Automated knowledge graph construction and dynamic evolution method for ultrahigh-speed optical module production

Abstract

The invention discloses an automatic knowledge graph construction and dynamic evolution method and system for production of an ultra-high-speed optical module. The method comprises the following steps: collecting multi-dimensional data in the production process of the ultra-high-speed optical module; the multi-dimensional data is cleaned, noise, abnormal values and redundant information are removed, standardization processing is carried out, and the multi-dimensional data from different sources are formatted in a unified mode; key elements representing the production process and the mutual relation of the key elements in the formatted multi-dimensional data are extracted, and structured data are formed; constructing a knowledge graph about the production of the ultra-high-speed optical module by using the structured data according to a preset rule and relation definition; data in the production process of the ultra-high-speed optical module are regularly collected and processed, the data are compared with data in an existing knowledge graph, and if new change occurs, the relation between nodes in the graph is automatically updated according to the new change data. The intelligent management level and the production efficiency of the ultra-high-speed optical module production line are improved.

Description

Technical Field

[0001] The present invention relates to the field of intelligent manufacturing technology, and specifically to a method and system for constructing and dynamically evolving an automated knowledge graph for ultra-high-speed optical module production. Background Art

[0002] With the rapid development of the information society, optical communication technology is becoming increasingly important in data transmission. This is particularly true in high-speed information flow applications such as data centers, 5G networks, and cloud computing, which are driving a sharp increase in demand for ultra-high-speed optical modules. Optical modules are core components in optical communication networks, converting electrical and optical signals to achieve high-speed data transmission. However, with increasing data rates and higher demands for transmission stability, the production process for optical modules has become increasingly complex, requiring continuous optimization and upgrading of the materials, equipment, and process flows involved in the manufacturing process. Therefore, maintaining efficient production while ensuring high product quality and consistency has become a major challenge for optical module manufacturers.

[0003] To address these challenges, the optical module production sector is gradually moving towards intelligent and automated processes. In recent years, the application of knowledge management technologies in manufacturing has garnered widespread attention, particularly the introduction of knowledge graphs, which have provided strong support for intelligent manufacturing. Knowledge graphs are tools that structure and semantically correlate complex and dispersed knowledge information. By integrating information such as technical specifications, process parameters, equipment status, and quality inspection data from the optical module production process, they can construct a complete knowledge network. This technology not only helps production personnel quickly locate and acquire the necessary process knowledge, but also supports production decision-making through reasoning and analysis, improving production flexibility and responsiveness. In optical module production, knowledge graphs help streamline the flow of knowledge across all links, enabling optimized and efficient management of production processes.

[0004] Although knowledge graph technology has been applied in many manufacturing fields, current research and application still face many limitations. First, existing knowledge graphs are mostly static and cannot adapt to the rapidly changing process requirements and equipment status during optical module production. This limits the update speed and flexibility of knowledge graphs when faced with real-time production changes. Second, data sources in the production process are diverse and frequently updated, such as production equipment operating data, process parameter fluctuations, and quality inspection information. This data is often not automatically integrated into the knowledge graph, resulting in delayed knowledge updates. Finally, optical module production has high requirements for real-time performance and stability. Traditional knowledge management methods are unable to cope with these complex and changing production environments and cannot provide timely decision support and intelligent fault diagnosis. Summary of the Invention

[0005] In response to the problems of low efficiency and difficulty in dynamic updating of manual knowledge graph construction in existing optical module production, the present invention provides an automated knowledge graph construction and dynamic evolution method and system for ultra-high-speed optical module production.

[0006] The technical solution adopted in the present invention is:

[0007] A method for constructing and dynamically evolving an automated knowledge graph for ultra-high-speed optical module production is provided, comprising the following steps:

[0008] S1. Collect multi-dimensional data during the production process of ultra-high-speed optical modules;

[0009] S2. Clean the multidimensional data to remove noise, outliers, and redundant information, and perform standardization to uniformly format the multidimensional data from different sources. Extract the key elements and their interrelationships in the production process from the formatted multidimensional data to form structured data.

[0010] S3. Construct a knowledge graph about ultra-high-speed optical module production based on the structured data according to preset rules and relationship definitions. Each node in the knowledge graph represents a key element in the production process, and the edges in the knowledge graph represent the relationship between the nodes.

[0011] S4. Regularly collect and process data from the ultra-high-speed optical module production process, and compare it with the data in the existing knowledge graph. If new changes occur, the nodes and relationships in the graph are automatically updated based on the new change data.

[0012] Following the above technical solution, the multi-dimensional data includes equipment status, process parameters and production conditions;

[0013] Following the above technical solution, we will use Neo4j database and Python scripts to automatically build the knowledge graph.

[0014] Following the above technical solution, the collected multi-dimensional data are converted into a specific standardized JSON format in real time and stored in the form of files on the local server.

[0015] Following the above technical solution, data collection is triggered specifically through a set threshold, event-driven mechanism or time interval.

[0016] Following the above technical solution, the automatic construction and dynamic evolution process of the knowledge graph is monitored through a visual interface.

[0017] Following the above technical solution, a query tool is set up to retrieve nodes and relationships in the knowledge graph to obtain real-time information about the production process.

[0018] Following the above technical solution, the specific nodes of the knowledge graph and the relationship between specific nodes are manually modified.

[0019] The present invention also provides an automated knowledge graph construction and dynamic evolution system for ultra-high-speed optical module production, which is characterized by including:

[0020] Data acquisition module, used to collect multi-dimensional data during the production process of ultra-high-speed optical modules;

[0021] The data processing module is used to clean the multi-dimensional data, remove noise, outliers and redundant information, and perform standardization to uniformly format the multi-dimensional data from different sources;

[0022] The knowledge graph automation construction module is used to extract key elements and their interrelationships in the production process from formatted multidimensional data, and construct a knowledge graph for ultra-high-speed optical module production based on preset rules and relationship definitions. Each node in the knowledge graph represents a key element in the production process, and the edges in the knowledge graph represent the relationships between the nodes.

[0023] The knowledge graph dynamic evolution module is used to compare the data regularly collected during the production process of ultra-high-speed optical modules with the data in the existing knowledge graph. If new changes occur, the nodes and the relationships between nodes in the graph are automatically updated according to the new change data.

[0024] The present invention also provides a computer storage medium storing a computer program executable by a processor, which executes the automated knowledge graph construction and dynamic evolution method for ultra-high-speed optical module production described in the above technical solution.

[0025] The beneficial effects of the present invention are as follows: Taking into account the complexity and dynamic nature of multi-source data in the production process (such as changes in equipment status and process conditions), the present invention automatically constructs and maintains a knowledge graph for the ultra-high-speed optical module production process by managing the updates of multi-source data. This method integrates and processes various types of data from the production line, combined with intelligent data management technology, to achieve automated generation of the knowledge graph, breaking away from the limitations of traditional manual construction. At the same time, with the help of a dynamic evolution mechanism, the knowledge graph can self-update and optimize according to real-time data changes, thereby improving its ability to adapt to complex production environments, ensuring the intelligence and efficiency of the production process, and ultimately improving the intelligent management level and production efficiency of the ultra-high-speed optical module production line.

[0026] Of course, any product implementing the present invention does not necessarily need to achieve all of the advantages described above at the same time. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following is a brief introduction to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0028] Figure 1 This is a flow chart of the automated knowledge graph construction and dynamic evolution method for ultra-high-speed optical module production according to an embodiment of the present invention;

[0029] Figure 2 This is a block diagram of the automated knowledge graph construction and dynamic evolution process for ultra-high-speed optical module production according to an embodiment of the present invention;

[0030] Figure 3 This is a schematic diagram of a knowledge graph automation construction module according to an embodiment of the present invention;

[0031] Figure 4 Schematic diagram of the knowledge graph dynamic evolution module according to an embodiment of the present invention;

[0032] Figure 5 It is a schematic diagram of the dynamic evolution of the knowledge graph according to an embodiment of the present invention. DETAILED DESCRIPTION

[0033] In order to make the purpose, technical solutions and advantages of the present invention more clearly understood, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0034] It should be noted that the illustrations provided in the embodiments of the present invention are only schematic illustrations of the basic concept of the present invention. Therefore, the drawings only show components related to the present invention and are not drawn according to the number, shape and size of components in actual implementation. In actual implementation, the type, quantity and proportion of each component can be changed at will, and the component layout type may also be more complicated.

[0035] In the present invention, it should also be noted that the terms "center," "upper," "lower," "left," "right," "vertical," "horizontal," "inner," and "outer" and the like are used to indicate positions or locations based on those shown in the accompanying drawings. These terms are intended solely to facilitate the description of the present application and to simplify the description. They are not intended to indicate or imply that the devices or components referred to must have a specific orientation, be constructed, or operate in a specific orientation. Therefore, they should not be construed as limiting the present application. Furthermore, the terms "first" and "second" are used solely for descriptive and distinguishing purposes and should not be construed as indicating or implying relative importance.

[0036] In addition, it should be noted that the features of the various embodiments of the present invention may be combined or coupled in part or in whole, and, as will be appreciated by those skilled in the art, may interact and operate in different ways. Each embodiment may be implemented independently of one another or in an associated relationship.

[0037] like Figure 1 、 2 As shown, the method for constructing and dynamically evolving an automated knowledge graph for ultra-high-speed optical module production according to an embodiment of the present invention includes the following steps:

[0038] S1. Collect multi-dimensional data during the production process of ultra-high-speed optical modules;

[0039] S2. Clean the multidimensional data to remove noise, outliers, and redundant information, and perform standardization to uniformly format the multidimensional data from different sources. Extract the key elements and their interrelationships in the production process from the formatted multidimensional data to form structured data.

[0040] S3. Construct a knowledge graph about ultra-high-speed optical module production based on the structured data according to preset rules and relationship definitions. Each node in the knowledge graph represents a key element in the production process, and the edges in the knowledge graph represent the relationship between the nodes.

[0041] S4. Regularly collect and process data from the ultra-high-speed optical module production process, and compare it with the data in the existing knowledge graph. If new changes occur, the nodes and relationships in the graph are automatically updated based on the new change data.

[0042] This embodiment achieves the automated generation of a knowledge graph based on production data through data collection, processing, and automated knowledge graph construction. It also proposes a dynamic data evolution mechanism that automatically updates the knowledge graph when the data changes, ensuring the timeliness and accuracy of the knowledge graph. The dynamic evolution of the knowledge graph can adapt to the ever-changing production environment and needs. Therefore, by constructing a knowledge graph with automated update and evolution capabilities, the present invention solves the problems of real-time processing of production data and effective utilization of knowledge, thereby providing reliable knowledge support for subsequent data analysis and decision-making.

[0043] Furthermore, when collecting multi-source data in step S1, multi-dimensional data such as equipment status, process parameters, and production conditions during the production of ultra-high-speed optical modules can be automatically collected through sensors, equipment interfaces, and environmental monitoring systems deployed on the production line.

[0044] Step S2 mainly preprocesses and integrates the data, cleans the collected multi-source data, removes noise, outliers and redundant information, and after standardization, formats the data from different sources in a unified manner to ensure that the data can be efficiently integrated.

[0045] In step S3, the knowledge graph can be automatically constructed using the Neo4j database and Python scripts. Based on the processed multi-source data, a preliminary knowledge graph is constructed using automated rules and models. Nodes represent key elements in the production process, and edges represent the relationships between them.

[0046] Step S4 activates the dynamic evolution mechanism, enabling dynamic updates to the knowledge graph. When production data changes (such as equipment status changes or process parameter adjustments), the system saves the processed data as a JSON file. An automated update algorithm reads the latest JSON file and adjusts the structure and content of the knowledge graph in real time to ensure it reflects the latest production environment.

[0047] The entire knowledge graph construction and update process of the present invention can be automated and run continuously. The entire automated construction and dynamic evolution module runs continuously without human intervention, ensuring that the knowledge graph is continuously updated according to changes in the production environment and reflects production status and process information in real time.

[0048] Specifically, various data collection methods (such as sensors, monitoring equipment, and production logs) are used to monitor various parameters and status information during the production process in real time, including equipment operating status, production process parameters, and environmental conditions. The collected data is converted into a specific JSON format in real time and stored as files on a local server. To ensure data quality, the system cleans and preprocesses the collected data to remove noise and outliers, and standardizes data from different sources into a unified format. Changes in data during the production process are then continuously monitored using predefined thresholds, event-driven mechanisms, or time intervals. For example, when equipment status changes, production parameters exceed preset ranges, or environmental conditions fluctuate, the system can detect these changes in real time. The system monitors real-time data sources through scheduled tasks or event monitoring mechanisms. Whenever a data source changes, the system updates the modified data to the corresponding JSON file. This ensures that the JSON file always contains the latest production data, providing a basis for subsequent knowledge graph evolution.

[0049] After reading the data stored in the JSON file, the system automatically constructs a knowledge graph using the Neo4j graph database interface. Using Python's neo4j library, a knowledge graph construction script is written. First, a connection to the Neo4j database is established. Then, the node attributes and the relationship types between nodes are defined. Nodes and their relationships are created in Neo4j using Cypher statements to build a knowledge graph for ultra-high-speed optical module production data. Specifically, the system parses each data field in the JSON file, converts it into a node in the graph (such as equipment, process steps, etc.), and assigns it a unique identifier and type based on different node attributes. The system creates relationships between nodes in the graph (such as the relationship between equipment and production steps, the input-output relationship in the production process, etc.) based on preset rules and relationship definitions, as shown in Tables 1 and 2. In this way, the system automatically constructs a preliminary knowledge graph that reflects the production process and its dynamic characteristics.

[0050] Table 1 Entity rules in the production data knowledge graph

[0051]

[0052] Table 2 Relationship rules in the production data knowledge graph

[0053]

[0054]

[0055] The latest production data is read from the JSON file periodically or through event triggering. This data is parsed and compared with the existing knowledge graph. If new changes are detected in the production process (such as changes in equipment status, updates to production steps, etc.), the system will automatically update the nodes and relationships in the graph based on the new data. For example, a new equipment status will cause the attributes of the corresponding node to change, or a new process step will lead to the creation of a new node and the establishment of relationships with other nodes. Through this automated process, the dynamic evolution of the knowledge graph is ensured so that it is always consistent with the actual situation in the production process.

[0056] Users can monitor the automated construction and dynamic evolution of the knowledge graph through a provided visual interface. Not only does it provide update logging and monitoring capabilities, it also offers graph query functionality, allowing users to view specific changes to the graph after each evolution. Users can use query tools to search for nodes and relationships within the graph, obtaining real-time information about the production process. Furthermore, the system supports manual graph management, allowing users to modify, delete, or supplement information on specific nodes or relationships, further optimizing the knowledge graph's structure. The entire process is seamlessly automated, reducing manual operations and intervention, and improving management efficiency and accuracy.

[0057] In order to implement the method of the above embodiment, the present invention also provides a system for automatic knowledge graph construction and dynamic evolution method for ultra-high-speed optical module production, such as Figure 2 As shown, the system includes:

[0058] Data acquisition module, used to collect multi-dimensional data during the production process of ultra-high-speed optical modules;

[0059] The data processing module is used to clean the multi-dimensional data, remove noise, outliers, and redundant information, and perform standardization to uniformly format the multi-dimensional data from different sources; extract the key elements representing the production process and their interrelationships from the formatted multi-dimensional data to form structured data;

[0060] The knowledge graph automation construction module is used to construct a knowledge graph about ultra-high-speed optical module production based on structured data according to preset rules and relationship definitions. Each node in the knowledge graph represents a key element in the production process, and the edges in the knowledge graph represent the relationship between each node.

[0061] The knowledge graph dynamic evolution module is used to compare the data regularly collected during the production process of ultra-high-speed optical modules with the data in the existing knowledge graph. If new changes occur, the nodes and the relationships between nodes in the graph are automatically updated according to the new change data.

[0062] The data acquisition module reads data from various sources, such as production equipment, sensors, and log files, formats the raw data in a simple manner (e.g., converting it to a standardized JSON format), and regularly updates the storage medium with new data. Data is processed in a standardized JSON format, facilitating the subsequent automated knowledge graph construction and updates.

[0063] The data processing module primarily cleans the JSON data provided by the acquisition module, removing noise, outliers, and redundant information. After standardization, it formats data from different sources uniformly to ensure efficient data integration. It is also responsible for parsing the data stored in JSON files, extracting key fields from the production process, and integrating them into unified structured data (including fields, attributes, and relationships), resulting in high-quality structured data that meets the requirements of knowledge graph construction.

[0064] like Figure 3As shown, the knowledge graph automation module achieves full-process automation from data acquisition to knowledge graph construction and dynamic updates through the synergy of the database connection module, node creation module, relationship creation module, and transaction management module. As a foundational link, the database connection module is responsible for establishing a stable connection with the graph database Neo4j to ensure the real-time construction of the knowledge graph. The node creation module and relationship creation module respectively obtain node and node relationship information by parsing the JSON file obtained by the data processing module, and use Cypher statements to create nodes and node relationships in Neo4j, which can accurately depict the key entities and their interrelationships in the production process. During the knowledge graph construction process, the transaction management module ensures the atomicity, consistency, and integrity of all node and relationship creation operations. That is, each construction transaction is either fully successful or completely rolled back to avoid data errors or graph structure anomalies caused by partial execution. At the same time, concurrency control and logging are used to ensure the reliability and recoverability of the system in a multi-user environment.

[0065] like Figure 4 As shown in the figure, based on the knowledge graph automatic construction module, the knowledge graph dynamic evolution module further enhances the graph's real-time update capabilities. Specifically, the data change perception module captures JSON file updates in real time through periodic or event-triggered methods; the data reading and parsing module reads the latest production data from the JSON file; the knowledge graph update module obtains new node and node relationship information from the latest production data and creates nodes and node relationships in Neo4j using Cypher statements; and the rule engine module synchronizes new or changed data to the knowledge graph based on established format adaptation rules, parsing and mapping rules, and update and evolution rules, ensuring that the graph content remains highly consistent with the production process, thereby achieving intelligent, dynamic, and precise evolution of the knowledge graph.

[0066] Specifically, if Figure 5As shown, in the process of building a knowledge graph, data format adaptation rules, data parsing and mapping rules, automatic update and evolution rules, and knowledge graph interaction rules can be pre-set. The data format adaptation rule is: all production data is stored and transmitted in JSON format. The JSON format facilitates structured storage, reading and subsequent parsing of data. All types of data collected by production equipment, sensors, etc. will be converted into a standardized JSON format to ensure the accuracy of subsequent data processing and knowledge graph construction. The data parsing and mapping rules are: during the knowledge graph construction process, the system will extract key information from data from different sources (such as sensor data, production logs, etc.) according to predetermined parsing rules and map it to nodes, attributes and relationships in the graph. The mapping relationship between data will be specified by a rule file to ensure that different data sources can be processed in a unified and standardized manner. The automatic update and evolution rules are: during the dynamic evolution of the knowledge graph, the present invention defines the trigger mechanism and rules for automatic updates. When the system detects that the data in the JSON file has changed, the knowledge graph will automatically perform the update operation and automatically adjust the nodes and relationships of the graph according to the changed data content. The update process does not require manual intervention, ensuring that the graph always reflects the actual production status. The knowledge graph interaction rules are as follows: This invention ensures the stability and flexibility of the graph by defining the knowledge graph interaction rules. Different data sources can interact with the knowledge graph through the data interface to transmit the latest production data and knowledge. The knowledge graph continuously updates nodes and relationships through the data acquisition and processing module, thereby supporting subsequent data query, analysis and decision-making. During the construction and dynamic evolution of the knowledge graph, the effective exchange and update rules of data avoid data conflicts and inconsistencies while ensuring the accuracy of the graph.

[0067] Compared with the prior art, the present invention has the following advantages:

[0068] (1) Solved the efficiency and accuracy issues in the process of multi-source data updating and automated knowledge graph generation.

[0069] (2) By defining the data collection, processing and automation construction process, the automatic generation of knowledge graphs based on production data is achieved.

[0070] (3) A dynamic evolution mechanism of data is proposed, which automatically updates the knowledge graph when the data changes, ensuring the timeliness and accuracy of the knowledge graph.

[0071] (4) By dynamically reading production data stored in JSON files, the knowledge graph can achieve dynamic evolution to adapt to the ever-changing production environment and needs.

[0072] (5) By constructing a knowledge graph with automatic updating and evolution capabilities, the problems of real-time processing of production data and effective utilization of knowledge are solved, thus providing reliable knowledge support for subsequent data analysis and decision-making.

[0073] The present application also provides a computer-readable storage medium, such as a flash memory, a hard disk, a multimedia card, a card-type memory (e.g., an SD or DX memory), a random access memory (RAM), a static random access memory (SRAM), a read-only memory (ROM), an electrically erasable programmable read-only memory (EEPROM), a programmable read-only memory (PROM), a magnetic memory, a disk, an optical disk, a server, an App store, etc., on which a computer program is stored, and when the program is executed by a processor, a corresponding function is implemented. The computer-readable storage medium of this embodiment, when executed by a processor, implements the method for constructing and dynamically evolving an automated knowledge graph for the production of ultra-high-speed optical modules according to the method embodiment.

[0074] It should be pointed out that, according to the needs of implementation, the various steps / components described in this application can be split into more steps / components, or two or more steps / components or partial operations of steps / components can be combined into new steps / components to achieve the purpose of the present invention.

[0075] The size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0076] It should be understood that those skilled in the art can make improvements or changes based on the above description, and all such improvements and changes should fall within the scope of protection of the appended claims of the present invention.

Claims

1. An automated knowledge graph construction and dynamic evolution method for ultra-high-speed optical module production, characterized in that: The following steps are involved: S1, collect multi-dimensional data during the production process of ultra-high-speed optical modules; S2. Clean the multi-dimensional data, remove noise, outliers and redundant information, and perform standardization to uniformly format the multi-dimensional data from different sources; Extract the key elements and their interrelationships in the production process from the formatted multidimensional data to form structured data; S3. Construct a knowledge graph about the production of ultra-high-speed optical modules based on the structured data according to preset rules and relationship definitions, where each node in the knowledge graph represents a key element in the production process, and the edge in the knowledge graph represents the relationship between each node; S4. Regularly collect and process data from the production process of ultra-high-speed optical modules, and compare it with the data in the existing knowledge graph. If new changes occur, the nodes and the relationship between nodes in the graph are automatically updated according to the new change data.

2. The method for constructing and dynamically evolving an automated knowledge graph for ultra-high-speed optical module production according to claim 1, characterized in that: Multi-dimensional data includes equipment status, process parameters and production conditions.

3. The method for constructing and dynamically evolving an automated knowledge graph for ultra-high-speed optical module production according to claim 1, characterized in that: Specifically, the knowledge graph is automatically constructed by using Neo4j database and Python scripts.

4. The method for constructing and dynamically evolving an automated knowledge graph for ultra-high-speed optical module production according to claim 1, characterized in that: The collected multi-dimensional data are converted into a specific standardized JSON format in real time and stored in the local server in the form of files.

5. The method for constructing and dynamically evolving an automated knowledge graph for ultra-high-speed optical module production according to claim 1, characterized in that: Specifically, data collection is triggered by set thresholds, event-driven mechanisms or time intervals.

6. The method for constructing and dynamically evolving an automated knowledge graph for ultra-high-speed optical module production according to claim 1, characterized in that: Specifically, the automated construction and dynamic evolution of the knowledge graph are monitored through a visual interface.

7. The method for constructing and dynamically evolving an automated knowledge graph for ultra-high-speed optical module production according to claim 1, characterized in that: Set up query tools to retrieve nodes and relationships in the knowledge graph to obtain real-time information about the production process.

8. The method for constructing and dynamically evolving an automated knowledge graph for ultra-high-speed optical module production according to claim 1, characterized in that: Manually modify specific nodes of the knowledge graph and the relationship between specific nodes.

9. An automated knowledge graph construction and dynamic evolution system for ultra-high-speed optical module production, characterized in that: include: Data acquisition module, used to collect multi-dimensional data during the production process of ultra-high-speed optical modules; The data processing module is used to clean the multi-dimensional data, remove noise, outliers and redundant information, and perform standardization to uniformly format the multi-dimensional data from different sources; Extract the key elements and their interrelationships in the production process from the formatted multidimensional data to form structured data; The knowledge graph automatic construction module is used to construct a knowledge graph about the production of ultra-high-speed optical modules based on structured data according to preset rules and relationship definitions, where each node in the knowledge graph represents a key element in the production process, and the edge in the knowledge graph represents the relationship between each node; The knowledge graph dynamic evolution module is used to compare the data regularly collected during the production process of ultra-high-speed optical modules with the data in the existing knowledge graph. If new changes occur, the nodes in the graph and the relationships between them are automatically updated according to the new change data.

10. A computer storage medium, characterized in that: A computer program executable by a processor is stored therein, and the computer program executes the automated knowledge graph construction and dynamic evolution method for ultra-high-speed optical module production as described in any one of claims 1-8.

Images