Safety check system and method based on hidden danger database model

Abstract

The invention discloses a safety check system and method based on a hidden danger database model, and the method comprises the following steps: S1, building a hidden danger table, a check record table and a rectification record table, and constructing a hidden danger rule base; s2, collecting hidden danger data, and storing the hidden danger data into a hidden danger database model after standardization processing; s3, constructing a hidden danger knowledge graph, and generating a feature matrix; s4, inputting the data and the feature matrix to the time sequence model, and generating a risk scoring matrix; s5, based on the risk score and the knowledge graph, optimizing hidden danger grading and updating the rule base; s6, inputting a multi-modal hidden danger recognition model, and classifying hidden dangers; s7, optimizing task distribution, updating a hidden danger state and storing the hidden danger state into a database; and S8, integrating the data to generate a dynamic characteristic label, optimizing the model, and outputting a heat map and a trend report. Through multi-modal data fusion and dynamic analysis, intelligent management of hidden danger detection, risk assessment, task allocation and model optimization is realized, and the safety check efficiency and accuracy are greatly improved.

Description

Technical Field

[0001] The present invention relates to the field of database technology, and in particular to a safety inspection system and method based on a hidden danger database model. Background Art

[0002] In recent years, with the rapid development of industrial production and social construction, safety hazards have received increasing attention. As an important part of safety inspection, hazard management aims to timely discover potential risks and take corresponding measures to manage them, thereby reducing the possibility of accidents. However, in the existing technologies, hazard inspection and management methods generally have the disadvantages of low efficiency, lack of intelligence and dynamic adaptability, and are difficult to meet the safety management needs in complex environments.

[0003] Traditional hidden danger management systems mainly rely on manual inspection and static records. This method is not only labor-intensive and time-consuming, but also easily affected by human factors, resulting in a high rate of missed hidden danger inspections. In addition, traditional systems are usually based on a single data type, such as text records or single sensor data. This method is difficult to fully reflect the multi-dimensional characteristics of hidden dangers and cannot effectively capture the dynamic evolution of hidden dangers. Especially when hidden dangers are highly contagious or complexly associated, traditional systems cannot promptly identify the transmission chain of hidden dangers and their potential threats to other areas, which seriously restricts the comprehensiveness and accuracy of hidden danger management.

[0004] In terms of hidden danger risk assessment, existing technologies usually adopt rule-based static assessment methods. For example, risks are simply classified and graded through pre-defined hidden danger levels and processing procedures. Although this method has played a certain role in standardization management, its limitations are also very obvious: on the one hand, the static assessment method cannot adapt to the needs of dynamic changes in hidden dangers and it is difficult to capture the real-time evolution of risk levels over time and environmental changes; on the other hand, this method is overly dependent on a fixed rule base and has difficulty processing complex multimodal hidden danger information, such as the dynamic association between hidden danger nodes, the execution status of rectification tasks, and the dynamic changes of environmental variables.

[0005] In addition, existing technologies also have shortcomings in hidden danger classification and task allocation. Traditional classification methods usually classify hidden dangers based on a single data dimension or static rules, and are unable to integrate multimodal data characteristics to improve the accuracy and reliability of classification. This leads to low accuracy of hidden danger classification results, which further affects the efficiency of rectification task allocation and the rationality of resource scheduling. At the same time, the task allocation process is mostly based on manual experience or simple priority rules, which makes it difficult to achieve dynamic optimization and efficient use of resources. Especially when hidden dangers are highly correlated, task allocation lacks in-depth analysis of the hidden danger propagation chain, which can easily lead to unbalanced resource allocation and delayed processing of some high-risk hidden dangers.

[0006] In terms of the analytical capabilities of hidden danger management systems, existing technologies lack the ability to deeply model and comprehensively analyze the dynamic characteristics of hidden danger nodes. For example, although some systems use hidden danger heat maps or risk distribution maps, these heat maps are mostly generated based on static data or simple association models, which are difficult to reflect the dynamic changes and propagation paths of hidden dangers. At the same time, the existing systems have weak predictive analysis capabilities for hidden danger trends and are unable to provide targeted trend analysis reports. This makes it difficult for managers to accurately judge the potential risks of hidden danger development and the priority of rectification tasks, further increasing the complexity and uncertainty of hidden danger management.

[0007] In terms of model optimization and feedback mechanism, the existing hidden danger management system also has major deficiencies. In traditional methods, model optimization is usually completed through offline training, which lacks dynamic adaptability to real-time data. This makes it difficult for the model performance to adjust as the hidden danger scenario changes, thus affecting the accuracy of hidden danger identification and task allocation. In addition, the imperfect feedback mechanism is also a major problem. After completing the task allocation, the existing system often lacks a comprehensive analysis of the execution results of the rectification task, and is unable to iteratively optimize the model performance based on historical data. This can easily lead to inefficient handling of repeated problems when multiple hidden dangers occur.

[0008] Therefore, how to provide a safety inspection system and method based on a hidden danger database model is an urgent problem that those skilled in the art need to solve. Summary of the invention

[0009] One object of the present invention is to propose a safety inspection system and method based on a hidden danger database model. The present invention makes full use of advanced technologies such as multimodal data fusion, dynamic risk assessment and task optimization allocation, and describes in detail the full-process method of hidden danger information collection, knowledge graph construction, dynamic characteristic analysis, risk assessment, task allocation and model optimization. It has the advantages of high intelligence, strong dynamic adaptability, high hidden danger handling efficiency and reasonable resource allocation.

[0010] A safety inspection method based on a hidden danger database model according to an embodiment of the present invention comprises the following steps:

[0011] S1. Establish a hidden danger table, inspection record table and rectification record table, and build a hidden danger rule library based on historical accident cases and industry norms;

[0012] S2. Collect multi-source hidden danger data through the data acquisition module, perform standardization processing, form a hidden danger data set, and store it in the hidden danger database model;

[0013] S3. Based on the hidden danger data set and hidden danger rule base, construct the hidden danger associated knowledge graph, extract the potential features of hidden danger nodes and edges, and generate the knowledge graph feature matrix;

[0014] S4, input the hidden danger data set and knowledge graph feature matrix into the time series model, conduct dynamic risk analysis, and generate a hidden danger risk scoring matrix;

[0015] S5. Combine the hidden danger risk scoring matrix and the knowledge graph feature matrix, perform causal inference through the Bayesian network model, analyze the hidden danger propagation chain and impact range, optimize the hidden danger risk classification, and update the hidden danger rule base;

[0016] S6. Combining the hidden danger dataset, knowledge graph feature matrix and time series features, input the multimodal hidden danger identification model to classify the hidden dangers;

[0017] S7. Combine the hidden danger risk classification results, classified hidden danger results and knowledge graph feature matrix to optimize the rectification task allocation strategy, update the hidden danger status in real time and store the rectification plan in the hidden danger database model;

[0018] S8. Integrate hidden danger risk grading results, hidden danger classification results, knowledge graph feature matrix and rectification task execution data, generate hidden danger dynamic characteristic labels, input time series model and multimodal hidden danger identification model, iterate model performance, and generate hidden danger heat map and trend analysis report.

[0019] Optionally, the S3 specifically includes:

[0020] S31. Extract hidden danger features from hidden danger data sets, including hidden danger description information, risk level, occurrence frequency, and associated inspection and rectification records;

[0021] S32. Classify the hidden danger data and mark the types and attributes of the hidden dangers according to the rules of the hidden danger rule library;

[0022] S33. Establishing knowledge graph of hidden danger association G= ( V,E ) , where V represents the set of hidden danger nodes, including the type, occurrence time and location of hidden dangers, and E represents the relationship between hidden danger nodes, including causal relationship, time association and spatial association;

[0023] S34. In the constructed hidden danger associated knowledge graph G, an embedding optimization algorithm combining the dynamic characteristics of time series and the hidden danger associated weights is used to embed the hidden danger node v i The eigenvector of ∈V is expressed as:

[0024]

[0025] Among them, f ( v i) For node v i The final embedding vector representation of 1 , W 2 and W 3are the trainable weight matrices of node features, time series features, and neighborhood features, T is the total number of time steps, α t is the attention weight at time step t, x i,t For node v i The time series features at time step t, β ij For node v i and neighboring node v j The association weight between ( v i ) For node v i The set of neighboring nodes, x j,t For node v j The time series features at time step t, h j is the neighborhood node v j The original eigenvector of i is the neighborhood node v i The original eigenvector of ( h j ,x j,t ) is a nonlinear combination function;

[0026] S35. Extract the hidden danger node features and edge features after graph embedding to generate the knowledge graph feature matrix F G , where F G =[f(v 1 ),f(v 2 ),...,f(v n )], each f(v i ) is the node v i The embedded feature vector of .

[0027] Optionally, the S4 specifically includes:

[0028] S41. Define the hidden danger dataset and knowledge graph feature matrix as X={x 1 ,x 2 ,…,x n} and F G ={f 1 ,f 2 ,…,f n}, where n represents the number of nodes with hidden dangers, x i is the original feature vector of potential risk node i, f i is the knowledge graph feature vector of hidden danger node i;

[0029] S42, merge the hidden danger dataset features and knowledge graph features to form a comprehensive feature vector z i , which is expressed as:

[0030] zi =σ(W 1 x i +W 2 f i );

[0031] Among them, W 1 and W 2 is the trainable weight matrix, σ is the activation function;

[0032] S43, the comprehensive feature vector z i Input time series model, define the input sequence Z of the time series model t ={z 1,t ,z 2,t ,…,z n,t}, where t is the time step, z i,t is the comprehensive characteristics of potential danger node i at time step t;

[0033] S44. Calculate the dynamic risk score of the hidden danger node through the time series model:

[0034]

[0035] Among them, r i,t is the risk score of potential danger node i at time step t, W 3 and W 4 is a trainable weight matrix, Softmax is a normalization function, z i,k is the comprehensive feature of potential danger node i at time step k, T is the total number of time steps in the time series, α k is the attention weight at time step k:

[0036]

[0037] in, is the attention score at time step k, is the attention score at time step j, exp is the exponential function;

[0038] S45, normalize the dynamic risk scores of all hidden danger nodes to generate a hidden danger risk score matrix R = {r i,t}.

[0039] Optionally, the S5 specifically includes:

[0040] S51. Combine the hidden danger risk score matrix R and the knowledge graph feature matrix F G Input the Bayesian network model to construct a causal relationship diagram of hidden danger propagation;

[0041] S52, define the Bayesian network as BN = (N, L, P), where the potential danger node set N = {n 1,n 2 ,…,n n}, the directed edge L between the potential hazard nodes = {l ij}, P is the conditional probability distribution, defined as:

[0042]

[0043] Among them, Pa(n i ) is the potential danger node n i The parent node set of θ k is the conditional probability of the kth parent node, x k is the state variable;

[0044] S53, according to the knowledge graph feature matrix F G And the hidden danger propagation causal relationship diagram, calculate the hidden danger node n i The propagation chain weight w i :

[0045]

[0046] Among them, β ij For node n i and parent node n j The strength of association, r j is the parent node n j The dynamic risk score, f j is the parent node n j The knowledge graph feature vector, j is the index, g(r j ,f j ) is the parent node n j The nonlinear combination function of the risk score and feature matrix:

[0047] g(r j ,f j )=ReLU(W q r j +W e f j );

[0048] Among them, ReLU is the activation function, W q and W e is a trainable weight matrix;

[0049] S54, normalize the propagation chain weights to generate a hidden danger propagation chain matrix W = {w i}, where the potential danger node n i The propagation chain weight w i It is expressed as:

[0050]

[0051] Among them, δ is the adjustment coefficient, h l For node n i The static propagation weight of l, k and m are indexes, n k is the node, h m For node n m The static propagation weight of N is the set of all nodes, β kj is the propagation weight, Pa(n k ) is node n k The parent node set of

[0052] S55, transform the hidden danger propagation chain matrix W = {w i}, Hidden danger risk scoring matrix R and knowledge graph feature matrix F G Combined to generate optimized hidden danger risk classification results i :

[0053]

[0054] Among them, γ 1 ,γ 2 ,γ 3 are the adjustment coefficients for the transmission chain weight, dynamic risk score and neighborhood comprehensive characteristics, Softmax is the normalization function, N(n i ) is a set of neighborhood nodes;

[0055] S56. Update the optimized hidden danger risk classification results to the hidden danger rule library.

[0056] Optionally, the S6 specifically includes:

[0057] S61, extracting a multimodal feature set of hidden danger nodes, including hidden danger data set feature X = {x 1 ,x 2 ,…,x n}、Knowledge graph feature matrix F G ={f 1 ,f 2 ,…,f n} and time series feature matrix T = {t 1 ,t 2 ,…,t n}, for each node n i Construct feature fusion input:

[0058]

[0059] in, For node n i The initial multimodal feature vector, ReLU is the activation function, R 1 , R2 and R 3 is the trainable weight matrix;

[0060] S62. Update the feature vector of the potential danger node through the multi-layer implicit feature propagation module:

[0061]

[0062] in, For node n i The feature vector after propagation in the l+1th layer, N(n i ) is the set of neighborhood nodes, is the attention weight, For node n j The feature vector after propagation in layer l, For node n i The feature vector after propagation in the lth layer, R 4 and R 5 is the trainable weight matrix, j is the index;

[0063] S63. Combined with the dynamic feature adjustment mechanism, according to the time series feature T, the attention weight is updated through the dynamic adjustment mechanism to generate the feature propagation matrix of the node:

[0064]

[0065] in, is the final attention weight, e ij and e ik is the basic attention score, is the time dynamic characteristic weight, ψ j and ψ k is the global importance weight, k 1 and k 2 is the adjustment coefficient, exp is the exponential function, and k is the index;

[0066] S64 converts the final feature vector of the potential danger node into Input the multimodal hidden danger identification model and generate classification results based on the multi-objective optimization mechanism and dynamic characteristic enhancement mechanism:

[0067]

[0068] Among them, y i is the classification result, Softmax is the normalization function, g(z j ,r j ) is the neighborhood feature aggregation function, For the prediction auxiliary module function, R 6 is the trainable weight matrix, λ 1 and λ2 is the adjustment coefficient, α ij is the attention weight, z j is the feature vector, r j is the risk score, p i To predict auxiliary characteristics;

[0069] S65. Output the hidden danger classification results, including hidden danger category, hidden danger risk level and key neighborhood influencing factors, and update the classification fields of the hidden danger database model.

[0070] Optionally, the S7 specifically includes:

[0071] S71. Extract hidden danger risk classification result S = {s 1 ,s 2 ,…,s n}、Hazard classification result Y={y 1 ,y 2 ,…,y n} and the knowledge graph feature matrix F G ={f 1 ,f 2 ,…,f n};

[0072] S72. Build an optimized task allocation model to determine the task priority of hidden danger nodes according to risk classification and hidden danger category:

[0073]

[0074] Among them, p i is the task priority, Softmax is the normalization function, B 1 , B 2 and B 3 is the adjustment coefficient, g(f j ) is the characteristic mapping function, β ij is the attention weight, s i is the risk grading score, y i is the classification result, f j is the knowledge graph feature vector, h(y i B is the hidden danger classification score function, N(n i ) is the neighborhood node set, j is the index;

[0075] S73, based on task priority p i , generate an optimized task allocation plan:

[0076]

[0077] Among them, Y is the task allocation matrix, c i is the rectification cost, d ijis the correlation distance, ξ ij is the task allocation constraint variable, N is the total number of nodes, argmin is to adjust the task allocation matrix Y so that the total task cost and task allocation coordination reach the optimal balance, i and j are indexes;

[0078] S74. Optimize the task allocation strategy through reinforcement learning, and use the policy gradient method to update the task allocation model parameters. The loss function is defined as:

[0079]

[0080] in, The objective loss for task allocation optimization, π(a i |s i ) is in state s i Next select action a i The probability of, ln is the logarithmic function, r i is the reward function, E is the expected symbol;

[0081] S75. Output the optimized task allocation result, and update the task execution field of the hidden danger database model.

[0082] Optionally, the S8 specifically includes:

[0083] S81. Integrate the hidden danger risk classification results S = {s 1 ,s 2 ,…,s n}、Hazard classification result Y={y 1 ,y 2 ,…,y n}、Rectification task execution data T={t 1 ,t 2 ,…,t n} and the knowledge graph feature matrix F G ={f 1 ,f 2 ,…,f n}, construct the hidden danger dynamic characteristic label L d = {l 1 ,l 2 ,…,l n}:

[0084]

[0085] Among them, Q 1 , Q 2 , Q 3 and Q 4 is a trainable weight matrix, ReLU is the activation function, s i is the risk grading score, y iis the hidden danger classification result, t i The data vector for the rectification task, f i is the knowledge graph feature vector, is the final feature vector, l i is a dynamic feature label, h(y i ) is the hidden danger classification score function;

[0086] S82, label the hidden danger dynamic characteristic L d Input the hidden danger feature propagation module, combine the time series model and the multimodal hidden danger identification model, and dynamically update the hidden danger node features:

[0087]

[0088] in, is the potential danger node n i The updated feature vector of is the final eigenvector of the potential danger node, Q 5 and Q 6 is the trainable weight matrix, α ij is the attention weight, g(z j ,f j ) is the neighborhood feature combination function, ReLU is the nonlinear activation function, z j is the characteristic vector of the neighborhood node, f j is the knowledge graph feature, N(n i ) is the neighborhood node set, j is the index;

[0089] S83, based on the updated hidden danger node characteristics, calculate the dynamic correlation heat between the hidden danger nodes, and generate a hidden danger heat map H = {H ij}:

[0090]

[0091] in, is the potential danger node n j The updated feature vector, cosine_similarity is the cosine similarity function, H ij is the potential danger node n i and n j Dynamic correlation heat;

[0092] S84. Using the hidden danger heat map H and the hidden danger dynamic characteristic label L d , analyze the dynamic evolution trend of potential danger nodes and generate a trend analysis report:

[0093]

[0094] Among them, Trend_Score iis the potential danger node n i Dynamic trend score, is the dynamic risk change rate, λ q , w and λ e is the weight parameter, cosine_similarity(l i ,l j ) is the dynamic feature label similarity, t i The time for completing rectification tasks;

[0095] S85. Combine the hidden danger heat map and trend analysis report to update the time series model and multimodal hidden danger identification model and iterate the model performance:

[0096]

[0097] in, is the loss function for iterative optimization, E is the expected symbol, is the real eigenvector, is the weight parameter, is the predicted distribution, is the actual distribution, N is the total number of nodes, is the KL divergence between the predicted distribution and the true distribution, and i is the index.

[0098] The safety inspection system based on the hidden danger database model according to an embodiment of the present invention includes the following modules:

[0099] Data collection and storage module, used to collect multi-source hidden danger data;

[0100] The knowledge graph construction module is used to construct a hidden danger-related knowledge graph and extract node features and association relationships;

[0101] The risk assessment and hidden danger classification module is used to generate hidden danger risk scores and classify hidden danger nodes;

[0102] Dynamic characteristic analysis and heat map generation module, used to analyze the dynamic characteristic labels of hidden danger nodes and generate hidden danger heat maps;

[0103] The risk assessment and hidden danger classification module is used to dynamically analyze and classify hidden danger nodes;

[0104] Task allocation and optimization module, used to optimize task allocation strategies and dynamically adjust resource allocation and priority;

[0105] Trend analysis and report generation module, used to generate hidden danger trend analysis reports and decision support information;

[0106] Model training and optimization module, used to optimize the performance of time series models and multimodal hidden danger identification models.

[0107] The beneficial effects of the present invention are:

[0108] The present invention significantly improves the intelligence level and dynamic adaptability of hidden danger management by constructing a safety inspection system and method based on a hidden danger database model. Compared with the prior art, the present invention integrates a number of technical means such as multimodal data fusion, knowledge graph construction, dynamic characteristic analysis, time series risk assessment, and task optimization allocation, and realizes full-process intelligent management from hidden danger information collection to analysis, classification, allocation, and feedback optimization. Through the combination of dynamic characteristic labels and hidden danger heat maps, the system can accurately capture the dynamic changes of hidden danger nodes, and conduct in-depth analysis of hidden danger propagation paths and potential impact ranges, solving the problem that traditional hidden danger management systems are difficult to dynamically adapt to risk evolution.

[0109] In addition, the present invention uses a time series model and a multimodal hidden danger identification model to dynamically evaluate and accurately classify hidden danger risks, thereby improving the accuracy and real-time performance of risk grading. At the same time, combined with the task allocation and optimization module, the system can dynamically adjust the priority and resource allocation strategy of rectification tasks according to the risk grading and classification results, thereby achieving efficient use of resources and priority treatment of high-risk hidden dangers. Through an iterative optimization mechanism, the present invention can continuously improve model performance based on historical data, enabling the system to have stronger robustness and predictive capabilities when dealing with complex hidden danger scenarios.

[0110] The present invention effectively makes up for the shortcomings of the existing technology, such as insufficient hidden danger data analysis capabilities, static risk assessment methods, low task allocation efficiency, and imperfect model optimization and feedback mechanisms, and significantly improves the overall efficiency and reliability of hidden danger management. The hidden danger trend analysis report generated by the system provides decision-making support for managers, helps to discover and prevent further expansion of safety hazards earlier, and ultimately realizes the intelligent, precise and efficient hidden danger management process. BRIEF DESCRIPTION OF THE DRAWINGS

[0111] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0112] Figure 1 A flowchart of a safety inspection method based on a hidden danger database model proposed by the present invention;

[0113] Figure 2 This is a structural schematic diagram of a safety inspection system based on a hidden danger database model proposed by the present invention. DETAILED DESCRIPTION

[0114] The present invention will now be described in further detail with reference to the accompanying drawings. These drawings are simplified schematic diagrams, which only illustrate the basic structure of the present invention in a schematic manner, and therefore only show the components related to the present invention.

[0115] refer to Figure 1 , a safety inspection method based on a hidden danger database model, comprising the following steps:

[0116] S1. Establish a hidden danger table, inspection record table and rectification record table, and build a hidden danger rule library based on historical accident cases and industry norms;

[0117] S2. Collect multi-source hidden danger data through the data acquisition module, perform standardized processing, form a hidden danger data set, and store it in the hidden danger database model;

[0118] S3. Based on the hidden danger data set and hidden danger rule base, construct the hidden danger associated knowledge graph, extract the potential features of hidden danger nodes and edges, and generate the knowledge graph feature matrix;

[0119] S4, input the hidden danger data set and knowledge graph feature matrix into the time series model, conduct dynamic risk analysis, and generate a hidden danger risk scoring matrix;

[0120] S5. Combine the hidden danger risk scoring matrix and the knowledge graph feature matrix, perform causal inference through the Bayesian network model, analyze the hidden danger propagation chain and impact range, optimize the hidden danger risk classification, and update the hidden danger rule base;

[0121] S6. Combining the hidden danger dataset, knowledge graph feature matrix and time series features, input the multimodal hidden danger identification model to classify the hidden dangers;

[0122] S7. Combine the hidden danger risk classification results, classified hidden danger results and knowledge graph feature matrix to optimize the rectification task allocation strategy, update the hidden danger status in real time and store the rectification plan in the hidden danger database model;

[0123] S8. Integrate hidden danger risk grading results, hidden danger classification results, knowledge graph feature matrix and rectification task execution data, generate hidden danger dynamic characteristic labels, input time series model and multimodal hidden danger identification model, iterate model performance, and generate hidden danger heat map and trend analysis report.

[0124] In this implementation, S3 specifically includes:

[0125] S31. Extract hidden danger features from hidden danger data sets, including hidden danger description information, risk level, occurrence frequency, and associated inspection and rectification records;

[0126] S32. Classify the hidden danger data and mark the types and attributes of the hidden dangers according to the rules of the hidden danger rule library;

[0127] S33. Establishing knowledge graph of hidden danger association G= ( V,E ) , where V represents the set of hidden danger nodes, including the type, occurrence time and location of hidden dangers, and E represents the relationship between hidden danger nodes, including causal relationship, time association and spatial association;

[0128] S34. In the constructed hidden danger associated knowledge graph G, an embedding optimization algorithm combining the dynamic characteristics of time series and the hidden danger associated weights is used to embed the hidden danger node v i The eigenvector of ∈V is expressed as:

[0129]

[0130] Among them, f(v i ) is the node v i The final embedding vector representation of 1 , W 2 and W 3 are the trainable weight matrices of node features, time series features, and neighborhood features, T is the total number of time steps, α t is the attention weight at time step t, x i,t For node v i The time series features at time step t, β ij For node v i and neighboring node v j The association weight between i ) is the node v i The set of neighboring nodes, x j,t For node v j The time series features at time step t, h j is the neighborhood node v j The original eigenvector of i is the neighborhood node v i The original eigenvector of g(h j ,x j,t ) is a nonlinear combination function;

[0131] S35. Extract the hidden danger node features and edge features after graph embedding to generate the knowledge graph feature matrix F G , where F G =[f(v 1 ),f(v 2 ),...,f(v n )], each f(v i ) is the node v i The embedded feature vector of .

[0132] In this implementation manner, the S4 specifically includes:

[0133] S41. Define the hidden danger dataset and knowledge graph feature matrix as X={x 1 ,x 2 ,…,x n} and F G ={f 1 ,f 2 ,…,f n}, where n represents the number of nodes with hidden dangers, x i is the original feature vector of potential risk node i, f i is the knowledge graph feature vector of hidden danger node i;

[0134] S42, merge the hidden danger dataset features and knowledge graph features to form a comprehensive feature vector z i , which is expressed as:

[0135] z i =σ(W 1 x i +W 2 f i );

[0136] Among them, W 1 and W 2 is the trainable weight matrix, σ is the activation function;

[0137] S43, the comprehensive feature vector z i Input time series model, define the input sequence Z of the time series model t ={z 1,t ,z 2,t ,…,z n,t}, where t is the time step, z i,t is the comprehensive characteristics of potential danger node i at time step t;

[0138] S44. Calculate the dynamic risk score of the hidden danger node through the time series model:

[0139]

[0140] Among them, r i,t is the risk score of potential danger node i at time step t, W 3 and W 4 is a trainable weight matrix, Softmax is a normalization function, z i,k is the comprehensive feature of potential danger node i at time step k, T is the total number of time steps in the time series, α k is the attention weight at time step k:

[0141]

[0142] in, is the attention score at time step k, is the attention score at time step j, exp is the exponential function;

[0143] S45, normalize the dynamic risk scores of all hidden danger nodes to generate a hidden danger risk score matrix R = { r i,t } .

[0144] In this implementation manner, S5 specifically includes:

[0145] S51. Combine the hidden danger risk score matrix R and the knowledge graph feature matrix F G Input the Bayesian network model to construct a causal relationship diagram of hidden danger propagation;

[0146] S52. Define Bayesian network as BN= ( N,L,P ) , where the potential danger node set N = {n 1 ,n 2 ,…,n n } , the directed edge L between the potential hazard nodes = { l ij } , P is the conditional probability distribution, defined as:

[0147]

[0148] Among them, Pa ( n i) is the potential danger node n i The parent node set of θ k is the conditional probability of the kth parent node, x k is the state variable;

[0149] S53, according to the knowledge graph feature matrix F G And the hidden danger propagation causal relationship diagram, calculate the hidden danger node n i The propagation chain weight w i :

[0150]

[0151] Among them, β ij For node n i and parent node n j The strength of association, r j is the parent node n j The dynamic risk score, f j is the parent node n j The knowledge graph feature vector, j is the index, g ( rj ,f j ) is the parent node n j The nonlinear combination function of the risk score and feature matrix:

[0152] g ( r j ,f j ) =ReLU ( W q r j +W e f j ) ;

[0153] Among them, ReLU is the activation function, W q and W e is a trainable weight matrix;

[0154] S54, normalize the propagation chain weights to generate the hidden danger propagation chain matrix W = { w i} , where the potential danger node n i The propagation chain weight w i It is expressed as:

[0155]

[0156] Among them, δ is the adjustment coefficient, h l For node n i The static propagation weight of l, k and m are indexes, n k is the node, h m For node n m The static propagation weight of N is the set of all nodes, β kj is the propagation weight, Pa ( n k ) is node n k The parent node set of

[0157] S55, transform the hidden danger propagation chain matrix W into { w i} , hidden danger risk scoring matrix R and knowledge graph feature matrix F G Combined to generate optimized hidden danger risk classification results i :

[0158]

[0159] Among them, γ 1 ,γ 2 ,γ 3are the adjustment coefficients for the transmission chain weight, dynamic risk score and neighborhood comprehensive characteristics, Softmax is the normalization function, N ( n i) is the set of neighborhood nodes;

[0160] S56. Update the optimized hidden danger risk classification results to the hidden danger rule library.

[0161] In this implementation manner, S6 specifically includes:

[0162] S61, extracting a multimodal feature set of hidden danger nodes, including hidden danger data set feature X = {x 1 ,x 2 ,…,x n} , knowledge graph feature matrix F G = { f 1 ,f 2 ,…,f n} And the time series feature matrix T = {t 1 ,t 2 ,…,t n} , for each node n i Construct feature fusion input:

[0163]

[0164] in, For node n i The initial multimodal feature vector, ReLU is the activation function, R 1 , R 2 and R 3 is the trainable weight matrix;

[0165] S62. Update the feature vector of the potential danger node through the multi-layer implicit feature propagation module:

[0166]

[0167] in, For node n i The feature vector after propagation in the l+1th layer, N ( n i) is the set of neighborhood nodes, is the attention weight, For node n j The feature vector after propagation in layer l, For node n i The feature vector after propagation in layer l, R 4 and R 5 is the trainable weight matrix, j is the index;

[0168] S63. Combined with the dynamic feature adjustment mechanism, according to the time series feature T, the attention weight is updated through the dynamic adjustment mechanism to generate the feature propagation matrix of the node:

[0169]

[0170] in, is the final attention weight, e ij and e ik is the basic attention score, is the time dynamic characteristic weight, ψ j and ψ k is the global importance weight, k 1 and k 2 is the adjustment coefficient, exp is the exponential function, and k is the index;

[0171] S64 converts the final feature vector of the potential danger node into Input the multimodal hidden danger identification model and generate classification results based on the multi-objective optimization mechanism and dynamic characteristic enhancement mechanism:

[0172]

[0173] Among them, y i is the classification result, Softmax is the normalization function, g ( z j ,r j ) is the neighborhood feature aggregation function, For the prediction auxiliary module function, R 6 is the trainable weight matrix, λ 1 and λ 2 is the adjustment coefficient, α ij is the attention weight, z j is the feature vector, r j is the risk score, p i To predict auxiliary characteristics;

[0174] S65. Output the hidden danger classification results, including hidden danger category, hidden danger risk level and key neighborhood influencing factors, and update the classification fields of the hidden danger database model.

[0175] In this implementation manner, the S7 specifically includes:

[0176] S71. Extract hidden danger risk classification results S = { s 1 ,s 2 ,…,s n} , Hidden danger classification result Y = {y 1 ,y 2 ,…,y n} And the knowledge graph feature matrix FG = { f 1 ,f 2 ,…,f n} ;

[0177] S72. Build an optimized task allocation model to determine the task priority of hidden danger nodes according to risk classification and hidden danger category:

[0178]

[0179] Among them, p i is the task priority, Softmax is the normalization function, B 1 , B 2 and B 3 is the adjustment coefficient, g ( f j ) is the characteristic mapping function, β ij is the attention weight, s i is the risk grading score, y i is the classification result, f j is the knowledge graph feature vector, h ( y i) is the hidden danger classification score function, N ( n i) is the set of neighborhood nodes, j is the index;

[0180] S73, based on task priority p i , generate an optimized task allocation plan:

[0181]

[0182] Among them, Y is the task allocation matrix, c i is the rectification cost, d ij is the correlation distance, ξ ij is the task allocation constraint variable, N is the total number of nodes, argmin is to adjust the task allocation matrix Y so that the total task cost and task allocation coordination reach the optimal balance, i and j are indexes;

[0183] S74. Optimize the task allocation strategy through reinforcement learning, and use the policy gradient method to update the task allocation model parameters. The loss function is defined as:

[0184]

[0185] in, The objective loss optimized for task allocation, π ( a i |s i) For state s iNext select action a i The probability of, ln is the logarithmic function, r i is the reward function, E is the expected symbol;

[0186] S75. Output the optimized task allocation result, and update the task execution field of the hidden danger database model.

[0187] In this implementation manner, S8 specifically includes:

[0188] S81. Integrate the hidden danger risk classification results S = { s 1 ,s 2 ,…,s n} , Hidden danger classification result Y = {y 1 ,y 2 ,…,y n} , rectification task execution data T = { t 1 ,t 2 ,…,t n} And the knowledge graph feature matrix F G ={f 1 ,f 2 ,…,f n} , construct the hidden danger dynamic characteristic label L d = { l 1 ,l 2 ,…,l n} :

[0189]

[0190] Among them, Q 1 , Q 2 , Q 3 and Q 4 is a trainable weight matrix, ReLU is the activation function, s i is the risk grading score, y i is the hidden danger classification result, t i The data vector for the rectification task, f i is the knowledge graph feature vector, is the final feature vector, l i is the dynamic feature label, h ( y i) is the hidden danger classification score function;

[0191] S82, label the hidden danger dynamic characteristic L d Input the hidden danger feature propagation module, combine the time series model and the multimodal hidden danger identification model, and dynamically update the hidden danger node features:

[0192]

[0193] in, is the potential danger node n i The updated feature vector of is the final eigenvector of the potential danger node, Q 5 and Q 6 is the trainable weight matrix, α ij is the attention weight, g ( z j ,f j ) is the neighborhood feature combination function, ReLU is the nonlinear activation function, z j is the characteristic vector of the neighborhood node, f j is the knowledge graph feature, N ( n i ) is the set of neighborhood nodes, j is the index;

[0194] S83. Based on the updated hidden danger node characteristics, the dynamic correlation heat between the hidden danger nodes is calculated to generate a hidden danger heat map H= { H ij } :

[0195]

[0196] in, is the potential danger node n j The updated feature vector, cosine_similarity is the cosine similarity function, H ij is the potential danger node n i and n j Dynamic correlation heat;

[0197] S84. Using the hidden danger heat map H and the hidden danger dynamic characteristic label L d , analyze the dynamic evolution trend of potential danger nodes and generate a trend analysis report:

[0198]

[0199] Among them, Trend_Score i is the potential danger node n i Dynamic trend score, is the dynamic risk change rate, λ q , w and λ e is the weight parameter, cosine_similarity(l i ,l j ) is the dynamic feature label similarity, t i The time for completing rectification tasks;

[0200] S85. Combine the hidden danger heat map and trend analysis report to update the time series model and multimodal hidden danger identification model and iterate the model performance:

[0201]

[0202] in, is the loss function for iterative optimization, E is the expected symbol, is the real eigenvector, is the weight parameter, is the predicted distribution, is the actual distribution, N is the total number of nodes, is the KL divergence between the predicted distribution and the true distribution, and i is the index.

[0203] refer to Figure 2 , a safety inspection system based on a hidden danger database model, including the following modules:

[0204] Data collection and storage module, used to collect multi-source hidden danger data;

[0205] The knowledge graph construction module is used to construct a hidden danger-related knowledge graph and extract node features and association relationships;

[0206] The risk assessment and hidden danger classification module is used to generate hidden danger risk scores and classify hidden danger nodes;

[0207] Dynamic characteristic analysis and heat map generation module, used to analyze the dynamic characteristic labels of hidden danger nodes and generate hidden danger heat maps;

[0208] The risk assessment and hidden danger classification module is used to dynamically analyze and classify hidden danger nodes;

[0209] Task allocation and optimization module, used to optimize task allocation strategies and dynamically adjust resource allocation and priority;

[0210] Trend analysis and report generation module, used to generate hidden danger trend analysis reports and decision support information;

[0211] Model training and optimization module, used to optimize the performance of time series models and multimodal hidden danger identification models.

[0212] Embodiment 1:

[0213] In order to verify the feasibility of the present invention in implementation, the present invention is applied to a large industrial park, which covers an area of ​​about 5 square kilometers, including multiple production workshops, storage areas and logistics sites, involving a variety of potential safety hazards, including equipment aging, accumulation of flammable materials, pipeline leakage and other problems. Traditional safety inspection methods are mainly manual inspections, and hidden danger records are stored in paper files or a single database, which is difficult to adapt to the dynamic changes of hidden dangers and management needs in complex environments.

[0214] In order to overcome this problem, the system of the present invention first deploys multimodal data acquisition equipment, including sensors, cameras and infrared detectors, at key locations in the industrial park to collect hidden danger related information in real time. Data collection covers equipment operating status, temperature and humidity information, smoke concentration, and hazardous materials stacking conditions. After standardized processing, these data are stored in the hidden danger database model. Subsequently, the system constructs a hidden danger rule base based on historical accident cases and the safety management specifications of the park, and generates a hidden danger association network using the knowledge graph construction module.

[0215] In actual application, a multimodal device in a production workshop detected an abnormally high temperature, and the smoke sensor sounded an alarm. The system marked this hidden danger event as a high-risk node through dynamic characteristic label analysis, and analyzed its possible propagation path in combination with the hidden danger heat map. The results showed that high-temperature areas may affect nearby stacked items, further causing fire risks. At the same time, the system used a time series risk assessment model to predict the risk level change trend of hidden dangers, and assessed the risk score of the hidden danger to be 0.85 (the risk score range is 0 to 1, 1 is extremely high risk).

[0216] In order to respond quickly, the system automatically assigned rectification tasks based on the hidden danger risk score and knowledge graph features. The system prioritized the dispatch of two professional maintenance personnel, and combined the task allocation with the path planning scheme calculated by the optimization module to ensure that the maintenance personnel arrived at the scene within 10 minutes. At the same time, the system generated a hidden danger dynamic characteristics report and rectification plan, and uploaded the hidden danger heat map, rectification steps and resource requirements to the management platform. According to the plan provided by the system, the management personnel mobilized the fire brigade to conduct a comprehensive inspection of the site, and completed the transfer of dangerous goods and equipment cooling within 30 minutes.

[0217] After the rectification is completed, the system dynamically integrates the rectification task execution data with the hidden danger node feature update, and records the evolution trend of the hidden danger through a trend analysis report. The analysis shows that the risk score of the hidden danger node has dropped from the initial 0.85 to 0.15, indicating that the system has effectively mitigated the security threat. In addition, the system updates the hidden danger rule base in the knowledge graph based on the task execution efficiency, providing data support for the subsequent management of similar hidden dangers.

[0218] Table 1 Comparison data of hidden danger management system

[0219]

[0220]

[0221] The above table shows the significant advantages of the system of the present invention over traditional hidden danger management methods. In terms of hidden danger detection time, the system of the present invention completes the detection in only 10 minutes through multimodal data fusion, which is 75% faster than the 40 minutes of the traditional method. The accuracy of hidden danger identification has increased from 70% of the traditional method to 92%, significantly reducing the false alarm and missed alarm rates. In addition, the traditional method is unable to analyze the hidden danger propagation path, while the system of the present invention achieves this function through hidden danger heat maps and knowledge graphs.

[0222] In terms of dynamic risk assessment, the static scoring of traditional methods cannot reflect the real-time changes of hidden dangers, while the system of the present invention uses time series models to perform dynamic risk analysis and achieves real-time assessment. In terms of task allocation efficiency, the system of the present invention shortens the task allocation time from 20 minutes to 5 minutes through optimization algorithms, and supports real-time feedback and task tracking, solving the problem of lack of rectification tracking in traditional methods.

[0223] At the same time, the system of the present invention also provides more accurate hidden danger propagation relationships and trend predictions through hidden danger heat map generation and trend analysis capabilities, assisting managers in making scientific decisions. Compared with traditional static models, the system of the present invention has dynamic optimization capabilities, can continuously improve model performance through online learning, and adapt to complex scenario requirements. These improvements fully demonstrate the superiority of the system of the present invention in terms of efficiency, accuracy, and intelligence.

[0224] The above description is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can make equivalent replacements or changes according to the technical scheme and inventive concept of the present invention within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

Claims

1. A safety inspection method based on a hidden danger database model, characterized in that: The steps include: S1. Establish a hidden danger table, inspection record table and rectification record table, and build a hidden danger rule library based on historical accident cases and industry norms; S2. Collect multi-source hidden danger data through the data acquisition module, perform standardized processing, form a hidden danger data set, and store it in the hidden danger database model; S3. Based on the hidden danger data set and hidden danger rule base, construct the hidden danger associated knowledge graph, extract the potential features of hidden danger nodes and edges, and generate the knowledge graph feature matrix; S4, input the hidden danger data set and knowledge graph feature matrix into the time series model, conduct dynamic risk analysis, and generate a hidden danger risk scoring matrix; S5. Combine the hidden danger risk scoring matrix and the knowledge graph feature matrix, perform causal inference through the Bayesian network model, analyze the hidden danger propagation chain and impact range, optimize the hidden danger risk classification, and update the hidden danger rule base; S6. Combining the hidden danger dataset, knowledge graph feature matrix and time series features, input the multimodal hidden danger identification model to classify the hidden dangers; S7. Combine the hidden danger risk classification results, classified hidden danger results and knowledge graph feature matrix to optimize the rectification task allocation strategy, update the hidden danger status in real time and store the rectification plan in the hidden danger database model; S8. Integrate hidden danger risk grading results, hidden danger classification results, knowledge graph feature matrix and rectification task execution data, generate hidden danger dynamic characteristic labels, input time series model and multimodal hidden danger identification model, iterate model performance, and generate hidden danger heat map and trend analysis report.

2. A safety inspection method based on a hidden danger database model according to claim 1, characterized in that: The S3 specifically includes: S31. Extract hidden danger features from hidden danger data sets, including hidden danger description information, risk level, occurrence frequency, and associated inspection and rectification records; S32. Classify the hidden danger data and mark the types and attributes of the hidden dangers according to the rules of the hidden danger rule library; S33, establish a hidden danger association knowledge graph G = (V, E), where V represents a set of hidden danger nodes, including the type, occurrence time, and location of the hidden danger, and E represents the association between hidden danger nodes, including causal relationship, time association, and spatial association; S34. In the constructed hidden danger associated knowledge graph G, an embedding optimization algorithm combining the dynamic characteristics of time series and the hidden danger associated weights is used to embed the hidden danger node v i The eigenvector of ∈V is expressed as: Among them, f(v i ) is the node v i The final embedding vector representation of , W1, W2 and W3 are the trainable weight matrices of node features, time series features and neighborhood features, T is the total number of time steps, α t is the attention weight at time step t, x i,t For node v i The time series features at time step t, β ij For node v i and neighboring node v j The association weight between i ) is the node v i The set of neighboring nodes, x j,t For node v j The time series features at time step t, h j is the neighborhood node v j The original eigenvector of i is the neighborhood node v i The original eigenvector of g(h j ,x j,t ) is a nonlinear combination function; S35. Extract the hidden danger node features and edge features after graph embedding to generate the knowledge graph feature matrix F G , where F G =[f(v1),f(v2),...,f(v n )], each f(v i ) is the node v i The embedded feature vector of .

3. A safety inspection method based on a hidden danger database model according to claim 1, characterized in that: The S4 specifically includes: S41. Define the hidden danger dataset and knowledge graph feature matrix as X = {x1, x2, …, x n } and F G ={f1,f2,…,f n }, where n represents the number of nodes with hidden dangers, x i is the original feature vector of potential risk node i, f i is the knowledge graph feature vector of hidden danger node i; S42, merge the hidden danger dataset features and knowledge graph features to form a comprehensive feature vector z i , which is expressed as: z i =σ(W1x i +W2f i ); Among them, W1 and W2 are trainable weight matrices, and σ is the activation function; S43, the comprehensive feature vector z i Input time series model, define the input sequence Z of the time series model t ={z 1,t ,z 2,t ,…,z n,t }, where t is the time step, z i,t is the comprehensive characteristics of potential danger node i at time step t; S44. Calculate the dynamic risk score of the hidden danger node through the time series model: Among them, r i,t is the risk score of potential risk node i at time step t, W3 and W4 are trainable weight matrices, Softmax is the normalization function, z i,k is the comprehensive feature of potential danger node i at time step k, T is the total number of time steps in the time series, α k is the attention weight at time step k: in, is the attention score at time step k, is the attention score at time step j, exp is the exponential function; S45, normalize the dynamic risk scores of all hidden danger nodes to generate a hidden danger risk score matrix R = {r i,t }.

4. A safety inspection method based on a hidden danger database model according to claim 1, characterized in that: The S5 specifically includes: S51. Combine the hidden danger risk score matrix R and the knowledge graph feature matrix F G Input the Bayesian network model to construct a causal relationship diagram of hidden danger propagation; S52. Define the Bayesian network as BN = (N, L, P), where the potential risk node set N = {n1, n2, ..., n n }, the directed edge L between the potential hazard nodes = {l ij }, P is the conditional probability distribution, defined as: Among them, Pa(n i ) is the potential danger node n i The parent node set of θ k is the conditional probability of the kth parent node, x k is the state variable; S53, according to the knowledge graph feature matrix F G And the hidden danger propagation causal relationship diagram, calculate the hidden danger node n i The propagation chain weight w i : Among them, β ij For node n i and parent node n j The strength of association, r j is the parent node n j The dynamic risk score, f j is the parent node n j The knowledge graph feature vector, j is the index, g(r j ,f j ) is the parent node n j The nonlinear combination function of the risk score and feature matrix: g(r j ,f j )=ReLU(W q r j +W e f j ); Among them, ReLU is the activation function, W q and W e is a trainable weight matrix; S54, normalize the propagation chain weights to generate a hidden danger propagation chain matrix W = {w i }, where the potential danger node n i The propagation chain weight w i It is expressed as: Among them, δ is the adjustment coefficient, h l For node n i The static propagation weight of l, k and m are indexes, n k is the node, h m For node n m The static propagation weight of N is the set of all nodes, β kj is the propagation weight, Pa(n k For node n k The parent node set of S55, transform the hidden danger propagation chain matrix W = {w i }, Hidden danger risk scoring matrix R and knowledge graph feature matrix F G Combined to generate optimized hidden danger risk classification results i : Among them, γ1, γ2, γ3 are the adjustment coefficients of the transmission chain weight, dynamic risk score and neighborhood comprehensive characteristics, Softmax is the normalization function, N(n i ) is a set of neighborhood nodes; S56. Update the optimized hidden danger risk classification results to the hidden danger rule library.

5. The safety inspection method based on the hidden danger database model according to claim 1 is characterized in that: The S6 specifically includes: S61, extracting a multimodal feature set of hidden danger nodes, including hidden danger data set features X = x1, x2, ..., x n }、Knowledge graph feature matrix F G ={f1,f2,…,f n } and time series feature matrix T = t1, t2, …, t n }, for each node n i Construct feature fusion input: in, For node n i The initial multimodal feature vector of , ReLU is the activation function, R1, R2 and R3 are trainable weight matrices; S62. Update the feature vector of the potential danger node through the multi-layer implicit feature propagation module: in, For node n i The feature vector after propagation in the l+1th layer, N(n i ) is the set of neighborhood nodes, is the attention weight, For node n j The feature vector after propagation in layer l, For node n i The feature vector after propagation in layer l, R4 and R5 are trainable weight matrices, and j is the index; S63. Combined with the dynamic feature adjustment mechanism, according to the time series feature T, the attention weight is updated through the dynamic adjustment mechanism to generate the feature propagation matrix of the node: in, is the final attention weight, e ij and e ik is the basic attention score, is the time dynamic characteristic weight, ψ j and ψ k is the global importance weight, k1 and k2 are adjustment coefficients, exp is the exponential function, and k is the index; S64 converts the final feature vector of the potential danger node into Input the multimodal hidden danger identification model and generate classification results based on the multi-objective optimization mechanism and dynamic characteristic enhancement mechanism: Among them, y i is the classification result, Softmax is the normalization function, g(z j ,r j ) is the neighborhood feature aggregation function, is the prediction auxiliary module function, R6 is the trainable weight matrix, λ1 and λ2 are the adjustment coefficients, α ij is the attention weight, z j is the feature vector, r j is the risk score, p i To predict auxiliary characteristics; S65. Output the hidden danger classification results, including hidden danger category, hidden danger risk level and key neighborhood influencing factors, and update the classification fields of the hidden danger database model.

6. A safety inspection method based on a hidden danger database model according to claim 1, characterized in that: The S7 specifically includes: S71, extract hidden danger risk classification result S = {s1, s2, ..., s n }、Hazard classification result Y=y1,y2,…,y n } and the knowledge graph feature matrix F G ={f1,f2,…,f n }; S72. Build an optimized task allocation model to determine the task priority of hidden danger nodes according to risk classification and hidden danger category: Among them, p i is the task priority, Softmax is the normalization function, B1, B2 and B3 are adjustment coefficients, g(f j ) is the characteristic mapping function, β ij is the attention weight, s i is the risk grading score, y i is the classification result, f j is the knowledge graph feature vector, h(y i ) is the hidden danger classification score function, N(n i ) is the neighborhood node set, j is the index; S73, based on task priority p i , generate an optimized task allocation plan: Among them, Y is the task allocation matrix, c i is the rectification cost, d ij is the correlation distance, ξ ij is the task allocation constraint variable, N is the total number of nodes, argmin is to adjust the task allocation matrix Y so that the total task cost and task allocation coordination reach the optimal balance, i and j are indexes; S74. Optimize the task allocation strategy through reinforcement learning, and use the policy gradient method to update the task allocation model parameters. The loss function is defined as: in, The objective loss for task allocation optimization, π(a i |s i ) is in state s i Next select action a i The probability of, ln is the logarithmic function, r i is the reward function, E is the expected symbol; S75. Output the optimized task allocation result, and update the task execution field of the hidden danger database model.

7. A safety inspection method based on a hidden danger database model according to claim 1, characterized in that: The S8 specifically includes: S81. Integrated hidden danger risk classification results S = {s1, s2, ..., s n }、Hazard classification result Y={y1,y2,…,y n }、Rectification task execution data T={t1,t2,…,t n } and the knowledge graph feature matrix F G ={f1,f2,…,f n }, construct the hidden danger dynamic characteristic label L d ={l1,l2,…,l n }: Among them, Q1, Q2, Q3 and Q4 are trainable weight matrices, ReLU is the activation function, and s i is the risk grading score, y i is the hidden danger classification result, t i The data vector for the rectification task, f i is the knowledge graph feature vector, is the final feature vector, l i is a dynamic feature label, h(y i ) is the hidden danger classification score function; S82, label the hidden danger dynamic characteristic L d Input the hidden danger feature propagation module, combine the time series model and the multimodal hidden danger identification model, and dynamically update the hidden danger node features: in, is the potential danger node n i The updated feature vector of is the final feature vector of the potential danger node, Q5 and Q6 are trainable weight matrices, α ij is the attention weight, g(z j ,f j ) is the neighborhood feature combination function, ReLU is the nonlinear activation function, z j is the characteristic vector of the neighborhood node, f j is the knowledge graph feature, N(n i ) is the neighborhood node set, j is the index; S83, based on the updated hidden danger node characteristics, calculate the dynamic correlation heat between the hidden danger nodes, and generate a hidden danger heat map H = {H ij }: in, is the potential danger node n j The updated feature vector, cosine_similarity is the cosine similarity function, H ij is the potential danger node n i and n j Dynamic correlation heat; S84. Using the hidden danger heat map H and the hidden danger dynamic characteristic label L d , analyze the dynamic evolution trend of potential danger nodes and generate a trend analysis report: Among them, Trend_Score i is the potential danger node n i Dynamic trend score, is the dynamic risk change rate, λ q , w and λ e is the weight parameter, cosine_similarity(l i ,l j (is the dynamic feature label similarity, t i The time for completing rectification tasks; S85. Combine the hidden danger heat map and trend analysis report to update the time series model and multimodal hidden danger identification model and iterate the model performance: in, is the loss function for iterative optimization, E is the expected symbol, is the real eigenvector, is the weight parameter, is the predicted distribution, is the actual distribution, N is the total number of nodes, is the KL divergence between the predicted distribution and the true distribution, and i is the index.

8. A safety inspection system based on a hidden danger database model, a safety inspection method based on a hidden danger database model according to any one of claims 1 to 7, characterized in that: Includes the following modules: Data collection and storage module, used to collect multi-source hidden danger data; The knowledge graph construction module is used to construct a hidden danger-related knowledge graph and extract node features and association relationships; The risk assessment and hidden danger classification module is used to generate hidden danger risk scores and classify hidden danger nodes; Dynamic characteristic analysis and heat map generation module, used to analyze the dynamic characteristic labels of hidden danger nodes and generate hidden danger heat maps; The risk assessment and hidden danger classification module is used to dynamically analyze and classify hidden danger nodes; Task allocation and optimization module, used to optimize task allocation strategies and dynamically adjust resource allocation and priority; Trend analysis and report generation module, used to generate hidden danger trend analysis reports and decision support information; Model training and optimization module, used to optimize the performance of time series models and multimodal hidden danger identification models.

Images