Multi-module collaborative thermal management material competitive product information acquisition and industry chain system

Abstract

The invention discloses a multi-module collaborative thermal management material competitive product information acquisition and industry chain system, and belongs to the technical field of network data mining and information processing. Comprising a competing product company collection module, a competing product company product information collection module, a competing product company upstream and downstream information collection module, a competing product company operation information collection module, a knowledge graph construction and display module and risk early warning and management module application software. According to the method, mass data in a network can be deeply mined, the data can be efficiently processed and analyzed through accurate semantic understanding, many defects of a traditional method are overcome, the data collection efficiency and quality are improved through an intelligent content filtering mechanism and an automatic information extraction process, meanwhile, an industrial chain knowledge graph can be constructed, and the data collection efficiency and quality are improved. The method is especially suitable for various practical application scenes such as product information analysis and competitive product dynamic monitoring of thermal management material enterprises, and helps the enterprises to obtain market information in time, accurately grasp market dynamics, formulate scientific competition strategies and improve competitiveness.

Description

Technical Field

[0001] The present invention relates to the technical field of network data mining and information processing, and in particular to a multi-module collaborative heat management material competitor information collection and industrial chain system. Background Art

[0002] In the existing technologies, during the process of product information collection by enterprises of heat management materials (such as heat dissipation materials used in electronic product radiators, etc.), due to technological limitations, a series of significant defects and challenges are generally faced, which are specifically as follows.

[0003] (1): When performing data collection tasks in the Internet through traditional crawler system software, it is often difficult to accurately distinguish product series from specific single products. This lack of discrimination ability directly leads to the collected data being in a mixed and disorderly state, making it difficult to perform effective screening and sorting. As a result, these data cannot be directly applied to subsequent analysis work, seriously affecting the accuracy and efficiency of data analysis. (2): When using static page parsing methods for information extraction, in the face of the dynamic rendering technologies widely used in modern web pages, the crawler system software is overwhelmed and has poor adaptability; and due to the inability to fully parse the dynamically loaded content, the integrity of information extraction is greatly reduced, making it difficult to meet the high standards of modern enterprises for data comprehensiveness and integrity, seriously restricting the scope and depth of data application. (3): In the current information collection process, there is generally a lack of intelligent content filtering mechanisms. This defect inevitably generates a large amount of invalid or redundant data during the collection process. Invalid data not only occupies storage resources but also greatly increases the workload of subsequent data processing and analysis, reducing the overall work efficiency and bringing an additional burden to the enterprise. (4): When performing product correlation analysis, the existing methods often rely on manual annotation. This manual-dependent method is not only time-consuming and laborious with extremely low processing efficiency but also difficult to meet the real-time processing requirements of large-scale data. In a fast-paced market environment, this inefficient processing method is obviously difficult to meet the high requirements of enterprises for real-time data analysis and decision-making support. (5) Regarding the acquisition of upstream and downstream industrial chain information of competitors, the existing technical means are not clear and comprehensive enough. Due to the inability to accurately and comprehensively grasp the upstream and downstream industrial chain information of the heat management material market, enterprises are difficult to build a complete understanding of the market ecosystem, which to a certain extent limits the enterprise's ability to formulate scientific market strategies and competitive strategies, affecting its adaptability and competitiveness in the fierce market competition. Summary of the Invention

[0004] In order to overcome the drawbacks described in the background due to technical limitations during the process of product information collection by existing thermal management material enterprises, the present invention provides an automated enterprise product information collection and analysis subsystem that combines an advanced semantic analysis model and an efficient multi-level crawling strategy under the combined action of relevant unit modules. During application, it can not only deeply mine the vast amount of data in the network, but also efficiently process and analyze this data through precise semantic understanding. It is particularly applicable to various actual application scenarios such as product intelligence analysis and competitor dynamics monitoring for thermal management material enterprises, can help enterprises obtain market information in a timely manner. Thermal management material enterprises can achieve comprehensive and automated collection of product information, thus better conducting market analysis and decision support, and enhancing the multi-module collaborative thermal management material competitor information collection and industrial chain system of product market competitiveness.

[0005] The technical solution adopted by the present invention to solve its technical problems is as follows: Multi-module collaborative thermal management material competitor information collection and industrial chain system, including a competitor company collection module, a competitor company product information collection module, a competitor company upstream and downstream information collection module, a competitor company operation information collection module, a knowledge graph construction and display module, and a risk early warning and management module application software installed in Internet devices; the competitor company collection module uses data retrieval technology to perform full-system information screening and matching operations on the enterprise information query platform based on the core keywords of the company's own products. It can not only intelligently identify and match keywords related to the company's products, but also deeply analyze and screen the query results, so as to obtain competitor company information that has a direct competitive relationship with the company's products; the core function of the competitor company product information collection module mainly depends on the official website URL information of the competitor company. Through the designed and optimized parsing algorithm, it can identify and extract relevant links containing the keyword "product", ensuring that the obtained target links have a direct relevance to the product information, avoiding the interference of irrelevant links, and improving the accuracy and efficiency of information collection; the competitor company upstream and downstream information collection module obtains the annual report of the enterprise through the Internet channel, and uses OCR technology and natural language processing technology to extract the detailed information of the upstream and downstream companies included in the annual report; the competitor company operation information collection module obtains the enterprise annual report data through the Internet platform. By using OCR technology and deep natural language processing technology, it can extract key operation information from the complex annual report text; the function of the knowledge graph construction and display module is to integrate multi-dimensional data obtained from the competitor company collection module, the competitor company product information collection module, the competitor company upstream and downstream information collection module, and the competitor company operation information collection module, construct a comprehensive and dynamic knowledge graph, and visually display it through visualization technology, providing in-depth market competition analysis and decision-making support for the enterprise; the risk early warning and management module can early warn potential market risks through abnormal relationships or trend changes in the knowledge graph, and help the enterprise adjust its strategies in a timely manner.

[0006] Furthermore, the competitor company collection module not only covers the intelligent identification and matching of keywords, but also includes in-depth analysis and multi-dimensional screening of the query results, ensuring that the obtained competitor company information is both accurate and comprehensive; based on the operation of the competitor company collection module, the company can provide data support for subsequent market analysis, competitive strategy formulation, and product optimization, so as to gain an advantageous position in the fierce market competition.

[0007] Furthermore, the product information collection module of the competitor company can actively initiate a network request to obtain the corresponding content of the target web page of the competitor company's official website; after successfully obtaining the web page corresponding content, the module performs screening and filtering operations to eliminate all content irrelevant to product information; specifically, when it detects that there is a product manual available for download on the target web page, the module will automatically trigger the download operation to ensure that relevant materials can be obtained and saved in a timely manner, and in the case where the product manual is missing on the target web page, the module will automatically generate a high-definition web page screenshot of the product details page to make up for the missing part of the information, ensuring the integrity and accuracy of the obtained information. Finally, the obtained data is stored in the database, and the collected competitor product information is evaluated and sorted in real time.

[0008] Furthermore, in the competitor company's upstream and downstream information collection module, the detailed information of upstream and downstream companies contained in the extracted annual report specifically covers multiple dimensions of information such as the name of the supplier, the specific content of the supply, the supply time node, the name of the customer, the sales proportion, and the sales volume. Through multi-dimensional information extraction, the system can comprehensively understand the enterprise's supply chain and sales chain situation; after the extraction is completed, the module stores these key data in the database to ensure the accuracy and queryability of the data. Subsequently, the enterprise can build an industrial chain map based on the data in the database, providing data support for the enterprise to occupy a favorable position in the market competition.

[0009] Furthermore, in the application of the competitor company's business information collection module, the extracted business information includes the enterprise's core financial indicators, business strategies, market layouts, and product R & D. The extracted data is integrated and stored in the background database to ensure the integrity and traceability of the data, facilitating the enterprise to query and analyze at any time.

[0010] Furthermore, in the application of the knowledge graph construction and display module, at the construction level, the module integrates competitor company information, product information, supply chain information, financial data, and business strategy data through data cleaning and standardization processing to ensure the accuracy and consistency of the data. Subsequently, using natural language processing technology, it automatically identifies key entities in the data and extracts the relationships between them to form the nodes and edges of the knowledge graph. On this basis, the module stores and manages the knowledge graph through a graph database and supports a dynamic update mechanism to ensure the timeliness and integrity of the graph.

[0011] Furthermore, in the application of the knowledge graph construction and display module, at the display level, the module presents the knowledge graph in a graphical manner through an interactive visualization tool. Users can analyze the market competition pattern layer by layer from macro to micro through zooming, dragging, and filtering operations. At the same time, the system supports keyword search and complex query functions, enabling users to quickly locate specific entities or relationships.

[0012] Furthermore, the risk early warning and management module can combine product competitiveness data to warn of potential market risks caused by a decline in product competitiveness. When a major competitor launches a product with higher competitiveness, the module will remind the enterprise to pay attention and take countermeasures.

[0013] Compared with the prior art, the beneficial effects of the present invention are as follows: Under the combined action of relevant unit modules, through a multi-level crawling strategy and semantic analysis technology, the present invention can not only deeply excavate massive data in the network, but also efficiently process and analyze these data through accurate semantic understanding, realizing the efficient collection and accurate processing of enterprise information of thermal management materials, solving many defects of traditional methods. Its intelligent content filtering mechanism and automated information extraction process significantly improve the efficiency and quality of data collection. At the same time, it can construct an industrial chain knowledge map, which is especially suitable for various practical application scenarios such as product intelligence analysis and competitor dynamics monitoring of thermal management material enterprises, helping enterprises obtain market information in a timely manner, accurately grasp market dynamics, formulate scientific competitive strategies, and enhance competitiveness. Thermal management material enterprises can achieve comprehensive and automated collection of product information, thereby better conducting market analysis and decision-making support. Brief Description of the Drawings

[0014] The present invention will be further described below in conjunction with the drawings and embodiments.

[0015] Figure 1 It is a schematic diagram of the software architecture block diagram of the present invention. Detailed Embodiments

[0016] Figure 1 As shown in [specific figure reference], the multi-module collaborative thermal management material competitor information collection and industrial chain system includes a competitor company collection module, a competitor company product information collection module, a competitor company upstream and downstream information collection module, a competitor company business information collection module, a knowledge graph construction and display module, and a risk early warning and management module application software installed in Internet devices (such as mobile phones, PCs, tablet computers, etc.). The present invention achieves the intended technical effects through the following modules and steps.

[0017] Figure 1As shown in the figure, competitor company collection module: The core function of this module is to select authoritative enterprise information query platforms, such as the National Enterprise Credit Information Publicity System, industry databases, etc., through precise data retrieval technology. These platforms provide rich basic enterprise information and business scope descriptions, and screen out competitor company information that has a direct competitive relationship with the company's products. The specific implementation steps are as follows: (1) According to the characteristics of the company's own products, extract core keywords, such as enterprises similar to the company's operating products, including "thermal management materials", "thermal interface materials", "thermal conductive materials", "phase change materials", etc. This scope covers all enterprises involved in the production and sales of thermal management materials in the business field, and whose product functions have a high similarity with the company's products. (2) After initially screening out potential competitor companies, conduct a more in-depth analysis of these companies, and further eliminate those enterprises with a low or no business association with the company, considering multiple factors such as industry background, market positioning, product characteristics, etc., to ensure that the competitor company information finally obtained is both accurate and comprehensive. (3) Store the competitor company information after in-depth screening into the system database. This information includes, but is not limited to, company name, business scope, registered address, contact information, number of patents, etc., in order to provide necessary data support for subsequent modules and ensure data consistency and traceability.

[0018] Figure 1As shown in the figure, the product information collection module of the competitor company extracts product-related information by crawling the official website of the competitor company. The specific implementation steps are as follows: (1) Target link identification: Based on the URL of the official website of the competitor company, the web crawler technology is used to comprehensively scan the website pages. Through the parsing algorithm, the links containing keywords such as "product", "product series", "product introduction", and "products" are identified. These links are the key entry points for obtaining product information and provide accurate positioning for subsequent information extraction. (2) Web page content acquisition and parsing: Initiate a network request for the identified target link to obtain the response content of the web page. Using natural language processing technology, deeply analyze the HTML structure of the web page, extract key information such as product lists and product details pages, and ensure the integrity and accuracy of the data. (3) Product hierarchical relationship identification: Use deep learning models to semantically classify the extracted product information and distinguish between product series and specific products. For example, "thermal grease series" is identified as a product series, and "model A thermal grease" is identified as a specific product, thereby building a clear product hierarchical relationship. (4) Data screening and filtering: Through preset rules and keyword filtering mechanisms, irrelevant content on the web page, such as advertisements, navigation bars, etc., is removed, and pure text information related to the product is retained to ensure the purity and availability of the data. (5) Product manual download and screenshot generation: If there is a download link for the product manual on the web page, the system will automatically download the manual. If the manual is missing, the system will automatically generate a webpage screenshot of the product details page and extract the text information in the screenshot through OCR technology to make up for the missing data. (6) Product parameter extraction: Combine OCR and NLP technology to extract key parameters such as thermal conductivity, thermal resistance, operating temperature range, etc. from product manuals or webpage screenshots; for example, regular expressions are used to match text in the format of "thermal conductivity: XX W / m·K" to ensure the accuracy of parameter extraction. (7) Data storage and classification: The extracted product information is stored in the database and classified according to product series and specific products to facilitate subsequent query and analysis and improve the efficiency of data management. (8) Product competitiveness ranking and specific process recording, A: First determine the scoring dimensions and weights: Thermal conductivity (35%), the thermal conductivity of the material, in W / m·K; Contact thermal resistance (25%): thermal resistance between the material and the contact surface, unit is K·cm² / W; Electrical insulation (15%): The insulation performance of the material, suitable for scenarios where insulation is required; Mechanical properties (10%): including flexibility, compressive strength, etc.; Reliability (10%): stability in long-term use, such as anti-aging, anti-pumping effect, etc. Environmental adaptability (5%): high temperature resistance, corrosion resistance, etc.

[0019] B: Establish the scoring criteria: The thermal conductivity is as follows: 10 points: > 10 W / m·K; 8 points: 5 - 10 W / m·K; 5 points: 1 - 5 W / m·K; 1 point: < 1 W / m·K; The contact thermal resistance is as follows: 10 points; extremely low contact thermal resistance; 5 points; medium contact thermal resistance; 1 point: high contact thermal resistance; The electrical insulation is as follows: 10 points: extremely high insulation (volume resistivity > 10¹² Ω·cm); 5 points: medium insulation; 1 point: low insulation (volume resistivity < 10 6 Ω·cm); The mechanical properties are as follows: 10 points: excellent flexibility and compressive strength; 5 points: medium performance; 1 point: prone to cracking or deformation; Reliability: 10 points; For long - term use without performance degradation: 5 points: slight degradation; 1 point: severe degradation or failure; The environmental adaptability is as follows: 10 points: excellent performance in high - temperature resistance, corrosion resistance, etc.; 5 points: medium performance; 1 point: poor performance; Calculate the comprehensive score as follows: Use the weighted average method to calculate the comprehensive score of each product: Ci = j =1∑6( Si , j × wj ), where: Ci is the comprehensive competitiveness score of the i - th competing product, Si,j is the score of the i - th competing product in the j - th performance dimension, and wj is the weight of the j - th performance dimension.

[0020] Figure 1As shown in [figure], the upstream and downstream information collection module of the competitor company extracts upstream and downstream company information by obtaining the annual report of the enterprise. The specific steps are as follows: (1) Annual report acquisition: Obtain the annual report of the competitor company through Internet channels, such as the official website of the stock exchange, the official website of the enterprise, etc.; support annual reports in various formats such as PDF and HTML to ensure the diversity and comprehensiveness of data. (2) OCR and NLP processing: For the annual report in PDF format, use OCR technology to convert it into an editable text format. For the annual report in HTML format, directly parse the HTML structure to extract the text content; use natural language processing technology to identify keywords such as "supplier", "customer", "sales ratio" in the annual report to provide accurate positioning for information extraction. (3) Information extraction and classification: Extract supplier information, including supplier name, supply content (such as raw material types), supply time (such as the starting year of cooperation). Extract customer information, including customer name, sales ratio, sales amount, etc.; classify and organize the extracted information to form structured upstream and downstream relationship data for subsequent analysis. (4) Data storage and graph construction: Store the upstream and downstream information in the database and construct an industrial chain knowledge graph based on these data. The graph takes the enterprise as the core node and the upstream and downstream enterprises as associated nodes to display the cooperation relationship and industrial chain hierarchical relationship between enterprises, providing intuitive data visualization support.

[0021] Figure 1 As shown in [figure], the business information collection module of the competitor company extracts business information by analyzing the annual report of the enterprise. The specific steps are as follows: (1) Annual report text extraction: Similar to the upstream and downstream information collection module, use OCR and NLP technologies to extract the text content in the annual report to ensure the integrity and accuracy of the data. (2) Key information identification: Use natural language processing technology to identify key business information in the annual report, such as financial indicators (operating income, net profit, gross profit margin, asset-liability ratio, etc.), business dynamics (new product R & D, market expansion, strategic planning, etc.), risk factors (risks and countermeasures mentioned in the management discussion and analysis (MD&A) section) to ensure the comprehensiveness and accuracy of the information. (3) Data structuring and storage: Structurally process the extracted business information and store it in the database to form a complete business information database of the competitor company. For example, store the financial indicators in tabular form for subsequent analysis and comparison. (4) Analysis tool integration: Provide an interface for data analysis tools to support users in further analyzing the extracted business information, such as financial indicator trend analysis, market share comparison, etc., to enhance the utilization value of the data.

[0022] Figure 1As shown in [figure], the Knowledge Graph Construction and Display Module. The core objective of this module is to integrate multi-dimensional data obtained from the Competitor Company Collection Module, the Competitor Company Product Information Collection Module (including the product competitiveness ranking function), the Competitor Company Upstream and Downstream Information Collection Module, and the Competitor Company Business Information Collection Module, construct a comprehensive and dynamic knowledge graph, and visually display it through visualization technology to provide in-depth market competition analysis and decision-making support for enterprises. The specific implementation steps are as follows: (1) Data integration: The system uniformly integrates the data obtained from modules such as competitor companies, product information, upstream and downstream information, and business information; this data includes basic information of competitor companies, product information, supply chain information, financial data, business strategies, etc. In particular, the product competitiveness ranking results will also be integrated into the knowledge graph as important data; through data cleaning and standardization processing, the accuracy and consistency of the data are ensured. (2) Data association: Using natural language processing (NLP) technology, the system automatically identifies key entities (such as companies, products, suppliers, customers, etc.) in the data and extracts the relationships between them (such as competition, supply, cooperation, etc.); for example, associate the products of competitor companies with their suppliers, customers, financial data, etc. to form a multi-dimensional data network; in particular, the system will also add the attribute of "competitiveness score" to each product according to the product competitiveness ranking results, and use the competitiveness relationship between products (such as "high-competitiveness products" and "low-competitiveness products") as relationship nodes to be added to the graph. (3) Graph structure design: Based on the extraction results of entities and relationships, design the structure of the knowledge graph; the nodes in the graph represent entities (such as companies, products, suppliers, etc.), and the edges represent the relationships between entities (such as supply, competition, cooperation, etc.); in the graph, the product nodes will contain the attribute of "competitiveness score" and visually display their competitiveness levels through changes in color or size; use a graph database (such as Neo4j) for storage and management to ensure efficient query and update of data. (4) Dynamic update mechanism: The knowledge graph has a dynamic update function and can automatically update the nodes and relationships in the graph according to newly collected data; for example, when the system obtains new competitor company information or product information, it automatically adds them to the graph to ensure the timeliness and accuracy of the graph; in particular, when the product competitiveness ranking results are updated, the attributes and relationships of the product nodes in the graph will also be updated accordingly. (5) Multi-dimensional analysis: The knowledge graph not only contains static entities and relationships, but also can conduct multi-dimensional analysis through dimensions such as time and geography to display the market performance and competition situation of enterprises in different time periods and different regions; for example, display the changes in the supply chain or market share of a certain company in the past three years. In addition, the graph will also support analysis by product competitiveness dimension, such as displaying the distribution and change trends of high-competitiveness products in the market. (6) Visualization display: The system provides a variety of visualization tools to display the knowledge graph in a graphical way.Users can view different entities and their relationships through an interactive interface, supporting operations such as zooming, dragging, and filtering, which facilitates users' layer-by-layer analysis from macro to micro. For example, users can click on a company node to view all its suppliers, customers, product lines, and corresponding products. In particular, the system will highlight high-competitive products through color coding or icons and provide a visual display of the competitiveness ranking. For example, it will display the competitiveness score distribution of products through bar charts or line charts. (7) Graph Query and Search: Users can quickly locate entities or relationships of interest through keyword search, conditional filtering, etc. For example, find all the suppliers of a certain company, all the competitors of a certain product, etc. The system also supports complex graph queries, such as finding all the cooperative customers of a company within a certain time period. In particular, users can query the competitiveness scores of products and filter and compare products based on the competitiveness ranking results. (8) Intelligent Recommendation and Early Warning: Based on the analysis of the knowledge graph, the system can provide intelligent recommendation functions, such as recommending potential partners, market opportunities, etc. At the same time, the system can also issue early warning signals according to abnormal relationships or trend changes in the graph to help enterprises respond to market risks in a timely manner. In particular, the system will provide early warnings based on the changing trend of product competitiveness. For example, when the competitiveness score of a certain product suddenly drops, the system will issue an early warning prompt. (9) Market Competition Analysis: Through the knowledge graph, enterprises can clearly see the comparison with competing companies in terms of products, supply chains, market layouts, etc., which helps to formulate more targeted competition strategies. For example, analyze the product line layout of competing companies to find market gaps. In particular, the graph will intuitively display the competitiveness ranking results of products, helping enterprises quickly identify high-competitive products and potential competitive threats in the market. (10) Supply Chain Optimization: The knowledge graph can display the upstream and downstream supply chain situations of enterprises, helping enterprises optimize supply chain management and reduce operating costs. For example, by analyzing the geographical distribution of suppliers, optimize logistics and procurement strategies. In particular, the graph will combine product competitiveness data to help enterprises evaluate the competitiveness bottlenecks in the supply chain, such as identifying the key suppliers of high-competitive products.

[0023] Figure 1 As shown in the figure, there is a risk early warning and management module. Through abnormal relationships or trend changes in the knowledge graph, the system can early warn potential market risks and help enterprises adjust their strategies in a timely manner. For example, when the sales proportion of a certain customer suddenly drops, the system will issue an early warning prompt. In particular, the system will combine product competitiveness data to early warn of the market risks that may be brought about by the decline in product competitiveness. For example, when a major competitor launches a product with higher competitiveness, the system will remind the enterprise to pay attention and take countermeasures.

[0024] Figure 1As shown in the figure, the present invention consists of six main modules. Each module is responsible for different information collection and processing tasks, and integrates the data into the knowledge graph construction and display module. The following is a brief summary of each module. In the application of the competing company collection module, when the core keywords of the company's products are input, it can retrieve data, conduct preliminary screening, in-depth analysis through an enterprise information query platform, eliminate irrelevant enterprises, and output and store the information of competing companies in the database. In the application of the competing company product information collection module, when the UR of the competing company's official website is input, it can identify the target link, obtain the web content, analyze the product hierarchy relationship, screen and filter data, download product manuals or generate screenshots, extract product parameters, score according to the product data, and output and store the product information in the database. In the application of the competing company upstream and downstream information collection module, when the annual report of the competing company is input, it can download the annual report, conduct OCR and NLP processing, extract supplier and customer information, and output and store the upstream and downstream information in the database. In the application of the competing company operation information collection module, when the annual report of the competing company is input, it can extract key information such as financial indicators and operation dynamics in the annual report, and output and store the operation information in a structured manner in the database. In the application of the knowledge graph construction and display module, it can integrate the data of all modules, identify entities and their relationships, design the graph structure, store it using a graph database, implement a dynamic update mechanism, conduct multi-dimensional analysis, provide a visualization display function, and display the knowledge graph through an interactive interface, supporting multi-dimensional query and analysis. The risk warning and management module can warn of potential market risks in advance and help enterprises adjust their strategies in a timely manner. Through the above, the entire system improves the efficiency and quality of data collection through an automated information collection and processing process, constructs an industrial chain knowledge graph, helps enterprises quickly and accurately grasp market dynamics, and formulate scientific competitive strategies.

[0025] The foregoing has shown and described the basic principles, main features and advantages of the present invention. For those skilled in the art, it is obvious that the present invention is limited to the details of the above-described exemplary embodiments, and without departing from the spirit or basic characteristics of the present invention, the present invention can be implemented in other specific forms. Therefore, in any regard, the embodiments should be regarded as exemplary and non-limiting. The scope of the present invention is defined by the appended claims rather than the above description. Therefore, it is intended to embrace all changes falling within the meaning and scope of the equivalent elements of the claims in the present invention.

[0026] In addition, it should be understood that although this specification is described according to embodiments, not every embodiment only contains an independent technical solution. This narrative way of the specification is only for clarity. Those skilled in the art should regard the specification as a whole. The technical solutions in the embodiments can also be appropriately combined to form other embodiments that can be understood by those skilled in the art.

Claims

1. A multi-module collaborative thermal management material competitor information collection and industrial chain system, characterized in that It includes application software such as a competitor company collection module, a competitor company product information collection module, a competitor company upstream and downstream information collection module, a competitor company operation information collection module, a knowledge graph construction and display module, and a risk warning and management module installed in an Internet device; the competitor company collection module, through data retrieval technology, based on the core keywords of the company's own products, performs information screening and matching operations on the entire system on the enterprise information query platform, which can not only intelligently identify and match keywords related to the company's products, but also deeply analyze and screen the query results, so as to obtain information on competitor companies that have a direct competitive relationship with the company's products; the core function of the competitor company product information collection module mainly depends on the official website URL information of the competitor company. Through the designed and optimized parsing algorithm, it can identify and extract relevant links containing the keyword "product", ensuring that there is a direct relevance between the obtained target links and product information, avoiding the interference of irrelevant links, and improving the accuracy and efficiency of information collection; the competitor company upstream and downstream information collection module obtains the annual report of the enterprise through Internet channels, and by using OCR technology and natural language processing technology, it can extract the detailed information of the upstream and downstream companies contained in the annual report; the competitor company operation information collection module, through the enterprise annual report data obtained through the Internet platform, by using OCR technology and deep natural language processing technology, can extract key operation information from the complex annual report text; the function of the knowledge graph construction and display module is to integrate multi-dimensional data obtained from the competitor company collection module, the competitor company product information collection module, the competitor company upstream and downstream information collection module, and the competitor company operation information collection module, construct a comprehensive and dynamic knowledge graph, and visually display it through visualization technology, providing in-depth market competition analysis and decision-making support for the enterprise; the risk warning and management module can early warn of potential market risks through abnormal relationships or trend changes in the knowledge graph, helping the enterprise adjust its strategies in a timely manner.

2. The multi-module collaborative thermal management material competitor information collection and industrial chain system according to claim 1, wherein The competitor company collection module not only covers the intelligent identification and matching of keywords, but also includes in-depth analysis and multi-dimensional screening of query results, ensuring that the obtained competitor company information is both accurate and comprehensive; based on the operation of the competitor company collection module, the company can provide data support for subsequent market analysis, formulation of competitive strategies, and product optimization, so as to gain an advantageous position in the fierce market competition.

3. The multi-module collaborative thermal management material competitor information collection and industrial chain system according to claim 1, characterized in that, The product information collection module of the competitor company can initiate network requests actively to obtain the corresponding content of the target web page of the official website of the competitor company; after successfully obtaining the web page corresponding content, the module performs screening and filtering operations to eliminate all content irrelevant to product information; specifically, when it detects that there is a product manual available for download on the target web page, the module will automatically trigger the download operation to ensure that relevant materials can be obtained and saved in a timely manner, and in the case where the product manual is missing on the target web page, the module will automatically generate a high-definition web page screenshot of the product details page to make up for the missing part of the information, ensuring the integrity and accuracy of the obtained information. Finally, the obtained data is stored in the database, and the collected competitor product information is evaluated and sorted in real time.

4. The multi-module collaborative thermal management material competitor information collection and industrial chain system according to claim 1, wherein The upstream and downstream information collection module of the competitor company extracts the detailed information of upstream and downstream companies included in the annual report, specifically covering multiple dimensions of information such as the name of the supplier, the specific content of the supply, the supply time node, the name of the customer, the sales proportion, and the sales volume. Through multi-dimensional information extraction, the system can comprehensively grasp the enterprise's supply chain and sales chain situation; after the extraction is completed, the module stores these key data in the database to ensure the accuracy and queryability of the data. Subsequently, the enterprise can build an industrial chain map based on the data in the database, providing data support for the enterprise to occupy a favorable position in the market competition.

5. The multi-module collaborative thermal management material competitor information collection and industrial chain system according to claim 1, characterized in that In the application of the competitor company's business information collection module, the extracted business information includes the enterprise's core financial indicators, business strategies, market layouts, and product R & D. The extracted data is integrated and stored in the background database to ensure the integrity and traceability of the data, facilitating the enterprise to query and analyze at any time.

6. The multi-module collaborative thermal management material competitor information collection and industrial chain system according to claim 1, wherein In the application of the knowledge graph construction and display module, at the construction level, the module unifies and integrates competitor company information, product information, supply chain information, financial data, and business strategy data through data cleaning and standardization processing to ensure the accuracy and consistency of the data. Subsequently, using natural language processing technology, it automatically identifies the key entities in the data and extracts the relationships between them to form the nodes and edges of the knowledge graph. Then, the module stores and manages the knowledge graph through a graph database and supports a dynamic update mechanism to ensure the timeliness and integrity of the graph.

7. The multi-module collaborative thermal management material competitor information collection and industrial chain system according to claim 1, characterized in that, In the application of the knowledge graph construction and display module, at the display level, the module presents the knowledge graph in a graphical way through an interactive visualization tool. Users can analyze the market competition pattern layer by layer from macro to micro through zooming, dragging, and filtering operations. At the same time, the system supports keyword search and complex query functions, and users can quickly locate specific entities or relationships.

8. The multi-module collaborative thermal management material competitor information collection and industrial chain system according to claim 1, characterized in that, The risk warning and management module can combine product competitiveness data to warn of the market risks that may be brought about by the decline in product competitiveness. When major competitors launch products with higher competitiveness, the module will remind the enterprise to pay attention and take countermeasures.

Images