Coal mine production management knowledge question-answering method based on natural language processing

Abstract

The invention discloses a coal mine production management knowledge question-answering method based on natural language processing, and the method comprises the following steps: S1, collecting environment data and user behavior data, and constructing a data set; s2, performing real-time processing on the data set; s3, constructing a user portrait by using a density-based spatial clustering algorithm; s4, constructing a knowledge graph, constructing a cognitive model by adopting a graph convolutional network and an improved Transform, and performing reasoning in combination with logistic regression and an XGBoost algorithm; s5, constructing an environment simulation model through historical data analysis; s6, generating a personalized natural language answer according to the user portrait, the knowledge graph and the environment state prediction; s7, collecting user feedback data, and adjusting model parameters and an optimization strategy by using an adaptive learning algorithm; and S8, storing the plan template by using a relational database, and continuously optimizing the plan template through historical data analysis. Natural language processing and deep learning are utilized, coal mine production management intelligent question answering is achieved, and the method has the advantages of being efficient and high in individuation.

Description

Technical Field

[0001] The present invention relates to the field of natural language processing and deep learning technology, and in particular to a coal mine production management knowledge question and answer method based on natural language processing. Background Art

[0002] Coal mine production management is a complex and highly dynamic process involving a large amount of data collection, analysis and decision-making. Traditional coal mine production management systems mainly rely on manual monitoring and empirical judgment, and have problems such as low efficiency, slow response speed, and insufficient decision-making accuracy. These defects are particularly obvious in the face of emergencies and complex environmental changes, which may lead to serious production safety accidents and economic losses.

[0003] With the development of information technology, more and more coal mine production management systems have begun to introduce automated monitoring and data analysis technologies. For example, sensor technology is used to monitor environmental data (such as temperature, humidity, equipment status, gas concentration, etc.) at coal mine production sites in real time, and log analysis technology is used to collect user behavior data. Although these technologies have improved the efficiency and accuracy of data collection to a certain extent, there are still significant deficiencies in data processing, analysis, and decision support.

[0004] Existing coal mine production management systems often lack the ability to effectively process and analyze massive amounts of data, especially in scenarios with high real-time requirements. The traditional centralized data processing model has problems such as high latency and low processing efficiency. The introduction of edge computing provides a solution to this problem. By deploying computing nodes on site in coal mines, data processing and analysis can be performed at the source of the data, significantly improving the system's response speed and processing efficiency. However, the existing edge computing technology still has a lot of room for improvement in the complexity and intelligence level of data processing algorithms.

[0005] In terms of user behavior analysis, traditional analysis methods mainly rely on simple statistical analysis and rule matching, which cannot accurately capture the complexity and diversity of user behavior. In recent years, density-based spatial clustering algorithms (such as DBSCAN) and association rule analysis techniques have been gradually applied to user behavior analysis, which can more accurately describe user behavior patterns and preferences. However, these methods still face challenges in processing high-dimensional and large-scale data, and need to be combined with more advanced data processing algorithms and computing technologies.

[0006] As an emerging knowledge management and representation technology, knowledge graph can represent complex knowledge in a structured and systematic way and support efficient knowledge retrieval and reasoning. Through natural language processing and information extraction technology, knowledge can be automatically extracted from massive documents and added to the knowledge graph. However, the existing knowledge graph construction and reasoning methods are still insufficient in dealing with dynamic and uncertain knowledge, and need to be combined with more advanced deep learning models to improve the accuracy and efficiency of knowledge reasoning.

[0007] In terms of environmental state prediction, traditional time series analysis methods perform poorly when dealing with complex nonlinear and multimodal data. The combination of mixed density networks and long short-term memory networks provides a more powerful tool for time series prediction, which can capture long-term and short-term dependencies and multimodal characteristics in data. However, these methods still face the problems of high model complexity and large computing resource requirements in practical applications, and need further optimization and improvement.

[0008] Personalized answer generation is one of the important applications of natural language processing technology in coal mine production management. Existing methods are mainly based on simple template matching and rule generation, which cannot meet the diverse and personalized needs of users.

[0009] Therefore, how to provide a coal mine production management knowledge question-answering method based on natural language processing is a problem that technical personnel in this field urgently need to solve. Summary of the invention

[0010] One purpose of the present invention is to propose a coal mine production management knowledge question and answer method based on natural language processing. The present invention makes full use of natural language processing, edge computing and deep learning to build an intelligent coal mine production management knowledge question and answer system. By collecting and analyzing environmental data and user behavior data in real time, personalized natural language answers are generated, and emergency plans are dynamically optimized. The system has the advantages of efficient processing, personalized services and high security, effectively improving the intelligent level of coal mine production management, significantly improving the system's response speed and decision-making accuracy, and providing more efficient and safe support for coal mine production.

[0011] A coal mine production management knowledge question-answering method based on natural language processing according to an embodiment of the present invention comprises the following steps:

[0012] S1. Use sensor technology to collect environmental data from coal mine production sites, use log analysis technology to collect and analyze user behavior data, and build a data set;

[0013] S2. Deploy edge computing nodes on-site at coal mines, use a data processing algorithm combining variational autoencoders and generative adversarial networks to perform edge analysis, and process data sets in real time;

[0014] S3. Use density-based spatial clustering algorithms to build user portraits, analyze user behaviors and preferences through association rules, and combine environmental data from production sites with user portraits;

[0015] S4. Build a knowledge graph, extract knowledge through natural language processing and information extraction technology, use graph convolutional networks and improved Transformer to build a cognitive model, and combine logistic regression and XGBoost algorithms for reasoning;

[0016] S5. Build an environmental simulation model through historical data analysis, use edge computing and cloud computing to combine real-time data fusion, and use a time series prediction algorithm that combines a hybrid density network with a long short-term memory network to predict environmental status;

[0017] S6, Generate personalized natural language answers based on user portraits, knowledge graphs, and environmental state predictions;

[0018] S7. Collect user feedback data, analyze it through data analysis tools, and use adaptive learning algorithms to adjust model parameters and optimization strategies;

[0019] S8. Use relational databases to store emergency plan templates, apply rule engines combined with knowledge graphs to generate rule-based emergency plans, automatically generate emergency plans based on environmental simulation and prediction results, and continuously optimize emergency plan templates through historical data analysis.

[0020] Furthermore, the S2 specifically includes:

[0021] S21. Use edge computing nodes to perform preliminary data cleaning and preprocessing, including noise filtering, missing value filling, and data standardization, to form a preprocessed data set X;

[0022] S22. Input the preprocessed data set X into the variational autoencoder model, extract features and reduce the dimension of the data through the variational autoencoder to generate latent variables Z:

[0023] Z=μ+σ⊙∈;

[0024] Among them, μ represents the mean, σ represents the variance, ∈~N(0,I), ⊙ represents element-by-element multiplication, and I represents the identity matrix;

[0025] S23, inputting the hidden variable Z into a generative adversarial network, where the generative adversarial network includes a generator G and a discriminator D;

[0026] The generator G generates new data samples G(Z) based on the hidden variable Z:

[0027] G(Z)=tanh(W g ·Z+b g);

[0028] Among them, W g represents the weight of the generator, b g represents the bias of the generator;

[0029] The discriminator D compares the generated data sample G(Z) with the real data set X, and uses the discriminator D to determine the authenticity of the sample:

[0030] D(G(Z))=f(W d ·G(Z)+b d );

[0031] Among them, W d represents the weight of the discriminator, b d represents the bias of the discriminator, and f represents the activation function;

[0032] S24. The variational autoencoder and the generative adversarial network are jointly trained through the back propagation algorithm to optimize the parameters of the generator and the discriminator so that the generated data samples gradually approach the real data distribution. The specific optimization objective function is:

[0033]

[0034] Among them, p data (x) represents the probability density function of the real data distribution, x represents the data point sampled from the real data distribution, and p z (z) represents the probability distribution of latent variables in the latent space, and z represents the latent variables sampled from the latent space;

[0035] S25. Process the real-time collected data through the trained variational autoencoder and generative adversarial network to generate high-quality processed data

[0036] Furthermore, the S25 specifically includes:

[0037]

[0038] Among them, α represents the weight of the attention mechanism, and Attention(D,G(Z)) represents the weighted fusion of attention to the data sample G(Z) and the real data.

[0039] Furthermore, the S3 specifically includes:

[0040] S31, using density-based spatial clustering algorithm to generate the Cluster analysis of the data;

[0041] Set two parameters: radius parameter ∈ and minimum sample parameter MinPts;

[0042] For each data point p in the dataset i , calculate the number of neighborhood data points N(p i ):

[0043]

[0044] Among them, dist(p i ,p j ) represents the data point p i and data point p j The distance between

[0045] The data points are divided into core points, boundary points and noise points, where the core points meet the number of neighborhood data points N(p i ) is greater than or equal to MinPts, the boundary point satisfies the condition that the number of neighboring data points is less than MinPts but is within the neighborhood of the core point, and the noise point does not meet the conditions of both the core point and the boundary point;

[0046] Cluster the core points and the points in their neighborhood, classify the connected core points and the points directly reachable by density into the same category, and form a user behavior pattern cluster;

[0047] S32, performing association rule analysis on the clustering results;

[0048] Calculate frequent item sets and generate frequent item sets F through Apriori algorithm or FP-Growth algorithm. Frequent item sets F meet the support threshold Support(A):

[0049]

[0050] Where Count(A) represents the number of transactions containing item set A, and N represents the total number of transactions;

[0051] Generate association rules in the form of A→B, where A and B represent elements in the frequent item set and satisfy the confidence threshold Confidence(A→B):

[0052]

[0053] To evaluate the effectiveness of association rules, lift (A→B) is used to measure the relevance of the rules:

[0054]

[0055] S33. Decompose the environmental data into time series into trend component, seasonal component and residual component, expressed as:

[0056] y t =T t+S t +R t ;

[0057] Among them, y t represents time series data, T t represents the trend component, S t represents the seasonal component, R t represents the residual component;

[0058] S34, use the moving average method to smooth the trend components and identify the long-term trend. The moving average formula is T t for:

[0059]

[0060] Where n represents the size of the moving window;

[0061] S35. Use fast Fourier transform to identify periodic changes in seasonal components. The Fourier transform formula is:

[0062]

[0063] Among them, X k represents the frequency domain signal, x t represents the time domain signal, and N represents the signal length;

[0064] S36. Combine the user behavior pattern and the time series characteristics of the environmental data to generate a user profile, which includes the user's operating habits, behavioral preferences, and reaction information to different environmental conditions.

[0065] Furthermore, the S4 specifically includes:

[0066] S41. Processing coal mine production management documents by natural language processing technology, including word segmentation, part-of-speech tagging, and named entity recognition. The word segmentation and part-of-speech tagging use the SpaCy tool, and the named entity recognition uses the BERT model;

[0067] S42. Extract knowledge from the processed documents, including entities, attributes and relationships, and use information extraction technology to add the extracted knowledge to the knowledge graph to form a complete knowledge graph;

[0068] S43. Use graph convolutional networks to learn embedded representations of knowledge graphs and generate low-dimensional vector representations of each node. Let the graph be G, the node be v, and the neighbor node be N(v). Then the representation of node v is h v The calculation formula is:

[0069]

[0070] Among them, σ represents the activation function, W(l) represents the weight matrix of the lth layer, aggregate represents the aggregation function, represents the representation of node v at layer l, represents the representation of node u at layer l, represents the representation of node v at layer l+1;

[0071] S44. The embedding representation result of the graph convolutional network is input into the improved Transformer model for further processing. The improved Transformer model includes an adaptive multi-head attention mechanism and dynamic position encoding to generate a more contextually understood knowledge representation. The adaptive multi-head attention score α ij The calculation formula is:

[0072]

[0073] Where a represents the adaptive attention weight vector, || represents the vector connection operation, W represents the weight matrix, and h i represents the feature representation of node i, h j represents the feature representation of node j, and PE(i,j) represents the dynamic position encoding of nodes i and j:

[0074]

[0075] Among them, i and j represent the index of the node, d represents the position dimension, and D represents the total embedding dimension;

[0076] The improved Transformer model plays the following roles in the coal mine production management knowledge question answering system:

[0077] Enhanced contextual understanding capabilities: Through the adaptive multi-head attention mechanism, the improved Transformer can more effectively capture the relationship between different parts of the input data, especially for complex knowledge graphs and long-distance dependencies. The improved Transformer can better understand and process contextual information.

[0078] Improve the flexibility of position encoding: Dynamic position encoding allows the model to adaptively adjust the position encoding according to the characteristics of the input data, thereby improving the adaptability of the model in different application scenarios. Compared with traditional fixed position encoding, dynamic position encoding can better handle the relationship and structural information between different nodes.

[0079] Optimize the effect of the attention mechanism: By improving the score calculation formula in the attention mechanism and introducing dynamic position encoding, the improved Transformer can more accurately calculate the attention weights between nodes, thereby improving the model's ability to identify key nodes and important information.

[0080] Improve the generalization ability of the model: The improved Transformer can better handle different types of input data by introducing adaptive multi-head attention and dynamic position encoding, enhance the generalization ability of the model, and perform better in dealing with diverse problems in coal mine production management.

[0081] The role of the improved Transformer in question-answering generation: When generating personalized natural language answers, the improved Transformer can use its enhanced context understanding ability and position encoding mechanism to generate more accurate and contextual answers, thereby improving the intelligence level of the question-answering system and user satisfaction.

[0082] S45. Classify the nodes in the knowledge graph through the logistic regression algorithm and predict the category of unknown nodes. The logistic regression prediction formula is:

[0083]

[0084] Where x represents the input feature, w represents the weight, b represents the bias, and P(y=1|x) represents the probability that the node belongs to category 1;

[0085] S46. Use the XGBoost algorithm to perform regression analysis on the nodes and relationships in the knowledge graph. XGBoost makes predictions by weighted averaging the results of multiple decision trees:

[0086]

[0087] Where K represents the number of trees, represents the predicted value of sample i, f k Represents the prediction result of the kth tree;

[0088] S47. Combine the results of logistic regression and XGBoost algorithms to generate the final inference results, improve the reasoning ability of the knowledge graph, and provide an accurate and comprehensive knowledge basis for the coal mine production management knowledge question and answer system.

[0089] Furthermore, the S5 specifically includes:

[0090] S51, build a mixed density network;

[0091] S52. Build a long short-term memory network. The network structure includes an input layer, an LSTM layer, and an output layer. The input layer receives the parameters output by the MDN. The LSTM layer is used to capture the long-term and short-term dependencies in the time series. The output layer generates prediction results.

[0092] S53. Combine the mixed density network with the long short-term memory network to predict the environmental state. The prediction formula is:

[0093]

[0094] in, represents the predicted value at time point t, y t represents the parameter input generated by the mixed density network, h t-1 represents the hidden state at the previous time point, c t-1 indicates the cell state at the previous time point;

[0095] S54. The prediction results are stored in the cloud computing platform and provided to the knowledge question answering system through an interface for query and use.

[0096] Furthermore, the S51 specifically includes:

[0097] Input layer, hidden layer and output layer. The input layer receives the fused comprehensive data set, the hidden layer is implemented by a multi-layer perceptron, and the output layer generates the parameters of the mixed density model:

[0098]

[0099] Among them, y t represents the predicted value at time point t, π j represents the weight of the jth Gaussian distribution, N(μ j ,σ j ) represents the probability density function of Gaussian distribution, μ j represents the mean of the jth Gaussian distribution, σ j Represents the standard value of the j-th Gaussian distribution.

[0100] Furthermore, the S52 specifically includes:

[0101] i t =σ(W i ·[h t-1 ,x t ]+b i );

[0102] f t =σ(W f ·[h t-1 ,x t ]+b f );

[0103] o t =σ(W o ·[h t-1 ,x t ]+b o );

[0104] g t =tanh(W g·[h t-1 ,x t ]+b g );

[0105] c t =f t ⊙c t-1 +i t ⊙g t ;

[0106] h t =o t ⊙tanh(c t );

[0107] Among them, i t represents the activation vector of the input gate, σ represents the activation function, W i , W f , W o and W g represents the weight matrix input to each gate and candidate memory state, b i , b f , b o and b g represents the bias term input to each gate and candidate memory state, h t-1 represents the hidden state at the previous time point, x t represents the input data at the current time point, f t represents the activation vector of the forget gate, o t represents the activation vector of the output gate, g t represents the activation vector of the candidate memory state, c t represents the cell state at the current time point, c t-1 represents the cell state at the previous time point, ⊙ represents the element multiplication operation, h t Indicates the hidden state at the current time point.

[0108] Furthermore, the S7 specifically includes:

[0109] S71. In the adaptive learning module, construct a reward function R;

[0110] S72, based on the optimization result of the reward function R, using the adaptive learning algorithm to update the model parameters of the system, so that the system can gradually improve its ability to respond to user needs;

[0111] S73. Regularly apply the updated model parameters to the system operation, and monitor and collect the new round of user feedback data to form a feedback closed loop to ensure that the system can continuously optimize and improve performance;

[0112] S74. Save the adjusted model parameters and optimization strategies to the parameter storage module to ensure that they can be quickly restored to the optimal state during system updates and maintenance.

[0113] Furthermore, the S71 specifically includes:

[0114]

[0115] Among them, S represents the user satisfaction score, T represents the system response time, F represents the number of new questions raised by users, U represents the number of opinions and suggestions provided by users, and α, β, γ, and δ represent weight coefficients.

[0116] The beneficial effects of the present invention are:

[0117] Through the coal mine production management knowledge question-and-answer method based on natural language processing of the present invention, we have achieved significant beneficial effects in many aspects. First, we use sensor technology and log analysis technology to collect and analyze environmental data and user behavior data at the coal mine production site, build a data set, and ensure the comprehensiveness and accuracy of the data. Combined with edge computing technology, real-time analysis and processing are performed through the data processing algorithm of variational autoencoders and generative adversarial networks, which significantly improves the efficiency and real-time performance of data processing and reduces system response time.

[0118] In terms of user portrait and behavior analysis, the use of density-based spatial clustering algorithms and association rule analysis technology can more accurately capture user behavior patterns and preferences, combine environmental data with user portraits, and provide more personalized and relevant services. By building a knowledge graph and combining natural language processing and information extraction technology, the systematization and structured representation of knowledge is achieved. The combination of graph convolutional networks and improved Transformer models enhances the accuracy and efficiency of knowledge reasoning. The combination of logistic regression and XGBoost algorithms for reasoning further improves the intelligence level of the system.

[0119] In terms of environmental state prediction, an environmental simulation model is constructed through historical data analysis, and a time series prediction algorithm combining a hybrid density network and a long short-term memory network is used to more accurately predict complex environmental state changes, providing forward-looking information support for the system. The user portrait, knowledge graph and environmental state prediction are combined to generate personalized natural language answers, making answer generation more intelligent and flexible, and able to meet the diverse needs of users.

[0120] By collecting user feedback data and using adaptive learning algorithms for analysis and optimization, the system can continuously adjust and improve based on user feedback, forming a feedback loop, improving the system's self-optimization capabilities and user satisfaction. In terms of emergency plan generation and optimization, combined with knowledge graphs and environmental simulation results, rule-based emergency plans are automatically generated to ensure the timeliness and effectiveness of emergency response. Through historical data analysis, the plan template is continuously optimized to improve the applicability and accuracy of the emergency plan. BRIEF DESCRIPTION OF THE DRAWINGS

[0121] 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:

[0122] Figure 1 A flow chart of a coal mine production management knowledge question-answering method based on natural language processing proposed by the present invention;

[0123] Figure 2 A flowchart of constructing a user portrait for a coal mine production management knowledge question-answering method based on natural language processing proposed by the present invention;

[0124] Figure 3 This is a flow chart of environmental status prediction for a coal mine production management knowledge question-answering method based on natural language processing proposed by the present invention. DETAILED DESCRIPTION

[0125] 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.

[0126] refer to Figure 1-3 , a coal mine production management knowledge question answering method based on natural language processing, comprising the following steps:

[0127] S1. Use sensor technology to collect environmental data from coal mine production sites, use log analysis technology to collect and analyze user behavior data, and build a data set;

[0128] S2. Deploy edge computing nodes on-site at coal mines, use a data processing algorithm combining variational autoencoders and generative adversarial networks to perform edge analysis, and process data sets in real time;

[0129] S3. Use density-based spatial clustering algorithms to build user portraits, analyze user behaviors and preferences through association rules, and combine environmental data from production sites with user portraits;

[0130] S4. Build a knowledge graph, extract knowledge through natural language processing and information extraction technology, use graph convolutional networks and improved Transformer to build a cognitive model, and combine logistic regression and XGBoost algorithms for reasoning;

[0131] S5. Build an environmental simulation model through historical data analysis, use edge computing and cloud computing to combine real-time data fusion, and use a time series prediction algorithm that combines a hybrid density network with a long short-term memory network to predict environmental status;

[0132] S6, Generate personalized natural language answers based on user portraits, knowledge graphs, and environmental state predictions;

[0133] S7. Collect user feedback data, analyze it through data analysis tools, and use adaptive learning algorithms to adjust model parameters and optimization strategies;

[0134] S8. Use relational databases to store emergency plan templates, apply rule engines combined with knowledge graphs to generate rule-based emergency plans, automatically generate emergency plans based on environmental simulation and prediction results, and continuously optimize emergency plan templates through historical data analysis.

[0135] In this implementation, S2 specifically includes:

[0136] S21. Use edge computing nodes to perform preliminary data cleaning and preprocessing, including noise filtering, missing value filling, and data standardization, to form a preprocessed data set X;

[0137] S22. Input the preprocessed data set X into the variational autoencoder model, extract features and reduce the dimension of the data through the variational autoencoder to generate latent variables Z:

[0138] Z=μ+σ⊙∈;

[0139] Among them, μ represents the mean, σ represents the variance, ∈~N(0,I), ⊙ represents element-by-element multiplication, and I represents the identity matrix;

[0140] S23, inputting the hidden variable Z into a generative adversarial network, where the generative adversarial network includes a generator G and a discriminator D;

[0141] The generator G generates new data samples G(Z) based on the hidden variable Z:

[0142] G(Z)=tanh(W g ·Z+b g );

[0143] Among them, W g represents the weight of the generator, b g represents the bias of the generator;

[0144] The discriminator D compares the generated data sample G(Z) with the real data set X, and uses the discriminator D to determine the authenticity of the sample:

[0145] D(G(Z))=f(W d ·G(Z)+b d );

[0146] Among them, W d represents the weight of the discriminator, b d represents the bias of the discriminator, and f represents the activation function;

[0147] S24. The variational autoencoder and the generative adversarial network are jointly trained through the back propagation algorithm to optimize the parameters of the generator and the discriminator so that the generated data samples gradually approach the real data distribution. The specific optimization objective function is:

[0148]

[0149] Among them, p data (x) represents the probability density function of the real data distribution, x represents the data point sampled from the real data distribution, and p z (z) represents the probability distribution of latent variables in the latent space, and z represents the latent variables sampled from the latent space;

[0150] S25. Process the real-time collected data through the trained variational autoencoder and generative adversarial network to generate high-quality processed data

[0151] In this implementation manner, the S25 specifically includes:

[0152]

[0153] Among them, α represents the weight of the attention mechanism, and Attention(D,G(Z)) represents the weighted fusion of attention to the data sample G(Z) and the real data.

[0154] In this implementation, S3 specifically includes:

[0155] S31, using density-based spatial clustering algorithm to generate the Cluster analysis of the data;

[0156] Set two parameters: radius parameter ∈ and minimum sample parameter MinPts;

[0157] For each data point p in the dataset i , calculate the number of neighborhood data points N(p i ):

[0158]

[0159] Among them, dist(p i ,p j ) represents the data point p i and data point p j The distance between

[0160] The data points are divided into core points, boundary points and noise points, where the core points meet the number of neighborhood data points N(p i ) is greater than or equal to MinPts, the boundary point satisfies the condition that the number of neighboring data points is less than MinPts but is within the neighborhood of the core point, and the noise point does not meet the conditions of both the core point and the boundary point;

[0161] Cluster the core points and the points in their neighborhood, classify the connected core points and the points directly reachable by density into the same category, and form a user behavior pattern cluster;

[0162] S32, performing association rule analysis on the clustering results;

[0163] Calculate frequent item sets and generate frequent item sets F through Apriori algorithm or FP-Growth algorithm. Frequent item sets F meet the support threshold Support(A):

[0164]

[0165] Among them, Count(A) represents the number of transactions containing item set A, and N represents the total number of transactions;

[0166] Generate association rules in the form of A→B, where A and B represent elements in the frequent item set and satisfy the confidence threshold Confidence(A→B):

[0167]

[0168] To evaluate the effectiveness of association rules, lift (A→B) is used to measure the relevance of the rules:

[0169]

[0170] S33. Decompose the environmental data into time series into trend component, seasonal component and residual component, expressed as:

[0171] y t =T t +S t +R t ;

[0172] Among them, y t represents time series data, Tt represents the trend component, S t represents the seasonal component, R t represents the residual component;

[0173] S34, use the moving average method to smooth the trend components and identify the long-term trend. The moving average formula is T t for:

[0174]

[0175] Where n represents the size of the moving window;

[0176] S35. Use fast Fourier transform to identify periodic changes in seasonal components. The Fourier transform formula is:

[0177]

[0178] Among them, X k represents the frequency domain signal, x t represents the time domain signal, and N represents the signal length;

[0179] S36. Combine the user behavior pattern and the time series characteristics of the environmental data to generate a user profile, which includes the user's operating habits, behavioral preferences, and reaction information to different environmental conditions.

[0180] In this implementation, S4 specifically includes:

[0181] S41. Processing coal mine production management documents by natural language processing technology, including word segmentation, part-of-speech tagging, and named entity recognition. The word segmentation and part-of-speech tagging use the SpaCy tool, and the named entity recognition uses the BERT model;

[0182] S42. Extract knowledge from the processed documents, including entities, attributes and relationships, and use information extraction technology to add the extracted knowledge to the knowledge graph to form a complete knowledge graph;

[0183] S43. Use graph convolutional networks to learn embedded representations of knowledge graphs and generate low-dimensional vector representations of each node. Let the graph be G, the node be v, and the neighbor node be N(v). Then the representation of node v is h v The calculation formula is:

[0184]

[0185] Among them, σ represents the activation function, W (l) represents the weight matrix of the lth layer, aggregate represents the aggregation function, represents the representation of node v at layer l, represents the representation of node u at layer l, represents the representation of node v at layer l+1;

[0186] S44. The embedding representation result of the graph convolutional network is input into the improved Transformer model for further processing. The improved Transformer model includes an adaptive multi-head attention mechanism and dynamic position encoding to generate a more contextually understood knowledge representation. The adaptive multi-head attention score α ij The calculation formula is:

[0187]

[0188] Where a represents the adaptive attention weight vector, || represents the vector connection operation, W represents the weight matrix, and h i represents the feature representation of node i, h j represents the feature representation of node j, and PE(i,j) represents the dynamic position encoding of nodes i and j:

[0189]

[0190] Among them, i and j represent the index of the node, d represents the position dimension, and D represents the total embedding dimension;

[0191] The improved Transformer model plays the following roles in the coal mine production management knowledge question answering system:

[0192] Enhanced contextual understanding capabilities: Through the adaptive multi-head attention mechanism, the improved Transformer can more effectively capture the relationship between different parts of the input data, especially for complex knowledge graphs and long-distance dependencies. The improved Transformer can better understand and process contextual information.

[0193] Improve the flexibility of position encoding: Dynamic position encoding allows the model to adaptively adjust the position encoding according to the characteristics of the input data, thereby improving the adaptability of the model in different application scenarios. Compared with traditional fixed position encoding, dynamic position encoding can better handle the relationship and structural information between different nodes.

[0194] Optimize the effect of the attention mechanism: By improving the score calculation formula in the attention mechanism and introducing dynamic position encoding, the improved Transformer can more accurately calculate the attention weights between nodes, thereby improving the model's ability to identify key nodes and important information.

[0195] Improve the generalization ability of the model: The improved Transformer can better handle different types of input data by introducing adaptive multi-head attention and dynamic position encoding, enhance the generalization ability of the model, and perform better in dealing with diverse problems in coal mine production management.

[0196] The role of the improved Transformer in question-answering generation: When generating personalized natural language answers, the improved Transformer can use its enhanced context understanding ability and position encoding mechanism to generate more accurate and contextual answers, thereby improving the intelligence level of the question-answering system and user satisfaction.

[0197] S45. Classify the nodes in the knowledge graph through the logistic regression algorithm and predict the category of unknown nodes. The logistic regression prediction formula is:

[0198]

[0199] Where x represents the input feature, w represents the weight, b represents the bias, and P(y=1|x) represents the probability that the node belongs to category 1;

[0200] S46. Use the XGBoost algorithm to perform regression analysis on the nodes and relationships in the knowledge graph. XGBoost makes predictions by weighted averaging the results of multiple decision trees:

[0201]

[0202] Where K represents the number of trees, represents the predicted value of sample i, f k Represents the prediction result of the kth tree;

[0203] S47. Combine the results of logistic regression and XGBoost algorithms to generate the final inference results, improve the reasoning ability of the knowledge graph, and provide an accurate and comprehensive knowledge basis for the coal mine production management knowledge question and answer system.

[0204] In this implementation manner, S5 specifically includes:

[0205] S51, build a mixed density network;

[0206] S52. Build a long short-term memory network. The network structure includes an input layer, an LSTM layer, and an output layer. The input layer receives the parameters output by the MDN. The LSTM layer is used to capture the long-term and short-term dependencies in the time series. The output layer generates prediction results.

[0207] S53. Combine the mixed density network with the long short-term memory network to predict the environmental state. The prediction formula is:

[0208]

[0209] in, represents the predicted value at time point t, y t represents the parameter input generated by the mixed density network, h t-1 represents the hidden state at the previous time point, c t-1 indicates the cell state at the previous time point;

[0210] S54. The prediction results are stored in the cloud computing platform and provided to the knowledge question answering system through an interface for query and use.

[0211] In this implementation manner, the S51 specifically includes:

[0212] Input layer, hidden layer and output layer. The input layer receives the fused comprehensive data set, the hidden layer is implemented by a multi-layer perceptron, and the output layer generates the parameters of the mixed density model:

[0213]

[0214] Among them, y t represents the predicted value at time point t, π j represents the weight of the jth Gaussian distribution, N(μ j ,σ j ) represents the probability density function of Gaussian distribution, μ j represents the mean of the jth Gaussian distribution, σ j Represents the standard value of the j-th Gaussian distribution.

[0215] In this implementation manner, the S52 specifically includes:

[0216] i t =σ(W i ·[h t-1 ,x t ]+b i );

[0217] f t =σ(W f ·[h t-1 ,x t ]+b f );

[0218] o t =σ(W o ·[h t-1 ,x t ]+b o );

[0219] g t =tanh(W g ·[h t-1 ,xt ]+b g );

[0220] c t =f t ⊙c t-1 +i t ⊙g t ;

[0221] h t =o t ⊙tanh(c t );

[0222] Among them, i t represents the activation vector of the input gate, σ represents the activation function, W i , W f , W o and W g represents the weight matrix input to each gate and candidate memory state, b i , b f , b o and b g represents the bias term input to each gate and candidate memory state, h t-1 represents the hidden state at the previous time point, x t represents the input data at the current time point, f t represents the activation vector of the forget gate, o t represents the activation vector of the output gate, g t represents the activation vector of the candidate memory state, c t represents the cell state at the current time point, c t-1 represents the cell state at the previous time point, ⊙ represents the element multiplication operation, h t Indicates the hidden state at the current time point.

[0223] In this implementation manner, the S7 specifically includes:

[0224] S71. In the adaptive learning module, construct a reward function R;

[0225] S72, based on the optimization result of the reward function R, using the adaptive learning algorithm to update the model parameters of the system, so that the system can gradually improve its ability to respond to user needs;

[0226] S73. Regularly apply the updated model parameters to the system operation, and monitor and collect the new round of user feedback data to form a feedback closed loop to ensure that the system can continuously optimize and improve performance;

[0227] S74. Save the adjusted model parameters and optimization strategies to the parameter storage module to ensure that they can be quickly restored to the optimal state during system updates and maintenance.

[0228] In this implementation manner, the S71 specifically includes:

[0229]

[0230] Among them, S represents the user satisfaction score, T represents the system response time, F represents the number of new questions raised by users, U represents the number of opinions and suggestions provided by users, and α, β, γ, and δ represent weight coefficients.

[0231] Embodiment 1:

[0232] In order to verify the feasibility of the present invention in implementation, the present invention is applied to a large coal mine production base. The base has a vast mining area and a complex underground environment. The mining area faces challenges of high temperature, high humidity and changes in toxic gas concentrations all year round. The traditional coal mine production management method mainly relies on manual monitoring and empirical judgment. This method has problems such as slow response speed and insufficient decision-making accuracy when facing emergencies and complex environmental changes, which greatly affects production efficiency and safety.

[0233] In order to improve the intelligent level of coal mine production management, we introduced a coal mine production management knowledge question-and-answer system based on natural language processing in the mine area. The system collects environmental data of the mine area in real time through sensor technology, including temperature, humidity, equipment status, and gas concentration. At the same time, the system uses log analysis technology to collect and analyze the behavior data of miners and build a complete data set. These data are transmitted to the edge computing nodes deployed in the mine area, and are processed and analyzed in real time by variational autoencoders and generative adversarial networks (GANs).

[0234] Through a density-based spatial clustering algorithm, the system builds detailed user portraits and analyzes the behavior patterns and preferences of miners. Combining these user behavior data with mining environment data, the system can better understand the miners' operating habits and the impact of environmental conditions on their behavior. Then, the system extracts knowledge from a large number of coal mine production management documents through natural language processing and information extraction technology to build a knowledge graph. Graph convolutional networks (GCNs) and improved Transformer models are used to reason about the knowledge graph to provide accurate answers and decision support.

[0235] Through historical data analysis, the system builds an environmental simulation model and uses a time series prediction algorithm that combines a mixed density network (MDN) and a long short-term memory network (LSTM) to make real-time predictions of the environmental status of the mining area. For example, the system can predict changes in temperature and humidity in the mining area within the next 24 hours, as well as possible fluctuations in toxic gas concentrations. Based on these prediction results, the system generates personalized natural language answers to help managers make decisions in advance.

[0236] In addition, the system continuously adjusts and optimizes model parameters by collecting feedback data from miners. For example, when miners are not satisfied with the answers provided by the system, the system records these feedbacks and adjusts the model through adaptive learning algorithms. The system's optimization strategy is saved through the parameter storage module to ensure that the system remains efficient and intelligent in continuous improvement.

[0237] Table 1. Related data of coal mine production management knowledge question and answer system

[0238]

[0239]

[0240] First, in terms of response speed, after the system was launched, the response time of mine managers was reduced from an average of 15 minutes to 5 minutes. This significant improvement is attributed to the application of edge computing and advanced data processing algorithms, which greatly improves the efficiency of data processing and decision support.

[0241] In terms of environmental prediction accuracy, the system's prediction accuracy for the environmental status of the mining area reached 92%. For example, the system successfully predicted a sudden increase in toxic gas concentration and issued an early warning 4 hours in advance, avoiding a potential safety accident. Such high accuracy provides strong support for the safety management of the mining area.

[0242] In terms of user satisfaction, according to the feedback data from miners, the satisfaction score of the answers and suggestions provided by the system has increased from 70 points at the beginning of the launch to the current 85 points. Through the continuous adjustment and optimization of the model by the adaptive learning algorithm, the user experience has been significantly improved.

[0243] In terms of emergency plan generation time, the system generated an emergency plan in just 10 seconds during a sudden mine fire, guiding miners to evacuate quickly. Subsequent statistics showed that there were no casualties in the fire accident and economic losses were reduced by 30%. This shows that the system performed well in terms of emergency response speed and effectiveness.

[0244] In terms of production efficiency, after the system was put into operation, the overall production efficiency of the mine area increased by 15%. Through real-time monitoring of equipment status and predictive maintenance, the equipment failure rate decreased by 20%. This preventive maintenance measure effectively reduced equipment downtime and improved production efficiency.

[0245] In terms of safety, the incidence of coal mine accidents has been reduced by 40% since the system was put into operation. This achievement is mainly attributed to the system's efficient environmental monitoring and timely response to emergency plans, which provide a solid guarantee for the safety management of the mining area.

[0246] In summary, the coal mine production management knowledge question-answering system based on natural language processing has achieved remarkable results in improving response speed, improving environmental prediction accuracy, increasing user satisfaction, optimizing emergency plan effects, improving production efficiency and enhancing safety. These data fully demonstrate the practical value and innovation of the invention, and provide more efficient and safe support for coal mine production management.

[0247] 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 coal mine production management knowledge question-answering method based on natural language processing, characterized in that: The steps include: S1. Use sensor technology to collect environmental data from coal mine production sites, use log analysis technology to collect and analyze user behavior data, and build a data set; S2. Deploy edge computing nodes on-site at coal mines, use a data processing algorithm combining variational autoencoders and generative adversarial networks to perform edge analysis, and process data sets in real time; S3. Use density-based spatial clustering algorithms to build user profiles, analyze user behaviors and preferences through association rules, and combine environmental data from production sites with user profiles; S4. Build a knowledge graph, extract knowledge through natural language processing and information extraction technology, use graph convolutional networks and improved Transformer to build a cognitive model, and combine logistic regression and XGBoost algorithms for reasoning; S5. Build an environmental simulation model through historical data analysis, use edge computing and cloud computing to combine real-time data fusion, and use a time series prediction algorithm that combines a hybrid density network with a long short-term memory network to predict environmental status; S6, Generate personalized natural language answers based on user portraits, knowledge graphs, and environmental state predictions; S7. Collect user feedback data, analyze it through data analysis tools, and use adaptive learning algorithms to adjust model parameters and optimization strategies; S8. Use relational databases to store emergency plan templates, apply rule engines combined with knowledge graphs to generate rule-based emergency plans, automatically generate emergency plans based on environmental simulation and prediction results, and continuously optimize emergency plan templates through historical data analysis.

2. According to a coal mine production management knowledge question-answering method based on natural language processing according to claim 1, it is characterized in that: The S2 specifically includes: S21. Use edge computing nodes to perform preliminary data cleaning and preprocessing, including noise filtering, missing value filling, and data standardization, to form a preprocessed data set X; S22. Input the preprocessed data set X into the variational autoencoder model, extract features and reduce the dimension of the data through the variational autoencoder to generate latent variables Z: Z=μ+σ⊙∈; Among them, μ represents the mean, σ represents the variance, ∈~N(0,I), ⊙ represents element-by-element multiplication, and I represents the identity matrix; S23, inputting the hidden variable Z into a generative adversarial network, where the generative adversarial network includes a generator G and a discriminator D; The generator G generates new data samples G(Z) based on the hidden variable Z: G(Z)=tanh(W g ·Z+b g ); Among them, W g represents the weight of the generator, b g represents the bias of the generator; The discriminator D compares the generated data sample G(Z) with the real data set X, and uses the discriminator D to determine the authenticity of the sample: D(G(Z))=f(W d ·G(Z)+b d ); Among them, W d represents the weight of the discriminator, b d represents the bias of the discriminator, and f represents the activation function; S24. The variational autoencoder and the generative adversarial network are jointly trained through the back propagation algorithm to optimize the parameters of the generator and the discriminator. The specific optimization objective function is: Among them, p data (x) represents the probability density function of the real data distribution, x represents the data point sampled from the real data distribution, and p z (z) represents the probability distribution of latent variables in the latent space, and z represents the latent variables sampled from the latent space; S25. Process the real-time collected data through the trained variational autoencoder and generative adversarial network to generate high-quality processed data 3. The coal mine production management knowledge question and answer method based on natural language processing according to claim 2 is characterized in that: The S25 specifically includes: Among them, α represents the weight of the attention mechanism, and Attention(D,G(Z)) represents the weighted fusion of attention to the data sample G(Z) and the real data.

4. The coal mine production management knowledge question and answer method based on natural language processing according to claim 1 is characterized in that: The S3 specifically includes: S31, using density-based spatial clustering algorithm to generate the Cluster analysis of the data; Set two parameters: radius parameter ∈ and minimum sample parameter MinPts; For each data point p in the dataset i , calculate the number of neighborhood data points N(p i ): Among them, dist(p i ,p j ) represents the data point p i and data point p j The distance between The data points are divided into core points, boundary points and noise points, where the core points meet the number of neighborhood data points N(p i ) is greater than or equal to MinPts, the boundary point satisfies the condition that the number of neighboring data points is less than MinPts but is within the neighborhood of the core point, and the noise point does not meet the conditions of both the core point and the boundary point; Cluster the core points and the points in their neighborhood, classify the connected core points and the points directly reachable by density into the same category, and form a user behavior pattern cluster; S32, performing association rule analysis on the clustering results; Calculate frequent item sets and generate frequent item sets F through Apriori algorithm or FP-Growth algorithm. Frequent item sets F meet the support threshold Support(A): Where Count(A) represents the number of transactions containing item set A, and N represents the total number of transactions; Generate association rules in the form of A→B, where A and B represent elements in the frequent item set and satisfy the confidence threshold Confidence(A→B): To evaluate the effectiveness of association rules, lift (A→B) is used to measure the relevance of the rules: S33. Decompose the environmental data into time series into trend component, seasonal component and residual component, expressed as: y t =T t +S t +R t ; Among them, y t represents time series data, T t represents the trend component, S t represents the seasonal component, R t represents the residual component; S34, use the moving average method to smooth the trend components and identify the long-term trend. The moving average formula is T t for: Where n represents the size of the moving window; S35. Use fast Fourier transform to identify periodic changes in seasonal components. The Fourier transform formula is: Among them, X k represents the frequency domain signal, x t represents the time domain signal, and N represents the signal length; S36. Combine the user behavior pattern and the time series characteristics of the environmental data to generate a user portrait, which includes the user's operating habits, behavioral preferences and reaction information to different environmental conditions.

5. The coal mine production management knowledge question and answer method based on natural language processing according to claim 1 is characterized in that: The S4 specifically includes: S41. Processing coal mine production management documents by natural language processing technology, including word segmentation, part-of-speech tagging, and named entity recognition. The word segmentation and part-of-speech tagging use the SpaCy tool, and the named entity recognition uses the BERT model; S42. Extract knowledge from the processed documents, including entities, attributes and relationships, and use information extraction technology to add the extracted knowledge to the knowledge graph to form a complete knowledge graph; S43. Use graph convolutional networks to learn embedded representations of knowledge graphs and generate low-dimensional vector representations of each node. Let the graph be G, the node be v, and the neighbor node be N(v). Then the representation of node v is h v The calculation formula is: Among them, σ represents the activation function, W (l) represents the weight matrix of the lth layer, aggregate represents the aggregation function, represents the representation of node v at layer l, represents the representation of node u at layer l, represents the representation of node v at layer l+1; S44. Input the embedding representation result of the graph convolutional network into the improved Transformer model for further processing. The improved Transformer model includes an adaptive multi-head attention mechanism and dynamic position encoding. The adaptive multi-head attention score α ij The calculation formula is: Where a represents the adaptive attention weight vector, || represents the vector connection operation, W represents the weight matrix, and h i represents the feature representation of node i, h j represents the feature representation of node j, and PE(i,j) represents the dynamic position encoding of nodes i and j: Among them, i and j represent the index of the node, d represents the position dimension, and D represents the total embedding dimension; S45. Classify the nodes in the knowledge graph through the logistic regression algorithm and predict the category of unknown nodes. The logistic regression prediction formula is: Where x represents the input feature, w represents the weight, b represents the bias, and P(y=1|x) represents the probability that the node belongs to category 1; S46. Use the XGBoost algorithm to perform regression analysis on the nodes and relationships in the knowledge graph. XGBoost makes predictions by weighted averaging the results of multiple decision trees: Where K represents the number of trees. represents the predicted value of sample i, f k Represents the prediction result of the kth tree; S47. Combine the results of the logistic regression and XGBoost algorithms to generate the final inference result.

6. The coal mine production management knowledge question and answer method based on natural language processing according to claim 1 is characterized in that: The S5 specifically includes: S51, build a mixed density network; S52. Build a long short-term memory network. The network structure includes an input layer, an LSTM layer, and an output layer. The input layer receives the parameters output by the MDN. The LSTM layer is used to capture the long-term and short-term dependencies in the time series. The output layer generates prediction results. S53. Combine the mixed density network with the long short-term memory network to predict the environmental state. The prediction formula is: in, represents the predicted value at time point t, y t represents the parameter input generated by the mixed density network, h t-1 represents the hidden state at the previous time point, c t-1 indicates the cell state at the previous time point; S54. The prediction results are stored in the cloud computing platform and provided to the knowledge question answering system through an interface for query and use.

7. The coal mine production management knowledge question and answer method based on natural language processing according to claim 6 is characterized in that: The S51 specifically includes: Input layer, hidden layer and output layer. The input layer receives the fused comprehensive data set, the hidden layer is implemented by a multi-layer perceptron, and the output layer generates the parameters of the mixed density model: Among them, y t represents the predicted value at time point t, π j represents the weight of the jth Gaussian distribution, N(μ j ,σ j ) represents the probability density function of Gaussian distribution, μ j represents the mean of the jth Gaussian distribution, σ j Represents the standard value of the j-th Gaussian distribution.

8. The method for coal mine production management knowledge question and answer based on natural language processing according to claim 6 is characterized in that: The S52 specifically includes: i t =σ(W i ·[h t-1 ,x t ]+b i ); f t =σ(W f ·[h t-1 ,x t ]+b f ); the t =σ(W o ·[h t-1 ,x t ]+b o ); g t =tanh(W g ·[h t-1 ,x t ]+b g ); c t =f t ⊙c t-1 +i t ⊙g t ; h t =o t ⊙tanh(c t ); Among them, i t represents the activation vector of the input gate, σ represents the activation function, W i , W f , W o and W g represents the weight matrix input to each gate and candidate memory state, b i 、b f 、b o and b g represents the bias term input to each gate and candidate memory state, h t-1 represents the hidden state at the previous time point, x t represents the input data at the current time point, f t represents the activation vector of the forget gate, o t represents the activation vector of the output gate, g t represents the activation vector of the candidate memory state, c t represents the cell state at the current time point, c t-1 represents the cell state at the previous time point, ⊙ represents the element multiplication operation, h t Indicates the hidden state at the current time point.

9. The coal mine production management knowledge question and answer method based on natural language processing according to claim 1 is characterized in that: The S7 specifically includes: S71. In the adaptive learning module, construct a reward function R; S72, based on the optimization result of the reward function R, using an adaptive learning algorithm to update the model parameters of the system; S73. Regularly apply the updated model parameters to the system operation, and monitor and collect a new round of user feedback data to form a feedback closed loop; S74. Save the adjusted model parameters and optimization strategies into a parameter storage module.

10. The coal mine production management knowledge question and answer method based on natural language processing according to claim 9, characterized in that: The S71 specifically includes: Among them, S represents the user satisfaction score, T represents the system response time, F represents the number of new questions raised by users, U represents the number of opinions and suggestions provided by users, and α, β, γ, and δ represent weight coefficients.

Images