Method for training ASE threshold and wavelength prediction model, prediction method and device

Abstract

The application relates to the technical field of organic laser materials, in particular to an ASE threshold and wavelength prediction model training method and an organic laser material performance prediction method, wherein the method comprises the following steps: acquiring the molecular structures and optical physical parameters of a plurality of reference organic laser materials; identifying the amplified spontaneous emission (ASE) threshold and wavelength in the optical physical parameters; generating a data set according to the molecular structures and the ASE threshold and wavelength of the reference organic laser materials; constructing an ASE threshold and wavelength prediction model based on a machine learning algorithm, training the prediction model by using the data set, and predicting the ASE threshold and wavelength of a target organic laser material based on the trained prediction model. Therefore, the problems that the related art is time-consuming and high in cost in finding low-amplified spontaneous emission threshold organic laser molecules, and it is difficult to quickly and effectively screen suitable molecules are solved.

Description

Technical Field

[0001] This application relates to the field of organic laser materials technology, and in particular to an ASE threshold and wavelength prediction model training method and a performance prediction method for organic laser materials. Background Technology

[0002] Organic electrically pumped lasers (OILs) have become a research hotspot in the optoelectronics field in recent years due to their excellent energy conversion efficiency, flexible manufacturing processes, and broad application potential. However, current technologies have made limited progress in finding organic laser molecules with low amplification spontaneous emission thresholds, making the reduction of the amplification spontaneous emission threshold a pressing problem. Traditional methods are typically time-consuming and costly, making it difficult to quickly and effectively screen suitable molecules. Summary of the Invention

[0003] This application provides a training method for ASE threshold and wavelength prediction models and a performance prediction method for organic laser materials, in order to solve the problems that related technologies are usually time-consuming and costly in finding organic laser molecules with low amplification spontaneous emission thresholds, and it is difficult to quickly and effectively screen out suitable molecules.

[0004] The first aspect of this application provides a method for training an ASE threshold and wavelength prediction model, comprising the following steps: acquiring the molecular structure and photophysical parameters of multiple reference organic laser materials; identifying the amplified spontaneous emission (ASE) threshold and wavelength in the photophysical parameters; generating a dataset based on the molecular structure and ASE threshold and wavelength of the reference organic laser materials; constructing a prediction model for the ASE threshold and wavelength based on a machine learning algorithm; training the prediction model using the dataset; and predicting the ASE threshold and wavelength of the target organic laser material based on the trained prediction model.

[0005] Optionally, a dataset is generated based on the molecular structure and ASE threshold and wavelength of the reference organic laser material, including: generating corresponding samples based on the molecular structure and ASE threshold and wavelength of each reference organic laser material; and generating a dataset based on the corresponding samples of each reference organic laser material.

[0006] Optionally, training a prediction model using a dataset includes: dividing the dataset into a training set and a test set; training the prediction model using the training set, testing the prediction performance of the prediction model using the test set, and iteratively updating the model parameters of the prediction model during the training process; and stopping the training of the prediction model if a preset stopping condition is met.

[0007] Optionally, the preset stopping conditions include: the number of training iterations reaches the target number, or the prediction performance of the prediction model reaches the target performance.

[0008] Optionally, the machine learning algorithm includes at least one of the eXtreme Gradient Boosting model and the Gradient Boosting model.

[0009] A second aspect of this application provides a method for predicting the performance of an organic laser material, comprising: obtaining the molecular structure of a target organic laser material; inputting the molecular structure into a prediction model for ASE threshold and wavelength, the prediction model outputting the ASE threshold and wavelength of the target organic laser material, wherein the prediction model is trained based on the ASE threshold and wavelength prediction model training method of the first aspect; and predicting the optical performance of the target organic laser material based on the ASE threshold and wavelength.

[0010] Optionally, the target organic laser material is the material of an electrically pumped organic laser.

[0011] A third aspect of this application provides an ASE threshold and wavelength prediction model training device, comprising: a first acquisition module for acquiring the molecular structure and photophysical parameters of multiple reference organic laser materials; an identification module for identifying the amplified spontaneous emission (ASE) threshold and wavelength among the photophysical parameters; a generation module for generating a dataset based on the molecular structure and ASE threshold and wavelength of the reference organic laser materials; and a first prediction module for constructing an ASE threshold and wavelength prediction model based on a machine learning algorithm, training the prediction model using the dataset, and predicting the ASE threshold and wavelength of a target organic laser material based on the trained prediction model.

[0012] A fourth aspect of this application provides a performance prediction device for organic laser materials, comprising: a second acquisition module for acquiring the molecular structure of a target organic laser material; an input module for inputting the molecular structure into a prediction model of ASE threshold and wavelength, wherein the prediction model outputs the ASE threshold and wavelength of the target organic laser material, and the prediction model is trained based on the ASE threshold and wavelength prediction model training method of the first aspect; and a second prediction module for predicting the optical performance of the target organic laser material based on the ASE threshold and wavelength.

[0013] A fifth aspect of this application provides an electronic device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor. The processor executes the program to implement the ASE threshold and wavelength prediction model training method of the first aspect and the performance prediction method of organic laser materials of the second aspect.

[0014] A sixth aspect of this application provides a computer-readable storage medium storing a computer program or instructions thereon, which, when executed, implement the ASE threshold and wavelength prediction model training method of the first aspect and the performance prediction method of organic laser materials of the second aspect.

[0015] Therefore, this application has the following beneficial effects:

[0016] This application's embodiments can acquire the molecular structure and photophysical parameters of multiple reference organic laser materials, identify the amplified spontaneous emission (ASE) threshold and wavelength, generate a dataset based on the molecular structure, ASE threshold, and wavelength of the reference organic laser materials, train a prediction model for ASE threshold and wavelength based on a machine learning algorithm using the dataset, and use the trained prediction model to predict the ASE threshold and wavelength of the target organic laser material. This allows for rapid screening of candidate molecules by predicting the amplified spontaneous emission threshold and wavelength of organic molecules. Therefore, it solves the problems of time-consuming and costly methods in finding organic laser molecules with low amplified spontaneous emission thresholds, making it difficult to quickly and effectively screen suitable molecules.

[0017] Additional aspects and advantages of this application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of this application. Attached Figure Description

[0018] The above and / or additional aspects and advantages of this application will become apparent and readily understood from the following description of the embodiments taken in conjunction with the accompanying drawings, wherein:

[0019] Figure 1 This is a flowchart of an ASE threshold and wavelength prediction model training method provided according to an embodiment of this application;

[0020] Figure 2 This is a flowchart illustrating a method for predicting the performance of organic laser materials according to an embodiment of this application;

[0021] Figure 3 A schematic diagram of model construction provided for one embodiment of this application;

[0022] Figure 4 This is an example diagram of an ASE threshold and wavelength prediction model training device according to an embodiment of this application;

[0023] Figure 5 This is an example diagram of a performance prediction device for organic laser materials according to an embodiment of this application;

[0024] Figure 6 This is a schematic diagram of the structure of an electronic device provided according to an embodiment of this application. Detailed Implementation

[0025] The embodiments of this application are described in detail below. Examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain this application, and should not be construed as limiting this application.

[0026] The following describes, with reference to the accompanying drawings, an ASE threshold and wavelength prediction model training method and a performance prediction method for organic laser materials according to embodiments of this application. Addressing the problems mentioned in the background art, such as the time-consuming and costly nature of related technologies in finding organic laser molecules with low amplification spontaneous emission thresholds (ASE), and the difficulty in quickly and effectively screening suitable molecules, this application provides an ASE threshold and wavelength prediction model training method. In this method, the molecular structure and photophysical parameters of multiple reference organic laser materials can be obtained, and the amplification spontaneous emission (ASE) threshold and wavelength can be identified. A dataset is generated based on the molecular structure and ASE threshold and wavelength of the reference organic laser materials. The dataset is used to train an ASE threshold and wavelength prediction model constructed based on a machine learning algorithm. The trained prediction model is then used to predict the ASE threshold and wavelength of the target organic laser material, thereby achieving rapid screening of candidate molecules by predicting the amplification spontaneous emission threshold and wavelength of organic molecules. This solves the problems of the time-consuming and costly nature of related technologies in finding organic laser molecules with low amplification spontaneous emission thresholds, and the difficulty in quickly and effectively screening suitable molecules.

[0027] Specifically, Figure 1 This is a flowchart illustrating an ASE threshold and wavelength prediction model training method provided in an embodiment of this application.

[0028] like Figure 1 As shown, the training method for the ASE threshold and wavelength prediction model includes the following steps:

[0029] In step S101, the molecular structure and photophysical parameters of multiple reference organic laser materials are obtained.

[0030] The molecular structure and photophysical parameters of the reference organic laser material were collected from existing literature, and the molecular structure of the reference organic laser material was described using electrical topological state fingerprints and cheminformatics descriptors. Electrical topological state fingerprints are descriptors used to quantify the electronic environment of each atom in the molecule, while cheminformatics descriptors are a series of numerical representations used to quantify molecular structural characteristics, describing various molecular properties, including size, shape, charge distribution, and hydrophobicity.

[0031] It is understood that the embodiments of this application obtain a large number of molecular structures and photophysical parameters of reference organic laser materials by consulting existing literature, and use electrical topological state fingerprints and cheminformatics descriptors to describe the molecular structure of the reference organic laser materials.

[0032] In step S102, the amplified spontaneous emission (ASE) threshold and wavelength in the photophysical parameters are identified.

[0033] The ASE threshold refers to the minimum pump power or excitation density required to achieve a significant ASE signal.

[0034] It is understood that, in this application, after obtaining a large number of reference organic laser material molecules' photophysical parameters by consulting existing literature, the amplified spontaneous emission (ASE) threshold and wavelength are identified from the photophysical parameters.

[0035] In step S103, a dataset is generated based on the molecular structure of the reference organic laser material and the ASE threshold and wavelength.

[0036] It is understood that, in the embodiments of this application, the molecular structure, ASE threshold and wavelength of the reference organic laser material described by the electrical topological state fingerprint and cheminformatics descriptor will be integrated to generate a dataset for training the prediction model.

[0037] In this embodiment of the application, a dataset is generated based on the molecular structure and ASE threshold and wavelength of a reference organic laser material, including: generating a corresponding sample based on the molecular structure and ASE threshold and wavelength of each reference organic laser material; and generating a dataset based on the corresponding sample of each reference organic laser material.

[0038] The corresponding sample is generated by integrating the molecular structure of the reference organic laser material described using electrical topological state fingerprints and cheminformatics descriptors with the amplified spontaneous emission (ASE) threshold and wavelength.

[0039] It is understood that, in the embodiments of this application, corresponding samples are generated by integrating the molecular structure and ASE threshold of the reference organic laser material with the wavelength, and then the corresponding samples of each reference organic laser material are integrated to generate a dataset.

[0040] In step S104, a prediction model for ASE threshold and wavelength is constructed based on a machine learning algorithm. The prediction model is trained using a dataset. Based on the trained prediction model, the ASE threshold and wavelength of the target organic laser material are predicted.

[0041] The machine learning algorithms include many models, such as Linear Regression, RandomForest Regression, Xgboost (eXtreme Gradient Boosting), and GBoost (Gradient Boosting Trees). This application selects the Xgboost and GBoost models to achieve prediction, which will be described in detail below and will not be repeated here.

[0042] It is understood that the embodiments of this application are based on machine learning algorithms, selecting the Xgboost model and the GBoost model to construct a prediction model for ASE threshold and wavelength, using the dataset generated above to train the model, and using the trained prediction model for ASE threshold and wavelength to predict the ASE threshold and wavelength of the target organic laser material.

[0043] In this embodiment of the application, training a prediction model using a dataset includes: dividing the dataset into a training set and a test set; training the prediction model using the training set, testing the prediction performance of the prediction model using the test set, and iteratively updating the model parameters of the prediction model during the training process; and stopping the training of the prediction model if a preset stopping condition is met.

[0044] It is understood that the dataset in this embodiment is divided into two parts: a training set and a test set. For example, 70% may be allocated to the training set and 30% to the test set. The specific division can be set and is not limited in any particular way. The training set is used to train the prediction model for ASE threshold and wavelength, and the test set is used to test the prediction performance of the prediction model. During the training of the prediction model for ASE threshold and wavelength, the model parameters of the prediction model are continuously updated iteratively until the model parameters meet the preset stopping condition and the training of the prediction model is stopped.

[0045] In this embodiment of the application, the preset stopping conditions include: the number of iterations for training reaches the target number, or the prediction performance of the prediction model reaches the target performance.

[0046] The target number of training iterations is the maximum number of training iterations that can be achieved based on actual needs. Once this number is reached, training of the prediction model will stop. No specific limit is set here. The target performance is the performance of the prediction model required to meet the preset requirements. This is set based on actual needs and is not specifically limited here.

[0047] It is understood that the preset stopping conditions in the embodiments of this application may include reaching the target number of iterations and reaching the target performance of the prediction model. As long as either the target number of iterations or the target performance of the prediction model is met during the training of the prediction model for the ASE threshold and wavelength, the training of the prediction model can be stopped.

[0048] In the embodiments of this application, the machine learning algorithm includes at least one of the eXtreme Gradient Boosting model and the Gradient Boosting model.

[0049] Specifically, the XGBoost model is used to predict the ASE threshold, and the GBoost model is used to predict the ASE wavelength.

[0050] It is understood that the machine learning algorithms selected in the embodiments of this application include the XGBoost model and the GBoost model. The XGBoost model is used to predict the ASE threshold, and the GBoost model is used to predict the ASE wavelength.

[0051] According to the ASE threshold and wavelength prediction model training method proposed in the embodiments of this application, the molecular structure and photophysical parameters of multiple reference organic laser materials can be obtained, the amplified spontaneous emission ASE threshold and wavelength can be identified, a dataset can be generated from the molecular structure and ASE threshold and wavelength of the reference organic laser materials, the ASE threshold and wavelength prediction model based on machine learning algorithm can be trained using the dataset, and the trained prediction model can be used to predict the ASE threshold and wavelength of the target organic laser material, thereby achieving rapid screening of candidate molecules by predicting the amplified spontaneous emission threshold and wavelength of organic molecules.

[0052] Next, with reference to the accompanying drawings, a method for predicting the performance of organic laser materials according to embodiments of this application is described.

[0053] Figure 2 This is a flowchart illustrating the performance prediction method for organic laser materials according to an embodiment of this application.

[0054] like Figure 2 As shown, the method for predicting the performance of this organic laser material includes the following steps:

[0055] In step S201, the molecular structure of the target organic laser material is obtained.

[0056] The molecular structure of the target organic laser material is sought from untested molecular structures.

[0057] It is understood that the molecular structure of the target organic laser material is obtained from a database that has never been tested.

[0058] In this embodiment, the target organic laser material is the material of an electrically pumped organic laser.

[0059] It is understood that the embodiments of this application do not obtain materials suitable for use as electrically pumped organic lasers from an untested database as target organic laser materials.

[0060] In step S202, the molecular structure is input into the prediction model of ASE threshold and wavelength, and the prediction model outputs the ASE threshold and wavelength of the target organic laser material. The prediction model is trained based on the above-mentioned ASE threshold and wavelength prediction model training method.

[0061] It is understood that after obtaining the molecular structure of the target organic laser material in this embodiment of the application, it is input into the ASE threshold and wavelength prediction model trained based on the above-mentioned ASE threshold and wavelength prediction model training method, and the ASE threshold and wavelength prediction model predicts and outputs the ASE threshold and wavelength of the target organic laser material.

[0062] In step S203, the optical properties of the target organic laser material are predicted based on the ASE threshold and wavelength.

[0063] It is understood that, in this embodiment of the application, the molecular structure of the target organic laser material is input into the prediction model of ASE threshold and wavelength. The prediction model predicts and outputs the ASE threshold and wavelength of the target organic laser material. By analyzing the ASE threshold and wavelength of the target organic laser material, it is determined whether the material is an organic laser molecule suitable for an electrically pumped laser, thereby screening out organic laser molecules suitable for an electrically pumped laser.

[0064] According to the performance prediction method for organic laser materials proposed in the embodiments of this application, the molecular structure of the target organic laser material can be obtained, and the molecular structure can be input into the prediction model of ASE threshold and wavelength. The prediction model outputs the ASE threshold and wavelength of the target organic laser material. Finally, the optical performance of the target organic laser material can be predicted based on the ASE threshold and wavelength, which can effectively identify potential low-threshold organic laser molecules.

[0065] The following specific example further describes the ASE threshold and wavelength prediction model training method and the performance prediction method for organic laser materials. Figure 3 As shown:

[0066] This application collects a large amount of data on organic laser molecules and their corresponding amplified spontaneous emission thresholds and wavelengths from existing literature, and uses electrical topological state fingerprints and cheminformatics descriptors to describe the molecular structure. The data is then divided into a training set (70%) and a test set (30%) and input into the XGBoost model to predict the ASE threshold, and the GBoost model is used to predict the ASE wavelength.

[0067] After training, this embodiment of the application further applies the model to an untested database to predict the ASE threshold and wavelength of organic molecules, screening out organic laser molecules suitable for electrically pumped lasers. Theoretically, this model screened out six novel organic laser molecules, which exhibit good photophysical properties and show potential for future laser applications.

[0068] Figure 4 This is a block diagram of the ASE threshold and wavelength prediction model training device according to an embodiment of this application.

[0069] like Figure 4 As shown, the ASE threshold and wavelength prediction model training device 10 includes: a first acquisition module 301, an identification module 302, a generation module 303, and a first prediction module 304.

[0070] The first acquisition module 301 is used to acquire the molecular structure and photophysical parameters of multiple reference organic laser materials; the identification module 302 is used to identify the amplified spontaneous emission (ASE) threshold and wavelength in the photophysical parameters; the generation module 303 is used to generate a dataset based on the molecular structure and ASE threshold and wavelength of the reference organic laser materials; and the first prediction module 304 is used to construct a prediction model for the ASE threshold and wavelength based on a machine learning algorithm, train the prediction model using the dataset, and predict the ASE threshold and wavelength of the target organic laser material based on the trained prediction model.

[0071] In this embodiment, the generation module 303 is further configured to: generate corresponding samples based on the molecular structure and ASE threshold and wavelength of each reference organic laser material; and generate a dataset based on the corresponding samples of each reference organic laser material.

[0072] In this embodiment of the application, the first prediction module 304 is further configured to: divide the dataset into a training set and a test set; train the prediction model using the training set, test the prediction performance of the prediction model using the test set, and iteratively update the model parameters of the prediction model during the training process; and stop the training of the prediction model if a preset stopping condition is met.

[0073] In this embodiment of the application, the preset stopping conditions include: the number of iterations for training reaches the target number, or the prediction performance of the prediction model reaches the target performance.

[0074] In the embodiments of this application, the machine learning algorithm includes at least one of the eXtreme Gradient Boosting model and the Gradient Boosting model.

[0075] According to the ASE threshold and wavelength prediction model training device proposed in the embodiments of this application, through the synergistic effect of the first acquisition module, the identification module, the generation module and the first prediction module, the molecular structure and photophysical parameters of multiple reference organic laser materials can be acquired, the amplified spontaneous emission ASE threshold and wavelength among them can be identified, a dataset can be generated from the molecular structure and ASE threshold and wavelength of the reference organic laser materials, the ASE threshold and wavelength prediction model based on machine learning algorithm can be trained using the dataset, and the trained prediction model can be used to predict the ASE threshold and wavelength of the target organic laser material, thereby achieving rapid screening of candidate molecules by predicting the amplified spontaneous emission threshold and wavelength of organic molecules.

[0076] Figure 5 This is a block diagram of a performance prediction device for organic laser materials according to an embodiment of this application.

[0077] like Figure 5 As shown, the performance prediction device 20 for organic laser materials includes: a second acquisition module 401, an input module 402, and a second prediction module 403.

[0078] The second acquisition module 401 is used to acquire the molecular structure of the target organic laser material; the input module 402 is used to input the molecular structure into the prediction model of ASE threshold and wavelength, and the prediction model outputs the ASE threshold and wavelength of the target organic laser material, wherein the prediction model is trained based on the above-mentioned ASE threshold and wavelength prediction model training method; the second prediction module 403 is used to predict the optical performance of the target organic laser material according to the ASE threshold and wavelength.

[0079] In this embodiment, the target organic laser material is the material of an electrically pumped organic laser.

[0080] According to the performance prediction device for organic laser materials proposed in the embodiments of this application, the molecular structure of the target organic laser material can be obtained through the synergistic effect of the second acquisition module, the input module and the second prediction module. The molecular structure is then input into the prediction model of ASE threshold and wavelength. The prediction model outputs the ASE threshold and wavelength of the target organic laser material. Finally, the optical performance of the target organic laser material is predicted based on the ASE threshold and wavelength, which can effectively identify potential low-threshold organic laser molecules.

[0081] Figure 6A schematic diagram of the structure of an electronic device provided in an embodiment of this application. The electronic device may include:

[0082] The memory 501, the processor 502, and the computer program stored on the memory 501 and capable of running on the processor 502.

[0083] When the processor 502 executes the program, it implements the ASE threshold and wavelength prediction model training method and the organic laser material performance prediction method provided in the above embodiments.

[0084] Furthermore, the electronic device also includes:

[0085] Communication interface 503 is used for communication between memory 501 and processor 502.

[0086] The memory 501 is used to store computer programs that can run on the processor 502.

[0087] The memory 501 may include high-speed RAM (Random Access Memory) memory, and may also include non-volatile memory, such as at least one disk storage.

[0088] If the memory 501, processor 502, and communication interface 503 are implemented independently, then the communication interface 503, memory 501, and processor 502 can be interconnected via a bus to complete communication between them. The bus can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus, or an EISA (Extended Industry Standard Architecture) bus, etc. The bus can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 6 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0089] Optionally, in a specific implementation, if the memory 501, processor 502, and communication interface 503 are integrated on a single chip, then the memory 501, processor 502, and communication interface 503 can communicate with each other through an internal interface.

[0090] Processor 502 may be a CPU (Central Processing Unit), an ASIC (Application Specific Integrated Circuit), or one or more integrated circuits configured to implement embodiments of this application.

[0091] This application also provides a computer-readable storage medium storing a computer program or instructions thereon, which, when executed, implements the above-described ASE threshold and wavelength prediction model training method and the above-described organic laser material performance prediction method.

[0092] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0093] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this application, "N" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0094] Any process or method described in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or N executable instructions for implementing custom logic functions or processes, and the scope of the preferred embodiments of this application includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as should be understood by those skilled in the art to which embodiments of this application pertain.

[0095] It should be understood that various parts of this application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any of the following techniques known in the art, or a combination thereof: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (FPGAs), field-programmable gate arrays (FPGAs), etc.

[0096] Those skilled in the art will understand that all or part of the steps of the methods implementing the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, the program includes one or a combination of the steps of the method embodiments.

[0097] Although embodiments of this application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting this application. Those skilled in the art can make changes, modifications, substitutions and variations to the above embodiments within the scope of this application.

Claims

1. A training method for an ASE threshold and wavelength prediction model, characterized in that, Includes the following steps: Obtain the molecular structure and photophysical parameters of multiple reference organic laser materials; Identify the amplified spontaneous emission (ASE) threshold and wavelength in the aforementioned photophysical parameters; A dataset is generated based on the molecular structure of the reference organic laser material and the ASE threshold and wavelength; A prediction model for ASE threshold and wavelength is constructed based on machine learning algorithms. The prediction model is trained using the dataset. Based on the trained prediction model, the ASE threshold and wavelength of the target organic laser material are predicted.

2. The ASE threshold and wavelength prediction model training method according to claim 1, characterized in that, The process of generating a dataset based on the molecular structure and ASE threshold and wavelength of the reference organic laser material includes: Generate corresponding samples based on the molecular structure, ASE threshold, and wavelength of each reference organic laser material; The dataset is generated based on the corresponding sample of each reference organic laser material.

3. The ASE threshold and wavelength prediction model training method according to claim 1, characterized in that, Training the prediction model using the dataset includes: The dataset is divided into a training set and a test set; The prediction model is trained using the training set, and its prediction performance is tested using the test set. The model parameters of the prediction model are iteratively updated during the training process. Training of the prediction model will stop if the preset stopping conditions are met.

4. The ASE threshold and wavelength prediction model training method according to claim 3, characterized in that, The preset stopping conditions include: the number of iterations for training reaches the target number, or the prediction performance of the prediction model reaches the target performance.

5. The ASE threshold and wavelength prediction model training method according to claim 1, characterized in that, The machine learning algorithm includes at least one of the eXtreme Gradient Boosting model and the Gradient Boosting model.

6. A method for predicting the performance of organic laser materials, characterized in that, Includes the following steps: To obtain the molecular structure of the target organic laser material; The molecular structure is input into the prediction model of ASE threshold and wavelength, and the prediction model outputs the ASE threshold and wavelength of the target organic laser material. The prediction model is trained based on the ASE threshold and wavelength prediction model training method according to any one of claims 1-5. The optical properties of the target organic laser material are predicted based on the ASE threshold and wavelength.

7. The method for predicting the performance of organic laser materials according to claim 6, characterized in that, The target organic laser material is the material used in electrically pumped organic lasers.

8. A training device for an ASE threshold and wavelength prediction model, characterized in that, include: The first acquisition module is used to acquire the molecular structure and photophysical parameters of multiple reference organic laser materials; The identification module is used to identify the amplified spontaneous emission (ASE) threshold and wavelength in the photophysical parameters. The generation module is used to generate a dataset based on the molecular structure and ASE threshold and wavelength of the reference organic laser material; The first prediction module is used to construct a prediction model for ASE threshold and wavelength based on machine learning algorithms, train the prediction model using the dataset, and predict the ASE threshold and wavelength of the target organic laser material based on the trained prediction model.

9. A performance prediction device for organic laser materials, characterized in that, include: The second acquisition module is used to acquire the molecular structure of the target organic laser material; An input module is used to input the molecular structure into a prediction model for ASE threshold and wavelength, wherein the prediction model outputs the ASE threshold and wavelength of the target organic laser material, and the prediction model is trained based on the ASE threshold and wavelength prediction model training method according to any one of claims 1-5; The second prediction module is used to predict the optical properties of the target organic laser material based on the ASE threshold and wavelength.

10. An electronic device, characterized in that, include: The memory, the processor, and the computer program stored in the memory and executable on the processor, the processor executing the program to implement the ASE threshold and wavelength prediction model training method according to any one of claims 1-5, or the performance prediction method for organic laser materials according to any one of claims 6-7.

Images