A method and system for constructing an industrial chain knowledge graph based on deep learning

Abstract

The present invention discloses a method and system for constructing an industrial chain knowledge graph based on deep learning, as well as a storage medium and electronic device. The method includes: deploying a cloud data acquisition program to obtain industrial chain data from multiple data sources and preprocessing it; classifying and screening the preprocessed data; filtering and labeling entity words using the ELECTRA model in combination with the BM‑25F score; constructing a graph structure, and using the GCNE model for entity recognition and relationship extraction; storing the obtained triples in a graph database to construct a knowledge graph; when a user searches, creating a suitable index according to the query requirements of the knowledge graph, matching the knowledge graph data, and pushing relevant data to the user. This method improves the efficiency, accuracy and completeness of constructing the industrial chain knowledge graph, can assist in industrial chain analysis, prediction and decision-making, has good scalability, and is applicable to industrial chains of different industries.

Description

Technical Field

[0001] The present invention relates to the field of knowledge graph technology, and in particular to a method and system for constructing an industrial chain knowledge graph based on deep learning. Background Art

[0002] With the rapid development of information technology, knowledge graphs are increasingly being used in various fields, particularly in industrial chain analysis. An industrial chain graph is a visualization tool for structured data systems, built using artificial intelligence algorithms and other technologies. It is used to describe the various links within an industry and their interrelationships. Industrial chain knowledge graphs play a significant role. In corporate strategic planning, they can help companies clarify their positioning and competitive landscape, optimize supply chains, expand their businesses, and assist in industrial planning. In academic research, they can provide analytical tools and perspectives for industrial economics, regional economics, and technological innovation research.

[0003] The industry chain knowledge graph divides the industry chain into distinct links or nodes. For example, the electronics industry chain can be divided into chip design, wafer fabrication, packaging and testing, component production, electronic product assembly, sales and service, and end-user segments. Chip design companies are responsible for developing chip functions and architecture; wafer fabrication companies translate designs into actual chip wafers; packaging and testing companies package and perform quality control on chips; component manufacturers produce the various components needed for electronic devices; electronic product assembly companies assemble chips and components into complete electronic products; sales and service encompass product promotion, sales, and after-sales service; and end-users are individuals or businesses that use electronic products. These various links or nodes are interconnected, forming a complete industry chain. The industry chain graph clearly illustrates the relationships and interactions between each link. In this way, the industry chain graph clearly demonstrates the relationships between upstream and downstream sectors of the industry chain, as well as the degree of dependency and mutual influence between different links.

[0004] However, existing technologies involve multiple steps in constructing an industrial chain knowledge graph, requiring significant computational resources and time. Furthermore, traditional methods have limited accuracy in data collection, data processing, entity recognition, and relationship extraction, and deep learning models also suffer from overfitting and misunderstanding of specialized terminology. Traditional industrial chain knowledge graphs are inefficient and error-prone, failing to meet practical needs. This invention aims to address these issues and construct a superior industrial chain knowledge graph.

[0005] To this end, the present invention provides a method and system for constructing an industrial chain knowledge graph based on deep learning. Summary of the Invention

[0006] In order to make up for the shortcomings of the existing technology, the present invention provides an industrial chain knowledge graph construction method based on deep learning, which can improve the efficiency, accuracy and completeness of industrial chain knowledge graph construction, assist in industrial chain analysis, prediction and decision-making, has good scalability, and is suitable for related industrial chains in different industries.

[0007] To achieve the above objectives, in a first aspect, an embodiment of the present invention provides a method for constructing an industrial chain knowledge graph based on deep learning, characterized in that it includes the following steps:

[0008] S1. Deploy a cloud data collection program, wherein the cloud data collection program is configured to obtain industrial chain data from multiple data sources and clean and pre-process the data;

[0009] S2. Classify and filter the preprocessed data. For structured data, use the random forest algorithm for classification and filtering. For unstructured data, use word embedding combined with a deep learning model to classify and filter the stored data to obtain text data related to the industry chain.

[0010] S3. Filter the text data for entity words. Use the ELECTRA model as a classifier and combine it with the BM-25F score to filter out important entity words, remove non-synonymous words, obtain entity words, and annotate them.

[0011] S4. Build a graph structure representation, create entity nodes, create and initialize edges, and use the GCNE model for entity recognition and relationship extraction;

[0012] S5. Based on the results of entity recognition and relationship extraction, the entity, attribute, and relationship triples required for the knowledge graph are obtained, and the triples are stored in the graph database to construct the industry chain knowledge graph;

[0013] S6. When users search for industrial chain information, create appropriate indexes based on the query requirements of the knowledge graph, match the knowledge graph data, and push relevant data to users.

[0014] In one embodiment, for step S1, rdd conversion is used for unstructured data in the collected data, and DataFrame conversion is used for structured data. After the data is aggregated using an aggregation function, the processed data is saved to cloud storage.

[0015] In one embodiment, for step S3, the BM-25F score of each field is calculated, the text embedding of each field is generated using the ELECTRA model, and other features that are helpful in identifying entity words are extracted; a deep learning model is constructed, the BM-25F score, text embedding and other features are used as input, the Transformer model is used for feature fusion and processing, and the probability of whether the output word is an important entity word is constructed.

[0016] In one embodiment, for step S3, entity word tagging specifically includes: combining the evaluation of industry chain experts, tagging the extracted entity words into six categories: company, expert, industry, product, technology, and application, and automatically tagging them in BIOES format.

[0017] In one embodiment, for step S4, constructing a graph structure representation specifically includes identifying entities in the text based on word segmentation results and industry chain domain knowledge, creating a node for each entity, and assigning an initial feature vector representation to each entity node. The initial feature vector is created based on the basic attribute information of the entity, and the attribute information is extracted from the text or obtained through other external data sources. According to the relationship description between the entities in the text, edges connecting the entity nodes are created.

[0018] In one embodiment, step S4 specifically includes: inputting the constructed graph structure data into the GCNE model, determining the set of neighbor nodes at each node according to the structure of the graph, and for each neighbor node, calculating the message from the neighbor node to the current node, wherein the message calculation is based on the current feature vector of the neighbor node and the features of the edges connecting them, and then aggregating the messages from all neighbor nodes; using the aggregated neighbor node information and edge information to update the state of the current node; using a linear layer to map the updated node feature vector to the entity label space; constructing a conditional random field (CRF) model, whose input is the representation of the node in the entity label space output by the linear layer, using the CRF model to predict the entity label of each node, selecting all possible node representations from the graph structure, and splicing them together to form the representation of the entity pair; then mapping the representation of the entity pair to the relationship label space, and predicting the relationship label between the entity pairs through the Softmax function.

[0019] In a second aspect, the present invention provides an industrial chain knowledge graph construction system based on deep learning, characterized by comprising:

[0020] Cloud data acquisition device, used to deploy cloud data acquisition programs, obtain industry chain data from multiple data sources, and clean and pre-process the data;

[0021] Data classification and screening device, used to classify and screen pre-processed data. For structured data, it uses the random forest algorithm for classification and screening. For unstructured data, it uses word embedding combined with a deep learning model to classify and screen the stored data to obtain text data related to the industrial chain.

[0022] The entity word processing device is used to filter entity words in text data, using the ELECTRA model as a classifier and combining it with the BM-25F score to screen out important entity words, remove non-word words, obtain entity words, and annotate them;

[0023] Graph structure construction and analysis device, used to construct graph structure representation, create entity nodes, and create and initialize edges, using the GCNE (Graph Convolutional Networks with Edge Features) model for entity recognition (NER) and relationship extraction (RE);

[0024] A knowledge graph construction device is used to obtain the entity, attribute and relationship triples required for the knowledge graph based on the results of entity recognition and relationship extraction, and store the triples in a graph database to construct an industrial chain knowledge graph;

[0025] The data push device is used to match the knowledge graph data according to the keyword fields and the industry to which the user's company belongs when the user searches for industrial chain information, and push the most relevant data to the user.

[0026] In a third aspect, an embodiment of the present invention further provides an electronic device, comprising a processor and a memory, wherein the memory stores computer-executable instructions that can be executed by the processor, and the processor executes the computer-executable instructions to implement any one of the methods provided in the first aspect.

[0027] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer-executable instructions. When the computer-executable instructions are called and executed by a processor, the computer-executable instructions prompt the processor to implement any one of the methods provided in the first aspect.

[0028] In a fifth aspect, an embodiment of the present invention further provides a computer program product, comprising a computer program stored on a computer-readable storage medium, and when the computer program is executed by a processor, implementing any one of the methods provided in the first aspect.

[0029] This paper proposes a method for constructing an industrial chain knowledge graph based on deep learning, including: deploying a cloud data acquisition program to obtain and preprocess industrial chain data from multiple data sources; classifying and screening the preprocessed data, using a random forest algorithm for structured data and word embedding combined with a deep learning model for unstructured data; filtering and annotating entity words using the ELECTRA model combined with BM-25F scoring; constructing a graph structure and using the GCNE model for entity recognition and relationship extraction; storing the resulting triples in a graph database to construct a knowledge graph; and matching and pushing data by keyword and industry when users search. This method improves the efficiency, accuracy, and completeness of constructing industrial chain knowledge graphs, can assist in industrial chain analysis, prediction, and decision-making, has good scalability, and is applicable to related industrial chains in different industries.

[0030] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] The above and other objects, features, and advantages of the present invention will become more apparent through a more detailed description of the embodiments of the present invention in conjunction with the accompanying drawings. The accompanying drawings are provided to provide a further understanding of the embodiments of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and are not intended to limit the present invention. In the drawings, the same reference numerals generally represent the same components or steps.

[0032] Figure 1 It is a flowchart of a method provided by an exemplary embodiment of the present invention.

[0033] Figure 2 It is a schematic structural diagram of a device provided by an exemplary embodiment of the present invention. DETAILED DESCRIPTION

[0034] Below, the exemplary embodiments according to the present invention will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments of the present invention, and it should be understood that the present invention is not limited to the exemplary embodiments described herein.

[0035] It should be noted that the relative arrangement of components and steps, the numerical expressions and numerical values ​​set forth in these embodiments do not limit the scope of the present invention unless specifically stated otherwise.

[0036] Those skilled in the art will understand that the terms "first" and "second" in the embodiments of the present invention are only used to distinguish different steps, devices or modules, and neither represent any specific technical meaning nor indicate the necessary logical order between them.

[0037] It should also be understood that, in the embodiments of the present invention, “a plurality of” may refer to two or more than two, and “at least one” may refer to one, two or more than two.

[0038] It should also be understood that any component, data or structure mentioned in the embodiments of the present invention can generally be understood as one or more, unless explicitly limited or otherwise indicated in the context.

[0039] To facilitate understanding of this embodiment, we first introduce in detail a method for constructing an industry chain knowledge graph based on deep learning disclosed in an embodiment of the present invention, as shown in the attached figure. Figure 1 As shown in FIG, a method for constructing an industrial chain knowledge graph based on deep learning includes the following steps:

[0040] S1. Deploy a cloud data acquisition program, which is configured to obtain industrial chain data from multiple data sources, clean and pre-process the data, and save the processed data to cloud storage.

[0041] In this embodiment, before classifying the industrial chain, it is necessary to collect text data related to the industrial chain, including corporate reports, industry research reports, news articles, technical documents, etc. This text data should cover all aspects of the industrial chain, such as raw material supply, production and processing, sales and distribution, and technology research and development. The cloud data collection tool can be implemented based on the Python Scrapy framework, for example.

[0042] In the above step S1, rdd conversion is used for the unstructured data in the collected data, and DataFrame data structure is used for conversion. After the data is aggregated using aggregation functions (such as groupby, reduce, and aggregate functions), the processed data is saved to cloud storage.

[0043] When processing collected data, for unstructured data, first load it into an RDD (Resilient Distributed Dataset), then perform transformation operations such as word splitting on text data, and then use aggregation functions for aggregation. For structured data, load it into a DataFrame data structure, perform transformation operations (such as selecting columns, adding new columns, etc.), and then use aggregation functions for grouping and aggregation. After determining the path and format of cloud storage (such as the path of services such as Amazon S3 and Google CloudStorage and data formats such as CSV and Parquet), save the processed RDD data of unstructured data as a text file, and save the processed DataFrame of structured data as a file in a specified format (such as CSV) to cloud storage. In actual operation, adjustments and optimizations can be made based on data characteristics and business needs.

[0044] Furthermore, the data is preprocessed to remove noise information in the text, such as redundant punctuation, special characters, and numbers that have little impact on entity recognition and relation extraction. For example, multiple consecutive spaces are replaced with a single space, and some irrelevant advertising information or web page tags are deleted.

[0045] Furthermore, the data is segmented: the cleaned text is segmented using appropriate segmentation tools. For Chinese text, tools such as jieba segmentation can be used; for English text, the segmenter in NLTK can be used. At the same time, according to the characteristics of the professional terms of the industrial chain, a custom dictionary is built to segment some specific industry terms as a whole to avoid incorrect segmentation. For example, terms such as "industrial chain", "supply chain", and "raw material supplier" should be identified as a whole. Considering the characteristics of the industrial chain data text, some professional terms need to be specially processed. For example, if there are some abbreviations or compound words for a specific industry, they can be processed as a whole to avoid incorrect segmentation. You can build a custom dictionary, add these professional terms to the dictionary, use the segmentation tool to identify them, and save the processed data to the target location.

[0046] S2. Classify and filter the preprocessed data. For structured data, use the random forest algorithm for classification and filtering. For unstructured data, use word embedding combined with a deep learning model to classify and filter the stored data to obtain text data related to the industry chain.

[0047] In the embodiment of the present application, for structured data: select an appropriate traditional machine learning algorithm, such as random forest or XGBoost, based on the data characteristics and task objectives, and divide the data set into a training set and a test set (for example, in a ratio of 7:3 or 8:2). Use the training set to train the selected model. For random forest, some key parameters need to be set, such as the number of trees and maximum depth; for XGBoost, parameters such as the learning rate, maximum tree depth, and minimum leaf node weight need to be adjusted to optimize model performance. In the industrial chain data, it accurately identifies and distinguishes different types of structured data, such as enterprise data of different scales, industries, and development stages, as well as product data of different quality levels and market positioning, and extracts valuable structured data information. After classification and screening by the random forest algorithm, the data quality and availability are improved, making the retained data more representative and accurate, providing a more reliable foundation for subsequent analysis and modeling; on the other hand, the random forest algorithm can automatically mine hidden patterns and relationships in structured data, such as discovering the relationship between enterprise characteristics and enterprise development, product characteristics and market demand, which helps to deeply understand the operation mechanism of the industrial chain. At the same time, by screening key data, it reduces the data dimension and complexity, reduces the data volume, reduces the difficulty of subsequent processing and analysis, and improves computing efficiency.

[0048] For unstructured data, such as text data, word embeddings combined with deep learning models (such as CNNs and LSTMs) or pre-trained language models (such as BERT) can be used to perform preliminary text classification and screening on stored data. Word embedding techniques such as Word2Vec are used to map words in a text to a low-dimensional vector space. When training the word embedding model, appropriate parameters, such as vector dimension, window size, and minimum word frequency, should be selected based on the scale and characteristics of the text data. Based on the task requirements, an appropriate deep learning model combined with word embeddings should be selected for text classification and screening. For processing shorter texts focusing on local features, a CNN (convolutional neural network) can be used. For processing longer texts that need to consider sequential information, an LSTM (long short-term memory network) can be used. Pre-trained language models such as BERT, which have powerful language understanding capabilities, can also be used to fully utilize unstructured data. Unstructured text data contains a wealth of industry chain information. Through effective classification and screening using the above methods, this information can be mined and utilized to supplement and improve the industry chain knowledge graph.

[0049] The industrial chain data set includes the following features: enterprise-related features, such as enterprise scale (for example, represented by the number of employees, asset size, etc.), years of establishment, industry category, geographical location, etc. Product-related features, such as product type, product quality level, market share, sales price range, etc. Technology-related features, such as technological advancement indicators (such as the number of patents, the proportion of R&D investment, etc.), technology application fields, etc. Supply relationship characteristics, such as the number of major suppliers, supply stability indicators (such as the number of supply interruptions, supply lead time fluctuations, etc.). Sales channel characteristics, such as the proportion of online sales, the number of offline dealers, the export ratio, etc. Classification prediction results, that is, predicting the category to which the new industrial chain data point belongs. For example, enterprises can be divided into different development stage categories (start-up, growth, maturity, decline), or products can be divided into high-demand, medium-demand, low-demand categories, etc.

[0050] S3. Filter the text data for entity words. Use the ELECTRA model as a classifier and combine it with the BM-25F score to filter out important entity words, remove non-synonymous words, obtain entity words, and annotate them.

[0051] Among them, the BM-25F (Best Match 25F) is an information retrieval algorithm, mainly used for text retrieval and ranking tasks. When calculating the relevance between a document and the query content, BM-25F will assign different weights according to the characteristics of different fields, and comprehensively consider factors such as word frequency, document length, and inverse document frequency. In an embodiment of the present application, for step S3, the BM-25F score of each field is calculated, and the ELECTRA (Efficiently Learning an Encoder that Classifies Token Replacements Accurately) model is used to generate a text embedding for each field, and other features that help identify entity words are extracted; a deep learning model is constructed, and the BM-25F score, text embedding, and other features are used as input. The Transformer model is used for feature fusion and processing, and the output is the probability of whether the word is an important entity word. This algorithm is used to further screen out important entity words and reduce the influence of non-word vocabulary. BM-25F can more accurately evaluate the relevance of a document to a specific query, thereby playing an important role in tasks such as text classification and screening of important entity words.

[0052] Specifically, an optional method for the above filtering is, for example, a pre-labeled dataset for the industrial chain, which contains the title, body, and summary of the document, as well as the important entity words in each document; for example, data = [{"title":"Automobile Company A Develops New Technology","body":"Automobile Company A announced the development of a new technology to improve production efficiency.","summary":"New Technology Improves Production Efficiency","entities":["Automobile Company A","New Technology"]};

[0053] Calculate the BM-25F score for each field (title, body, abstract); use the ELECTRA model to generate text embeddings for each field and extract other features that help identify entity words, such as word frequency and word position. Build a deep learning model where the input layer takes the BM-25F score, text embedding, and other features as input, the middle layer uses the Transformer model for feature fusion and processing, and the output layer outputs the probability of whether the word is an important entity word. Through the above steps, the BM-25F score and the ELECTRA model are combined to build a deep learning classifier for screening important entity words. Leveraging the BM-25F's ability to score different fields and the ELECTRA model's powerful semantic understanding capabilities can effectively improve the accuracy and efficiency of entity word screening.

[0054] Further, for step S3, the entity word annotation specifically includes: combining the evaluation of industry experts in the industrial chain, annotating the extracted entity words into six categories: company, expert, industry, product, technology, and application. BIOES is a annotation method for named entity recognition (NER). BIOES stands for Begin (entity start), Inside (entity inside), Outside (non-entity part), End (entity end), and Single (single entity). The present invention also uses the BIOES format for automatic annotation. The text after word segmentation is tagged with parts of speech to better understand the text structure and semantics. An automatic annotation program can be written in a programming language (such as Python). Read the extracted entity word list and the category information to which they belong, wherein the category information can be predetermined by manual judgment or reference to expert opinions. Then, each entity word is annotated according to the BIOES annotation rules. The program loops through each word in the entity word and annotates it accordingly according to its position and category.

[0055] Furthermore, you can use the part-of-speech tagger in NLTK or some Chinese part-of-speech tagging tools (such as HanLP) to implement BIOES tagging. By properly configuring the toolkit, it can be adapted to the specific requirements of entity word tagging in related industries, such as setting the correct category labels and tagging rules.

[0056] S4. Build a graph structure representation, create entity nodes, and create and initialize edges. Use the GCNE (Graph Convolutional Networks with Edge Features) model for entity recognition (NER) and relation extraction (RE).

[0057] In an embodiment of the present application, step S4 specifically includes: inputting the constructed graph structure data into the GCNE model, and at each node, determining its neighbor node set according to the structure of the graph, and for each neighbor node, calculating the message transmitted from the neighbor node to the current node, wherein the message calculation is based on the current feature vector of the neighbor node and the features of the edges connecting them, and then aggregating the messages from all neighbor nodes; using the aggregated neighbor node information and edge information to update the state of the current node; using the linear layer to map the updated node feature vector to the entity label space; constructing a conditional random field (CRF) model, whose input is the representation of the node in the entity label space output by the linear layer, using the CRF model to predict the entity label of each node, selecting all possible node representations from the graph structure and splicing them together to form an entity pair representation; then mapping the entity pair representation to the relationship label space, and predicting the relationship label between the entity pairs through the Softmax function.

[0058] The following are the detailed implementation steps for using the GCNE model to perform entity recognition and relationship extraction on industrial chain text data to construct an industrial chain knowledge graph: S401. Build a graph structure representation. Based on the word segmentation results and industrial chain domain knowledge, identify entities in the text and create a node for each entity. Entities can include industry chain-related enterprises, products, technologies, raw materials, markets, regulations, and so on. For example, from the text "A metal processing enterprise uses advanced smelting technology to produce high-quality metal products, and its products are mainly sold to the domestic market," entities such as "metal processing enterprise," "smelting technology," "metal products," and "domestic market" can be identified and corresponding nodes created. Each entity node is assigned an initial feature vector representation. This initial feature vector is based on some basic attribute information of the entity. For example, for industry chain-related enterprise entities, this may include encodings of information such as the enterprise name, location, enterprise size, founding date, and industry; for industry chain-related product entities, this may include encodings of information such as the product name, product category, product function, applicable field, and quality standards; and for industry chain-related technology entities, this may include encodings of information such as the technology name, field of technology, development time, and application results. This attribute information can be extracted from the text or obtained from other external data sources. Based on the relationship descriptions between entities in the text, edges connecting entity nodes are created. For example, in the above text, there is an "adoption" relationship between "metal processing enterprises" and "smelting technology," a "production" relationship between "metal enterprises" and "metal products," and a "sales" relationship between "metal products" and "domestic market." Therefore, corresponding edges can be created and their types labeled as "adoption," "production," "sales," etc. The feature vector of an edge can include information encoding the strength, time span, direction, and legality of the relationship. In the initial stage, if this information is unclear in the text, default values ​​can be assigned or reasonable guesses can be made based on domain knowledge. For example, for the "production" relationship, where production is a core business relationship, the relationship strength can be set to a high value, and the time span can be evaluated based on the company's production cycle or the product's update cycle.

[0059] S402. Apply the GCNE model for entity recognition and relationship extraction. The constructed graph structure data is input into the GCNE model. At each node, a set of neighboring nodes is determined based on the graph structure. For each neighboring node, the message transmitted from the neighboring node to the current node is calculated. The message calculation is based on the neighboring node's current feature vector and the features of the edges connecting them. For example, if the edge features contain information about the strength of the relationship, the message calculation can be performed by multiplying the neighboring node's feature vector by the relationship strength weight. The messages from all neighboring nodes are then aggregated. The aggregation operation can be performed in various ways, such as summation, averaging, and weighted summation. For example, weighted summation can assign different weights based on the closeness of the connection between the neighboring node and the current node (such as edge weights or other relevant metrics), so that more important neighboring nodes have a greater impact on the aggregation results. The aggregated neighboring node information and edge information are used to update the current node's state. The update method can use a nonlinear function, ReLU, to process the fused information and then perform a weighted sum with the original feature vector of the current node to obtain an updated node feature vector. A linear layer is used to map the updated node feature vector to the entity label space. For example, if the entity label space includes labels for related enterprises, products, technologies, and raw materials in the industry chain, the updated node feature vectors are mapped to this space through a linear layer, resulting in a representation of each node in the entity label space. For CRF entity label prediction, a conditional random field (CRF) model is constructed, with the node representation in the entity label space output by the linear layer as input. The CRF model defines a transition probability matrix between adjacent labels, which reflects the likelihood of transitions between different entity labels. For example, an enterprise entity label is more likely to be followed by a partner entity label or a product entity label, and less likely to be directly followed by a technical detail entity label. The CRF model is used to predict the entity label for each node. The prediction process considers not only the node's own representation in the entity label space, but also the labels of neighboring nodes and the transition probabilities between them. By maximizing the label probability of the entire sequence (based on the CRF energy function or probability calculation formula), the label assignment for the entire sequence is optimized, making the label assignment more reasonable and logical. In the graph structure, the node representations are concatenated to form entity pair representations. These entity pair representations are then mapped to the relationship label space, and the relationship labels between the entity pairs are predicted using the Softmax function. For example, for the pair of entities "metal processing enterprise" and "smelting technology", their node representations are concatenated and mapped to the relationship label space, and the relationship between them is predicted to be an "adoption" relationship.

[0060] S5. Based on the results of entity recognition and relationship extraction, the entity, attribute, and relationship triples required for the knowledge graph are obtained, and the triples are stored in the graph database to construct the industry chain knowledge graph;

[0061] In an embodiment of the present application, entities and relationships are stored in a graph database, and entity and relationship information is stored in the graph database based on the results of entity recognition and relationship extraction. According to the aforementioned method, nodes are created in the graph database, and their attributes are set. For example, "metal processing enterprise" is stored as a node, and its attributes include the name of the enterprise related to the industrial chain, the region where it is located, the size of the enterprise, the time of establishment, the industry to which it belongs, etc.; the "adoption" relationship is stored as an edge, and its attributes include the relationship strength, time span, direction, etc. If relevant entities and relationships already exist in the graph database, they can be updated according to the new recognition and extraction results.

[0062] S6. When users search for industrial chain information, create appropriate indexes based on the query requirements of the knowledge graph, match the knowledge graph data, and push relevant data to users.

[0063] In the embodiment of the present application, a suitable visualization tool, such as Cytoscape, Gephi, etc., is selected to display the knowledge graph in a graphical manner. Through the visualization tool, the layout of the knowledge graph can be adjusted, the color of the nodes and edges can be set, the size can be adjusted, etc., to highlight important entities. For example, the enterprise node can be set to different sizes according to its size, and the relationship edge can be set to different colors according to its strength. Through the visualization display, the distribution of entities and relationships in the industrial chain can be more intuitively understood.

[0064] Provide convenience for further analysis. The present invention can provide corresponding applications according to the application requirements of the industrial chain data text. For example, if the purpose is to provide cooperation suggestions for enterprises, an enterprise cooperation suggestion system can be provided to recommend potential cooperation partners to enterprises by querying the industrial chain-related enterprise entities and relationships in the knowledge graph. If the purpose is to analyze the structure and dynamic changes of the industrial chain, an industrial chain analysis system can be provided to monitor and analyze the dynamic changes of entities and relationships in the knowledge graph, and provide a report on the structure and dynamic changes of the industrial chain. Create appropriate indexes according to the query requirements of the knowledge graph. For example, if you often need to query enterprises in a certain area, you can create an index on the regional attributes of the enterprise node to improve query efficiency.

[0065] Secondly, as attached Figure 2 As shown, an embodiment of the present invention further provides an industry chain knowledge graph construction system 200 based on deep learning, comprising: a cloud data acquisition device 201 for deploying a cloud data acquisition program, acquiring industry chain data from multiple data sources, and cleaning and preprocessing the data;

[0066] Data classification and screening device 202 is used to classify and screen the pre-processed data. For structured data, it uses the random forest algorithm for classification and screening. For unstructured data, it uses word embedding combined with a deep learning model to classify and screen the stored data to obtain text data related to the industrial chain.

[0067] Entity word processing device 203 is used to filter entity words from text data, use the ELECTRA model as a classifier, and combine the BM-25F score to screen out important entity words, remove non-word words, obtain entity words, and mark them;

[0068] Graph structure construction and analysis device 204, used to construct graph structure representation, create entity nodes, and create and initialize edges, using the GCNE (Graph Convolutional Networks with Edge Features) model for entity recognition (NER) and relationship extraction (RE);

[0069] The knowledge graph construction device 205 is used to obtain the entity, attribute and relationship triples required for the knowledge graph based on the results of entity recognition and relationship extraction, and store the triples in the graph database to construct the industry chain knowledge graph;

[0070] The data push device 206 is used to match the knowledge graph data according to the keyword field and the industry to which the user's company belongs when the user searches for industrial chain information, and push the most relevant data to the user.

[0071] In a third aspect, an embodiment of the present invention further provides an electronic device, comprising a processor and a memory, wherein the memory stores computer-executable instructions that can be executed by the processor, and the processor executes the computer-executable instructions to implement any one of the methods provided in the first aspect.

[0072] In a fourth aspect, the present invention provides a data processing system based on a knowledge graph, which includes a memory, a processor, and a computer program stored in the memory and runnable on the processor, wherein the processor executes the computer program and implements the data processing method based on the knowledge graph as described above.

[0073] In addition to the above-mentioned methods and devices, the embodiments of this document may also be a computer program product, which includes computer program instructions, which, when executed by a processor, enable the processor to perform the steps of the methods according to various embodiments of this document described in the above-mentioned "Exemplary Methods" section of this specification.

[0074] The basic principles of the present disclosure have been described above in conjunction with specific embodiments. However, it should be noted that the advantages, strengths, and effects mentioned in this disclosure are merely illustrative and not restrictive, and should not be construed as necessarily possessed by each embodiment of the present disclosure. Furthermore, the specific details disclosed above are provided for illustrative purposes and to facilitate understanding, rather than as limitations. These details do not limit the present disclosure to necessarily being implemented using these specific details.

[0075] Each embodiment in this specification is described in a progressive manner, with each embodiment focusing on its differences from the other embodiments. References to the same or similar parts between the various embodiments are sufficient. For system embodiments, since they largely correspond to method embodiments, their description is relatively simple. For relevant parts, references to the description of the method embodiments are sufficient.

[0076] The block diagrams of the devices, devices, equipment, and systems involved in this disclosure are merely illustrative examples and are not intended to require or imply that they must be connected, arranged, or configured in the manner shown in the block diagrams. As will be appreciated by those skilled in the art, these devices, devices, equipment, and systems can be connected, arranged, or configured in any manner. Words such as "include," "comprise," "have," and the like are open-ended words, meaning "including but not limited to," and can be used interchangeably therewith. The words "or" and "and" used herein refer to the words "and / or" and can be used interchangeably therewith, unless the context clearly indicates otherwise. The word "such as" used herein refers to the phrase "such as but not limited to," and can be used interchangeably therewith.

[0077] The methods and apparatus of the present disclosure may be implemented in many ways. For example, the methods and apparatus of the present disclosure may be implemented by software, hardware, firmware, or any combination of software, hardware, and firmware. The above order of steps for the method is for illustration only, and the steps of the method of the present disclosure are not limited to the order specifically described above unless otherwise specified. In addition, in some embodiments, the present disclosure may also be implemented as programs recorded in a recording medium, which include machine-readable instructions for implementing the methods according to the present disclosure. Thus, the present disclosure also covers recording media that store programs for executing the methods according to the present disclosure.

[0078] It should also be noted that, in the apparatus, equipment and method of the present disclosure, each component or each step can be decomposed and / or recombined. These decompositions and / or recombinations should be regarded as equivalent schemes of the present disclosure. The above description of the disclosed aspects is provided to enable any technician in this field to make or use the present disclosure. Various modifications to these aspects will be very obvious to those skilled in the art, and the general principles defined herein can be applied to other aspects without departing from the scope of the present disclosure. Therefore, the present disclosure is not intended to be limited to the aspects shown here, but to the widest range consistent with the principles and novel features disclosed herein.

[0079] The above description has been provided for the purpose of illustration and description. In addition, this description is not intended to limit the embodiments of the present disclosure to the forms disclosed herein. Although a number of example aspects and embodiments have been discussed above, those skilled in the art will recognize certain variations, modifications, alterations, additions, and sub-combinations thereof.

Claims

1. A method for constructing an industrial chain knowledge graph based on deep learning, characterized in that: The following steps are involved: S1. Deploy a cloud data collection program, wherein the cloud data collection program is configured to obtain industrial chain data from multiple data sources and clean and pre-process the data; S2. Classify and filter the preprocessed data. For structured data, use the random forest algorithm for classification and filtering. For unstructured data, use word embedding combined with a deep learning model to classify and filter the stored data to obtain text data related to the industry chain. S3. Filter the text data for entity words. Use the ELECTRA model as a classifier and combine it with the BM-25F score to filter out important entity words, remove non-synonymous words, obtain entity words, and annotate them. S4. Build a graph structure representation, create entity nodes, create and initialize edges, and use the GCNE model for entity recognition and relationship extraction; S5. Based on the results of entity recognition and relationship extraction, the entity, attribute, and relationship triples required for the knowledge graph are obtained, and the triples are stored in the graph database to construct the industry chain knowledge graph; S6. When users search for industry chain information, we create appropriate indexes based on the knowledge graph’s query requirements, match the knowledge graph data, and push relevant data to users. For step S3, calculate the BM-25F score for each field, use the ELECTRA model to generate text embeddings for each field, and extract other features that help identify entity words; build a deep learning model, use the BM-25F score and text embeddings as input, use the Transformer model for feature fusion and processing, and output the probability of whether the word is an important entity word.

2. The method according to claim 1, characterized in that For step S1, rdd conversion is used for unstructured data in the collected data, and DataFrame conversion is used for structured data. After the data is aggregated using the aggregation function, the processed data is saved to cloud storage.

3. The method according to claim 1, characterized in that For step S3, entity word labeling specifically includes: combining the evaluation results of industry experts in the industrial chain, labeling the extracted entity words into six categories: company, expert, industry, product, technology, and application, and automatically labeling them in BIOES format.

4. The method according to claim 1, characterized in that For step S4, constructing a graph structure representation specifically includes identifying entities in the text based on word segmentation results and industry chain domain knowledge, creating a node for each entity, and assigning an initial feature vector representation to each entity node. The initial feature vector is created based on the basic attribute information of the entity, and the attribute information is extracted from the text or obtained through other external data sources. According to the relationship description between the entities in the text, edges connecting the entity nodes are created.

5. The method according to claim 3, characterized in that: For step S4, it specifically includes: inputting the constructed graph structure data into the GCNE model, at each node, determining its neighbor node set according to the structure of the graph, for each neighbor node, calculating the message from the neighbor node to the current node, wherein the calculation of the message is based on the current feature vector of the neighbor node and the features of the edge connecting the node, and then aggregating the messages from all neighbor nodes; using the aggregated neighbor node information and edge information to update the state of the current node; using the linear layer to map the updated node feature vector to the entity label space; constructing a conditional random field CRF model, whose input is the representation of the node in the entity label space output by the linear layer, using the CRF model to predict the entity label of each node, selecting all possible node representations from the graph structure, and splicing them together to form the representation of the entity pair; then mapping the representation of the entity pair to the relationship label space, and predicting the relationship label between the entity pairs through the Softmax function.

6. A deep learning-based industrial chain knowledge graph construction system, characterized by: include: Cloud data acquisition device, used to deploy cloud data acquisition programs, obtain industry chain data from multiple data sources, and clean and pre-process the data; Data classification and screening device, used to classify and screen pre-processed data. For structured data, it uses the random forest algorithm for classification and screening. For unstructured data, it uses word embedding combined with a deep learning model to classify and screen the stored data to obtain text data related to the industrial chain. The entity word processing device is used to filter entity words in text data, using the ELECTRA model as a classifier and combining it with the BM-25F score to screen out important entity words, remove non-word words, obtain entity words, and annotate them; Graph structure construction and analysis device, used to construct graph structure representation, create entity nodes, and create and initialize edges, using the GCNE model for entity recognition (NER) and relationship extraction (RE); A knowledge graph construction device is used to obtain the entity, attribute and relationship triples required for the knowledge graph based on the results of entity recognition and relationship extraction, and store the triples in a graph database to construct an industrial chain knowledge graph; The data push device is used to create appropriate indexes according to the query requirements of the knowledge graph when users search for industrial chain information, match the knowledge graph data, and push relevant data to users; The entity word processing device is also used to calculate the BM-25F score of each field, use the ELECTRA model to generate text embedding for each field, and extract other features that are helpful in identifying entity words; build a deep learning model, take the BM-25F score and text embedding as input, use the Transformer model to perform feature fusion and processing, and output the probability of whether the word is an important entity word.

7. An electronic device, characterized in that: The electronic device includes: a memory and a processor, wherein the memory and the processor are coupled; the memory stores program instructions, and when the program instructions are executed by the processor, the electronic device executes the method according to any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that The method comprises a computer program, which, when executed on an electronic device, causes the electronic device to execute the method according to any one of claims 1 to 5.

9. A computer program product, comprising a computer program stored on a computer-readable storage medium, wherein when the computer program is executed by a processor, the method according to any one of claims 1 to 5 is implemented.

Images