Process parameter optimization method, equipment and storage medium

Abstract

The invention discloses a process parameter optimization method and device and a storage medium, and relates to the technical field of data processing, the process parameter optimization method comprises the steps of obtaining a model cue word corresponding to to-be-optimized parameter information, the model cue word being generated based on structured parameter information corresponding to the to-be-optimized parameter information; inputting the model cue words into a plurality of process parameter optimization models to obtain process parameter optimization values output by the process parameter optimization models; and performing preferential comparison on the process parameter optimization values, and determining target parameter optimization information. According to the method, the optimal parameters are selected from the optimal parameter optimization values obtained from the different large models, and the target parameters meeting the requirements are selected, so that the quality of produced products is optimized, the experience dependence on process workers is reduced, and the decision accuracy is improved.

Description

Technical Field

[0001] This application relates to the technical field of data processing, and particularly to a process parameter optimization method, device, and storage medium. Background Art

[0002] In the molding process of molding equipment, traditional parameter adjustment methods highly rely on the experience of operators. This method is not only inefficient, but also due to the experience differences of different operators, the molding results are inconsistent. The frequent trial-and-error process during this period will consume a large amount of time and materials, and it is difficult to meet the optimization requirements of complex process parameters, making it difficult to ensure the stability and consistency of product quality.

[0003] With the development of automation control, sensors, and computer-aided engineering technologies, the monitoring and simulation capabilities of process parameters have been significantly improved. However, these technologies mainly provide auxiliary support and fail to fully utilize production data for intelligent optimization.

[0004] Therefore, in the context of the advancement of Industry 4.0 and intelligent manufacturing, the requirements for efficient and stable production processes are increasing day by day. Summary of the Invention

[0005] The main purpose of this application is to provide a process parameter optimization method, device, and storage medium, aiming to solve the problem that traditional parameter adjustment methods highly rely on the experience of operators.

[0006] To achieve the above objective, this application proposes a process parameter optimization method, and the method includes: Obtain a model prompt word corresponding to the parameter information to be optimized, where the model prompt word is generated based on the structured parameter information corresponding to the parameter information to be optimized; Input the model prompt word into a plurality of process parameter optimization models to obtain the process parameter optimization values output by each of the process parameter optimization models; Perform an optimal comparison on each of the process parameter optimization values to determine the target parameter optimization information.

[0007] In one embodiment, the training process of each of the process parameter optimization models includes: Obtain a plurality of groups of model training data, and determine the model frameworks corresponding to a plurality of initial process parameter optimization models, where the model training data includes process parameter setting values, product quality feedback, and die parameters; Perform data preprocessing, data dimensionality reduction, and feature extraction on each of the model training data to obtain a plurality of groups of model structured feature data; Input each of the model structured feature data into the model frameworks corresponding to a plurality of initial process parameter optimization models for iterative training to obtain each of the process parameter optimization models.

[0008] In one embodiment, obtaining the model prompt words corresponding to the parameter information to be optimized includes: Obtain the parameter information to be optimized; Perform data preprocessing and importance analysis on the parameter information to be optimized to obtain structured parameter information; Generate the model prompt words corresponding to the parameter information to be optimized based on the structured parameter information.

[0009] In one embodiment, the process of comparing and selecting the optimized values of each process parameter to determine the target parameter optimization information includes: Based on a preset integration strategy, integrate the optimized values of each process parameter to obtain a parameter integration ranking; Determine whether each optimized value of the process parameter conforms to a preset conflict range; If so, obtain the target parameter optimization information based on the parameter integration ranking and the expert scoring model.

[0010] In one embodiment, the process of obtaining the target parameter optimization information based on the parameter integration ranking and the expert scoring model includes: Input the optimized values of each process parameter into the expert scoring model to obtain the expert scores corresponding to the optimized values of each process parameter output by the expert scoring model; Based on the expert scores corresponding to the optimized values of each process parameter, re-rank the parameter integration ranking to obtain a parameter comprehensive ranking; Determine the target parameter optimization information based on the parameter comprehensive ranking.

[0011] In one embodiment, the training process of the expert scoring model includes: Obtain a number of groups of expert parameter adjustment knowledge information and a number of groups of parameter adjustment optimized values, and convert each group of expert parameter adjustment knowledge information into expert knowledge rules; Based on each group of expert knowledge rules, establish an expert knowledge base and inject the expert knowledge base into the initial expert scoring model; Input each group of parameter adjustment optimized values into the initial expert scoring model for iterative training to obtain the expert scoring model.

[0012] In one embodiment, after comparing and selecting the optimized values of each process parameter to determine the target parameter optimization information, it further includes: Perform visualization processing on the target parameter optimization information to obtain visualization parameter information; Push the visualized parameter information to the target user for the target user to view, and obtain the user feedback information corresponding to the visualized parameter information; Optimize the process parameter optimization process based on the user feedback information.

[0013] In one embodiment, before obtaining the model prompt words corresponding to the parameter information to be optimized, it further includes: Obtain the parameter information to be optimized, and input the parameter information to be optimized into the process parameter defect identification model to obtain the process parameter defect type output by the process parameter defect identification model; Based on the process parameter defect type, determine the parameter optimization path corresponding to the parameter information to be optimized through a preset greedy algorithm; If the parameter optimization path is multiple large model prediction strategies, obtain the model prompt words corresponding to the parameter information to be optimized.

[0014] In one embodiment, before inputting the model prompt words into several process parameter optimization models to obtain the process parameter optimization values output by each process parameter optimization model, it further includes: If the process parameter optimization model is an external large model, obtain the external model interface corresponding to the process parameter optimization model; According to the external model interface, call the external large model to execute the step of inputting the model prompt words into several process parameter optimization models to obtain the process parameter optimization values output by each process parameter optimization model.

[0015] In addition, to achieve the above object, the present application also proposes a process parameter optimization device, and the process parameter optimization device includes: An acquisition module, configured to acquire model prompt words corresponding to parameter information to be optimized; An output module, configured to input the model prompt words into several process parameter optimization models to obtain the process parameter optimization values output by each process parameter optimization model; An optimization module, configured to perform an optimal comparison on each of the process parameter optimization values to determine the target parameter optimization information.

[0016] In addition, to achieve the above object, the present application also proposes a process parameter optimization device, and the device includes: a memory, a processor, and a computer program stored on the memory and executable on the processor, and the computer program is configured to implement the steps of the process parameter optimization method as described above.

[0017] In addition, to achieve the above object, the present application further provides a storage medium, which is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the process parameter optimization method described above are implemented.

[0018] In addition, to achieve the above object, the present application further provides a computer program product, which includes a computer program. When the computer program is executed by a processor, the steps of the process parameter optimization method described above are implemented.

[0019] The present application provides a process parameter optimization method, device and storage medium. The process parameter optimization method obtains a model prompt corresponding to the parameter information to be optimized, wherein the model prompt is generated based on the structured parameter information corresponding to the parameter information to be optimized. Then, the model prompt is input into a plurality of process parameter optimization models to obtain the process parameter optimization values output by each of the process parameter optimization models. Then, the process parameter optimization values are compared for selection to determine the target parameter optimization information, thereby optimizing the quality of the produced product, reducing the dependence on the experience of the process master, and improving the accuracy of decision-making. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] The drawings herein are incorporated into the specification and constitute a part of the specification, showing embodiments consistent with the present application, and are used together with the specification to explain the principles of the present application.

[0021] To more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, for those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0022] Figure 1 It is a schematic flowchart provided for Embodiment 1 of the process parameter optimization method of the present application; Figure 2 It is a schematic system architecture diagram provided for the process parameter optimization method of the present application; Figure 3 It is a schematic flowchart principle diagram of large model prediction provided for the process parameter optimization method of the present application; Figure 4 It is a schematic principle diagram of the selection of algorithm parameters of multiple large models provided for the process parameter optimization method of the present application; Figure 5 It is a brief example diagram of the overall process of process parameter optimization provided for the process parameter optimization method of the present application; Figure 6 It is a schematic module structure diagram of the process parameter optimization device in the embodiment of the present application; Figure 7 This is a schematic diagram of the device structure of the hardware operating environment involved in the process parameter optimization method in the embodiments of the present application.

[0023] The realization of the purpose, functional characteristics and advantages of the present application will be further described with reference to the embodiments and the accompanying drawings. Specific embodiments

[0024] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application and are not used to limit the present application.

[0025] In order to better understand the technical solutions of the present application, the following will be described in detail with reference to the accompanying drawings of the specification and specific embodiments.

[0026] It should be noted that the execution subject of this embodiment can be a computing service device with data processing, network communication and program running functions, such as a tablet computer, a personal computer, a mobile phone, etc., or an electronic device, a big data service platform, a process parameter optimization system, etc. that can implement the above functions. The following takes the process parameter optimization system as an example to illustrate this embodiment and the following embodiments.

[0027] Based on this, the embodiments of the present application provide a process parameter optimization method, referring to Figure 1 , Figure 1 This is a schematic flowchart provided for Embodiment 1 of the process parameter optimization method of the present application.

[0028] In this embodiment, the process parameter optimization method includes steps S11 to S13: Step S11, obtaining a model prompt word corresponding to the parameter information to be optimized, where the model prompt word is generated based on the structured parameter information corresponding to the parameter information to be optimized; It should be noted that the parameter information to be optimized refers to the relevant information of the process parameters that need to be adjusted and optimized in the production process such as injection molding, die casting, and rubber molding processes, including parameter setting values, etc., which are not limited here.

[0029] Furthermore, it should be noted that the model prompt word refers to the prompt text or data structure generated according to the parameter information to be optimized for guiding the process parameter optimization model to generate parameter optimization values. By obtaining accurate model prompt words, clear and accurate inputs can be provided for subsequent process parameter optimization, ensuring that the optimization model can understand and generate parameter optimization values for specific problems, and improving the pertinence and effectiveness of optimization.

[0030] Specifically, obtain the information of the parameters to be optimized, and then perform data preprocessing and importance analysis on the information of the parameters to be optimized to obtain structured parameter information, so as to generate a model prompt word corresponding to the information of the parameters to be optimized based on the structured parameter information.

[0031] Step S12, input the model prompt word into a plurality of process parameter optimization models, and obtain the optimized values of the process parameters output by each of the process parameter optimization models; It should be noted that the process parameter optimization model refers to a model constructed based on specific algorithms or rules for generating optimized values of process parameters according to the input model prompt word. The model can include models constructed based on different technologies such as machine learning, deep learning, and expert systems, so as to output optimization suggestions for specific problems through the analysis and processing of input data. For reference, Figure 2 , Figure 2 is a schematic diagram of the system architecture provided for the process parameter optimization method of this application.

[0032] This picture shows the system architecture diagram of an intelligent manufacturing system, which is divided into four layers: the infrastructure layer, the model layer, the interaction layer, and the application layer. Each layer has its specific functions and components, jointly constituting a complete intelligent manufacturing solution.

[0033] Among them, the infrastructure layer provides necessary hardware resources, such as servers, workstations, etc., for running the software and algorithms of the intelligent manufacturing system, and collecting and storing various data from the production line, including machine operation data, product quality data, production efficiency data, etc. At the same time, it also collects and stores industry knowledge, which contains the professional knowledge and experience of a specific industry and is used to guide the decision-making and optimization of the intelligent manufacturing system. The regression model in the model layer is used to predict continuous variables, such as product size, weight, etc.; the classification model is used to classify data into different categories, such as whether a product is qualified or not, defect types, etc.; the data analysis model is used to analyze and interpret the patterns and trends in the data; the control model is used to control the operation of the system, such as the automatic adjustment and optimization of machines; the general model is a model applicable to multiple scenarios and problems, providing general solutions; the reasoning model is used for logical reasoning and decision-making, such as fault diagnosis and parameter optimization.

[0034] Secondly, the network system in the interaction layer is used to connect different devices and systems to achieve data transmission and sharing; the intelligent system integrates artificial intelligence technology to handle complex tasks and make decisions; the physical system is used for actual production lines and machines to execute production tasks. The application layer is applied to molding equipment, including: intelligent injection molding machines for injection molding of plastic products, with intelligent control and optimization functions; intelligent die-casting machines for die-casting of metal parts, capable of intelligently adjusting parameters to improve quality and efficiency; intelligent rubber machines for the production of rubber products, with intelligent monitoring and adjustment capabilities. Here, the specific types of molding equipment are not limited and can be configured according to actual situations.

[0035] The entire architecture diagram shows how the intelligent manufacturing system realizes the full-process intelligence from data collection, analysis, decision-making to execution through the collaborative work of different levels. Through this architecture, manufacturing enterprises can improve production efficiency, reduce costs, enhance product quality, and achieve more flexible production management.

[0036] It should be further noted that the optimized process parameter values refer to the optimized process parameter values independently output by the process parameter optimization models of multiple different model frameworks. In addition, it may also include structured outputs of optimization parameter suggestions and adjustment reasons, the process parameter values recommended for adjustment, and the logical explanations behind these adjustments to improve the interpretability of the optimization.

[0037] Specifically, input the model prompt words into several process parameter optimization models to obtain the optimized process parameter values output by each of the process parameter optimization models, so as to utilize the advantages of different models to generate optimized parameter values for process parameters from different perspectives and methods, thereby providing diverse choices for subsequent selection of optimized parameter values and improving the accuracy and reliability of the optimization results. For reference, Figure 3 。

[0038] In this embodiment, the system will input the model prompt words into multiple pre-trained process parameter optimization models at the same time, so that each of the process parameter optimization models independently generates its own optimized process parameter values according to the input prompt words, providing rich candidate solutions for subsequent selection of optimized parameter values.

[0039] Step S13, compare and select the best from each of the optimized process parameter values to determine the target parameter optimization information; It should be noted that the selection and comparison refer to evaluating and comparing multiple candidate optimized process parameter values according to certain criteria and methods, so as to screen out the optimal optimized parameter values.

[0040] Further, it should be noted that the target parameter optimization information refers to the final set values of process parameters obtained after optimization. These parameter values are considered to be the most suitable for the current production requirements after comprehensively considering various factors such as optimization objectives and actual production conditions.

[0041] Additionally, in the process of selecting the best through comparison, various methods can be used to evaluate the advantages and disadvantages of parameter optimization values. For example, the large model can be used to predict the predicted values of evaluation indicators generated after each of the process parameter optimization values are actually put into production. That is, the predicted values of multiple evaluation indicators such as the degree of product quality improvement, the reduction range of production costs, and the difficulty of parameter adjustment obtained after optimizing the actual injection molding process according to each of the process parameter optimization values are estimated. Among them, the evaluation indicators can be set with reference to the user optimization intention of the target user, and corresponding weights are assigned to each indicator. Then, the predicted values of the evaluation indicators corresponding to each process parameter optimization value are weighted and scored according to these weights, and finally the parameter value with the highest score is selected as the target parameter optimization information. In a possible implementation manner, the system will dynamically adjust the weights of the evaluation indicators in combination with the data feedback in actual production to better reflect the importance of different optimization objectives in actual production, thereby improving the accuracy and practicality of the selection through comparison.

[0042] Specifically, based on the preset integration strategy, the process parameter optimization values are integrated to obtain a parameter integration ranking, and then it is judged whether each of the process parameter optimization values conforms to the preset conflict range. Thus, if so, based on the parameter integration ranking and the expert scoring model, the target parameter optimization information can be obtained, for reference Figure 4 。

[0043] Additionally, during the parameter optimization process, the parameter optimization values can be fine-tuned according to the actual production situation. For example, according to the results of actual trial production, the adjustment range of certain parameters can be corrected, or according to abnormal situations during the production process, the parameter optimization values can be temporarily adjusted.

[0044] Furthermore, a feedback mechanism is established through the system to collect data and information in the production process in real time, and the parameter optimization values are dynamically adjusted according to this feedback information, so as to ensure the stability and effectiveness of the optimization process and ultimately achieve the optimization goal of the production process.

[0045] In this embodiment, the model prompt words corresponding to the parameter information to be optimized are obtained, where the model prompt words are generated based on the structured parameter information corresponding to the parameter information to be optimized, and then the model prompt words are input into a plurality of process parameter optimization models to obtain the process parameter optimization values output by each of the process parameter optimization models, so as to perform an optimal comparison on each of the process parameter optimization values, determine the target parameter optimization information, and further optimize the quality of the produced products, reduce the dependence on the experience of the process masters, and improve the accuracy of decision-making.

[0046] In a feasible implementation manner, the training process of each of the process parameter optimization models includes: Step S21, obtain a plurality of groups of model training data, and determine the model frameworks corresponding to a plurality of initial process parameter optimization models, where the model training data includes process parameter setting values, product quality feedback, and die parameters; It should be noted that the model training data refers to various data sets used to train the process parameter optimization models, including process parameter setting values, that is, the process parameter values preset during the production process; product quality feedback, which refers to various quality problems and corresponding feedback information that occur during the production process; additional explanatory information, which refers to other information that affects the production process in addition to the above data, such as production environment conditions, etc.; statistical process control data (SPC data, Statistical Process Control), which refers to the data collected through statistical process control methods and is used to evaluate the stability and quality level of the production process; curve data, which refers to the curve data of certain parameters changing with time during the production process, such as temperature curves, pressure curves, etc.; die parameters, which refer to various parameters related to the die, such as die temperature, die material, etc., so as to provide a rich data basis for subsequent model training, enable the model to learn the relationships between different parameters and their impacts on product quality, and further improve the accuracy and reliability of the model.

[0047] Furthermore, it should be noted that the model framework refers to the model framework constructed according to a specific algorithm or architecture and is used for the subsequent model training process. An appropriate deep learning model framework can be selected according to the characteristics and objectives of the die-casting process. For example, AI models such as recurrent neural networks, long short-term memory networks, and convolutional neural networks can be used to provide a basic structure and algorithm framework for model training, enabling the model to learn and optimize based on these frameworks. Additionally, in order to accelerate model training, transfer learning can be used to utilize existing models in related fields for subsequent model training.

[0048] Even further, Figure 3The full-blooded version of the general model and the inference model in it can be large models that have been trained and can be directly used, while the fine-tuned model is further iteratively trained on the basis of the model framework. For example, a lightweight expert model obtained by fine-tuning the initial model framework according to the internal knowledge base, industry knowledge base, and historical data, etc., to improve the accuracy and robustness of parameter optimization. There is no limitation here and it can be adjusted according to the actual situation.

[0049] Specifically, a number of groups of model training data are obtained, and the model frameworks corresponding to a number of initial process parameter optimization models are determined. In this embodiment, the system will collect this data from multiple data sources and integrate it into a number of groups of model training data to prepare for subsequent model training.

[0050] Furthermore, according to different optimization objectives and data characteristics, a variety of different model frameworks are selected, such as model frameworks based on machine learning, model frameworks based on deep learning, etc., to improve the diversity and adaptability of the model.

[0051] Step S22: Perform data preprocessing, data dimensionality reduction, and feature extraction on each of the model training data to obtain a number of groups of model structured feature data; It should be noted that the data preprocessing refers to operations such as cleaning, screening, and standardizing the original model training data to remove noise and outliers in the data and improve the quality and usability of the data; the data dimensionality reduction refers to reducing the dimension of the data through data dimensionality reduction methods to remove redundant information and improve the training efficiency and performance of the model; the feature extraction refers to extracting features that are of great significance to model training from the original data, so as to better reflect the internal laws and characteristics of the data. Finally, through the above data processing methods, the original data is transformed into structured feature data suitable for model training, improving the learning effect and optimization ability of the model.

[0052] It should be further noted that the model structured feature data refers to data with a specific format and structure that can be used for model training obtained after a series of preprocessing, data dimensionality reduction, and feature extraction operations, containing information that is of great significance to model training, while removing irrelevant or redundant parts, so as to provide high-quality and high-efficiency input for the process parameter optimization model, enabling the model to better learn and understand the laws in the data, and thus improving the performance and optimization effect of the model.

[0053] Specifically, a variety of data preprocessing methods (such as data cleaning, data transformation, data standardization, and data filtering), data dimensionality reduction, and feature extraction methods are used to process the model training data of each group, obtaining several groups of model structured feature data, providing high-quality inputs for subsequent model training. Among them, the data dimensionality reduction includes performing importance analysis between different defects and process parameters to obtain the corresponding relationship between defects and key parameters, thereby reducing the dimensionality of the input, reducing misjudgments caused by unnecessary parameters, and improving the accuracy of the large model's analysis of the process situation; the feature extraction project refers to extracting meaningful features from the original data, for example, statistical features (mean, variance, etc.), time-domain features, and frequency-domain features, etc.; the data filtering identifies and processes outliers and missing values, uses statistical methods or machine learning methods to detect and eliminate abnormal data that does not meet the process requirements, filters out data irrelevant to the target according to process knowledge. Additionally, statistical methods and visualization tools can also be used to analyze the relationship between process parameters and product quality. For example, using machine learning methods such as clustering analysis and association rule mining to discover potential patterns in the data, identifying fluctuations and anomalies in the process by analyzing SPC data and curve data, and ultimately realizing the structured processing of model training data.

[0054] In one embodiment, during the data preprocessing process, the system will select appropriate methods for processing according to the characteristics of the data and the optimization goal. For example, for a dataset with a large amount of noise data, a filtering algorithm can be used for denoising; for a dataset with uneven data distribution, a standardization method can be used for processing. During the data dimensionality reduction process, methods such as principal component analysis (PCA) can be used to remove redundant information in the data and retain the main features. During the feature extraction process, methods such as statistical analysis and machine learning can be used to extract features that have an important impact on the optimization goal, thereby effectively improving the quality and usability of the model training data and providing strong support for the optimization of the model.

[0055] In another embodiment, the correlation between product quality problems and process parameters is analyzed. The analysis methods are not limited to (PCA method (Principal Component Analysis, main component analysis), covariance, probability analysis, etc.). By analyzing the key parameters of quality problems, the input quantity of process parameters is reduced in dimensionality, thereby reducing the input interference to the large model and achieving the purpose of improving the accuracy.

[0056] Specifically, the user provides the current process parameters, product defect types and degrees, and other relevant remarks information to the large language model in a structured manner through a predefined data format (not limited to standard formats such as JSON and XML). Thus, through structured input prompts, the LLM can accurately understand the user's intention and generate a structured output containing optimized parameter suggestions and reasons for adjustment based on its internally pre-trained knowledge and reasoning ability. Among them, the output also adopts a standard data format (not limited to standard formats such as JSON and XML), clearly presenting the process parameter values recommended for adjustment and the logical explanations behind these adjustments. Therefore, through the structured input-output method, not only the efficiency and accuracy of human-computer interaction are improved, but also the optimization process of process parameters becomes more transparent and interpretable.

[0057] Step S23: Input the structured feature data of each model into the model frameworks corresponding to a number of initial process parameter optimization models for iterative training to obtain each process parameter optimization model.

[0058] Specifically, input the structured feature data of each model and the sample labels corresponding to the structured feature data of each model into the number of initial process parameter optimization models. In one embodiment, according to the characteristics and objectives of the die-casting process, a suitable data model is selected. For example, process parameters, SPC data, curve data, die parameters, and other data can be integrated into a multi-dimensional time series data model to obtain the predicted values output by each initial process parameter optimization model. Then, based on the predicted values and the sample labels, the model loss value is calculated using a loss function. In this embodiment, the loss function can be set according to actual needs and is not specifically limited here. After calculating the model loss value, this training process ends, and then the model parameters in each initial process parameter optimization model are updated using the error backpropagation algorithm, and then the next training is carried out. During the training process, it is judged one by one whether the updated initial process parameter optimization model meets the preset training end conditions. If it meets, the updated initial process parameter optimization model is used as the process parameter optimization model. If it does not meet, the model continues to be trained. Among them, the preset training end conditions include loss convergence and reaching the maximum iteration number threshold, etc., so that by continuously adjusting the model parameters, the model can better fit the training data and improve the accuracy and reliability of the model.

[0059] Among them, the processed model structured feature data can be divided into a training set, a validation set, and a test set. The model is trained using the training set with an optimization algorithm (such as the Adam algorithm); the performance of the model is evaluated using the validation set. To improve the accuracy of the model, the model needs to be optimized, including adjusting the hyperparameters of the model, adjusting the structure of the model, and using different optimizers, etc.; the performance of the model is evaluated using the test set, and relevant metrics are calculated, such as mean squared error (MSE), mean absolute error (MAE), and R-squared, to achieve the training and validation of the model.

[0060] Additionally, during the iterative training process, the system can dynamically adjust the training parameters and parameter optimization values according to the training progress and performance of the model. For example, the learning rate and other parameters can be adjusted according to the change of the loss function value of the model to accelerate the convergence speed of the model; the structure and algorithm of the model can be adjusted according to metrics such as the accuracy and recall rate of the model to improve the performance of the model. Through these dynamic adjustment mechanisms, the training effect and optimization ability of the model can be effectively improved, providing high-quality model support for subsequent process parameter optimization.

[0061] In this embodiment, a number of groups of model training data are obtained, and the model frameworks corresponding to a number of initial process parameter optimization models are determined. Among them, the model training data includes process parameter setting values, product quality feedback, and die parameters. Then, data preprocessing, data dimensionality reduction, and feature extraction are performed on each group of the model training data to obtain a number of groups of model structured feature data. Thus, each group of the model structured feature data is input into the model frameworks corresponding to a number of initial process parameter optimization models for iterative training to obtain each of the process parameter optimization models. Furthermore, a number of groups of model training data containing rich information (such as process parameter setting values, product quality feedback, statistical process control data, etc.) are obtained, enabling the model to learn the relationship between parameters and quality under different scenarios and conditions. As a result, the trained process parameter optimization model has stronger generalization ability and can better adapt to various production environments and tasks, rather than being limited to a specific scenario or dataset. When the model faces new and unseen production situations, it can also give reasonable and effective optimization suggestions based on the learned knowledge and rules, thereby improving the stability of the production process and the consistency of product quality, enhancing the accuracy of the model, and reducing the dependence on expert experience by increasing the diversity of parameter optimization values.

[0062] In a feasible implementation manner, the obtaining of the model prompt corresponding to the parameter information to be optimized includes: Step S31, obtaining the parameter information to be optimized; Specifically, the information of parameters to be optimized can be obtained from the production site or relevant data sources. Real-time data during the production process can also be collected through sensors to obtain the current process parameter settings. Product quality feedback information can be obtained through the quality inspection system, and additional description information can be obtained through manual input or system recording, etc. Thus, the information of parameters to be optimized can be obtained in various ways to ensure the comprehensiveness and accuracy of the information. There is no limitation here, and it can be set according to the actual situation.

[0063] Additionally, format verification and validity check are performed on the information of parameters to be optimized to ensure the integrity and accuracy of the data. For example, check whether the values of process parameters are within a reasonable range and whether the defect types are predefined types, etc.

[0064] Step S32: Perform data preprocessing and importance analysis on the information of parameters to be optimized to obtain structured parameter information; It should be noted that the importance analysis refers to evaluating the importance of each parameter information through a certain method to determine which parameters have an important impact on the optimization goal, thereby providing a basis for generating model prompts in the subsequent process. Thus, the original parameter information is transformed into structured parameter information, highlighting key information, removing irrelevant information, and improving the quality of model prompt generation and the optimization effect.

[0065] Furthermore, it should be noted that the structured parameter information refers to the parameter information obtained after data preprocessing and importance analysis, which has a clear format and organizational form. It extracts the content of important significance for the optimization goal from the original information of parameters to be optimized, removes irrelevant or redundant parts, and is organized and formatted according to certain rules and standards, thereby clearly reflecting the relationships between various parameters and their impacts on the optimization goal, providing accurate and efficient basic data for generating model prompts in the subsequent process, enabling the optimization model to more quickly understand and process input information, and thus improving the efficiency and quality of generating optimized parameter values.

[0066] Specifically, in one embodiment, during the data preprocessing process, the system will select a suitable method for processing according to the characteristics of the parameter information and the optimization goal. For example, preprocess and format the original information of parameters to be optimized to ensure its compliance with the input requirements of the optimization model; clean and standardize the data, or convert unstructured data into structured data, etc., thereby improving the processing efficiency and accuracy of the model for input data.

[0067] During the importance analysis process, statistical analysis methods (such as correlation analysis, principal component analysis, etc.) or machine learning methods (such as feature importance evaluation algorithms) can be used to evaluate the importance of each parameter information in the parameter information to be optimized. In one embodiment, the importance analysis can be achieved by calculating the correlation coefficient between each parameter in the parameter information to be optimized and the product quality index, and then sorting the importance according to each correlation coefficient; or by using a machine learning model to output the feature importance scores corresponding to each parameter in the parameter information to be optimized, so as to determine the importance of each parameter in the parameter information to be optimized. Thus, the quality and usability of the structured parameter information are effectively improved, providing strong support for the generation of model prompts.

[0068] Additionally, by combining the system with specific production scenarios and optimization goals, the content and format of the model prompts are dynamically adjusted to better meet different optimization requirements.

[0069] Step S33, generate model prompts corresponding to the parameter information to be optimized based on the structured parameter information.

[0070] Specifically, according to the characteristics of the structured parameter information and the optimization goal, a certain algorithm (such as a machine learning model) or rule (such as a preset prompt generation template) is used to generate model prompts, providing clear and accurate input for subsequent process parameter optimization. Among them, in order to improve the output quality of the model, various prompt engineering techniques can be adopted, such as: providing detailed background information and constraints; using example data for guidance; adopting different questioning methods to stimulate the diverse thinking of the large model.

[0071] Furthermore, the model prompts are sent in parallel to multiple LLM (Large Language Model) instances, and techniques such as multi-threading, multi-processing, or distributed computing are used to achieve parallel inference of the LLM, so that parameter adjustment suggestions for multiple model outputs can be obtained simultaneously, improving the processing efficiency.

[0072] In this embodiment, by obtaining the parameter information to be optimized, and then performing data preprocessing and importance analysis on the parameter information to be optimized, structured parameter information is obtained. Based on the structured parameter information, a model prompt corresponding to the parameter information to be optimized is generated. Then, by removing irrelevant and redundant information, the parameters that truly affect the optimization target are extracted, so that the generated model prompt can more accurately reflect the optimization requirements, thereby guiding the process parameter optimization model to more accurately generate parameter optimization values. The optimization model can more effectively adjust and optimize process parameters based on these high-quality prompts, reduce the optimization deviation caused by the interference of irrelevant information, and then improve the accuracy and effectiveness of optimization, enhance the understanding ability and response speed of the model, while improving the quality and reliability of the parameter optimization values, and reducing the dependence on manual experience.

[0073] In a feasible implementation manner, the process of comparing and selecting the optimal values of each process parameter optimization value to determine the target parameter optimization information includes: Step S41, based on a preset integration strategy, integrating the process parameter optimization values to obtain a parameter integration ranking; It should be noted that the preset integration strategy refers to a solution for comprehensively processing multiple process parameter optimization values according to specific rules and methods, including the voting method: counting the output results of multiple LLMs and selecting the parameter adjustment scheme with the highest frequency; the weighted average method: assigning different weights according to the performance and reliability of the LLMs, and then performing weighted averaging on the output results. There is no limitation here. Thus, through the preset integration strategy, these scattered parameter values can be summarized and sorted to form a comprehensive ordered list of parameter values, that is, the parameter integration ranking, providing an ordered set of candidate parameter values for subsequent conflict detection and optimization selection, enabling the system to more efficiently screen out the optimal optimization parameter values.

[0074] Specifically, various factors can be considered in the generation process of the parameter integration ranking, such as the accuracy, reliability, and implementation difficulty of the parameter optimization values. In a possible implementation manner, each parameter optimization value is weighted and scored according to its historical performance and the confidence of the model, and then sorted according to the scoring results, so as to ensure that each set of parameter values in the parameter integration ranking has undergone comprehensive evaluation, improving the scientificity and rationality of the selection of parameter optimization values.

[0075] Step S42, determining whether each process parameter optimization value meets the preset conflict range; It should be noted that the preset conflict range refers to a conflict detection range preset when there may be conflicts among multiple parameter optimization values. Conflict means that there are significant differences in the parameter adjustment direction or amplitude among different parameter optimization values, which may lead to the inability to achieve the optimization goal or generate contradictions. In one embodiment, assume that during the injection molding process, temperature is a key process parameter, and different optimization models may give different temperature adjustment suggestions. For example, Model A suggests increasing the temperature by 5°C, Model B suggests decreasing the temperature by 3°C, and Model C suggests keeping the current temperature unchanged. If the preset conflict range is ±3°C, then the suggestions of Model A and Model B are beyond this range because the difference between them reaches 8°C. In this case, the system will consider that there is a conflict between these two parameter optimization values and further processing is required.

[0076] Furthermore, it should be noted that the purpose of judging whether each process parameter optimization value conforms to the preset conflict range is to identify those parameter optimization values that may have problems or need further processing. This process judges whether there is a conflict by detecting whether the difference between parameter optimization values exceeds the preset reasonable range. In this embodiment, the system will check each process parameter optimization value one by one according to the preset conflict range to judge whether there is a conflict situation.

[0077] Specifically, the setting of the preset conflict range can be adjusted according to actual production requirements and optimization goals, which is not limited here and can be set according to the actual situation. In a possible implementation manner, the system will set a reasonable conflict threshold based on historical data and expert experience. When the difference between two or more parameter optimization values exceeds this threshold, the system will mark it as having a conflict, so as to ensure that the system can effectively identify conflicts in different scenarios and improve the stability and reliability of the optimization process.

[0078] Step S43, if so, then based on the parameter integration and sorting and the expert scoring model, obtain the target parameter optimization information.

[0079] It should be noted that the expert scoring model refers to a model constructed based on expert experience and historical data for evaluating and scoring parameter optimization values.

[0080] Specifically, if so, input each of the optimized process parameter values into the expert scoring model to obtain the expert scores corresponding to each of the optimized process parameter values output by the expert scoring model. Then, based on the expert scores corresponding to each of the optimized process parameter values, reorder the parameter integration ranking to obtain a comprehensive parameter ranking. Thus, based on the comprehensive parameter ranking, determine the target optimized parameter information, so as to select the optimal optimized parameter value through the evaluation of the expert scoring model, or adjust and integrate conflicting optimized parameter values to generate an optimized parameter value with the best comprehensive performance.

[0081] In this embodiment, based on a preset integration strategy, integrate each of the optimized process parameter values to obtain a parameter integration ranking. Then, determine whether each of the optimized process parameter values meets the preset conflict range. Thus, if so, based on the parameter integration ranking and the expert scoring model, obtain the target optimized parameter information. Furthermore, integrate multiple similar optimized process parameter values to combine the advantages of multiple models, avoid the limitations and biases that may exist in a single model, enable the integrated optimized parameter value to consider various factors and constraints more comprehensively, thereby improving the comprehensiveness and reliability of the optimized parameter value, effectively solving the conflict of the optimized parameter value, enhancing the scientificity and practicality of the optimized parameter value, and reducing the dependence on a single model.

[0082] In a feasible implementation manner, obtaining the target optimized parameter information based on the parameter integration ranking and the expert scoring model includes: Step S51, input each of the optimized process parameter values into the expert scoring model to obtain the expert scores corresponding to each of the optimized process parameter values output by the expert scoring model; It should be noted that the level of the expert score can directly reflect the quality of the optimized parameter value, providing an important basis for the subsequent selection of the optimized parameter value. The expert score is determined by comprehensively considering factors such as the improvement effect of the optimized process parameter value on product quality, the impact on production efficiency, implementation difficulty, cost-benefit, etc., to ensure the comprehensiveness and objectivity of the evaluation result and avoid evaluation biases caused by the preference for a single factor. In practical applications, an enterprise can adjust the evaluation criteria and weights of the expert scoring model according to its own production goals and requirements to make it more in line with the actual optimization needs of the enterprise, which is not limited here.

[0083] Specifically, input each of the optimized process parameter values into the expert scoring model. The expert scoring model extracts relevant features from the integrated parameter adjustment suggestions, such as the adjustment range, adjustment reason, etc. Then, score each parameter adjustment suggestion, and at the same time, evaluate the parameter adjustment suggestion according to the industry knowledge rule base with prior knowledge injection. Finally, obtain the expert scores corresponding to each of the optimized process parameter values output by the expert scoring model.

[0084] Step S52: Based on the expert scores corresponding to the optimized values of each process parameter, reorder the integrated parameter ranking to obtain the comprehensive parameter ranking. It should be noted that the integrated parameter ranking refers to the result of ranking all the optimized values of the process parameters according to certain rules in the preliminary evaluation stage. This ranking may be based on the preliminary evaluation results of the optimized parameter values, the confidence level of the model, or other preset criteria. However, this preliminary ranking may not fully consider the comprehensive performance of the optimized parameter values in actual production. Therefore, the purpose of reordering the integrated parameter ranking based on the expert scores output by the expert scoring model is to generate a more accurate and practical parameter optimization value ranking that meets the actual production requirements. The expert scores provide a quantitative index for each optimized parameter value under multi-dimensional evaluation. By incorporating these scores into the ranking process, it can be ensured that the final comprehensive parameter ranking can more truly reflect the advantages and disadvantages of each optimized parameter value.

[0085] Furthermore, it should be noted that various methods can be used in the reordering process. In one embodiment, the expert scores are used as the main ranking basis, and other auxiliary indicators (such as the confidence level of the model, the innovation of the optimized parameter values, etc.) are combined for comprehensive ranking, so as to ensure the dominant position of the main evaluation criterion (expert scores) while taking into account other important factors and improving the rationality and practicality of the ranking results.

[0086] Step S53: Based on the comprehensive parameter ranking, determine the target parameter optimization information.

[0087] Specifically, due to the fact that the large model itself has a certain degree of randomness and hallucination problems in answering different questioning methods and at different times, this situation will lead to a certain error rate in the answers. Therefore, a method of using a model trained by multiple experts under multiple questions for scoring is adopted. Under the condition of joint decision-making, combined with an expert scoring system, each optimized parameter value is scored, and the one with the highest score becomes the optimal optimized parameter value. That is, the optimized value of the process parameter ranked first in the comprehensive parameter ranking is used as the target parameter optimization information, and among them, the confidence level of the optimal parameter adjustment plan is evaluated and provided to the user for reference.

[0088] In this embodiment, by inputting the optimized values of each process parameter into the expert scoring model, the expert scores corresponding to the optimized values of each process parameter output by the expert scoring model are obtained. Then, based on the expert scores corresponding to the optimized values of each process parameter, the parameter integration sorting is re-sorted to obtain the parameter comprehensive sorting. Thus, based on the parameter comprehensive sorting, the target parameter optimization information is determined. Furthermore, each parameter optimization value is objectively and accurately evaluated to ensure that each parameter optimization value has undergone strict scientific evaluation, thereby effectively improving the scientificity and reliability of the parameter optimization value, avoiding optimization deviations caused by the limitations or randomness of a single model, and further comprehensively evaluating the advantages and disadvantages of each parameter optimization value, selecting the parameter optimization value that performs best in multiple aspects, thereby improving the practicality and feasibility of the parameter optimization value, and solving the conflict of parameter optimization values to avoid optimization failures or production problems caused by the conflict of parameter optimization values.

[0089] In a feasible implementation manner, the training process of the expert scoring model includes: Step S61, obtaining a number of groups of expert parameter adjustment knowledge information and a number of groups of parameter adjustment optimized values, and converting each group of expert parameter adjustment knowledge information into expert knowledge rules; It should be noted that the expert parameter adjustment knowledge information refers to the knowledge and experience of experienced process engineers and technicians in the long-term production practice regarding process parameter adjustment, and the knowledge and experience usually exist in an unstructured form, such as technical documents, operation manuals, and the oral descriptions of engineers.

[0090] Furthermore, it should be noted that the parameter adjustment optimized value refers to the process parameter value actually recorded and optimized by experts during the production process, including process parameter setting values, product quality feedback, production environment conditions, etc., so as to combine the expert's experience knowledge with the actual production data and provide a rich knowledge basis for subsequent model training.

[0091] Specifically, a number of groups of expert parameter adjustment knowledge information and a number of groups of parameter adjustment optimized values are obtained, such as organizing interviews with experienced die-casting process engineers, mold designers, and equipment maintenance personnel; collecting their cause analysis and parameter adjustment experience regarding various die-casting defects (such as porosity, cracks, deformation, etc.); recording their parameter adjustment optimized values under different production conditions (such as different alloys, molds, and equipment states) to obtain a number of groups of expert parameter adjustment knowledge information and a number of groups of parameter adjustment optimized values.

[0092] Furthermore, the process of converting expert parameter adjustment knowledge information into expert knowledge rules is to transform unstructured expert experience into structured rules that can be understood and processed by a computer. In one embodiment, these rules can be represented in the form of "IF-THEN". For example, "IF the porosity defect is severe AND the mold temperature is too low, THEN increase the mold temperature" and "IF the product has cold shuts, then increase the molten metal temperature and the injection speed". Thus, through the above conversion process, the expert's experience knowledge can be systematically applied to process parameter optimization, improving the scientificity and practicality of the parameter optimization values.

[0093] In this embodiment, the system obtains expert parameter adjustment knowledge information through methods such as interviews and document analysis, and combines the parameter adjustment optimization values to convert them into specific expert knowledge rules, preparing for the subsequent establishment of the expert knowledge base and model training.

[0094] In addition, the process of converting expert knowledge rules requires professional knowledge and experience to ensure the accuracy and effectiveness of the rules. In one possible implementation, domain experts can be invited to participate in the rule conversion process. Through the review and verification by the experts, it is ensured that each rule can accurately reflect the expert's experience and knowledge. At the same time, the system also tests and verifies the converted rules to ensure their feasibility and effectiveness in practical applications.

[0095] Step S62: Based on each of the expert knowledge rules, establish an expert knowledge base and inject the expert knowledge base into the initial expert scoring model. It should be noted that the expert knowledge base is a system for storing and managing expert knowledge rules, providing rich knowledge resources for process parameter optimization. It integrates and organizes the scattered rules to form a systematic knowledge system, which is not only convenient for management and query, but also can provide unified knowledge support for subsequent model training, enabling the model to fully consider the expert's experience and knowledge when evaluating process parameter optimization values, improving the accuracy and reliability of the evaluation.

[0096] Specifically, based on each of the expert knowledge rules, an expert knowledge base is established. To ensure the timeliness of knowledge, the effectiveness of the rules is verified using parameter adjustment optimization values and simulation data. According to the verification results, the rules are adjusted and optimized to ensure their accuracy and applicability, and then the expert knowledge base is updated regularly.

[0097] Further, inject the rules in the expert knowledge base into the initial expert scoring model one by one, enabling the model to learn and apply these rules during the training process, so as to generate evaluation results that better meet the actual production requirements. Among them, the process of knowledge injection can be achieved through various technical means, such as rule engines, knowledge graphs, etc. For example, use a rule engine to embed expert knowledge rules into the evaluation logic of the model, so that the model can refer to these rules when evaluating each parameter optimization value. At the same time, the system will also dynamically manage and update the injected knowledge to ensure the timeliness and accuracy of the knowledge base.

[0098] Step S63: Input each of the parameter adjustment and optimization values into the initial expert scoring model for iterative training to obtain the expert scoring model.

[0099] Specifically, obtain each of the parameter adjustment and optimization values, and then perform data preprocessing on each of the parameter adjustment and optimization values, such as data cleaning, normalization, etc., so as to input each of the parameter adjustment and optimization values and the sample labels corresponding to each of the parameter adjustment and optimization values into the initial expert scoring model to obtain the predicted value output by the initial expert scoring model. Then, based on the predicted value and the sample label, calculate the model loss value using a loss function. In this embodiment, the loss function can be set according to actual needs and will not be specifically limited here. After calculating the model loss value, this training process ends, and then use the error backpropagation algorithm to update the model parameters in the initial expert scoring model, and then perform the next training. During the training process, determine whether the updated initial expert scoring model meets the preset training end conditions. If it meets, use the updated initial expert scoring model as the expert scoring model. If it does not meet, continue to train the model. Among them, the preset training end conditions include loss convergence and reaching the maximum iteration number threshold, etc.

[0100] It should be noted that the initial expert scoring model in the above iterative training is the initial expert scoring model that has undergone knowledge injection.

[0101] In this embodiment, by obtaining several sets of expert parameter adjustment knowledge information and several sets of parameter adjustment optimization values, each of the expert parameter adjustment knowledge information is transformed into expert knowledge rules. Then, based on each of the expert knowledge rules, an expert knowledge base is established, and the expert knowledge base is used for knowledge injection into the initial expert scoring model. Thus, each of the parameter adjustment optimization values is input into the initial expert scoring model for iterative training to obtain the expert scoring model. Furthermore, when the model evaluates the process parameter optimization value, it can fully consider the experience and knowledge of experts, improve the accuracy of the model, and make the evaluation result of the model closer to the optimization requirements in actual production. At the same time, when the model scores a certain parameter optimization value, it can clearly display the basis and logic of the score, enabling production personnel to better understand the evaluation process and result of the model, enhancing the interpretability of the model, and reducing the dependence on experts. Then, by quickly evaluating a large number of parameter optimization values, the optimal parameter optimization value is selected, reducing the time and cost of manual evaluation and improving the efficiency of the optimization process.

[0102] In a feasible implementation manner, after comparing and selecting the optimal values of each of the process parameter optimization values to determine the target parameter optimization information, the following steps are further included: Step S71, performing visualization processing on the target parameter optimization information to obtain visualization parameter information; It should be noted that the target parameter optimization information refers to the final process parameter setting values obtained after optimization processing. These parameter values are considered to be the most suitable parameter settings for the current production requirements after comprehensively considering the optimization objectives and actual production conditions.

[0103] Specifically, key parameters in the target parameter optimization information, such as temperature, pressure, injection speed, etc., are displayed in the form of a line chart to clearly present the change trend of the parameters before and after optimization. At the same time, the production quality indicators before and after optimization, such as defect rate, production efficiency, etc., are compared through a bar chart to intuitively display the actual effect brought by the optimization. In addition, the system can also display the difference between the actual value and the recommended value of the current parameter in the form of a dashboard to help users quickly judge whether the parameter needs to be further adjusted. Thus, these complex parameter information are transformed into an intuitive and easy-to-understand visualization form, such as charts, curve graphs, dashboards, etc., so that users can quickly understand and evaluate the optimization result. Users can not only clearly display the adjustment direction and amplitude of the parameters, but also display the differences before and after optimization through comparative analysis, thereby providing a more intuitive reference basis for users. The system can adopt a variety of visualization technologies to transform the target parameter optimization information into visualization parameter information, providing convenience for subsequent user viewing and feedback. The types of visualization are not limited here and can be set according to the actual situation.

[0104] Step S72: Push the visualization parameter information to the target user for the target user to view, and obtain the user feedback information corresponding to the visualization parameter information; It should be noted that the user feedback information includes the satisfaction evaluation of the optimization result, suggestions for parameter adjustment, adjustment requirements for the optimization goal, etc. In one embodiment, the system provides parameter adjustment suggestions for the target user, so that the target user can choose whether to adopt the adjustment suggestions to obtain the user feedback information. For example, the system can obtain the defect description supplemented by the staff, etc., which is not limited here. The target user can be an operator at the production site, a process engineer, a quality management personnel, etc.

[0105] Specifically, through channels such as the user interface or mobile devices, the visualization parameter information is pushed to the target user in real time, and a feedback interface is provided to obtain the user feedback information corresponding to the visualization parameter information, which is convenient for the user to submit feedback information at any time.

[0106] In one embodiment, through a dedicated production management platform, the visualization parameter information can be displayed to the target user in the form of a real-time updated dashboard. At the same time, the user can give feedback through the feedback button on the platform.

[0107] Step S73: Optimize the process parameter optimization process based on the user feedback information.

[0108] Specifically, according to the user feedback information, the process parameter optimization process is optimized, that is, the actual experience and opinions of the user are incorporated into the optimization process to improve the applicability and effectiveness of the optimization process. Because the user feedback information provides an evaluation of the optimization result from the perspective of actual production, these information can help the system discover the deficiencies in the optimization process, such as the deviation of the optimization goal, the unreasonableness of the parameter optimization value, etc. Thus, by adjusting and optimizing the optimization process, the system can better meet the actual production needs and improve the quality and reliability of the optimization result.

[0109] In one embodiment, according to the collected user feedback information, each link in the optimization process is analyzed and adjusted, such as the setting of optimization goals, the selection of model training data, the generation of parameter optimization values, etc., so as to achieve continuous improvement of the optimization process. For example, if users are generally satisfied with the optimized production quality indicators but are concerned about the increased cost, the optimization goals can be readjusted to incorporate cost control into the optimization goal system. At the same time, the system will also supplement or adjust the training data of the optimization model according to the specific suggestions of users for parameter adjustment, so as to improve the adaptability of the model to the actual production situation. For example, if users feedback that the adjustment range of a certain parameter is too large, resulting in new problems in actual production, the system can adjust the relevant weights in the model training data, retrain the optimization model, and generate more reasonable parameter optimization values. Through this dynamic adjustment mechanism based on user feedback, the system can continuously optimize the process parameter optimization process and improve the practicality and reliability of the optimization results.

[0110] In this embodiment, the target parameter optimization information is visually processed to obtain visual parameter information, and then the visual parameter information is pushed to the target user for the target user to view, and the user feedback information corresponding to the visual parameter information is obtained. Based on the user feedback information, the process parameter optimization process is optimized. Furthermore, through visual processing, the complex target parameter optimization information is presented to the user in an intuitive and easy-to-understand form, such as charts, curves, etc., so that the user can more quickly understand the optimization results, including the adjustment direction, amplitude, and expected effects of the parameters, thereby improving the comprehensibility of the optimization results and helping the user better accept and apply the parameter optimization values, and further improving the practicality and effectiveness of the optimization process.

[0111] In a feasible implementation manner, before obtaining the model prompt words corresponding to the parameter information to be optimized, it further includes: Step S81, obtain the parameter information to be optimized, and input the parameter information to be optimized into the process parameter defect identification model to obtain the process parameter defect type output by the process parameter defect identification model; It should be noted that the process parameter defect identification model is a model specifically designed to analyze and identify potential defects caused by improper process parameter settings in the production process. In one embodiment, this model can identify the defect types that may be caused by the current parameter settings by learning the relationship between normal and abnormal process parameters and product quality in historical data.

[0112] Furthermore, it should be noted that the process parameter defect type refers to various product quality problems that may be caused by improper process parameter settings in the production process, including dimensional deviation, surface defects, insufficient material properties, appearance problems, and functional failures, etc., which are not limited here.

[0113] Step S82: Based on the type of process parameter defect, determine the parameter optimization path corresponding to the parameter information to be optimized through a preset greedy algorithm; It should be noted that the preset greedy algorithm refers to an algorithm that makes the optimal choice in the current state at each step of selection, with the expectation that the final result is also the optimal parameter optimization value. The specific greedy algorithm varies depending on the application scenario and is not limited here.

[0114] Furthermore, it should be noted that the parameter optimization path refers to the path from the current process parameter settings to the optimization goal through a series of ordered adjustment steps. The parameter optimization path includes various different parameter optimization values, such as: prediction strategy based on the historical experience library: adjusting parameters according to the historical experience library; single model prediction guidance: using a neural network prediction model to predict the impact of different parameter settings on product quality and guiding parameter adjustment; simulation optimization: evaluating the effect of parameter adjustment through simulation technology and selecting the best solution; multiple large model prediction strategies: using multiple large language models or other advanced analysis models to provide deeper insights and optimization suggestions. The parameter optimization path is not limited here and can be set according to the actual situation.

[0115] Specifically, based on the type of process parameter defect, determine the parameter optimization path corresponding to the parameter information to be optimized through a preset greedy algorithm. In one embodiment, the steps of the preset greedy algorithm are as follows: Define the selection criterion: determine the criterion or rule based on which each step of selection is made; Local optimal selection: in each step, select the current optimal option according to the defined criterion; Iterative selection: repeat the local optimal selection until the termination condition is reached; Result verification: check whether the final result meets the global optimal or acceptable solution. Further, use the above solution as the parameter optimization path corresponding to the parameter information to be optimized.

[0116] In one embodiment, for a process parameter in the parameter information to be optimized, the process of determining the parameter optimization path of the cooling time through a preset greedy algorithm is as follows: Define the selection criterion: The system obtains the current process parameters (such as temperature, pressure, time, etc.) and the corresponding product quality indicators (such as the yield rate, defect rate), and combines the type of process parameter defect (such as "excessive temperature fluctuation", "insufficient pressure") to clarify the specific problem to be optimized, that is, the selection criterion.

[0117] Local Optimal Selection: Based on the defect types of process parameters, the system provides the following four optional parameter optimization paths, including: Adjustment of the historical experience library: Invoke the historical optimization solutions for similar defects; Single-model prediction: Use a single process parameter optimization model to generate recommended values; Multi-model collaborative prediction: Comprehensively analyze the output results of multiple large models; Simulation optimization: Simulate the effects of different parameter combinations through digital twins. Then, immediately evaluate the expected effects of each parameter optimization path (such as estimating the quality improvement range and cost reduction ratio), and select the path with the highest benefit related to the specific problem to be optimized in the current step. For example: If the benefit of multi-model collaborative prediction (such as a 70% quality improvement + a 30% cost reduction) is the highest, then this strategy is preferentially executed.

[0118] Iterative Execution and Termination: Apply the parameter optimization path with the highest benefit in the current step, and re-check the quality indicators after updating the process parameters. It should be noted that this is the step where the parameter optimization path has been determined and parameter optimization is carried out according to this parameter optimization path (i.e., has exited step S82), and reference can be made to Figure 5 . If the standard is not met, that is, the specific problem to be optimized in the "Define Selection Criteria" step is not achieved, then return to the "Local Optimal Selection" step to continue optimization; if the standard is met or the number of iterations exceeds the limit (such as 10 times), terminate the process and output the final parameters.

[0119] Result Verification: Dynamic rollback mechanism. If the actual effect of a certain path deviates from the expectation (such as the quality not increasing but decreasing instead), the system automatically rolls back to the previous step and switches to the sub-optimal path to try again.

[0120] In another specific embodiment, in the injection molding process, when the system detects that the current parameter information to be optimized (melt temperature 200°C, injection pressure 80 MPa, holding time 5 s) causes sink marks on the product surface, it is identified as an "insufficient holding pressure" defect through the process parameter defect identification model, and the specific problem to be optimized is "how to improve the sink marks to more than 70% by adjusting the pressure". Based on the greedy algorithm, the system first estimates the benefits of four optimization schemes related to the specific problem to be optimized. For example, the benefit of the historical experience strategy is "the sink marks are improved to 70%", the benefit of the single model strategy is "the sink marks are improved to 54%", the benefit of the multiple large model prediction strategies is "the sink marks are improved to 85%", and the benefit of the digital twin simulation strategy is "the sink marks are improved to 60%" (it should be noted here that the estimated benefits of the four optimization schemes related to the specific problem to be optimized are not necessarily the actual benefits obtained after the actual operation of the four optimization schemes, but are only the possible benefits close to the true value quickly evaluated by the greedy algorithm, so as to improve the efficiency of path selection). For example, if the system selects the multiple large model prediction strategy with the highest benefit as the parameter optimization path, then the actual parameter optimization is carried out according to the multiple large model prediction strategy (that is, execute the steps of "obtaining the model prompt words corresponding to the parameter information to be optimized, where the model prompt words are generated based on the structured parameter information corresponding to the parameter information to be optimized; inputting the model prompt words into several process parameter optimization models to obtain the process parameter optimization values output by each process parameter optimization model; and comparing and selecting the optimal values of the process parameter optimization values to determine the target parameter optimization information").

[0121] Further, if new problems such as flash occur after adjustment according to the target parameter optimization information of the multiple large model prediction strategy, the system will automatically roll back to the previous effective solution and try again until the quality target is achieved or the iteration limit is reached, for reference Figure 5 .

[0122] Step S83, if the parameter optimization path is the multiple large model prediction strategy, obtain the model prompt words corresponding to the parameter information to be optimized.

[0123] Specifically, if the parameter optimization path is the multiple large model prediction strategy, obtain the model prompt words corresponding to the parameter information to be optimized, for reference Figure 5 , and the process shown in the figure is an automated defect parameter optimization process.

[0124] This embodiment obtains parameter information to be optimized and inputs the parameter information to be optimized into a process parameter defect recognition model to obtain the process parameter defect type output by the process parameter defect recognition model, and then determines the parameter optimization path corresponding to the parameter information to be optimized through a preset greedy algorithm based on the process parameter defect type. If the parameter optimization path is a plurality of large model prediction strategies, the model prompt words corresponding to the parameter information to be optimized are obtained, and then the problem or defect type existing in the current process parameter setting is accurately identified, which helps to quickly locate the source of the problem, provide a clear direction for subsequent optimization work, and automatically determine the best parameter optimization path. At the same time, through the automated parameter optimization value selection, human intervention is reduced, decision-making efficiency is improved, and decision-making errors caused by human factors are reduced, thereby enhancing the targeted optimization and reducing dependence on expert experience.

[0125] In a feasible embodiment, before inputting the model prompt words into a plurality of process parameter optimization models to obtain the process parameter optimization values output by each of the process parameter optimization models, the method further includes: Step S91: if the process parameter optimization model is an external large model, obtaining the external model interface corresponding to the process parameter optimization model; It should be noted that the term "external large models" refers to highly complex and advanced algorithmic models developed by third-party organizations or companies. These models typically run on cloud computing platforms or remote servers and can be accessed and interacted with through network interfaces. These include, but are not limited to, deep learning models, reinforcement learning models, or other machine learning models, capable of processing large amounts of data and providing advanced analytical and predictive capabilities. These models, owing to their sheer scale and powerful computing power, are capable of handling complex optimization tasks and providing more accurate and reliable optimization results.

[0126] Specifically, in intelligent manufacturing systems, when process parameters need to be optimized, if there is no corresponding optimization model internally or more advanced technology needs to be used, or when the target user chooses to directly use an external model for parameter optimization, the system will choose to call an external large model to complete this task. Therefore, it is necessary to obtain an external model interface to be able to communicate and exchange data with these remotely running large models, thereby utilizing their optimization capabilities.

[0127] Step S92: calling the external large model according to the external model interface to execute the step of inputting the model prompt words into a plurality of process parameter optimization models through the external large model to obtain the process parameter optimization values output by each of the process parameter optimization models.

[0128] Specifically, using the method provided by the external model interface, the model prompt is passed as a parameter to the external large model. Then, the model prompt is transmitted from the local system to the external large model on the remote server through the network. After the external large model receives the input data, it executes its internal algorithm for analysis and calculation to generate optimized process parameter values. Subsequently, the optimization result is received from the external large model and stored in the local system for use in the application layer for subsequent process adjustment and production decision-making, thereby achieving the purpose of using the powerful computing and analysis capabilities of the external large model to precisely optimize the process parameters.

[0129] In this embodiment, if the process parameter optimization model is an external large model, the external model interface corresponding to the process parameter optimization model is obtained. Then, according to the external model interface, the external large model is called to execute the step of inputting the model prompt into a plurality of process parameter optimization models to obtain the process parameter optimization values output by each process parameter optimization model. Thus, by calling an external large model that has been trained and verified with a large amount of data and has high accuracy and reliability, the accuracy of process parameter optimization is improved, thereby improving product quality and production efficiency. At the same time, since using the external model interface can easily switch different optimization models to adapt to different production requirements and conditions, the development and maintenance costs are reduced, and the system can quickly adapt to changes, improving the adaptability of the system. Furthermore, the integration and deployment process of the process parameter optimization model is simplified, reducing the implementation time and accelerating the project progress.

[0130] Exemplarily, to facilitate understanding of the implementation process of the process parameter optimization method, please refer to Figure 5 , Figure 5 which is a brief example diagram of the overall process of process parameter optimization provided for the process parameter optimization method of this application.

[0131] Specifically, the figure shows an implementation process of process parameter defect optimization. This process starts with the discovery of defects, and then neural network technology is used to identify the defect types. Once the defects are classified, the system will decide the next action path according to the classification result.

[0132] Further, if the identified defect type is a machine problem, human intervention is required for processing, such as pushing it to the staff and further resolving it by means of human intervention. For non-machine problems, that is, parameter problems, the system will use a greedy algorithm to select parameter optimization values to determine the best optimization path. This parameter optimization value may involve one or more of neural network prediction strategies, multiple large model prediction strategies, or historical experience library prediction strategies, which are not limited here and can be independently predicted or multiple selected predictions. After determining the optimization path, the system will check whether the parameters of the selected parameter optimization value conform to the preset basic rules. If the parameters conform to the rules, the system will evaluate whether the defect has been resolved; if the defect still exists, the process will return to the stage of neural network identifying the defect type to reclassify the defect. If the parameters do not conform to the rules, the system will also return to the step of using the greedy algorithm to select parameter optimization values to determine the best optimization path until the parameters conform to the rules.

[0133] For example, in the injection molding process, if it is found that there are air hole defects on the product surface, the system first identifies through the neural network whether this is due to equipment failure or improper parameter settings. If it is a parameter problem, the system uses a greedy algorithm to select parameter optimization values to determine the best optimization path, so as to output corresponding optimization parameters according to the strategies in the best optimization path. Further, if the proposed parameter adjustment conforms to the production rules and the defect is resolved after implementation, the process ends; if the defect still exists, it is necessary to re-identify the defect type and continue to optimize the process. If the proposed parameter adjustment does not conform to the production rules, it will return to the step of using the greedy algorithm to select parameter optimization values to determine the best optimization path until the parameters conform to the rules, so as to continuously learn and adjust by combining artificial intelligence and expert knowledge to improve the stability of the production process and product quality and reduce the dependence on manual labor.

[0134] It should be noted that the examples in the figure are only for understanding this application and do not constitute a limitation on the process parameter optimization method of this application. Based on this technical concept, more forms of simple transformations are within the protection scope of this application.

[0135] It should be understood that the magnitudes of the sequence numbers of the steps in the above embodiments do not mean the order of execution. The order of execution of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0136] This application also provides a process parameter optimization device. Please refer to Figure 6 The process parameter optimization device includes: An acquisition module 61, configured to acquire a model prompt word corresponding to the parameter information to be optimized, where the model prompt word is generated based on the structured parameter information corresponding to the parameter information to be optimized; An output module 62 for inputting the model prompt words into a plurality of process parameter optimization models to obtain the optimized values of the process parameters output by each of the process parameter optimization models; An optimization module 63 for preferentially comparing the optimized values of the process parameters to determine the target parameter optimization information.

[0137] The process parameter optimization device is further configured to: Obtain several sets of model training data and determine the model frameworks corresponding to several initial process parameter optimization models, where the model training data includes process parameter setting values, product quality feedback, and die parameters; Perform data preprocessing, data dimensionality reduction, and feature extraction on each set of model training data to obtain several sets of model structured feature data; Input each set of model structured feature data into the model frameworks corresponding to several initial process parameter optimization models for iterative training to obtain each of the process parameter optimization models.

[0138] The process parameter optimization device is further configured to: Obtain the parameter information to be optimized; Perform data preprocessing and importance analysis on the parameter information to be optimized to obtain structured parameter information; Generate a model prompt word corresponding to the parameter information to be optimized based on the structured parameter information.

[0139] The process parameter optimization device is further configured to: Integrate the optimized values of the process parameters based on a preset integration strategy to obtain a parameter integration ranking; Determine whether each of the optimized values of the process parameters meets a preset conflict range; If so, obtain the target parameter optimization information based on the parameter integration ranking and an expert scoring model.

[0140] The process parameter optimization device is further configured to: Input each of the optimized values of the process parameters into the expert scoring model to obtain the expert scores corresponding to each of the optimized values of the process parameters output by the expert scoring model; Re-rank the parameter integration ranking based on the expert scores corresponding to each of the optimized values of the process parameters to obtain a parameter comprehensive ranking; Determine the target parameter optimization information based on the parameter comprehensive ranking.

[0141] The process parameter optimization device is further configured to: Obtain several sets of expert parameter adjustment knowledge information and several sets of parameter adjustment optimized values, and convert each set of expert parameter adjustment knowledge information into expert knowledge rules; Based on each of the expert knowledge rules, an expert knowledge base is established, and the expert knowledge base is used to inject knowledge into the initial expert scoring model; The adjusted and optimized values of each parameter are input into the initial expert scoring model for iterative training to obtain the expert scoring model.

[0142] The process parameter optimization device is further configured to: Perform visualization processing on the target parameter optimization information to obtain visualized parameter information; Push the visualized parameter information to the target user for the target user to view, and obtain the user feedback information corresponding to the visualized parameter information; Optimize the process parameter optimization process based on the user feedback information.

[0143] The process parameter optimization device is further configured to: Obtain the parameter information to be optimized, and input the parameter information to be optimized into the process parameter defect identification model to obtain the process parameter defect type output by the process parameter defect identification model; Based on the process parameter defect type, determine the parameter optimization path corresponding to the parameter information to be optimized through a preset greedy algorithm; If the parameter optimization path is multiple large model prediction strategies, obtain the model prompt words corresponding to the parameter information to be optimized.

[0144] The process parameter optimization device is further configured to: If the process parameter optimization model is an external large model, obtain the external model interface corresponding to the process parameter optimization model; According to the external model interface, call the external large model to execute the step of inputting the model prompt words into a plurality of process parameter optimization models to obtain the process parameter optimization values output by each of the process parameter optimization models.

[0145] The process parameter optimization device provided in this application adopts the process parameter optimization method in the above embodiment and can solve the technical problems in the background art. Compared with the prior art, the beneficial effects of the process parameter optimization device provided in this application are the same as those of the process parameter optimization method provided in the above embodiment, and other technical features in the process parameter optimization device are the same as the features disclosed in the above embodiment method, and will not be elaborated here.

[0146] The present application provides a process parameter optimization device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein, the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the process parameter optimization method in the first embodiment above.

[0147] Reference is made below Figure 7 , which shows a schematic structural diagram of a process parameter optimization device suitable for implementing the embodiments of the present application. The process parameter optimization device in the embodiments of the present application may include, but is not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistant), PADs (Portable Application Description: tablet computers), PMPs (Portable Media Player: portable multimedia players), in-vehicle terminals (such as in-vehicle navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 7 The process parameter optimization device shown is merely an example and should not impose any limitation on the functions and usage scope of the embodiments of the present application.

[0148] As Figure 7 shown, the process parameter optimization device may include a processing device 1001 (such as a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory 1002 or a program loaded from a storage device 1003 into a random access memory 1004. In the random access memory 1004, various programs and data required for the operation of the process parameter optimization device are also stored. The processing device 1001, the read-only memory 1002, and the random access memory 1004 are connected to each other through a bus 1005. An input / output interface 1006 is also connected to the bus. Generally, the following systems may be connected to the input / output interface 1006: an input device 1007 including, for example, a touch screen, a touchpad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; an output device 1008 including, for example, a liquid crystal display (LCD: Liquid Crystal Display), a speaker, a vibrator, etc.; a storage device 1003 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 1009. The communication device 1009 can allow the process parameter optimization device to communicate with other devices wirelessly or wiredly to exchange data. Although the figure shows a process parameter optimization device with various systems, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems may be implemented or provided alternatively.

[0149] In particular, according to the embodiments disclosed in the present application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, the embodiments disclosed in the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program contains program codes for executing the methods shown in the flowcharts. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device, or installed from a storage device 1003, or installed from a read-only memory 1002. When the computer program is executed by a processing device 1001, the above functions defined in the methods of the embodiments disclosed in the present application are executed.

[0150] The process parameter optimization device provided by the present application adopts the process parameter optimization method in the above embodiment and can solve the technical problems in the background art. Compared with the prior art, the beneficial effects of the process parameter optimization device provided by the present application are the same as those of the process parameter optimization method provided by the above embodiment, and other technical features in the process parameter optimization device are the same as the features disclosed in the method of the previous embodiment, which will not be elaborated here.

[0151] It should be understood that each part disclosed in the present application can be implemented by hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in a suitable manner in any one or more embodiments or examples.

[0152] As described above, only the specific embodiments of the present application are provided, but the protection scope of the present application is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed in the present application, and all of them should be covered by the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

[0153] The present application provides a computer-readable storage medium having computer-readable program instructions (i.e., computer programs) stored thereon, and the computer-readable program instructions are used to execute the process parameter optimization method in the above embodiment.

[0154] The computer-readable storage medium provided by the present application can be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems or devices, or any combination of the above. More specific examples of the computer-readable storage medium may include, but are not limited to: electrical connections with one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM) or flash memory, optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the above. In this embodiment, the computer-readable storage medium can be any tangible medium that contains or stores a program, and this program can be used by or in combination with an instruction execution system or device. The program code contained on the computer-readable storage medium can be transmitted by any suitable medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination of the above.

[0155] The above computer-readable storage medium can be included in the process parameter optimization device; or it can exist independently and not be assembled into the process parameter optimization device.

[0156] The above computer-readable storage medium carries one or more programs. When the above one or more programs are executed by the process parameter optimization device, the process parameter optimization device is caused to: Obtain a model prompt word corresponding to the parameter information to be optimized, where the model prompt word is generated based on the structured parameter information corresponding to the parameter information to be optimized; Input the model prompt word into a number of process parameter optimization models to obtain the process parameter optimization values output by each of the process parameter optimization models; Perform an optimization comparison on each of the process parameter optimization values to determine the target parameter optimization information.

[0157] Computer program code for performing the operations of this application can be written in one or more programming languages or combinations thereof. The above-mentioned programming languages include object-oriented programming languages such as Java, Smalltalk, C++, and also include conventional procedural programming languages such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, executed as an independent software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any kind of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computer (for example, by connecting through an Internet service provider using the Internet).

[0158] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions, and operations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in the flowchart or block diagram may represent a module, a program segment, or a part of the code, and this module, program segment, or part of the code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than that marked in the accompanying drawings. For example, two consecutively represented blocks may actually be executed substantially in parallel, and they may sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram and / or flowchart, as well as the combination of blocks in the block diagram and / or flowchart, can be implemented by a dedicated hardware-based system for performing the specified functions or operations, or can be implemented by a combination of dedicated hardware and computer instructions.

[0159] The modules involved in the embodiments described in this application can be implemented in software or in hardware. Among them, the name of the module does not constitute a limitation on the unit itself in some cases.

[0160] The readable storage medium provided in this application is a computer-readable storage medium. The computer-readable storage medium stores computer-readable program instructions (i.e., computer programs) for performing the above-mentioned process parameter optimization method, and can solve the technical problems in the background art. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in this application are the same as those of the process parameter optimization method provided in the above embodiments, and will not be elaborated here.

[0161] An embodiment of the present application provides a computer program product, including a computer program, which when executed by a processor implements the steps of the process parameter optimization method as described above.

[0162] The computer program product provided by the present application can solve the technical problems in the background art. Compared with the prior art, the beneficial effects of the computer program product provided by the embodiment of the present application are the same as those of the process parameter optimization method provided by the above embodiment, and will not be elaborated here.

[0163] The above are only some embodiments of the present application, and do not limit the patent scope of the present application. Any equivalent structural transformation made by using the content of the specification and drawings of the present application under the technical concept of the present application, or direct / indirect application in other related technical fields, is included in the patent protection scope of the present application.

Claims

1. A process parameter optimization method, characterized in that, Including: Obtain a model prompt corresponding to the parameter information to be optimized, where the model prompt is generated based on the structured parameter information corresponding to the parameter information to be optimized; Input the model prompt into a number of process parameter optimization models to obtain the process parameter optimization values output by each of the process parameter optimization models; Perform a preference comparison on each of the process parameter optimization values to determine the target parameter optimization information.

2. The process parameter optimization method according to claim 1, characterized in that, The training process of each of the process parameter optimization models includes: Obtain a number of sets of model training data and determine the model frameworks corresponding to a number of initial process parameter optimization models, where the model training data includes process parameter setting values, product quality feedback, and die parameters; Perform data preprocessing, data dimensionality reduction, and feature extraction on each of the model training data to obtain a number of sets of model structured feature data; Input each of the model structured feature data into the model frameworks corresponding to a number of initial process parameter optimization models for iterative training to obtain each of the process parameter optimization models.

3. The process parameter optimization method according to claim 1, wherein The obtaining of the model prompt corresponding to the parameter information to be optimized includes: Obtain the parameter information to be optimized; Perform data preprocessing and importance analysis on the parameter information to be optimized to obtain structured parameter information; Generate a model prompt corresponding to the parameter information to be optimized based on the structured parameter information.

4. The process parameter optimization method according to claim 1, wherein The performing of a preference comparison on each of the process parameter optimization values to determine the target parameter optimization information includes: Based on a preset integration strategy, integrate the process parameter optimization values to obtain a parameter integration ranking; Determine whether each of the process parameter optimization values conforms to a preset conflict range; If so, obtain the target parameter optimization information based on the parameter integration ranking and an expert scoring model.

5. The process parameter optimization method according to claim 4, characterized in that The obtaining of the target parameter optimization information based on the parameter integration ranking and the expert scoring model includes: Input each of the process parameter optimization values into the expert scoring model to obtain the expert scores corresponding to each of the process parameter optimization values output by the expert scoring model; Based on the expert scores corresponding to each of the process parameter optimization values, re-rank the parameter integration ranking to obtain a parameter comprehensive ranking; Determine the target parameter optimization information based on the parameter comprehensive ranking.

6. The process parameter optimization method according to claim 4, wherein, The training process of the expert scoring model includes: Obtain a number of sets of expert parameter adjustment knowledge information and a number of sets of parameter adjustment optimization values, and convert each of the expert parameter adjustment knowledge information into expert knowledge rules; Based on each of the expert knowledge rules, establish an expert knowledge base and inject the expert knowledge base into an initial expert scoring model; Input each of the parameter adjustment optimization values into the initial expert scoring model for iterative training to obtain the expert scoring model.

7. The process parameter optimization method according to claim 1, wherein After the performing of a preference comparison on each of the process parameter optimization values to determine the target parameter optimization information, it further includes: Perform visualization processing on the target parameter optimization information to obtain visualization parameter information; Push the visualization parameter information to a target user for the target user to view, and obtain user feedback information corresponding to the visualization parameter information; Optimize the process parameter optimization process based on the user feedback information.

8. The process parameter optimization method according to claim 1, wherein Before obtaining the model prompt words corresponding to the parameter information to be optimized, it further includes: Obtain the parameter information to be optimized, and input the parameter information to be optimized into the process parameter defect recognition model to obtain the process parameter defect type output by the process parameter defect recognition model; Based on the process parameter defect type, determine the parameter optimization path corresponding to the parameter information to be optimized through a preset greedy algorithm; If the parameter optimization path is multiple large model prediction strategies, obtain the model prompt words corresponding to the parameter information to be optimized.

9. The process parameter optimization method according to claim 1, characterized in that Before inputting the model prompt words into several process parameter optimization models to obtain the process parameter optimization values output by each of the process parameter optimization models, it further includes: If the process parameter optimization model is an external large model, obtain the external model interface corresponding to the process parameter optimization model; According to the external model interface, call the external large model to execute the step of inputting the model prompt words into several process parameter optimization models to obtain the process parameter optimization values output by each of the process parameter optimization models.

10. A process parameter optimization device, characterized in that, The process parameter optimization device includes: a memory, a processor, and a computer program stored on the memory and executable on the processor, and the computer program is configured to implement the steps of the process parameter optimization method according to any one of claims 1 to 9.

11. A storage medium, characterized in that, The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, it implements the steps of the process parameter optimization method according to any one of claims 1 to 9.

Images