Design method and system of reaction cup mold for in-vitro diagnosis

Abstract

The invention relates to the technical field of mold design, in particular to a reaction cup mold design method and system for in-vitro diagnosis. The method comprises the following steps: obtaining a reaction cup mold production log and a preset reaction cup mold design drawing; performing multi-application scene deep analysis and scene diagnosis demand mining one by one according to the reaction cup mold production log so as to obtain a diagnosis demand of each scene; performing multi-stage production process analysis on the reaction cup mold production log, performing process logic dependency mining, and constructing a production process logic law diagram; and carrying out mold structure deep analysis on a preset reaction cup mold design drawing, and carrying out standardized module assembly definition based on the production process logic rule diagram, so as to generate a plurality of standardized module assemblies. According to the method, efficient and accurate reaction cup mold design is provided through multi-scene self-adaptive production parameter adjustment.

Description

Technical Field

[0001] The present invention relates to the technical field of mold design, and in particular to a method and system for designing a mold for a reaction cup for in vitro diagnosis. Background Art

[0002] In vitro diagnostic (IVD) technology plays an important role in the field of medical diagnosis, especially in the early screening and monitoring of diseases. With the continuous advancement of science and technology, IVD technology continues to develop in the direction of high precision and high efficiency, especially in the design of reaction cup molds, the requirements are getting higher and higher. As a key component of in vitro diagnostic equipment, the design of the reaction cup mold directly affects the reagent reaction effect and the accuracy of the results during the diagnosis process. Therefore, accurate reaction cup mold design is not only the core to ensure the performance of in vitro diagnostic products, but also a key link to improve detection accuracy and ensure patient safety.

[0003] At present, the traditional reaction cup mold design method usually relies on experience and manual design. The design process is relatively cumbersome and has certain limitations when facing complex and diversified needs. Traditional methods often find it difficult to balance the accuracy, production efficiency and design flexibility of the mold, especially when dealing with variable factors such as different sample types, reaction temperatures, reaction times, etc., the design lacks a unified standardized standard. At the same time, due to the accelerating development of the in vitro diagnostic industry, the requirements for molds are becoming increasingly complex, and it is necessary to complete the optimized design in different scenarios in a short period of time to adapt to changing market demands and technological advances.

[0004] In this context, traditional cuvette mold design methods face many challenges, such as low design efficiency, difficulty in meeting personalized needs, lack of automated optimization methods, etc. In order to cope with these problems, the industry urgently needs a new intelligent and systematic design method that can provide efficient and accurate cuvette mold design solutions according to the needs of different application scenarios. Summary of the invention

[0005] In order to solve the above technical problems, the present invention proposes a method and system for designing a reaction cup mold for in vitro diagnosis, so as to solve at least one of the above technical problems.

[0006] To achieve the above object, the present invention provides a method for designing a mold for an in vitro diagnostic reaction cup, comprising the following steps: Step S1: Obtain the reaction cup mold production log and the preset reaction cup mold design drawing; perform in-depth analysis of multiple application scenarios and scene-by-scene diagnostic demand mining based on the reaction cup mold production log, so as to obtain the diagnostic demand of each scene; Step S2: Conduct multi-stage production process analysis on the production log of the reaction cup mold, and perform process logic dependency mining to construct a production process logic diagram; Step S3: Conduct in-depth analysis of the mold structure of the preset reaction cup mold design drawing, and define standardized module components based on the production process logic diagram to generate multiple standardized module components; Step S4: Design adaptive requirement parameters for multiple standardized module components according to the diagnostic requirements of each scenario, and perform production simulation for multi-scenario requirements to generate comprehensive evaluation values for mold construction simulation in multiple scenarios; Step S5: Perform iterative parameter optimization calculation and mold structure optimization for each scenario based on the comprehensive evaluation values of mold construction simulation in multiple scenarios to generate an optimized mold structure for each scenario requirement; Step S6: Adjust the process parameters of the dynamic production line according to the optimized mold structure required for each scenario, thereby constructing a mold production monitoring and optimization engine.

[0007] The present invention establishes a complete data foundation by obtaining production logs and design drawings. This is the basis for subsequent analysis, ensuring that all decisions and optimizations are based on actual production data and design requirements. Through in-depth analysis of multiple application scenarios and excavation of diagnostic requirements for each scenario, potential challenges and requirements in each scenario can be accurately identified, providing targeted information for subsequent optimization. Through multi-stage analysis of the production process, the process characteristics and problems in each stage of the production process can be comprehensively understood. This provides comprehensive data support for subsequent optimization. Process logic dependency mining helps identify the critical path and potential bottlenecks in production, enabling special attention and optimization of key links in the production process. By analyzing the bottlenecks and dependencies in the production process, it is possible to identify in advance which process stages or links may lead to low production efficiency or quality problems, and then take measures for optimization. By deeply analyzing the design drawings and combining with the production process rules, the complex mold structure can be disassembled into standardized modular components, which can simplify the design, reduce production complexity, and improve the universality of the components. It can ensure the coordination between mold design and production process, avoid conflicts between design and process, and thus improve production efficiency and product quality. Adaptive parameter design of modular components according to the diagnostic requirements of different scenarios enables the mold design of each scenario to accurately match the actual requirements, improving the adaptability and effectiveness of the mold. Through multi-scenario production simulation, the feasibility and performance of the design can be verified in advance, ensuring that it can operate efficiently and meet various requirements in actual production. By simulating and evaluating and optimizing the parameters, the deficiencies in the mold design can be found and targeted improvements can be made to optimize the structure and improve the performance and lifespan of the mold. The mold structure of each scenario can be individually optimized to ensure that each production link can achieve the best effect under different requirements, avoiding a one-size-fits-all design approach and improving production adaptability. It can dynamically adjust the process parameters of the production line according to the optimized mold design to ensure that the production line always operates with optimal parameters, improving production efficiency and reducing resource waste. The constructed mold production monitoring and optimization engine can monitor various parameters in the production process in real time, promptly detect abnormalities and make adjustments, thereby ensuring the stability of production and the consistency of products. Through monitoring and feedback, a closed-loop optimization system is formed, enabling continuous optimization of each link in mold production and continuously improving production efficiency and product quality.

[0008] In this specification, a reaction cup mold design system for in vitro diagnosis is provided, which is used to execute the reaction cup mold design method for in vitro diagnosis as described above, and includes: A scenario requirement module, configured to obtain the production log of the reaction cup mold and the preset reaction cup mold design drawing; perform in-depth analysis of multiple application scenarios and excavation of diagnostic requirements for each scenario according to the production log of the reaction cup mold, so as to obtain the diagnostic requirements of each scenario; A logical dependency mining module, which is used to perform multi-stage production process analysis on the production logs of reaction cup molds, mine process logical dependencies, and construct a production process logical law diagram; A module component definition module, which is used to deeply analyze the mold structure of a preset reaction cup mold design drawing, and perform standardized module component definition based on the production process logical law diagram, so as to generate multiple standardized module components; A demand production simulation module, which is used to perform adaptive demand parameter design on multiple standardized module components according to the diagnostic requirements of each scenario, and perform multi-scenario demand production simulation to generate comprehensive evaluation values of mold construction simulation for multiple scenarios; A mold structure optimization module, which is used to perform iterative parameter optimization calculation and mold structure optimization for each scenario according to the comprehensive evaluation values of mold construction simulation for multiple scenarios, and generate a mold optimization structure required for each scenario; A production monitoring optimization module, which is used to adjust the dynamic production line process parameters according to the mold optimization structure required for each scenario, so as to construct a mold production monitoring optimization engine.

[0009] Through the analysis of the production logs of the reaction cup mold, the present invention can identify potential problems and requirements in different application scenarios. This targeted requirement mining ensures that the requirements of each scenario can be accurately defined, providing data support for subsequent design and optimization. Through the comprehensive analysis of multiple scenarios, the solution can find appropriate design paths under different production environments or usage conditions, avoiding a one-size-fits-all design strategy and enhancing the adaptability of the mold. By analyzing multi-stage processes, the dependencies between various process links can be identified, thereby discovering bottlenecks and critical paths in the processes in advance and optimizing the production process. The mining of dependencies not only helps identify the key links in production but also provides decision-making support for production scheduling, ensuring a smooth and efficient production process and reducing resource waste. Constructing a production process logic diagram provides a clear reference for subsequent mold design and optimization, ensuring the standardization and efficiency of the production process. Through the in-depth analysis of the mold design drawings, standardized module components are disassembled, making the mold design more general and flexible. The standardized module components can effectively reduce the complexity of design and production and improve production efficiency. The standardized components can be reused in different production scenarios, reducing the cost and time of customized design, while improving product consistency and quality stability. The standardized modules make the production process more concise, allowing for quick assembly and adjustment, reducing commissioning time and errors in production. According to the specific requirements of each scenario, adaptive parameter design of the module components is carried out to ensure that the mold design can accurately meet different requirements in actual production. Through multi-scenario simulation, potential problems in the design can be discovered in advance, the design scheme can be optimized, and unforeseen problems in production can be avoided. Through simulation evaluation, the best production path and process can be identified in the design stage, improving efficiency and quality in the production process. Through continuous iterative optimization, the most suitable mold structure can be found, not only enhancing the service life of the mold but also improving the accuracy and stability of production. The optimization of each scenario can be customized according to specific requirements, avoiding over-design and waste, and enabling each production scenario to obtain a dedicated solution. The optimized mold structure can effectively handle complex production requirements, enhancing the performance of the mold in the actual production process and ensuring high-quality production output. By dynamically adjusting process parameters, a rapid response to changes in the production process can be made, ensuring that the mold always operates in the best working state and avoiding quality fluctuations in production. By real-time adjusting process parameters, the production line can be continuously optimized, improving production efficiency and reducing unnecessary downtime and commissioning time. The production monitoring optimization engine can form a closed-loop feedback mechanism, continuously optimizing the process through data collection and analysis to achieve continuous improvement and ensuring stability and consistency in the production process. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] Figure 1 It is a schematic diagram of the step flow of a method for designing a reaction cup mold for in vitro diagnosis according to the present invention; Figure 2 Detailed implementation flow chart of step S1; Figure 3 Detailed implementation flow chart of step S2; Figure 4 Detailed implementation flow chart of step S3. DETAILED DESCRIPTION

[0011] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0012] The present application example provides a method and system for designing a reaction cup mold for in vitro diagnosis. The execution subject of the method and system for designing a reaction cup mold for in vitro diagnosis includes but is not limited to: mechanical equipment, data processing platform, cloud server node, network upload device, etc. equipped with the system can be regarded as the general computing node of the present application, and the data processing platform includes but is not limited to: at least one of an audio and image management system, an information management system, and a cloud data management system.

[0013] See also Figures 1 to 4 The present invention provides a method for designing a mold for an in vitro diagnostic reaction cup, the method comprising the following steps: Step S1: Obtain the reaction cup mold production log and the preset reaction cup mold design drawing; perform in-depth analysis of multiple application scenarios and scene-by-scene diagnostic demand mining based on the reaction cup mold production log, so as to obtain the diagnostic demand of each scene; Step S2: Perform multi-stage production process analysis on the reaction cup mold production log, and perform process logic dependency mining to construct a production process logic law diagram; Step S3: performing in-depth analysis of the mold structure of the preset reaction cup mold design drawing, and defining standardized module components based on the production process logic law diagram, thereby generating multiple standardized module components; Step S4: Adaptively designing the demand parameters of multiple standardized module components according to the diagnostic requirements of each scenario, and performing multi-scenario demand production simulation to generate comprehensive evaluation values ​​of mold construction simulation for multiple scenarios; Step S5: performing iterative parameter optimization calculation and scene-by-scene mold structure optimization according to the comprehensive evaluation values ​​of mold construction simulation of multiple scenes, and generating a mold optimization structure required for each scene; Step S6: Dynamically adjust the production line process parameters according to the mold optimization structure required by each scenario, thereby building a mold production monitoring optimization engine.

[0014] The present invention establishes a complete data foundation by obtaining production logs and design drawings. This is the basis for subsequent analysis, ensuring that all decisions and optimizations are based on actual production data and design requirements. Through in-depth analysis of multiple application scenarios and mining of diagnostic requirements for each scenario, potential challenges and requirements in each scenario can be accurately identified, providing targeted information for subsequent optimization. Through multi-stage analysis of the production process, the process characteristics and problems at each stage of the production process can be comprehensively understood. This provides comprehensive data support for subsequent optimization. Process logic dependency mining helps identify the critical path and potential bottlenecks in production, enabling special attention and optimization of key links in the production process. By analyzing the bottlenecks and dependencies in the production process, it is possible to identify in advance which process stages or links may lead to low production efficiency or quality problems, and then take measures for optimization. By deeply analyzing the design drawings and combining them with the production process rules, the complex mold structure can be disassembled into standardized modular components, which can simplify the design, reduce production complexity, and improve the generality of the components. It can ensure the coordination between mold design and production process, avoid conflicts between design and process, and thus improve production efficiency and product quality. Adaptive parameter design of modular components according to the diagnostic requirements of different scenarios enables the mold design of each scenario to accurately match the actual requirements, improving the adaptability and effectiveness of the mold. Through multi-scenario production simulation, the feasibility and performance of the design can be verified in advance, ensuring that it can operate efficiently and meet various requirements in actual production. Through simulation evaluation and parameter optimization, the deficiencies in the mold design can be found and targeted improvements can be made to optimize the structure and improve the performance and lifespan of the mold. The mold structure of each scenario can be individually optimized to ensure that each production link can achieve the best effect under different requirements, avoiding a one-size-fits-all design approach and improving production adaptability. According to the optimized mold design, the process parameters of the production line can be dynamically adjusted to ensure that the production line always operates with optimal parameters, improving production efficiency and reducing resource waste. The constructed mold production monitoring and optimization engine can monitor various parameters in the production process in real time, promptly detect abnormalities and make adjustments, thereby ensuring production stability and product consistency. Through monitoring and feedback, a closed-loop optimization system is formed, enabling continuous optimization of each link in mold production and continuously improving production efficiency and product quality.

[0015] In an embodiment of the present invention, refer to Figure 1 , which is a schematic diagram of the step flow of a method for designing a reaction cup mold for in vitro diagnosis according to the present invention. In this example, the steps of the method for designing a reaction cup mold for in vitro diagnosis include: Step S1: Obtain the production log of the reaction cup mold and the preset design drawing of the reaction cup mold; conduct in-depth analysis of multiple application scenarios and mine diagnostic requirements for each scenario based on the production log of the reaction cup mold, so as to obtain the diagnostic requirements for each scenario; In this embodiment, the source of the production log of the reaction cup mold is determined. Usually, relevant data is recorded in real time during the production process. The data may include the production date, production batch, material type, production parameters (such as temperature, pressure, time, etc.), and the quality inspection results during the production process. When obtaining this data, it is necessary to ensure the integrity and accuracy of the log. Database query tools can be used to extract relevant data and ensure that the data format is unified for subsequent analysis. Obtain the preset design drawings of the reaction cup mold. These design drawings usually contain information such as the structure, dimensions, and material specifications of the mold. The design files can be exported through CAD software or other design tools, and it is ensured that the version of the design drawings is consistent with the production log. When analyzing the design drawings, key parameters of the mold need to be concerned, such as the inner and outer diameters, wall thickness, and cooling channel layout. This information will provide a basis for subsequent scenario analysis. Preprocess the obtained production log and design drawings. For the production log, data cleaning is required to handle missing values, outliers, and duplicate records to ensure the accuracy of the data; for the design drawings, they need to be converted into an analyzable format, such as a vector diagram or an image database. This step can be carried out using data processing software (such as Excel, Pandas, etc.) to ensure the smooth progress of subsequent analysis. According to the sorted production log, conduct in-depth analysis of multiple application scenarios. This process requires identifying common problems and their influencing factors existing in different production batches. Data mining and statistical analysis (such as clustering analysis, association rule mining) can be used to discover the root causes of problems. For example, analyze whether the production parameters in a specific batch are related to quality problems to determine potential influencing factors. After completing the analysis of multiple application scenarios, mine the diagnostic requirements for each scenario one by one. For each identified scenario, define its diagnostic objectives and requirements. For example, if the forming of the reaction cup is poor in a certain scenario, analyze its reasons (such as uneven mold temperature, insufficient material fluidity, etc.) and generate corresponding diagnostic requirements. This process can obtain opinions from multiple parties through expert interviews, questionnaires, or group discussions to ensure that the diagnostic requirements are comprehensive and accurate. Record the diagnostic requirements of each scenario in the database to form a standardized document for subsequent reference and implementation. These requirements not only provide a basis for subsequent production improvement but also provide feedback for new design schemes. By regularly reviewing and updating these requirements, the production process and product quality can be continuously optimized.

[0016] Step S2: Conduct multi-stage production process analysis on the production log of the reaction cup mold, mine the process logical dependencies, and construct a production process logical law diagram; In this embodiment, data related to the production process is extracted from the production log of the reaction cup mold. The key parameters may include the usage of raw materials, production temperature, pressure, time, equipment operating status, etc. These data are organized into a structured format and stored using a spreadsheet or a database management system. Ensure that the data for each production stage is recorded with a clear timestamp for subsequent stage analysis. Conduct a multi-stage process analysis on the organized production data. The production process can be divided into several key stages, such as raw material preparation, mold forming, cooling and solidification, post-treatment, etc. Use statistical analysis methods (such as descriptive statistics, analysis of variance, etc.) to summarize the main production parameters and their change trends for each stage. Display the key parameter changes for each stage through data visualization tools (such as charts or dashboards) to help identify possible process bottlenecks and key influencing factors. After completing the stage analysis, conduct process logic dependency mining. Use association rule mining techniques (such as the Apriori algorithm or the FP-Growth algorithm) to analyze the relationships between different production parameters. By calculating support and confidence, determine which parameters influence each other during the production process. For example, the relationship between mold temperature and cooling time, the relationship between material fluidity and forming pressure, etc. Based on the mined logical associations, construct a production process logic rule diagram. Using the basic concepts of graph theory, regard each production parameter as a node and the logical dependency relationship as an edge to form a directed graph. In the graph, the direction of the edge of the node represents a causal relationship, helping to visualize the dependency relationship between different process parameters. The key parameters and their value ranges of each node should be clearly marked in the graph for easy understanding. After constructing the logic rule diagram, it needs to be verified. Through historical data regression analysis, verify the accuracy and feasibility of the logical relationships in the graph. For example, check whether the impact of mold temperature changes on the finished product quality conforms to the logical relationships in the graph. According to the verification results, further optimize the graph to ensure that it reflects the true production process logic.

[0017] Step S3: Perform a deep analysis of the mold structure on the preset reaction cup mold design drawing, and define standardized module components based on the production process logic rule diagram, so as to generate multiple standardized module components; In this embodiment, a preset design drawing of a reaction cup mold is obtained, which usually exists in the CAD format. The design drawing is opened using CAD software (such as AutoCAD or SolidWorks), and the structure of the mold is analyzed layer by layer. Key components of the mold are focused on, such as the main structure, cooling channels, feed inlets, exhaust ports, and the parting line design of the mold. The dimensions, materials, and functional characteristics of each component are recorded for subsequent definition of standardized modular components. After the mold structure analysis is completed, functional partitioning is carried out. Based on the working principle of the mold and the production process logic diagram, the separable functional modules in the mold are identified. For example, the mold can be divided into a heating module, a cooling module, an injection molding module, and a control module, etc. Each module should have independent functions and be able to play a role in the entire production process. The functions of each module are described in detail, including its working principle, operating conditions, and interrelationships. Based on the above functional partitioning of the mold, the definition of standardized modular components is carried out. Each module should follow certain design standards and parameter ranges to ensure the compatibility and interchangeability of the modules. Standardized design specifications are formulated, including material selection, dimensional tolerances, connection methods, etc. For example, the design standard for the cooling module can specify the use of a certain specific aluminum alloy material, and the diameter of the cooling channels should be within a specific range (such as 5 - 10 mm) to ensure the heat dissipation efficiency. After the standardized modular components are defined, model verification is required. Computer-aided engineering (CAE) software can be used for simulation analysis to verify the performance of each module in the actual production process. For example, thermal analysis software is used to evaluate the heat conduction effect of the cooling module to ensure that it can effectively reduce the mold temperature under working conditions. According to the simulation results, necessary optimization and adjustment are carried out to ensure that the performance of the standardized components meets the production requirements.

[0018] Step S4: Adaptive demand parameter design is carried out on multiple standardized modular components according to the diagnostic requirements of each scenario, and multi-scenario demand production simulation is carried out to generate a comprehensive evaluation value of the mold construction simulation for multiple scenarios; In this embodiment, according to the diagnostic requirements mined in the previous steps, the specific parameter requirements of each production scenario are analyzed one by one. This analysis needs to combine the specific conditions of each scenario, such as the use of different materials, production speed, temperature, and pressure. Through discussions with the production team and engineers, ensure a comprehensive understanding of the requirements of each scenario. Record the key performance indicators (KPIs) of each scenario, such as the durability of the mold, forming accuracy, and production efficiency. According to the diagnostic requirements of the scenario, perform adaptive requirement parameter design for multiple standardized module components. First, identify the key parameters of the standardized components, such as dimensions, material properties, connection methods, and working conditions. Then, adjust these parameters to meet the specific production conditions for each scenario. For example, in a high-temperature environment, high-temperature-resistant materials need to be selected, and the design of the cooling module is adjusted to improve the heat dissipation effect. Use parametric design software (such as SolidWorks or CATIA) to quickly generate design models with different parameter configurations. After completing the adaptive requirement parameter design, perform production simulations for multi-scenario requirements. Select computer-aided engineering (CAE) software (such as ANSYS, COMSOL, etc.) for simulation. By inputting the production parameters of each scenario, simulate the performance of the mold under different working conditions. Focus on the thermodynamic behavior, hydrodynamic characteristics, and material stress distribution of the mold. During the simulation process, record the performance data of each scenario, such as the forming cycle, mold temperature change, and material utilization rate. After the simulation is completed, analyze the mold construction simulation results of each scenario and calculate the comprehensive evaluation value. These evaluation values can be production efficiency, product quality, consistency, and cost-effectiveness. Use statistical analysis methods (such as analysis of variance, regression analysis) to evaluate the mold performance under different scenarios and compare the advantages and disadvantages between scenarios. In addition, generate visual charts (such as radar charts, bar charts) for each scenario's evaluation indicators for easy comparison and analysis. Based on the comprehensive evaluation results, put forward optimization suggestions. For example, if it is found that the mold performance in a certain scenario is poor, trace back its adaptive parameter design to check whether there are design defects or unreasonable parameter settings. Establish a feedback mechanism to compare the simulation results with the actual production data and adjust the design and parameters in a timely manner to ensure the expected effect in actual production.

[0019] Step S5: Perform iterative parameter optimization calculation and optimize the mold structure for each scenario according to the comprehensive evaluation value of the mold construction simulation for multiple scenarios, and generate the optimized mold structure for each scenario requirement; In this embodiment, an in-depth analysis is carried out on the comprehensive evaluation values of the die construction simulation for multiple scenarios generated in the previous step. These evaluation values should include key performance indicators such as production efficiency, finished product quality, material utilization rate, and energy consumption. Statistical analysis tools (such as SPSS or R language) are used to analyze these data to identify the main parameters affecting die performance. For example, it may be found that there is a significant negative correlation between the cooling time of the die and the finished product quality, thereby determining the direction of optimization. Based on the results of the comprehensive evaluation, iterative parameter optimization calculations are carried out. Set an initial parameter set, including the die size, material type, cooling channel design, etc. On this basis, iterative calculations are carried out using optimization algorithms (such as genetic algorithms, particle swarm optimization, etc.). After each iteration, the parameter set is updated according to the results feedback by the optimization algorithm, in order to find the optimal solution under certain constraints. For example, set the objective function to maximize production efficiency while meeting the standards of finished product quality. After completing the parameter optimization calculations, the die structure is optimized according to the specific requirements of each scenario. According to the iterative results, the die structure required for each scenario is adjusted one by one. For example, for a die that requires high strength, the wall thickness may need to be increased or the material selection improved; while for a scenario with high cooling requirements, the layout of the cooling channels needs to be redesigned. Use computer-aided design (CAD) software (such as SolidWorks or CATIA) to draw the optimized die structure diagram and ensure that every change meets the production requirements. After the optimized structure design is completed, its performance needs to be verified. This can be preliminarily evaluated through computer simulation analysis (such as finite element analysis, thermal fluid analysis, etc.) to ensure the feasibility of the optimized structure in actual production. At the same time, physical samples are prepared for small-scale trial production, and the optimization effect is verified by comparing actual data. For example, test whether the newly designed cooling channels can effectively reduce the die temperature and record relevant production parameters. Record the optimized die structure and its performance verification results in the project documents to form a complete optimization report. The report should include the optimized structure diagrams, key parameters, performance indicators and their comparative analysis for each scenario. These documents not only provide reference for subsequent die production, but also provide data support for subsequent optimization. Establish a feedback mechanism to regularly review the optimization results, collect problems and improvement suggestions that occur during the production process for further optimization. Based on this optimization experience, establish a standardized optimization process and template to provide guidance for future die design and optimization. The process should include the selection of evaluation indicators, the application of optimization algorithms, the methods of performance verification, etc., to ensure that subsequent projects can draw on existing experience and improve efficiency and accuracy.

[0020] Step S6: Dynamically adjust the process parameters of the production line according to the optimized die structure required for each scenario, so as to construct an optimized engine for die production monitoring.

[0021] In this embodiment, in-depth analysis is carried out on the optimized structure of the mold for each scenario requirement. The analysis content should include the design characteristics of the mold, key parameters (such as dimensions, materials, structures), and their impacts on the production process. Through discussions with engineers and the production team, the production process parameters required for each optimized structure are clarified. For example, for a mold using new materials, key parameters such as melting point, fluidity, and cooling rate need to be considered to ensure the smooth progress of the production process. According to the analysis results of the optimized structure, a dynamic process parameter adjustment scheme is designed. The key parameters may include temperature, pressure, injection speed, cooling time, etc. For different scenario requirements, corresponding combinations of process parameters are formulated. For example, for a mold with high cooling requirements, the cooling water flow rate needs to be increased and the cooling temperature needs to be reduced; while for a mold with high forming accuracy requirements, the injection pressure and speed need to be adjusted. A standard operation process for parameter adjustment is established to enable quick response during the production process. In order to achieve real-time monitoring and adjustment of dynamic process parameters, a production monitoring system is designed and implemented. The system should include a data acquisition module, a real-time monitoring module, and a feedback adjustment module. The data acquisition module is responsible for collecting real-time data of various process parameters (such as temperature, pressure, flow rate, etc.) during the production process, and connecting sensors with data acquisition devices. The monitoring module displays various parameters in real time and compares them with the set standards to ensure that the production process meets the expected process requirements. Based on the monitoring system, a mold production monitoring optimization engine is constructed. The engine should possess data analysis and intelligent decision-making capabilities, and can automatically adjust process parameters according to the real-time monitored data. The core of the engine can adopt machine learning algorithms, train the model through historical production data, and identify the key factors affecting production efficiency and product quality. For example, using regression analysis or decision tree algorithms, predict the production effect under a certain specific process parameter and give corresponding adjustment suggestions. Experimental verification is carried out on the constructed monitoring optimization engine. Select multiple production scenarios for pilot testing, record the performance of the engine in actual production, and evaluate its effectiveness in dynamic process parameter adjustment. By comparing the experimental data with historical data, analyze the adjustment effect of the optimization engine, such as the improvement of production efficiency and the improvement of finished product quality. According to the experimental results, further optimize the algorithm and parameter settings of the engine to ensure its reliability and accuracy in actual production.

[0022] In this embodiment, refer to Figure 2 , which is a schematic diagram of the detailed implementation steps of step S1. In this embodiment, the detailed implementation steps of step S1 include: Step S11: Obtain real-time vehicle-mounted recorded images based on vehicle-mounted image sensors; Step S12: Perform time-series frame decomposition on the real-time vehicle-mounted recorded images to extract vehicle-mounted image time-series frames; Step S13: Calculate the inter-frame delay between adjacent frames of the vehicle-mounted image time-series frames to generate multiple inter-frame delay parameters; Step S14: Identify the inter-frame delay variation based on multiple adjacent inter-frame delay parameters to generate the inter-frame delay variation features of the image; Step S15: Perform dynamic delay interpolation optimization on the real-time in-vehicle recorded image based on the inter-frame delay variation features of the image to obtain the inter-frame delay optimized image; Step S16: Perform motion blur compensation on the inter-frame delay optimized image to construct the distortion optimized in-vehicle image.

[0023] In this embodiment, a high-resolution vehicle-mounted image sensor is selected. Usually, a CMOS sensor is adopted because of its excellent dynamic range and performance under low-light conditions. Sensor parameters are configured, with the frame rate set to 30fps and the resolution to 1920x1080 to ensure clear images are captured under various driving conditions. During driving, vehicle-mounted images are collected in real time by the sensor. The image data is processed and stored in real time by the vehicle-mounted computer to ensure the stability and accuracy of the data. It is recommended to use a real-time data stream processing framework (such as ROS) to support the efficient transmission and processing of data. After image acquisition, preliminary preprocessing is performed, including denoising, white balance, and color correction. A Gaussian filter is used for denoising, and adaptive histogram equalization is used for color correction to improve the image quality and lay a foundation for subsequent processing. During image acquisition, the image quality is monitored in real time to ensure the integrity and accuracy of each frame of data. Thresholds are set, such as the degree of motion blur not exceeding a certain value, to determine whether the image meets the requirements for subsequent processing. According to the real-time vehicle-mounted image data stream, a method for extracting sequential frames is selected. A simple frame extraction algorithm can be used to extract frames at a set frame interval (such as extracting 30 frames per second). Each extracted frame of the image is stored in a buffer for subsequent processing. To avoid data loss, it is recommended to use an efficient storage structure, such as a circular buffer, to update and manage the extracted frame data in real time. A timestamp is recorded for each extracted sequential frame to ensure that the time relationship between frames can be accurately reconstructed during subsequent processing. This process is an important basis for subsequent analysis of the inter-frame delay calculation. During the sequential frame extraction process, the number and quality of the extracted frames are monitored in real time to ensure that the requirements for subsequent processing are met. The minimum number of frames extracted within each time window can be set to evaluate the extraction effect. A suitable method for calculating the inter-frame delay is selected. An estimation method based on the optical flow method can be used to calculate the delay parameters by analyzing the motion information between adjacent frames. The difference between adjacent frames is calculated, usually using the mean squared error (MSE) or the structural similarity index (SSIM) to quantify the inter-frame difference. Thresholds can be set to identify significant changes for subsequent delay calculation. For each pair of adjacent frames, its delay parameters are calculated. By analyzing the optical flow field between frames, the motion vector of each pixel can be extracted to obtain the information on the relative motion between frames. These parameters will be used for subsequent delay change identification. The calculated inter-frame delay parameters between adjacent frames are recorded in a database and statistically analyzed to calculate the average delay and standard deviation within each time period to evaluate the overall delay change situation. A suitable delay change identification model is selected, such as a method based on time series analysis, or a statistical model (such as Z-score or moving average) is used to identify delay changes. Change detection is performed on the recorded inter-frame delay parameters between adjacent frames. Thresholds (for example, the delay change exceeds a certain standard deviation) are set to determine whether there are significant delay changes. This process can help identify important changes in dynamic scenes.Extract the characteristics of latency changes, including information such as the amplitude, frequency, and duration of latency changes. These characteristics can be presented using histograms or time series plots to facilitate subsequent analysis and visualization. Record the identified latency change characteristics in a database and generate a visualization chart to display the latency changes. This process helps with subsequent dynamic interpolation optimization and motion blur compensation. Select a suitable dynamic interpolation algorithm, such as an optical flow-based interpolation method or a deep learning interpolation method. The optical flow method can generate intermediate frames by analyzing motion information, thus effectively reducing image distortion caused by latency. Based on the latency change characteristics, perform dynamic interpolation on adjacent frames. By analyzing the motion vectors between each pair of adjacent frames, generate new intermediate frames. Dynamically adjust the interpolation parameters according to the change characteristics to ensure the smoothness of the interpolation effect. Evaluate the generated interpolated images using metrics such as Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity Index (SSIM) to assess the interpolation effect. Adjust the interpolation parameters according to the results to achieve the best visual effect. Save the images optimized by dynamic latency interpolation and record the relevant data parameters. This process ensures a significant improvement in the quality of the generated images and lays a foundation for subsequent motion blur compensation. In the optimized images, detect the presence of motion blur. The frequency distribution of the images can be analyzed using the Laplacian operator or Fourier transform to evaluate the degree of blur. For the detected motion-blurred images, calculate the degree of blur. By calculating the gradient values of each pixel, obtain the blur intensity and determine the direction and amplitude of the blur based on the intensity information. Select a suitable motion blur compensation algorithm, such as a deconvolution-based deblurring method. These algorithms can improve the image quality by restoring the details of the blurred image. Blind deconvolution techniques can be used, combined with blur kernel estimation for deconvolution processing. Evaluate the quality of the compensated images using metrics such as PSNR and SSIM to assess the compensation effect. Adjust the compensation parameters according to the evaluation results to improve the quality of the final images.

[0024] In this embodiment, the specific steps of step S15 are as follows: Perform dynamic object visual recognition on the inter-frame latency optimized images and mark multiple dynamic objects; Perform dynamic optical flow estimation on the multiple dynamic objects and extract the motion vectors of the dynamic objects; Perform motion blur analysis on the inter-frame latency optimized image pairs to generate motion blur data in the images; Perform delay vector compensation calculation on the motion vectors of the dynamic objects according to the inter-frame latency change characteristics of the images to obtain the object motion vector compensation parameters for inter-frame latency; Eliminate the motion blur in the motion blur data in the images based on the object motion vector compensation parameters for inter-frame latency to generate motion blur eliminated images; Perform lens distortion detection on the motion blur eliminated images and extract the sensor lens distortion data; Optimize geometric distortion based on sensor lens distortion data to construct a distortion-optimized vehicle-mounted image.

[0025] In this embodiment, a suitable dynamic object visual recognition model is selected, such as YOLOv5 or Faster R-CNN. These models can effectively identify and label multiple dynamic objects in a real-time environment, with good accuracy and processing speed. Preprocess the inter-frame delay optimized image, including adjusting the image size (such as 640x640 pixels) and performing normalization. Ensure that the input data meets the model requirements to improve the recognition accuracy. Input the preprocessed image into the selected object detection model for inference. The model will identify the dynamic objects in the image and generate bounding boxes, corresponding categories, and confidence scores for each object. Set a confidence threshold (such as 0.5) to retain only the high-confidence recognition results. Record the detected dynamic object information (such as position, category, and confidence) in the database and draw bounding boxes and labels on the image for subsequent analysis and visualization. Display the recognition results through a visualization tool to help evaluate the detection accuracy. Select a suitable dynamic optical flow estimation method, such as the Lucas-Kanade algorithm or the Horn-Schunck algorithm. These methods can effectively estimate the motion vectors between adjacent frames and are suitable for the motion analysis of dynamic objects. Extract adjacent frames (such as the previous and next frames) from the inter-frame delay optimized image to ensure that the motion information of dynamic objects can be captured. Preprocess the extracted adjacent frames, including grayscale conversion and noise reduction, to improve the accuracy of optical flow estimation. Calculate the optical flow between adjacent frames and extract the motion vectors of dynamic objects. Generate a motion vector field by analyzing the motion information of each pixel and record the speed and direction of each dynamic object. Record the calculated motion vectors in the database and analyze the motion characteristics of each dynamic object. The motion pattern can be further understood by statistically analyzing the speed and direction changes of each object. Select a suitable motion blur detection method, such as the Laplacian operator or the Sobel operator. These methods can effectively detect the degree of blur in the image and help analyze the impact of motion blur. Apply the selected blur detection method to the inter-frame delay optimized image to calculate the degree of blur. Obtain the blur intensity by calculating the gradient value of each pixel and judge the direction and amplitude of the blur based on the intensity information. Record the motion blur analysis results in the database, including the blur intensity, direction, and affected area. These data will provide an important basis for subsequent blur compensation. Display the motion blur analysis results through a visualization tool to help evaluate the impact of the degree of blur on the image quality. A blur region heat map can be generated for subsequent processing. Based on the extracted inter-frame delay change characteristics of the image, analyze the relationship between the motion vectors of dynamic objects and the delay. Set a delay threshold to identify significant delay-affected areas. For each dynamic object, calculate the compensation parameters for its motion vector. Set a calculation formula, for example, analyze the relationship between the motion vector and the delay parameter through linear regression to obtain the compensation value. Record the compensation parameters in the database and analyze the compensation requirements of different objects. The difference in compensation effects can be evaluated through statistical analysis to ensure the accuracy of processing.According to the calculation results of the compensation parameters, the motion state of the dynamic object is monitored in real time, and the compensation parameters are adjusted to achieve the best compensation effect. Select a suitable motion blur removal algorithm, such as the deconvolution-based method or the pyramid deblurring algorithm. These algorithms can restore the details of the blurred image by compensating for the motion information. Process the motion-blurred image according to the motion vector compensation parameters calculated in the previous step. Through deconvolution technology, compensation is performed for each blurred area to generate a clear motion blur removal image. Evaluate the quality of the generated clear image, and use indicators such as PSNR and SSIM to evaluate the removal effect. Adjust the compensation parameters according to the evaluation results to improve the image quality. Save the removed image and record the relevant data parameters. This process ensures that the generated image has good clarity, facilitating subsequent analysis and use. Select a suitable lens distortion detection method, such as the checkerboard calibration method or the circular calibration method. These methods can effectively detect the geometric distortion in the image and help extract the lens distortion parameters. Prepare the calibration image, usually using an image with a known geometric shape (such as a checkerboard or a circle), and obtain the calibration image by shooting. Ensure that the calibration image covers the entire field of view to improve the detection accuracy. Calibrate the motion blur removal image to calculate the distortion parameters of the lens (such as radial distortion and tangential distortion). Use the least squares method to optimize the distortion model to obtain accurate distortion coefficients. Record the extracted distortion parameters in the database for subsequent geometric distortion optimization. Analyze the influence of the distortion parameters and evaluate their impact on the image quality. Select a suitable geometric distortion optimization model, such as the method based on the inverse distortion model. This method can correct the geometric distortion in the image by applying the inverse transformation. According to the distortion parameters extracted in the previous step, perform geometric correction on the motion blur removal image. Through inverse distortion processing, the coordinates of each pixel are adjusted to eliminate the distortion effect. Evaluate the quality of the optimized image, and use indicators such as PSNR and SSIM to evaluate the geometric correction effect. Make adjustments according to the evaluation results to ensure the geometric accuracy of the image. Save the vehicle-mounted image after distortion optimization and record the relevant data parameters. This process ensures that the generated image achieves an optimized effect both geometrically and visually, providing high-quality data support for subsequent applications (such as autonomous driving, object recognition, etc.).

[0026] In this embodiment, refer to Figure 3 , which is a schematic diagram of the detailed implementation steps of step S2. In this embodiment, the detailed implementation steps of the said step S2 include: Step S21: Identify the ambient light source of the vehicle-mounted image after distortion optimization and mark the real-time ambient light source; Step S22: Calculate the color temperature of the ambient light source according to the real-time ambient light source to generate the ambient light source color temperature feature; Step S23: Calculate the real-time ambient light intensity distribution of the vehicle-mounted image after distortion optimization to generate the ambient light intensity time series distribution feature; Step S24: Perform real-time scene spectral feature evolution based on the color temperature characteristics of the ambient light source and the temporal distribution characteristics of the ambient light intensity to generate the real-time scene light spectral features; Step S25: Based on the real-time scene light spectral features, adjust the dynamic image spectral parameters of the distorted and optimized vehicle-mounted image to generate a dynamically spectrally adjusted image.

[0027] In this embodiment, a suitable environmental light source detection model is selected. Usually, deep learning models (such as YOLO or SSD) are used for real-time light source recognition. These models can effectively identify light sources under different lighting conditions and mark their positions. Preprocess the distorted and optimized vehicle-mounted images, including image scaling, normalization, and noise removal. Adjust the image size to the requirements of the model (such as 416x416 pixels) to improve the recognition accuracy. Input the preprocessed image into the selected environmental light source detection model for real-time inference. The model will identify the environmental light sources in the image and generate bounding boxes, corresponding categories, and confidence scores for each light source. Set a confidence threshold (such as 0.5), and only retain the recognition results with high confidence. Record the detected environmental light source information (such as position, category, and confidence) in the database, and draw bounding boxes and labels on the image for subsequent analysis and visualization. Display the recognition results through a visualization tool to help evaluate the accuracy of the detection. Select a suitable color temperature calculation method, usually using the blackbody radiation theory. Calculate the color temperature (Kelvin value) through the color temperature conversion formula according to the RGB values of the environmental light source. Obtain the RGB values of the environmental light sources identified in step S21. For each light source, extract its average RGB value in the image to improve the accuracy of the calculation. According to the extracted RGB values, use the color temperature calculation formula, T=( R⋅100 / ) G, where T is the color temperature, and R and G are the values of the red and green channels of the environmental light source. This formula can convert the corresponding color temperature value. Record the calculated color temperature of the environmental light source in the database and analyze the color temperature characteristics of different light sources. Through statistical analysis, evaluate the impact of color temperature on image quality and provide a basis for subsequent processing. Select a suitable environmental light intensity distribution calculation method, usually using the light intensity (luminance) measurement method. The grayscale value averaging method can be adopted to calculate the light intensity according to the brightness values of each pixel in the image. Perform grayscale processing on the distorted and optimized vehicle-mounted image to convert the RGB image into a grayscale image. Calculate the brightness value of each pixel through the formula: L=0.299⋅R+0.587⋅G+0.114⋅B, where L is the brightness value, and R, G, and B are the values of the red, green, and blue channels respectively. Calculate the light intensity distribution of the entire image, count the brightness values of each region, and generate the light intensity time series distribution characteristics. For example, set the region size to 100x100 pixels, calculate the average brightness of the corresponding region, and form a light intensity distribution map. Record the calculated light intensity distribution characteristics in the database and generate a visualization chart to display the light intensity time series distribution. This helps with subsequent analysis and the evolution of dynamic spectral characteristics. Select a suitable spectral feature evolution model, usually based on the color temperature and light intensity of the environmental light source for modeling. A spectral reconstruction algorithm can be used to incorporate the color temperature and light intensity information into the generation of spectral features. Integrate the environmental light source color temperature characteristics calculated in step S22 and the light intensity time series distribution characteristics generated in step S23. Combine the color temperature and light intensity through the weighted average method to generate the spectral features of the real-time scene.Generate real-time scene light spectral features based on the fused data. Interpolation methods can be used to smooth the spectral feature curve to better reflect the changes in scene light. Record the generated real-time scene light spectral features in the database and analyze their impact on subsequent image processing. Display the spectral feature changes through visualization tools to help understand the dynamic evolution process of scene light. Select a suitable dynamic spectral parameter adjustment model, such as a model based on color correction or an image enhancement algorithm. These models can effectively adjust the color and brightness of the image according to the real-time spectral features. Perform dynamic spectral parameter adjustment on the distorted and optimized vehicle images according to the generated real-time scene light spectral features. The RGB values of each pixel can be adjusted to adapt to the new spectral features. For example, use stretching methods to adjust the brightness and contrast to match the changes in scene light. Evaluate the quality of the adjusted image, and use metrics such as PSNR and SSIM to evaluate the quality of the adjusted image. Further optimize the adjustment parameters according to the evaluation results to ensure that the color and brightness of the image meet the expectations. Save the image after dynamic spectral adjustment and record the relevant data parameters. This process ensures that the generated images maintain high quality under dynamic lighting conditions and provide reliable data support for subsequent applications (such as autonomous driving, image analysis, etc.).

[0028] In this embodiment, refer to Figure 4 , which is a schematic diagram of the detailed implementation steps of step S3. In this embodiment, the detailed implementation steps of step S3 include: Step S31: Calculate the histogram of each pixel point of the dynamically spectrally adjusted image and extract the histogram features of each pixel point; Step S32: Divide the dynamically spectrally adjusted image into multiple regions to generate a multi-region image; Step S33: Perform histogram shape recognition based on the histogram features of each pixel point and analyze the exposure degree to generate exposure classification data; Step S34: Perform regional exposure recognition on the multi-region image according to the exposure classification data to generate the exposure features of each region. The exposure features of each region include overexposed regions, underexposed regions, and acceptable dynamic range regions; Step S35: Visualize the dynamic exposure range distribution of the exposure features of each region to construct a dynamic exposure range distribution perception map.

[0029] In this embodiment, a suitable histogram calculation method is selected. Usually, histograms are calculated separately for each color channel (red, green, blue). The number of intervals (bins) of the histogram is set, usually 256, to cover the full range of each color channel. Each pixel point in the dynamically spectrally adjusted image is traversed, its RGB value is recorded, and the corresponding count is incremented. This can be implemented using nested loops, with the outer loop traversing each row and the inner loop traversing each column. Histograms for the three color channels are generated based on the traversal results to obtain the histogram features for each channel. The histogram for each channel shows the number of pixels at different brightness levels, which helps analyze the overall illumination distribution of the image. The calculated histogram features are recorded in the database, and a visualization tool is used to generate a histogram display. Through visualization, the brightness distribution of each color channel can be intuitively observed to assist subsequent analysis. A suitable region partitioning method is selected. Commonly used methods include the uniform partitioning method, clustering algorithms (such as K-means), or segmentation algorithms based on image features (such as SLIC superpixel segmentation). According to the selected method, the dynamically spectrally adjusted image is partitioned. For example, using the uniform partitioning method, the image can be divided into a 4x4 or 8x8 grid to form multiple small regions. The size of each region should be set according to the image resolution and subsequent analysis requirements. For each partitioned region, features such as the average RGB value, brightness value, and standard deviation within the region are extracted. These features will be used for subsequent exposure classification analysis and identification. The results of the multi-region partitioning are recorded in the database, and the region boundaries are drawn on the original image for visualization. The partitioning results are displayed through a visualization tool to help understand the distribution and features of each region. A suitable exposure level analysis method is selected. Usually, it is classified based on the morphological features of the histogram. For example, the peak, width, and distribution range of the histogram can be analyzed, and thresholds are set to distinguish different exposure states. The histogram of each color channel is analyzed to extract morphological features. Thresholds are set. For example, if 90% of the pixels are near 255 (overexposed) or 0 (underexposed), the corresponding region is classified as overexposed or underexposed. Based on the morphological analysis results, exposure classification data is generated for each region, including "overexposed", "underexposed", and "acceptable dynamic range". The exposure status of each region is recorded for subsequent processing. The exposure classification data is recorded in the database, and a visualization chart is generated to display the exposure status. The exposure type of each region is displayed through a visualization tool to help analyze the image quality. A suitable region exposure identification method is selected. Usually, it combines exposure classification data and region features for comprehensive analysis. The weighted average method can be used to combine the exposure classification factors with the features of each region. Each region is analyzed, and its exposure classification data is combined to evaluate the exposure characteristics of the region. Rules are set. For example, if the proportion of the "overexposed" region exceeds 50%, the entire region is marked as "overexposed". The exposure characteristics of each region are recorded, including "overexposed area", "underexposed area", and "acceptable dynamic range area".Ensure that the exposure status of each area can accurately reflect its lighting conditions. Record the area exposure characteristics in a database and mark different exposure statuses on the multi-area image. Displaying the area exposure characteristics through visualization tools is helpful for subsequent analysis and improvement. Select a suitable visualization method, usually using a heat map or a hierarchical map to display the exposure characteristics of each area. The heat map can intuitively reflect the exposure status of different areas. Map the exposure characteristics of each area to the visualization graph. Set the color mapping rules. For example, mark the "overexposed" area as red, the "underexposed" area as blue, and the "acceptable dynamic range" area as green. Generate a dynamic exposure range distribution perception map to reflect the exposure status of each area through color changes. Ensure that the visualization chart has good readability to quickly identify problem areas. Record the generated dynamic exposure range distribution perception map in the database and conduct analysis. By comparing the exposure statuses at different time periods, evaluate the image processing effect to help optimize the exposure control strategy in the future.

[0030] In this embodiment, step S4 includes the following steps: Step S41: Perform adaptive exposure compensation calculation for each area according to the dynamic exposure range distribution perception map to generate the exposure compensation parameter range for each area; Step S42: Perform multi-compensation parameter quantification processing according to the exposure compensation parameter range of each area to generate multiple exposure compensation parameters; Step S43: Perform multi-parameter exposure compensation adjustment on the dynamic spectral adjustment image according to the multiple exposure compensation parameters to obtain multiple exposure compensation images; Step S44: Comprehensively evaluate the compensation effects of the multiple exposure compensation images to generate the evaluation values of the multiple compensation images; extract the optimal exposure compensation parameters based on the evaluation values of the multiple compensation images.

[0031] In this embodiment, a suitable adaptive exposure compensation model is selected and usually adjusted based on regional exposure characteristics (such as overexposure and underexposure). A linear compensation model can be adopted to adjust the compensation value according to the current exposure state of the region. Based on the dynamic exposure range distribution perception map, the exposure characteristics of each region are analyzed. Thresholds are set for each region. For example, if a region is marked as "overexposed", the compensation range is set to [-1, 0]; if it is "underexposed", it is set to [0, 1]; and the acceptable dynamic range region is set to [0]. The exposure compensation parameter calculation is performed for each region. C = α ⋅ (E - T), where C is the exposure compensation parameter, E is the current exposure value, T is the target exposure value, and α is the adjustment coefficient (which can be set to 0.5) to obtain a reasonable compensation range. The calculated exposure compensation parameter ranges for each region are recorded in the database, and a visualization chart is generated to display the compensation ranges of each region. This helps with subsequent compensation parameter processing and analysis. A suitable method for generating compensation parameters is selected. Usually, parameters are randomly generated through uniform distribution or normal distribution. The number of compensation parameters generated for each region is set. For example, 5 parameters are generated for each region. According to the previously calculated exposure compensation parameter ranges for each region, the generation intervals of the compensation parameters are divided. For overexposed regions, the generated compensation parameters should be between [-1, 0]; for underexposed regions, the generated parameters should be between [0, 1]. A random number generator is used to generate compensation parameters according to the set distribution. For example, the uniform distribution function can be used to generate 5 compensation parameters for each region and ensure that the generated parameters conform to their respective ranges. The generated multiple exposure compensation parameters are recorded in the database and statistically analyzed to calculate the mean and variance of the compensation parameters for each region. This process helps with subsequent evaluation of the compensation effect. A suitable method for adjusting exposure compensation is selected. Usually, linear transformation or non-linear transformation is used to adjust the brightness of the image. The corresponding exposure compensation parameters are applied to each region to generate a compensated image. Each region is traversed, and the corresponding compensation parameter is applied to each pixel point within the region to update the pixel value. According to the multiple exposure compensation parameters of each region, the corresponding compensated images are generated. For each region, the above adjustment process is repeated to generate up to 5 different compensated images. The generated multiple exposure compensated images are saved and visually displayed. By comparing different compensated images, the compensation effect is preliminarily evaluated to prepare for subsequent evaluation. A suitable evaluation index for the compensation effect is selected. Usually, indexes such as peak signal-to-noise ratio (PSNR), structural similarity index (SSIM), and mean squared error (MSE) are used. These indexes can better reflect the image quality. Each generated exposure compensated image is evaluated to calculate its PSNR, SSIM, and MSE values. Using a reference image (such as the original image) as a benchmark, each compensated image is compared with the reference image. The evaluation values of each compensated image are recorded in the database to form statistical data of the evaluation values. These data will be used to analyze the effects of different compensation parameters for subsequent selection of the optimal parameters.Based on the evaluation value, select the exposure compensation image with the best effect and the corresponding compensation parameters. For example, select the image with the highest SSIM value as the optimal compensation image, and record the compensation parameters of this image for subsequent processing.

[0032] In this embodiment, step S5 includes the following steps: Step S51: Classify the types of multiple dynamic objects to generate dynamic object types; Step S52: Accurately locate the bounding boxes of each object one by one according to the dynamic object types to generate multiple dynamic object bounding boxes; Step S53: Track the multiple dynamic object bounding boxes in consecutive frames to generate the real-time positions of each dynamic bounding box; Step S54: Fit the dynamic movement trajectories according to the real-time positions of each dynamic bounding box to generate the movement trajectories of each dynamic object.

[0033] In this embodiment, a suitable object classification model is selected. Usually, deep learning models such as YOLO, FasterR-CNN, or MobileNet-SSD are used. These models can effectively perform object classification in a real-time environment. A sufficiently trained dataset (such as COCO, PASCAL VOC) is selected according to the application requirements to ensure the accuracy of the model. Each detected object in the dynamic image is preprocessed, including resizing (such as 416x416 pixels) and normalization, to ensure that the input data meets the model requirements. Data augmentation techniques (such as random cropping, flipping, etc.) can also be applied in the training stage to improve the robustness of the model. The preprocessed object images are input into the selected object classification model for inference. The model will output the category of each object and its confidence score. A confidence threshold (such as 0.5) is set, and only the classification results with high confidence are retained to ensure the accuracy of classification. The classification results (object types and their confidence levels) are recorded in the database, and the distribution of different object types is analyzed. Through statistical analysis, the performance of the model on different types of objects is evaluated to ensure that the classification effect meets the application requirements. A suitable bounding box localization method is selected, usually used in conjunction with the object detection model. The bounding box coordinates output by the model (such as the coordinates of the upper left corner and the lower right corner) will be directly used for subsequent processing. The bounding box coordinates of each object are extracted from the object classification results. For each detected object, its position in the image is recorded and converted into the bounding box format (xmin, ymin, xmax, ymax). To improve the accuracy of the bounding box, the Bounding Box Regression technique can be used to correct the initially detected bounding box. By minimizing the loss function between the predicted bounding box and the ground truth bounding box, the position of the bounding box is optimized. The generated multiple dynamic object bounding boxes are recorded in the database, and the bounding boxes are drawn on the image for visualization. The localization effect of the bounding boxes is displayed through a visualization tool to ensure that the localization accuracy meets the requirements. A suitable tracking algorithm is selected. Commonly used methods include the KLT optical flow method, Kalman filtering, or SORT (Simple Online and Realtime Tracking). These algorithms can efficiently track the bounding boxes of dynamic objects in consecutive frames. The tracker for each dynamic object's bounding box is initialized. The selected tracking algorithm is used to create an independent tracking instance for each bounding box to update its position in each frame. In each frame, the tracking algorithm is used to update the position of each dynamic object's bounding box. By analyzing the position difference of the object between the current frame and the previous frame, the new position of the object is calculated in real-time. For example, in the KLT optical flow method, the optical flow field of each key point in the current frame is calculated to update the bounding box position. The real-time position of each dynamic bounding box is recorded in the database, and the bounding boxes are drawn on the image for visualization. The tracking effect of the bounding boxes is displayed through a visualization tool to ensure the stability and accuracy of tracking.Select a suitable trajectory fitting model, usually using a linear regression model or polynomial fitting method. Select an appropriate fitting model according to the motion characteristics of the object to ensure the accuracy of the trajectory. Collect the real-time position data of each dynamic object to construct a time series data set. Record the timestamp of each object and the corresponding bounding box position (such as the center point coordinates). Fit the real-time position data of each dynamic object. Use the selected trajectory fitting model to calculate the motion trajectory of the object. For example, for the center coordinates (x, y) of each object, apply the least squares method for fitting to generate a trajectory equation. Record the moving trajectories of each generated dynamic object in the database and draw trajectory lines on the image for visualization. Display the dynamic moving trajectories of the objects through a visualization tool to help analyze the motion patterns of the objects.

[0034] In this embodiment, step S6 includes the following steps: Step S61: Calculate the moving speed of each dynamic object's moving trajectory to generate the dynamic object's moving speed; Step S62: Adjust the local exposure frequency according to the dynamic object's moving speed to generate the local exposure adjustment frequency; Step S63: Analyze the light change rate of each dynamic object's moving trajectory to generate the dynamic object's light change rate; Step S64: Fine-tune the local exposure amplitude based on the dynamic object's light change rate to generate the local exposure fine-tuning amplitude; Step S65: Make a dynamic tracking exposure decision on the dynamic object's light change rate and the local exposure fine-tuning amplitude to construct a local dynamic tracking exposure strategy; Step S66: Perform end-to-end exposure control according to the local dynamic tracking exposure control strategy and the optimal exposure compensation parameters to construct a dynamic exposure control model.

[0035] In this embodiment, a suitable moving speed calculation method is selected. Usually, the relationship between displacement and time is used to calculate the speed. Collect the real-time position data of each dynamic object from step S53, and record its center coordinates (x, y) and timestamp in consecutive frames. Ensure the integrity of the position data of each object in multiple frames to facilitate speed calculation. For each dynamic object, calculate its moving speed between adjacent frames. Traverse the trajectory data of each object, take the center coordinates of two frames, record the calculated moving speed of each dynamic object in the database, and perform statistical analysis. The average speed and maximum speed of each object can be calculated to evaluate its motion characteristics and provide a basis for subsequent exposure adjustment. Select a suitable exposure frequency adjustment model, usually dynamically adjusted according to the object's moving speed. Set a reference exposure frequency (such as 30 fps) and make corresponding adjustments according to the object speed. Set the relationship between speed and exposure frequency. For example, if the object speed is higher than a certain threshold (such as 5 m / s), increase the exposure frequency; if the speed is lower than the threshold, decrease the exposure frequency. A linear or non-linear function relationship can be adopted. For each dynamic object, adjust the corresponding exposure frequency according to its calculated moving speed. Set the frequency adjustment formula: f = f(0) + k ⋅ v, where f(0) is the reference frequency, k and v are the proportional coefficients of speed and frequency respectively, and v is the moving speed of the object. Record the generated local exposure adjustment frequency in the database and generate a visualization chart to show the exposure frequency adjustment of different objects. This helps with subsequent exposure strategy optimization and analysis. Select a suitable light change rate analysis method, usually based on the model of light intensity changing over time. Extract the light intensity data of each object in different frames from the dynamic image. Image processing techniques can be used to calculate the average brightness value of each object area to obtain the light intensity. For each dynamic object, calculate its light change rate between adjacent frames. Traverse the light intensity data of each object, take the light intensity of two frames, record the light change rate of each dynamic object in the database, and generate a visualization chart to show the light change of different objects. This will help with subsequent exposure adjustment decisions. Select a suitable exposure amplitude fine-tuning model, usually dynamically adjusted based on the light change rate. Set a reference exposure amplitude (such as ±1 EV) and make corresponding fine-tuning according to the light change rate. Set the relationship between the light change rate and the exposure amplitude. For example, if the light change rate is higher than a certain threshold (such as 0.5 Lux / s), increase the amplitude; if it is lower than the threshold, decrease the amplitude. For each dynamic object, adjust the corresponding exposure amplitude according to its calculated light change rate. A = A(0) + k ⋅ r, where A(0) is the reference exposure amplitude, k is the proportional coefficient of the change rate and the exposure amplitude, and r is the light change rate. Record the generated local exposure fine-tuning amplitude in the database and generate a visualization chart to show the exposure amplitude adjustment of different objects. This helps with subsequent exposure control strategy optimization and analysis.Select a suitable dynamic tracking exposure decision model, usually using a rule-based decision system. Set a series of rules to dynamically adjust the exposure settings. Set decision rules based on the light change rate and the exposure fine-tuning amplitude. For example, if the light change rate is high and the exposure amplitude is adjusted to a positive value, increase the exposure; conversely, if the change rate is low and the amplitude is adjusted to a negative value, decrease the exposure. For each dynamic object, evaluate its light change rate and exposure fine-tuning amplitude in real time, apply the set decision rules, and dynamically adjust the exposure settings. This can be achieved through conditional judgments and logical operations. Record the dynamic exposure decisions of each object in a database and analyze the effectiveness of the decisions. Evaluate the robustness and applicability of the strategy by statistically analyzing the exposure effects in different situations. Design a suitable dynamic exposure control model, usually by combining local dynamic tracking exposure strategies with optimal exposure compensation parameters for control. The model should be able to receive the motion state of the object and light change information in real time. According to the local dynamic tracking exposure control strategy, adjust the exposure settings of the image in real time. For example, use a PID controller or a fuzzy controller to automatically adjust the exposure parameters according to the input light and motion data. Test the constructed dynamic exposure control model and evaluate its performance in different scenarios. Record the exposure effects under different light and motion conditions, and adjust the model parameters to optimize the control performance. Record the results of dynamic exposure control in a database, and evaluate the effectiveness of the model by comparing the effects of different control strategies. According to the test results, continuously optimize the exposure control strategy to improve the image quality.

[0036] In this embodiment, a reaction cup mold design system for in vitro diagnosis is provided, which is used to execute the reaction cup mold design method for in vitro diagnosis as described above, and includes: A scenario requirement module, which is used to obtain the production log of the reaction cup mold and the preset reaction cup mold design drawing; perform in-depth analysis of multiple application scenarios based on the production log of the reaction cup mold and mine the diagnostic requirements for each scenario one by one, so as to obtain the diagnostic requirements for each scenario; A logical dependency mining module, which is used to perform multi-stage production process analysis on the production log of the reaction cup mold, mine the process logical dependencies, and construct a production process logical rule diagram; A module component definition module, which is used to perform in-depth analysis of the mold structure on the preset reaction cup mold design drawing, and perform standardized module component definition based on the production process logical rule diagram, so as to generate multiple standardized module components; A requirement production simulation module, which is used to perform adaptive requirement parameter design on multiple standardized module components according to the diagnostic requirements of each scenario, and perform multi-scenario requirement production simulation to generate comprehensive evaluation values of mold construction simulation for multiple scenarios; The mold structure optimization module is used to perform iterative parameter optimization calculations and optimize the mold structure for each scenario one by one based on the comprehensive evaluation values of mold construction simulations in multiple scenarios, and generate the optimized mold structure required for each scenario; The production monitoring optimization module is used to adjust the process parameters of the dynamic production line according to the optimized mold structure required for each scenario, thereby constructing a mold production monitoring optimization engine.

[0037] Through the analysis of the production log of the reaction cup mold, potential problems and requirements in different application scenarios can be identified. This targeted requirement mining ensures that the requirements of each scenario can be precisely defined, providing data support for subsequent design and optimization. Through the comprehensive analysis of multiple scenarios, the solution can find appropriate design paths under different production environments or usage conditions, avoiding a one-size-fits-all design strategy and enhancing the adaptability of the mold. By analyzing the multi-stage process, the dependencies between various process links can be identified, thereby discovering bottlenecks and critical paths in the process in advance and optimizing the production process. The mining of dependencies not only helps identify the key links in production but also provides decision-making support for production scheduling, ensuring a smooth and efficient production process and reducing resource waste. Constructing a production process logic diagram provides a clear reference for subsequent mold design and optimization, ensuring the standardization and efficiency of the production process. Through the in-depth analysis of the mold design drawing, standardized module components are disassembled, making the mold design more general and flexible. Standardized module components can effectively reduce the complexity of design and production and improve production efficiency. Standardized components can be reused in different production scenarios, reducing the cost and time of customized design, while improving product consistency and quality stability. Standardized modules make the production process more concise, can be quickly assembled and adjusted, reducing commissioning time and errors in production. According to the specific requirements of each scenario, adaptive parameter design of module components is carried out to ensure that the mold design can accurately meet different requirements in actual production. Through multi-scenario simulation, potential problems in the design can be discovered in advance, the design scheme can be optimized, and unforeseen problems in production can be avoided. Through simulation evaluation, the best production path and process can be identified in the design stage, improving efficiency and quality in the production process. Through continuous iterative optimization, the most suitable mold structure can be found, not only enhancing the service life of the mold but also improving the accuracy and stability of production. The optimization of each scenario can be customized according to specific requirements, avoiding over-design and waste, and enabling each production scenario to obtain a dedicated solution. The optimized mold structure can effectively handle complex production requirements, enhancing the performance of the mold in the actual production process and ensuring high-quality production output. By dynamically adjusting process parameters, a rapid response to changes in the production process can be made, ensuring that the mold always operates in the best working state and avoiding quality fluctuations in production. By real-time adjusting process parameters, the production line can be continuously optimized, improving production efficiency and reducing unnecessary downtime and commissioning time. The production monitoring optimization engine can form a closed-loop feedback mechanism, continuously optimizing the process through data collection and analysis to achieve continuous improvement and ensuring stability and consistency in the production process.

[0038] Therefore, in any case, the embodiments should be regarded as exemplary and non-limiting. The scope of the present invention is defined by the appended claims rather than the above description. Thus, all changes falling within the meaning and scope of the equivalent elements of the application documents are intended to be encompassed within the present invention.

[0039] As described above, these are merely specific embodiments of the present invention, enabling those skilled in the art to understand or implement the present invention. Various modifications to these embodiments will be obvious to those skilled in the art. The general principles defined herein can 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 these embodiments shown herein, but rather to the broadest scope consistent with the principles and novel features invented herein.

Claims

1. A method for designing a mold for an in vitro diagnostic cuvette, characterized in that: The following steps are involved: Step S1: Obtain the reaction cup mold production log and the preset reaction cup mold design drawing; perform in-depth analysis of multiple application scenarios and scene-by-scene diagnostic demand mining based on the reaction cup mold production log, so as to obtain the diagnostic demand of each scene; Step S2: Perform multi-stage production process analysis on the reaction cup mold production log, and perform process logic dependency mining to construct a production process logic law diagram; Step S3: performing in-depth analysis of the mold structure of the preset reaction cup mold design drawing, and defining standardized module components based on the production process logic law diagram, thereby generating multiple standardized module components; Step S4: Adaptively designing the demand parameters of multiple standardized module components according to the diagnostic requirements of each scenario, and performing multi-scenario demand production simulation to generate comprehensive evaluation values ​​of mold construction simulation for multiple scenarios; Step S5: performing iterative parameter optimization calculation and scene-by-scene mold structure optimization according to the comprehensive evaluation values ​​of mold construction simulation of multiple scenes, and generating a mold optimization structure required for each scene; Step S6: Dynamically adjust the production line process parameters according to the mold optimization structure required for each scenario, thereby building a mold production monitoring optimization engine.

2. The method for designing a mold for an in vitro diagnostic cuvette according to claim 1, characterized in that: The specific steps of step S1 are: Step S11: Obtaining the reaction cup mold production log and the preset reaction cup mold design drawing; Step S12: performing in-depth analysis of multiple application scenarios based on the cuvette mold production log, thereby generating multiple in vitro diagnostic application scenarios; Step S13: performing application environment feature recognition on multiple in vitro diagnostic application scenarios to generate environment features for each application scenario; Step S14: Analyze user usage habits according to multiple in vitro diagnostic application scenarios to generate user usage habit data; Step S15: mining the diagnostic requirements of each scenario based on the environmental characteristics of each application scenario and the user's usage habit data, so as to obtain the diagnostic requirements of each scenario.

3. The method for designing a mold for an in vitro diagnostic cuvette according to claim 1, characterized in that: The specific steps of step S2 are: Step S21: performing a multi-stage production process analysis on the reaction cup mold production log to obtain production behavior process data of multiple stages; Step S22: identifying the process sequence of the production behavior process data of multiple stages to obtain the process sequence characteristics between the stages; Step S23: mining process logic dependencies according to the process sequence characteristics between stages to obtain multi-stage process logic dependencies; Step S24: Perform production process logic evolution on the multi-stage process logic dependency relationship and construct a production process logic law diagram.

4. The method for designing a mold for an in vitro diagnostic cuvette according to claim 1, characterized in that: The specific steps of step S3 are: Step S31: performing a mold structure in-depth analysis on the preset cuvette mold design drawing to generate mold structure features; Step S32: performing structural function type analysis on the mold structural features to obtain functional types of different structures; Step S33: dividing the regions according to the preset cuvette mold design drawings of different structural functional types to generate multiple key structural regions; Step S34: Calculating geometric parameters of multiple key structural regions to generate geometric parameters of each region; Step S35: defining standardized module components for the preset reaction cup mold design drawing according to the production process logic law diagram and the geometric shape parameters of each area, thereby generating multiple standardized module components.

5. The method for designing a mold for an in vitro diagnostic cuvette according to claim 1, characterized in that: The specific steps of step S4 are: Step S41: performing a multi-scenario demand commonality analysis on the diagnostic demand of each scenario to generate multi-scenario common demand features; Step S42: performing differentiated demand identification according to the diagnostic demand of each scenario to obtain differentiated demand data for different scenarios; Step S43: Adaptively design demand parameters for multiple standardized module components according to the common demand characteristics of multiple scenarios and the differentiated demand data of different scenarios, so as to generate different scenario parameters for each module component; Step S44: Perform multi-scenario demand production simulation according to different scenario parameters of each module component to generate comprehensive evaluation values ​​of mold construction simulation for multiple scenarios.

6. The method for designing a mold for an in vitro diagnostic cuvette according to claim 5, characterized in that: The specific steps of step S44 are: Perform multi-scenario production simulation based on different scenario parameters of each module component, and generate mold production simulation data for each scenario requirement; Extract the mold production simulation data required by the first scenario based on the mold production simulation data required by each scenario; Decomposing the mold production simulation data required by the first scenario into stage process parameters, and extracting multiple stage process parameters; Calculate the dimensional accuracy of the production mold according to the process parameters of multiple stages to obtain the dimensional accuracy value of the mold; Quantify the product surface finish of multiple stage process parameters to generate product surface finish; Identify texture uniformity based on process parameters at multiple stages and extract mold texture uniformity; Conduct precise comprehensive evaluation of mold production on mold dimensional accuracy, product surface finish and mold texture uniformity to generate comprehensive evaluation values ​​for mold construction simulation; Traverse each scenario requirement and repeat the above steps to obtain the comprehensive evaluation value of mold construction simulation for multiple scenarios.

7. The method for designing a mold for an in vitro diagnostic cuvette according to claim 1, characterized in that: The specific steps of step S5 are: Step S51: performing optimization target identification according to the comprehensive evaluation values ​​of mold construction simulation of multiple scenes to extract multiple target parameters to be optimized; Step S52: performing iterative parameter optimization calculation on multiple target parameters to be optimized, thereby obtaining multiple optimized target parameters; Step S53: Optimize the mold structure for each scenario based on multiple optimization target parameters to generate a mold optimization structure required for each scenario.

8. The method for designing a mold for an in vitro diagnostic cuvette according to claim 1, characterized in that: The specific steps of step S6 are: Step S61: dynamically adjusting the process parameters of the production line according to the mold optimization structure required by each scenario to obtain a production line process adjustment strategy; Step S62: Perform dynamic mold production control based on the production line process adjustment strategy, and monitor the production line status information in real time; Step S63: performing state change analysis on the monitored production line status information to generate production line state change characteristics; Step S64: Calculate the production efficiency based on the state change characteristics of the production line to obtain the real-time production efficiency; Step S65: Perform adaptive optimization according to the real-time production efficiency, thereby constructing a mold production monitoring optimization engine.

9. A system for designing a mold for an in vitro diagnostic cuvette, characterized in that: The method for designing a mold for an in vitro diagnostic reaction cup according to claim 1 comprises: The scenario requirement module is used to obtain the reaction cup mold production log and the preset reaction cup mold design drawing; based on the reaction cup mold production log, it conducts in-depth analysis of multiple application scenarios and digs out the diagnosis requirements of each scenario, so as to obtain the diagnosis requirements of each scenario; The logic dependency mining module is used to analyze the multi-stage production process of the reaction cup mold production log, and to mine the process logic dependency to build a production process logic law diagram; The module component definition module is used to perform in-depth analysis of the mold structure of the preset reaction cup mold design drawing, and to define standardized module components based on the production process logic law diagram, thereby generating multiple standardized module components; The demand production simulation module is used to design adaptive demand parameters for multiple standardized module components according to the diagnostic requirements of each scenario, and to perform multi-scenario demand production simulation to generate comprehensive evaluation values ​​of mold construction simulation for multiple scenarios; The mold structure optimization module is used to perform iterative parameter optimization calculations and scene-by-scene mold structure optimization based on the comprehensive evaluation values ​​of mold construction simulation in multiple scenarios, and generate the mold optimization structure required for each scenario; The production monitoring and optimization module is used to dynamically adjust the production line process parameters according to the mold optimization structure required for each scenario, thereby building a mold production monitoring and optimization engine.

Images