Preparation method of organic light-emitting display material

Abstract

The invention relates to the technical field of organic light-emitting display manufacturing data processing, provides a preparation method of an organic light-emitting display material, and aims to solve the problem that the material performance is not matched with a data model in the prior art. The method comprises the following steps: acquiring organic light-emitting display material preparation historical data, receiving a preparation task, performing data feature extraction and historical data matching, calling experimental data and theoretical model data in approximate historical data for marking, configuring the experimental data and theoretical model data to a preset control model, and outputting predicted operation control parameters. And comparing the predicted parameter with the historical parameter, and if the difference exceeds a preset error range, optimizing the experimental data and the theoretical model data until the optimized data is within the error range. According to the method, through data integration, model configuration and parameter optimization, the performance of the prepared material meets the expectation, and the preparation efficiency and the material quality are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing for organic light-emitting display manufacturing, and particularly to a method for preparing organic light-emitting display materials. Background Art

[0002] There are various methods for preparing organic light-emitting display materials. Common methods for preparing organic light-emitting display materials include chemical synthesis, solution processing, molecular assembly, etc. Chemical synthesis prepares organic compounds with luminescent properties through organic synthesis chemical reactions. Solution processing dissolves organic light-emitting materials in appropriate solvents and forms luminescent films or devices through processes such as coating, printing, and spraying, which has the characteristics of simplicity and flexibility. Molecular assembly utilizes intermolecular interactions to form an ordered structure, thereby controlling the microstructure of the luminescent material and regulating its optical properties.

[0003] There are the following technical pain points in the method for preparing organic light-emitting display materials: the material properties do not match the data model. In chemical synthesis, the luminescent properties of organic compounds are closely related to their structures, but accurately predicting and simulating the relationship between these properties and structures requires high-precision calculation models and a large amount of experimental data. The difficulty in data processing lies in how to effectively integrate experimental data and theoretical models to accurately predict the luminescent properties of new compounds. To solve this technical pain point, the present invention provides a method for preparing organic light-emitting display materials. Summary of the Invention

[0004] Aiming at the deficiencies of the prior art, the present invention provides a method for preparing organic light-emitting display materials, which solves the problem that the existing method for preparing organic light-emitting display materials has a mismatch between material properties and the data model.

[0005] To solve the above technical problems, the specific technical solution of the present invention is as follows: The present invention provides a method for preparing organic light-emitting display materials, including: Step S101, obtaining historical data for preparing organic light-emitting display materials, where the historical data for preparing organic light-emitting display materials includes experimental data for preparing organic light-emitting display materials and theoretical model data for preparing organic light-emitting display materials; Step S102, receiving a task for preparing organic light-emitting display materials, extracting data features of the task for preparing organic light-emitting display materials to obtain data features corresponding to the task for preparing organic light-emitting display materials, and matching the data features corresponding to the task for preparing organic light-emitting display materials with the historical data for preparing organic light-emitting display materials to obtain approximate historical data for the task for preparing organic light-emitting display materials; Step S103: Retrieve the organic light-emitting display material preparation experimental data and the organic light-emitting display material preparation theoretical model data corresponding to the organic light-emitting display material preparation task included in the approximate historical data of the organic light-emitting display material preparation task, and mark the organic light-emitting display material preparation experimental data and the organic light-emitting display material preparation theoretical model data corresponding to the organic light-emitting display material preparation task; Step S104: Receive the organic light-emitting display material preparation task, configure the marked organic light-emitting display material preparation experimental data and the organic light-emitting display material preparation theoretical model data into a preset organic light-emitting display material preparation control model to obtain a configured organic light-emitting display material preparation control model, substitute the organic light-emitting display material preparation task into the configured organic light-emitting display material preparation control model, and the configured organic light-emitting display material preparation control model outputs predicted operation control parameters; Step S105: Match the organic light-emitting display material preparation task in the organic light-emitting display material preparation historical data to obtain the historical operation control parameters corresponding to the organic light-emitting display material preparation task, compare the predicted operation control parameters with the historical operation control parameters corresponding to the organic light-emitting display material preparation task to obtain a control parameter comparison result, compare the control parameter comparison result with a preset control parameter error range. If the control parameter comparison result is not within the preset control parameter error range, optimize the organic light-emitting display material preparation experimental data and the organic light-emitting display material preparation theoretical model data corresponding to the organic light-emitting display material preparation task until the organic light-emitting display material preparation experimental data and the organic light-emitting display material preparation theoretical model data corresponding to the optimized organic light-emitting display material preparation task are within the preset control parameter error range after operation.

[0006] Further, for the organic light-emitting display material preparation method of the present invention, the step S101 includes: The organic light-emitting display material preparation experimental data includes the material composition of the organic light-emitting display material preparation, the preparation process parameters of the organic light-emitting display material preparation, the equipment settings of the organic light-emitting display material preparation, the experimental environmental conditions, and the experimental results; The organic light-emitting display material preparation theoretical model data includes a material structure model, a physical and chemical property prediction model, and a luminescence mechanism model.

[0007] Further, for the organic light-emitting display material preparation method of the present invention, the step S102 includes: The organic light-emitting display material preparation task includes the type of the target material, the desired performance parameters, and the preparation conditions; The data features corresponding to the task of preparing organic light-emitting display materials include the chemical composition, structural characteristics, desired emission color, brightness, efficiency indicators of the target material, and process parameters involved in the preparation process; Organize the extracted data features into a structured data feature vector, which includes information on the task of preparing organic light-emitting display materials; Match the constructed data feature vector with the historical data of organic light-emitting display material preparation. Using a similarity measurement method, calculate the similarity between the data feature vector and the historical data to obtain a matching result; According to the matching result, select the historical data of organic light-emitting display material preparation with the highest similarity as the approximate historical data for the task of preparing organic light-emitting display materials.

[0008] Further, in the method for preparing organic light-emitting display materials according to the present invention, step S103 includes: Add labels to the experimental data of organic light-emitting display material preparation to obtain experimental condition labels, experimental result labels, and experimental data labels; Add labels to the theoretical model data of organic light-emitting display material preparation to obtain model type labels, applicable range labels, and preparation prediction labels.

[0009] Further, in the method for preparing organic light-emitting display materials according to the present invention, step S104 includes: The task of preparing organic light-emitting display materials includes the material type of the target material to be prepared, the performance indicators of the target material to be prepared, and the preparation conditions of the target material to be prepared; Retrieve the labeled experimental data and theoretical model data of organic light-emitting display material preparation obtained in step S103; configure the labeled experimental data and theoretical model data into a preset control model for organic light-emitting display material preparation.

[0010] Substitute the task of preparing organic light-emitting display materials into the configured control model for organic light-emitting display material preparation, and use the parameters of the task of preparing organic light-emitting display materials, the conditions of the task of preparing organic light-emitting display materials, and the goal of the task of preparing organic light-emitting display materials as inputs to the configured control model for organic light-emitting display material preparation; Start the configured control model for organic light-emitting display material preparation, so that the configured control model for organic light-emitting display material preparation performs calculations based on the input task of preparing organic light-emitting display materials. The configured control model for organic light-emitting display material preparation will generate predicted operation control parameters based on its algorithm and configured data. The predicted operation control parameters include the temperature during the preparation process, the pressure during the preparation process, the time during the preparation process, the process parameters during the preparation process, and the expected material performance indicators.

[0011] Further, in the method for preparing an organic light-emitting display material according to the present invention, step S105 includes: Using the organic light-emitting display material preparation task as a query condition, the characteristics of the organic light-emitting display material preparation task include material type, preparation process, and target performance indicators; Search for historical records similar to the organic light-emitting display material preparation task in the organic light-emitting display material preparation historical database, identify and select the organic light-emitting display material preparation historical data record that best matches the organic light-emitting display material preparation task, and extract the organic light-emitting display material preparation historical operation control parameters from the selected organic light-emitting display material preparation historical data record. The organic light-emitting display material preparation historical operation control parameters include temperature settings, pressure control, time periods, and raw material ratio process parameters during the preparation process; Retrieve the predicted operation control parameters generated in step S104, compare the predicted operation control parameters with the historical operation control parameters one by one, and for each parameter, calculate the difference or deviation between the predicted value and the historical value.

[0012] According to the comparison results, calculate the relative error, absolute error, or percentage error index of the control parameters to quantify the similarity or difference degree between the predicted operation control parameters and the historical operation control parameters.

[0013] Further, in the method for preparing an organic light-emitting display material according to the present invention, step S105 includes: Determine the optimization goal, which is to reduce the difference between the predicted operation control parameters and the historical operation control parameters to within a preset control parameter error range; Define the fitness function of the optimization problem to reflect the error magnitude between the predicted parameters and the historical parameters; When using the genetic algorithm, initialize a population, where each individual in the population represents a set of possible combinations of experimental data and theoretical model parameters; Evaluate each individual in the population and calculate the fitness value of each individual to reflect the error between the predicted operation control parameters corresponding to each individual and the historical operation control parameters; Selection operation, select excellent individuals in the population for reproduction according to the fitness value; Crossover operation, perform a crossover operation on the selected individuals to generate new individuals; Mutation operation, perform a mutation operation on the newly generated individuals; Update the population, update the population with the newly generated individuals to form the next generation population; Iterative optimization, repeat the process of evaluating fitness, selection, crossover, mutation, and updating the population until the preset number of iterations or optimization goal is reached; In each iteration, check whether the predicted operating control parameters of the optimal individual are within the preset control parameter error range.

[0014] When the optimization goal is reached, output the optimized experimental data and the combination of theoretical model parameters.

[0015] Advantages of the present invention: Through steps such as obtaining historical data, data feature extraction and matching, data marking and configuration, control model operation, and parameter optimization, the present invention effectively solves the problem of mismatch between material properties and data models in the preparation process of organic light-emitting display materials. Through the pre-configured control model for the preparation of organic light-emitting display materials, the predicted operating control parameters can be quickly output to guide the actual preparation process, thereby improving the preparation efficiency and quality.

[0016] When the difference between the predicted operating control parameters and the historical operating control parameters is large, the present invention optimizes the experimental data and the theoretical model parameters through optimization algorithms such as genetic algorithms, so that the optimized parameter combination is within the preset error range, improving the accuracy and reliability of the data model.

[0017] The method provided by the present invention is not only applicable to the preparation of organic light-emitting display materials, but also can provide reference for the development of other new display materials, which helps to promote the application scope and performance improvement of organic light-emitting display materials. By integrating experimental data and theoretical model data, and using advanced data processing technologies such as similarity measurement methods and genetic algorithms, the present invention enhances the data processing ability and provides strong data support for the preparation of organic light-emitting display materials. By optimizing the control parameters in the preparation process, the number of experiments and material waste are reduced, thereby reducing the preparation cost and improving the economic benefits. Through data marking and configuration, the control model can adapt to different types of organic light-emitting display material preparation tasks, improving the adaptability and generalization ability of the model.

[0018] In summary, the present invention effectively solves the technical pain points in the preparation process of organic light-emitting display materials, improves the preparation efficiency and quality, and promotes the application and development of organic light-emitting display materials. Brief Description of the Drawings

[0019] In order to more clearly illustrate the technical solutions of the present invention, the following will briefly introduce the drawings required in the embodiments. Obviously, for those of ordinary skill in the art, without creative efforts, other drawings can also be obtained according to the drawings.

[0020] Figure 1 It is a schematic flowchart of the method for preparing organic light-emitting display materials provided by the embodiment of the present invention. Detailed Embodiments

[0021] To make the objectives, technical solutions and advantages of the present invention clearer, the technical solutions of the present invention will be clearly and completely described below in conjunction with specific embodiments of the present invention and the corresponding drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts fall within the scope of protection of the present invention. The following describes the technical solutions provided by the embodiments of the present invention with reference to the drawings. To better understand the objectives of the present invention, the present invention will be further described below.

[0022] The present invention provides a method for preparing an organic light-emitting display material, including: Step S101, obtaining historical data on the preparation of organic light-emitting display materials, where the historical data on the preparation of organic light-emitting display materials includes experimental data on the preparation of organic light-emitting display materials and theoretical model data on the preparation of organic light-emitting display materials; Obtaining experimental data on the preparation of organic light-emitting display materials: Direct experimental records: Directly extract experimental data from past laboratory records, including experimental reports of experimenters, data records automatically generated by experimental equipment, etc.

[0023] Data integration platform: Use a dedicated data integration platform to aggregate experimental data from different experimental equipment and different experimental projects, and query and extract through a unified interface or database.

[0024] Obtaining theoretical model data on the preparation of organic light-emitting display materials: Literature database: Retrieve relevant literature from academic literature databases (such as SciFinder, Reaxys, etc.) and extract the theoretical model data therein.

[0025] Internal R & D database: Obtain verified and optimized theoretical model data from the internal R & D databases of companies or research institutions.

[0026] Data sources: Experimental data: mainly sourced from laboratory experimental records, data outputs of experimental equipment, and observational records of experimenters.

[0027] Theoretical model data: sourced from published academic papers, patent documents, industry standards, and internal R & D achievements.

[0028] The data is stored in tabular form with experimental parameters (such as temperature, pressure, time, etc.) and experimental results (such as luminous efficiency, brightness, color purity, etc.).

[0029] Unstructured data is stored in the form of text or multimedia files, including written descriptions of experimenters, images or videos generated by experimental equipment, etc.

[0030] Theoretical model data: Mathematical model: Represented in the form of mathematical formulas or equations, such as the quantum chemical model of the light-emitting mechanism.

[0031] Simulation data: The simulated data obtained through computer simulation, stored in the form of tables, images, or data files.

[0032] Establish a dedicated database to store experimental data and theoretical model data. The database should have efficient data retrieval and query functions. For unstructured data or structured data with a small amount of data, it can be stored in the file system, such as using Excel tables, text files, or multimedia files, etc. Utilize cloud computing technology to store the data on the cloud server for easy remote access and sharing of the data, and at the same time provide data backup and recovery functions.

[0033] Step S102: Receive the organic light-emitting display material preparation task, extract the data features of the organic light-emitting display material preparation task to obtain the data features corresponding to the organic light-emitting display material preparation task, and match the data features corresponding to the organic light-emitting display material preparation task with the historical data of the organic light-emitting display material preparation to obtain the approximate historical data of the organic light-emitting display material preparation task; After receiving the organic light-emitting display material preparation task, data feature extraction needs to be carried out first. The specific method is as follows: Task parsing: Parse the organic light-emitting display material preparation task to clarify the type of target material, the expected performance parameters, and the preparation conditions.

[0034] Feature recognition: According to the task parsing results, identify the key data features related to the target material, including chemical composition, structural characteristics, expected light-emitting color, brightness, efficiency indicators, etc., as well as the process parameters during the preparation process, such as temperature, pressure, time, etc.

[0035] Feature vectorization: Organize the identified data features into a structured data feature vector, which contains all the key information of the organic light-emitting display material preparation task for subsequent data matching.

[0036] After the data feature extraction is completed, data matching is carried out next. The algorithms and processes of data matching are as follows: Construct a matching model: Use similarity measurement methods (such as cosine similarity, Euclidean distance, etc.) to construct a data matching model.

[0037] Historical data preparation: Extract all available historical data from the historical database of the organic light-emitting display material preparation.

[0038] Feature vector matching: Match the data feature vector with each data item in the historical data of the organic light-emitting display material preparation and calculate the similarity.

[0039] Matching result screening: According to the similarity calculation results, several historical data items with the highest similarity are selected as candidate approximate historical data.

[0040] Determination criteria for approximate historical data: After obtaining the candidate approximate historical data, it is necessary to determine the final approximate historical data. The determination criteria are as follows: Similarity threshold: Set a similarity threshold, and only historical data with a similarity exceeding this threshold can be selected as approximate historical data.

[0041] Data integrity: Check the integrity of the candidate approximate historical data.

[0042] Data quality: Evaluate the quality of the candidate approximate historical data, including data accuracy, reliability, and whether it has been verified, etc. Give priority to historical data with high data quality.

[0043] Data relevance: Analyze the relevance of the candidate approximate historical data to the current preparation task, so that the selected data is highly relevant to key information such as the type of target material, expected performance parameters, and preparation conditions.

[0044] Step S103, retrieve the organic light-emitting display material preparation experimental data and organic light-emitting display material preparation theoretical model data corresponding to the organic light-emitting display material preparation task included in the approximate historical data of the organic light-emitting display material preparation task, and mark the organic light-emitting display material preparation experimental data and organic light-emitting display material preparation theoretical model data corresponding to the organic light-emitting display material preparation task; Specific process of data retrieval: Determine the retrieval scope: According to the identifier or index of the approximate historical data of the organic light-emitting display material preparation task obtained in step S102, determine the data scope to be retrieved. Improve the relevance of the retrieved data to the current preparation task and avoid interference from irrelevant data.

[0045] Data retrieval and extraction: Use the database query or file system retrieval function to quickly locate and extract the required approximate historical data. The extracted data should include but not be limited to organic light-emitting display material preparation experimental data and theoretical model data.

[0046] Data verification and integration: Verify the extracted data to improve its integrity and accuracy. Integrate the verified data to form a unified data format for subsequent processing.

[0047] Method of data marking: Purpose of data marking: Data marking is to better understand and utilize data, and improve the efficiency and accuracy of data processing. Through marking, key information such as the source, nature, and use of data can be quickly identified.

[0048] Experimental data marking: Experimental condition label: Mark the specific conditions of the experiment, such as temperature, pressure, reaction time, etc.

[0049] Experimental result label: Mark the specific results obtained from the experiment, such as luminous efficiency, brightness, color purity, etc.

[0050] Experimental data label: Assign a unique identifier to each experimental data for easy tracking and reference.

[0051] Theoretical model data marking: Model type label: Mark the type of the model, such as material structure model, physical and chemical property prediction model, luminescence mechanism model, etc.

[0052] Applicable scope label: Indicate the specific conditions or scope to which the model applies, such as material type, preparation process, etc.

[0053] Preparation prediction label: Mark the prediction results of the model for the preparation process, such as predicted material properties, preparation process parameters, etc.

[0054] Marking standard: The marking should be accurate, clear, and avoid ambiguity. The marking should be unified and standardized for easy data management and sharing. The marking should follow the standards within the industry or organization to improve data compatibility and comparability.

[0055] Marking implementation: Adopt an automated marking tool or manual marking method, and select a suitable marking method according to the specific situation of the data. Review the marked data to improve the correctness and consistency of the marking. Store the marked data in an appropriate location for subsequent processing and analysis.

[0056] In step S104, receive the organic light-emitting display material preparation task, configure the marked experimental data of the organic light-emitting display material preparation and the theoretical model data of the organic light-emitting display material preparation into a preset organic light-emitting display material preparation control model to obtain a configured organic light-emitting display material preparation control model, substitute the organic light-emitting display material preparation task into the configured organic light-emitting display material preparation control model, and the configured organic light-emitting display material preparation control model outputs the expected operation control parameters; Receive the organic light-emitting display material preparation task, which includes the material type of the target material to be prepared, performance indicators (such as luminous color, brightness, efficiency, etc.) and preparation conditions (such as temperature, pressure, time, etc.).

[0057] Obtain the labeled experimental data and theoretical model data for the preparation of organic light-emitting display materials from step S103. These data include experimental condition labels, experimental result labels, experimental data labels, as well as model type labels, applicable scope labels, and preparation prediction labels.

[0058] Integrate the obtained experimental data and theoretical model data to improve the integrity and consistency of the data.

[0059] Format the data to meet the input requirements of the preset control model for the preparation of organic light-emitting display materials. This may include data type conversion, data range adjustment, etc.

[0060] Configure the formatted data into the preset control model for the preparation of organic light-emitting display materials. This usually involves using the experimental data and theoretical model data as input parameters or training data for the model.

[0061] Set the parameters of the control model correctly, including algorithm selection, number of iterations, learning rate, etc. of the model.

[0062] Operating principle of the control model Model input: Relevant parameters and conditions of the organic light-emitting display material preparation task are used as the input of the control model. These parameters and conditions include detailed information of the target material to be prepared, desired performance indicators, and preparation conditions, etc.

[0063] Model operation: The control model operates based on its built-in algorithms and configured data. This may involve complex mathematical calculations, simulation, or machine learning processes, etc. The purpose of the model operation is to predict the optimal preparation process control parameters according to the input task parameters and conditions, so that the prepared materials meet the desired performance indicators.

[0064] Model output: After the control model operation is completed, the predicted operation control parameters are output. These parameters include temperature, pressure, time, process parameters, etc. during the preparation process, as well as expected material performance indicators.

[0065] Determination method of the predicted operation control parameters: Use the control model to predict the input task parameters and conditions to obtain the predicted operation control parameters.

[0066] During the prediction process, the model will comprehensively consider experimental data, theoretical model data, as well as factors such as the luminescence mechanism and physical and chemical properties of the material.

[0067] Verify the predicted operation control parameters to make them meet the actual requirements and limiting conditions during the preparation process.

[0068] If the prediction parameters exceed the actual operable range or do not meet the preparation requirements, the model needs to be adjusted or the task parameters need to be re - input for prediction.

[0069] Parameter optimization: Optimize the predicted expected operation control parameters. This may involve fine - tuning the model parameters, adding additional experimental data or theoretical model data, etc.

[0070] The purpose of optimization is to further improve the accuracy of the predicted expected operation control parameters, so that the prepared materials have excellent luminescent properties and stability.

[0071] Step S105: Match the organic light - emitting display material preparation task in the historical data of organic light - emitting display material preparation to obtain the historical operation control parameters corresponding to the organic light - emitting display material preparation task. Compare the predicted operation control parameters with the historical operation control parameters corresponding to the organic light - emitting display material preparation task to obtain the control parameter comparison result. Compare the control parameter comparison result with the preset control parameter error range. If the control parameter comparison result is not within the preset control parameter error range, optimize the experimental data of organic light - emitting display material preparation and the theoretical model data of organic light - emitting display material preparation corresponding to the organic light - emitting display material preparation task until the experimental data of organic light - emitting display material preparation and the theoretical model data of organic light - emitting display material preparation corresponding to the optimized organic light - emitting display material preparation task are within the preset control parameter error range after running.

[0072] Specific method for historical data matching: In step S105, in order to match a historical record similar to the current task from the historical data of organic light - emitting display material preparation, the following specific method can be adopted: Feature extraction and vectorization: Extract features from the organic light - emitting display material preparation task, including key information such as material type, preparation process, target performance indicators, etc. Organize these features into a structured data feature vector for matching with historical data.

[0073] Similarity measurement: Use similarity measurement methods (such as cosine similarity, Euclidean distance, etc.) to calculate the similarity between the data feature vector of the current task and the historical data. According to the similarity score, select the historical data with the highest score as the approximate historical data.

[0074] Multi - dimensional matching: In the matching process, multiple dimensions can be comprehensively considered, such as material composition, preparation process parameters, equipment settings, experimental environment conditions, etc., to improve the accuracy of matching.

[0075] Process of control parameter comparison: After obtaining the approximate historical data, it is necessary to compare the predicted operation control parameters with the historical operation control parameters. The specific process is as follows: Parameter extraction: Extract the historical operating control parameters for the preparation of organic light-emitting display materials from approximate historical data, including process parameters such as temperature settings, pressure control, time periods, and raw material ratios during the preparation process.

[0076] Parameter comparison: Compare the expected operating control parameters with the historical operating control parameters one by one, and calculate the difference or deviation between the expected value and the historical value of each parameter.

[0077] Error calculation: According to the comparison results, calculate relative error, absolute error, or percentage error indicators of the control parameters to quantify the similarity or difference degree between the expected operating control parameters and the historical operating control parameters.

[0078] Strategies for data optimization: If the comparison results of the control parameters show that the difference between the expected operating control parameters and the historical operating control parameters exceeds the preset control parameter error range, it is necessary to optimize the experimental data and theoretical model data corresponding to the organic light-emitting display material preparation task. The specific strategies and criteria are as follows: Optimization goal: Define the optimization goal, that is, to reduce the difference between the expected operating control parameters and the historical operating control parameters so that it falls within the preset control parameter error range.

[0079] Definition of fitness function: Define the fitness function for the optimization problem, which should be able to reflect the error size between the expected parameters and the historical parameters, so as to evaluate the advantages and disadvantages of different parameter combinations during the optimization process.

[0080] Application of genetic algorithm: Use optimization algorithms such as genetic algorithms for parameter optimization. Initialize a population, and each individual in the population represents a possible combination of experimental data and theoretical model parameters.

[0081] Evaluate each individual in the population and calculate its fitness value.

[0082] Select excellent individuals for reproduction according to the fitness value, and generate new individuals through crossover and mutation operations.

[0083] Update the population, and repeat the process of evaluation, selection, crossover, mutation, and population update until the preset number of iterations or optimization goal is reached.

[0084] Verification of optimization results: In each iteration, check whether the expected operating control parameters of the optimal individual are within the preset control parameter error range.

[0085] When the optimization goal is reached, output the optimized combination of experimental data and theoretical model parameters, and verify it to improve its effectiveness.

[0086] Optimization criteria: Set clear optimization criteria, such as error thresholds, number of iterations, etc., to enhance the controllability of the optimization process and the reliability of the results.

[0087] Specifically, for the method for preparing an organic light-emitting display material described in the present invention, the step S101 includes: The experimental data for preparing an organic light-emitting display material includes the material components for preparing an organic light-emitting display material, the preparation process parameters for preparing an organic light-emitting display material, the equipment settings for preparing an organic light-emitting display material, the experimental environmental conditions, and the experimental results; The theoretical model data for preparing an organic light-emitting display material includes a material structure model, a physical and chemical property prediction model, and a light-emitting mechanism model.

[0088] In step S101, the historical data obtained for preparing an organic light-emitting display material mainly includes two major categories: the experimental data for preparing an organic light-emitting display material and the theoretical model data for preparing an organic light-emitting display material.

[0089] The experimental data for preparing an organic light-emitting display material, specific content: Material components: List in detail the raw materials used in the experiment and their proportions.

[0090] Preparation process parameters: Include reaction temperature, pressure, time, stirring speed, etc.

[0091] Equipment settings: Record the model of the experimental equipment and the set parameters (such as heating rate, cooling method, etc.).

[0092] Experimental environmental conditions: Such as humidity, temperature, light conditions, etc.

[0093] Experimental results: Include the properties of the experimental product (such as emission color, brightness, efficiency, etc.) and the phenomena observed during the experiment.

[0094] Structure: The experimental data is usually stored in the form of a table or a database. Each row represents an experimental condition or result, and the columns correspond to different data points (such as material components, process parameters, experimental results, etc.).

[0095] Format: CSV, Excel, or a dedicated database software (such as MySQL) can be used to store and manage this data.

[0096] The theoretical model data for preparing an organic light-emitting display material; Specific content: Material structure model: Describe the molecular structure, atomic arrangement, etc. of the material. Physical and chemical property prediction model: Predict the physical and chemical properties of the material (such as solubility, melting point, conductivity, etc.) based on the material structure. Light-emitting mechanism model: Explain the physical and chemical processes of material luminescence, including exciton generation, migration, and recombination, etc.

[0097] Structure: Theoretical model data usually exists in the form of mathematical equations, algorithms, or simulation software. These models can input information such as material composition and structure and output predicted physical and chemical properties and luminescence properties.

[0098] Format: Model data may be stored in the form of code, scripts, or model files, depending on the modeling software or platform used.

[0099] Method for obtaining experimental data: Obtained through channels such as experimental records, equipment outputs, and experimental reports.

[0100] Method for obtaining theoretical model data: Obtained through methods such as literature research, database queries, and generation by modeling software.

[0101] Specifically, in the method for preparing an organic light-emitting display material according to the present invention, step S102 includes: The task of preparing an organic light-emitting display material includes the type of target material, desired performance parameters, and preparation conditions; The data characteristics corresponding to the task of preparing an organic light-emitting display material include the chemical composition, structural characteristics, desired luminescence color, brightness, efficiency index, and process parameters involved in the preparation process of the target material; Organize the extracted data characteristics into a structured data feature vector, and the data feature vector includes information on the task of preparing an organic light-emitting display material; Match the constructed data feature vector with the historical data of the preparation of organic light-emitting display materials. Use a similarity measurement method to calculate the similarity between the data feature vector and the historical data to obtain a matching result; According to the matching result, select the historical data of the preparation of organic light-emitting display materials with the highest similarity as the approximate historical data for the task of preparing organic light-emitting display materials.

[0102] The task of preparing an organic light-emitting display material includes the following key elements: Type of target material: Specify the type of organic light-emitting material to be prepared, such as small molecule luminescent materials, polymer luminescent materials, etc.

[0103] Desired performance parameters: Clearly define the performance indicators that the prepared material should achieve, such as luminescence color, brightness, efficiency, stability, etc.

[0104] Preparation conditions: Describe the environmental conditions required during the preparation process, such as temperature, pressure, atmosphere, etc., and possible special process requirements.

[0105] Method for extracting and organizing data characteristics: According to the specific content of the preparation task, extract key data characteristics from the task description. These data characteristics include but are not limited to: Chemical composition of the target material: List the main elements or compounds that make up the target material.

[0106] Structural characteristics: Describe the molecular structure, crystal form, bonding mode, etc. of the target material.

[0107] Desired luminescence color, brightness, and efficiency indicators: Quantitatively represent the required optical properties.

[0108] Process parameters involved in the preparation process: Such as reaction temperature, time, solvent selection, catalyst type and dosage, etc.

[0109] The extracted data features need to be organized into a structured form for subsequent processing and analysis.

[0110] Construction of the data feature vector: Combine the extracted and organized data features into a data feature vector. This vector contains all the key information of the preparation task and is presented in a structured manner. The construction process of the data feature vector improves the integrity and consistency of the information.

[0111] Matching process: Match the constructed data feature vector with the data in the organic light-emitting display material preparation history database. The matching process includes the following steps: Data preprocessing: Clean, standardize, and format the data in the historical database to make it comparable with the data feature vector.

[0112] Similarity calculation: Use a similarity measurement method to calculate the similarity between the data feature vector and the historical data. The choice of the similarity measurement method should be determined according to the characteristics of the data and application requirements.

[0113] Sorting of matching results: Sort the historical data from high to low according to the similarity calculation results.

[0114] Selection and application of similarity measurement methods: The choice of similarity measurement method depends on the type and structure of the data. For the organic light-emitting display material preparation task, common similarity measurement methods include: Euclidean distance: Suitable for comparing continuous numerical data.

[0115] Cosine similarity: Suitable for comparing vector-type data, especially when considering direction rather than magnitude.

[0116] Jaccard similarity coefficient: Suitable for comparing set-type data, calculating the ratio of the intersection to the union of two sets.

[0117] When choosing a similarity measurement method, it is necessary to consider the characteristics of the data, the computational complexity, and the application requirements. For this task, since the data feature vectors contain various types of data (such as numerical, categorical, etc.), it may be necessary to combine multiple similarity measurement methods for comprehensive evaluation.

[0118] Processing of matching results and selection of approximate historical data: According to the sorting of the matching results, select the historical data with the highest similarity as the approximate historical data for the organic light-emitting display material preparation task. When processing the matching results, the following points need to be noted: Verify similarity: Verify the similarity results to ensure that the selected historical data has a high correlation with the preparation task.

[0119] Consider diversity: If the similarities of multiple historical data to the preparation task are similar, historical data with different preparation conditions or material compositions can be considered as references to increase the diversity of the preparation scheme.

[0120] Update the database: Add the new preparation task and its results to the historical database to continuously enrich and improve the database content and improve the accuracy and efficiency of subsequent matching tasks.

[0121] Specifically, for the organic light-emitting display material preparation method described in the present invention, step S103 includes: Add labels to the experimental data for the preparation of organic light-emitting display materials to obtain experimental condition labels, experimental result labels, and experimental data labels; Add labels to the theoretical model data for the preparation of organic light-emitting display materials to obtain model type labels, applicable range labels, and preparation prediction labels.

[0122] Step S103: Specific methods and implementation of data labeling Specific methods of data labeling: In step S103, adding labels to the experimental data and theoretical model data for the preparation of organic light-emitting display materials is a key link. The specific methods include: Experimental data labeling: Experimental condition labels: According to the specific content of the experimental data, such as preparation conditions like temperature, pressure, time, etc., assign one or more condition labels to each piece of experimental data. For example, if an experiment is carried out at 25°C and 1 atmosphere pressure, it can be labeled as "temperature_25°C", "pressure_1 atmosphere".

[0123] Experimental result labels: According to the experimental results, such as performance indicators like luminous efficiency, brightness, etc., assign corresponding result labels to each piece of experimental data. For example, if an experimental result shows a luminous efficiency of 50%, it can be labeled as "luminous efficiency_50%".

[0124] Experimental data label: Assign a unique identifier (such as an experiment number) to the overall experimental data for easy reference and tracking in subsequent steps.

[0125] Theoretical model data marking: Model type label: According to the specific type of the theoretical model, such as a material structure model, a physical and chemical property prediction model, etc., assign corresponding type labels to each model.

[0126] Applicable scope label: Assign an applicable scope label to the model according to the applicable conditions or scope of the model. For example, if a model is only applicable to a specific type of organic light-emitting material, it can be labeled as "Applicable scope_XXX material".

[0127] Preparation prediction label: Assign a prediction label to the model according to the model's prediction ability for the preparation process. For example, if a model can predict the change in luminous efficiency, it can be labeled as "Prediction ability_Luminous efficiency".

[0128] To perform data marking efficiently, a marking system needs to be designed. This system should have the following functions: Label library management: Establish and maintain a label library, including all possible labels and their definitions. This helps improve the consistency and accuracy of the labels.

[0129] Data marking interface: Provide a user-friendly interface that allows users to select corresponding labels for marking according to the specific content of the data. The interface should support batch marking and custom label functions.

[0130] Data verification and validation: During the marking process, the system should automatically verify and validate the accuracy and consistency of the labels. For example, if a piece of experimental data is marked as "Temperature_25°C", but the actual temperature value in the data is 30°C, the system should issue a warning or error message.

[0131] After marking is completed, the marking results need to be stored and managed. The specific methods include: Database storage: Establish a dedicated database for storing the marked experimental data and theoretical model data. The database should support efficient data retrieval and query functions.

[0132] Data association: Establish an association between each piece of data and the corresponding label. This can be achieved by setting foreign keys or indexes in the database.

[0133] Data backup and recovery: Regularly back up the marked data to prevent data loss or damage. At the same time, a data recovery function should be provided to restore lost or damaged data when necessary.

[0134] Permission Management: To enhance data security, a permission management mechanism should be established to restrict access and modification permissions to data. Only authorized users can access and modify data.

[0135] Specifically, for the method for preparing an organic light-emitting display material described in the present invention, step S104 includes: The organic light-emitting display material preparation task includes the material type of the target material to be prepared, the performance indicators of the target material to be prepared, and the preparation conditions of the target material to be prepared; Retrieve the marked experimental data and theoretical model data of the organic light-emitting display material preparation obtained in step S103; configure the marked experimental data and theoretical model data into a preset organic light-emitting display material preparation control model.

[0136] Substitute the organic light-emitting display material preparation task into the configured organic light-emitting display material preparation control model, and use the parameters of the organic light-emitting display material preparation task, the conditions of the organic light-emitting display material preparation task, and the goal of the organic light-emitting display material preparation task as inputs to the configured organic light-emitting display material preparation control model; Start the configured organic light-emitting display material preparation control model, and enable the configured organic light-emitting display material preparation control model to perform calculations based on the input organic light-emitting display material preparation task. The configured organic light-emitting display material preparation control model will generate predicted operation control parameters based on its algorithm and configured data. The predicted operation control parameters include the temperature during the preparation process, the pressure during the preparation process, the time during the preparation process, the process parameters during the preparation process, and the expected material performance indicators.

[0137] In step S104, the received organic light-emitting display material preparation task includes the following specific contents: Material type of the target material to be prepared: Specify the type of organic light-emitting material to be prepared, such as polymers, small molecules, or quantum dots, etc.

[0138] Performance indicators of the target material to be prepared: Set key performance indicators such as the emission color, brightness, and efficiency of the material to meet the requirements of specific display applications.

[0139] Preparation conditions of the target material to be prepared: Include process parameters such as temperature, pressure, and time required during the preparation process, as well as possible raw material ratios and reaction media, etc.

[0140] Configuration method of the marked experimental data and theoretical model data: Relevant experimental data and theoretical model data have been obtained and marked in step S103. In S104, these marked data will be configured into a preset organic light-emitting display material preparation control model in the following manner: Configuration of experimental data: Associate experimental condition tags (such as temperature, pressure, time, etc.), experimental result tags (such as emission color, brightness, efficiency, etc.), and experimental data tags (such as experimental number, date, operator, etc.) with the corresponding experimental data to form an experimental data set.

[0141] Configuration of theoretical model data: Associate model type tags (such as physical and chemical property prediction models, luminescence mechanism models, etc.), applicable scope tags (such as specific material types, specific process conditions, etc.), and preparation prediction tags (such as predicted emission color, brightness, efficiency, etc.) with the corresponding theoretical model data to form a theoretical model data set.

[0142] Construction and startup process of the organic light-emitting display material preparation control model: Construction of the control model: Based on the labeled experimental data and theoretical model data obtained in step S103, construct an organic light-emitting display material preparation control model. This model may include a data preprocessing module, an algorithm model module, a result output module, etc.

[0143] Initialization of the model: After construction, initialize the model, including setting the initial parameters of the algorithm, loading necessary databases, etc.

[0144] Startup of the model: Input the configured experimental data set and theoretical model data set into the model and start the model for operation.

[0145] Generation and application of predicted operation control parameters: Generation of predicted operation control parameters: The configured organic light-emitting display material preparation control model performs operations based on the input preparation task, experimental data, and theoretical model data and generates predicted operation control parameters. These parameters may include temperature, pressure, time, process parameters during the preparation process, and expected material property indicators, etc.

[0146] Application of predicted operation control parameters: Use the generated predicted operation control parameters to guide the actual organic light-emitting display material preparation process. In actual preparation, the preparation process and equipment settings can be adjusted according to these parameters to achieve the expected luminescence performance.

[0147] Specifically, for the organic light-emitting display material preparation method described in the present invention, step S105 includes: Use the organic light-emitting display material preparation task as a query condition. The characteristics of the organic light-emitting display material preparation task include material type, preparation process, and target performance indicators; Search for historical records similar to the organic light-emitting display material preparation task in the historical database of organic light-emitting display material preparation, identify and select the historical data record of organic light-emitting display material preparation that best matches the organic light-emitting display material preparation task, and extract the historical operation control parameters of organic light-emitting display material preparation from the selected historical data record of organic light-emitting display material preparation. The historical operation control parameters of organic light-emitting display material preparation include temperature settings, pressure control, time periods, and raw material ratio process parameters during the preparation process; Retrieve the predicted operation control parameters generated in step S104, compare the predicted operation control parameters with the historical operation control parameters one by one, and for each parameter, calculate the difference or deviation between the predicted value and the historical value.

[0148] According to the comparison results, calculate the relative error, absolute error, or percentage error index of the control parameters to quantify the similarity or difference degree between the predicted operation control parameters and the historical operation control parameters.

[0149] In step S105, first, the organic light-emitting display material preparation task needs to be used as the query condition. These query conditions should be comprehensive and specific so that similar historical records can be accurately found in the historical database. Specifically, the query conditions should include: Material type: Specify the type of the target material required in the preparation task, such as organic small molecules, polymers, or quantum dots, etc.

[0150] Preparation process: Describe the main process steps and methods involved in the preparation process, such as chemical synthesis, solution processing, or molecular assembly, etc.

[0151] Target performance indicators: Specify the performance indicators expected to be achieved in the preparation task, such as emission color, brightness, efficiency, stability, etc.

[0152] After receiving the query conditions, the next step is to search and match in the historical database of organic light-emitting display material preparation. This process can be broken down into the following steps: Data preprocessing: Preprocess the data in the historical database, including data cleaning, format unification, and index establishment, etc., to improve the search efficiency.

[0153] Similarity calculation: Use appropriate similarity measurement methods, such as cosine similarity, Euclidean distance, or Jaccard similarity, etc., to calculate the similarity between the query conditions and the historical data.

[0154] Matching result screening: According to the similarity calculation results, screen out the historical data records that best match the query conditions. These records will serve as the basis for subsequent comparison and analysis.

[0155] Comparison method of predicted operation control parameters and historical operation control parameters: After obtaining the matched historical data records, it is necessary to retrieve the predicted operation control parameters generated in step S104 and compare them with the historical operation control parameters one by one. The comparison method should include the following steps: Parameter extraction: Extract the historical operation control parameters for the preparation of organic light-emitting display materials from the matched historical data records. These parameters should include temperature settings, pressure control, time periods, and raw material ratios during the preparation process, etc.

[0156] Parameter comparison: Compare the predicted operation control parameters with the historical operation control parameters one by one, and calculate the differences or deviations between each parameter.

[0157] Analysis of comparison results: Analyze the comparison results to determine whether the predicted operation control parameters are consistent with the historical operation control parameters within an acceptable range.

[0158] Calculation of error metrics: To quantify the degree of difference between the predicted operation control parameters and the historical operation control parameters, it is necessary to calculate error metrics. These error metrics can include relative error, absolute error, or percentage error, etc. The specific calculation methods are as follows: Relative error: Calculate the relative difference between the predicted value and the historical value, that is, relative error = (predicted value - historical value) / historical value × 100%.

[0159] Absolute error: Calculate the absolute difference between the predicted value and the historical value, that is, absolute error = |predicted value - historical value|.

[0160] Percentage error: Another form of relative error, used to reflect the percentage deviation between the predicted value and the historical value.

[0161] After calculating the error metrics, they can be applied in the following aspects: Optimization judgment: Determine whether the predicted operation control parameters are within the preset control parameter error range. If not, optimization is required.

[0162] Optimization guidance: According to the magnitude and direction of the error metrics, guide the optimization of the experimental data and theoretical model data corresponding to the organic light-emitting display material preparation task to reduce the difference between the predicted value and the historical value.

[0163] Specifically, for the method for preparing organic light-emitting display materials described in the present invention, step S105 includes: Determine the optimization objective, which is to reduce the difference between the predicted operation control parameters and the historical operation control parameters to within the preset control parameter error range; Define the fitness function of the optimization problem, which is used to reflect the error magnitude between the predicted parameters and the historical parameters; When using the genetic algorithm, initialize a population, where each individual in the population represents a set of possible experimental data and theoretical model parameter combinations; Evaluate each individual in the population, calculate the fitness value of each individual, which is used to reflect the error between the predicted operating control parameters corresponding to each individual and the historical operating control parameters; Selection operation, select excellent individuals in the population for reproduction according to the fitness value; Crossover operation, perform crossover operation on the selected individuals to generate new individuals; Mutation operation, perform mutation operation on the newly generated individuals; Update the population, update the population with the newly generated individuals to form the next generation population; Iterative optimization, repeat the process of evaluating fitness, selection, crossover, mutation, and updating the population until the preset number of iterations or optimization goal is reached; In each iteration, check whether the predicted operating control parameters of the optimal individual are within the preset control parameter error range.

[0164] When the optimization goal is reached, output the optimized experimental data and theoretical model parameter combinations.

[0165] Determination of the optimization goal: The optimization goal is to reduce the difference between the predicted operating control parameters (such as temperature, pressure, time, process parameters, etc. in the preparation process) and the historical operating control parameters to within the preset control parameter error range. This means that a method needs to be found to make the predicted operating control parameters as close as possible to the optimal value in the historical data by adjusting the experimental data and theoretical model parameters.

[0166] Definition of the fitness function: The fitness function is used to quantify the error magnitude between the predicted parameters and the historical parameters. In the present invention, a fitness function can be defined, which calculates the relative error, absolute error, or percentage error between the predicted operating control parameters and the historical operating control parameters, and uses these error values as the fitness value. The smaller the fitness value, the smaller the error between the predicted parameters and the historical parameters, and the higher the fitness of the individual.

[0167] Use of the genetic algorithm: The genetic algorithm is an optimization algorithm that simulates natural selection and genetic mechanisms. It iteratively optimizes the individuals in the population to find the optimal solution or an approximate optimal solution. In the present invention, the genetic algorithm can be used to optimize the experimental data and theoretical model parameters.

[0168] Population initialization: In the genetic algorithm, it is first necessary to initialize a population. Each individual in the population represents a set of possible experimental data and theoretical model parameter combinations. These parameter combinations can be initialized by random generation or based on existing data.

[0169] Individual evaluation: Each individual in the population is evaluated to calculate its fitness value. This usually involves substituting the parameters of the individual into the control model for preparing organic light-emitting display materials to generate predicted operation control parameters and comparing them with the historical operation control parameters to calculate the fitness value.

[0170] Selection operation: Excellent individuals in the population are selected for reproduction according to the fitness value. This can be achieved through strategies such as roulette wheel selection and tournament selection. During the selection process, individuals with higher fitness values have a greater chance of being selected.

[0171] Crossover operation: The selected individuals are subjected to a crossover operation to generate new individuals. The crossover operation can simulate the process of genetic recombination by exchanging some parameters of two individuals to generate new parameter combinations.

[0172] Mutation operation: The newly generated individuals are subjected to a mutation operation to increase the diversity of the population. The mutation operation can simulate the process of gene mutation by randomly changing some parameters of the individuals to generate new parameter combinations.

[0173] Population update: The population is updated with the newly generated individuals to form the next generation population. During the update process, some excellent individuals can be retained as elite individuals so that the excellent genes in the population can be inherited.

[0174] Iterative optimization: The processes of evaluating fitness, selection, crossover, mutation, and population update are repeated until the preset number of iterations or optimization goal is reached. In each iteration, a new population is generated and the fitness value of each individual is calculated.

[0175] Inspection of the optimal individual: In each iteration, it is checked whether the predicted operation control parameters of the optimal individual are within the preset control parameter error range. If the optimization goal is achieved, the optimized experimental data and the combination of theoretical model parameters are output. If the optimization goal is not achieved, the iterative optimization process continues.

[0176] The technical solution of the present invention effectively solves the problem of mismatch between material properties and data models in the existing methods for preparing organic light-emitting display materials: The present invention first obtains a large amount of historical data for preparing organic light-emitting display materials, including experimental data and theoretical model data. These data provide a basis for subsequent data matching and model configuration. When a new task for preparing organic light-emitting display materials is received, the present invention extracts the data characteristics of the task and matches them with the historical data to find the historical data most similar to the new task as approximate historical data.

[0177] Retrieve the experimental data and theoretical model data related to the new task from the approximate historical data, and add detailed labels to these data. Then, configure these labeled data into a preset control model for the preparation of organic light-emitting display materials to obtain a configured control model. Substitute the new preparation task into the configured control model to generate the expected operation control parameters. At the same time, extract the historical operation control parameters similar to the new task from the historical database, and compare the expected parameters with the historical parameters to quantify the difference between the two. If the difference between the expected operation control parameters and the historical operation control parameters exceeds the preset error range, optimize the experimental data and theoretical model data related to the new task.

[0178] The optimization process uses optimization algorithms such as genetic algorithms to continuously iterate and optimize the combination of experimental data and theoretical model parameters until the preset optimization goal or the number of iterations is reached.

[0179] Through the above steps, the technical solution of the present invention can make the error between the expected operation control parameters and the historical operation control parameters within the preset error range, thus effectively solving the problem of mismatch between material performance and data model. This solution not only improves the preparation efficiency and quality of organic light-emitting display materials, but also provides an effective way for the application scope and performance improvement of organic light-emitting display materials.

Claims

1. A method for preparing an organic light-emitting display material, characterized in that: include: Step S101, obtaining historical data of organic light-emitting display material preparation, where the historical data of organic light-emitting display material preparation includes experimental data of organic light-emitting display material preparation and theoretical model data of organic light-emitting display material preparation; Step S102, receiving an organic light-emitting display material preparation task, extracting data features of the organic light-emitting display material preparation task, obtaining data features corresponding to the organic light-emitting display material preparation task, matching the data features corresponding to the organic light-emitting display material preparation task with organic light-emitting display material preparation historical data, and obtaining approximate historical data of the organic light-emitting display material preparation task; Step S103, retrieving the organic light-emitting display material preparation experimental data and the organic light-emitting display material preparation theoretical model data corresponding to the organic light-emitting display material preparation task included in the organic light-emitting display material preparation task approximate historical data, and marking the organic light-emitting display material preparation experimental data and the organic light-emitting display material preparation theoretical model data corresponding to the organic light-emitting display material preparation task; Step S104, receiving an organic light-emitting display material preparation task, configuring the marked organic light-emitting display material preparation experimental data and the organic light-emitting display material preparation theoretical model data to a preset organic light-emitting display material preparation control model, obtaining a configured organic light-emitting display material preparation control model, substituting the organic light-emitting display material preparation task into the configured organic light-emitting display material preparation control model, and the configured organic light-emitting display material preparation control model outputs an expected operation control parameter; Step S105, matching the organic light-emitting display material preparation task with the organic light-emitting display material preparation historical data to obtain the historical operation control parameters corresponding to the organic light-emitting display material preparation task, comparing the expected operation control parameters with the historical operation control parameters corresponding to the organic light-emitting display material preparation task to obtain the control parameter comparison result, comparing the control parameter comparison result with the preset control parameter error range, if the control parameter comparison result is not within the preset control parameter error range, optimizing the organic light-emitting display material preparation experimental data and the organic light-emitting display material preparation theoretical model data corresponding to the organic light-emitting display material preparation task until the optimized organic light-emitting display material preparation experimental data and the organic light-emitting display material preparation theoretical model data corresponding to the organic light-emitting display material preparation task are within the preset control parameter error range after operation.

2. The method for preparing an organic light-emitting display material according to claim 1, wherein: The step S101 includes: The experimental data of the preparation of organic light-emitting display materials include the material composition of the preparation of organic light-emitting display materials, the preparation process parameters of the preparation of organic light-emitting display materials, the equipment settings of the preparation of organic light-emitting display materials, the experimental environment conditions and the experimental results; The theoretical model data for the preparation of organic light-emitting display materials include material structure model, physical and chemical property prediction model and luminescence mechanism model.

3. The method for preparing an organic light-emitting display material according to claim 1, wherein: The step S102 includes: The task of preparing organic light-emitting display materials includes the type of target material, the expected performance parameters and preparation conditions; The data features corresponding to the task of preparing organic light-emitting display materials include the chemical composition, structural characteristics, expected luminous color, brightness, efficiency index, and process parameters involved in the preparation process of the target material; Arrange the extracted data features into a structured data feature vector, wherein the data feature vector includes information of the organic light-emitting display material preparation task; Matching the constructed data feature vector with the historical data of organic light-emitting display material preparation, using a similarity measurement method to calculate the similarity between the data feature vector and the historical data, and obtaining a matching result; According to the matching results, the organic light-emitting display material preparation historical data with the highest similarity is selected as the approximate historical data of the organic light-emitting display material preparation task.

4. The method for preparing an organic light-emitting display material according to claim 1, wherein: The step S103 includes: Adding tags to the experimental data of the preparation of organic light-emitting display materials to obtain experimental condition labels, experimental result labels and experimental data labels; Labels are added to the theoretical model data for the preparation of organic light-emitting display materials to obtain model type labels, applicable scope labels, and preparation prediction labels.

5. The method for preparing an organic light-emitting display material according to claim 1, wherein: The step S104 includes: The task of preparing organic light-emitting display materials includes the material type of the target material, the performance index of the target material and the preparation conditions of the target material; The marked organic light-emitting display material preparation experimental data and theoretical model data obtained in step S103 are retrieved; the marked experimental data and theoretical model data are configured into a preset organic light-emitting display material preparation control model. Substituting the organic light-emitting display material preparation task into the configured organic light-emitting display material preparation control model, and taking the parameters of the organic light-emitting display material preparation task, the conditions of the organic light-emitting display material preparation task, and the target of the organic light-emitting display material preparation task as inputs to the configured organic light-emitting display material preparation control model; Start the configured organic light-emitting display material preparation control model, and make the configured organic light-emitting display material preparation control model perform calculations according to the input organic light-emitting display material preparation tasks. The configured organic light-emitting display material preparation control model will generate expected operation control parameters based on its algorithm and configured data. The expected operation control parameters include the temperature during the preparation process, the pressure during the preparation process, the time during the preparation process, the process parameters during the preparation process, and the expected material performance indicators.

6. The method for preparing an organic light-emitting display material according to claim 1, wherein: The step S105 includes: Using the task of preparing organic light-emitting display materials as a query condition, the characteristics of the task of preparing organic light-emitting display materials include material type, preparation process and target performance index; Searching for historical records similar to the organic light-emitting display material preparation task in the organic light-emitting display material preparation history database, identifying and selecting the organic light-emitting display material preparation history data record that best matches the organic light-emitting display material preparation task, and extracting the organic light-emitting display material preparation history operation control parameters from the selected organic light-emitting display material preparation history data record, the organic light-emitting display material preparation history operation control parameters including temperature setting, pressure control, time cycle, and raw material ratio process parameters during the preparation process; The estimated operation control parameters generated in step S104 are retrieved, and the estimated operation control parameters are compared with the historical operation control parameters one by one. For each parameter, the difference or deviation between the estimated value and the historical value is calculated. Based on the comparison results, the relative error, absolute error or percentage error index of the control parameters is calculated to quantify the similarity or difference between the expected operating control parameters and the historical operating control parameters.

7. The method for preparing an organic light-emitting display material according to claim 1, wherein: The step S105 includes: Determine an optimization target, where the optimization target is to reduce the difference between the expected operation control parameters and the historical operation control parameters to within a preset control parameter error range; Define the fitness function of the optimization problem to reflect the error between the expected parameters and the historical parameters; When using a genetic algorithm, a population is initialized, and each individual in the population represents a possible combination of experimental data and theoretical model parameters; Evaluate each individual in the population and calculate the fitness value of each individual to reflect the error between the expected operation control parameters and the historical operation control parameters corresponding to each individual; Selection operation, which selects excellent individuals in the population for reproduction according to their fitness values; Crossover operation: perform crossover operation on selected individuals to generate new individuals; Mutation operation, performing mutation operation on the newly generated individuals; Update the population, use the newly generated individuals to update the population and form the next generation of population; Iterative optimization, repeating the process of evaluating fitness, selection, crossover, mutation, and updating the population until a preset number of iterations or optimization goal is reached; In each iteration, it is checked whether the estimated operating control parameters of the optimal individual are within the preset control parameter error range. When the optimization goal is reached, the optimized combination of experimental data and theoretical model parameters is output.

Images