making necessary adjustments, and obtaining real-time threshold records.

[0030] S402: Based on the real-time threshold record, adjust the smart fire alarm trigger threshold according to the new risk level, check whether the threshold matches the real-time risk level, and update the smart fire alarm parameters. The execution process of obtaining the adjusted trigger parameters is as follows; In sub-step S402, the trigger threshold of the smart fire alarm is adjusted based on the real-time threshold record. This adjustment is based on the new risk level and the requirements for system sensitivity. By evaluating the match between the risk level and the current threshold, the trigger threshold is appropriately adjusted to improve the system's prevention and response capabilities. After the adjustment is completed, the system parameters are updated, including updating the trigger parameters in the smart fire system and ensuring that the new parameters match the actual risk level, as they directly affect the system's performance in actual fire situations. The adjusted trigger parameters are obtained using the formula: ; in, is the new trigger threshold after adjustment, is the old trigger threshold, It is an adjustment factor determined based on the risk level.

[0031] S403: Update the configuration file of the smart fire alarm using the adjusted trigger parameters, reload the configuration to evaluate the effect of the new threshold implementation, test the adjusted response time, and obtain the alarm threshold adjustment result. The execution process is as follows; Sub-step S403 updates the alarm configuration file of the smart fire protection system through the adjusted trigger parameters; reloads the configuration and evaluates the implementation effect of the new threshold; including testing the response time after the threshold adjustment and the overall response capability of the system; through testing, ensures that the newly set threshold not only reflects the latest risk assessment results, but also can provide effective alarms in emergency situations, and obtains the alarm threshold adjustment results.

[0032] See also Figure 6 , implement the alarm threshold adjustment results, monitor environmental data in real time and compare it with the preset threshold, conduct real-time fire risk assessment, update the response status of the smart fire alarm, and generate real-time risk assessment results. The specific steps are: S501: Based on the alarm threshold adjustment result, real-time monitoring is performed via the Internet to collect environmental temperature, humidity, and smoke concentration data of differentiated areas in real time. The data is cyclically monitored and recorded to obtain real-time monitoring data. The execution process is as follows; Sub-step S501 implements real-time monitoring of the smart fire protection system through the Internet based on the alarm threshold adjustment results, including real-time collection of ambient temperature, humidity and smoke concentration data in differentiated areas; uses a sensor network to continuously monitor key parameters, and performs cyclic monitoring and recording through the system's data management platform; real-time monitoring data provides the system with continuously updated environmental status, ensuring that it can respond quickly to any abnormal situation and generate real-time risk assessment results.

[0033] S502: Based on the real-time monitoring data, the new trigger threshold is compared with the set value to analyze whether the parameters exceed the safety range, identify potential fire risk areas, and conduct risk assessment to obtain the early warning risk level. The execution process is as follows; Sub-step S502 compares real-time monitoring data with the new trigger thresholds set in the smart fire protection system, analyzes whether the parameters exceed the safety range, and identifies potential fire risk areas based on the exceeding conditions; the analysis process includes statistical evaluation of temperature, humidity and smoke data to determine whether the area is in a high-risk state; a risk assessment is performed based on the data to generate an early warning risk level.

[0034] S503: Using the early warning risk level, the alarm response status is updated. If the assessment result exceeds the target risk level, the associated alarm signal is triggered and the time and area of ​​alarm activation are recorded. The execution process for obtaining the real-time risk assessment result is as follows; Sub-step S503 uses the early warning risk level to update the alarm response status of the smart fire protection system; if the assessment results show that the risk level of a certain area exceeds the set target risk level, the system will automatically trigger the associated alarm signal; at the same time, the time and specific area of ​​alarm activation are recorded to ensure that all key information is recorded in detail to facilitate subsequent analysis and the formulation of improvement measures to obtain risk assessment results.

[0035] See also Figure 7 Based on the real-time risk assessment results, the smart fire emergency response simulation test is carried out using the Internet to evaluate the implementation effect of the response strategy. The specific steps for generating a smart fire alarm log are as follows: S601: Using the real-time risk assessment results, conduct a simulation test of the smart fire alarm via the internet. Fire responses under different environmental conditions are simulated through network connections. The activation status of the smart fire alarm and response equipment is checked, and the response time of the equipment in each simulated scenario is verified. The execution process for obtaining simulation test records is as follows; Sub-step S601 uses the real-time risk assessment results to conduct simulation tests on the smart fire protection system through the Internet, simulating fire responses under different environmental conditions to ensure that the system can work effectively in various situations; through network connection, set up simulated fire scenarios and check the activation status of smart fire alarms and response equipment; record the response time of the equipment in each scenario in detail, evaluate the timeliness of the alarm system and the effectiveness of the response equipment, and obtain simulation test records.

[0036] S602: Based on the simulation test records, a decision tree algorithm is used to analyze the response time and effect of the smart fire alarm in differentiated test scenarios. The execution process for obtaining the response strategy evaluation results is as follows; In sub-step S602, based on the simulation test records, a decision tree algorithm is used to analyze the response time and effectiveness of the smart fire alarm system in different test scenarios. The decision tree algorithm classifies the data by evaluating the response time and scenario variables to identify the effectiveness of the response strategy. This helps determine the factors that most affect the performance of the alarm system, provides a basis for optimizing the alarm strategy, and obtains the response strategy evaluation results.

[0037] The formula for the decision tree algorithm is as follows: ; in, is the weighted Gini impurity, For classification The proportion of samples under For classification The key weight coefficient, For category The total number of .

[0038] The execution process is as follows: Determine the weight coefficient for each category The coefficient is adjusted according to the influence and sensitivity of each category in the previous historical data to calculate the probability of occurrence of each category , after cumulative weighting , to evaluate the weighted impurity of each split node, select the split attribute with the smallest weighted Gini impurity, determine the structure of the tree, and the weight coefficient The determination of can be obtained through statistical analysis of the frequency and influence of categories in historical data, making the decision tree algorithm more accurate when dealing with unbalanced data.

[0039] S603: Based on the response strategy evaluation results, the date, time, response status, and adjustment measures of each simulation test are recorded via the Internet. The time and area of ​​the smart fire alarm are also recorded and tracked. The execution process of the smart fire alarm log is as follows; Based on the response strategy evaluation results, sub-step S603 records the date, time, response status and adjustment measures of each simulation test through the Internet, providing detailed historical data for long-term monitoring and maintenance of the system; the record includes the specific details of each test and the corresponding adjustments and optimization measures to ensure that all important information is tracked and archived; the log is crucial for continuously improving the performance and response capabilities of the smart fire alarm system, forming a smart fire alarm log.

[0040] See also Figure 8 An Internet-based smart fire alarm system is provided. The Internet-based smart fire alarm system is used to implement the above-mentioned Internet-based smart fire alarm method. The system includes: The data collection module transmits data via the Internet based on temperature, humidity, and electrical equipment status, classifies it into environmental data, analyzes and identifies fire risk indicators, and generates environmental risk analysis results; The risk analysis module establishes a probability update model based on the environmental risk analysis results, calculates the posterior probability under differentiated environmental conditions, uses the probability to evaluate the fire risk level, and obtains the posterior probability update results; The risk identification module updates the results through the posterior probability, calculates the weight of the environmental risk level through the Internet, analyzes the risk level of differentiated environmental factors, and obtains the risk level determination result; The threshold optimization module uses the risk level determination results to adjust the trigger parameters of the smart fire alarm, dynamically sets the trigger threshold according to the differentiated risk level, optimizes the timeliness of alarm triggering, and generates the alarm threshold adjustment results; The real-time monitoring module applies the alarm threshold adjustment results, monitors environmental data in real time, and compares it with the preset threshold to assess the real-time risk of fire, update the response status of the smart fire alarm, and generate a smart fire alarm log through simulation testing of the smart fire alarm response.

[0041] The above are merely preferred embodiments of the present invention and do not limit the present invention in any other form. Any technician familiar with the profession may use the technical content disclosed above to change or modify it into an equivalent embodiment with equivalent changes and apply it to other fields. However, any simple modification, equivalent change and modification made to the above embodiment based on the technical essence of the present invention without departing from the content of the technical solution of the present invention shall still fall within the scope of protection of the technical solution of the present invention.

Claims

1. An Internet-based intelligent fire alarm method, characterized by: The following steps are involved: By analyzing temperature, humidity, and electrical equipment status, using the Internet for real-time data transmission, performing data classification, and identifying fire risk indicators, environmental risk analysis results are generated; Using the environmental risk analysis results, a probability update model is constructed to calculate the posterior probability under differentiated environmental conditions, and the posterior probability is used to analyze the risk level of the fire to obtain a posterior probability update result; Using the posterior probability update result, the fire risk is assessed through the Internet, the risk weight of the environmental factors is calculated, and the risk level of the environment is analyzed based on the risk weight calculation result to obtain the risk level determination result; According to the risk level determination result, the trigger parameters of the smart fire alarm are adjusted, the trigger threshold is set according to the risk level, the timeliness of the alarm trigger is optimized, and the alarm threshold adjustment result is generated; Implement the alarm threshold adjustment results, monitor environmental data in real time and compare it with preset thresholds, conduct real-time fire risk assessment, update the response status of the smart fire alarm, and generate real-time risk assessment results; Based on the real-time risk assessment results, a smart fire emergency response simulation test is conducted using the Internet to evaluate the implementation effect of the response strategy and generate a smart fire alarm log.

2. The Internet-based intelligent fire alarm method according to claim 1, characterized in that: The environmental risk analysis results include key temperature indicators, key humidity indicators and fire equipment operation indicators; the posterior probability update results include temperature adjustment probability, humidity adjustment probability and environmental safety probability; the risk level determination results include temperature risk level, humidity risk level and fire risk level; the alarm threshold adjustment results include temperature trigger threshold, humidity trigger threshold and electrical abnormality trigger threshold; the real-time risk assessment results include real-time temperature data, real-time humidity data and electrical data; the smart fire alarm log includes response time records, simulation test evaluation and strategy effect analysis results.

3. The Internet-based intelligent fire alarm method according to claim 2, characterized in that: The steps to generate environmental risk analysis results are as follows: By analyzing temperature, humidity, and electrical equipment status, data is uploaded to a central server via the Internet. Differentiated data is marked as temperature data, humidity data, and equipment status data, and formatted to obtain real-time environmental data. Based on the real-time environmental data, data classification processing is performed to screen the data, distinguish between data in a normal range and data in an abnormal range, iteratively mark the data in the abnormal range, identify potential abnormal states, and obtain classified state data; A fire risk assessment is performed based on the classified status data, and the risk value of the differentiated data is calculated based on a preset risk assessment threshold to evaluate the overall fire risk level of the environment and obtain an environmental risk analysis result.

4. The Internet-based intelligent fire alarm method according to claim 3, characterized in that: The environmental risk analysis results are used to construct a probability update model, calculate the posterior probability under differentiated environmental conditions, and use the posterior probability to analyze the risk level of the fire. The specific steps for obtaining the posterior probability update result are as follows: Using the environmental risk analysis results, a comparison model of environmental parameters and historical environmental data is initialized. Through data normalization, the comparison data is checked to see if they are on the target scale, the deviation between the real-time environmental parameters and the historical data is identified, and the environmental change parameters are obtained. Based on the environmental change parameters, a parameter adjustment strategy is adopted to update the posterior probability model, and the model parameters are gradually adjusted to match the new environmental change information. After the parameter update, the model is verified to verify the applicability of the parameter adjustment and obtain the adjusted posterior probability; According to the adjusted posterior probability, the fire risk levels of the differentiated environments are classified and quantitatively analyzed, and the analysis results are compared with the preset risk level threshold to obtain the posterior probability update result.

5. The Internet-based intelligent fire alarm method according to claim 4, characterized in that: The fire risk is assessed through the Internet using the posterior probability update result, the risk weight of environmental factors is calculated, and the risk level of the environment is analyzed based on the risk weight calculation result. The specific steps for obtaining the risk level determination result are as follows: Based on the posterior probability update result, the current fire risk data is synchronized via the Internet, the integrity of the data is checked, and the cause of the fire risk is analyzed to obtain synchronized risk data; Based on the synchronized risk data, weights of environmental factors are assigned, differentiated weight values ​​are set according to the risk contribution of each factor, and the fire risk value of the environmental factors is calculated to obtain a weighted risk score; By using the weighted risk score, differentiated risk levels are assigned to environmental factors, each risk level is associated with a risk value within a target range, and the real-time performance of the fire risk assessment is verified to obtain a risk level determination result.

6. The Internet-based intelligent fire alarm method according to claim 5, characterized in that: According to the risk level determination result, the trigger parameters of the smart fire alarm are adjusted, the trigger threshold is dynamically set according to the risk level, and the timeliness of the alarm trigger is optimized. The steps for generating the alarm threshold adjustment result are as follows: Based on the risk level determination result, access the configuration interface through the Internet, query the trigger parameters of the smart fire alarm, record the old trigger thresholds associated with the differentiated level risks, and obtain real-time threshold records; According to the real-time threshold record, adjust the smart fire alarm trigger threshold according to the new risk level, check whether the threshold matches the real-time risk level, update the smart fire alarm parameters, and obtain the adjusted trigger parameters; The configuration file of the smart fire alarm is updated through the adjusted trigger parameters, the configuration is reloaded to evaluate the effect of the new threshold implementation, the adjusted response time is tested, and the alarm threshold adjustment result is obtained.

7. The Internet-based intelligent fire alarm method according to claim 6, characterized in that: The steps of implementing the alarm threshold adjustment result, monitoring environmental data in real time and comparing it with the preset threshold, conducting real-time fire risk assessment, updating the response status of the smart fire alarm, and generating real-time risk assessment results are as follows: Based on the alarm threshold adjustment result, real-time monitoring is performed via the Internet to collect environmental temperature, humidity, and smoke concentration data of differentiated areas in real time, and the data is cyclically monitored and recorded to obtain real-time monitoring data; Based on the real-time monitoring data, the data is compared with the set new trigger threshold to analyze whether the parameters exceed the safety range, identify potential fire risk areas, and conduct risk assessment to obtain an early warning risk level; The warning risk level is used to update the alarm response status. If the assessment result exceeds the target risk level, the associated alarm signal is triggered, and the time and area of ​​the alarm activation are recorded to obtain real-time risk assessment results.

8. The Internet-based intelligent fire alarm method according to claim 7, characterized in that: Based on the real-time risk assessment results, a smart fire emergency response simulation test is conducted using the Internet to evaluate the effectiveness of the response strategy. The specific steps for generating a smart fire alarm log are as follows: Using the real-time risk assessment results, conduct simulation tests on the smart fire alarm via the internet, simulate fire responses under differentiated environmental conditions through network connections, check the activation status of the smart fire alarm and response equipment, verify the response time of the equipment in each simulated scenario, and obtain simulation test records; Based on the simulation test records, a decision tree algorithm is used to analyze the response time and effect of the smart fire alarm in differentiated test scenarios to obtain response strategy evaluation results; Based on the response strategy evaluation results, the date, time, response situation and adjustment measures of each simulation test are recorded through the Internet, and the time and area of ​​the smart fire alarm are recorded and tracked to obtain a smart fire alarm log.

9. The Internet-based intelligent fire alarm method according to claim 8, characterized in that: The formula of the decision tree algorithm is as follows: ； in, is the weighted Gini impurity, For classification The proportion of samples under For classification The key weight coefficient, For category The total number of .

10. An Internet-based intelligent fire alarm system, characterized by: According to the Internet-based intelligent fire alarm method of claim 9, the system comprises: The data collection module transmits data via the Internet based on temperature, humidity, and electrical equipment status, classifies it into environmental data, analyzes and identifies fire risk indicators, and generates environmental risk analysis results; The risk analysis module establishes a probability update model based on the environmental risk analysis results, calculates the posterior probability under differentiated environmental conditions, uses the probability to evaluate the fire risk level, and obtains the posterior probability update result; The risk identification module uses the posterior probability update result to calculate the weight of the environmental risk level through the Internet, analyzes the risk level of differentiated environmental factors, and obtains the risk level determination result; The threshold optimization module uses the risk level determination results to adjust the trigger parameters of the smart fire alarm, dynamically sets the trigger threshold according to the differentiated risk level, optimizes the timeliness of the alarm trigger, and generates the alarm threshold adjustment results; The real-time monitoring module applies the alarm threshold adjustment results, monitors environmental data in real time, and compares it with the preset threshold to assess the real-time risk of fire, update the response status of the smart fire alarm, and generate a smart fire alarm log through simulation testing of the smart fire alarm response.

Images