Chemical park industry chain data knowledge graph construction method and system based on big data

Abstract

The present invention relates to the technical field of knowledge graph construction, and more specifically, to a method and system for constructing a chemical park industry chain data knowledge graph based on big data. The method comprises the following steps: obtaining chemical park industry chain data; defining nodes and edges of the knowledge graph, using an evolutionary graph convolutional network model to predict the relationship between the number changes of adjacent nodes and placing them in the edges, and constructing a product reserve relationship knowledge graph; introducing timestamps to update node definitions, using a dynamic temporal graph network algorithm to convert the product reserve relationship knowledge graph into a product time relationship knowledge graph, merging repeated routes and products in the chemical park to obtain a final product time relationship knowledge graph; and using a visual interface to display the product reserve relationship knowledge graph and the product time relationship knowledge graph. The method and system for constructing a chemical park industry chain data knowledge graph based on big data achieves temporal management and dynamic optimization of product reserve relationships by constructing two knowledge graphs.

Description

Technical Field

[0001] The present invention relates to the technical field of knowledge graph construction, and specifically to a method and system for constructing a chemical park industry chain data knowledge graph based on big data. Background Art

[0002] The big data-based chemical park industry chain data knowledge graph construction method and system aim to improve the data processing efficiency of the chemical park industry chain and optimize the resource scheduling and decision support of the industry chain. By using the in-evolution graph convolutional network model to calculate and analyze the changes in production capacity relationships caused by changes in the quantity of adjacent chemical products with production up-and-down relationships, a product reserve relationship knowledge graph with the function of reflecting the changes in the quantity relationship of adjacent chemical products and real-time updating is constructed. On the basis of the product reserve relationship knowledge graph, timestamps are introduced to construct a product time relationship knowledge graph that can reflect the production sequence and mutual dependence between different chemical products. The two knowledge graphs are independently stored and cooperate with each other to realize the intelligent storage management of chemical park industry chain data, dynamic update of product reserves and on-demand query of product resources.

[0003] Existing knowledge graph construction methods and systems are usually static knowledge graphs that can only simply store industrial chain data. They are unable to handle complex industrial chain relationships that change over time and changes in product relationships caused by dynamic updates of product quantities. In addition, due to the strong temporal nature and interdependence of chemical park industrial chain data, ordinary knowledge graphs cannot update product quantities in real time, predict relationship changes from data changes, and reflect upstream and downstream relationships between products. This will result in multiple employees being unable to query the required product status in real time when querying at the same time, leading to product resource shortages and conflicts. Therefore, a chemical park industrial chain data knowledge graph construction method and system based on big data are provided. Summary of the Invention

[0004] The purpose of the present invention is to provide a method and system for constructing a chemical park industry chain data knowledge graph based on big data, so as to solve the problem raised in the above background technology that due to the strong temporality and interdependence of chemical park industry chain data, ordinary knowledge graphs cannot update the product quantity in real time, predict relationship changes from data changes, and reflect the upstream and downstream relationships between products, which will result in multiple employees being unable to query the required product status in real time when querying at the same time, thereby leading to product resource shortage conflicts.

[0005] To achieve the above objectives, the present invention provides a method for constructing a chemical park industry chain data knowledge graph based on big data, comprising:

[0006] S1. Obtain chemical park industry chain data from the industry database and use natural language processing technology to extract industry chain product entity information and product relationship information;

[0007] S2. Define nodes and edges of the knowledge graph based on product entity information and product relationship information. Use the evolutionary graph convolutional network model to predict the relationship between the number of adjacent nodes and place it on the edges to build a product reserve relationship knowledge graph.

[0008] The evolutionary graph convolutional network model is implemented based on a graph convolutional network fused with a multi-layer perceptron model. It is used to consider the changes in nodes and edges over time to handle the changes in graph structure over time, and to predict the impact of changes in the number of nodes on edges.

[0009] S3. Based on the product reserve relationship knowledge graph, timestamps are introduced to update node definitions. The product reserve relationship knowledge graph is converted into a product time relationship knowledge graph using a dynamic temporal graph network algorithm. Repeated routes and products in the chemical park are merged to obtain the final product time relationship knowledge graph.

[0010] S4. Use a visual interface to display the product reserve relationship knowledge graph and the product time relationship knowledge graph, so that users can perform query operations according to their needs.

[0011] As a further improvement of the present technical solution, in said S1, the product entity information includes the Chinese and English name, quantity, molecular weight, molecular formula, structural formula, production capacity, appearance, physical properties, specifications, process information, market price and supplier of each product;

[0012] Product relationship information includes raw material supply relationships, production relationships, consumption relationships, substitution relationships, and transportation relationships.

[0013] As a further improvement to this technical solution, in S2, the nodes and edges of the knowledge graph are defined based on product entity information and product relationship information. The evolutionary graph convolutional network model is used to predict the relationship between the number of adjacent nodes and place them in the edges to construct a product reserve relationship knowledge graph. The specific method steps are as follows:

[0014] S2.1. Define product entity nodes based on product entity information;

[0015] S2.2. Define product relationship edges based on product relationship information;

[0016] S2.3. Use the Evolved Graph Convolutional Network model to predict the production capacity relationship caused by the change in the quantity of adjacent chemical products with production up-down relationships and place it on the corresponding product relationship edge;

[0017] S2.4. Based on product entity nodes and product relationship edges, construct a product reserve relationship knowledge graph.

[0018] As a further improvement of this technical solution, in S2.1, a product entity node is defined based on the product entity information. The specific method is as follows:

[0019] N i =(P i ,Q i ,X i );

[0020] Where i is the product entity index; N i is the i-th product entity node; P i is the name of the i-th product entity; Q i is the number of product entities of the i-th type; X i are the characteristics of the i-th product entity except name and quantity;

[0021] In S2.2, product relationship edges are defined based on product relationship information. The specific method is as follows:

[0022] E ij =(N i ,N j ,R ij ,w ij ,ΔQ ij );

[0023] Among them, j is the product entity index; N j is the jth product entity node; E ij is the product relationship edge between the i-th product entity node and the j-th product entity node; R ij is product relationship information; w ij is the product relationship edge weight; ΔQ ij Product relationship change information.

[0024] As a further improvement to this technical solution, in S2.3, the evolutionary graph convolutional network model is used to predict the production capacity relationship caused by the change in the quantity of adjacent chemical products with production up-down relationships and place it in the corresponding product relationship edge. The specific method steps are as follows:

[0025] S2.3.1. Set the time step to t. Each product entity node has a corresponding number at each time step t.

[0026] S2.3.2. Based on the graph convolutional network model, aggregate the feature information of neighboring nodes and calculate the new feature representation of each product entity node:

[0027]

[0028] Among them, X i (t+1) is the feature of the i-th product entity node at time step t+1 except for the name and quantity; μ is the index of the neighbor node; is the neighbor node set of the i-th product entity node; Aij is the adjacency matrix; d i is the degree of the i-th product entity node; X μ (t) is the feature of the neighbor node μ except the name and quantity; W is the weight matrix; σ(·) is the Sigmoid nonlinear activation function;

[0029] S2.3.3. Based on the features of the i-th product entity node at time step t+1, except for the name and quantity, a multi-layer perceptron model is integrated to predict the change in the quantity of product entities at time step t+1:

[0030]

[0031] in, is the change in product quantity of the i-th product entity node at time step t+1; X i (t+1) X is the feature of the i-th product entity node at time step t+1 except for the name and quantity; j (t+1) A' is the feature of the j-th product entity node at time step t+1 except for the name and quantity; ij is the node connection strength weight; MLP([·]) is the multi-layer perceptron model operation;

[0032] Similarly, the product quantity change based on the j-th product entity node at time step t+1 can be obtained

[0033] S2.3.4. Product quantity changes based on the i-th product entity node and the j-th product entity node at time step t+1 and Analyze the changes in the production capacity relationship between the i-th chemical product and the adjacent j-th chemical product, and place them in the product relationship edge;

[0034] As a further improvement of this technical solution, in S2.3.4, the product quantity change between the i-th product entity node and the j-th product entity node at time step t+1 is calculated. and Analyze the changes in the production capacity relationship between the i-th chemical product and the adjacent j-th chemical product and place them in the product relationship edge. The specific method is as follows:

[0035] S2.3.4.1. Based on product relationship information R ij Combine the product quantity changes of the i-th product entity node and the j-th product entity node at time step t+1 and Calculate product relationship information at time step t+1:

[0036]

[0037] in, is the product relationship information at time step t, which is equivalent to the product relationship information R ij ; The change of product relationship information at time step t+1; γ1 is the weight coefficient of the i-th product entity; γ2 is the weight coefficient of the j-th product entity; γ3 is the product relationship weight coefficient; ∈ is a smoothing term;

[0038] S2.3.4.2. Update the product relationship edge weights of the product relationship edges based on the product relationship information changes at time step t+1:

[0039]

[0040] in, is the product relationship edge weight at time step t, which is equivalent to the product relationship edge weight w ij ; is the product relationship edge weight at time step t+1; α is the weight coefficient of the product relationship edge weight; β is the weight coefficient of the product relationship information change;

[0041] Based on the evolutionary graph convolutional network model, the capacity relationship changes caused by the changes in the quantity of adjacent chemical products with production hierarchical relationships are calculated and analyzed. In the product reserve relationship knowledge graph, it is used to query in real time whether the capacity relationship between adjacent chemical products can meet the current production demand, and it is also used to update the quantity and capacity changes of each chemical product in real time.

[0042] In S2.4, a product reserve relationship knowledge graph is constructed based on product entity nodes and product relationship edges, as follows:

[0043] G1=({N1,N2,…,N i ,…,N n},{E' ij |1≤i≠j≤n});

[0044]

[0045] Among them, G1 is the product reserve relationship knowledge graph; n is the total number of product entity nodes; E' ij It is the product relationship edge between the i-th product entity node and the j-th product entity node after adding the prediction data.

[0046] As a further improvement of this technical solution, in S3, based on the product reserve relationship knowledge graph, a timestamp update node definition is introduced, and a dynamic temporal graph network algorithm is used to convert the product reserve relationship knowledge graph into a product time relationship knowledge graph. The repeated routes and products of the chemical park are merged to obtain the final product time relationship knowledge graph. The specific method steps are as follows:

[0047] S3.1. Introduce timestamps to update and define product entity nodes and product relationship edges:

[0048]

[0049] E” ij =(N i ,N j ,R ij ,w ij );

[0050] in, The i-th product entity node containing the timestamp after the update; E” ij is the product relationship edge between the i-th product entity node and the j-th product entity node after the update; is the node timestamp;

[0051] S3.2. Use the dynamic temporal graph network algorithm to transform the product reserve relationship knowledge graph into the product time relationship knowledge graph;

[0052] S3.3. Use the incremental hierarchical temporal memory model to adaptively merge repeated routes and product entity nodes in the chemical park to obtain the final product time relationship knowledge graph.

[0053] As a further improvement of this technical solution, in S3.2, a dynamic temporal graph network algorithm is used to convert the product reserve relationship knowledge graph into a product time relationship knowledge graph. The specific method steps are as follows:

[0054] S3.2.1. Use graph neural networks to perform temporal embedding of each product entity node and product relationship edge:

[0055]

[0056] in, The i-th product entity node containing the timestamp after the update Temporal embedding of is the set of neighbor nodes of the i-th product entity node;

[0057]

[0058] in, is the temporal embedding of the product relationship edge between the i-th product entity node and the j-th product entity node; is the edge timestamp;

[0059] S3.2.2. Combine the temporal information of product entity nodes and product relationship edges to obtain the product temporal relationship knowledge graph:

[0060]

[0061] Among them, G2 is the product time relationship knowledge graph; The nth product entity node containing the timestamp after the update Temporal embedding of .

[0062] As a further improvement of this technical solution, in S3.3, an incremental hierarchical temporal memory model is used to adaptively merge repeated routes and product entity nodes in the chemical park to obtain the final product time relationship knowledge graph. The specific method steps are as follows:

[0063] S3.3.1. At each time step, based on the temporal embedding of each product entity node, calculate the cosine similarity between each product entity node and set the node similarity threshold δ to determine whether it can be merged:

[0064]

[0065] like If the i-th product entity node is similar to the j-th product entity node, they can be merged; otherwise, they cannot be merged.

[0066] in, is the cosine similarity between the i-th product entity node and the j-th product entity node; δ is the node similarity threshold;

[0067] S3.3.2. At each time step, based on the temporal embedding of each product relationship edge, calculate the cosine similarity of each product relationship edge and set the edge similarity threshold τ to determine whether it can be merged:

[0068]

[0069] like Then the product relationship edge Product relationship Similar ones can be merged, otherwise they cannot be merged;

[0070] in, Product relationship edge Product relationship The cosine similarity of ; τ is the edge similarity threshold; s is the product entity node index; l is the product entity node index; is the temporal embedding of the product relationship edge between the sth product entity node and the lth product entity node;

[0071] S3.3.3. Merge similar product entity nodes and product relationship edges to obtain the final product time relationship knowledge graph.

[0072] On the other hand, the present invention provides a chemical park industry chain data knowledge graph construction system based on big data, including a memory, a processor, and a computer program stored in the memory and runnable on the processor. The processor executes the computer program to implement any one of the above-mentioned chemical park industry chain data knowledge graph construction methods based on big data.

[0073] Compared with the prior art, the present invention has the following beneficial effects:

[0074] 1. In this big data-based chemical park industry chain data knowledge graph construction method and system, based on the evolutionary graph convolutional network model, it is possible to predict the changes in the quantity of each product entity in the chemical park industry chain over time, dynamically capture the relationship evolution between product entity nodes in the knowledge graph, and optimize the resource allocation of the industry chain based on this change, reducing the risk of redundant production and supply chain disruptions.

[0075] 2. In the chemical park industry chain data knowledge graph construction method and system based on big data, by constructing a product reserve relationship knowledge graph, the problem that the relationship between products changes with changes in output and cannot be presented in the static knowledge graph is solved. By constructing a product time relationship knowledge graph, the problem that the upstream and downstream relationships of products cannot be expressed in the product reserve relationship knowledge graph is compensated. The two knowledge graphs complement each other in functional requirements, realize the timing management and dynamic optimization of product reserve relationships, and thus improve the resource scheduling accuracy in the chemical park industry chain. BRIEF DESCRIPTION OF THE DRAWINGS

[0076] Figure 1 The figure is a flow chart of the overall method of the present invention. DETAILED DESCRIPTION

[0077] The following will provide a clear and complete description of the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0078] Example 1: Please refer to Figure 1 As shown, this embodiment provides a method for constructing a chemical park industry chain data knowledge graph based on big data, including the following steps:

[0079] S1. Obtain chemical park industry chain data from the industry database and use natural language processing technology to extract industry chain product entity information and product relationship information;

[0080] In S1, the product entity information includes the Chinese and English name, quantity, molecular weight, molecular formula, structural formula, production capacity, appearance, physical properties, specifications, process information, market price and supplier of each product;

[0081] Product relationship information includes raw material supply relationships, production relationships, consumption relationships, substitution relationships, and transportation relationships.

[0082] In this embodiment, relevant product entity information and product relationship information are obtained from the industrial database of the chemical park and preprocessed, including removing unnecessary symbols, HTML tags, blank characters and other irrelevant information; segmenting long text into meaningful words; filtering out common but meaningless words; for English text, using morphological restoration technology to restore words to their basic form; and using named entity recognition technology to extract the Chinese and English name, quantity, molecular weight, molecular formula, structural formula, production capacity, appearance, physical properties, specifications, process information, market price and supplier of each product from the text;

[0083] Based on the extracted entities, the relationships between entities are identified and extracted. For example, the production of product A requires raw material B, and company X has a supply relationship with product Y. Relationship extraction algorithms are used to automatically extract relationships from text, and by parsing the dependency relationships of sentences, the grammatical relationships between entities are identified and the logical relationships between entities are inferred.

[0084] The product relationship information includes raw material supply relationship, production relationship, consumption relationship, substitution relationship, and transportation relationship, as follows:

[0085] The raw material supply relationship is that upstream products provide raw materials for downstream products; the production relationship is that a product is produced by one or more upstream raw materials or intermediate products through a certain production process; the consumption relationship is that downstream products or applications consume upstream products; the substitution relationship is that one product can replace the function or use of another product; the transportation relationship is the transportation path and method of raw materials and products between different enterprises or production stages.

[0086] S2. Define nodes and edges of the knowledge graph based on product entity information and product relationship information. Use the evolutionary graph convolutional network model to predict the relationship between the number of adjacent nodes and place it on the edges to build a product reserve relationship knowledge graph.

[0087] The evolutionary graph convolutional network model is implemented based on a graph convolutional network fused with a multi-layer perceptron model. It is used to consider the changes in nodes and edges over time to handle the changes in graph structure over time, and to predict the impact of changes in the number of nodes on edges.

[0088] In S2, the nodes and edges of the knowledge graph are defined based on product entity information and product relationship information. The evolutionary graph convolutional network model is used to predict the relationship between the number of adjacent nodes and place them in the edges to construct a product reserve relationship knowledge graph. The specific method steps are as follows:

[0089] S2.1. Define product entity nodes based on product entity information;

[0090] S2.2. Define product relationship edges based on product relationship information;

[0091] S2.3. Use the Evolved Graph Convolutional Network model to predict the production capacity relationship caused by the change in the quantity of adjacent chemical products with production up-down relationships and place it on the corresponding product relationship edge;

[0092] S2.4. Construct a product reserve relationship knowledge graph based on product entity nodes and product relationship edges. In S2.1, product entity nodes are defined based on product entity information. The specific method is as follows:

[0093] N i =(P i ,Q i ,X i );

[0094] Where i is the product entity index; N i is the i-th product entity node; P i is the name of the i-th product entity; Q i is the number of product entities of the i-th type; X i are the characteristics of the i-th product entity except name and quantity;

[0095] In S2.2, product relationship edges are defined based on product relationship information. The specific method is as follows:

[0096] E ij =(N i ,N j ,R ij ,w ij ,ΔQ ij );

[0097] Among them, j is the product entity index; N j is the jth product entity node; E ij is the product relationship edge between the i-th product entity node and the j-th product entity node; R ij is product relationship information; w ij is the product relationship edge weight; ΔQ ij Product relationship change information.

[0098] In this embodiment, X iX is the characteristics of the i-th product entity other than the name and quantity, that is, the molecular weight, molecular formula, structural formula, production capacity, appearance, physical properties, specifications, process information, market price and supplier of the product in the product entity information. i The data can be queried when users need to conduct detailed inquiries. It is not explicitly stored in the product entity node or in the product reserve relationship knowledge graph, which simplifies the graph structure and satisfies the knowledge graph's need for detailed records of chemical park industry chain data.

[0099] w ij is the product relationship edge weight, which represents the importance of the i-th product entity node and the j-th product entity node to the integrated knowledge graph. It can better reflect the indispensable importance of the two product entities in the entire chemical park industrial chain and provide a basis for subsequent knowledge graph transformation.

[0100] In S2.3, the evolutionary graph convolutional network model is used to predict the production capacity relationship caused by the change in the quantity of adjacent chemical products with production up-down relationships and place it in the corresponding product relationship edge. The specific method steps are as follows:

[0101] S2.3.1. Set the time step to t. Each product entity node has a corresponding number at each time step t.

[0102] As time goes by, the number of products in the graph will change. The graph convolutional network will update the feature information of the node according to the change in the number of each node. A new graph structure needs to be established for each time step, where the number of nodes It will be updated according to the changes in the previous step to form a new feature representation X i (t) ;

[0103] S2.3.2. Based on the graph convolutional network model, aggregate the feature information of neighboring nodes and calculate the new feature representation of each product entity node:

[0104]

[0105] Among them, X i (t+1) is the feature of the i-th product entity node at time step t+1 except for the name and quantity; μ is the index of the neighbor node; is the neighbor node set of the i-th product entity node; A ij is the adjacency matrix; d i is the degree of the i-th product entity node; X μ (t) is the feature of the neighbor node μ except the name and quantity; W is the weight matrix; σ(·) is the Sigmoid nonlinear activation function;

[0106] S2.3.3. Based on the features of the i-th product entity node at time step t+1, except for the name and quantity, a multi-layer perceptron model is integrated to predict the change in the quantity of product entities at time step t+1:

[0107]

[0108] in, is the change in product quantity of the i-th product entity node at time step t+1; X i (t+1) X is the feature of the i-th product entity node at time step t+1 except for the name and quantity; j (t+1) A' is the feature of the j-th product entity node at time step t+1 except for the name and quantity; ij is the node connection strength weight; MLP([·]) is the multi-layer perceptron model operation;

[0109] And based on S2.3.1-S2.3.3, the product quantity change based on the j-th product entity node at time step t+1 can be obtained

[0110] S2.3.4 Product quantity changes based on the i-th product entity node and the j-th product entity node at time step t+1 and Analyze the changes in the production capacity relationship between the i-th chemical product and the adjacent j-th chemical product, and place them in the product relationship edge.

[0111] In this embodiment, the evolutionary graph convolutional network model is implemented based on the graph convolutional network fused with a multi-layer perceptron model. Node representations are learned through graph convolution operations, and the evolutionary changes of node features are processed using MLP, thereby capturing the temporal dependency between the graph structure and the attributes of product entity nodes, predicting changes in the number of products at product entity nodes, and analyzing changes in relationships caused by changes in product quantity. A time step t is introduced into the evolutionary graph convolutional network model. This model only considers changes in the number of products at each product entity node over time, without considering temporal changes in the entire knowledge graph.

[0112] In S2.3.4, the product quantity change between the i-th product entity node and the j-th product entity node at time step t+1 is calculated. and Analyze the changes in the production capacity relationship between the i-th chemical product and the adjacent j-th chemical product and place them in the product relationship edge. The specific method is as follows:

[0113] S2.3.4.1. Based on product relationship information R ijCombine the product quantity changes of the i-th product entity node and the j-th product entity node at time step t+1 and Calculate product relationship information at time step t+1:

[0114]

[0115] in, is the product relationship information at time step t, which is equivalent to the product relationship information R ij ; The change of product relationship information at time step t+1; γ1 is the weight coefficient of the i-th product entity; γ2 is the weight coefficient of the j-th product entity; γ3 is the product relationship weight coefficient; ∈ is a smoothing term;

[0116] S2.3.4.2. Update the product relationship edge weights of the product relationship edges based on the product relationship information changes at time step t+1:

[0117]

[0118] in, is the product relationship edge weight at time step t, which is equivalent to the product relationship edge weight w ij ; is the product relationship edge weight at time step t+1; α is the weight coefficient of the product relationship edge weight; β is the weight coefficient of the product relationship information change;

[0119] Based on the evolutionary graph convolutional network model, the capacity relationship changes caused by the changes in the quantity of adjacent chemical products with production hierarchical relationships are calculated and analyzed. In the product reserve relationship knowledge graph, it is used to query in real time whether the capacity relationship between adjacent chemical products can meet the current production demand, and it is also used to update the quantity and capacity changes of each chemical product in real time.

[0120] In this embodiment, the evolutionary graph convolutional network model is used to update the quantity and production capacity changes of each chemical product in the product reserve relationship knowledge graph in real time, ensuring that the product reserve relationship knowledge graph is updated in real time as the product data of the chemical park changes, thereby ensuring the real-time nature of the product reserve relationship knowledge graph; at the same time, the evolutionary graph convolutional network model is used to calculate and analyze the changes in production capacity relationships caused by changes in the quantity of adjacent chemical products with upstream and downstream production relationships. For example, the products polyethylene (PE) and polypropylene (PP) have upstream and downstream relationships in the production process. The production process of polyethylene requires the use of polypropylene by-products, and the production of polypropylene depends on ethylene as a raw material. Ethylene is produced through steam cracking. Due to the interdependence in the production process, the production of polyethylene and polypropylene needs to be coordinated and adjusted according to market demand and reserves. The evolutionary graph convolutional network model operates as follows in this case: Assume that at time step t+1, the demand for polyethylene increases by 10%, while the production of polypropylene decreases by 5%. Through the evolutionary graph convolutional network model, the quantity changes between polyethylene and polypropylene can be captured, and the production capacity of polyethylene and polypropylene can be calculated. The change in the relationship between polyethylene and polypropylene is that the increase in polyethylene production capacity may require an increase in ethylene supply, while the decrease in polypropylene production capacity may lead to adjustments in the ethylene supply chain. According to the dynamic changes in the production chain, the evolutionary graph convolutional network model will update the changes in the capacity relationship between polyethylene and polypropylene in real time, including: whether the polyethylene production line has sufficient capacity to expand production under current production demand; whether the polypropylene production line will be affected by the ethylene supply limit, thereby affecting the polyethylene by-product supply capacity; whether the ethylene supply can keep up with the production demand of polypropylene and polyethylene; the evolutionary graph convolutional network model will update the product reserve relationship knowledge graph in real time according to the above changes, and perform queries: by querying the relationship edge weights between polyethylene and polypropylene in the graph, confirm whether the production capacity of the two products is coordinated and whether they can meet current production needs; for example, if the production of polypropylene decreases, will it lead to insufficient ethylene supply, thereby affecting the production of polyethylene, resulting in a bottleneck in the capacity chain between polyethylene and ethylene? In the product reserve relationship knowledge graph, it is used to query in real time whether the capacity relationship between adjacent chemical products can meet current production needs;

[0121] In S2.4, a product reserve relationship knowledge graph is constructed based on product entity nodes and product relationship edges, as follows:

[0122] G1=({N1,N2,…,N i ,…,N n},{E' ij |1≤i≠j≤n});

[0123]

[0124] Among them, G1 is the product reserve relationship knowledge graph; n is the total number of product entity nodes; E' ij It is the product relationship edge between the i-th product entity node and the j-th product entity node after adding the prediction data.

[0125] In this example, we infer the change in the product relationship between the i-th and j-th product entity nodes by calculating the change in the number of them, and further update the weight of the product relationship edge:

[0126] and Corresponding to the change ratio of the quantity of the i-th and j-th product entity nodes, a ∈ smoothing term is added to avoid the denominator being zero. It considers the historical information of product relationships, which can help us capture the stability and continuity of existing relationships. If the relationship between the i-th and j-th product entity nodes was strong before, it may affect future changes;

[0127] After calculating changes in product relationship information, the next step is to update the weights of the product relationship edges based on these changes. The weights of relationship edges represent the importance or strength of the relationship between products and are typically used to measure the degree of connectivity or interaction frequency between products.

[0128] In the chemical park industry chain, the relationships between products are not static but change with time and demand. Changes in the production volume of a particular product may affect its supply relationship, dependency, or capacity scheduling with other products. Static product relationship graphs cannot accurately reflect the actual dynamic interactions between products in the industry chain. By using an evolving graph convolutional network model to dynamically update the product relationship graph, the direct impact of changes in product quantity on product relationships is considered. This allows product relationships to be updated in a timely manner based on factors such as demand and capacity fluctuations, thus reflecting the actual interactions between products in the industry chain. The impact of changes in product quantity on product relationships is very complex. For example, when the output of a product increases, it may cause changes in the demand for upstream or downstream products. However, this impact is usually nonlinear and affected by multiple factors. Traditional knowledge graph models may only provide static relationships between products, but cannot provide a dynamic view of how relationships adjust over time and changing trends. This makes it difficult to predict future changes in the industry chain, especially when facing demand fluctuations or production bottlenecks. By considering the impact of time step changes and product quantity changes on relationships, this method provides predictive capabilities for dynamic changes in the industry chain. The updates of edge weights and product relationships not only allow the graph to reflect changes between products in real time but also provide useful trend forecasts for decision makers.

[0129] S3. Based on the product reserve relationship knowledge graph, timestamps are introduced to update node definitions. The product reserve relationship knowledge graph is converted into a product time relationship knowledge graph using a dynamic temporal graph network algorithm. Repeated routes and products in the chemical park are merged to obtain the final product time relationship knowledge graph.

[0130] In S3, based on the product reserve relationship knowledge graph, timestamp update node definition is introduced, and the product reserve relationship knowledge graph is converted into a product time relationship knowledge graph using a dynamic temporal graph network algorithm. Repeated routes and products in the chemical park are merged to obtain the final product time relationship knowledge graph. The specific method steps are as follows:

[0131] S3.1. Introduce timestamps to update and define product entity nodes and product relationship edges:

[0132]

[0133] E” ij =(N i ,N j ,R ij ,w ij );

[0134] in, The i-th product entity node containing the timestamp after the update; E” ij is the product relationship edge between the i-th product entity node and the j-th product entity node after the update; is the node timestamp;

[0135] In this embodiment, the i-th product entity node containing a timestamp after the update additionally contains a timestamp Used to sort out the time sequence between product entity nodes; after updating, the product relationship edge E between the i-th product entity node and the j-th product entity node ij Removed forecast data and This is because the product time relationship knowledge graph does not need to consider the changes between product entities, but only expresses the broad relationship between products. Therefore, it does not need to consider the prediction data in the product reserve relationship knowledge graph;

[0136] S3.2. Use the dynamic temporal graph network algorithm to transform the product reserve relationship knowledge graph into the product time relationship knowledge graph;

[0137] In this embodiment, multiple production links and products often have strict dependencies and time constraints. For example, the production of ethylene needs to be carried out after the production of polyethylene, and the production of polyethylene relies on naphtha as a raw material. However, the product reserve relationship knowledge graph cannot well reflect the time dependency between these products and cannot reflect the dynamic changes of the production process. Especially when it involves complex dependencies between multiple products, timestamps are introduced and updated in the nodes, and the product reserve relationship is updated in the knowledge graph and converted into a product time relationship knowledge graph to reflect the production sequence and mutual dependencies between different products.

[0138] S3.3. Use the incremental hierarchical temporal memory model to adaptively merge repeated routes and product entity nodes in the chemical park to obtain the final product time relationship knowledge graph.

[0139] In S3.2, a dynamic temporal graph network algorithm is used to convert the product reserve relationship knowledge graph into a product time relationship knowledge graph. The specific method steps are as follows:

[0140] S3.2.1. Use graph neural networks to perform temporal embedding of each product entity node and product relationship edge:

[0141]

[0142] in, The i-th product entity node containing the timestamp after the update Temporal embedding of is the set of neighbor nodes of the i-th product entity node;

[0143]

[0144] in, is the temporal embedding of the product relationship edge between the i-th product entity node and the j-th product entity node; is the edge timestamp;

[0145] S3.2.2. Combine the temporal information of product entity nodes and product relationship edges to obtain the product temporal relationship knowledge graph:

[0146]

[0147] Among them, G2 is the product time relationship knowledge graph; The nth product entity node containing the timestamp after the update Temporal embedding of .

[0148] In S3.3, an incremental hierarchical temporal memory model is used to adaptively merge repeated routes and product entity nodes in the chemical park to obtain the final product temporal relationship knowledge graph. The specific steps are as follows:

[0149] S3.3.1. At each time step, based on the temporal embedding of each product entity node, calculate the cosine similarity between each product entity node and set the node similarity threshold δ to determine whether it can be merged:

[0150]

[0151] like If the i-th product entity node is similar to the j-th product entity node, they can be merged; otherwise, they cannot be merged.

[0152] in, is the cosine similarity between the i-th product entity node and the j-th product entity node; δ is the node similarity threshold;

[0153] S3.3.2. At each time step, based on the temporal embedding of each product relationship edge, calculate the cosine similarity of each product relationship edge and set the edge similarity threshold τ to determine whether it can be merged:

[0154]

[0155] like Then the product relationship edge Product relationship Similar ones can be merged, otherwise they cannot be merged;

[0156] in, Product relationship edge Product relationship The cosine similarity of ; τ is the edge similarity threshold; s is the product entity node index; l is the product entity node index; is the temporal embedding of the product relationship edge between the sth product entity node and the lth product entity node;

[0157] S3.3.3. Merge similar product entity nodes and product relationship edges to obtain the final product time relationship knowledge graph.

[0158] In this embodiment, the product time relationship knowledge graph is constructed by temporally embedding the product entity nodes and product relationship edges of the product reserve relationship knowledge graph, and then based on this temporal embedding information; by using graph neural networks and temporal embedding methods, we can capture the dynamic characteristics of product entities and relationship edges that change over time, which enables the product time relationship knowledge graph to reflect the impact of time evolution on product relationships; compared with the product reserve relationship knowledge graph, the product time relationship knowledge graph can consider the relationship between products that changes over time.

[0159] S4. Use a visual interface to display the product reserve relationship knowledge graph and the product time relationship knowledge graph, so that users can perform query operations according to their needs.

[0160] Example 2:

[0161] This embodiment provides a chemical park industry chain data knowledge graph construction system based on big data, including a memory, a processor, and a computer program stored in the memory and runnable on the processor. The processor executes the computer program to implement any one of the above-mentioned chemical park industry chain data knowledge graph construction methods based on big data.

[0162] The basic principles, main features, and advantages of the present invention are shown and described above. It should be understood by those skilled in the art that the present invention is not limited to the above-described embodiments. The above-described embodiments and descriptions are merely preferred examples of the present invention and are not intended to limit the present invention. Various changes and modifications may be made to the present invention without departing from the spirit and scope of the present invention, and such changes and modifications fall within the scope of the invention claimed.

Claims

1. A method for constructing a chemical park industry chain data knowledge graph based on big data, characterized in that: The following steps are involved: S1. Obtain chemical park industry chain data from the industry database and use natural language processing technology to extract industry chain product entity information and product relationship information; S2. Define nodes and edges of the knowledge graph based on product entity information and product relationship information. Use the evolutionary graph convolutional network model to predict the relationship between the number of adjacent nodes and place it on the edges to build a product reserve relationship knowledge graph. The evolutionary graph convolutional network model is implemented based on a graph convolutional network fused with a multi-layer perceptron model. It is used to consider the changes in nodes and edges over time to handle the changes in graph structure over time, and to predict the impact of changes in the number of nodes on edges. The specific steps of the method in S2 are as follows: S2.

1. Define product entity nodes based on product entity information; S2.

2. Define product relationship edges based on product relationship information; S2.

3. Use the Evolved Graph Convolutional Network model to predict the production capacity relationship caused by the change in the quantity of adjacent chemical products with production up-down relationships and place it on the corresponding product relationship edge; S2.

4. Construct a product reserve relationship knowledge graph based on product entity nodes and product relationship edges; In S2.3, the evolutionary graph convolutional network model is used to predict the production capacity relationship caused by the change in the quantity of adjacent chemical products with production up-down relationships and place it in the corresponding product relationship edge. The specific method steps are as follows: S2.3.1, set the time step to , each product entity node at each time step With corresponding quantity ; S2.3.

2. Based on the graph convolutional network model, aggregate the feature information of neighboring nodes and calculate the new feature representation of each product entity node: ； in, is the time step No. Features of each product entity node except name and quantity; is the index of the neighbor node; For the The neighbor node set of a product entity node; is the adjacency matrix; For the The degree of each product entity node; Neighbor nodes characteristics other than name and quantity; is the weight matrix; is the Sigmoid nonlinear activation function; S2.3.

3. Time step based No. The features of product entity nodes other than name and quantity are integrated into the multi-layer perceptron model to predict the time step The quantity of the product entity changes: ； in, is the time step No. Changes in the number of products per product entity node; is the time step No. Features of each product entity node except name and quantity; is the time step No. Features of each product entity node except name and quantity; is the node connection strength weight; Operates for multi-layer perceptron models; And similarly, we can get the time step-based No. Changes in the number of products per product entity node ; S2.3.4, based on time step No. The product entity node and the Changes in the number of products per product entity node and , analyze the Chemical products and adjacent The capacity relationship changes of each chemical product are placed on the product relationship edge; S3. Based on the product reserve relationship knowledge graph, timestamps are introduced to update node definitions. The product reserve relationship knowledge graph is converted into a product time relationship knowledge graph using a dynamic temporal graph network algorithm. Repeated routes and products in the chemical park are merged to obtain the final product time relationship knowledge graph. S4. Use a visual interface to display the product reserve relationship knowledge graph and the product time relationship knowledge graph, so that users can perform query operations according to their needs.

2. The method for constructing a chemical park industry chain data knowledge graph based on big data according to claim 1 is characterized in that: In S1, the product entity information includes the Chinese and English name, quantity, molecular weight, molecular formula, structural formula, production capacity, appearance, physical properties, specifications, process information, market price and supplier of each product; Product relationship information includes raw material supply relationships, production relationships, consumption relationships, substitution relationships, and transportation relationships.

3. The method for constructing a chemical park industry chain data knowledge graph based on big data according to claim 2, characterized in that: In S2.1, the product entity node is defined based on the product entity information. The specific method is as follows: ； in, Index for product entities; For the Product entity nodes; For the The name of the product entity; For the The number of product entities; For the Characteristics of a product entity other than name and quantity; In S2.2, product relationship edges are defined based on product relationship information. The specific method is as follows: ； in, Index for product entities; For the Product entity nodes; For the The product entity node and the Product relationship edges of product entity nodes; Product relationship information; is the product relationship edge weight; Product relationship change information.

4. The method for constructing a chemical park industry chain data knowledge graph based on big data according to claim 3 is characterized by: In S2.3.4, based on the time step No. The product entity node and the Changes in the number of products per product entity node and , analyze the Chemical products and adjacent The capacity relationship changes of chemical products are placed on the product relationship edge. The specific method is as follows: S2.3.4.

1. Based on product relationship information Combined time steps No. The product entity node and the Changes in the number of products per product entity node and , calculate the time step Product relationship information: ； in, is the time step Product relationship information, which is equivalent to product relationship information ; Time step Changes in product relationship information; For the Product entity weight coefficient; For the Product entity weight coefficient; is the product relationship weight coefficient; is the smoothing term; S2.3.4.

2. Set the time step Update the product relationship edge weight of the product relationship edge when the product relationship information changes: ； in, is the time step The product relationship edge weight is equivalent to the product relationship edge weight ; is the time step The product relationship edge weight; is the weight coefficient of the product relationship edge weight; is the weight coefficient of product relationship information change; In S2.4, a product reserve relationship knowledge graph is constructed based on product entity nodes and product relationship edges, as follows: ； ； in, Reserve relational knowledge graph for products; is the total number of product entity nodes; After adding the forecast data, The product entity node and the Product relationship edges of product entity nodes.

5. The method for constructing a chemical park industry chain data knowledge graph based on big data according to claim 4 is characterized in that: In S3, based on the product reserve relationship knowledge graph, timestamp update node definition is introduced, and the product reserve relationship knowledge graph is converted into a product time relationship knowledge graph using a dynamic temporal graph network algorithm. Repeated routes and products in the chemical park are merged to obtain the final product time relationship knowledge graph. The specific method steps are as follows: S3.

1. Introduce timestamps to update and define product entity nodes and product relationship edges: ； ； in, The updated Product entity nodes; After the update The product entity node and the Product relationship edges of product entity nodes; is the node timestamp; S3.

2. Use the dynamic temporal graph network algorithm to transform the product reserve relationship knowledge graph into the product time relationship knowledge graph; S3.

3. Use the incremental hierarchical temporal memory model to adaptively merge repeated routes and product entity nodes in the chemical park to obtain the final product time relationship knowledge graph.

6. The method for constructing a chemical park industry chain data knowledge graph based on big data according to claim 5 is characterized by: In S3.2, a dynamic temporal graph network algorithm is used to convert the product reserve relationship knowledge graph into a product time relationship knowledge graph. The specific method steps are as follows: S3.2.

1. Use graph neural networks to perform temporal embedding of each product entity node and product relationship edge: ； in, The updated Product entity nodes Temporal embedding of For the The neighbor node set of a product entity node; ； in, For the The product entity node and the Temporal embedding of product entity nodes and product relationship edges; is the edge timestamp; S3.2.

2. Combine the temporal information of product entity nodes and product relationship edges to obtain the product temporal relationship knowledge graph: ； in, It is the product time relationship knowledge graph; The updated Product entity nodes Temporal embedding of .

7. The method for constructing a chemical park industry chain data knowledge graph based on big data according to claim 6, characterized in that: In S3.3, an incremental hierarchical temporal memory model is used to adaptively merge repeated routes and product entity nodes in the chemical park to obtain the final product temporal relationship knowledge graph. The specific steps are as follows: S3.3.

1. At each time step, based on the temporal embedding of each product entity node, calculate the cosine similarity between each product entity node and set the node similarity threshold Determine whether it can be merged: ； like , then The product entity node and the If the product entity nodes are similar, they can be merged; otherwise, they cannot be merged; in, For the The product entity node and the Cosine similarity of product entity nodes; is the node similarity threshold; S3.3.

2. At each time step, based on the temporal embedding of each product relationship edge, calculate the cosine similarity of each product relationship edge and set the edge similarity threshold Determine whether it can be merged: ； like , then the product relationship edge Product relationship Similar ones can be merged, otherwise they cannot be merged; in, Product relationship edge Product relationship The cosine similarity of is the edge similarity threshold; Index of product entity node; Index of product entity node; The sth product entity node and the Temporal embedding of product entity nodes and product relationship edges; S3.3.

3. Merge similar product entity nodes and product relationship edges to obtain the final product time relationship knowledge graph.

8. A chemical park industry chain data knowledge graph construction system based on big data, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: The processor executes a computer program to implement the method for constructing a chemical park industry chain data knowledge graph based on big data as described in any one of claims 1 to 7.

Images