Warehouse logistics place intelligent fire safety risk assessment method and system

Abstract

The invention relates to the technical field of fire safety, and provides a warehouse logistics place intelligent fire safety risk assessment method and system, and the method comprises the steps: obtaining original data collected by a plurality of sensors in a warehouse logistics place, carrying out the preprocessing, and generating fire monitoring data; performing feature extraction based on the fire-fighting monitoring data to obtain fire-fighting monitoring features; inputting the fire-fighting monitoring features into a pre-trained risk assessment model, and outputting risk early warning information through the risk assessment model; and sending the risk early warning information to a fire safety interaction platform, and performing corresponding risk investigation. The problem that automatic assessment and accurate early warning of existing fire safety risks are difficult is solved.

Description

Technical Field

[0001] The present invention relates to the field of fire safety technology, and in particular to a smart fire safety risk assessment method and system for warehousing and logistics sites. Background Art

[0002] At present, fire safety risk assessment in warehousing and logistics sites mainly relies on manual inspections and traditional sensor monitoring. Manual inspections have problems such as low efficiency, high cost, and easy omissions; while traditional sensor monitoring can obtain data in real time, it often lacks intelligent processing and analysis capabilities, making it difficult to identify potential risks in a timely and accurate manner.

[0003] In recent years, although some smart fire protection systems have been introduced, most of these systems focus on fire alarm and emergency response, and the comprehensiveness and accuracy of risk assessment still need to be improved. For example, the fire monitoring system of the Internet of Things built by existing enterprises, although the system can integrate a variety of sensor data, is limited to the collection and prompting of a large number of alarms, but it still has limitations in risk assessment algorithms and intelligent early warnings, and fails to make full use of big data and artificial intelligence technologies to achieve in-depth analysis and prediction. In addition, the current research focus covers a wide range of aspects such as production safety standards, static risk assessment indicators, and the construction of safety evaluation systems. However, these studies are still insufficient in the dynamic assessment and in-depth risk judgment of the warehousing and logistics fire safety assessment index. There is a lack of a comprehensive fire safety assessment system that can fully integrate dynamic and static data, run through the entire business chain, and cover all dimensions. There is also a lack of risk factor identification and judgment of the assessment content, which makes it difficult to directly guide logistics and warehousing companies to achieve automated assessment of fire safety risks and accurate early warning in advance. Summary of the invention

[0004] The present invention provides a method and system for intelligent fire safety risk assessment in warehousing and logistics sites, which are used to solve the problem that existing fire safety risks are difficult to automatically assess and accurately warn.

[0005] The present invention provides a method for intelligent fire safety risk assessment in a warehousing and logistics site, comprising: Obtain and pre-process the raw data collected by various sensors in the warehousing and logistics sites to generate fire monitoring data; Perform feature extraction based on the fire monitoring data to obtain fire monitoring features; Inputting the fire monitoring features into a pre-trained risk assessment model, and outputting risk warning information through the risk assessment model; The risk warning information is sent to the fire safety interactive platform for corresponding risk investigation.

[0006] According to a method for intelligent fire safety risk assessment of a warehousing and logistics site provided by the present invention, the raw data collected by various sensors in the warehousing and logistics site are obtained and pre-processed to generate fire monitoring data, specifically including: Collect raw data from temperature sensors, humidity sensors, and smoke detectors in warehouse logistics locations; The raw data is deduplicated, missing values ​​are processed, and erroneous data are corrected to complete preprocessing; The preprocessed raw data is converted to unify the data format and generate fire monitoring data.

[0007] According to a method for intelligent fire safety risk assessment of a warehousing and logistics site provided by the present invention, the feature extraction based on the fire monitoring data to obtain the fire monitoring feature specifically includes: Screening out key features related to fire safety risk assessment based on the fire monitoring data; Perform feature conversion based on the key features to extract representative features; Based on the representative features, feature construction is performed according to business requirements and data characteristics to obtain fire monitoring features.

[0008] According to a method for intelligent fire safety risk assessment of a warehousing and logistics site provided by the present invention, the training method of the risk assessment model is: Obtain known risk events and corresponding feature data; The preset machine learning model is trained through known risk events and corresponding feature data. During the training process, the machine learning model is tuned through cross-validation and grid search to obtain a risk assessment model.

[0009] According to a method for intelligent fire safety risk assessment in a warehousing and logistics site provided by the present invention, the fire monitoring features are input into a pre-trained risk assessment model, and risk warning information is output through the risk assessment model, specifically including: Performing risk assessment on the input fire monitoring features through the risk assessment model to obtain an assessment result; Comparing the evaluation result with the set warning threshold to generate a comparison result; Determine whether to issue risk warning information based on the comparison results.

[0010] According to a method for intelligent fire safety risk assessment of a storage and logistics site provided by the present invention, the risk warning information is sent to a fire safety interactive platform to conduct corresponding risk investigation, specifically including: Sending the risk warning information to a fire safety interactive platform, and performing hierarchical management and control of message distribution on the fire safety interactive platform; Issue risk investigation instructions on mobile and computer terminals to conduct corresponding risk investigations.

[0011] According to a method for intelligent fire safety risk assessment in a warehousing and logistics site provided by the present invention, the risk warning information is compared with the actual situation, and the accuracy of the risk assessment model is verified according to the comparison result to generate a verification result; The risk assessment model is iteratively updated according to the verification results.

[0012] The present invention also provides a smart fire safety risk assessment system for warehousing and logistics sites, comprising: The data acquisition module is used to obtain and pre-process the raw data collected by various sensors in the storage and logistics sites to generate fire monitoring data; A feature extraction module, used to extract features based on the fire monitoring data to obtain fire monitoring features; A risk assessment module, used for inputting the fire monitoring features into a pre-trained risk assessment model, and outputting risk warning information through the risk assessment model; The early warning module is used to send the risk early warning information to the fire safety interactive platform for corresponding risk investigation.

[0013] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, it implements any of the above-described intelligent fire safety risk assessment methods for warehousing and logistics sites.

[0014] The present invention also provides a non-transitory computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, it implements any of the above-mentioned intelligent fire safety risk assessment methods for warehousing and logistics sites.

[0015] The present invention also provides a computer program product, including a computer program, which, when executed by a processor, implements any of the above-mentioned intelligent fire safety risk assessment methods for warehousing and logistics sites.

[0016] The invention provides a method and system for intelligent fire safety risk assessment of storage and logistics sites. By introducing advanced big data processing technology and artificial intelligence algorithms, the developed intelligent fire safety risk assessment method for storage and logistics sites can more accurately analyze various risk factors, including building structure, fire protection facility status, personnel behavior, etc., thereby significantly improving the accuracy of risk assessment. At the same time, the assessment model can collect and update data in real time, ensure the real-time nature of risk assessment, and calculate the current risk status in a timely manner. In addition, by optimizing algorithms and models, automatically calculating scores, giving risk factors, reducing unnecessary interference and misunderstandings, and improving the accuracy and automation of algorithms; not only can the changes in risk factors be monitored in real time, but also future risk trends can be predicted through machine learning algorithms. This dynamic tracking and prediction capability enables managers to discover potential risks in advance and take corresponding preventive measures. In addition, the data analysis and visualization functions provided by the system enable managers to understand the risk status more intuitively and provide a more scientific basis for decision-making. This helps managers to formulate more reasonable and effective risk management strategies and reduce the probability and impact of accidents; the developed intelligent fire safety risk assessment system for storage and logistics sites integrates multiple functional modules, including data collection, processing, analysis, early warning and response. These modules achieve seamless connection and efficient collaboration, allowing managers to perform all fire safety management operations on a unified platform. This not only improves management efficiency, but also makes the system more intelligent and automated. By introducing IoT and AI technologies, the system can automatically collect data, analyze risks, issue warnings, and guide managers to take corresponding countermeasures. This highly integrated system makes fire safety management more convenient and efficient. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0018] Figure 1 It is a flow chart of the intelligent fire safety risk assessment method for warehousing and logistics sites provided by the present invention.

[0019] Figure 2 This is the architecture diagram of the intelligent fire safety risk assessment system for warehousing and logistics sites provided by the present invention.

[0020] Figure 3 It is a hierarchical flow chart of the intelligent fire safety risk assessment method for warehousing and logistics sites provided by the present invention.

[0021] Figure 4 It is a schematic diagram of the module connection of the intelligent fire safety risk assessment system for warehousing and logistics sites provided by the present invention.

[0022] Figure 5 It is a structural schematic diagram of the electronic device provided by the present invention.

[0023] Reference numerals: 110: data acquisition module; 120: feature extraction module; 130: risk assessment module; 140: early warning module; 510: processor; 520: communication interface; 530: memory; 540: communication bus. DETAILED DESCRIPTION

[0024] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings 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.

[0025] In the present invention, based on the actual situation of logistics warehousing fire safety, by accurately identifying and classifying key risk factors, the practicality, operability and quantification of the evaluation indicators are comprehensively considered, and three-level evaluation indicators are established. The first-level indicators cover eight core fire safety areas, including building fire protection performance, equipment and facility completeness, safety management level, safety investment intensity, safety violation penalties, safety risk hazards, personnel safety quality and the application of IoT sensing technology. As a detailed decomposition of the first-level indicators, the second-level indicators specifically cover 41 key indicators such as building fire resistance rating assessment, fire protection facility maintenance integrity rate, fire protection task completion efficiency, and employee fire safety knowledge mastery. The third-level indicators are further deepened and finely classified into 193 items. Through the constructed intelligent fire safety risk assessment index system for warehousing and logistics places and the weight calculation method of each indicator determined, the second-level indicators in the eight first-level indicators are compared and scored in pairs, the judgment matrix is ​​constructed using the 1-9 scaling method, the eigenvector corresponding to the maximum eigenroot is calculated using the eigenroot method, and normalized to obtain the weight of each factor. Combined with the fire safety index management level assessment (excellent, good, qualified, unqualified), a 30-day safety index monitoring was conducted on general cargo, cold chain and chemical logistics and storage parks. By comparing the safety index of each park with its actual operation, the level is bound to the total index score, excellent [90, 100], good [80, 90], qualified [70, 80], unqualified [0, 70); it can comprehensively consider multiple risk factors and achieve accurate risk assessment and early warning.

[0026] Combine the following Figure 1 and Figure 3 The present invention describes a smart fire safety risk assessment method for a warehousing and logistics site, including: step 100, obtaining and preprocessing raw data collected by a variety of sensors in the warehousing and logistics site to generate fire monitoring data.

[0027] Specifically, raw data is collected from temperature sensors, humidity sensors, and smoke detectors in storage and logistics locations; The raw data is deduplicated, missing values ​​are processed, and erroneous data are corrected to complete preprocessing; The preprocessed raw data is converted to unify the data format and generate fire monitoring data.

[0028] In the present invention, data collection: raw data is collected from various sensors in warehousing and logistics sites (such as temperature sensors, humidity sensors, smoke detectors, etc.) and other relevant data sources (such as historical fire records, fire equipment status, etc.).

[0029] Data cleaning: remove duplicate data, process missing values, correct erroneous data, and ensure data accuracy and completeness.

[0030] Data standardization: Data from different sources and dimensions are processed uniformly to make them comparable. For example, continuous data such as temperature and humidity are converted into standard fractions or percentages.

[0031] By uniformly standardizing data after collection, interference items can be removed, so that the final available data can ensure accuracy and improve the accuracy of risk assessment.

[0032] Step 200: extract features based on the fire monitoring data to obtain fire monitoring features.

[0033] Specifically, based on the fire monitoring data, key features related to fire safety risk assessment are screened out; Perform feature conversion based on the key features to extract representative features; Based on the representative features, feature construction is performed according to business requirements and data characteristics to obtain fire monitoring features.

[0034] In the present invention, feature selection: key features related to fire safety risk assessment, such as temperature anomalies, humidity changes, smoke concentration, etc., are screened out from the preprocessed data.

[0035] Feature transformation: Further processing of selected features, such as through mathematical transformation, dimensionality reduction techniques (such as principal component analysis PCA), etc., to extract more representative features.

[0036] Feature construction: Based on business needs and data characteristics, new features or combined features are constructed to better reflect fire safety risks.

[0037] Step 300: input the fire monitoring features into a pre-trained risk assessment model, and output risk warning information through the risk assessment model.

[0038] Specifically, the training method of the risk assessment model is: Obtain known risk events and corresponding feature data; The preset machine learning model is trained through known risk events and corresponding feature data. During the training process, the machine learning model is tuned through cross-validation and grid search to obtain a risk assessment model.

[0039] In the present invention, when training the model, the algorithm is first selected: according to the risk assessment requirements and data characteristics, a suitable machine learning or deep learning algorithm is selected, such as logistic regression, support vector machine, random forest, neural network, etc.

[0040] Training model: Use historical data (including known risk events and corresponding feature data) to train the algorithm to obtain a risk assessment model.

[0041] Model tuning: Tune the model through methods such as cross-validation and grid search to improve the accuracy and generalization ability of the model.

[0042] Heinrich's law is used to analyze the probability of safety hazards caused by different risk factors, and the probability of safety incidents and fire incidents caused by different safety hazards. A dynamic tracking and prediction mechanism for warehousing and logistics sites is designed to monitor the changes in fire risk factors in real time and predict future risk trends. The mechanism uses the Internet of Things technology to deploy sensors and monitoring equipment to collect fire-related data in real time, and cleans, integrates and analyzes these data through big data and artificial intelligence technology to extract the characteristics and change trends of key risk factors. In order to deeply analyze the probability of safety hazards caused by different risk factors, as well as the probability of safety incidents and fire incidents caused by these safety hazards, Heinrich's law is introduced, and a risk prediction model is established through historical data and statistical analysis. After training and optimizing the model using machine learning or deep learning algorithms, the mechanism can monitor the changes in risk factors in real time and predict future risk trends based on the prediction model. When potential risks are predicted, the mechanism will issue early warning information in a timely manner to remind managers to take corresponding measures to intervene; it can monitor the changes in risk factors in real time and predict future risk trends.

[0043] By introducing advanced big data processing technology and artificial intelligence algorithms, the developed intelligent fire safety risk assessment method for warehousing and logistics sites can more accurately analyze various risk factors, including building structure, fire protection facility conditions, personnel behavior, etc., thereby significantly improving the accuracy of risk assessment. At the same time, the assessment model can collect and update data in real time to ensure the real-time nature of risk assessment and timely calculate the current risk status. In addition, by optimizing algorithms and models, automatically calculating scores and giving risk factors, unnecessary interference and misunderstandings can be reduced, and the accuracy and automation of the algorithm can be improved.

[0044] Step 400: Send the risk warning information to the fire safety interactive platform for corresponding risk investigation.

[0045] In the present invention, risk assessment is performed on the input fire monitoring features through the risk assessment model to obtain an assessment result; Comparing the evaluation result with the set warning threshold to generate a comparison result; Determine whether to issue risk warning information based on the comparison results.

[0046] Sending the risk warning information to a fire safety interactive platform, and performing hierarchical management and control of message distribution on the fire safety interactive platform; Issue risk investigation instructions on mobile and computer terminals to conduct corresponding risk investigations.

[0047] Specifically, during the risk assessment process, real-time data input: the sensor data collected in real time is input into the trained risk assessment model.

[0048] Risk calculation: The model calculates the fire safety risk level or probability of the current storage and logistics site based on the input feature data.

[0049] Result output: The risk assessment results are presented to managers in the form of visual charts, reports, etc.

[0050] Ability to generate warnings based on risk assessment results, and set thresholds: Set risk warning thresholds based on business needs and security standards.

[0051] Early warning judgment: Compare the risk assessment results with the early warning threshold, and trigger an early warning if the threshold is exceeded.

[0052] Early warning notification: Early warning information will be promptly notified to relevant personnel through SMS, email, system messages, etc., so that they can take corresponding measures.

[0053] By building a multi-level intelligent fire safety risk assessment system for warehousing and logistics sites, we support the multi-level application management of the headquarters company, second-level company, third-level company and logistics warehousing park, and realize the management mechanism of data homogeneity, matter classification and focus. The system automatically gathers various types of fire safety risk monitoring and early warning data and risk analysis results, and monitors the equipment and facility data and dynamic event data of each floor and each part from macro to micro in the form of a picture. For example, real-time monitoring of the manual and automatic status of the fire automatic alarm control system and the fire water level and other ten red line contents, real-time monitoring of the "three items and six rates" data indicators required by fire regulations, and real-time monitoring of the on-duty personnel of the fire control room sleeping and leaving their posts, effectively strengthening the full-time, full-process and full-factor safety management and control. At the same time, the intelligent fire safety risk assessment method for warehousing and logistics sites is combined with the building fire prevention, fire work management and equipment and facility operation. It will automatically analyze and judge the real-time problems and potential risk trends of the pilot units, give risk factors and disposal suggestions based on the trends, and achieve "early warning, prior notification, and prior intervention"; realize unified management and intelligent analysis of data, and improve management efficiency and decision-making accuracy.

[0054] It can not only monitor the changes of risk factors in real time, but also predict future risk trends through machine learning algorithms. This dynamic tracking and prediction capability enables managers to detect potential risks in advance and take corresponding preventive measures. In addition, the data analysis and visualization functions provided by the system enable managers to understand the risk status more intuitively and provide a more scientific basis for decision-making. This helps managers formulate more reasonable and effective risk management strategies and reduce the probability and impact of accidents.

[0055] In the specific implementation, a smart fire safety risk assessment system for warehousing and logistics sites is built. Fire-related data (such as temperature, humidity, smoke concentration, etc.) of warehousing and logistics sites are collected through Internet of Things technology, and then the data is cleaned and integrated using big data processing technology. Artificial intelligence algorithms are introduced to model and analyze the integrated data to generate risk assessment reports and early warning information. Finally, the results are displayed to managers through the user interaction layer, and intelligent decision support is provided. refer to Figure 2The overall architecture of the intelligent fire safety risk assessment system for warehousing and logistics sites was demonstrated, including the perception layer, collection layer, transmission layer, platform layer, application layer and user layer. The perception layer perceives various fire, gas, water and electricity situations in real time through IoT devices, and collects various static data in the park; transmits data to the intelligent fire protection system deployed by China Merchants Cloud through wired and wireless networks; the platform layer provides fire protection protocol analysis products, fire protection business middle-end products and other support system applications; the application layer includes intelligent fire protection supervision PC terminal, intelligent fire protection supervision mobile terminal, and fire protection housekeeper system; users include management units at all levels, front-line production and operation units, and external service units, providing large-screen terminals, computers, and mobile phones for display. The internal and external systems involved in the system application layer will ensure data interconnection applications through cloud security links.

[0056] In addition, the warning information is compared with the actual situation to verify the accuracy and reliability of the risk assessment model; based on the verification results and new data, the risk assessment model is iteratively updated to improve its adaptability and accuracy.

[0057] The developed intelligent fire safety risk assessment system for warehousing and logistics sites integrates multiple functional modules, including data collection, processing, analysis, early warning and response. These modules achieve seamless connection and efficient collaboration, allowing managers to perform all fire safety management operations on a unified platform. This not only improves management efficiency, but also makes the system more intelligent and automated. By introducing Internet of Things technology and artificial intelligence technology, the system can automatically collect data, analyze risks, issue early warnings, and guide managers to take corresponding countermeasures. This highly integrated system makes fire safety management more convenient and efficient.

[0058] refer to Figure 4 The present invention also discloses a smart fire safety risk assessment system for warehousing and logistics sites, including: The data acquisition module 110 is used to acquire and pre-process the raw data collected by various sensors in the storage and logistics site to generate fire monitoring data; A feature extraction module 120, configured to extract features based on the fire monitoring data to obtain fire monitoring features; A risk assessment module 130, configured to input the fire monitoring features into a pre-trained risk assessment model, and output risk warning information through the risk assessment model; The early warning module 140 is used to send the risk early warning information to the fire safety interactive platform to perform corresponding risk investigation.

[0059] The acquisition of raw data collected by various sensors in the storage and logistics site and preprocessing to generate fire monitoring data specifically includes: Collect raw data from temperature sensors, humidity sensors, and smoke detectors in warehouse logistics locations; The raw data is deduplicated, missing values ​​are processed, and erroneous data are corrected to complete preprocessing; The preprocessed raw data is converted to unify the data format and generate fire monitoring data.

[0060] The feature extraction based on the fire monitoring data to obtain the fire monitoring feature specifically includes: Screening out key features related to fire safety risk assessment based on the fire monitoring data; Perform feature conversion based on the key features to extract representative features; Based on the representative features, feature construction is performed according to business requirements and data characteristics to obtain fire monitoring features.

[0061] The training method of the risk assessment model is: Obtain known risk events and corresponding feature data; The preset machine learning model is trained through known risk events and corresponding feature data. During the training process, the machine learning model is tuned through cross-validation and grid search to obtain a risk assessment model.

[0062] Inputting the fire monitoring features into a pre-trained risk assessment model, and outputting risk warning information through the risk assessment model, specifically includes: Performing risk assessment on the input fire monitoring features through the risk assessment model to obtain an assessment result; Comparing the evaluation result with the set warning threshold to generate a comparison result; Determine whether to issue risk warning information based on the comparison results.

[0063] The risk warning information is sent to the fire safety interactive platform for corresponding risk investigation, specifically including: Sending the risk warning information to a fire safety interactive platform, and performing hierarchical management and control of message distribution on the fire safety interactive platform; Issue risk investigation instructions on mobile and computer terminals to conduct corresponding risk investigations.

[0064] Comparing the risk warning information with the actual situation, verifying the accuracy of the risk assessment model based on the comparison result, and generating a verification result; The risk assessment model is iteratively updated according to the verification results.

[0065] Based on the intelligent fire safety risk assessment system for storage and logistics sites provided by the present invention, by introducing advanced big data processing technology and artificial intelligence algorithms, the developed intelligent fire safety risk assessment method for storage and logistics sites can more accurately analyze various risk factors, including building structure, fire protection facility status, personnel behavior, etc., thereby significantly improving the accuracy of risk assessment. At the same time, the assessment model can collect and update data in real time, ensure the real-time nature of risk assessment, and calculate the current risk status in a timely manner. In addition, by optimizing algorithms and models, automatically calculating scores, giving risk factors, reducing unnecessary interference and misunderstandings, and improving the accuracy and automation of algorithms; not only can the changes in risk factors be monitored in real time, but also future risk trends can be predicted through machine learning algorithms. This dynamic tracking and prediction capability enables managers to discover potential risks in advance and take corresponding preventive measures. In addition, the data analysis and visualization functions provided by the system enable managers to understand the risk status more intuitively and provide a more scientific basis for decision-making. This helps managers to formulate more reasonable and effective risk management strategies and reduce the probability and impact of accidents; the developed intelligent fire safety risk assessment system for storage and logistics sites integrates multiple functional modules, including data collection, processing, analysis, early warning and response. These modules achieve seamless connection and efficient collaboration, allowing managers to perform all fire safety management operations on a unified platform. This not only improves management efficiency, but also makes the system more intelligent and automated. By introducing IoT and AI technologies, the system can automatically collect data, analyze risks, issue warnings, and guide managers to take corresponding countermeasures. This highly integrated system makes fire safety management more convenient and efficient.

[0066] Figure 5 An example of a physical structure diagram of an electronic device is shown in FIG. Figure 5 As shown, the electronic device may include: a processor 510, a communications interface 520, a memory 530 and a communication bus 540, wherein the processor 510, the communications interface 520 and the memory 530 communicate with each other through the communication bus 540. The processor 510 may call the logic instructions in the memory 530 to execute a method for intelligent fire safety risk assessment in a warehousing and logistics site, the method comprising: obtaining and preprocessing the raw data collected by various sensors in the warehousing and logistics site to generate fire monitoring data; extracting features based on the fire monitoring data to obtain fire monitoring features; inputting the fire monitoring features into a pre-trained risk assessment model, and outputting risk warning information through the risk assessment model; sending the risk warning information to a fire safety interactive platform to perform corresponding risk screening.

[0067] In addition, the logic instructions in the above-mentioned memory 530 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0068] On the other hand, the present invention also provides a computer program product, which includes a computer program. The computer program can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute a smart fire safety risk assessment method for a warehousing and logistics site provided by the above methods. The method includes: obtaining and preprocessing raw data collected by various sensors in the warehousing and logistics site to generate fire monitoring data; extracting features based on the fire monitoring data to obtain fire monitoring features; inputting the fire monitoring features into a pre-trained risk assessment model, and outputting risk warning information through the risk assessment model; sending the risk warning information to a fire safety interactive platform to perform corresponding risk investigation.

[0069] On the other hand, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, it is implemented to execute a smart fire safety risk assessment method for a warehousing and logistics site provided by the above-mentioned methods. The method includes: obtaining and preprocessing raw data collected by various sensors in the warehousing and logistics site to generate fire monitoring data; performing feature extraction based on the fire monitoring data to obtain fire monitoring features; inputting the fire monitoring features into a pre-trained risk assessment model, and outputting risk warning information through the risk assessment model; sending the risk warning information to a fire safety interactive platform to perform corresponding risk investigation.

[0070] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0071] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0072] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements 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. A smart fire safety risk assessment method for warehousing and logistics sites, characterized in that: include: Obtain and pre-process the raw data collected by various sensors in the warehousing and logistics sites to generate fire monitoring data; Perform feature extraction based on the fire monitoring data to obtain fire monitoring features; Inputting the fire monitoring features into a pre-trained risk assessment model, and outputting risk warning information through the risk assessment model; The risk warning information is sent to the fire safety interactive platform for corresponding risk investigation.

2. The intelligent fire safety risk assessment method for warehousing and logistics sites according to claim 1 is characterized in that: The raw data collected by various sensors in the storage and logistics site are obtained and pre-processed to generate fire monitoring data, specifically including: Collect raw data from temperature sensors, humidity sensors, and smoke detectors in warehouse logistics locations; The raw data is deduplicated, missing values ​​are processed, and erroneous data are corrected to complete preprocessing; The preprocessed raw data is converted to unify the data format and generate fire monitoring data.

3. The intelligent fire safety risk assessment method for warehousing and logistics sites according to claim 1 is characterized in that: The feature extraction based on the fire monitoring data to obtain the fire monitoring feature specifically includes: Screening out key features related to fire safety risk assessment based on the fire monitoring data; Perform feature conversion based on the key features to extract representative features; Based on the representative features, feature construction is performed according to business requirements and data characteristics to obtain fire monitoring features.

4. The intelligent fire safety risk assessment method for warehousing and logistics sites according to claim 1 is characterized in that: The training method of the risk assessment model is: Obtain known risk events and corresponding feature data; The preset machine learning model is trained through known risk events and corresponding feature data. During the training process, the machine learning model is tuned through cross-validation and grid search to obtain a risk assessment model.

5. The intelligent fire safety risk assessment method for warehousing and logistics sites according to claim 1 is characterized in that: Inputting the fire monitoring features into a pre-trained risk assessment model, and outputting risk warning information through the risk assessment model, specifically includes: Performing risk assessment on the input fire monitoring features through the risk assessment model to obtain an assessment result; Comparing the evaluation result with the set warning threshold to generate a comparison result; Determine whether to issue risk warning information based on the comparison results.

6. The intelligent fire safety risk assessment method for warehousing and logistics sites according to claim 1 is characterized in that: The risk warning information is sent to the fire safety interactive platform for corresponding risk investigation, specifically including: Sending the risk warning information to a fire safety interactive platform, and performing hierarchical management and control of message distribution on the fire safety interactive platform; Issue risk investigation instructions on mobile and computer terminals to conduct corresponding risk investigations.

7. The intelligent fire safety risk assessment method for warehousing and logistics sites according to claim 1 is characterized in that: Comparing the risk warning information with the actual situation, verifying the accuracy of the risk assessment model based on the comparison result, and generating a verification result; The risk assessment model is iteratively updated according to the verification results.

8. A smart fire safety risk assessment system for warehousing and logistics sites, characterized in that: include: The data acquisition module is used to obtain and pre-process the raw data collected by various sensors in the storage and logistics sites to generate fire monitoring data; A feature extraction module, used to extract features based on the fire monitoring data to obtain fire monitoring features; A risk assessment module, used for inputting the fire monitoring features into a pre-trained risk assessment model, and outputting risk warning information through the risk assessment model; The early warning module is used to send the risk early warning information to the fire safety interactive platform for corresponding risk investigation.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, it implements the intelligent fire safety risk assessment method for warehousing and logistics sites as described in any one of claims 1 to 7.

10. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by the processor, it implements the intelligent fire safety risk assessment method for warehousing and logistics sites as described in any one of claims 1 to 7.

Images