A method for quickly constructing a railway bridge design standard knowledge graph

Abstract

The application discloses a kind of railway bridge design standard knowledge graph fast construction method, comprising: S1, data is collected and preprocessed;S2, the BERT pre-training model and Bi-LSTM model are used to the processed data Chinese text sequence conversion labeled label sequence {y1,y2…y n};S3, using conditional random field CRF and graph neural network GNN technology, identify and label entity, attribute and its relationship, form the node and edge of knowledge graph, obtain complete knowledge graph KG;S4, using dynamic topology optimization algorithm real-time adjustment the complete knowledge graph KG structure.The method quickly integrates and optimizes design standard data, reduces data redundancy and effectively processes the addition and change of data, so as to improve the construction speed and maintenance efficiency of knowledge graph.

Description

Technical Field

[0001] The present invention belongs to the field of engineering design information management, and specifically relates to a method for quickly constructing a railway bridge design standard knowledge graph. Background Art

[0002] With the continuous development of modern railway engineering, railway bridge design standards and specifications have become increasingly complex. These design standards involve a wide range of technical requirements and regulatory documents, encompassing design parameters, structural requirements, material properties, and construction techniques. Because these design standards are derived from a variety of specifications and technical documents, and their data formats and sources vary, data integration and management in the railway bridge design field present significant challenges. While current knowledge graph construction methods can handle complex data to a certain extent, they still have many shortcomings in rapidly constructing and maintaining knowledge graphs for railway bridge design standards.

[0003] Traditional knowledge graph construction methods typically require extensive manual intervention to process and integrate data, making the knowledge graph construction and update process inefficient and difficult to adapt to rapidly changing design standards. Secondly, existing knowledge graph construction methods often contain duplicate records of standards and specifications, as well as redundant information. This not only increases the complexity of data management but also affects the efficiency of knowledge graph queries. Furthermore, the constant updating of railway bridge design standards poses challenges to knowledge graphs in handling new additions and changes to data. Existing knowledge graph construction methods often require the reconstruction of the knowledge graph or complex adjustments, making it difficult to efficiently respond to changes in new standards.

[0004] Therefore, there is an urgent need for an efficient method to quickly construct a knowledge graph of railway bridge design standards to solve the problems existing in existing technologies. Summary of the Invention

[0005] To address the aforementioned issues in the existing technology, the present invention provides a method for rapidly constructing a railway bridge design standards knowledge graph. This method rapidly integrates and optimizes design standards data, reduces data redundancy, and effectively handles data additions and changes, thereby improving the speed of knowledge graph construction and maintenance efficiency.

[0006] The technical solutions of the present invention are as follows:

[0007] A method for rapidly constructing a railway bridge design standard knowledge graph includes the following steps:

[0008] S1, data collection and preprocessing: Collect data from standard documents related to railway bridge design; remove redundant data and noise data from the collected data through data cleaning technology to obtain processed data, where:

[0009] The processed data includes multiple text sequences, the first text sequence S={w1,w2,…,w n},w i is the i-th word in the corresponding text sequence S, i = 1, 2, 3…n;

[0010] S2, using the BERT pre-trained model and the Bi-LSTM model to convert the text sequence S into structured data with high information density, including:

[0011] S2-1, extract embedding vector: use the BERT pre-training model to embed the text sequence S, and obtain the embedding vector X of the text sequence S = {x1, x2, ..., x n};in, is the i-th word w in the text sequence S i word vectors; is the word embedding vector used to represent word w i The basic semantic information is obtained from the word embedding matrix W in the BERT pre-training model s generate; is the sentence embedding vector used to represent word w i The role of the text sequence S, generated by the multi-layer Transformer encoder in the BERT pre-trained model; is the position embedding vector used to represent word w i The position in the text sequence S is embedded in the position matrix W in the BERT pre-trained model p generate;

[0012] S2-2, extract the context features corresponding to each word in the text sequence S according to the embedding vector X:

[0013] S2-2-1, traverse the embedding vector X={x1,x2,…,x n}, taking the word vector of each word as the input of the mapping function, the initial context features corresponding to each word in the text sequence S are calculated, and the initial context feature set H = {h0(w1),h0(w2),…,h0(w n )};

[0014] Among them, calculate the i-th word w in the text sequence S i The initial context feature h0(w i ) is calculated as follows:

[0015] h0(w i )=f(x i )

[0016] Where f is the mapping function used to process word w i The embedding vector xi , i∈[1,n];

[0017] S2-2-2, traverse the initial context feature set H = {h0(w1),h0(w2),…,h0(w n )}, the initial context features of each word in the set H are input into the pre-trained BERT model respectively, and the N-layer Transformer encoder of the BERT model outputs the context features of each word and forms the context feature set H of each word S ={h N (w1),h N (w2),…,h N (w n )};

[0018] S2-3, extract the final context features based on the Bi-LSTM model:

[0019] Traverse the set H S ={h N (w1),h N (w2),…,h N (w n )}, set H S Each context feature in is used as the input of the Bi-LSTM model to capture the bidirectional context dependency in the text sequence S, obtain the final context feature corresponding to each word in the text sequence S, and form the final context feature sequence C S ={c1,c2,…,c n};

[0020] S2-4, calculate the final context feature sequence C S The average of the vector s g , s g is the overall semantic feature of the text sequence S: s g =avg{c1,c2,…,c n},in, 2×d he is the mean vector s g Dimensions;

[0021] S2-5, construct the relationship set R:

[0022] In the process of processing text sequences with the pre-trained BERT model, entities are identified from the text sequences, and the semantic relationships between different entities are inferred based on the contextual information between them. The semantic relationships are embedded into the relationship vector space to obtain the relationship vector, and then added to the relationship set R to obtain the relationship set R = {r1, r2, ..., r k ,…r t}, where t is the total number of relationship vectors in the relationship set R, and the relationship vector r k Represents a specific relationship type or semantic connection in the text sequence S, represents the spatial dimension, d r is the dimension;

[0023] S2-6, according to the final context feature sequence C S and the mean vector s g , the attention mechanism is used to calculate the relationship vector r of each word in the text sequence S through linear mapping and nonlinear transformation k The attention alignment scores under , and form the attention alignment score set {e 1k ,e 2k ,…,e nk}, attention alignment score e ik Used to measure the final context feature c i In the relationship vector r k The weight under

[0024] S2-7, use the Softmax function to adjust the attention alignment score set {e 1k ,e 2k ,…,e nk} to normalize and get the relationship r of each word in the current target k The attention weights under , and form the attention weight set {α 1k ,α 2k ,…,α nk};

[0025] S2-8, through the attention weight set {α 1k ,α 2k ,…,α nk}For the final context feature sequence C S ={c1,c2,…,c n} Perform weighted summation to obtain the relationship vector r k The feature vector s of the text sequence S is k :

[0026]

[0027] Among them, the text sequence S is in the relation vector r k The specific semantic information under will be integrated into the feature vector s k middle, n is the total number of words in the text sequence S, and d is the feature dimension of each word;

[0028] S2-9, the eigenvector s k Input to the relation gating unit, the relation gating unit is based on the feature vector sk And the activation function is used to calculate the gating vector G; the gating vector G is used to control the feature vector s k Filter and obtain the filtered feature vector Among them, the gate vector G filters out the relationship vector r k Irrelevant feature information is retained while the most beneficial features for entity annotation are retained. The activation function is Sigmoid.

[0029] S2-10, the filtered feature vector Each element in is input into the hidden layer of the Bi-LSTM network, and the filtered feature vector is output The hidden state corresponding to each element in the text sequence, that is, the hidden state corresponding to each word in the text sequence, is obtained as a hidden state set.

[0030] S2-11, the hidden state set Each hidden state in the text is input into the entity annotation layer of the Bi-LSTM network, and the entity annotation layer outputs the labels of all words in the text sequence S, and forms a label sequence {y1,y2…y n};

[0031] S2-12, according to the label sequence {y1,y2…y n}, determine the text sequence S and the relationship vector r k Related head entities and tail entities, and label the sequence {y1,y2…y according to the determined head entity and tail entity n} for annotation, where the method for identifying the head entity and the tail entity is:

[0032] When identifying the head entity, we start from the label sequence {y1,y2…y n} find the first B-Head position as the starting position of the head entity, and end when encountering the non-entity O or the starting position B-Tail of the tail entity. This process includes the subsequent I-Head; when identifying the tail entity, start from the label sequence {y1, y2…y n} find the position of the first B-Tail as the starting position of the tail entity until a non-entity O or B-Head is encountered, which includes the subsequent I-Tail;

[0033] S3 uses conditional random fields (CRFs) and graph neural networks (GNNs) to identify and label entities, attributes, and their relationships in the design standards, forming nodes and edges of the knowledge graph to build a detailed knowledge graph. The specific steps are as follows:

[0034] S3-1, according to the label sequence {y1,y2…y n}, add all identified head entities and tail entities to the entity set, which includes all entities with relationship vector r k Related entities;

[0035] S3-2, traverse the relation set R = {r1, r2, ..., r k ,…r t}, each time a relation vector in the relation set R is selected, and S2-6 to S3-1 are repeated to obtain the entity set E={E1, E2,…, E u}, E i is an entity, and u is the total number of entities;

[0036] S3-3, analyze the attributes of each entity in the entity set E, obtain the attribute set of each entity, traverse the entity set E, and obtain the attribute set A of all entities = A1, A2, ..., A u , where A i For entity E i The attribute set A i =a1,a2,…,a m ;

[0037] Among them, get entity E i The attribute set A i =a1,a2,…,a m The method is:

[0038] (1) Extract entity E from text sequence S i The two words before and after each constitute the context word set N i , where the context word set N i ={w i-2 ,w i-1 ,E i ,w i+1 ,w i+2}, where w i-2 ,w i-1 ,w i+1 ,w 1+2 Represents entity E respectively i Two words before and after;

[0039] (2) Use the conditional random field CRF model to calculate the context word set N i Lower entity E i The attribute set A i The conditional probability distribution of , and then generate the entity E i The attribute set A i =a1,a2,…,a m , attribute set A ieach attribute in A i is a specific feature of entity E i , where the conditional random field model is as follows:

[0040]

[0041] where Z(N i ) is a normalization factor for making the sum of probabilities of all attributes equal to 1, ψ m (A i ,N i ) is a feature function for capturing the mutual relationship between context N i and attribute set A i , represents the product of all feature functions;

[0042] S3-4, according to entity set E = {E1, E2, …, E u} and attribute set A = A1, A2, …, A u , a node set N = {E1, E2, …, E u , A1, A2, …, A u} of a knowledge graph is formed;

[0043] S3-5, traversing the node set N, adding feature information to each node of the knowledge graph, using the vectorization technology Word2Vec to convert each node in the node set N into a vector, obtaining a vector set V(N) for facilitating subsequent efficient storage and retrieval in a graph database;

[0044] where the vector set V(N) = {v(E1), v(E2), …, v(E u ), v(A1), v(A2), …, v(A u )}, v(E i ) and v(A i ) are respectively the representations of entity E i and attribute A i converted into vectors;

[0045] S3-6, according to the head entity and the tail entity in the entity set E = {E1, E2, …, E u}, an edge between nodes is constructed, the edge between nodes describes the relationship between entities and attributes and the relationship between entities, each relationship vector in the relationship set R = {r1, r2, …, r t} is taken as the representation of the edge, and each edge is vectorized to obtain a set V(R) = {v(r1), v(r2), …, v(r t )}, and the vector set V(N) and the set V(R) form a complete knowledge graph KG = (V(N), V(R));

[0046] S3-7, execute S2 to S3-6 on all text sequences in the processed data described in S1 to obtain a complete knowledge graph KG;

[0047] S4, using a dynamic topology optimization algorithm to adjust the complete knowledge graph KG structure in real time, the specific steps are as follows:

[0048] S4-1, performing a preliminary analysis on the complete knowledge graph KG, evaluating the importance of each node in the complete knowledge graph KG by calculating the degree of each node, and calculating the weight of each edge based on the degree of the node, where the edge weight reflects the strength of the relationship between nodes;

[0049] Among them, get node E i degree d i The calculation formula is as follows:

[0050]

[0051] Where A i,j is an element in the adjacency matrix, A i,j Represents node E i and node E j The connection between

[0052] Among them, get node E i →E j The edge weight w ij The calculation formula is as follows:

[0053]

[0054] Weight w ij Reflects node E i and node E j The strength of the relationship between i ,d j ) is the weight calculation function;

[0055] S4-2: Based on the degree of each node and the weight of each edge in the complete knowledge graph KG, a dynamic topology adjustment strategy is formulated to optimize the structure of the knowledge graph:

[0056] The nodes with the same or similar attributes in the complete knowledge graph KG have a degree less than d minThe nodes of the complete knowledge graph KG are regarded as redundant nodes, and the redundant nodes in the complete knowledge graph KG are merged, the redundant nodes are deleted, and the connection relationship of the redundant nodes is transferred to the nodes with higher degrees to obtain the entity set E′; according to the calculation formula of the node degree, the degree of the nodes in the complete knowledge graph KG at this time is calculated, and the nodes with zero degree are regarded as isolated nodes to obtain the isolated node set I, and the isolated nodes are removed from the knowledge graph according to the isolated node set I;

[0057] S4-3, according to the weight of the edge in the complete knowledge graph KG, optimize the edge, traverse the set of all edges in the complete knowledge graph KG V(R) = {v(r1), v(r2), ..., v(r k )}, delete the edges with weights less than or equal to the threshold in the complete knowledge graph KG. If the deleted edges disconnect some nodes in the complete knowledge graph KG and the degrees of these nodes become zero, these nodes will be regarded as isolated nodes and deleted. After the edge deletion operation in the complete knowledge graph KG, the connection relationship between the remaining nodes will change, and S4 will be re-executed to optimize the knowledge graph KG.

[0058] In S1, the standard documents related to railway bridge design include structural design specifications, material standards, construction specifications, inspection and maintenance standards, and environmental and sustainability standards. Data cleaning techniques include deleting duplicate records, processing missing values, correcting erroneous information, and standardizing data formats.

[0059] In S2-2-2, get the i-th word w in the text sequence S i The context feature h N (w i ) is as follows: the initial context feature h0(w i ) is input into the first layer of the N-layer Transformer encoder. Each layer of Transformer encoder performs self-attention calculation and nonlinear transformation on the output of the previous layer of Transformer encoder to obtain the contextual features output by the current layer of Transformer encoder. The contextual features output by the N-th layer of Transformer encoder are recorded as the following features h N (w i ); Among them, the context feature output by the l-th layer Transformer encoder is h l (w i ):

[0060] h l (w i )=Trans(h l-1 (w i )),l∈[1,N]

[0061] Where Trans() represents the Transformer encoding operation, including self-attention calculation and nonlinear transformation, which is used to update the context features; h l-1 (w i ) is the context feature output by the l-1th layer Transformer encoder.

[0062] In S2-3, the Bi-LSTM model extracts word w i The corresponding final context feature c i The method is: h N (w i ) is the input of the Bi-LSTM model, and h is calculated respectively through the forward LSTM and backward LSTM of the Bi-LSTM model. N (w i ) is context-dependent at the position in the text sequence S, and the hidden state of the forward LSTM output is obtained and the hidden state of the backward LSTM output Will and Perform splicing and output word w i The corresponding final context feature c i , the calculation formula is:

[0063]

[0064] Where i∈[1,n], the final context feature is a two-dimensional real matrix, is the set of all real numbers, 2×d he is the final context feature c i dimension.

[0065] In S2-6, obtain the attention alignment score e ik The method is:

[0066] e ik =v T tanh(W r r k +W g s g +W h c i )

[0067] Where v is the attention vector; the linear mapping matrix W r Used to transform the relationship vector r k Mapping to attention space; W g Used to average the vector s g Mapping to attention space; W hUsed to convert the final context feature c i Mapping to the attention space.

[0068] In S2-7, get the word w in the text sequence S i The corresponding attention weight α ik The method is:

[0069]

[0070] Among them, the attention weight set {α 1k ,α 2k ,…,α nk}satisfy

[0071] S2-9 includes the following steps:

[0072] S2-9-1, obtain the gate vector G, the method is as follows:

[0073] G=σ(W g s k +b g )

[0074] Among them, W g is the weight matrix of the gating mechanism, the weight matrix W g Used to transform the feature vector s k Mapped to the gated space, b g is the bias term of the gating mechanism, bias term b g The offset used to control the gating mechanism, Weight matrix W g and the bias term b g Obtained by linear transformation through the gating mechanism; σ is the activation function Sigmoid, which is used to map the input value to the range of [0,1], and the gating vector G is used to determine the feature vector s k The passing degree of each element in The value of each element in the gate vector G is between [0, 1]. The closer it is to 1, the more important the element feature is, and the closer it is to 0, the smaller the contribution of the element feature is.

[0075] S2-9-2, through the gate vector G to the feature vector s k Filter, that is, multiply element by element to obtain the filtered feature vector

[0076]

[0077] in, Each element G in the gate vector G i Controls the eigenvector sk Each element s in ki The retention or suppression of G and s; ⊙ represents element-by-element multiplication. k Multiply the corresponding elements in the filter, and the eigenvector Contained in the relation vector r k Provide meaningful information.

[0078] In S2-10, get the word w in the text sequence S i The corresponding hidden state The method is:

[0079]

[0080] Where, Contains the word w i The relation vector r in the text sequence S k The following context information, is the hidden state space, hidden is the hidden state The length of is determined by the parameters of the hidden layer of the Bi-LSTM network.

[0081] In S2-11, get the i-th word w in the text sequence S i The label method is:

[0082] In the entity annotation layer, the Softmax function is used to transform the hidden state Converted to the probability distribution of each entity category [p1,p2,…,p q ], the calculation formula is as follows:

[0083]

[0084] Where q is the number of entity categories, For hidden state Perform linear transformation to obtain the original score of each entity category, and the softmax function converts the original score of each entity category into a probability distribution [p1, p2, ..., p q ], each element in the probability distribution is word w i is the probability of an entity category; W e is the weight matrix of the entity annotation layer; b e is the bias term;

[0085] The word w i The entity category corresponding to the maximum probability in the probability distribution is the word w i The label y of the entity category i , the calculation formula is as follows:

[0086] yi =argmax(p1,p2,…,p q )

[0087] In the formula, argmax(p1,p2,…,p q ) refers to the label of the entity category corresponding to the maximum output probability.

[0088] Preferably, in S4-2, d min =5; in S4-3, the threshold is 0.2.

[0089] The present invention has the following beneficial effects:

[0090] 1. This invention integrates railway bridge design data from various sources, including technical specifications, industry standards, and historical documents, to form a comprehensive knowledge graph. This graph construction method seamlessly integrates data from various sources, resulting in more comprehensive information coverage and richer relationships, thus ensuring the comprehensiveness of the knowledge graph.

[0091] 2. The present invention uses a dynamic topology optimization algorithm to adjust the structure of the knowledge graph, optimizes the layout of nodes and edges, effectively reduces data redundancy, improves the query efficiency of the graph, and improves the overall quality of data management.

[0092] 3. The present invention automatically identifies and deletes redundant nodes and duplicate information through topology optimization, selectively retains nodes with higher degrees, and ensures that the knowledge graph only contains information with practical significance and query value, thereby increasing the reliability of the data and ensuring the simplicity and readability of the graph; by automatically adjusting the weight and direction of the edges, the query path of the knowledge graph is more concise and efficient. BRIEF DESCRIPTION OF THE DRAWINGS

[0093] Figure 1 It is a schematic diagram of the process of the present invention;

[0094] Figure 2 Schematic diagram of the process of step S2 of the present invention;

[0095] Figure 3 Schematic diagram of the knowledge graph KG of the present invention. DETAILED DESCRIPTION

[0096] The construction method of the present invention is described in detail below with reference to the accompanying drawings and examples.

[0097] See also Figure 1-Figure 3 The present invention provides a method for rapidly constructing a railway bridge design standard knowledge graph, which specifically includes the following steps:

[0098] S1, data collection and preprocessing: collect data from standard documents related to railway bridge design; remove redundant data and noise data from the collected data through data cleaning technology to obtain processed data.

[0099] The processed data includes multiple text sequences, a text sequence S = {w1, w2, ..., w n},w i is the i-th word in the text sequence S, where i = 1, 2, 3…n. Data cleaning technology improves the quality of raw data and ensures its accuracy and consistency.

[0100] The standard documents related to railway bridge design include structural design specifications, material standards, construction specifications, inspection and maintenance standards, and environmental and sustainability standards. Data cleaning techniques include deleting duplicate records, processing missing values, correcting erroneous information, and standardizing data formats.

[0101] S2: Perform deep semantic analysis on the processed data using the BERT pre-trained model and the Bi-LSTM model to extract the key elements, technical parameters, and relationships of the text sequence S in the processed data (design standards), and convert the processed data into structured data with high information density. This includes the following steps:

[0102] S2-1, extracting embedding vectors: using the BERT pre-trained model to embed a text sequence S in the processed data, and obtain the embedding vector X of the text sequence S = {x1, x2, ..., x n};

[0103] in, is the i-th word w in the text sequence S i word vectors; is the word embedding vector used to represent word w i The basic semantic information is obtained from the word embedding matrix W in the BERT pre-training model s generate; is the sentence embedding vector used to represent word w i The role of the text sequence S, generated by the multi-layer Transformer encoder in the BERT pre-trained model; is the position embedding vector used to represent word w i The position in the text sequence S is embedded in the position matrix W in the BERT pre-trained model p generate;

[0104] S2-2, extract the context features corresponding to each word in the text sequence S according to the embedding vector X:

[0105] S2-2-1, traverse the embedding vector X={x1,x2,…,x n}, taking the word vector of each word as the input of the mapping function, the initial context features corresponding to each word in the text sequence S are calculated, and the initial context feature set H = {h0(w1),h0(w2),…,h0(w n )};

[0106] Among them, calculate the i-th word w in the text sequence S i The initial context feature h0(w i ) is calculated as follows:

[0107] h0(w i )=f(x i )

[0108] Where f is the mapping function used to process word w i The embedding vector x i , i∈[1,n].

[0109] S2-2-2, traverse the initial context feature set H = {h0(w1),h0(w2),…,h0(w n )}, the initial context features of each word in the set H are input into the pre-trained BERT model respectively, and the N-layer Transformer encoder of the BERT model outputs the context features of each word and forms the context feature set H of each word S ={h N (w1),h N (w2),…,h N (w n )}.

[0110] Get the i-th word w in the text sequence S i The context feature h N (w i ) is as follows: the initial context feature h0(w i ) is input into the first layer of the N-layer Transformer encoder. Each layer of Transformer encoder performs self-attention calculation and nonlinear transformation on the output of the previous layer of Transformer encoder to obtain the contextual features output by the current layer of Transformer encoder. The contextual features output by the N-th layer of Transformer encoder are recorded as the following features h N (w i ); Among them, the context feature output by the l-th layer Transformer encoder is h l (w i ):

[0111] hl (w i )=Trans(h l-1 (w i )),l∈[1,N]

[0112] Where Trans() represents the Transformer encoding operation, including self-attention calculation and nonlinear transformation, which is used to update the context features; h l-1 (w i ) is the context feature output by the l-1th layer Transformer encoder.

[0113] S2-3, extract the final context features based on the Bi-LSTM model:

[0114] Traverse the set H S ={h N (w1),h N (w2),…,h N (w n )}, set H S Each context feature in is used as the input of the Bi-LSTM model to capture the bidirectional context dependency in the text sequence S, obtain the final context feature corresponding to each word in the text sequence S, and form the final context feature sequence C S ={c1,c2,…,c n}.

[0115] Among them, the Bi-LSTM model extracts word w i The corresponding final context feature c i The method is: h N (w i ) is the input of the Bi-LSTM model, and h is calculated respectively through the forward LSTM and backward LSTM of the Bi-LSTM model. N (w i ) is context-dependent at the position in the text sequence S, and the hidden state of the forward LSTM output is obtained and the hidden state of the backward LSTM output Will and Perform splicing and output word w i The corresponding final context feature c i , the calculation formula is:

[0116]

[0117] Where i∈[1,n], the final context feature is a two-dimensional real matrix, is the set of all real numbers, 2×dhe is the final context feature c i dimension.

[0118] S2-4, calculate the final context feature sequence G S The average of the vector s g , s g is the overall semantic feature of the text sequence S: s g =avg{c1,c2,…,c n},in, 2×d he is the mean vector s g dimension.

[0119] S2-5, construct the relationship set R:

[0120] In the process of processing text sequences with the pre-trained BERT model, entities are identified from the text sequences, and the semantic relationships between different entities are inferred based on the contextual information between them. The semantic relationships are embedded into the relationship vector space to obtain the relationship vector, and then added to the relationship set R to obtain the relationship set R = {r1, r2, ..., r k ,…r t}, where t is the total number of relationship vectors in the relationship set R, and the relationship vector r k Represents a specific relationship type or semantic connection in the text sequence S, represents the spatial dimension, d r is the dimension.

[0121] The relationship set R will continue to expand as new relationship vectors are discovered. Whenever the pre-trained BERT model discovers an unidentified relationship vector when processing text, it will add this new relationship vector to the relationship set R, thereby maintaining the dynamic expansion of the knowledge graph.

[0122] S2-6, according to the final context feature sequence C s and the mean vector s g , the attention mechanism is used to calculate the relationship vector r of each word in the text sequence S through linear mapping and nonlinear transformation k The attention alignment scores under , and form the attention alignment score set {e 1k ,e 2k ,…,e nk}, attention alignment score e ik Used to measure the final context feature c i In the relationship vector r k The weight under which the attention alignment score e is obtained ik The method is:

[0123] eik =v T tanh(W r r k +W g s g +W h c i )

[0124] Where v is the attention vector, Linear mapping matrix W r Used to transform the relationship vector r k Mapped to the attention space, W g Used to average the vector s g Mapped to the attention space, W h Used to convert the final context feature c i Mapped to the attention space, is the spatial dimension of the attention vector v, d att is the dimension of the attention space, W g and W h The spatial dimension of ,2×d he is the mean vector s g The dimension of .

[0125] S2-7, use the Softmax function to adjust the attention alignment score set {e 1k ,e 2k ,…,e nk} to normalize and get the relationship r of each word in the current target k The attention weights under , and form the attention weight set {α 1k ,α 2k ,…,α nk};

[0126] Get word w in text sequence S i The corresponding attention weight α ik The method is:

[0127]

[0128] Among them, the attention weight set {α 1k ,α 2k ,…,α nk}satisfy

[0129] S2-8, through the attention weight set {α 1k ,α 2k ,…,α nk}For the final context feature sequence C S={c1,c2,…,c n} Perform weighted summation to obtain the relationship vector r k The feature vector s of the text sequence S is k :

[0130]

[0131] Among them, the text sequence S is in the relation vector r k The specific semantic information under will be integrated into the feature vector s k middle, n is the total number of words in the text sequence S, and d is the feature dimension of each word;

[0132] S2-9, the eigenvector s k Input to the relation gating unit, the relation gating unit is based on the feature vector s k And the activation function is used to calculate the gating vector G; the gating vector G is used to control the feature vector s k Filter and obtain the filtered feature vector Among them, the gate vector G filters out the relationship vector r k The activation function is Sigmoid. It includes the following steps:

[0133] S2-9-1, obtain the gate vector G, the method is as follows:

[0134] G=σ(W g s k +b g )

[0135] Among them, W g is the weight matrix of the gating mechanism, the weight matrix W g Used to transform the feature vector s k Mapped to the gated space, b g is the bias term of the gating mechanism, bias term b g The offset used to control the gating mechanism, Weight matrix W g and the bias term b g Obtained by linear transformation through the gating mechanism; σ is the activation function Sigmoid, which is used to map the input value to the range of [0,1], and the gating vector G is used to determine the feature vector s k The passing degree of each element in The value of each element in the gate vector G is between [0, 1]. The closer it is to 1, the higher the importance of the element feature is, and the closer it is to 0, the smaller the contribution of the element feature is.

[0136] S2-9-2, through the gate vector G to the feature vector s k Filter, that is, multiply element by element to obtain the filtered feature vector

[0137]

[0138] in, Each element G in the gate vector G i Controls the eigenvector s k Each element s in ki The retention or suppression of G and s; ⊙ represents element-by-element multiplication. k Multiply the corresponding elements in the filter, and the eigenvector Contained in the relation vector r k Provide meaningful information.

[0139] S2-10, the filtered feature vector Each element in is input into the hidden layer of the Bi-LSTM network, and the filtered feature vector is output The hidden state corresponding to each element in the text sequence, that is, the hidden state corresponding to each word in the text sequence, is obtained as a hidden state set.

[0140] Among them, get the word w in the text sequence S i The corresponding hidden state The method is:

[0141]

[0142] Where, Contains the word w i The relation vector r in the text sequence S k The following context information, is the hidden state space, hidden is the hidden state The length of is determined by the parameters of the hidden layer of the Bi-LSTM network.

[0143] S2-11, the hidden state set Each hidden state in the text is input into the entity annotation layer of the Bi-LSTM network, and the entity annotation layer outputs the labels of all words in the text sequence S, and forms a label sequence {y1,y2…y n}.

[0144] Among them, get the i-th word w in the text sequence S i The label method is:

[0145] In the entity annotation layer, the Softmax function is used to transform the hidden state Converted to the probability distribution of each entity category [p1,p2,…,p q ], the calculation formula is as follows:

[0146]

[0147] Where q is the number of entity categories, For hidden state Perform linear transformation to obtain the original score of each entity category, and the softmax function converts the original score of each entity category into a probability distribution [p1, p2, ..., p q ], each element in the probability distribution is word w i is the probability of an entity category; W e is the weight matrix of the entity annotation layer; b e is the bias term.

[0148] The word w i The entity category corresponding to the maximum probability in the probability distribution is the word w i The label y of the entity category i , the calculation formula is as follows:

[0149] y i =argmax(p1,p2,…,p q )

[0150] In the formula, argmax(p1,p2,…,p q ) refers to the label of the entity category corresponding to the maximum output probability.

[0151] S2-12, according to the label sequence {y1,y2…y n}, determine the text sequence S and the relationship vector r k Related head entities and tail entities, and label the sequence {y1,y2…y according to the determined head entity and tail entity n} for annotation, where the method for identifying the head entity and the tail entity is:

[0152] When identifying the head entity, we start from the label sequence {y1,y2…y n} find the first B-Head position as the starting position of the head entity, and continue until O (non-entity) or the starting position B-Tail of the tail entity is encountered. This process includes the subsequent I-Head (continuation of the head entity); when identifying the tail entity, start from the label sequence {y1, y2…y n} finds the position of the first B-Tail as the starting position of the tail entity until it encounters O (non-entity) or B-Head, and the process includes the subsequent I-Tail (continuation of the tail entity).

[0153] S3 uses conditional random fields (CRF) and graph neural network (GNN) technology to identify and annotate entities, attributes, and their relationships in the design standards, forming nodes and edges of the knowledge graph to build a detailed knowledge graph. The specific steps are as follows:

[0154] S3-1, according to the label sequence {y1,y2…y n}, add all identified head entities and tail entities to the entity set, which includes all entities with relationship vector r k Related entities.

[0155] S3-2, traverse the relation set R = {r1, r2, ..., r k ,…r t}, each time a relation vector in the relation set R is selected, and S2-6 to S3-1 are repeated to obtain the entity set E={E1, E2,…, E u}, E i is an entity, and u is the total number of entities.

[0156] S3-3, analyze the attributes of each entity in the entity set E, obtain the attribute set of each entity, traverse the entity set E, and obtain the attribute set A of all entities = A1, A2, ..., A u , where A i For entity E i The attribute set A i =a1,a2,…,a m .

[0157] Among them, get entity E i The attribute set A i =a1,a2,…,a m The method is:

[0158] (1) Extract entity E from text sequence S i The two words before and after each constitute the context word set N i , where the context word set N i ={w i-2 ,w i-1 ,E i ,w i+1 ,w i+2}, where w i-2 ,w i-1 ,w i+1 ,w i+2 Represents entity E respectively i Two words before and after;

[0159] (2) Use the Conditional Random Field (CRF) model to calculate the context word set N i Lower entity E i The attribute set A i The conditional probability distribution of , and then generate the entity E i The attribute set A i =a1,a2,…,a m , attribute set A i Each attribute in entity E i A specific feature of , where the conditional random field model formula is as follows:

[0160]

[0161] Among them, Z(N i ) is a normalization factor used to make the sum of the probabilities of all attributes equal to 1, ψ m (A i ,N i ) is a feature function used to capture the context N i With attribute set A i The mutual relationship between Indicates the multiplication of all characteristic functions.

[0162] S3-4, according to the entity set E={E1,E2,…,E u} and attribute set A=A1,A2,…,A u The node set N that forms the knowledge graph is {E1, E2,…, E u ,A1,A2,…,A u}.

[0163] S3-5 traverses the node set N and adds feature information (including node ID, type, and description) to each node in the knowledge graph to quickly locate and identify the node in knowledge graph queries. Using the vectorization technology Word2Vec, each node in the node set N is converted into a vector, resulting in a vector set V(N) for efficient storage and retrieval in the graph database.

[0164] Among them, the vector set V(N)={v(E1),v(E2),…,v(E u ),v(A1),v(A2),…,v(A u )},v(E i ) and v(A i ) are entities E i and attribute A i Convert to a vector representation.

[0165] S3-6, according to the entity set E={E1,E2,…,E u} constructs the edges between nodes. The edges between nodes describe the relationship between entities and attributes and the relationship between entities. The relationship set R = {r1, r2, ..., r t Each relation vector in} is used as the representation of the edge, and each edge is vectorized to obtain the set V(R)={v(r1),v(r2),…,v(r t )}, the vector set V(N) and the set V(R) form a complete knowledge graph KG = (V(N), V(R)).

[0166] S3-7, execute S2 to S3-6 on all text sequences in the processed data described in S1 to obtain a complete knowledge graph KG.

[0167] The construction of nodes in the complete knowledge graph KG ensures that all extracted information is included, while the construction of edges effectively connects this information, making the knowledge graph efficient and usable in query and reasoning.

[0168] S4: Use a dynamic topology optimization algorithm to adjust the complete knowledge graph KG structure in real time. The dynamic topology optimization algorithm optimizes the layout of nodes and edges, reduces data redundancy, and automatically handles the addition and modification of nodes in the complete knowledge graph KG, ensuring efficient query and maintenance of the knowledge graph. The specific steps are as follows:

[0169] S4-1, perform preliminary analysis on the complete knowledge graph KG, evaluate the importance of each node in the complete knowledge graph KG by calculating the number of connections (degree) of each node, and identify potential structural problems; calculate the weight of each edge according to the degree of the node, and the weight of the edge reflects the strength of the relationship between nodes. The lower the weight of the edge, the lower the association strength between nodes in the complete knowledge graph KG.

[0170] Among them, get node E i degree d i The calculation formula is as follows:

[0171]

[0172] Where A i,j is an element in the adjacency matrix, A i,j Represents node E i and node E j The connection between.

[0173] Among them, get node E i →E j The edge weight w ij The calculation formula is as follows:

[0174]

[0175] Weight w ij Reflects node E i and node E j The strength of the relationship between i ,d j ) is the weight calculation function.

[0176] S4-2: Based on the degree of each node and the weight of each edge in the complete knowledge graph KG, a dynamic topology adjustment strategy is formulated to optimize the structure of the knowledge graph:

[0177] The nodes with the same or similar attributes in the complete knowledge graph KG have a degree less than d min =5 as redundant nodes, merge the redundant nodes in the complete knowledge graph KG, delete the redundant nodes, and transfer the connection relationship of the redundant nodes to the nodes with higher degrees to obtain the entity set E′; according to the calculation formula of the node degree, calculate the degree of the nodes in the complete knowledge graph KG at this time, regard the nodes with zero degree as isolated nodes, and obtain the isolated node set I, remove the isolated nodes from the knowledge graph according to the isolated node set I, and reduce the complexity of the complete knowledge graph KG.

[0178] Among them, redundant nodes are nodes with the same or similar attributes in the knowledge graph. Redundant nodes are entities of the same type or have repeated information.

[0179] S4-3, according to the weight of the edge in the complete knowledge graph KG, optimize the edge, traverse the set of all edges in the complete knowledge graph KG V(R) = {v(r1), v(r2), ..., v(r k )}, edges with weights less than or equal to a threshold are deleted from the complete knowledge graph KG, where the threshold = 0.2. If the deleted edges disconnect certain nodes in the complete knowledge graph KG and the degrees of these nodes become zero, these nodes are treated as isolated nodes and deleted. After deleting the edges in the complete knowledge graph KG, the connection relationships between the remaining nodes will change, and S4 will be re-executed to optimize the knowledge graph KG. Among them, deleting low-weight edges and redundant nodes helps reduce noise and the complexity of the complete knowledge graph KG, thereby improving query efficiency.

[0180] The performance of the complete knowledge graph KG after optimization is verified by evaluating its query performance, data redundancy, and information aggregation:

[0181] Based on the benchmark query, the query response time of the complete knowledge graph KG is calculated to verify its query efficiency and maintenance cost, wherein the total time T to execute all benchmark queries is calculated. q The method is:

[0182]

[0183] Among them, t a is the response time of the ath query, h is the total number of queries, query performance: the response time of simple queries should be within 1 second, the response time of complex queries should not exceed 5 seconds, the query throughput should reach more than 1000 times / second, and the query response time should be stable with a standard deviation of less than 0.5 seconds.

[0184] The data redundancy of the complete knowledge graph KG: node redundancy and relationship redundancy are controlled below 5%, and attribute redundancy is less than 10%, thereby reducing storage waste and improving query efficiency.

[0185] The information aggregation degree of the complete knowledge graph KG: the average degree of each node reaches more than 10 times, the edge aggregation and information coverage are high, the clustering coefficient is close to 1, and the information of the complete knowledge graph KG is closely connected and effectively covered.

[0186] In summary, the complete knowledge graph KG meets the set quality standards and supports efficient query and maintenance operations.

Claims

1. A method for rapidly constructing a knowledge graph of railway bridge design standards, characterized in that: The following steps are involved: S1, data collection and preprocessing: Collect data from standard documents related to railway bridge design; remove redundant data and noise data from the collected data through data cleaning technology to obtain processed data, where: The processed data includes multiple text sequences, the first text sequence S={w1,w2,…,w n },w i is the i-th word in the corresponding text sequence S, i = 1, 2, 3…n; S2, using the BERT pre-trained model and the Bi-LSTM model to convert the text sequence S into structured data with high information density, including: S2-1, extract embedding vector: use the BERT pre-training model to embed the text sequence S, and obtain the embedding vector X of the text sequence S = {x1, x2, ..., x n }; where x i is the i-th word w in the text sequence S i word vectors; S2-2, extract the context features corresponding to each word in the text sequence S according to the embedding vector X: S2-2-1, traverse the embedding vector X={x1,x2,…,x n }, taking the word vector of each word as the input of the mapping function, the initial context features corresponding to each word in the text sequence S are calculated, and the initial context feature set H = {h0(w1),h0(w2),…,h0(w n )}; S2-2-2, traverse the initial context feature set H = {h0(w1),h0(w2),…,h0(w n )}, the initial context features of each word in the set H are input into the pre-trained BERT model respectively, and the N-layer Transformer encoder of the BERT model outputs the context features of each word and forms the context feature set H of each word S ={h N (w1),h N (w2),…,h N (w n )}; S2-3, extract the final context features based on the Bi-LSTM model: Traverse the set H S ={h N (w1),h N (w2),…,h N (w n )}, set H S Each context feature in is used as the input of the Bi-LSTM model to capture the bidirectional context dependency in the text sequence S, obtain the final context feature corresponding to each word in the text sequence S, and form the final context feature sequence C S ={c1,c2,…,c n }; S2-4, calculate the final context feature sequence C S The average of the vector s g , s g is the overall semantic feature of the text sequence S: s g =avg{c1,c2,…,c n }; S2-5, construct the relationship set R: In the process of processing text sequences with the pre-trained BERT model, entities are identified from the text sequences, and the semantic relationships between different entities are inferred based on the contextual information between them. The semantic relationships are embedded into the relationship vector space to obtain the relationship vector, and then added to the relationship set R to obtain the relationship set R = {r1, r2, ..., r k ,…r t }, where t is the total number of relationship vectors in the relationship set R, and the relationship vector r k Represents a specific relationship type or semantic connection in the text sequence S; S2-6, according to the final context feature sequence C S and the mean vector s g , the attention mechanism is used to calculate the relationship vector r of each word in the text sequence S through linear mapping and nonlinear transformation k The attention alignment scores under , and form the attention alignment score set {e 1k ,e 2k ,…,e nk }, attention alignment score e ik Used to measure the final context feature c i In the relationship vector r k The weight under S2-7, use the Softmax function to adjust the attention alignment score set {e 1k ,e 2k ,…,e nk } to normalize and get the relationship r of each word in the current target k The attention weights under , and form the attention weight set {α 1k ,α 2k ,…,α nk }; S2-8, through the attention weight set {α 1k ,α 2k ,…,α nk }For the final context feature sequence C S ={c1,c2,…,c n } Perform weighted summation to obtain the relationship vector r k The feature vector s of the text sequence S is k : Among them, the text sequence S is in the relation vector r k The specific semantic information under will be integrated into the feature vector s k In the equation, n is the total number of words in the text sequence S, and d is the feature dimension of each word; S2-9, the eigenvector s k Input to the relation gating unit, the relation gating unit is based on the feature vector s k And the activation function is used to calculate the gating vector G; the gating vector G is used to control the feature vector s k Filter and obtain the filtered feature vector Among them, the gate vector G filters out the relationship vector r k Irrelevant feature information is retained while the most beneficial features for entity annotation are retained. The activation function is Sigmoid. S2-10, the filtered feature vector Each element in is input into the hidden layer of the Bi-LSTM network, and the filtered feature vector is output The hidden state corresponding to each element in the text sequence, that is, the hidden state corresponding to each word in the text sequence, is obtained as a hidden state set. S2-11, the hidden state set Each hidden state in the text is input into the entity annotation layer of the Bi-LSTM network, and the entity annotation layer outputs the labels of all words in the text sequence S, and forms a label sequence {y1,y2…y n }; S2-12, according to the label sequence {y1,y2…y n }, determine the text sequence S and the relationship vector r k Related head entities and tail entities, and label the sequence {y1,y2…y according to the determined head entity and tail entity n } to mark; S3 uses conditional random fields (CRFs) and graph neural networks (GNNs) to identify and label entities, attributes, and their relationships in the design standards, forming nodes and edges of the knowledge graph to build a complete knowledge graph (KG). S4, using a dynamic topology optimization algorithm to adjust the complete knowledge graph KG structure in real time, the specific steps are as follows: S4-1, performing a preliminary analysis on the complete knowledge graph KG, evaluating the importance of each node in the complete knowledge graph KG by calculating the degree of each node, and calculating the weight of each edge based on the degree of the node, where the edge weight reflects the strength of the relationship between nodes; S4-2: Based on the degree of each node and the weight of each edge in the complete knowledge graph KG, a dynamic topology adjustment strategy is formulated to optimize the structure of the knowledge graph: The nodes with the same or similar attributes in the complete knowledge graph KG have a degree less than d min The nodes of the complete knowledge graph KG are regarded as redundant nodes, and the redundant nodes in the complete knowledge graph KG are merged, the redundant nodes are deleted, and the connection relationship of the redundant nodes is transferred to the nodes with higher degrees to obtain the entity set E′; according to the calculation formula of the node degree, the degree of the nodes in the complete knowledge graph KG at this time is calculated, and the nodes with zero degree are regarded as isolated nodes to obtain the isolated node set I, and the isolated nodes are removed from the knowledge graph according to the isolated node set I; S4-3, according to the weight of the edge in the complete knowledge graph KG, optimize the edge, traverse the set of all edges in the complete knowledge graph KG V(R) = {v(r1), v(r2), ..., v(r k )}, delete the edges with weights less than or equal to the threshold in the complete knowledge graph KG. If the deleted edges disconnect some nodes in the complete knowledge graph KG and the degrees of these nodes become zero, these nodes will be regarded as isolated nodes and deleted. After the edge deletion operation in the complete knowledge graph KG, the connection relationship between the remaining nodes will change, and S4 will be re-executed to optimize the knowledge graph KG.

2. The method for rapidly constructing a railway bridge design standard knowledge graph according to claim 1 is characterized by: In S1, the standard documents related to railway bridge design include structural design specifications, material standards, construction specifications, inspection and maintenance standards, and environmental and sustainability standards. Data cleaning techniques include deleting duplicate records, processing missing values, correcting erroneous information, and standardizing data formats.

3. The method for rapidly constructing a railway bridge design standard knowledge graph according to claim 1 is characterized by: In S2-2-2, get the i-th word w in the text sequence S i The context feature h N (w i ) is as follows: the initial context feature h0(w i ) is input into the first layer of the N-layer Transformer encoder. Each layer of Transformer encoder performs self-attention calculation and nonlinear transformation on the output of the previous layer of Transformer encoder to obtain the contextual features output by the current layer of Transformer encoder. The contextual features output by the N-th layer of Transformer encoder are recorded as the following features h N (w i ); Among them, the context feature output by the l-th layer Transformer encoder is h l (w i ): h l (w i )=Trans(h l-1 (w i )),l∈[1,N] Where Trans() represents the Transformer encoding operation, including self-attention calculation and nonlinear transformation, which is used to update the context features; h l-1 (w i ) is the context feature output by the l-1th layer Transformer encoder.

4. The method for rapidly constructing a railway bridge design standard knowledge graph according to claim 1 is characterized by: In S2-3, the Bi-LSTM model extracts word w i The corresponding final context feature c i The method is: h N (w i ) is the input of the Bi-LSTM model, and h is calculated respectively through the forward LSTM and backward LSTM of the Bi-LSTM model. N (w i ) is context-dependent at the position in the text sequence S, and the hidden state of the forward LSTM output is obtained and the hidden state of the backward LSTM output Will and Perform splicing and output word w i The corresponding final context feature c i , the calculation formula is: Where i∈[1,n], the final context feature is a two-dimensional real matrix, is the set of all real numbers, 2×d he is the final context feature c i dimension.

5. The method for rapidly constructing a railway bridge design standard knowledge graph according to claim 1 is characterized by: In S2-6, obtain the attention alignment score e ik The method is: e ik =v T tanh(W r r k +W g s g +W h c i ) Where v is the attention vector; the linear mapping matrix W r Used to transform the relationship vector r k Mapping to attention space; W g Used to average the vector s g Mapping to attention space; W h Used to convert the final context feature c i Mapping to the attention space.

6. The method for rapidly constructing a railway bridge design standard knowledge graph according to claim 1 is characterized by: In S2-7, get the word w in the text sequence S i The corresponding attention weight α ik The method is: Among them, the attention weight set {α 1k ,α 2k ,…,α nk }satisfy 7. A method for rapidly constructing a railway bridge design standard knowledge graph according to claim 1, characterized in that S2-9 includes the following steps: S2-9-1, obtain the gate vector G, the method is as follows: G=σ(W g s k +b g ) Among them, W g is the weight matrix of the gating mechanism, the weight matrix W g Used to transform the feature vector s k Mapped to the gated space, b g is the bias term of the gating mechanism, bias term b g The offset used to control the gating mechanism, Weight matrix W g and the bias term b g Obtained by linear transformation through the gating mechanism; σ is the activation function Sigmoid, which is used to map the input value to the range of [0,1], and the gating vector G is used to determine the feature vector s k The passing degree of each element in The value of each element in the gate vector G is between [0, 1]. The closer it is to 1, the more important the element feature is, and the closer it is to 0, the smaller the contribution of the element feature is. S2-9-2, through the gate vector G to the feature vector s k Filter, that is, multiply element by element to obtain the filtered feature vector in, Each element G in the gate vector G i Controls the eigenvector s k Each element s in ki The retention or suppression of G and s; ⊙ represents element-by-element multiplication. k Multiply the corresponding elements in the filter, and the eigenvector Contained in the relation vector r k Provide meaningful information.

8. The method for rapidly constructing a railway bridge design standard knowledge graph according to claim 1 is characterized by: In S2-10, get the word w in the text sequence S i The corresponding hidden state The method is: Where, Contains the word w i The relation vector r in the text sequence S k The following context information, is the hidden state space, hidden is the hidden state The length of is determined by the parameters of the hidden layer of the Bi-LSTM network.

9. The method for rapidly constructing a railway bridge design standard knowledge graph according to claim 1 is characterized by: In S2-11, get the i-th word w in the text sequence S i The label method is: In the entity annotation layer, the Softmax function is used to transform the hidden state Converted to the probability distribution of each entity category [p1,p2,…,p q ], the calculation formula is as follows: Where q is the number of entity categories, For hidden state Perform linear transformation to obtain the original score of each entity category, and the softmax function converts the original score of each entity category into a probability distribution [p1, p2, ..., p q ], each element in the probability distribution is word w i is the probability of an entity category; W e is the weight matrix of the entity annotation layer; b e is the bias term; The word w i The entity category corresponding to the maximum probability in the probability distribution is the word w i The label y of the entity category i , the calculation formula is as follows: y i =argmax(p1,p2,…,p q ) In the formula, argmax(p1,p2,…,p q ) refers to the label of the entity category corresponding to the maximum output probability.

10. The method for rapidly constructing a railway bridge design standard knowledge graph according to claim 1, characterized in that: In S4-2, d min =5; in S4-3, the threshold is 0.2.

Images