A method and device for drawing a MAB synthesis probability graph, equipment and medium

Abstract

The application discloses a MAB synthesis probability mapping method and device, equipment and medium, relates to the field of material big data, and comprises the following steps: obtaining an original data set of a MAB material, dividing the original data set to obtain a training set and a test set; determining model training feature data from the training set, training and testing a preset machine learning model by using the model training feature data and the test set to obtain a target machine learning model, and performing prediction calculation on the test set by using the target machine learning model to obtain a crystal synthesis prediction score; and mapping a MAB synthesis probability graph based on the crystal synthesis prediction score and the model training feature data. Through the above technical scheme of the application, the complexity of MAB material synthesis analysis can be reduced, the accuracy of MAB material synthesis feasibility analysis can be increased, the cost can be reduced, the efficiency of MAB material synthesis feasibility analysis can be improved, and support can be provided for MAB material synthesis design and optimization.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of material big data, and particularly relates to a MAB synthesis probability graph drawing method, device, equipment and medium. BACKGROUND

[0002] MAB phase (MBene, ternary layered transition metal boride) is a new ternary layered transition metal boride after the birth of MAX phase (ternary layered transition metal nitride / carbide / carbonitride), so the traditional MAX phase family has been expanded from carbide to nitride and boride. MAB is a new type of layered material formed by A elements, transition metal elements M and boron elements, which has a similar layered structure to MXene (two-dimensional layered metal carbon / nitride), but boron atoms have smaller atomic radius and higher electronegativity, so the electrical properties and chemical stability of MAB phase three-dimensional bulk material may be better. In addition, the material also has excellent thermal conductivity and mechanical properties, so it has wide application prospects in the fields of energy, catalysts, sensors, etc. The traditional synthesis feasibility analysis method is mainly based on experience and domain knowledge, which is difficult to cope with large-scale and complex material space.

[0003] How to reduce the complexity of MAB material synthesis analysis, increase the accuracy of MAB material synthesis feasibility analysis, reduce the cost, improve the efficiency of MAB material synthesis feasibility analysis, and provide support for MAB material synthesis design and optimization is a problem to be solved in the field. SUMMARY

[0004] Therefore, the purpose of the present application is to provide a MAB synthesis probability graph drawing method, device, equipment and medium, which can reduce the complexity of MAB material synthesis analysis, increase the accuracy of MAB material synthesis feasibility analysis, reduce the cost, improve the efficiency of MAB material synthesis feasibility analysis, and provide support for MAB material synthesis design and optimization. The specific scheme is as follows:

[0005] In a first aspect, the present application discloses a MAB synthesis probability graph drawing method, comprising:

[0006] Obtaining an original data set of MAB material, dividing the original data set to obtain a training set and a test set;

[0007] Determining model training feature data from the training set, training and testing a preset machine learning model using the model training feature data and the test set to obtain a target machine learning model, and performing prediction calculation on the test set using the target machine learning model to obtain a crystal synthesis prediction score;

[0008] draw a MAB synthesis probability graph based on the crystal synthesis prediction score and the model training feature data.

[0009] Optionally, the original data set of the MAB material is obtained, and the original data set is divided to obtain a training set and a test set, comprising:

[0010] An original data set of a MAB material is obtained; the original data set includes band structure data and charge density data of the MAB material;

[0011] The original data set is divided according to a preset data set division ratio to obtain the training set and the test set.

[0012] Optionally, before the training and testing of the preset machine learning model using the model training feature data and the test set, the method further comprises:

[0013] Parameter information of the MAB material is obtained;

[0014] The parameter information is input into a preset initial machine learning model to obtain the machine learning model.

[0015] Optionally, the parameter information includes chemical composition, structure and properties of the MAB material; and the machine learning model is a positive sample unlabeled learning model.

[0016] Optionally, the method of determining model training feature data from the training set, training and testing a preset machine learning model using the model training feature data and the test set to obtain a target machine learning model, comprises:

[0017] The model training feature data including feature formation energy, layer number, M atom charge, system mass and cohesive energy of the MAB material is determined from the training set;

[0018] The machine learning model is trained using the feature formation energy, the layer number, the M atom charge, the system mass and the cohesive energy to obtain a trained machine learning model;

[0019] The trained machine learning model is tested using the test set to obtain a target machine learning model.

[0020] Optionally, the method of drawing a MAB synthesis probability graph based on the crystal synthesis prediction score and the model training feature data, comprises:

[0021] It is judged whether the crystal synthesis prediction score is greater than a preset prediction score boundary value;

[0022] If the crystal synthesis prediction score is greater than the prediction score boundary value, then the MAB synthesis probability map is plotted based on the crystal synthesis prediction score, the characteristic formation energy, the M atom charge, and the prediction score boundary value.

[0023] Optionally, the horizontal coordinate of the MAB synthesis probability map is the characteristic formation energy, the vertical coordinate is the M atom charge, and the prediction score boundary value is presented in the form of a straight line.

[0024] In a second aspect, the present application discloses a MAB synthesis probability map plotting device, comprising:

[0025] A dividing module is configured to obtain an original data set of a MAB material, divide the original data set to obtain a training set and a test set;

[0026] A score determining module is configured to determine model training feature data from the training set, train and test a preset machine learning model by using the model training feature data and the test set to obtain a target machine learning model, and perform prediction calculation on the test set by using the target machine learning model to obtain a crystal synthesis prediction score;

[0027] A plotting module is configured to plot a MAB synthesis probability map based on the crystal synthesis prediction score and the model training feature data.

[0028] In a third aspect, the present application discloses an electronic device, comprising:

[0029] A memory is configured to save a computer program;

[0030] A processor is configured to execute the computer program to implement the MAB synthesis probability map plotting method.

[0031] In a fourth aspect, the present application discloses a computer storage medium configured to save a computer program; wherein the computer program is executed by a processor to implement the steps of the MAB synthesis probability map plotting method disclosed above.

[0032] It can be seen that the application provides a MAB synthesis probability mapping method, which comprises the following steps: obtaining an original data set of a MAB material, dividing the original data set to obtain a training set and a test set, determining model training feature data from the training set, training and testing a preset machine learning model by using the model training feature data and the test set to obtain a target machine learning model, performing prediction calculation on the test set by using the target machine learning model to obtain a crystal synthesis prediction score, and mapping a MAB synthesis probability graph based on the crystal synthesis prediction score and the model training feature data. The application trains and tests the preset machine learning model by using the model training feature data and the test set to obtain the target machine learning model, then performs prediction calculation on the test set to obtain the crystal synthesis prediction score, thereby reducing the complexity of MAB material synthesis analysis, finally mapping the MAB synthesis probability graph, which can increase the accuracy of MAB material synthesis feasibility analysis, reduce the cost, improve the efficiency of MAB material synthesis feasibility analysis, and solve the problems of low efficiency, high cost and long cycle in the prior art, thereby providing support for MAB material synthesis design and optimization. BRIEF DESCRIPTION OF DRAWINGS

[0033] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the drawings needed in the embodiments or the prior art description will be briefly introduced below. Obviously, the drawings in the following description are only embodiments of the present application, and those skilled in the art can obtain other drawings according to the provided drawings without creative labor.

[0034] Figure 1 A MAB synthesis probability mapping method disclosed by the present application is shown in the flow chart;

[0035] Figure 2 A specific MAB synthesis probability graph disclosed by the present application is shown in the flow chart;

[0036] Figure 3 A MAB synthesis probability mapping method disclosed by the present application is shown in the flow chart;

[0037] Figure 4 A MAB synthesis probability mapping device structure disclosed by the present application is shown in the schematic diagram;

[0038] Figure 5 An electronic device structure provided by the present application is shown in the schematic diagram. DETAILED DESCRIPTION

[0039] With reference to the drawings of the embodiments of the present application, the technical solutions in the embodiments of the present application will be described clearly and completely. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments of the present application, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the scope of the present application.

[0040] MAB phase is a new ternary layered transition metal boride born after MAX phase, so the traditional MAX phase family has been expanded from carbide, nitride to boride. MAB is a new type of layered material formed by A elements, transition metal elements M and boron elements, which has a similar layered structure to MXene. However, boron atoms have smaller atomic radius and higher electronegativity, so the electrical properties and chemical stability of MAB phase three-dimensional bulk materials may be better. In addition, the material also has excellent thermal conductivity and mechanical properties, so it has wide application prospects in the fields of energy, catalysts, sensors, etc. The traditional synthesis feasibility analysis method is mainly based on experience and domain knowledge, which is difficult to cope with large-scale and complex material space. How to reduce the complexity of MAB material synthesis analysis, increase the accuracy of MAB material synthesis feasibility analysis, reduce the cost, improve the efficiency of MAB material synthesis feasibility analysis, and provide support for MAB material synthesis design and optimization is a problem to be solved in the field.

[0041] Referring to Figure 1 As shown in the drawings, the embodiment of the present application discloses a MAB synthesis probability mapping method, which can specifically include:

[0042] Step S11: Obtain the original data set of the MAB material, divide the original data set to obtain the training set and the test set.

[0043] Step S12: Determine the model training feature data from the training set, use the model training feature data and the test set to train and test the preset machine learning model to obtain the target machine learning model, and use the target machine learning model to predict and calculate the test set to obtain the crystal synthesis prediction score.

[0044] In the embodiment, the model training feature data including the formation energy, the number of layers, the M atom charge, the system mass and the cohesive energy of the MAB material is determined from the training set; the machine learning model is trained by using the formation energy, the number of layers, the M atom charge, the system mass and the cohesive energy to obtain the trained machine learning model; and the trained machine learning model is tested by using the test set to obtain the target machine learning model. The machine learning model is a PUlearning (Positive Unlabeled learning) model.

[0045] Specifically, the model training feature data including the formation energy, the number of layers, the M atom charge, the system mass and the cohesive energy of the MAB material is determined from the training set, the five features are taken as inputs to train the machine learning model to obtain the trained machine learning model, and the trained machine learning model is tested by using the test set to obtain the target machine learning model.

[0046] Step S13: drawing the MAB synthesis probability graph based on the crystal synthesis prediction score and the model training feature data.

[0047] In the embodiment, it is determined whether the crystal synthesis prediction score is greater than a preset prediction score boundary value; if the crystal synthesis prediction score is greater than the prediction score boundary value, the MAB synthesis probability graph is drawn based on the crystal synthesis prediction score, the formation energy, the M atom charge and the prediction score boundary value.

[0048] The horizontal coordinate of the MAB synthesis probability graph of the present application is the formation energy, the vertical coordinate is the M atom charge, and the prediction score boundary value is in the form of a straight line.

[0049] Specifically, the test set is predicted and calculated by using the target machine learning model, the original data set is abstractly represented by randomly distributed positive data and unlabeled data, in each iteration of the PU (Positive-unlabeled, positive sample and unlabeled) learning process, some unlabeled samples are randomly labeled as negative values, by constructing a PU learning binary classification model, the remaining unlabeled data is predicted, if the unlabeled sample is likely to be a positive sample (synthesizable), the classifier prediction classification output is close to 1, the iteration process is repeated, the final score is obtained by averaging the prediction scores of the classifier trained on the sub-sample excluding the sample, that is, the crystal synthesis prediction score is obtained, the crystal synthesis prediction score is used to evaluate the synthesis ability of the MAB phase material which has not been synthesized, taking the crystal synthesis prediction score boundary value = 0.5 as an example, if the crystal synthesis prediction score > 0.5, it is predicted that it can be synthesized, if the crystal synthesis prediction score < 0.5, it is predicted that the synthesis rate is low, so that the MAB material with synthesis potential is distinguished from the known positive material sample and the unlabeled material sample, the MAB synthesis probability graph is drawn based on the crystal synthesis prediction score and the model training feature data, and the specific MAB synthesis probability graph is as shown in Figure 2

[0050] In the embodiment, the original data set of the MAB material is obtained, the original data set is divided to obtain a training set and a test set; the model training feature data is determined from the training set, the preset machine learning model is trained and tested by using the model training feature data and the test set to obtain a target machine learning model, the test set is predicted and calculated by using the target machine learning model to obtain a crystal synthesis prediction score; and the MAB synthesis probability graph is drawn based on the crystal synthesis prediction score and the model training feature data. The model training feature data and the test set are used to train and test the preset machine learning model to obtain the target machine learning model, then the test set is predicted and calculated to obtain the crystal synthesis prediction score, so as to reduce the complexity of the MAB material synthesis analysis, finally the MAB synthesis probability graph is drawn, the accuracy of the MAB material synthesis feasibility analysis can be increased, the cost can be reduced, the efficiency of the MAB material synthesis feasibility analysis can be improved, and the problems of low efficiency, high cost and long cycle in the prior art are solved, thereby providing support for MAB material synthesis design and optimization.

[0051] Referring to Figure 3 The embodiment of the application discloses a MAB synthesis probability graph drawing method, which can specifically include:

[0052] ​Step S21: Obtain an original data set of the MAB material, and divide the original data set according to a preset data set division ratio to obtain the training set and the test set; the original data set includes band structure data and charge density data of the MAB material.

[0053] In this embodiment, the original data set of the MAB material is obtained, including the band structure data and the charge density data of the MAB material, and the collected original data set is divided into a training set and a test set according to a set data set division ratio, wherein the data set division ratio includes but is not limited to 5:1.

[0054] Step S22: Determine model training feature data from the training set, obtain parameter information of the MAB material, and input the parameter information into a preset initial machine learning model to obtain the machine learning model.

[0055] In this embodiment, the parameter information includes the chemical composition, structure and properties of the MAB material; and the machine learning model is a positive sample unlabeled learning model.

[0056] Step S23: Train and test the machine learning model using the model training feature data and the test set to obtain a target machine learning model, and perform prediction calculation on the test set using the target machine learning model to obtain a crystal synthesis prediction score.

[0057] Step S24: Draw a MAB synthesis probability graph based on the crystal synthesis prediction score and the model training feature data.

[0058] In this embodiment, an original data set of the MAB material is obtained, and the original data set is divided to obtain a training set and a test set; model training feature data is determined from the training set, the preset machine learning model is trained and tested using the model training feature data and the test set to obtain a target machine learning model, and prediction calculation is performed on the test set using the target machine learning model to obtain a crystal synthesis prediction score; and a MAB synthesis probability graph is drawn based on the crystal synthesis prediction score and the model training feature data. The model training feature data and the test set are used to train and test the preset machine learning model to obtain a target machine learning model, and then prediction calculation is performed on the test set to obtain a crystal synthesis prediction score, thereby reducing the complexity of MAB material synthesis analysis, ultimately drawing a MAB synthesis probability graph, which can increase the accuracy of MAB material synthesis feasibility analysis, reduce costs, improve the efficiency of MAB material synthesis feasibility analysis, and solve the problems of low efficiency, high cost and long cycle in the prior art, thereby providing support for MAB material synthesis design and optimization.

[0059] Referring toFigure 4 As shown, the embodiment of the present application discloses a MAB synthesis probability mapping device, which can specifically include:

[0060] The division module 11 is configured to obtain an original data set of a MAB material, divide the original data set to obtain a training set and a test set;

[0061] The score determination module 12 is configured to determine model training feature data from the training set, perform training test on a preset machine learning model by using the model training feature data and the test set to obtain a target machine learning model, and perform prediction calculation on the test set by using the target machine learning model to obtain a crystal synthesis prediction score;

[0062] The mapping module 13 is configured to map a MAB synthesis probability graph based on the crystal synthesis prediction score and the model training feature data.

[0063] In the embodiment, an original data set of a MAB material is obtained, the original data set is divided to obtain a training set and a test set, model training feature data is determined from the training set, a preset machine learning model is trained and tested by using the model training feature data and the test set to obtain a target machine learning model, prediction calculation is performed on the test set by using the target machine learning model to obtain a crystal synthesis prediction score, and a MAB synthesis probability graph is mapped based on the crystal synthesis prediction score and the model training feature data. The preset machine learning model is trained and tested by using the model training feature data and the test set to obtain a target machine learning model, prediction calculation is performed on the test set to obtain a crystal synthesis prediction score, the complexity of MAB material synthesis analysis is reduced, a MAB synthesis probability graph is finally mapped, the accuracy of MAB material synthesis feasibility analysis can be increased, the cost is reduced, the efficiency of MAB material synthesis feasibility analysis is improved, the problems of low efficiency, high cost and long cycle in the prior art are solved, and support is provided for MAB material synthesis design and optimization.

[0064] In some specific embodiments, the division module 11 can specifically include:

[0065] The data set acquisition module is configured to obtain an original data set of a MAB material; the original data set includes energy band structure data and charge density data of the MAB material;

[0066] The data set division module is configured to divide the original data set according to a preset data set division ratio to obtain the training set and the test set.

[0067] In some specific embodiments, the score determination module 12 can specifically include:

[0068] a parameter information acquisition module configured to acquire parameter information of the MAB material;

[0069] a parameter information input module configured to input the parameter information into a preset initial machine learning model to obtain the machine learning model.

[0070] In some specific embodiments, the parameter information includes chemical composition, structure and properties of the MAB material; and the machine learning model is a positive sample unlabeled learning model.

[0071] In some specific embodiments, the score determination module 12 specifically can include:

[0072] a data determination module configured to determine, from the training set, the model training feature data including formation energy of features of the MAB material, number of layers, M atom charge, system mass and cohesive energy;

[0073] a training module configured to train the machine learning model by using the formation energy of features, the number of layers, the M atom charge, the system mass and the cohesive energy to obtain the trained machine learning model;

[0074] a testing module configured to test the trained machine learning model by using the test set to obtain a target machine learning model.

[0075] In some specific embodiments, the drawing module 13 specifically can include:

[0076] a judgment module configured to judge whether the crystal synthesis prediction score is greater than a preset prediction score boundary value;

[0077] a drawing module configured to, if the crystal synthesis prediction score is greater than the prediction score boundary value, draw the MAB synthesis probability graph based on the crystal synthesis prediction score, the formation energy of features, the M atom charge and the prediction score boundary value.

[0078] In some specific embodiments, the horizontal coordinate of the MAB synthesis probability graph is the formation energy of features, the vertical coordinate is the M atom charge, and the prediction score boundary value is in the form of a straight line.

[0079] Figure 5A structural schematic diagram of an electronic device is provided in the embodiments of the present application. The electronic device 20 can specifically include at least one processor 21, at least one memory 22, a power supply 23, a communication interface 24, an input / output interface 25, and a communication bus 26. The memory 22 is configured to store a computer program, and the processor 21 is configured to load and execute the computer program to implement the related steps in the MAB synthesis probability mapping method performed by the electronic device disclosed in any of the foregoing embodiments.

[0080] In the embodiments, the power supply 23 is configured to provide working voltage for each hardware device on the electronic device 20; the communication interface 24 is capable of creating a data transmission channel between the electronic device 20 and external devices, and the communication protocol followed by the communication interface 24 can be any communication protocol applicable to the technical solutions of the present application, which is not specifically limited herein; the input / output interface 25 is configured to acquire external input data or output data to the outside, and the specific interface type can be selected according to specific application requirements, which is not specifically limited herein.

[0081] In addition, the memory 22 as a carrier for resource storage can be a read-only memory, a random access memory, a magnetic disk, or an optical disk, and the resources stored thereon include an operating system 221, a computer program 222, and data 223, etc., and the storage mode can be temporary storage or permanent storage.

[0082] The operating system 221 is configured to manage and control each hardware device on the electronic device 20 and the computer program 222, so as to implement the operation and processing of the processor 21 on the data 223 in the memory 22, and the operating system 221 can be Windows, Unix, Linux, etc. The computer program 222 can further include computer programs for completing other specific work in addition to the computer programs for completing the MAB synthesis probability mapping method performed by the electronic device 20 disclosed in any of the foregoing embodiments. The data 223 can include data transmitted by external devices and received by the MAB synthesis probability mapping device, and can also include data collected by the input / output interface 25, etc.

[0083] The steps of the methods or algorithms described in conjunction with the embodiments disclosed herein can be implemented directly by hardware, by a software module executed by a processor, or by a combination thereof. The software module can be placed in a random access memory (RAM), a memory, a read-only memory (ROM), an electrically programmable ROM, an electrically erasable programmable ROM, a register, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the technical field.

[0084] Further, the embodiment of the present application further discloses a computer readable storage medium, the storage medium stores a computer program, the computer program is loaded and executed by a processor, and the method steps of the MAB synthesis probability mapping method disclosed by any of the foregoing embodiments are realized.

[0085] Finally, it should be further noted that in this document, the relationship terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply that there is any such actual relationship or order between these entities or operations. Moreover, the terms "include", "contain" or any other variants thereof are intended to cover non-exclusive inclusion, so that the process, method, article or device including a series of elements not only includes those elements, but also includes other elements not explicitly listed or inherent to such process, method, article or device. Without more limitations, the element defined by the statement "including a" does not exclude the presence of other identical elements in the process, method, article or device including the element.

[0086] The above describes in detail the MAB synthesis probability mapping method, device, equipment and storage medium provided by the present application. The principles and implementation manners of the present application are described by applying specific examples in this document. The above embodiment is only used to help understand the method and core idea of the present application; meanwhile, for those skilled in the art, according to the idea of the present application, the specific implementation manner and application range will be changed; in conclusion, the content of the specification should not be understood as the limitation of the present application.

Claims

1. A method for MAB synthetic probability mapping, characterized in that, The method comprises the following steps: obtaining an original data set of MAB materials, and dividing the original data set to obtain a training set and a test set; determining model training feature data from the training set, training and testing a preset machine learning model by using the model training feature data and the test set, obtaining a target machine learning model, and performing prediction calculation on the test set by using the target machine learning model to obtain a crystal synthesis prediction score; drawing an MAB synthesis probability graph based on the crystal synthesis prediction score and the model training feature data; the step of obtaining an original data set of MAB materials and dividing the original data set to obtain a training set and a test set comprises the following steps: obtaining an original data set of MAB materials; the original data set comprises band structure data and charge density data of the MAB materials; and dividing the original data set according to a preset data set division ratio to obtain the training set and the test set; the step of determining model training feature data from the training set, training and testing a preset machine learning model by using the model training feature data and the test set, obtaining a target machine learning model, and performing prediction calculation on the test set by using the target machine learning model to obtain a crystal synthesis prediction score comprises the following steps: determining the model training feature data comprising feature formation energy, layer number, M atom charge, system mass and cohesive energy of the MAB materials from the training set; training the machine learning model by using the feature formation energy, the layer number, the M atom charge, the system mass and the cohesive energy to obtain a trained machine learning model; and testing the trained machine learning model by using the test set to obtain a target machine learning model; the machine learning model is a positive sample unlabeled learning model.

2. The MAB synthetic probability mapping method of claim 1, wherein, Before the step of training and testing a preset machine learning model by using the model training feature data and the test set, the method further comprises the following steps: obtaining parameter information of the MAB materials; inputting the parameter information into a preset initial machine learning model to obtain the machine learning model.

3. The MAB synthetic probability mapping method of claim 2, wherein, The parameter information comprises chemical composition, structure and properties of the MAB materials; and the machine learning model is a positive sample unlabeled learning model.

4. The MAB synthetic probability mapping method of claim 1, wherein, The step of drawing an MAB synthesis probability graph based on the crystal synthesis prediction score and the model training feature data comprises the following steps: determining whether the crystal synthesis prediction score is greater than a preset prediction score boundary value; if the crystal synthesis prediction score is greater than the prediction score boundary value, drawing the MAB synthesis probability graph based on the crystal synthesis prediction score, the feature formation energy, the M atom charge and the prediction score boundary value.

5. The MAB synthetic probability mapping method of claim 4, wherein, The horizontal coordinate of the MAB synthesis probability graph is the feature formation energy, the vertical coordinate is the M atom charge, and the prediction score boundary value is in the form of a straight line.

6. A MAB synthesis probability mapping device, characterized by, The method comprises the following steps: a division module is configured to obtain an original data set of MAB materials, and divide the original data set to obtain a training set and a test set; The score determination module is configured to determine model training feature data from the training set, perform training test on a preset machine learning model by using the model training feature data and the test set, obtain a target machine learning model, and perform prediction calculation on the test set by using the target machine learning model to obtain a crystal synthesis prediction score. The drawing module is configured to draw an MAB synthesis probability graph based on the crystal synthesis prediction score and the model training feature data. The method comprises the following steps: obtaining an original data set of MAB materials; dividing the original data set to obtain a training set and a test set; the original data set comprises band structure data and charge density data of the MAB materials; and the original data set is divided according to a preset data set division ratio to obtain the training set and the test set. The method comprises the following steps: determining the model training feature data comprising feature formation energy, layer number, M atom charge, system mass and cohesive energy of the MAB materials from the training set; training the machine learning model by using the feature formation energy, the layer number, the M atom charge, the system mass and the cohesive energy to obtain a trained machine learning model; testing the trained machine learning model by using the test set to obtain a target machine learning model; and the machine learning model is a positive sample unlabeled learning model.

7. An electronic device, comprising: The method comprises the following steps: A memory is configured to save a computer program. A processor is configured to execute the computer program to implement the MAB synthesis probability graph drawing method according to any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that, A memory is configured to save a computer program; wherein the computer program is executed by a processor to implement the MAB synthesis probability graph drawing method according to any one of claims 1 to 5.

Images