Industrial instrument knowledge base construction method

Abstract

The invention relates to the technical field of industrial instrument knowledge bases, in particular to an industrial instrument knowledge base construction method. The method comprises the following steps: analyzing target audience information by obtaining medical instrument log data, and calculating a medical instrument use demand, thereby obtaining knowledge base information demand data; obtaining medical instrument product information by using the demand data, and performing function division, evaluation, diagnosis and assistance of the performance of the medical instrument; constructing a medical instrument knowledge graph according to the product and performance data, classifying medical instruments of the same kind, performing clinical effectiveness comparison, and identifying high-performance instruments; a database is used for storing a knowledge graph, and a knowledge base is optimized and retrieved, so that the understanding and safety of the medical apparatus and instruments are improved; according to the method, the industrial instrument knowledge base is constructed, so that the industrial instrument knowledge base can retrieve instrument knowledge more conveniently and quickly.

Description

Technical Field

[0001] The present invention relates to the technical field of industrial equipment knowledge base, and in particular to a method for constructing an industrial equipment knowledge base. Background Art

[0002] Build an efficient industrial device knowledge base, such as a medical device knowledge base, which can centrally store and organize detailed information on various medical devices, including their performance parameters, indications, methods of use, and clinical effects, thereby providing users with a unified and authoritative information acquisition platform. Through data mining and intelligent analysis, these knowledge bases can be updated in real time to ensure the latest medical device information. The construction of an industrial device knowledge base can also use knowledge graph technology to visualize the relationship and functions between different medical devices, helping users quickly understand the scope of application of the device and its interrelationships. This structured information presentation not only improves the accessibility of information, but also promotes knowledge sharing and collaboration, which helps to improve the accuracy of clinical decision-making. However, the traditional method of building an industrial device knowledge base has the problem of inaccurate analysis of device performance and low efficiency of the knowledge base in obtaining device information. Summary of the invention

[0003] Based on this, it is necessary to provide a method for constructing an industrial equipment knowledge base to solve at least one of the above technical problems.

[0004] To achieve the above purpose, a method for constructing an industrial equipment knowledge base includes the following steps:

[0005] Step S1: Obtain medical device log data; collect target audiences based on the medical device log data to obtain medical device target audience data; perform knowledge base information demand analysis based on the medical device target audience data to obtain industrial device knowledge base information demand data;

[0006] Step S2: using the information demand data of the industrial equipment knowledge base to obtain the product information of medical equipment, and obtaining the product data of medical equipment; dividing the functions of medical equipment according to the product data of medical equipment, and obtaining the diagnostic medical equipment data and the auxiliary medical equipment data; performing the performance analysis of medical equipment based on the diagnostic medical equipment data and the auxiliary medical equipment data, and obtaining the performance data of medical equipment;

[0007] Step S3: construct a medical device knowledge graph based on the medical device product data and the medical device performance data to obtain a medical device knowledge graph; classify similar medical devices based on the medical device knowledge graph and the medical device product data to obtain similar medical device data; compare the performance of similar devices based on similar medical device data and similar device clinical effectiveness data sets to obtain similar high-performance medical device data;

[0008] Step S4: Use a preset relational database to store knowledge in the medical device knowledge graph to obtain industrial device knowledge base data; optimize the industrial device knowledge base data based on similar high-performance medical device data to obtain industrial device knowledge base optimized data.

[0009] The present invention can deeply understand user needs by acquiring medical device log data and collecting target audiences, thereby providing basic data for information demand analysis of the knowledge base. This process ensures the pertinence and practicality of the knowledge base content, so that subsequent information acquisition is more in line with actual needs. Next, through the acquisition of medical device product information and functional division, the characteristics of different types of devices can be clarified, thereby providing a scientific basis for the performance analysis of diagnostic and auxiliary devices. This analysis not only reveals the performance indicators of various types of devices, but also helps users understand the effectiveness of their clinical applications. The construction of a medical device knowledge graph allows the relationship and function between various types of devices to be visualized, enhances the structuring and systematization of knowledge, and helps users quickly find what they need in complex information. By comparing the classification of similar medical devices with clinical effectiveness data sets, high-performance devices can be identified, providing a reliable basis for the procurement and use of medical institutions. At the same time, this comparative analysis helps users to be more scientific when choosing devices and reduces misjudgments caused by insufficient information. The knowledge graph is stored and optimized using a database to ensure the stability and scalability of the knowledge base. This optimization not only improves the accuracy and completeness of the data, but also makes subsequent knowledge updates and management more efficient. Overall, the synergy of each step enhances the application value of the industrial equipment knowledge base, provides powerful information support, and promotes the accuracy of clinical decision-making and the quality of medical services. Therefore, the present invention optimizes a traditional method for building an industrial equipment knowledge base, solves the problem of inaccurate equipment performance analysis and low efficiency of the knowledge base in acquiring equipment information in the traditional method for building an industrial equipment knowledge base, and improves the accuracy of equipment performance analysis and the efficiency of the knowledge base in acquiring equipment information.

[0010] Preferably, step S1 comprises the following steps:

[0011] Step S11: Obtaining medical device log data;

[0012] Step S12: collecting target audiences according to the medical device log data to obtain medical device target audience data;

[0013] Step S13: Calculate the use demand of the medical device according to the target audience data of the medical device and the log data of the medical device to obtain the use demand data of the medical device;

[0014] Step S14: performing a knowledge base information demand analysis based on the medical device target audience data and the medical device usage demand data to obtain industrial device knowledge base information demand data.

[0015] In the process of constructing the industrial equipment knowledge base of the present invention, the beneficial effects of each step significantly improve the pertinence and practicality of information. By obtaining the log data of medical devices, the information generated during the use process can be deeply excavated, which lays the foundation for subsequent analysis. The data not only includes the frequency of use, operating environment and usage of the device, but also provides key user feedback information, which is helpful to understand the performance of medical devices in practical applications. Then, according to these log data, the target audience is collected, the characteristics and needs of the user can be identified, and the collection and analysis of subsequent information are more targeted, so that the knowledge base can better serve the needs of actual users. By combining the target audience data of medical devices with the log data, the use demand calculation of medical devices can accurately capture the specific needs of users for medical devices in different situations. This calculation result provides data support for optimizing the function and design of medical devices, so that the development and improvement of equipment are more in line with market demand and user expectations. At the same time, the knowledge base information demand analysis based on the target audience data and the use demand data can identify the information type and content that need to be included in the knowledge base, thereby ensuring the effectiveness and practicality of the knowledge base in practical applications.

[0016] Preferably, step S13 comprises the following steps:

[0017] Step S131: Obtain disease epidemic trend data;

[0018] Step S132: Calculate clinical application demand based on medical device target audience data and disease epidemic trend data to obtain clinical application demand data of medical devices;

[0019] Step S133: Calculate the frequency of use of medical devices according to the clinical application demand data of medical devices and the epidemic trend data of diseases to obtain the frequency of use data of medical devices;

[0020] Step S134: Calculate the medical device usage demand using the medical device usage frequency data and the medical device clinical application demand data to obtain the medical device usage demand data.

[0021] In the process of constructing the industrial equipment knowledge base, the present invention obtains disease epidemic trend data to provide key basic information for the research and development and market positioning of medical devices, so that enterprises can accurately identify high-risk diseases and epidemic areas, thereby effectively planning the functions and specifications of products. Then, the clinical application requirements are calculated in combination with the target audience data of medical devices to ensure that the design of medical devices is more in line with the actual clinical use scenarios and needs, which helps to improve the treatment effect and reduce unnecessary medical expenses. In addition, by analyzing the relationship between clinical application requirements and disease epidemic trends, the frequency of use of devices in different diseases can be deeply understood, which provides data support for the rational allocation of resources, the optimization of production plans, and the prediction of market demand. Further comprehensive calculation using the frequency of use and clinical application demand data helps to comprehensively evaluate the potential demand for medical devices in the market and promote the adjustment of enterprises in product development. This series of steps complement each other, so that medical devices can effectively respond to market changes while meeting actual clinical needs, enhance the competitiveness and market share of enterprises, and ultimately improve the treatment experience and health outcomes. Through such a data-driven approach, the medical device industry can achieve more accurate and efficient development, promote technological progress and the improvement of medical services.

[0022] Preferably, step S2 comprises the following steps:

[0023] Step S21: using the information demand data of the industrial equipment knowledge base to obtain medical equipment product information, thereby obtaining medical equipment product data;

[0024] Step S22: dividing the medical device functions according to the medical device product data to obtain diagnostic medical device data and auxiliary medical device data;

[0025] Step S23: performing diagnostic medical device performance evaluation according to the diagnostic medical device data to obtain diagnostic medical device performance data;

[0026] Step S24: performing comfort evaluation on the auxiliary medical device data to obtain auxiliary medical device comfort data;

[0027] Step S25: Performing medical device performance analysis based on the auxiliary medical device comfort data and the medical device performance evaluation data to obtain medical device performance data.

[0028] The present invention obtains medical device product information by utilizing the information demand data of the industrial device knowledge base, which can ensure the accuracy and comprehensiveness of the data and lay a solid foundation for subsequent analysis. The efficiency of this process makes the information integration of medical devices more convenient and reduces the time cost of sorting. The division of functions helps to clarify the application fields of different medical devices, facilitates subsequent performance evaluation and market promotion, and performs performance evaluation on diagnostic medical devices, which can scientifically evaluate their effectiveness and reliability in clinical environments and ensure that the provided diagnostic results are accurate. In the comfort evaluation of auxiliary medical devices, paying attention to the use experience is the key to improving the acceptance of the device. This evaluation not only focuses on the function of the device, but also pays attention to the comfort of interaction, so as to effectively reduce the discomfort during use and improve the overall use satisfaction. In addition, the overall performance of medical devices can be deeply explored by combining comfort data with performance evaluation data for comprehensive analysis. This systematic analysis method makes the advantages and disadvantages of medical devices clear at a glance, which helps enterprises to optimize the design and function in a targeted manner in product development and improvement, thereby improving market competitiveness. In summary, the effective implementation of each step not only improves the quality and safety of medical devices, but also enhances the use experience, which is of great significance to promoting the progress and application of medical technology.

[0029] Preferably, step S23 includes the following steps:

[0030] Step S231: Acquire the device model according to the diagnostic medical device data to obtain the medical device model data;

[0031] Step S232: performing device operation simulation according to the medical device model data and the medical device product information data to obtain medical device operation simulation data;

[0032] Step S233: Calculating the device response time according to the medical device operation simulation data to obtain the medical device response time data;

[0033] Step S234: Calculate the detection accuracy according to the medical device operation simulation data to obtain the medical device detection accuracy data;

[0034] Step S235: estimating the medical device detection error probability according to the medical device detection accuracy data to obtain medical device detection error probability data;

[0035] Step S236: Perform diagnostic medical device performance evaluation based on the medical device detection error probability data and the medical device response time data to obtain diagnostic medical device performance data.

[0036] The present invention can provide a clear basis for product classification and subsequent analysis by obtaining the device model according to the diagnostic medical device data. Clear model data not only helps to manage and maintain medical devices of different models, but also facilitates the rapid identification and use of corresponding equipment. Subsequently, based on the medical device model and product information, operation simulation can provide a preview of real scenes for actual use, help predict the performance of the device in the clinical environment, thereby identifying potential problems in advance and reducing the risk in actual operation. On the basis of the operation simulation, the response time and detection accuracy of the device are calculated, and the performance of the device can be deeply analyzed. This process provides a quantitative evaluation of the real-time response capability and accuracy of the medical device, ensuring that doctors can obtain reliable results when using it, and improving safety and diagnostic effectiveness. Further, the probability of detection error is estimated according to the detection accuracy data, and the errors occurring during use can be identified, thereby helping medical institutions to formulate corresponding usage specifications and corrective measures to reduce the risk of misdiagnosis. Finally, the detection error probability and response time data are combined to evaluate the performance of the medical device, which can comprehensively evaluate the comprehensive performance of the device. This comprehensive evaluation method ensures the stability and reliability of medical devices in practical applications and promotes the continuous improvement of products. At the same time, this data-driven evaluation method provides manufacturers with valuable feedback, helping them better meet market needs and user expectations during the research and development process.

[0037] Preferably, step S24 comprises the following steps:

[0038] Step S241: extracting constituent materials using auxiliary medical device data to obtain constituent material data of the auxiliary medical device;

[0039] Step S242: Use the auxiliary medical device data to perform design structure analysis to obtain auxiliary medical device design structure data

[0040] Step S243: measuring the rigidity and weight of the auxiliary medical device according to the material data of the auxiliary medical device, and obtaining the rigidity data and weight data of the auxiliary device;

[0041] Step S244: Calculate the center of gravity of the auxiliary medical device according to the auxiliary medical device design structure data and the auxiliary medical device weight data to obtain the center of gravity data of the auxiliary medical device;

[0042] Step S245: using the auxiliary device rigidity data and the auxiliary medical device gravity center data to perform device support stability detection to obtain auxiliary device support stability data;

[0043] Step S246: Perform a comfort assessment based on the auxiliary device support stability data and the auxiliary device rigidity data to obtain auxiliary medical device comfort data.

[0044] The present invention can deeply understand the material properties and structural design of medical devices by using auxiliary medical device data to extract constituent materials and analyze design structures, thereby providing basic information for product optimization. This process not only helps to identify the physical and chemical properties of materials, but also evaluates the rationality of the design to ensure that the medical device has sufficient safety and reliability during use. Next, the rigidity and weight measurements of the constituent materials can effectively quantify the load-bearing capacity and stability of the device during use, providing important data support for subsequent performance evaluation. Further, the center of gravity calculation based on the design structure and weight data helps to evaluate the balance of the medical device during operation. The rationality of the center of gravity position directly affects the control performance and safety of the device, ensuring stability and comfort during use. Subsequently, the support stability test is performed using the rigidity data and the center of gravity data, which can systematically analyze the performance of the device in actual use, identify potential instability risks, and thus help designers to perform targeted optimization in product development. Finally, the comfort evaluation is performed based on the support stability data and the rigidity data, not only focusing on the functionality of the device, but also paying attention to the experience during use. This evaluation can ensure that the medical device meets the technical standards while also meeting the demand for comfort, reducing discomfort and improving user satisfaction. Overall, this series of steps systematically improves the design and performance of auxiliary medical devices through scientific analysis methods, enhances their safety and effectiveness in clinical applications, and lays a solid foundation for promoting the advancement of medical technology.

[0045] Preferably, step S3 comprises the following steps:

[0046] Step S31: construct a medical device knowledge graph based on the medical device product data and the medical device performance data to obtain a medical device knowledge graph;

[0047] Step S32: classifying the medical devices of the same type on the medical device knowledge graph and the medical device product data to obtain the medical devices of the same type data;

[0048] Step S33: Performing clinical effectiveness testing of medical devices based on data of similar medical devices to obtain a clinical effectiveness data set of similar devices;

[0049] Step S34: Compare the performance of similar medical devices based on similar medical device data and similar device clinical effectiveness data sets to obtain similar high-performance medical device data.

[0050] The present invention can effectively integrate and visualize the multi-dimensional information of medical devices by combining medical device product data and performance data to construct a medical device knowledge graph. This knowledge graph provides a global perspective for research and analysis, making the relationship between the characteristics, functions and performance of medical devices clearer, helping medical institutions and R&D teams to quickly obtain key information, thereby accelerating the decision-making process. Next, by classifying similar medical devices based on the knowledge graph and product data, various types of products on the market can be systematically sorted and classified, laying the foundation for subsequent comparison and analysis. Clinical effectiveness testing of similar medical devices can verify the effects of these devices in actual use through real clinical data. This process not only provides evidence support for the market promotion of medical devices, but also provides a scientific basis for medical institutions to select appropriate equipment, which helps to improve the quality and safety of medical services. At the same time, performance comparison based on similar medical device data and clinical effectiveness data can reveal the advantages and disadvantages of different devices, help manufacturers and medical institutions identify high-performance devices, and make more informed choices when purchasing and using them. This systematic methodology not only improves the transparency of medical devices, but also promotes the continuous improvement and innovation of products, and promotes the overall development of the medical device industry. Ultimately, the implementation of these steps can not only improve treatment outcomes, but also optimize the allocation of medical resources, achieve a higher level of medical services, and enhance trust in and satisfaction with medical institutions.

[0051] Preferably, step S31 includes the following steps:

[0052] Step S311: performing device usage function analysis based on medical device product data and medical device performance data to obtain medical device usage function data;

[0053] Step S312: Matching medical device indications according to the medical device usage function data to obtain medical device product indication data;

[0054] Step S313: Summarizing the medical device knowledge according to the medical device usage function data, the medical device product indication data, and the medical device performance data to obtain the medical device knowledge data;

[0055] Step S314: construct a medical device knowledge graph using the medical device product indication data and the medical device knowledge data to obtain a medical device knowledge graph.

[0056] The present invention can fully understand the specific application capabilities and operation procedures of the device by performing functional analysis on the product data and performance data of the medical device. This analysis not only provides a functional overview of the device for medical institutions, but also provides data support for the R&D team to optimize the design and improve the performance. Further, the indication correspondence based on the functional data of the medical device helps to clarify the clinical application scope of various medical devices. Subsequently, the device knowledge is summarized by combining the functional data, indication data and performance data to form a detailed medical device knowledge data set. This integrated information not only helps to improve the transparency of medical devices, but also provides a quick reference for clinicians, so that they can make scientific judgments based on data in complex medical decisions. Finally, the medical device knowledge map is constructed using indication data and knowledge data, which can realize the visualization of device characteristics and their applications. This map intuitively shows the relationship, indications and performance characteristics of different medical devices, providing researchers with valuable decision-making basis. Through this visualized knowledge map, medical institutions can more conveniently select devices and formulate usage strategies, and also provide rich basic data for future scientific research.

[0057] Preferably, step S34 includes the following steps:

[0058] Step S341: extracting high effectiveness data from clinical effectiveness data sets of similar devices using a preset effectiveness threshold to obtain similar high effectiveness device data;

[0059] Step S342: Calculate the device detection sensitivity of similar medical device data and similar high-effectiveness device data to obtain a similar device detection sensitivity data set;

[0060] Step S343: Calculate the diagnostic efficiency of the detection sensitivity data set of similar equipment to obtain a diagnostic efficiency data set of similar equipment;

[0061] Step S344: Compare the performance of similar equipment based on the diagnostic efficiency data set and the detection sensitivity data set of similar equipment to obtain similar high-performance medical equipment data.

[0062] The present invention can systematically identify devices that perform well in practical applications by extracting high-effectiveness devices from the clinical effectiveness data set of similar devices. This process not only ensures that medical institutions can give priority to those verified high-efficiency devices, but also provides more reliable medical options, significantly improving the treatment effect and safety. Subsequently, the device detection sensitivity calculation is performed based on the data of similar medical devices and high-effectiveness devices, which can quantify the device's ability to respond to small changes during the detection process. On the basis of the sensitivity calculation, the diagnostic efficiency of similar devices is further calculated, and the performance of each device in the diagnosis process can be evaluated. This evaluation not only helps doctors understand the actual effectiveness of the device in the clinical environment, but also promotes the improvement and optimization of the equipment and ensures the efficient use of medical resources. Next, by comprehensively comparing the diagnostic efficiency and detection sensitivity data, the performance differences between different types of devices can be deeply analyzed. This series of steps not only improves the effectiveness and efficiency of medical devices in clinical applications through scientific methods and data analysis, but also promotes the standardization and innovative development of the medical device industry. By identifying high-performance medical devices.

[0063] Preferably, step S4 comprises the following steps:

[0064] Step S41: Using a preset relational database to store knowledge in the medical device knowledge graph to obtain industrial device knowledge base data;

[0065] Step S42: searching for medical devices according to the industrial device knowledge base data to obtain medical device ranking data;

[0066] Step S43: Prioritizing the medical device ranking data according to the data of similar high-performance medical devices to obtain medical device priority ranking data;

[0067] Step S44: Optimizing the industrial equipment knowledge base data based on the medical equipment priority ranking data and similar high-performance medical equipment data to obtain industrial equipment knowledge base optimized data.

[0068] The present invention can efficiently integrate and manage a large amount of medical device related information by using a database to store knowledge of medical device knowledge graphs. This process not only improves the accessibility and security of data, but also provides a solid foundation for subsequent data analysis and application, ensuring that medical institutions and researchers can obtain the required information at any time. Then, based on the industrial equipment knowledge base data, retrieval can be performed to quickly find and analyze specific equipment, greatly improving the efficiency and accuracy of information acquisition, and helping to quickly find the most relevant equipment information in clinical decision-making. After obtaining the medical device ranking data, priority sorting is performed according to similar high-performance medical device data, which can ensure that medical institutions can give priority to those verified high-efficiency products when purchasing and using equipment. This priority sorting not only optimizes the allocation of resources, but also improves the quality of medical services. Further, knowledge base optimization based on priority sorting data and similar high-performance medical device data helps to continuously update and improve the knowledge base content to ensure that it is consistent with the latest clinical research and market trends. This optimization process can effectively eliminate outdated information and unnecessary redundancy, and improve the practicality and credibility of the knowledge base. At the same time, with the continuous improvement and updating of the industrial equipment knowledge base, medical institutions can better adapt to the rapidly changing medical environment and improve the scientificity and accuracy of decision-making.

[0069] The beneficial effects of the present invention are that the present invention can deeply understand user needs by acquiring medical device log data and collecting target audiences, thereby providing basic data for information demand analysis of the knowledge base. This process ensures the pertinence and practicality of the knowledge base content, so that subsequent information acquisition is more in line with actual needs. Next, through the acquisition of medical device product information and functional division, the characteristics of different types of devices can be clarified, thereby providing a scientific basis for performance analysis of diagnostic and auxiliary devices. This analysis not only reveals the performance indicators of various types of devices, but also helps users understand the effectiveness of their clinical applications. The construction of a medical device knowledge graph enables the relationship and function between various types of devices to be visualized, enhances the structuring and systematization of knowledge, and helps users quickly find what they need in complex information. By comparing the classification of similar medical devices with clinical effectiveness data sets, high-performance devices can be identified, providing a reliable basis for the procurement and use of medical institutions. At the same time, this comparative analysis helps users to be more scientific when choosing devices and reduces misjudgments caused by insufficient information. The knowledge graph is stored and optimized using a database to ensure the stability and scalability of the knowledge base. This optimization not only improves the accuracy and completeness of the data, but also makes subsequent knowledge updates and management more efficient. Overall, the synergy of each step enhances the application value of the industrial equipment knowledge base, provides powerful information support, and promotes the accuracy of clinical decision-making and the quality of medical services. Therefore, the present invention optimizes a traditional method for building an industrial equipment knowledge base, solves the problem of inaccurate equipment performance analysis and low efficiency of the knowledge base in acquiring equipment information in the traditional method for building an industrial equipment knowledge base, and improves the accuracy of equipment performance analysis and the efficiency of the knowledge base in acquiring equipment information. BRIEF DESCRIPTION OF THE DRAWINGS

[0070] Figure 1 A schematic diagram of the steps of a method for building an industrial equipment knowledge base;

[0071] Figure 2 for Figure 1 Detailed implementation steps of step S2 in the flowchart;

[0072] Figure 3 for Figure 1 Detailed implementation steps of step S3 in FIG.

[0073] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0074] The technical method of the present invention is described clearly and completely below in conjunction with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by technicians in this field without creative work are within the scope of protection of the present invention.

[0075] In addition, the accompanying drawings are only schematic illustrations of the present invention and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and their repeated description will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. The functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor methods and / or microcontroller methods.

[0076] It should be understood that, although the terms "first", "second", etc. may be used herein to describe various units, these units should not be limited by these terms. These terms are used only to distinguish one unit from another unit. For example, without departing from the scope of the exemplary embodiments, the first unit may be referred to as the second unit, and similarly the second unit may be referred to as the first unit. The term "and / or" used herein includes any and all combinations of one or more of the listed associated items.

[0077] To achieve this, please refer to Figures 1 to 3 , a method for constructing an industrial equipment knowledge base, comprising the following steps:

[0078] Step S1: Obtain medical device log data; collect target audiences based on the medical device log data to obtain medical device target audience data; perform knowledge base information demand analysis based on the medical device target audience data to obtain industrial device knowledge base information demand data;

[0079] Step S2: using the information demand data of the industrial equipment knowledge base to obtain the product information of medical equipment, and obtaining the product data of medical equipment; dividing the functions of medical equipment according to the product data of medical equipment, and obtaining the diagnostic medical equipment data and the auxiliary medical equipment data; performing the performance analysis of medical equipment based on the diagnostic medical equipment data and the auxiliary medical equipment data, and obtaining the performance data of medical equipment;

[0080] Step S3: construct a medical device knowledge graph based on the medical device product data and the medical device performance data to obtain a medical device knowledge graph; classify similar medical devices based on the medical device knowledge graph and the medical device product data to obtain similar medical device data; compare the performance of similar devices based on similar medical device data and similar device clinical effectiveness data sets to obtain similar high-performance medical device data;

[0081] Step S4: Use a preset relational database to store knowledge in the medical device knowledge graph to obtain industrial device knowledge base data; optimize the industrial device knowledge base data based on similar high-performance medical device data to obtain industrial device knowledge base optimized data.

[0082] In the embodiment of the present invention, reference Figure 1 The above is a schematic diagram of the steps of a method for constructing an industrial equipment knowledge base of the present invention. In this example, the method for constructing an industrial equipment knowledge base includes the following steps:

[0083] Step S1: Obtain medical device log data; collect target audiences based on the medical device log data to obtain medical device target audience data; perform knowledge base information demand analysis based on the medical device target audience data to obtain industrial device knowledge base information demand data;

[0084] In an embodiment of the present invention, the process of obtaining medical device log data involves collecting real-time operation records from various types of medical devices, including information such as usage time, fault reports, maintenance records, and user feedback. These log data are automatically extracted and stored through professional data collection tools to ensure the integrity and accuracy of the data. Next, target audiences are collected based on the medical device log data, and the log data is classified using data analysis tools to identify user groups and device types with high frequency of use. This process generates medical device target audience data, covering different medical institutions and doctor professional fields. Subsequently, a knowledge base information demand analysis is performed based on the medical device target audience data. Through questionnaire surveys and data mining methods, the actual needs of target users when using medical devices are deeply analyzed, and finally the industrial equipment knowledge base information demand data is obtained.

[0085] Step S2: using the information demand data of the industrial equipment knowledge base to obtain the product information of medical equipment, and obtaining the product data of medical equipment; dividing the functions of medical equipment according to the product data of medical equipment, and obtaining the diagnostic medical equipment data and the auxiliary medical equipment data; performing the performance analysis of medical equipment based on the diagnostic medical equipment data and the auxiliary medical equipment data, and obtaining the performance data of medical equipment;

[0086] In the embodiment of the present invention, the information demand data of the industrial equipment knowledge base is used to obtain the product information of medical devices, and the API interface is used to extract the latest product information of medical devices from medical device-related websites, databases and literature. This process includes product specifications, functional descriptions, indications and clinical trial data, etc., to generate detailed medical device product data. Subsequently, the functions are divided according to the medical device product data, and the products are classified according to their functions using the rule engine to identify diagnostic medical devices and auxiliary medical devices. This functional division is based on the specific use of medical devices and user feedback. Next, performance analysis is performed based on the diagnostic medical device data and the auxiliary medical device data, and statistical analysis software is used to perform data comparison and regression analysis to obtain medical device performance data.

[0087] Step S3: construct a medical device knowledge graph based on the medical device product data and the medical device performance data to obtain a medical device knowledge graph; classify similar medical devices based on the medical device knowledge graph and the medical device product data to obtain similar medical device data; compare the performance of similar devices based on similar medical device data and similar device clinical effectiveness data sets to obtain similar high-performance medical device data;

[0088] In an embodiment of the present invention, a medical device knowledge graph is constructed based on medical device product data and performance data, and a graph database is used to visualize the relationship between medical devices and their related characteristics, functions, and indications. A medical device knowledge graph is generated by defining nodes (such as devices, functions, indications) and edges (such as "belongs to", "applicable to", and other relationships). This graph provides intuitive support for subsequent data analysis and decision-making. Next, the medical device knowledge graph and medical device product data are classified into similar medical devices, and the products are grouped using a clustering algorithm to identify medical devices with similar functions and performances, and similar medical device data are generated. The performance of similar devices is compared based on similar medical device data and similar device clinical effectiveness data sets. A performance evaluation model is used to compare the performance of various types of devices based on quantitative indicators such as sensitivity, specificity, clinical effectiveness, etc., and finally similar high-performance medical device data is obtained.

[0089] Step S4: Use a preset relational database to store knowledge in the medical device knowledge graph to obtain industrial device knowledge base data; optimize the industrial device knowledge base data based on similar high-performance medical device data to obtain industrial device knowledge base optimized data.

[0090] In the embodiment of the present invention, a database is used to store knowledge of a medical device knowledge graph, a knowledge graph constructed using a preset relational database is used for persistent storage, and the industrial device knowledge base data is optimized based on similar high-performance medical device data. Data cleaning and normalization techniques are applied to remove redundant information and standardize data formats. This optimization process is achieved through a feedback mechanism, that is, the knowledge base is regularly updated and maintained using clinical usage feedback and market trends to ensure that the industrial device knowledge base always reflects the latest industry trends and clinical needs, ultimately forming an industrial device knowledge base.

[0091] Preferably, step S1 comprises the following steps:

[0092] Step S11: Obtaining medical device log data;

[0093] Step S12: collecting target audiences according to the medical device log data to obtain medical device target audience data;

[0094] Step S13: Calculate the use demand of the medical device according to the target audience data of the medical device and the log data of the medical device to obtain the use demand data of the medical device;

[0095] Step S14: performing a knowledge base information demand analysis based on the medical device target audience data and the medical device usage demand data to obtain industrial device knowledge base information demand data.

[0096] In an embodiment of the present invention, the process of obtaining medical device log data first needs to extract operation records from various types of medical devices, including equipment usage frequency, usage time, fault information and maintenance records. In specific implementation, data acquisition equipment and systems (for example, IoT sensors or special logging tools) are used to transmit real-time data to a central database. Each medical device is equipped with an identifier to accurately record its operating status and usage. Data storage uses a relational database management system (such as MySQL) to ensure structured storage and convenient query of data. In addition, log data must be backed up regularly to prevent data loss and damage, and to ensure the integrity and traceability of information. The step of collecting target audiences based on medical device log data involves the application of data analysis tools. Using data mining technology, different log data can be identified by classifying and screening.

[0097] The usage behavior patterns of user groups. In the specific implementation, the ETL (extraction, transformation, loading) tool was used to extract the log data into the data warehouse, and then the data analysis software (such as the Pandas library in R or Python) was used to process the data to identify high-frequency users, types of medical institutions, and professional fields of doctors. Results The target audience data of medical devices was generated. When calculating the use demand of medical devices based on the target audience data of medical devices and the log data of medical devices, the target audiences needed to be grouped first, and cluster analysis was performed based on their use frequency and functional preferences. In the specific implementation, the user behavior was modeled using statistical analysis software (such as SPSS or Scikit-learn in Python), and the actual use demand of various medical devices was calculated by cross-analyzing the demand characteristics of different groups. In addition, historical usage data needed to be analyzed to identify the usage patterns of specific devices in specific situations. Finally, the use demand data of medical devices was generated to reflect the demand intensity and usage of various devices by different user groups. When conducting the information demand analysis of the knowledge base, the target audience data of medical devices and the use demand data of medical devices were combined, and the key indicators were first identified by constructing an information demand analysis framework. In the specific implementation process, data analysis and visualization tools (such as Tableau or Power BI) are used to compare the needs of the target audience with the usage situation and extract important information demand points. This includes the user's specific requirements for the function, performance, maintenance and usage guidance of medical devices. By analyzing the common needs of different user groups, the information demand data of the industrial equipment knowledge base is generated.

[0098] Preferably, step S13 comprises the following steps:

[0099] Step S131: Obtain disease epidemic trend data;

[0100] Step S132: Calculate clinical application demand based on medical device target audience data and disease epidemic trend data to obtain clinical application demand data of medical devices;

[0101] Step S133: Calculate the frequency of use of medical devices according to the clinical application demand data of medical devices and the epidemic trend data of diseases to obtain the frequency of use data of medical devices;

[0102] Step S134: Calculate the medical device usage demand using the medical device usage frequency data and the medical device clinical application demand data to obtain the medical device usage demand data.

[0103] In an embodiment of the present invention, the implementation step of obtaining disease epidemic trend data involves the integration and analysis of multiple data sources. First, statistical data related to specific diseases are collected through public health databases, case records of medical institutions and epidemiological research results. The data may include the incidence, distribution and geographical prevalence of each disease in different time periods. Data processing tools such as Excel or R are used to clean the data to ensure the accuracy and consistency of the data, and data visualization tools (such as Tableau or Power BI) are used to display the epidemic trend, which is convenient for identifying key diseases and epidemic peaks, and forming a preliminary disease epidemic trend analysis report. The step of calculating clinical application requirements based on the target audience data of medical devices and the epidemic trend data of diseases includes first defining the characteristics of the target audience group, such as age, gender, medical history and other information, and using questionnaires, focus group discussions and other methods to collect relevant data. Then, combined with the epidemic trend data, the incidence of the target audience in a specific disease is analyzed, and the application requirements of medical devices in different populations are calculated using a cross analysis method. For example, by setting the demand weights of different populations, the audience characteristics and the epidemic trend of the disease are quantified, and finally the clinical application demand data of the medical device is obtained. Compare and analyze the acquired clinical application demand data of medical devices with historical usage records, and count the frequency of use of various types of devices in the same disease situation in the past. Relevant usage data can be collected through the hospital's medical record system to ensure the reliability of the data source. Subsequently, use statistical analysis tools (such as SPSS or SAS) to perform frequency distribution analysis to identify the actual use of the device in different clinical scenarios. When using medical device usage frequency data and medical device clinical application demand data to calculate the demand for medical device use, first integrate the two sets of data to build a comprehensive demand model. The model can use the weighted average method to multiply the frequency of use by the application demand to calculate the overall use demand of each device. Further analyze the integrated data through data analysis tools (such as the Pandas library in Python) to ensure that the final medical device usage demand data truly reflects market demand.

[0104] Preferably, step S2 comprises the following steps:

[0105] Step S21: using the information demand data of the industrial equipment knowledge base to obtain medical equipment product information, thereby obtaining medical equipment product data;

[0106] Step S22: dividing the medical device functions according to the medical device product data to obtain diagnostic medical device data and auxiliary medical device data;

[0107] Step S23: performing diagnostic medical device performance evaluation according to the diagnostic medical device data to obtain diagnostic medical device performance data;

[0108] Step S24: performing comfort evaluation on the auxiliary medical device data to obtain auxiliary medical device comfort data;

[0109] Step S25: Performing medical device performance analysis based on the auxiliary medical device comfort data and the medical device performance evaluation data to obtain medical device performance data.

[0110] As an example of the present invention, refer to Figure 2 As shown, in this example, step S2 includes:

[0111] Step S21: using the information demand data of the industrial equipment knowledge base to obtain medical equipment product information, thereby obtaining medical equipment product data;

[0112] In the embodiment of the present invention, the information demand data of the industrial equipment knowledge base is used to obtain the product information of medical equipment. First, multiple medical equipment databases and online platforms, such as FDA, CE marking databases and related industry association websites, are accessed to automatically extract the basic information of medical equipment, including name, model, manufacturer, specification and registration status, etc. The integrity and accuracy of the information are ensured, and the data is stored in a relational database, such as MySQL, after extraction, for subsequent query and analysis.

[0113] Step S22: dividing the medical device functions according to the medical device product data to obtain diagnostic medical device data and auxiliary medical device data;

[0114] In the embodiment of the present invention, when the functions of medical devices are divided according to the medical device product data, the extracted product data must first be classified. This process clarifies the functional attributes of various types of medical devices by establishing functional classification standards. In specific implementations, data analysis tools (such as Excel or the Pandas library in Python) are used to classify medical devices, and they are divided into diagnostic medical devices and auxiliary medical devices according to their functions. In this step, the purpose and function of each product are reviewed to ensure accurate classification.

[0115] Step S23: performing diagnostic medical device performance evaluation according to the diagnostic medical device data to obtain diagnostic medical device performance data;

[0116] In the embodiment of the present invention, when the performance evaluation is performed based on the diagnostic medical device data, the evaluation indicators, including sensitivity, specificity, accuracy, etc., must be determined first. During implementation, the performance data of each diagnostic medical device is collected by consulting clinical trial data, product instructions, and related literature. Statistical analysis software (such as R or Python) is used for data analysis, and the performance data of the diagnostic medical device is obtained by calculating the mean and standard deviation of various indicators.

[0117] Step S24: performing comfort evaluation on the auxiliary medical device data to obtain auxiliary medical device comfort data;

[0118] In the embodiment of the present invention, when evaluating the comfort of auxiliary medical device data, it is necessary to first establish a comfort evaluation standard, taking into account user experience factors such as weight, material, shape, etc. During the implementation process, user feedback, questionnaire survey results and clinical use data are collected, and statistical analysis methods (such as satisfaction scoring system) are used to quantitatively evaluate comfort. After the data is collected, data analysis tools are used to summarize and visualize the data to ensure that the comfort evaluation results are clear, and finally the comfort data of the auxiliary medical device is generated.

[0119] Step S25: Performing medical device performance analysis based on the auxiliary medical device comfort data and the medical device performance evaluation data to obtain medical device performance data.

[0120] In the embodiment of the present invention, when the performance analysis of medical devices is performed based on the auxiliary medical device comfort data and the medical device performance evaluation data, the two sets of data must first be integrated together, and a weighted calculation method is used to combine the comfort score and the performance index. In specific implementation, statistical software (such as SPSS or Scikit-learn in Python) is used to perform regression analysis on the data to determine the relationship between comfort and performance and obtain comprehensive performance analysis results. Finally, the medical device performance data is generated.

[0121] Preferably, step S23 includes the following steps:

[0122] Step S231: Acquire the device model according to the diagnostic medical device data to obtain the medical device model data;

[0123] Step S232: performing device operation simulation according to the medical device model data and the medical device product information data to obtain medical device operation simulation data;

[0124] Step S233: Calculating the device response time according to the medical device operation simulation data to obtain the medical device response time data;

[0125] Step S234: Calculate the detection accuracy according to the medical device operation simulation data to obtain the medical device detection accuracy data;

[0126] Step S235: estimating the medical device detection error probability according to the medical device detection accuracy data to obtain medical device detection error probability data;

[0127] Step S236: Perform diagnostic medical device performance evaluation based on the medical device detection error probability data and the medical device response time data to obtain diagnostic medical device performance data.

[0128] In the embodiment of the present invention, in the process of obtaining the device model according to the diagnostic medical device data, it is first necessary to extract relevant information from the existing medical device product database. This operation extracts the model, name and related characteristics of the device by constructing an SQL query. In the specific implementation, the query statement defined in the data management system (such as MySQL) is used to filter out the data of all diagnostic medical devices from the product table. On this basis, all model information is ensured to be consistent and non-redundant through data cleaning and standardization. The device operation simulation is performed according to the medical device model data and the medical device product information data. In the specific implementation, the key parameters of the device operation are first defined, including power, operating time and load conditions. A computer simulation tool (such as MATLAB Simulink) is used to build a dynamic model of the medical device, and the operating conditions are set and adjusted by inputting the device model and product information. During the simulation operation, the operating status of the device under different conditions is recorded, and the medical device operation simulation data is generated. When calculating the device response time and detection accuracy, the relevant information is first extracted from the operation simulation data. In the specific implementation, statistical analysis software (such as NumPy and SciPy libraries in Python) is used to calculate the response time of each simulation operation to determine the time required for the device to work stably from startup. At the same time, for the detection accuracy, set a standard test method, record the results of each measurement, and calculate the corresponding accuracy index. Combined with data analysis, generate medical device response time data and medical device detection accuracy data. When estimating the probability of detection error based on the medical device detection accuracy data, it is necessary to first establish an error model. In the specific implementation, the historical detection data and the current detection accuracy data are used to analyze the error using probability statistics methods (such as the normal distribution assumption). By calculating the mean and standard deviation of the error, the error probability distribution is derived. In this step, statistical software (such as R language) is used for data processing to ensure that the calculation of the error probability is based on real data. The medical device detection error probability data finally generated is used to evaluate the performance of diagnostic medical devices based on the medical device detection error probability data and medical device response time data. In the specific implementation, the error probability data and response time data are first integrated to construct a performance evaluation model. The multivariate statistical analysis method is used to analyze the impact of error probability and response time on the overall performance of the device, and the comprehensive performance index is calculated. The evaluation results are displayed using visualization tools (such as Tableau or Python's Matplotlib library) for easy analysis and interpretation. The diagnostic medical device performance data is finally generated.

[0129] Preferably, step S24 comprises the following steps:

[0130] Step S241: extracting constituent materials using auxiliary medical device data to obtain constituent material data of the auxiliary medical device;

[0131] Step S242: Use the auxiliary medical device data to perform design structure analysis to obtain auxiliary medical device design structure data

[0132] Step S243: measuring the rigidity and weight of the auxiliary medical device according to the material data of the auxiliary medical device, and obtaining the rigidity data and weight data of the auxiliary device;

[0133] Step S244: Calculate the center of gravity of the auxiliary medical device according to the auxiliary medical device design structure data and the auxiliary medical device weight data to obtain the center of gravity data of the auxiliary medical device;

[0134] Step S245: using the auxiliary device rigidity data and the auxiliary medical device gravity center data to perform device support stability detection to obtain auxiliary device support stability data;

[0135] Step S246: Perform a comfort assessment based on the auxiliary device support stability data and the auxiliary device rigidity data to obtain auxiliary medical device comfort data.

[0136] In the embodiment of the present invention, in the process of extracting constituent materials and analyzing design structures using auxiliary medical device data, it is first necessary to obtain relevant information from product documents and technical specifications. During implementation, the material composition data of auxiliary devices, including plastics, metals, and composite materials, are extracted from the medical device database through data mining technology. Next, the design structure of the auxiliary device is modeled using CAD software (such as AutoCAD), and each structural component is identified and its size, shape, and connection method are recorded. Through the material property database, the physical and mechanical properties of the materials used are analyzed, and a detailed report containing constituent material data and design structure data is finally generated. When measuring the rigidity of the device and the weight of the device according to the constituent material data of the auxiliary medical device, it is first necessary to use a special instrument to perform a rigidity test. In the specific implementation, a material testing machine (such as a universal testing machine) is used to perform a material rigidity test according to ISO standards, and the deformation of each material under different loads is recorded to calculate its rigidity value. At the same time, a precision electronic balance is used to measure the weight of the complete auxiliary device to ensure the accuracy of the data. The measured rigidity data and weight data are sorted and stored. When calculating the center of gravity of the device according to the design structure data and weight data of the auxiliary medical device, a three-dimensional model of the device is first required. In this process, CAD software is used to input the design structure data and generate a complete three-dimensional model. Then, by calculating the mass of each component and its position in space, the center of gravity calculation formula is applied to obtain the center of gravity position of the device. In the implementation, the symmetry of the device and the distribution of the material need to be considered to ensure the accuracy of the center of gravity calculation. The center of gravity data of the auxiliary medical device is finally generated. When using the auxiliary device rigidity data and the auxiliary medical device center of gravity data to perform the device support stability test, it is necessary to first build a stability test model. In the implementation, finite element analysis software (such as ANSYS or ABAQUS) is used to input the rigidity data and center of gravity position of the device, and the stability of the device is evaluated by simulating the support conditions under different load conditions. During the analysis process, the deformation and stress distribution of the device under force are observed to ensure that all important parameters are taken into account. When evaluating the comfort based on the auxiliary device support stability data and auxiliary device rigidity data, it is necessary to establish a comfort evaluation standard and consider the user experience. In the specific implementation, questionnaires and user feedback are used to collect data, and combined with the support stability and rigidity data, the comfort is quantitatively evaluated by weighted analysis method. Based on the analysis results, a comfort score is generated and visualized for easy understanding and decision-making. The final auxiliary medical device comfort data is formed.

[0137] Preferably, step S3 comprises the following steps:

[0138] Step S31: construct a medical device knowledge graph based on the medical device product data and the medical device performance data to obtain a medical device knowledge graph;

[0139] Step S32: classifying the medical devices of the same type on the medical device knowledge graph and the medical device product data to obtain the medical devices of the same type data;

[0140] Step S33: Performing clinical effectiveness testing of medical devices based on data of similar medical devices to obtain a clinical effectiveness data set of similar devices;

[0141] Step S34: Compare the performance of similar medical devices based on similar medical device data and similar device clinical effectiveness data sets to obtain similar high-performance medical device data.

[0142] As an example of the present invention, refer to Figure 3 As shown, in this example, step S3 includes:

[0143] Step S31: construct a medical device knowledge graph based on the medical device product data and the medical device performance data to obtain a medical device knowledge graph;

[0144] In an embodiment of the present invention, a medical device knowledge graph is constructed based on medical device product data and medical device performance data. First, relevant product information, including model, function, scope of application and performance indicators, etc., needs to be extracted from the medical device database. By using graph database technology (such as Neo4j), this information is constructed into a structure of nodes and edges, and the relationship between products (such as similarity, functional association, etc.) is represented graphically. During the implementation process, data mining algorithms are used to automatically identify and connect relevant information to generate a preliminary knowledge graph. After verification and adjustment, it is ensured that the knowledge graph can accurately reflect the characteristics and relationships of medical devices, and finally a complete medical device knowledge graph is output.

[0145] Step S32: classifying the medical devices of the same type on the medical device knowledge graph and the medical device product data to obtain the medical devices of the same type data;

[0146] In an embodiment of the present invention, the medical device knowledge graph and medical device product data are classified into similar medical devices. First, the classification criteria need to be defined, for example, based on the functions, fields of use and technical characteristics of the medical devices. During implementation, similar products are clustered using graph algorithms (such as community detection algorithms) through the established node relationships in the graph to form medical device data sets of various categories. Subsequently, the classification results are verified using existing product data to ensure that the devices in each category are similar in function and performance. Upon completion, the data of similar medical devices are sorted and stored.

[0147] Step S33: Performing clinical effectiveness testing of medical devices based on data of similar medical devices to obtain a clinical effectiveness data set of similar devices;

[0148] In an embodiment of the present invention, the clinical effectiveness test of medical devices is performed based on the data of similar medical devices. During implementation, a representative sample must first be selected to randomly extract a certain number of devices from a data set of similar medical devices. Subsequently, a clinical trial plan is formulated, and the clinical effectiveness of each device is evaluated using a standardized testing process. Data collection includes feedback after clinical use, satisfaction surveys, and efficacy evaluations. Statistical analysis tools (such as SPSS) are used to analyze the collected data, determine the effectiveness indicators of each device, and ultimately generate a clinical effectiveness data set for similar devices.

[0149] Step S34: Compare the performance of similar medical devices based on similar medical device data and similar device clinical effectiveness data sets to obtain similar high-performance medical device data.

[0150] In an embodiment of the present invention, the performance of similar devices is compared based on the data of similar medical devices and the clinical effectiveness data set of similar devices. First, the data that has undergone clinical effectiveness testing is integrated with the performance data of similar medical devices to construct a comprehensive data set. During the implementation process, a multidimensional comparative analysis method is used to analyze the differences in multiple dimensions such as performance, effectiveness, and user feedback between different devices. Statistical chart tools (such as Excel or Tableau) are used to display the comparison results to ensure that the advantages and disadvantages of each type of device are clear. Finally, data on similar high-performance medical devices is generated.

[0151] Preferably, step S1 comprises the following steps:

[0152] Step S311: performing device usage function analysis based on medical device product data and medical device performance data to obtain medical device usage function data;

[0153] Step S312: Matching medical device indications according to the medical device usage function data to obtain medical device product indication data;

[0154] Step S313: Summarizing the medical device knowledge according to the medical device usage function data, the medical device product indication data, and the medical device performance data to obtain the medical device knowledge data;

[0155] Step S314: construct a medical device knowledge graph using the medical device product indication data and the medical device knowledge data to obtain a medical device knowledge graph.

[0156] In an embodiment of the present invention, first, relevant information including product model, purpose, operation method and performance parameters is extracted from the medical device database. These data can be obtained from the relational database through structured query language (SQL) to ensure the accuracy and completeness of the data. Subsequently, a data analysis tool (such as Python's Pandas library) is used to organize and clean the extracted data to identify the use functions of different devices. By setting functional classification standards, the devices are divided into different functional groups, such as diagnosis, monitoring, treatment, etc. Finally, the analysis results are integrated to generate medical device use function data, and the obtained use function data is used to establish a mapping relationship table to clarify the connection between each device function and the corresponding indication. This process uses literature retrieval and clinical guidelines to collect existing indication information, and through analysis and comparison, ensure that the indication of each device corresponds accurately. The data can be organized and classified using Excel, and a visual chart can be generated for easy understanding. After completion, the medical device product indication data is recorded, the device knowledge is summarized, and the medical device knowledge data is obtained. This step combines medical device use function data, medical device product indication data and medical device performance data. First, the above three types of data are integrated into a unified data framework. Through data association and matching, the performance of each device under different functions and indications is identified. Use data analysis tools (such as the dplyr package of R language) for statistical analysis to calculate the average performance value, effectiveness index, etc. of each device. Through cross-analysis, the comprehensive knowledge data of medical devices is summarized to form knowledge base entries with practical value, laying the foundation for the construction of knowledge graphs. Use medical device product indication data and medical device knowledge data to construct medical device knowledge graphs, and clarify the structure of knowledge graphs, including nodes (medical devices, indications, functions) and edges (relationships). According to the data sorted in steps S312 and S313, use a graph database (such as Neo4j) to create nodes and define the relationship between each node. During the implementation process, use a graph database query language (such as Cypher) to insert and update data to ensure that the graph reflects the logical relationship and functional association between devices. Through this structured information presentation method, the construction of the medical device knowledge graph is completed.

[0157] Preferably, step S34 includes the following steps:

[0158] Step S341: extracting high effectiveness data from clinical effectiveness data sets of similar devices using a preset effectiveness threshold to obtain similar high effectiveness device data;

[0159] Step S342: Calculate the device detection sensitivity of similar medical device data and similar high-effectiveness device data to obtain a similar device detection sensitivity data set;

[0160] Step S343: Calculate the diagnostic efficiency of the detection sensitivity data set of similar equipment to obtain a diagnostic efficiency data set of similar equipment;

[0161] Step S344: Compare the performance of similar equipment based on the diagnostic efficiency data set and the detection sensitivity data set of similar equipment to obtain similar high-performance medical equipment data.

[0162] In an embodiment of the present invention, relevant data is extracted from the clinical effectiveness data set of similar devices, focusing on the clinical trial results and feedback of approved devices. This process uses data cleaning tools, such as the Pandas library in Python, to screen out devices with effectiveness scores higher than the set threshold. These devices are classified to form a high-effectiveness device data set, and the device detection sensitivity is calculated to obtain a similar device detection sensitivity data set. This step requires combining similar medical device data and similar high-effectiveness device data. First, define a calculation formula for detection sensitivity, which usually involves true positive and false negative values. By performing experimental tests on the device, collect the test results of each device under different conditions, and record the corresponding sensitivity index. Use statistical analysis software (such as R language) to calculate sensitivity to ensure that the sensitivity results of each device are scientifically verified. Finally, the results are summarized to form a similar device detection sensitivity data set, and the diagnostic efficiency of the similar device detection sensitivity data set is calculated. First, define a calculation method for diagnostic efficiency, which usually includes a true positive rate and a true negative rate. According to the sensitivity data obtained in step S342, statistical analysis is performed in combination with specific clinical application scenarios. Use tools such as R language or Excel to calculate the diagnostic efficiency index of each device and generate a data set. By comparing the diagnostic results of different devices, we can identify devices that perform well under specific conditions and ensure that each data entry is accompanied by a corresponding effectiveness indicator. Finally, a diagnostic efficiency data set for similar devices is formed, and the performance of similar devices is compared based on the diagnostic efficiency data set and the detection sensitivity data set of similar devices. First, set the comparison criteria, including key indicators such as sensitivity, specificity, and diagnostic efficiency. Use statistical analysis tools (such as the SciPy library in Python) to perform multivariate analysis on the performance data of different devices. By using methods such as analysis of variance (ANOVA) or paired t-test, determine the differences and superiority of each device under different performance indicators. Display the results in the form of visual charts to make the performance comparison of different devices more intuitive. Finally, generate data on similar high-performance medical devices.

[0163] Preferably, step S4 comprises the following steps:

[0164] Step S41: Using a database to store knowledge of the medical device knowledge graph to obtain industrial device knowledge base data;

[0165] Step S42: searching for medical devices according to the industrial device knowledge base data to obtain medical device ranking data;

[0166] Step S43: Prioritizing the medical device ranking data according to the data of similar high-performance medical devices to obtain medical device priority ranking data;

[0167] Step S44: Optimizing the industrial equipment knowledge base data based on the medical equipment priority ranking data and similar high-performance medical equipment data to obtain industrial equipment knowledge base optimized data.

[0168] In an embodiment of the present invention, a database is used to store knowledge of a medical device knowledge graph to generate industrial device knowledge base data. First, a relational database management system (such as MySQL or PostgreSQL) is selected as the basis for knowledge storage. When building a database architecture, multiple tables are designed to store different types of data, such as basic information of medical devices, performance indicators, clinical effectiveness, etc. In this process, a data model design tool (such as ERDPlus) is used to draw an entity relationship diagram to clarify the association between the tables. Then, various types of information extracted from the knowledge graph are inserted into the corresponding table item by item through SQL statements. To ensure the consistency and integrity of the data, necessary constraints such as primary keys and foreign keys are set. After completion, industrial device knowledge base data is formed, and medical devices are retrieved based on the industrial device knowledge base data to obtain medical device sorting data. First, a query interface is constructed, and an API is implemented using a Web framework such as Flask or Django so that users can search by entering keywords. Then, the relevant medical device data is obtained from the database using SQL query statements. The key is to optimize the efficiency of the query statement to ensure that the results can be returned quickly even when the amount of data is large. The results are returned in a structured form, including information such as the name, type, and performance indicators of the device. Then, according to the set sorting criteria, such as effectiveness score or market share, the search results are sorted, and finally the medical device sorting data is generated, and the data of similar high-performance medical devices are extracted, and the data is merged with the medical device sorting data generated in step S42 using SQL query. By comparing key performance indicators, such as detection sensitivity, response time, etc., the calculation rules for priority sorting are established. This process can use Python for data analysis, and use the Pandas library to merge and calculate the data frame. By setting weights, each indicator is scored, and the results are sorted from high to low according to priority, and finally the medical device priority sorting data is formed, the medical device priority sorting data is analyzed, the low-priority devices that need to be optimized are identified, and corresponding optimization strategies are formulated, such as adding product information or enhancing market promotion efforts. Then, the corresponding records in the database are updated using SQL statements to ensure that the advantages of high-performance devices are reflected in the knowledge base. Next, the optimized data are evaluated using statistical analysis tools (such as R or Python) to ensure the effectiveness of the optimization measures. Finally, the optimization results are stored in the database to form the industrial device knowledge base optimization data.

[0169] The above description is only a specific embodiment of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but should conform to the widest scope consistent with the principles and novel features invented herein.

Claims

1. A method for constructing an industrial equipment knowledge base, characterized in that: The following steps are involved: Step S1: Obtain medical device log data; collect target audiences based on the medical device log data to obtain medical device target audience data; perform knowledge base information demand analysis based on the medical device target audience data to obtain industrial device knowledge base information demand data; Step S2: using the information demand data of the industrial equipment knowledge base to obtain the product information of medical equipment, and obtaining the product data of medical equipment; dividing the functions of medical equipment according to the product data of medical equipment, and obtaining the diagnostic medical equipment data and the auxiliary medical equipment data; performing the performance analysis of medical equipment based on the diagnostic medical equipment data and the auxiliary medical equipment data, and obtaining the performance data of medical equipment; Step S3: construct a medical device knowledge graph based on the medical device product data and the medical device performance data to obtain a medical device knowledge graph; classify similar medical devices based on the medical device knowledge graph and the medical device product data to obtain similar medical device data; compare the performance of similar devices based on similar medical device data and similar device clinical effectiveness data sets to obtain similar high-performance medical device data; Step S4: Use a preset relational database to store knowledge in the medical device knowledge graph to obtain industrial device knowledge base data; optimize the industrial device knowledge base data based on similar high-performance medical device data to obtain industrial device knowledge base optimized data.

2. The method for constructing an industrial equipment knowledge base according to claim 1, characterized in that: Step S1 includes the following steps: Step S11: Obtaining medical device log data; Step S12: collecting target audiences according to the medical device log data to obtain medical device target audience data; Step S13: Calculate the use demand of medical devices according to the target audience data of medical devices to obtain the use demand data of medical devices; Step S14: performing a knowledge base information demand analysis based on the medical device target audience data and the medical device usage demand data to obtain industrial device knowledge base information demand data.

3. The method for constructing an industrial equipment knowledge base according to claim 2, characterized in that: Step S13 includes the following steps: Step S131: Obtain disease epidemic trend data; Step S132: Calculate clinical application demand based on medical device target audience data and disease epidemic trend data to obtain clinical application demand data of medical devices; Step S133: Calculate the frequency of use of medical devices according to the clinical application demand data of medical devices and the epidemic trend data of diseases to obtain the frequency of use data of medical devices; Step S134: Calculate the medical device usage demand using the medical device usage frequency data and the medical device clinical application demand data to obtain the medical device usage demand data.

4. The method for constructing an industrial equipment knowledge base according to claim 1, characterized in that: Step S2 includes the following steps: Step S21: using the information demand data of the industrial equipment knowledge base to obtain medical equipment product information, thereby obtaining medical equipment product data; Step S22: dividing the medical device functions according to the medical device product data to obtain diagnostic medical device data and auxiliary medical device data; Step S23: performing diagnostic medical device performance evaluation according to the diagnostic medical device data to obtain diagnostic medical device performance data; Step S24: performing comfort evaluation on the auxiliary medical device data to obtain auxiliary medical device comfort data; Step S25: Performing medical device performance analysis based on the auxiliary medical device comfort data and the medical device performance evaluation data to obtain medical device performance data.

5. The method for constructing an industrial equipment knowledge base according to claim 4, characterized in that: Step S23 includes the following steps: Step S231: Acquire the device model according to the diagnostic medical device data to obtain the medical device model data; Step S232: performing device operation simulation according to the medical device model data and the medical device product information data to obtain medical device operation simulation data; Step S233: Calculating the device response time according to the medical device operation simulation data to obtain the medical device response time data; Step S234: Calculate the detection accuracy according to the medical device operation simulation data to obtain the medical device detection accuracy data; Step S235: estimating the medical device detection error probability according to the medical device detection accuracy data to obtain medical device detection error probability data; Step S236: Perform diagnostic medical device performance evaluation based on the medical device detection error probability data and the medical device response time data to obtain diagnostic medical device performance data.

6. The method for constructing an industrial equipment knowledge base according to claim 4, characterized in that: Step S24 includes the following steps: Step S241: extracting constituent materials using auxiliary medical device data to obtain constituent material data of the auxiliary medical device; Step S242: Use the auxiliary medical device data to perform design structure analysis to obtain auxiliary medical device design structure data Step S243: measuring the rigidity and weight of the auxiliary medical device according to the material data of the auxiliary medical device, and obtaining the rigidity data and weight data of the auxiliary device; Step S244: Calculate the center of gravity of the auxiliary medical device according to the auxiliary medical device design structure data and the auxiliary medical device weight data to obtain the center of gravity data of the auxiliary medical device; Step S245: using the auxiliary device rigidity data and the auxiliary medical device gravity center data to perform device support stability detection to obtain auxiliary device support stability data; Step S246: Perform a comfort assessment based on the auxiliary device support stability data and the auxiliary device rigidity data to obtain auxiliary medical device comfort data.

7. The method for constructing an industrial equipment knowledge base according to claim 1, characterized in that: Step S3 includes the following steps: Step S31: construct a medical device knowledge graph based on the medical device product data and the medical device performance data to obtain a medical device knowledge graph; Step S32: classifying the medical devices of the same type on the medical device knowledge graph and the medical device product data to obtain the medical devices of the same type data; Step S33: Performing clinical effectiveness testing of medical devices based on data of similar medical devices to obtain a clinical effectiveness data set of similar devices; Step S34: Compare the performance of similar medical devices based on similar medical device data and similar device clinical effectiveness data sets to obtain similar high-performance medical device data.

8. The method for constructing an industrial equipment knowledge base according to claim 7, characterized in that: Step S31 The following steps are involved: Step S311: performing device usage function analysis based on medical device product data and medical device performance data to obtain medical device usage function data; Step S312: Matching medical device indications according to the medical device usage function data to obtain medical device product indication data; Step S313: Summarizing the medical device knowledge according to the medical device usage function data, the medical device product indication data, and the medical device performance data to obtain the medical device knowledge data; Step S314: construct a medical device knowledge graph using the medical device product indication data and the medical device knowledge data to obtain a medical device knowledge graph.

9. The method for constructing an industrial equipment knowledge base according to claim 7, characterized in that: Step S34 includes the following steps: Step S341: extracting high effectiveness data from clinical effectiveness data sets of similar devices using a preset effectiveness threshold to obtain similar high effectiveness device data; Step S342: Calculate the device detection sensitivity of similar medical device data and similar high-effectiveness device data to obtain a similar device detection sensitivity data set; Step S343: Calculate the diagnostic efficiency of the detection sensitivity data set of similar equipment to obtain a diagnostic efficiency data set of similar equipment; Step S344: Compare the performance of similar equipment based on the diagnostic efficiency data set and the detection sensitivity data set of similar equipment to obtain similar high-performance medical equipment data.

10. The method for constructing an industrial equipment knowledge base according to claim 1, characterized in that: Step S4 includes the following steps: Step S41: Using a preset relational database to store knowledge in the medical device knowledge graph to obtain industrial device knowledge base data; Step S42: searching for medical devices according to the industrial device knowledge base data to obtain medical device ranking data; Step S43: Prioritizing the medical device ranking data according to the data of similar high-performance medical devices to obtain medical device priority ranking data; Step S44: Optimizing the industrial equipment knowledge base data based on the medical equipment priority ranking data and similar high-performance medical equipment data to obtain industrial equipment knowledge base optimized data.

Images