Knowledge graph completion method based on deep semantic and entity category information extraction

Abstract

The application relates to a knowledge graph completion method based on deep semantic and entity category information extraction, and belongs to the field of knowledge graph completion. The method proposes a DSET model of an end-to-end neural network, and outputs entities of missing positions of a predicted knowledge graph based on the DSET model; the DSET model comprises a type similarity graph attention encoder TS-GAT which focuses on modeling of entity type information, and a deep semantic information three-dimensional convolution decoder DS-Conv3 which is responsible for extracting deep semantic features of entities and relations. The method solves the problems of neglecting entity category information and insufficient deep semantic feature extraction in traditional knowledge graph completion methods.

Description

Technical Field

[0001] The present invention belongs to the field of knowledge graph completion, and specifically relates to a knowledge graph completion method based on deep semantics and entity category information extraction. Background Art

[0002] A knowledge graph (KG) is a structured knowledge representation designed to organize and manage information in a graph-like structure. It is directed and heterogeneous. The core components of a knowledge graph are entities and relationships, which form the basic structural units of a knowledge graph in the form of triples (subject, relationship, object), such as (Einstein, belongs to, scientist). This representation intuitively expresses the semantic relationship between entities, such as Einstein is a scientist. Through this structured data, knowledge graphs store a vast amount of world knowledge and support complex queries and reasoning.

[0003] Knowledge Graph Completion (KGC) involves using existing knowledge graph data to predict and fill in missing entities or relationships. This process is crucial for improving the quality and completeness of knowledge graphs, enabling them to better support a variety of applications. Existing knowledge graph completion models are primarily categorized into four main types: translation models, tensor decomposition models, convolutional neural network models, and graph neural network models.

[0004] 1. Translation model: The TransE[1] model assumes that each relation in the knowledge graph can be viewed as a linear transformation between the head entity vector and the tail entity vector. TransE encountered challenges in handling complex relations, while TransH[2] introduced the concept of relational hyperplane to improve this problem. TransR[3] further overcomes the limitation that entities and relations are in different semantic spaces, and each relation has an independent space for translation. TransD[4] develops the idea of ​​TransR, dynamically generates independent mapping matrices for each entity and relation, and enhances the flexibility of the model in handling complex relational data. RotatE[5] simulates symmetry, antisymmetry and transitivity through rotation in complex space; 2. Tensor decomposition model: The RESCAL[6] model represents entities as vectors and relations as matrices, and makes predictions through multiplication. DistMult[7] simplifies the relational representation of RESCAL, improves computational efficiency, and retains representation capabilities. ComplEx[8] introduces the embedding of complex domains to enhance the expression of symmetric and antisymmetric relations. SimplE[9] uses CP decomposition to introduce head and tail embeddings and two types of relationship embeddings, which improves prediction accuracy. Third, convolutional neural network model: ConvE

[10] uses a two-dimensional convolutional neural network to learn the embedding representation of entities and relationships, which improves the accuracy of link prediction. On the other hand, ConvKB

[11] directly applies a one-dimensional convolution operation on triple embeddings to learn complex interactive relationships. InteractE

[12] improves ConvE by introducing more complex feature interactions and embedding mechanisms. Fourth, graph neural network model: R-GCN

[13] introduces independent specific weights for each type of relationship, thereby effectively handling relationship diversity and improving model accuracy, and introduces a self-connection mechanism to enhance the understanding of entity self-attributes. SACN

[14] combines structured attention with graph convolutional networks to selectively aggregate information from neighboring nodes, significantly improving the accuracy of knowledge graph completion. KBGAT

[15] dynamically captures the importance of relationships through a graph attention network and assigns a unique attention weight to each connection. CompGCN

[16] incorporates entity and relation embeddings into the graph convolution process by combining them, and updates the relation embeddings at the same time, thus enhancing the expressiveness of the embeddings.

[0005] Knowledge graphs provide excellent support for many intelligent applications such as intelligent question answering

[17] , intelligent recommendation

[18] , and semantic parsing

[19] . Currently, many large-scale knowledge graphs have been developed, such as YAGO

[20] , WIKI

[21] , WordNet

[22] , Freebase

[23] , and ICEWS

[24] , but they still have the problem of incompleteness, which means that a large number of potential entities and relationships have not yet been discovered. Taking Freebase as an example, there is a large amount of missing information inside it

[25] . For example, in terms of "nationality", "education" and "parents", 75%, 91% and 94% of the person entities lack this information respectively. This incompleteness of the knowledge graph seriously limits the efficiency of downstream applications. Therefore, knowledge graph completion (KGC) has become a research hotspot in the current knowledge graph field. KGC aims to use existing data or knowledge to predict and complete the missing entities or relationships in the knowledge graph through inference or learning

[26] , thereby improving the completeness and utilization value of the knowledge graph.

[0006] Historically, research on knowledge graph completion has primarily focused on structured representation learning, attempting to mine and predict missing information in knowledge graphs by learning low-dimensional embeddings of entities and relationships. Recently emerging neural network models can be trained to learn deep features and mapping relationships in data, enabling a better understanding and processing of complex entity relationships. Graph neural network models, in particular, fully leverage the structural information of knowledge graphs, effectively integrating node and contextual information to capture the complex relationships between nodes.

[0007] In addition, in order to simultaneously complete the tail entity prediction and head entity prediction tasks of knowledge graph completion, most existing methods such as ConvE, InteractE, and CompGCN will create the inverse relationship of the relationship for the knowledge graph, that is, from the existing triples (e s ,r,e o ) generates the corresponding anti-relation triple (e o ,r',e s ) and add the generated triples to the training, validation, and test sets to accurately evaluate model performance. This workflow is based on a simple assumption: if a relationship holds in one direction, then its inverse relationship also holds in the reverse direction. This effectively increases the number of training samples and, to a certain extent, enhances the model's learning and expressive capabilities. However, existing models have the following limitations:

[0008] First, it ignores the category similarity between entities, that is, ignores entity category information. Entity category information plays a crucial role in knowledge graphs and is crucial for reasoning about missing entities. Taking the "born at" relationship in the real world as an example, a reasonable connection should be "person" and "place." If entity category information is ignored, the model may make incorrect predictions, such as mistakenly connecting a "person" and "born at" relationship to another "person." Based on the categories of the entities connected by the relationship, relationships in knowledge graphs can be divided into two types: equivalence relationships, where the categories of the head and tail entities in the relationship are the same, typical examples being "classmate" and "colleague." Non-equivalence relationships, where the categories of the head and tail entities in the relationship are different, such as relationships like "born at" and "nationality." In fact, equivalence relationships contain latent category information, and the head and tail entities can be considered to be of the same category. Aggregating the head and tail entity information connected by these equivalence relationships can effectively model and reveal entity category information in knowledge graphs. Current graph neural network models, such as R-GCN and CompGCN, also have a central entity aggregation process, but ignore the entity category information in the equivalence relation and do not include it in the scope of message passing. Therefore, it is impossible to explicitly model the entity category information.

[0009] 2. Insufficient extraction of deep semantic features. On the one hand, in the current traditional knowledge graph completion model, entities and relationships are represented by low-dimensional vectors. However, such methods make it difficult to capture and express the deep and complex semantics of entities and relationships. On the other hand, while the current neural network model improves the interaction between entity and relationship embeddings, it is unable to retain their respective local features, resulting in the loss of deep semantics. For example, ConvE converts the knowledge graph completion task into a two-dimensional input that can be processed by a convolutional neural network to extract the local features of entities and relationships, but the interaction between entities and relationships is insufficient. InteractE adopts a complex interaction method of random feature arrangement, and further increases the interaction between entity embedding and relationship embedding on the basis of ConvE, thereby improving the performance of knowledge graph completion, but loses the extraction of local features of entities and relationships. The current KGC model has not yet proposed a solution for extracting interaction features and local features at the same time.

[0010] Therefore, how to achieve efficient completion of static knowledge graphs by deeply mining entity category information and deep semantic information in knowledge graphs is the key research content of this invention. Summary of the Invention

[0011] The purpose of the present invention is to solve the problem of neglecting entity category information and insufficient extraction of deep semantic features in traditional knowledge graph completion methods, and to provide a knowledge graph completion method based on deep semantics and entity category information extraction.

[0012] To achieve the above objectives, the technical solution of the present invention is: a knowledge graph completion method based on deep semantics and entity category information extraction, an end-to-end neural network DSET model is proposed, and the entities at the missing positions in the predicted knowledge graph are output based on the DSET model.

[0013] In one embodiment of the present invention, the DSET model includes: a type similarity graph attention encoder TS-GAT that focuses on modeling entity type information, and a deep semantic information three-dimensional convolutional decoder DS-Conv3 that is responsible for extracting deep semantic features of entities and relationships.

[0014] In one embodiment of the present invention, the type similarity graph attention encoder TS-GAT considers the intrinsic connection between entity types in equivalence relations, and identifies equivalence relations by calculating the similarity of positive and negative relationship embeddings during the aggregation process, thereby giving similar entities higher association weights; at the same time, TS-GAT also considers the diversity information between entities, and aggregates triple-level information with both entity and relationship information for the central entity.

[0015] In one embodiment of the present invention, the deep semantic information three-dimensional convolution decoder DS-Conv3 uses Gaussian function mapping to capture the deep complex semantics of entities and relationships, and uses three-dimensional convolution operations to extract local features of entities and relationships, while capturing the complex interaction patterns between them.

[0016] In one embodiment of the present invention, the type similarity graph attention encoder TS-GAT proposes a head-tail type attention mechanism. By calculating the cosine similarity between the forward and reverse relationship embeddings corresponding to the relationship, it determines whether it is an equivalence relationship and whether the head and tail entities belong to the same category. The specific implementation is as follows:

[0017] First, the calculation formula for the positive and negative relationship similarity is:

[0018]

[0019] Here, the symbol · represents the dot product of two vectors, ||r||2 and ||r'||2 represent the bi-norm of vectors r and r', respectively. Since the value range of cosine similarity is between -1 and 1, in order to facilitate the subsequent attention score calculation, the value range of positive and negative relationship similarity is controlled between 0 and 1;

[0020] Next, calculate the attention score between the head and tail entities:

[0021]

[0022] Among them, α ij Representative entity e i and entity e jThe type attention score between ij Represents entity e i and entity e j The embedding vector of the relationship between ij 'Represents entity e i and entity e j The embedding vectors corresponding to the reverse relationship between It is entity e i The neighbor relationship set of

[0023] Next, the embedding vectors of the neighbor entities are weighted according to the attention scores and updated; the passed messages are calculated and updated in the following way:

[0024]

[0025] in, Indicates that the neighbor entity passes to entity e i Type information, Represents all and entity e i A collection of connected entities, It is the mapping matrix of type information.

[0026] In one embodiment of the present invention, the type similarity graph attention encoder TS-GAT further adopts a diversified information transmission process based on the attention mechanism, so that the central entity can obtain discriminative information from different connected triplets. The specific implementation is as follows:

[0027] The entity similarity attention score is used to measure the similarity between the neighbor entity and the central entity. The calculation formula is as follows:

[0028]

[0029] Among them, β ij It is entity e i About Entity e j Through the relationship ij Entity similarity attention score;

[0030] After calculating the entity similarity attention scores of each neighbor entity, TS-GAT performs weighted aggregation of the information of each neighbor entity based on these scores. The aggregation process considers not only the neighbor entity embeddings but also the relationship embeddings between them. The two embeddings are fused by the Hadamard product to obtain an updated representation of the diversity information. The calculation formula is as follows:

[0031]

[0032] in, Represents the entity e idiversity information, Represents all entities e i The connected fact set, ⊙ represents the Hadamard product, It is the mapping matrix of diversity information.

[0033] In one embodiment of the present invention, the update mechanism of the type similarity graph attention encoder TS-GAT is defined as follows:

[0034]

[0035] in, is a learnable parameter matrix, σ is the nonlinear activation function ReLU, e' i is the updated entity embedding, which will be used as the input entity embedding for the next iteration until the entire model training process is completed.

[0036] In one embodiment of the present invention, the deep semantic information three-dimensional convolution decoder DS-Conv3 designs a multi-dimensional Gaussian mapping method to perform mapping transformation on the embedding of entities and relationships, as follows:

[0037] The mapping function of the entity is composed of a series of Gaussian functions φ i (e) Composition, where each kernel function focuses on the input embedding and a specific center point c i The similarity between them; specifically, for the i-th kernel function, we get:

[0038]

[0039] where c i Represents the i-th Gaussian center, which can be obtained by model parameterization learning, σ i is the corresponding standard deviation; the mapping function covers d Gaussian functions, forming a mapping function Φ(e):

[0040] Φ(e)=[φ1(e),φ2(e),…,φ d (e)]

[0041] Through the mapping function Φ, the head entity embedding vector e s is converted into a new feature vector Similarly, the relation embedding r is also converted into a new feature vector r Φ :

[0042]

[0043] In one embodiment of the present invention, the deep semantic information three-dimensional convolution decoder DS-Conv3 also depicts the high-dimensional complex semantics of entities and relationships and their interactive information through three-dimensional convolution operations, which is specifically implemented as follows:

[0044] Given the original head entity and relation embedding e s , r, and the embedding vector obtained by Gaussian mapping r Φ , the feature input is constructed as follows:

[0045]

[0046] Among them, ρ represents the reshape operation, which reshapes the embedded vector into a two-dimensional feature map with a height of h and a width of w. Stack represents the stacking operation, and axis is the dimension in which the stacking operation is performed. F has a dimension of h×w×5, which represents the feature input tensor.

[0047] Then use a three-dimensional convolution kernel to calculate the feature input tensor:

[0048] X = σ(Conv3D(F))

[0049] Among them, X represents the output feature vector after the three-dimensional convolution extracts the interactive features and local features, σ represents the nonlinear activation function ReLU, Conv3D represents the three-dimensional convolution operation, and the size of the convolution kernel is set to c×k h ×k w ×2, c represents the number of channels, k h 、k w Represent the height and width of the convolution kernel respectively, and its depth dimension is 2;

[0050] Finally, the feature map obtained after the convolution layer is converted into a one-dimensional feature vector using the flattening operation vec():

[0051] Out=vec(X).

[0052] The present invention also provides a knowledge graph completion system based on deep semantics and entity category information extraction, including a memory, a processor, and computer program instructions stored in the memory and capable of being executed by the processor. When the processor executes the computer program instructions, the method steps described above can be implemented.

[0053] Compared with the prior art, the present invention has the following beneficial effects:

[0054] 1. To address the problem that existing models in this field ignore entity category information, this paper designs a novel type similarity graph attention encoder to deeply analyze the similarity and equivalence relationship between entities, and models entity type information in the graph context entity aggregation process. This process helps the model understand and distinguish different types of entities and their relationships.

[0055] 2. To address the inadequacy of deep semantics extraction in existing models in this field, this paper designs a novel 3D convolutional decoder for deep semantic information. This decoder employs Gaussian function mapping to capture the deep semantics of entities and relationships. This approach not only enhances the model's understanding of complex interactions between entities, but also achieves precise extraction of interaction features between various embeddings through stacking operations and the application of 3D convolutional kernels. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] Figure 1 This is a flow chart of the knowledge graph completion method based on deep semantics and entity category information extraction of the present invention. DETAILED DESCRIPTION

[0057] The technical solution of the present invention will be described in detail below with reference to the accompanying drawings.

[0058] This paper proposes a knowledge graph completion method based on deep semantic and entity category information extraction. It proposes an end-to-end neural network DSET model, which outputs predicted entities at missing locations in the knowledge graph. The DSET model comprises a Type Similarity Graph Attention Encoder (TS-GAT) that focuses on modeling entity type information and a Deep Semantic Information 3D Convolutional Decoder (DS-Conv3) that extracts deep semantic features of entities and relationships.

[0059] The present invention also provides a knowledge graph completion system based on deep semantics and entity category information extraction, including a memory, a processor, and computer program instructions stored in the memory and capable of being executed by the processor. When the processor executes the computer program instructions, the method steps described above can be implemented.

[0060] The following are specific implementation examples of the present invention.

[0061] 1. Overall idea and pre-definition

[0062] The DSET model aims to solve the problem of neglecting entity category information and insufficient extraction of deep semantic features in traditional knowledge graph completion methods. Figure 1As shown in Figure 1, the DSET model is an end-to-end neural network that consists of two core components: (1) Type Similarity Graph Attention Encoder TS-GAT: This encoder focuses on modeling entity type information. This module considers the intrinsic connection between entity types in equivalence relations. During the aggregation process, it identifies equivalence relations by calculating the similarity of positive and negative relation embeddings, thereby giving similar entities a higher association weight. At the same time, TS-GAT also considers the diversity information between entities, and therefore aggregates triple-level information with both entities and relations for the central entity; (2) Deep Semantic Information 3D Convolution Decoder DS-Conv3D: The decoder is responsible for extracting deep semantic features of entities and relations. First, a Gaussian function mapping is used to capture the deep and complex semantics of entities and relations, and a 3D convolution operation is used to extract local features of entities and relations, while capturing the complex interaction patterns between them. Combining TS-GAT and DS-Conv3D, the DSET model outputs predicted missing entities. By calculating the matching scores between candidate entities and existing entities and relations, the model predicts the entity that is most likely to fill the missing position in the knowledge graph.

[0063] The following are definitions related to the present invention.

[0064] Definition 1 (Knowledge Graph, ) in They represent entity sets, relationship sets, and fact triple sets respectively.

[0065] Definition 2 (Entity Set, ) represents the set of all entities in the knowledge graph, e s ,e o Represent the subject entity and object entity respectively.

[0066] Definition 3 (relation set, ) Represents the set of all relations r in the knowledge graph.

[0067] Definition 4 (Fact Set, ) Represents a set of triple facts.

[0068] Definition 5 (Embedding Dimension) d represents the dimension of the embedding vector in the model

[0069] Definition 6 (Entity Embedding) denote the embeddings corresponding to the subject and object entities, respectively.

[0070] Definition 7 (Relation Embedding) Represents the embedding of relation r.

[0071] 2. DSET model design

[0072] 2.1 Type Similarity Graph Attention Encoder (TS-GAT)

[0073] When performing knowledge graph completion tasks, entity type information is crucial for inferring the possible head and tail entities under a specific relationship. Currently popular graph neural network models, such as R-GCN and CompGCN, all adopt a central entity aggregation mechanism when processing knowledge graphs. These models update the representation of central nodes by aggregating information from neighboring nodes to capture and integrate structural information in the graph. However, a significant limitation of these models is that they ignore the entity category information contained in equivalence relations and do not fully consider the importance of category information in the interaction and information transfer between entities. This flaw limits the model's performance in inferring potential entities.

[0074] To address this challenge, the present invention designs a novel Type-Similarity Graph Attention Encoder (TS-GAT). TS-GAT is dedicated to enhancing the entity aggregation process. Its uniqueness lies in the introduction of a head-tail type attention score for the first time to identify equivalence relationships. TS-GAT can analyze and dynamically adjust the connection weights between entities based on the head-tail type attention scores, thereby more accurately capturing similar characteristics between entities of the same type. This process significantly improves the model's ability to identify and model entity categories in knowledge graphs. At the same time, TS-GAT also takes into account the differences between entities, and achieves a more comprehensive understanding of entities by aggregating diverse information including neighboring entities and relationships for the central entity.

[0075] 2.1.1 Type Information Transfer

[0076] The explicit modeling of entity types in TS-GAT stems from the observation that equivalence relations connect the same entity types at the head and tail of an equivalence relation. Furthermore, the positive and negative relations of an equivalence relation should be highly semantically similar. Therefore, capturing equivalence relations allows for the sharing of similar information between the head and tail entities of an equivalence relation, thereby enabling modeling of entity types.

[0077] This paper proposes a head-tail type attention mechanism. By calculating the cosine similarity between the forward and reverse relationship embeddings corresponding to the relationship, it can determine whether it is an equivalent relationship and whether the head and tail entities belong to the same category. First, the calculation formula for the forward and reverse relationship similarity is:

[0078]

[0079] Here, the symbol · represents the dot product of two vectors, and ||r||2 and ||r'||2 represent the bi-norm of vectors r and r', respectively. Since the value range of cosine similarity is between -1 and 1, in order to facilitate the subsequent attention score calculation, the value range of the positive and negative relationship similarity is controlled between 0 and 1. Next, the attention score between the head and tail entities is further calculated:

[0080]

[0081] Among them, α ij Representative entity e i and entity e j The type attention score between ij Represents entity e i and entity e j The embedding vector of the relationship between ij ' represents the embedding vector of its corresponding reverse relation, It is entity e i The neighbor relationship set of .

[0082] As can be seen from the above formula, the greater the similarity between the positive and negative relationships of a relationship, the greater the likelihood that the relationship is an equivalence relationship, and the higher the attention score. Based on this attention score, the model can dynamically adjust the connection weights between entities, giving similar entities a greater weight when conveying type information. Next, the embedding vectors of neighboring entities are weighted according to the attention score and updated. The transferred messages can be calculated and updated using the following methods:

[0083]

[0084] here, Indicates that the neighbor entity passes to entity e i Type information, Represents all and entity e i A collection of connected entities, It is the mapping matrix of type information.

[0085] 2.1.2 Diversity Information Transmission

[0086] In addition to emphasizing the importance of entity type information, TS-GAT also considers the diversity between entities. To more comprehensively represent the different characteristics of entities and their interactions with relationships, TS-GAT introduces a diversity information transfer mechanism to more meticulously capture the similarities and differences between entities and characterize their unique roles in the knowledge graph.

[0087] Therefore, the present invention adopts a diversity information transfer process based on the attention mechanism, which enables the central entity to obtain discriminative information from different connected triples. Like type information transfer, diversity information transfer also uses the attention mechanism to determine the weights of neighboring entities, but when calculating the weights, it emphasizes the differences between entities. Specifically, the model uses the entity similarity attention score to measure the similarity between neighboring entities and the central entity. The calculation formula is as follows:

[0088]

[0089] Among them, β ij It is entity e i About Entity e j Through the relationship ij Entity similarity attention score.

[0090] After calculating the entity similarity attention scores for each neighboring entity, TS-GAT performs weighted aggregation of information about each neighboring entity based on these scores. This aggregation process considers not only the neighboring entity embeddings but also the relationship embeddings between them, fusing these two embeddings using the Hadamard product to obtain an updated representation of diverse information. This approach provides complete triple-level information for the central entity, enriching the diversity of entity representations. The calculation formula is as follows:

[0091]

[0092] Here, Represents the entity e i diversity information, Represents all entities e i The connected fact set, ⊙ represents the Hadamard product, It is the mapping matrix of diversity information.

[0093] 2.1.3 Entity Aggregation and Update

[0094] The entity aggregation and update process of TS-GAT combines the type information transmission described in Section 2.1.1 with the diversity information transmission mentioned in Section 2.1.2. On this basis, in order to incorporate type information and diversity information, the original entity embedding also needs to be integrated with the information of neighboring entities through a special update strategy. First, each entity collects the type information transmitted from its neighbors. and diversity information In addition, the entity also retains its original embedding i , which represents the initial state of the entity without the influence of external information. Subsequently, TS-GAT will combine this information to update the entity embedding. The specific update mechanism is defined as follows:

[0095]

[0096] in, is a learnable parameter matrix, and σ is the nonlinear activation function ReLU. e' i is the updated entity embedding, which will be used as the input entity embedding for the next iteration until the entire model training process is completed.

[0097] Through this process, TS-GAT not only captures the type attributes of entities, but also depicts the complex relationships between entities and their neighbors, extracting the critical diversity information that influences knowledge graph reasoning. Combining a dual attention mechanism for both type and diversity information, TS-GAT can more comprehensively understand and represent entities and relationships in knowledge graphs, thereby improving the effectiveness of knowledge graph completion tasks.

[0098] 2.2 Deep Semantic Extraction 3D Convolutional Decoder (DS-Conv3D)

[0099] In order to extract the deep semantic information of entities and relationships from the neural network and make full use of this information to complete the knowledge graph completion task, the present invention designs a novel deep semantic extraction 3D convolutional decoder (DS-Conv3D). DS-Conv3D uses Gaussian function mapping and improves the low-dimensional embedding of entities and relationships through nonlinear transformation to capture deep semantic information. In addition, compared with the existing two-dimensional convolutional decoder, the DS-Conv3D of the present invention shows more efficient and sophisticated performance. With the help of stacking operations in three-dimensional space and three-dimensional convolution kernels designed to capture complex data patterns, DS-Conv3D can capture the complex interaction patterns between entities and relationships, and can maintain a high degree of sensitivity and maintenance to the unique local features of entities and relationships.

[0100] 2.2.1 Gaussian function mapping

[0101] This paper designs a multi-dimensional Gaussian mapping method to perform mapping transformation on the embedding of entities and relations. After such transformation, the original embedding space is decoupled into an independent feature space representing deep semantic attributes. Taking the mapping function of the entity as an example, the mapping is composed of a series of Gaussian functions φ i (e) Composition, where each kernel function focuses on the input embedding and a specific center point c i Specifically, for the i-th kernel function, we can get:

[0102]

[0103] where ci Represents the i-th Gaussian center, which can be obtained by model parameterization learning, σ i is the corresponding standard deviation, which is also part of the model parameters. The mapping function covers d such Gaussian functions, thus forming a mapping function Φ(e):

[0104] Φ(e)=[φ1(e),φ2(e),…,φ d (e)]

[0105] Through this mapping function Φ, the head entity embedding vector e s is converted into a new feature vector Similarly, the relation embedding r is also converted into a new feature vector r Φ :

[0106]

[0107] r Φ =Φ(r)

[0108] This Gaussian mapping approach can reveal nonlinear structures and deep patterns in embeddings and facilitate the capture of rich semantic information about entities and relations. By adopting this technique, the model can more effectively infer and generalize complex information in knowledge graphs.

[0109] 2.2.2 Three-dimensional convolution operation

[0110] In the design of the DS-Conv3D decoder, the three-dimensional convolution operation is one of the core links, which is used to characterize the high-dimensional complex semantics of entities and relationships and their interactive information. The following details the implementation steps of the three-dimensional convolution operation. First, it is necessary to construct the input features, that is, to reshape the embedding vector mapped by the Gaussian function and the original embedding vector and use the stacking operation in the depth dimension. Given the original head entity and relationship embedding e s , r, and the embedding vector obtained by Gaussian mapping r Φ , the feature input is constructed as follows:

[0111]

[0112] Where ρ represents a reshape operation, which reshapes the embedding vector into a two-dimensional feature map with height h and width w. Stack represents a stacking operation, and axis is the dimension along which the stacking operation is performed. F has dimensions h×w×5 and represents the feature input tensor. A three-dimensional convolution kernel is then used to compute the feature input tensor:

[0113] X = σ(Conv3D(F))

[0114] Where X represents the output feature vector after extracting interactive features and local features through three-dimensional convolution. σ represents the nonlinear activation function ReLU. Conv3D represents the three-dimensional convolution operation, and the size of the convolution kernel is set to c×k h ×k w ×2, c represents the number of channels, k h 、k w They represent the height and width of the convolution kernel respectively, and its depth is 2.

[0115] The three-dimensional convolution operation can capture the interaction between entity and relation embeddings at different embedding levels, which include original features and deep features obtained by Gaussian function mapping. Using a convolution kernel with a depth of 2 is particularly conducive to extracting such interactive features because it can process two adjacent feature map layers at the same time. For a given feature map stack F, the two layers spanned by the three-dimensional convolution kernel in the depth direction can be equivalent to processing the following four feature pair interactions: the original head entity embedding e s With the original relation embedding r, the original head entity embedding e s The relationship between the Gaussian mapping and the embedding r Φ , head entity embedding after Gaussian mapping Relationship embedding r with Gaussian mapping Φ , Gaussian-mapped head entity embedding Embed r with the original relation;

[0116] The three-dimensional convolution kernel is k in the spatial dimension h ×k w The movement of also allows the model to extract features of each local area. In this way, the model not only integrates the relationship between local features, but also explores the deep interaction between entities and relationships in different dimensions and levels, which is something that previous two-dimensional convolution methods cannot do.

[0117] Finally, the feature map obtained after the convolution layer needs to be converted into a one-dimensional feature vector using the flattening operation vec() for subsequent tasks:

[0118] Out=vec(X)

[0119] 2.3 Training and Optimization

[0120] 2.3.1 Score Function

[0121] Project the flattened vector Out into the embedding space And match it with the tail entity embedding through the dot product operation, and the score function is defined as follows:

[0122]

[0123] Among them, eo represents the tail entity embedding, W out is a trainable weight matrix.

[0124] 2.3.2 Loss Function

[0125] Model training aims to minimize the gap between the predicted tail entity and the true tail entity. In the process of selecting the tail entity, the predicted probability Obtained by applying the logistic function sigmoid to the score. To train the model parameters, the binary cross entropy loss defined below is minimized:

[0126]

[0127] Where N is the number of entities, y i Indicates the label of the positive or negative triplet. In the case of the positive triplet, y i The value is 1, and the negative triples are obtained by randomly replacing the subject or object entity. In this case, y i The value is 0.

[0128] 3. Experiment

[0129] 3.1 Experimental Setup

[0130] 3.1.1 Dataset

[0131] In order to effectively evaluate the knowledge graph completion technology and improve the challenge and fairness of the dataset, this paper experimentally evaluates the DSET model on two modified benchmark datasets FB15k-237

[27] and WN18RR

[10] . WN18RR is a revised version of WN18 derived from the English vocabulary knowledge base WordNet. Because WN18 has the problem of test set information leakage, some inverse relations that may cause evaluation bias, such as "hypernym" and "hyponym", are removed from WN18RR to increase the difficulty and practicality of the dataset. FB15k-237 is a subset of the Freebase knowledge graph, mainly involving movies, actors, awards, sports and other related content. It contains 14,951 entities and 592,213 relationship triples, and is mainly used for knowledge graph completion research, especially link prediction tasks. The statistical information of each dataset is shown in Table 1:

[0132] Table 1 Dataset details

[0133]

[0134] 3.1.2 Evaluation Metrics

[0135] In order to accurately measure the effectiveness of the model, this paper will discuss two key evaluation indicators: Mean Reciprocal Rank (MRR) and Hit Rate@N (Hits@N). These two indicators are widely used in knowledge graph completion tasks and can provide a detailed and comprehensive evaluation of model performance. In the knowledge graph completion task, given a triple (subject, relation, object) containing a missing subject entity or object entity, the model's task is to predict the correct entity of the missing part and give a ranking of a list of candidate entities. MRR calculates the average of the reciprocal rankings of the correct answers of all test samples. Specifically, if a model predicts the correct answer for a test sample to be ranked pth, the reciprocal ranking of the sample is 1 / p. The performance of the model for all test samples is expressed as the average of all reciprocal rankings, that is:

[0136]

[0137] Among them, |Q| is the total number of test samples, and rank i is the ranking of the correct answer for the i-th sample. A higher MRR value indicates a more accurate prediction ranking of the model. Therefore, MRR is a powerful indicator for evaluating the overall performance of the model in the knowledge graph completion task.

[0138] Hits@N is another important indicator to measure the predictive ability of the model. For a given test triple, the model provides a ranked list. If the correct answer appears in the top N positions, it is considered a "hit". Therefore, Hits@N reflects the probability that the correct answer is in the top N positions. Usually, researchers will choose different N values, such as 1, 3 or 10, to observe the performance of the model under different strictness indicators. A higher Hits@N value means that the model is more accurate and reliable in predicting the top N positions. The hit rate calculation formula can be expressed as:

[0139]

[0140] 3.1.3 Baseline

[0141] In this paper, the DSET model is compared with the state-of-the-art models in the field of static knowledge graph completion. The comparison covers translation-based models, TransE, RotatE, and PairRE

[28] ; tensor decomposition-based models, including DistMult, ComplEx, and TuckER

[29] ; neural network-based models, ConvE, InteractE, JointE

[30] , M-DCN

[31] , MRAN

[32] , and DTAE

[33] ; and graph neural network-based models, SACN and CompGCN.

[0142] 3.1.4 Experimental Details

[0143] The DSET model was developed using the PyTorch framework, and all experiments were conducted on a computing platform equipped with an NVIDIA GeForce RTX 3090 graphics card. The model was initialized using the Xavier algorithm to set starting parameter values, and the Adam optimizer was used for training. The learning rate was uniformly set to 0.001. An early stopping mechanism was implemented to select the model with the best performance on the validation set. When processing the FB15k-237 dataset, the convolution kernel size was set to 7×7×2; on the WN18RR dataset, the convolution kernel size was 5×5×2. For both datasets, the model's embedding dimension (d) was 400, and 128 convolution filters were used.

[0144] 3.2 Experimental Results

[0145] 3.2.1 Link Prediction

[0146] Link prediction is a key task in knowledge completion, which aims to predict entities and relations that are not directly observed based on known entities and relations. A knowledge graph is a network structure composed of entity nodes, and the edges in the network represent the semantic connections between entities. Link prediction aims to reveal these potential connections, thereby expanding and refining the knowledge graph. The link prediction performance of the DSET model on the FB15K-237 and WN18RR datasets is shown in Table 2. The best and second-best results are marked in bold and underlined respectively. The results of TransE, DistMult, and ComplEx are derived from the JointE report, while other results are cited from the corresponding original papers.

[0147] The proposed DSET model surpasses current leading models on both datasets. On the FB15k-237 dataset, the DSET model achieves improvements of 2.2%, 0.4%, 1.8%, and 0.9% on the MRR, Hits@1, Hits@3, and Hits@10 metrics, respectively. On the WN18RR dataset, the improvements on the same metrics are 1.5%, 0.4%, 3.4%, and 4.9%, respectively. CompGCN uses ConvE as a decoder and incorporates an encoder to integrate graph context, achieving significant performance improvements. However, it fails to fully model type information and extract deep semantics. In contrast, DSET introduces a novel type similarity graph attention mechanism. This mechanism enables the model to effectively identify equivalence relations when aggregating information from the central entity, more accurately representing entity type information and promoting precise interactions between entities. DSET also employs Gaussian function mapping techniques to extract deep semantic features and effectively captures the complex interactions between entities and relations through three-dimensional convolution operations, preserving their unique local properties. These advantages enable DSET to achieve significant improvements in link prediction tasks, highlighting its advanced capabilities in knowledge graph completion.

[0148] Table 2 Link prediction results of FB15k-237 and WN18RR datasets

[0149]

[0150] 3.2.2 Ablation Experiment

[0151] In order to prove the effectiveness of the various modules introduced in the model proposed in this invention for the KG completion task, this invention designed a series of ablation experiments. In this part, some key components are eliminated one by one and the changes in model performance are observed. Ablation experiments with four settings are mainly carried out: DSET(-G) represents the removal of the graph encoder, namely the TS-GAT encoder, from the model to verify its importance in capturing the deep relationship between entities and entity type information; DSET(-3D) represents the model using ConvE to replace the deep semantic information three-dimensional convolution decoder DS-Conv3D proposed in this invention; DSET(-M) represents the removal of the Gaussian function mapping and the use of the original embedding instead; DSET(-A) represents the removal of type attention, that is, the removal of the type attention score mechanism in the TS-GAT encoder, in order to observe the importance of this mechanism in conveying type information to similar entities. The ablation experiment results are shown in Table 3.

[0152] First, the results in the DSET(-G) setting show that without the TS-GAT encoder, the model's performance significantly degrades compared to the full model. This demonstrates the critical role of the TS-GAT encoder in capturing deep relationships between entities and entity type information. Second, in the DSET(-3D) setting, performance also declines after replacing the decoder with a ConvE, demonstrating that the 3D convolutional decoder is better at capturing local features of entities and relations, as well as deep interaction patterns. Third, in the DSET(-M) setting, performance also declines after removing the Gaussian kernel mapping, demonstrating the critical role of the Gaussian kernel mapping in capturing deep semantic information in entity and relation embeddings. Finally, in the DSET(-A) setting, the model without the typed attention mechanism performs poorly, demonstrating the crucial role of the typed attention mechanism in conveying and updating type information. In summary, the ablation results demonstrate that each component in the model significantly impacts its final performance, demonstrating the effectiveness and necessity of our proposed model design.

[0153] Table 3 Ablation experiment results

[0154]

[0155] 3.2.3 Case Study

[0156] This paper demonstrates the performance and effectiveness of the DSET model in the knowledge graph completion task through a specific case study. Specifically, the FB15k-237 dataset is used as the research object, and the performance difference between the DSET model and the classic graph neural network-based model CompGCN is compared for the link prediction task. Table 4 provides an example for the link prediction task (Jennifer Aniston, friend,?). In this example, the model needs to predict entities that have a "friend" relationship with "JenniferAniston".

[0157] Table 4: Sample study of the FB15k-237 dataset. Bold indicates the correct candidate answer.

[0158]

[0159]

[0160] According to the data in Table 4, the CompGCN model predicts three candidate answers, the highest of which is the incorrect answer, "Friends, season 1." This is because while the CompGCN model can aggregate contextual information from the graph structure, it cannot model entity category information, resulting in an incorrect predicted entity category. The DSET model, on the other hand, successfully predicts the correct answer, "Justin Long." The key reason for the DSET model's success lies in its ability to explicitly model equivalence relations and entity category information. By incorporating the TS-GAT encoder, the DSET model incorporates head and tail type attention into the graph context entity aggregation process. This design enables the model to dynamically adjust the connection weights between entities based on the type information of the head and tail entities during prediction. For this task, DSET uses TS-GAT to recognize that "friend" is an equivalence relation with the same head and tail entity type, and that both "Jennifer Aniston" and "Justin Long" are "person" entities and co-starred in the movie "He's Just Not That Into You," achieving accurate predictions.

[0161] 3.2.4 Stacking sequence analysis

[0162] This paper conducts a stacking order analysis experiment, the main purpose of which is to explore the impact of changing the stacking order of feature construction before 3D convolution on model performance. In the depth dimension, this paper defines the following different stacking orders: (r,e s ,r Φ , r)、(e s ,r, e s ,r)、(r,e s ,e,r Φ , )、(e s ,r,r, r Φ )、(r,e s ,r Φ , We tested these five different combinations and found that varying the stacking order did affect model performance, demonstrating the importance of selecting an appropriate stacking order for capturing deep interactions between entities and relationships. The experimental results are shown in Table 5.

[0163] Table 5 Stacking sequence analysis experimental results

[0164]

[0165] The experimental results show that among all the experimental combinations, the combination (r,e,r Φ , r) provides the best performance, indicating that including the original embedding and the Gaussian-mapped embedding in the first two layers and using only the original embedding in the last two layers can obtain the best deep interaction information of entities and relations. When the convolution kernel depth is 2, since the convolution kernel can operate across two adjacent feature layers, this combination can capture four interaction features, while other combinations can only capture three or two. Therefore, from the perspective of capturing interaction features, (r,e s ,r Φ , r) This stacking order has obvious advantages, which also explains why this combination performs best in the experiment.

[0166] 3.3 Application Scenarios

[0167] The DSET model's deep semantic mining capabilities give it broad application potential in multiple fields, and is particularly suitable for the following scenarios:

[0168] ① Question-answering system:

[0169] Knowledge Q&A: The DEST model's powerful semantic recognition and understanding capabilities can help the question-answering system perform relational reasoning based on its semantic and category information, thereby answering users' questions more accurately.

[0170] Knowledge graph enhancement: The DSET model can help build and enhance the knowledge graph in the question-answering system so that it contains richer information, thereby improving the accuracy and practicality of the question-answering system.

[0171] ② Recommendation system:

[0172] Recommendations based on knowledge graphs: The DSET model can analyze user behavior and entity relationships, complete the relationship between users and recommended entities, and thus make more accurate recommendations, such as making recommendations based on user interests, preferences, and entity relationships in the knowledge graph.

[0173] ③Smart Search:

[0174] Intelligent search integrated with knowledge graph: The DSET model uses semantic analysis and recognition to help intelligent search engines better understand user search intent and provide more relevant search results.

[0175] References:

[0176] [1]Bordes A,Usunier N,Garcia-Duran A,et al.Translating embeddings formodeling multi-relational data[J].Advances in neural informationprocessingsystems,2013,26.

[0177] [2]Wang Z,Zhang J,Feng J,et al.Knowledge graph embedding bytranslating on hyperplanes[C] / / Proceedings of theAAAI conference onartificial intelligence.2014,28(1).

[0178] [3]Lin Y,Liu Z,Sun M,et al.Learning entity and relation embeddingsfor knowledge graph completion[C] / / Proceedings oftheAAAI conference onartificial intelligence.2015,29(1).

[0179] [4]Ji G,He S,Xu L,et al.Knowledge graph embedding via dynamic mappingmatrix[C] / / Proceedings ofthe 53rd annual meeting of the association forcomputational linguistics and the 7th international joint conference onnatural language processing(volume 1:Longpapers).2015:687-696.

[0180] [5]Sun Z,Deng Z H,Nie JY,et al.Rotate:Knowledge graph embeddingbyrelational rotation in complex space[J].arXiv preprint arXiv:1902.10197,2019.

[0181] [6]Nickel M,Tresp V,Kriegel H P.A three-way model for collectivelearning on multi-relational data[C] / / Icml.2011,11(10.5555):3104482.3104584.

[0182] [7]Yang B,Yih W,He X,et al.Embedding entities and relations forlearning and inference in knowledge bases[J].arXiv preprint arXiv:1412.6575,2014.

[0183] [8]Trouillon T,Welbl J,Riedel S,et al.Complex embeddings for simplelink prediction[C] / / International conference on machine learning.PMLR,2016:2071-2080.

[0184] [9]Kazemi S M,Poole D.Simple embedding for link prediction inknowledge graphs[J].Advances in neural information processing systems,2018,31.

[0185]

[10] Dettmers T,Minervini P,Stenetorp P,et al.Convolutional 2dknowledge graph embeddings[C] / / Proceedings of the AAAI conference onartificial intelligence.2018,32(1).

[0186]

[11] Nguyen D Q,Nguyen T D,Nguyen D Q,et al.A novel embedding modelfor knowledge base completion based on convolutional neuralnetwork[J].arXivpreprint arXiv:1712.02121,2017.

[0187]

[12] Vashishth S,Sanyal S,Nitin V,et al.Interacte:Improvingconvolution-based knowledge graph embeddings by increasing featureinteractions[C] / / Proceedings of the AAAI Conference on ArtificialIntelligence.Palo Alto,USA:AAAIPress,2020,34(03):3009-3016.

[0188]

[13] Schlichtkrull M,Kipf T N,Bloem P,et al.Modeling relational datawith graph convolutional networks[C] / / The Semantic Web:15th InternationalConference,ESWC 2018,Heraklion,Crete,Greece,June 3–7,2018,Proceedings15.Springer InternationalPublishing,2018:593-607.

[0189]

[14] Shang C, Tang Y, Huang J, et al. End-to-end structure-awareconvolutional networks for knowledge base completion[C] / / ProceedingsoftheAAAI conference on artificial intelligence.2019,33(01):3060-3067.

[0190]

[15] Nathani D, Chauhan J, Sharma C, et al.Learning attention-basedembeddings for relation prediction in knowledge graphs[J].arXivpreprintarXiv:1906.01195,2019.

[0191]

[16] Vashishth S,Sanyal S,Nitin V,et al.Composition-based multi-relational graph convolutional networks[J].arXiv preprint arXiv:1911.03082,2019.

[0192]

[17] Wang Zhiyue, Yu Qing, Wang Nan, et al. A review of intelligent question answering based on knowledge graph [J]. Computer Engineering and Applications, 2020, 56(23): 11. DOI: 10.3778 / j.issn.1002-8331.2004-0370.

[0193]

[18] Zhou Jing, Sun Ximin, Yu Xiaokun, et al. Knowledge graph and data application - intelligent recommendation [J]. Telecommunications Science, 2019, 35(8): 8. DOI: CNKI: SUN: DXKX.0.2019-08-019.

[0194]

[19] Berant J,ChouA,Frostig R,et al.Semantic parsing on freebase fromquestion-answer pairs[C] / / Proceedings of the 2013conference on empiricalmethods in natural language processing.2013:1533-1544.

[0195]

[20] Mahdisoltani F,Biega J,Suchanek F.Yago3:A knowledge base frommultilingual wikipedias[C] / / 7th biennial conference on innovative datasystems research.CIDR Conference,2014.

[0196]

[21] Erxleben F,Günther M, M,et al.Introducing Wikidata to thelinked data web[C] / / International semantic web conference.Berlin,Germany:Springer,2014:50-65.

[0197]

[22] Miller GA.WordNet:a lexical database forEnglish[J].CommunicationsoftheACM,1995,38(11):39-41.

[0198]

[23] Bollacker K,Evans C,Paritosh P,et al.Freebase:a collaborativelycreated graph database for structuring human knowledge[C] / / Proceedings ofthe2008ACM SIGMOD international conference on Management ofdata.2008:1247-1250.

[0199]

[24] Boschee E, Lautenschlager J, O'Brien S, et al. ICEWS Coded Event Data [M / OL]. [2021-01-22]. https: / / doi.org / 10.7910 / DVN / 28075.

[0200]

[25] Dong

[0201]

[26] Zhang Wenhao, Xu Zhenshun, Liu Na, et al. A review of knowledge graph completion methods [J / OL]. Computer Engineering and Applications, 1-16 [2024-04-05]. http: / / kns.cnki.net / kcms / detail / 11.2127.TP.20240105.1412.010.html.

[0202]

[27] Toutanova K,Chen D.ObservedVersus Latent Features for KnowledgeBase andText Inference[C] / / The 3rd Workshop on Continuous Vector Space Modelsandtheir Compositionality.2015.

[0203]

[28] Chao L,He J,Wang T,et al.Pairre:Knowledge graph embeddings viapaired relation vectors[J].arXiv preprint arXiv:2011.03798,2020.

[0204]

[29] I,Allen C,Hospedales T M.Tucker:Tensor factorization forknowledge graph completion[J].arXiv preprint arXiv:1901.09590,2019.

[0205]

[30] Zhou Z,Wang C,Feng Y,et al.JointE:Jointly utilizing 1D and 2Dconvolution for knowledge graph embedding[J].Knowledge-Based Systems,2022,240:108100.

[0206]

[31] Zhang Z,Li Z,Liu H,et al.Multi-scaledynamic convolutional networkfor knowledge graph embedding[J].IEEE Transactions on Knowledge andDataEngineering,2020,34(5):2335-2347.

[0207]

[32] Xue Z,Zhang Z,Liu H,et al.Learning knowledge graph embedding withmulti-granularity relational augmentation network[J].Expert SystemswithApplications,2023,233:120953.

[0208]

[33] Deng W,Zhang Y,Yu H,et al.Knowledge graph embedding based ondynamic adaptive atrous convolution and attention mechanism forlinkprediction[J].Information Processing&Management,2024,61(3):103642.。

[0209] The above are preferred embodiments of the present invention. Any changes made according to the technical solution of the present invention, as long as the resulting functions and effects do not exceed the scope of the technical solution of the present invention, shall fall within the scope of protection of the present invention.

Claims

1. A knowledge graph completion method based on deep semantics and entity category information extraction, characterized by: An end-to-end neural network DSET model is proposed, and based on the DSET model, the predicted entities at the missing positions in the knowledge graph are output; the DSET model includes: a type similarity graph attention encoder TS-GAT that focuses on modeling entity type information, and a deep semantic information three-dimensional convolutional decoder DS-Conv3 that is responsible for extracting deep semantic features of entities and relationships; the type similarity graph attention encoder TS-GAT considers the intrinsic connection between entity types in equivalence relations, and identifies equivalence relations by calculating the similarity of positive and negative relationship embeddings during the aggregation process, thereby giving similar entities higher association weights; at the same time, TS-GAT also considers the diversity information between entities, and aggregates triple-level information with both entities and relationships for the central entity; the deep semantic information three-dimensional convolutional decoder DS-Conv3 uses Gaussian function mapping to capture the deep and complex semantics of entities and relationships, and uses three-dimensional convolution operations to extract local features of entities and relationships, while capturing the complex interaction patterns between them; The Type Similarity Graph Attention Encoder TS-GAT proposes a head-tail type attention mechanism. By calculating the cosine similarity between the forward and reverse relationship embeddings corresponding to the relationship, it determines whether it is an equivalence relationship and whether the head and tail entities belong to the same category. The specific implementation is as follows: First, the calculation formula for the positive and negative relationship similarity is: Here, the symbol · represents the dot product of two vectors, ||r||2 and ||r'||2 represent the bi-norm of vectors r and r', respectively. Since the value range of cosine similarity is between -1 and 1, in order to facilitate the subsequent attention score calculation, the value range of positive and negative relationship similarity is controlled between 0 and 1; Next, calculate the attention score between the head and tail entities: Among them, α ij Representative entity e i and entity e j The type attention score between ij Represents entity e i and entity e j The embedding vector of the relationship between ij 'Represents entity e i and entity e j The embedding vectors corresponding to the reverse relationship between It is entity e i The neighbor relationship set of Next, the embedding vectors of the neighbor entities are weighted according to the attention scores and updated; the passed messages are calculated and updated in the following way: in, Indicates that the neighbor entity passes to entity e i Type information, Represents all and entity e i A collection of connected entities, It is the mapping matrix of type information; The deep semantic information three-dimensional convolution decoder DS-Conv3 designs a multi-dimensional Gaussian mapping method to map and transform the embedding of entities and relations as follows: The mapping function of the entity is composed of a series of Gaussian functions φ i (e) Composition, where each kernel function focuses on the input embedding and a specific center point c i The similarity between them; specifically, for the i-th kernel function, we get: where c i Represents the i-th Gaussian center, which can be obtained by model parameterization learning, σ i is the corresponding standard deviation; the mapping function covers d Gaussian functions, forming a mapping function Φ(e): Φ(e)=[φ1(e),φ2(e),…,φ d (e)] Through the mapping function Φ, the head entity embedding vector e s is converted into a new feature vector Similarly, the relation embedding r is also converted into a new feature vector r Φ :

2. The knowledge graph completion method based on deep semantics and entity category information extraction according to claim 1 is characterized in that: The type similarity graph attention encoder TS-GAT also adopts a diverse information transmission process based on the attention mechanism, so that the central entity can obtain discriminative information from different connected triplets. The specific implementation is as follows: The entity similarity attention score is used to measure the similarity between the neighbor entity and the central entity. The calculation formula is as follows: Among them, β ij It is entity e i About Entity e j Through the relationship ij Entity similarity attention score; After calculating the entity similarity attention scores of each neighbor entity, TS-GAT performs weighted aggregation of the information of each neighbor entity based on these scores. The aggregation process considers not only the neighbor entity embeddings but also the relationship embeddings between them. The two embeddings are fused by the Hadamard product to obtain an updated representation of the diversity information. The calculation formula is as follows: in, Represents the entity e i diversity information, Represents all entities e i The connected fact set, ⊙ represents the Hadamard product, It is the mapping matrix of diversity information.

3. The knowledge graph completion method based on deep semantics and entity category information extraction according to claim 2 is characterized in that: The update mechanism of the type similarity graph attention encoder TS-GAT is defined as follows: in, is a learnable parameter matrix, σ is the nonlinear activation function ReLU, e ' i is the updated entity embedding, which will be used as the input entity embedding for the next iteration until the entire model training process is completed.

4. The knowledge graph completion method based on deep semantics and entity category information extraction according to claim 1 is characterized in that: The deep semantic information 3D convolution decoder DS-Conv3 also depicts the high-dimensional complex semantics of entities and relationships and their interaction information through 3D convolution operations. The specific implementation is as follows: Given the original head entity and relation embedding e s , r, and the embedding vector obtained by Gaussian mapping r Φ , the feature input is constructed as follows: Among them, ρ represents the reshape operation, which reshapes the embedded vector into a two-dimensional feature map with a height of h and a width of w. Stack represents the stacking operation, and axis is the dimension in which the stacking operation is performed. F has a dimension of h×w×5, which represents the feature input tensor. Then use a three-dimensional convolution kernel to calculate the feature input tensor: X = σ(Conv3D(F)) Among them, X represents the output feature vector after the three-dimensional convolution extracts the interactive features and local features, σ represents the nonlinear activation function ReLU, Conv3D represents the three-dimensional convolution operation, and the size of the convolution kernel is set to c×k h ×k w ×2, c represents the number of channels, k h 、k w Represent the height and width of the convolution kernel respectively, and its depth dimension is 2; Finally, the feature map obtained after the convolution layer is converted into a one-dimensional feature vector using the flattening operation vec(): Out=vec(X).

5. A knowledge graph completion system based on deep semantics and entity category information extraction, characterized by: The method comprises a memory, a processor, and computer program instructions stored in the memory and capable of being executed by the processor. When the processor executes the computer program instructions, the method steps according to any one of claims 1 to 4 can be implemented.

Images