Material doping detection method, device, electronic equipment and storage medium

Abstract

The present application discloses a material doping detection method, device, electronic device and storage medium, which relates to the material doping technology field, including: obtaining the doping system information of the sample to be tested, the doping system information includes: main material information, doping material information and doping standard information, the main material information is the information related to the main material and doping, the doping material information is the information of the material doped into the main material, and the doping standard information refers to the information of the doping system formed after the doping is successful; obtaining the hyperspectral data of the sample to be tested after photoluminescence; based on the hyperspectral data and the doping system information, obtaining the material doping detection result of the sample to be tested. The technical solution of the present application aims to solve the technical problem of how to efficiently detect the result of material doping without damaging the sample.

Description

Technical Field

[0001] The present application relates to the technical field of material doping, and in particular to a material doping detection method, device, electronic equipment and storage medium. Background Art

[0002] Material doping is a technique that introduces impurity atoms into another material in order to change or enhance certain physical and chemical properties of the material in order to adapt it to different uses. Nowadays, X-ray diffraction, nuclear magnetic resonance and other technologies can be used to detect whether material doping is successful. However, such technologies are not only time-consuming, but also prone to damage to samples. Therefore, how to efficiently detect the results of material doping without damaging the sample is a technical problem that has yet to be solved by those skilled in the art. Summary of the invention

[0003] The present application proposes a material doping detection method, device, electronic device and storage medium, aiming to solve the technical problem of how to efficiently detect the results of material doping without damaging the sample.

[0004] To solve the above problems, the material doping detection method proposed in this application includes:

[0005] Obtaining doping system information of the sample to be tested, the doping system information including: main material information, doping material information and doping standard information, the main material information is information related to the main material and doping, the doping material information is information about the material doped into the main material, and the doping standard information refers to information about the doping system formed after successful doping;

[0006] Acquiring hyperspectral data of the sample to be tested after photoluminescence;

[0007] Based on the hyperspectral data and the doping system information, a material doping detection result of the sample to be tested is obtained.

[0008] In one embodiment, the step of obtaining the material doping detection result of the sample to be tested based on the hyperspectral data and the doping system information includes:

[0009] Acquire a first wavelength range of the main material information, a second wavelength range of the doping material information, and a third wavelength range of the doping standard information;

[0010] constructing a spectrum graph based on the hyperspectral data, and determining a first spectrum area within the first wavelength range, a second spectrum area within the second wavelength range, and a third spectrum area within the third wavelength range based on the spectrum graph;

[0011] The sum of the first spectral area, the second spectral area and the third spectral area is taken as the total area, and based on the first spectral area, the second spectral area and the total area, a material doping detection result of the sample to be tested is obtained.

[0012] In one embodiment, the material doping detection result includes undoped, successfully doped, and unsuccessfully doped; the step of obtaining the material doping detection result of the sample to be tested based on the first spectral area, the second spectral area, and the total area includes:

[0013] The sum of the first spectrum area and the second spectrum area is used as the invalid area, the ratio of the invalid area to the total area is used as the first ratio, the ratio of the first spectrum area to the invalid area is used as the second ratio, and the ratio of the second spectrum area to the invalid area is used as the third ratio;

[0014] When the first ratio is less than or equal to a first preset value, determining that the material doping detection result is successful doping;

[0015] When the first ratio is greater than the first preset value, and the second ratio is greater than the second preset value, determining that the material doping detection result is undoped;

[0016] When the first ratio is greater than the first preset value and the third ratio is greater than or equal to the second preset value, it is determined that the material doping detection result is unsuccessful doping.

[0017] In one embodiment, the step of obtaining the material doping detection result of the sample to be tested based on the hyperspectral data and the doping system information includes:

[0018] Determine a standard spectrum vector corresponding to the doping material information, and obtain a pixel spectrum vector corresponding to each pixel contained in the sample to be tested based on the hyperspectral data;

[0019] According to the angle parameter between each of the pixel spectrum vectors and the standard spectrum vector, the actual spectrum angle coordinates corresponding to each of the pixels are obtained;

[0020] Obtaining the ideal spectral angle coordinates corresponding to each of the pixels, and calculating the Euler distance between each of the ideal spectral angle coordinates and each of the actual spectral angle coordinates;

[0021] Each of the Euler distances is compared with a preset experimental ideal value to obtain a comparison result corresponding to each of the pixels, and a material doping detection result of the sample to be tested is obtained based on each of the comparison results.

[0022] In one embodiment, before the step of comparing each of the Euler distances with a preset experimental ideal value to obtain a comparison result corresponding to each of the pixels, the method further includes:

[0023] Obtaining a weight correction coefficient, wherein the weight correction coefficient is used to adjust the weight of each doping material in the area represented by the pixel;

[0024] Obtaining a new Euler distance according to the product of each of the Euler distances and the weight correction coefficient;

[0025] The step of comparing each of the Euler distances with a preset experimental ideal value to obtain a comparison result corresponding to each of the pixels comprises:

[0026] Each of the new Euler distances is compared with a preset experimental ideal value to obtain a comparison result corresponding to each of the pixels.

[0027] In one embodiment, the step of obtaining the material doping detection result of the sample to be tested based on the hyperspectral data and the doping system information includes:

[0028] Inputting the hyperspectral data into a target convolutional neural network model, wherein the target convolutional neural network model is trained based on the doping system information;

[0029] Obtain the material doping detection result of the sample to be tested output by the target convolutional neural network model.

[0030] In one embodiment, before the step of inputting the hyperspectral data into the target convolutional neural network model, the method further comprises:

[0031] Acquire sample hyperspectral data of the doping system information, and input the sample hyperspectral data into a convolutional neural network model to be trained to obtain a predicted material doping detection result output by the convolutional neural network model to be trained;

[0032] Calculating a loss value between the predicted material doping detection result and the actual doping result of the sample hyperspectral data;

[0033] The convolutional neural network model to be trained is iteratively optimized according to the loss value until the loss value converges to obtain a target convolutional neural network model.

[0034] In addition, the present application also proposes a material doping detection device, which is applied to the material doping detection method as described above, and the material doping detection device includes: an excitation light source, a light source coupling optical path, a hyperspectral camera, a detection coupling optical path, a semi-transparent and semi-reflective mirror, a microscope lens, a three-dimensional motion stage and a main control module, wherein a sample to be tested is placed on the three-dimensional motion stage, and the main control module is communicatively connected with the excitation light source and the hyperspectral camera;

[0035] The excitation light source emits laser light, which passes through the light source coupling optical path to reach the semi-transparent and semi-reflective mirror, is reflected by the semi-transparent and semi-reflective mirror to the microscope lens, and irradiates the sample to be tested, so that the sample to be tested is photoluminescent;

[0036] The light emitted by the sample to be tested reaches the semi-transparent and semi-reflective mirror through the microscope lens, reaches the hyperspectral camera through the semi-transparent and semi-reflective mirror and the detection coupling optical path, and is collected by the hyperspectral camera to obtain the hyperspectral data of the sample to be tested.

[0037] In addition, the present application also proposes an electronic device, which includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the material doping detection method as described above.

[0038] In addition, the present application also proposes a storage medium, which is a computer-readable storage medium. A computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the material doping detection method as described above are implemented.

[0039] In an embodiment of the present application, by obtaining the doping material information in the sample to be tested, the doping system information includes: main material information, doping material information and doping standard information, the main material information is the information related to the main material and doping, the doping material information is the information of the material doped into the main material, and the doping standard information refers to the information of the doping system formed after the doping is successful, and the hyperspectral data of the sample to be tested is obtained by a hyperspectral camera. The spectral information in the sample to be tested can be efficiently obtained by hyperspectral imaging technology without damaging the sample to be tested; then, based on the hyperspectral data and the doping material information, the material doping detection result of the sample to be tested is obtained, and the doping material in the sample to be tested can be identified based on the rich information in the hyperspectral data and the characteristics of the doping material represented by the doping material information, and then the material doping situation of the sample to be tested can be determined.

[0040] It can be seen that the method of detecting the sample to be tested by hyperspectral imaging technology proposed in this application not only does not damage the sample to be tested, but also can efficiently identify the doping status of the doped material based on the rich information in the hyperspectral data. Therefore, this application solves the problem of how to efficiently detect the result of material doping without damaging the sample. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0042] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0043] Figure 1 A schematic diagram of a process flow provided for the first embodiment of the material doping detection method of the present application;

[0044] Figure 2 This is a photoluminescence spectrum diagram of an embodiment of a material doping detection method of the present application;

[0045] Figure 3 This is the spectrum of the material doping detection method of this application after 10% Ir(ppy)2acac is doped in CzAO;

[0046] Figure 4 This is a schematic diagram of the detection results of Ir(ppy)2acac doped in CzAO using the material doping detection method of this application;

[0047] Figure 5 A schematic diagram of a convolutional neural network model of an embodiment of a material doping detection method of the present application;

[0048] Figure 6 This is a schematic diagram of the structure of a material doping detection device according to an embodiment of the present application;

[0049] Figure 7 It is a schematic diagram of the electronic device structure of the hardware operating environment involved in the material doping detection method in the embodiment of the present application.

[0050] Description of reference numerals:

[0051] 1. Spectral curve of CzAO; 2. Spectral curve of Ir(ppy)2acac; 3. Spectral curve after CzAO is doped with 10% Ir(ppy)2acac;

[0052] S1, first spectral area; S2, second spectral area; S3, third spectral area;

[0053] 101. Excitation light source; 102. Light source coupling optical path; 103. Hyperspectral camera; 104. Detection coupling optical path; 105. Semi-transparent and semi-reflective mirror; 106. Microscope lens; 107. Three-dimensional motion stage; 201. Main control module.

[0054] The purpose, features and advantages of this application will be further described in conjunction with the embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0055] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application and are not used to limit the present application.

[0056] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.

[0057] Material doping is a technique that introduces impurity atoms into another material in order to change or enhance certain physical and chemical properties of the material in order to adapt it to different uses. Nowadays, X-ray diffraction, nuclear magnetic resonance and other technologies can be used to detect whether material doping is successful. However, such technologies are not only time-consuming, but also prone to damage to samples. Therefore, how to efficiently detect the results of material doping without damaging the sample is a technical problem that has yet to be solved by those skilled in the art.

[0058] In the present application, by obtaining the doping material information in the sample to be tested and obtaining the hyperspectral data of the sample to be tested through a hyperspectral camera, the spectral information in the sample to be tested can be efficiently obtained through hyperspectral imaging technology without damaging the sample to be tested; then, based on the hyperspectral data and the doping material information, the material doping detection result of the sample to be tested is obtained, and the doping material in the sample to be tested can be identified based on the rich information in the hyperspectral data and the characteristics of the doping material represented by the doping material information, and then the material doping situation of the sample to be tested can be determined.

[0059] It can be seen that the method of detecting the sample to be tested by hyperspectral imaging technology proposed in this application not only does not damage the sample to be tested, but also can efficiently identify the doping status of the doped material based on the rich information in the hyperspectral data. Therefore, this application solves the problem of how to efficiently detect the result of material doping without damaging the sample.

[0060] Based on this, the present application embodiment provides a material doping detection method, referring to Figure 1 , Figure 1 This is a schematic diagram of the process of the first embodiment of the material doping detection method of the present application.

[0061] In this embodiment, the material doping detection method includes steps S10 to S30:

[0062] Step S10, obtaining doping system information of the sample to be tested, the doping system information includes: main material information, doping material information and doping standard information, the main material information is information related to the main material and doping, the doping material information is information about the material doped into the main material, and the doping standard information refers to information about the doping system formed after successful doping;

[0063] It is understood that the sample to be tested is extracted from the finished product obtained after the material is doped. For example, in the semiconductor field, the sample to be tested can be a semiconductor film; in the organic material field, the sample to be tested can be an organic doped material film. It is understood that the sample to be tested in this application only needs to have the property of photoluminescence, and this application does not limit the specific type of the sample to be tested.

[0064] Step S20, obtaining the hyperspectral data of the sample to be tested after photoluminescence;

[0065] It can be understood that the hyperspectral data is data of the sample to be tested collected after photoluminescence based on the hyperspectral imaging technology.

[0066] Step S30, obtaining the material doping detection result of the sample to be tested based on the hyperspectral data and the doping system information.

[0067] In this embodiment, the hyperspectral data can not only depict the spatial distribution pattern inside the sample to be tested in detail, but also capture and display the spectral characteristics of the sample in each band that are closely related to the chemical composition, physical state and internal structure of the sample. At the same time, the doping system information can also provide the basic properties of the main material and key details such as the type, concentration and distribution of the doping elements. Therefore, this application can achieve comprehensive and accurate detection of the doping state of the sample material to be tested by integrating and analyzing the hyperspectral data with the doping system information.

[0068] In this embodiment, by obtaining the doping material information in the sample to be tested, the doping system information includes: main material information, doping material information and doping standard information, the main material information is the information related to the main material and doping, the doping material information is the information of the material doped into the main material, and the doping standard information refers to the information of the doping system formed after the doping is successful, and the hyperspectral data of the sample to be tested is obtained by a hyperspectral camera, and the information in the sample to be tested can be efficiently obtained through hyperspectral imaging technology without damaging the sample to be tested; then, based on the hyperspectral data and the doping material information, the material doping detection result of the sample to be tested is obtained, and the doping material in the sample to be tested can be identified based on the rich information in the hyperspectral data and the characteristics of the doping material represented by the doping material information, and then the material doping situation of the sample to be tested can be determined.

[0069] It can be seen that the method of detecting the sample to be tested by hyperspectral imaging technology proposed in this application not only does not damage the sample to be tested, but also can efficiently identify the doping status of the doped material based on the rich information in the hyperspectral data. Therefore, this application solves the problem of how to efficiently detect the result of material doping without damaging the sample.

[0070] Furthermore, based on the first embodiment of the material doping detection method of the present application, a second embodiment of the material doping detection method of the present application is proposed.

[0071] In this embodiment, the above step S30 includes:

[0072] Step S301, obtaining a first wavelength range of main material information, a second wavelength range of doping material information, and a third wavelength range of doping standard information;

[0073] It should be noted that the main material refers to the material to be doped, and the doping material refers to the material doped into the main material. After the doping material is doped into the main material, a doping system is formed. The main material information may include the chemical elements contained in the main material, the chemical structure of the main material, the physical properties of the main material, etc. The doping material information may include the chemical elements of the doping material, the chemical formula of the doping material, the chemical structure of the doping material, the electrical properties of the doping material, the optical properties of the doping material, etc. The first wavelength range refers to the wavelength range corresponding to the photoluminescence characteristics of the main material itself, the second wavelength range refers to the wavelength range corresponding to the photoluminescence characteristics of the doping material itself, and the third wavelength range refers to the wavelength range corresponding to the overall luminescence characteristics in the system after successful doping. In this embodiment, the doping standard information refers to the information of the doping system formed after successful doping.

[0074] For example, when the main material is CzAO (indolo[3,2,1-de]acridin-8-one) and the doping material is Ir(ppy)2acac (bis(2-phenylpyridine)(acetylacetonate)iridium(III), the photoluminescence spectra of the main material, the doping material and the doping system are as follows: Figure 2 Specifically, curve 1 represents the spectrum curve of CzAO, curve 2 represents the spectrum curve of Ir(ppy)2acac, and curve 3 represents the spectrum curve after CzAO is doped with 10% Ir(ppy)2acac. Since CzAO is characterized by blue, Ir(ppy)2acac is characterized by green, and Figure 2 A red emission wavelength can eventually be obtained in the mid-doping system, so the first wavelength range is blue, the second wavelength range is green, and the third wavelength range is red.

[0075] Step S302, constructing a spectrum graph based on the hyperspectral data, and determining a first spectrum area within a first wavelength range, a second spectrum area within a second wavelength range, and a third spectrum area within a third wavelength range based on the spectrum graph;

[0076] Step S303, taking the sum of the first spectral area, the second spectral area and the third spectral area as the total area, and obtaining the material doping detection result of the sample to be tested based on the first spectral area, the second spectral area and the total area.

[0077] It can be understood that after obtaining the hyperspectral data of the photoluminescence of the sample to be tested through hyperspectral imaging technology, the hyperspectral data can be converted into a spectrum graph, and then the material doping detection result of the sample to be tested can be obtained based on the spectral area composed of the first wavelength range, the second wavelength range and the third wavelength range in the spectrum graph.

[0078] Specifically, the first spectral area and the second spectral area are used to characterize the independent conditions of the main material and the doping material in the sample to be tested. The larger the first spectral area and / or the second spectral area, the worse the effect of characterizing the material doping in the sample to be tested. Therefore, after obtaining the first spectral area, the second spectral area and the third spectral area, the material doping detection result of the sample to be tested can be obtained through the size relationship between each spectral area.

[0079] In a feasible implementation manner, the material doping detection results include undoped, successfully doped, and unsuccessfully doped. The above step S303 includes:

[0080] Step S3031, taking the sum of the first spectrum area and the second spectrum area as the invalid area, taking the ratio of the invalid area to the total area as the first ratio, taking the ratio of the first spectrum area to the invalid area as the second ratio, and taking the ratio of the second spectrum area to the invalid area as the third ratio;

[0081] Step S3032, when the first ratio is less than or equal to the first preset value, determining that the material doping detection result is successful doping;

[0082] Step S3033, when the first ratio is greater than the first preset value and the second ratio is greater than the second preset value, determining that the material doping detection result is undoped;

[0083] Step S3034: when the first ratio is greater than the first preset value and the third ratio is greater than or equal to the second preset value, determine that the material doping detection result is unsuccessful doping.

[0084] It can be understood that the first preset value and the second preset value are both pre-set, and the present application does not limit the specific numerical values ​​of the first preset value and the second preset value. Those skilled in the art can flexibly set the first preset value and the second preset value according to experimental conditions.

[0085] In the present embodiment, when the first ratio is less than or equal to the first preset value, it indicates that there are fewer independent main materials or independent doping materials in the sample to be tested, and therefore, the material doping test result of the sample to be tested can be determined to be successful doping. When the first ratio is greater than the first preset value, it indicates that there are more independent main materials or independent doping materials in the sample to be tested, and at this time, the material doping result may be undoped or unsuccessful doping, so it is necessary to further determine the material doping test result through the second ratio or the third ratio. Specifically, when the second ratio is greater than the second preset value, it indicates that only a trace amount of doping material interacts with the main material, and therefore, the material doping test result can be determined to be undoped; when the third ratio is greater than or equal to the second preset value, it indicates that the effect of the interaction between the doping material and the main material does not meet expectations, and therefore, the material doping test result can be determined to be unsuccessful doping.

[0086] For example, please refer to Figure 3 , Figure 3 This is the spectrum of CzAO doped with 10% Ir(ppy)2acac. Figure 3In the figure, the first wavelength range is 399.60nm-485.10nm, the second wavelength range is 485.10nm-570.10 nm, and the third wavelength range is 570.10nm-800.10 nm. S1 is the first spectral area, S2 is the second spectral area, and S3 is the third spectral area. When the first preset value is a and the second preset value is b, if (S1+S2) / S0≤a, it indicates that the doping is successful; if (S1+S2) / S0>a and S1 / (S1+S2)>b, it indicates that the doping is undoped; if (S1+S2) / S0>a and S2 / (S1+S2)≥b, it indicates that the doping is unsuccessful.

[0087] For further information, please refer to Figure 4 , Figure 4 This is a schematic diagram of the detection results of Ir(ppy)2acac doped in CzAO. Figure 4 , the first preset value and the second preset value are both 10%. Specifically, for the hyperspectral data corresponding to crystal material 1, there are 0 pixels representing successful doping (good), 4458 pixels representing undoped (Class A), and 35542 pixels representing unsuccessful doping (Class B). For the hyperspectral data corresponding to crystal material 2, there are 13595 pixels representing successful doping, 25012 pixels representing undoped, and 1393 pixels representing unsuccessful doping. Comparing the pixels of successful doping in crystal material 1 and crystal material 2, it can be seen that the doping effect of crystal material 2 is better than that of crystal material 1.

[0088] In this embodiment, the present application determines the spectral area by the wavelength range, and then determines the material doping detection result by the spectral area, which reduces the data processing amount and also reduces the data processing steps. Therefore, this embodiment can easily and quickly obtain the material doping detection result of the sample to be tested.

[0089] Furthermore, based on the first embodiment of the material doping detection method of the present application, a third embodiment of the material doping detection method of the present application is proposed.

[0090] In this embodiment, the above step S30 includes:

[0091] Step S304, determining the standard spectrum vector corresponding to the doping material information, and obtaining the pixel spectrum vector corresponding to each pixel contained in the sample to be tested based on the hyperspectral data;

[0092] It should be noted that the spectral vector is given by Spectral response value at wavelength constitute, record . The standard spectral vector refers to a spectral vector obtained based on the spectrum of the doping material. In the present embodiment, the standard spectral vector corresponds one-to-one to the doping material, that is, the number of standard spectral vectors is the same as the number of types of doping materials. In addition, it should be noted that the pixel spectral vector refers to the spectral vector of the pixel in the image obtained by the sample to be tested based on the hyperspectral imaging technology. In the present embodiment, the pixel spectral vector corresponds one-to-one to the pixel.

[0093] In this embodiment, the standard spectrum vector of the nth doping material is recorded as , the pixel spectrum vector of the pth pixel is recorded as .

[0094] Step S305, obtaining the actual spectral angle coordinates corresponding to each pixel according to the angle parameter between each pixel spectral vector and the standard spectral vector;

[0095] It should be noted that the angle parameter refers to a parameter related to the angle formed by two vectors. For example, the angle parameter can be the cosine value of the included angle, the sine value of the included angle, or other parameters related to the angle, which are not limited in this application.

[0096] For example, for each pixel, the cosine value of the angle between the pixel spectrum vector of the pixel and each standard spectrum vector can be used as the actual spectrum angle coordinate corresponding to the pixel. Alternatively, for each pixel, the sine value of the angle between the pixel spectrum vector of the pixel and each standard spectrum vector can be used as the actual spectrum angle coordinate corresponding to the pixel.

[0097] When the spectral angle coordinates are obtained based on the cosine value of the angle, the formula for calculating the cosine value Cn of the angle between the pixel and the nth doping material may be:

[0098] ,

[0099] Thus, the actual spectral angle coordinate at the p pixel position can be expressed as .

[0100] Step S306, obtaining the ideal spectral angle coordinates corresponding to each pixel, and calculating the Euler distance between each ideal spectral angle coordinate and each actual spectral angle coordinate;

[0101] It should be noted that the ideal spectral angle coordinates refer to the spectral angle coordinates corresponding to each pixel under the ideal state of successful doping. In a feasible implementation, the ideal spectral angle coordinates can be expressed as In order to determine the doping state in pixels, the Euler distance between the actual spectral angle coordinate and the ideal spectral angle coordinate corresponding to each pixel can be calculated, and then the value of the Euler distance can be used to determine whether the component at the pixel is close to the experimental ideal value.

[0102] Exemplarily, the formula for calculating the Euler distance O may be:

[0103] .

[0104] Step S307, comparing each Euler distance with a preset experimental ideal value, obtaining a comparison result corresponding to each pixel, and obtaining a material doping detection result of the sample to be tested according to each comparison result.

[0105] It can be understood that the closer the Euler distance corresponding to a pixel is to the experimental ideal value, the closer the component at the pixel is to the ideal value. Therefore, the comparison results corresponding to each pixel can be obtained by numerical comparison, so that the material doping detection result of the sample to be tested can be obtained according to the comparison results.

[0106] In a feasible implementation, if the Euler distance corresponding to a certain pixel is detected to be close to the experimental ideal value, the material doping detection result at the pixel can be determined to be successful doping, otherwise, the material doping detection result can be determined to be unsuccessful doping.

[0107] In addition, in another possible implementation, the actual spectral angle coordinate of the pixel and the ideal spectral angular coordinates The projection distance in a certain dimension can characterize the proportion of the doping material represented by the dimension, wherein the mapping relationship between the projection distance and the proportion of the doping material can be obtained through experimental fitting.

[0108] In this embodiment, the method of determining the material doping status in units of pixels adopted in the present application can accurately obtain the material doping detection result based on the material composition of each pixel, thereby improving the accuracy of the material doping detection result.

[0109] In a feasible implementation manner, before the above step S307, the method further includes:

[0110] Step S308, obtaining a weight correction coefficient, where the weight correction coefficient is used to adjust the weight of each doping material in the area represented by the pixel;

[0111] It is understandable that the weight correction coefficient is pre-set based on the main material and the doping material.

[0112] Step S309, obtaining a new Euler distance according to the product of each Euler distance and the weight correction coefficient;

[0113] Based on this, the above step S307 includes:

[0114] Step S3071, comparing each new Euler distance with a preset experimental ideal value to obtain a comparison result corresponding to each pixel.

[0115] For example, the expression of the new Euler distance Oc may be:

[0116] ;

[0117] in, is the weight correction factor.

[0118] Specifically, when Alq3 (Tris-(8-hydroxyquinolinato)aluminum) is doped with Ir(ppy)3 (Tris(2-phenylpyridine)iridium), Can be The experimental ideal value corresponding to the doping system of Alq3 and Ir(ppy)3 can be In a feasible implementation, if the new Euler distance corresponding to a pixel is less than , then it can be determined that the material doping detection result of the pixel point is successful doping; if the new Euler distance corresponding to a certain pixel is greater than or equal to , it can be determined that the material doping detection result of the pixel point is unsuccessful doping.

[0119] It is understandable that after obtaining the Euler distance corresponding to each pixel, the doping material ratio relationship at each pixel can be obtained based on the mapping relationship between the pre-set Euler distance and the doping material ratio. However, there are differences in the weights between different doping materials. Therefore, in this embodiment, the weights corresponding to different doping materials in the pixel can be adjusted by the weight correction coefficient to improve the accuracy of the calculated Euler distance, thereby improving the accuracy of the obtained material doping detection result.

[0120] Furthermore, based on the first embodiment of the material doping detection method of the present application, a fourth embodiment of the material doping detection method of the present application is proposed.

[0121] In this embodiment, the above step S30 further includes:

[0122] Step S310, inputting the hyperspectral data into a target convolutional neural network model, where the target convolutional neural network model is trained based on the doping system information;

[0123] Step S311, obtaining the material doping detection result of the sample to be tested output by the target convolutional neural network model.

[0124] It is understandable that the convolutional neural network model can extract image features and perform classification based on the extracted image features. Therefore, the hyperspectral data can be input into the target convolutional neural network model trained according to the doping system information, and the material doping detection results can be obtained through the target convolutional neural network model.

[0125] In a feasible implementation, the target convolutional neural network model includes an input layer, a hidden layer, and an output layer, wherein the input layer is used to receive raw data; the hidden layer is used to extract various features of the raw data, specifically, a series of convolution kernels and pooling operations can be used to mine deep-level patterns and structural information of the raw data, and then feature transformation and abstract operations can be completed; the output layer is used to output classification results. When processing hyperspectral data through the target convolutional neural network model, the input layer preprocesses and inputs the hyperspectral data, the hidden layer performs feature extraction and pattern recognition, and the output layer performs decision-making and judgment, so that the material doping detection results output by the output layer can be obtained.

[0126] In a feasible implementation manner, before the above step S310, the method further includes:

[0127] Step S312, obtaining sample hyperspectral data of doping system information, and inputting the sample hyperspectral data into the convolutional neural network model to be trained, to obtain the predicted material doping detection result output by the convolutional neural network model to be trained;

[0128] It can be understood that the sample hyperspectral data is the hyperspectral data obtained in the doping system corresponding to the doping system information and used for training the model. The predicted material doping detection result is the material doping detection result obtained by the untrained convolutional neural network model based on the characteristics of the sample hyperspectral data.

[0129] Step S313, calculating the loss value between the predicted material doping detection result and the actual doping result of the sample hyperspectral data;

[0130] It can be understood that the actual doping result may be a material doping detection result corresponding to the sample hyperspectral data obtained according to the second embodiment or the third embodiment.

[0131] Step S314, iteratively optimize the convolutional neural network model to be trained according to the loss value until the loss value converges to obtain the target convolutional neural network model.

[0132] In this embodiment, the convolutional neural network model can also be trained using sample hyperspectral data of the doping system information to improve the probability that the convolutional neural network model can correctly predict the material doping detection results.

[0133] Please refer to Figure 5 , Figure 5 This is a convolutional neural network model diagram of an embodiment of the material doping detection method of this application. It should be noted that Figure 5 In the figure, the main material is CzAO and the doping material is Ir (ppy) 2acac. The multiple colored three-dimensional data blocks in the input layer represent the hyperspectral data of the collected material sample library. Among them, the hyperspectral data contains spectral information of multiple bands, which can reflect the detailed physical and chemical properties of the material. The data received by the input layer is processed by multiple hidden layers. These hidden layers are composed of multiple neurons, which are connected by weights to extract and transform the features of the input data. Then each neuron performs a weighted summation on the input data, and generates an output through an activation function, which is passed to the next layer. The data processed by multiple layers obtains the result in the output layer. Specifically, the output layer maps the processed data to specific sample ratings, thereby achieving the purpose of analyzing the samples to be inspected based on the hyperspectral data. Specifically, Figure 5 In the scatter plot corresponding to the input layer, the parameter MB is used to measure the defects caused by the doping material, and the parameter MG is used to measure the defects caused by the main material; in addition, the red scatter points, yellow-green scatter points, green scatter points, blue scatter points, and purple scatter points in the scatter plot represent the five clusters distributed by MB and MG. Specifically, there is a clear dividing line along the MG axis between the two clusters of 180℃ to 195℃ and 195℃ to 210℃, indicating that the defect characteristics caused by the doping material are very obvious when annealed at 180℃ and 195℃. However, at 210℃, 225℃, and 240℃, the defects caused by the doping material are difficult to distinguish. Moreover, under high temperature conditions, since the arrangement of the main molecules becomes loose, the doping molecules can be doped, so along the MB axis, the higher the temperature, the smaller the MB, indicating the phenomenon that the defects caused by the main material gradually disappear.

[0134] Figure 5 In the probability density function curve corresponding to the middle hidden layer, MBP is a convex point determined on the curve corresponding to MB, which is used as a threshold to determine whether the sample is a defect caused by doped materials. If MB exceeds the threshold MBP, the sample is classified as a defect caused by doped materials. MGP1 and MGP2 are two convex points observed on the curve corresponding to MG, which are used as thresholds to determine whether the sample is a defect of the main material.

[0135] Figure 5In the scatter plot corresponding to the middle output layer, Q represents the sample with successful doping (both the blue peak and the green peak are very small or not detected), G1 represents the sample that only contains defects caused by the main material, but only contains the sample with a very small blue peak or not detected and a large green peak, G2 also represents the sample that only contains defects caused by the main material, but only contains the sample with a very small blue peak or not detected and a very large green peak, B represents the sample with defects caused only by the doping material (the blue peak is large, the green peak is very small or not detected), BG1 represents the sample that contains defects caused by both the doping material and the main material, but only contains the sample with a large blue peak and a very large green peak, BG2 represents the sample that contains defects caused by both the doping material and the main material, but only contains the sample with a large blue peak and a very large green peak.

[0136] It should be noted that the above examples are only used to understand the present application and do not constitute a limitation on the material doping detection method of the present application. More simple transformations based on this technical concept are all within the scope of protection of the present application.

[0137] In addition, the present application also provides a material doping detection device, which is applied to the above material doping detection method. Figure 6 , the material doping detection device comprises:

[0138] An excitation light source 101, a light source coupling optical path 102, a hyperspectral camera 103, a detection coupling optical path 104, a semi-transparent and semi-reflective mirror 105, a microscope lens 106, a three-dimensional motion stage 107 and a main control module 201. The three-dimensional motion stage 107 is placed with a sample to be inspected. The main control module 201 is communicatively connected with the excitation light source 101 and the hyperspectral camera 103.

[0139] In the optical path for exciting the sample to be tested to generate photoluminescence, the excitation light source 101 emits laser light, which passes through the light source coupling optical path 102 to reach the semi-transparent and semi-reflective mirror 105, is reflected by the semi-transparent and semi-reflective mirror 105 to the microscope lens 106, and irradiates the sample to be tested, causing the sample to be tested to photoluminesce. Figure 6 The solid arrow in the figure indicates the direction of light propagation in this optical path.

[0140] In the optical path of the hyperspectral imaging of the sample to be tested, the light emitted by the sample to be tested passes through the microscope lens 106 to reach the semi-transparent and semi-reflective mirror 105, passes through the semi-transparent and semi-reflective mirror 105 and the detection coupling optical path 104 to reach the hyperspectral camera 103, and is collected by the hyperspectral camera 103 to obtain the hyperspectral data of the sample to be tested. Figure 6 The dotted arrow in the figure indicates the propagation direction of the light in this light path. It should be noted that in order to distinguish, Figure 6 Separating the propagation directions of different light paths does not mean that the spatial positions of the light paths in actual situations are completely separated.

[0141] In a feasible implementation, the excitation light source 101 can use a 380nm laser. The short-wave laser 380nm emitted by the excitation light source 101 irradiates the sample to be tested, which can cause the sample to be tested to photoluminesce and generate a signal to be detected; the light source coupling optical path 102 is a key component for coupling the laser to the position of the three-dimensional motion stage 107. A 380nm purification sheet is added to the coupling optical path, which can make the excitation light bandwidth narrower; the hyperspectral camera 103 is a key component for collecting hyperspectral data. A single collection can simultaneously obtain a microscopic image and the luminescence spectrum of each pixel point; the detection coupling optical path 104 is a key component for importing the signal to be tested into the hyperspectral camera 103. In addition, a 380nm notch filter can be set in the detection coupling optical path 104 to remove the energy of the excitation light reflected by the sample surface; the semi-transparent and semi-reflective mirror 105 can keep the optical path of the laser exciting the sample to be tested to produce photoluminescence and the hyperspectral imaging optical path on the same axis to form a coaxial optical system; the microscope lens 106 is used to facilitate the main control module 201 to obtain the microscopic appearance and spectral signals of the material; the three-dimensional motion stage 107 can move linearly along the XY axis and rotate around the Z axis, so as to realize the automated detection of the entire sample to be tested; the main control module 201 can control the excitation light source 101, the three-dimensional motion stage 107 and the hyperspectral camera 103, receive and store hyperspectral signals, and analyze hyperspectral data.

[0142] The material doping detection device provided by the present application adopts the material doping detection method in the above embodiment, which can solve the technical problem of how to efficiently detect the result of material doping without damaging the sample. Compared with the prior art, the beneficial effects of the material doping detection device provided by the present application are the same as the beneficial effects of the material doping detection method provided by the above embodiment, and the other technical features of the material doping detection device are the same as the features disclosed in the above embodiment method, which will not be repeated here.

[0143] An embodiment of the present application also provides an electronic device, which can be used as a main control module 201, and the electronic device includes: at least one processor; and a memory that is communicatively connected to the at least one processor; wherein the memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the material doping detection method in the above-mentioned embodiment one.

[0144] Reference below Figure 7 , Figure 7 This is a schematic diagram of the electronic device structure of the hardware operating environment involved in the material doping detection method in the embodiment of this application. It should be noted that: Figure 7 The electronic device shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0145] like Figure 7 As shown, the electronic device may include a processing device 1001 (e.g., a central processing unit, a graphics processor, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM: Read Only Memory) 1002 or a program loaded from a storage device 1003 to a random access memory (RAM: Random Access Memory) 1004. In RAM1004, various programs and data required for the operation of the electronic device are also stored. The processing device 1001, ROM1002, and RAM1004 are connected to each other through a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Generally, the following systems can be connected to the I / O interface 1006: an input device 1007 including, for example, a touch screen, a touch pad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; an output device 1008 including, for example, a liquid crystal display (LCD: Liquid Crystal Display), a speaker, a vibrator, etc.; a storage device 1003 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 1009. The communication device 1009 can allow the electronic device to communicate with other devices wirelessly or by wire to exchange data. Although the figure shows an electronic device with various systems, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems can be implemented or have alternatively.

[0146] In particular, according to the embodiments disclosed in the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.

[0147] The electronic device provided by the present application adopts the material doping detection method in the above embodiment, which can solve the technical problem of how to efficiently detect the result of material doping without damaging the sample. Compared with the prior art, the beneficial effects of the electronic device provided by the present application are the same as the beneficial effects of the material doping detection method provided by the above embodiment, and the other technical features in the electronic device are the same as the features disclosed in the method of the previous embodiment, which will not be repeated here.

[0148] It should be understood that the various parts disclosed in this application can be implemented by hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0149] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0150] The present application provides a computer-readable storage medium having computer-readable program instructions (ie, computer programs) stored thereon, wherein the computer-readable program instructions are used to execute the material doping detection method in the above-mentioned embodiment.

[0151] The computer-readable storage medium provided in the present application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems or devices, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM: Random Access Memory), a read-only memory (ROM: Read Only Memory), an erasable programmable read-only memory (EPROM: Erasable Programmable Read Only Memory or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM: CD-Read Only Memory), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution system or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency: Radio Frequency), etc., or any suitable combination of the above.

[0152] The computer-readable storage medium may be included in the electronic device, or may exist independently without being installed in the electronic device.

[0153] The computer-readable storage medium carries one or more programs. When the one or more programs are executed by an electronic device, the electronic device: obtains doping system information of the sample to be tested, the doping system information includes: main material information, doping material information and doping standard information, the main material information is information related to the main material and doping, the doping material information is information about the material doped into the main material, and the doping standard information refers to information about the doping system formed after successful doping; obtains hyperspectral data of the sample to be tested after photoluminescence; and obtains material doping detection results of the sample to be tested based on the hyperspectral data and the doping system information.

[0154] Computer program code for performing the operations of the present application may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0155] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0156] The modules involved in the embodiments described in this application may be implemented by software or hardware, wherein the name of the module does not constitute a limitation on the unit itself in some cases.

[0157] The readable storage medium provided in the present application is a computer-readable storage medium, which stores computer-readable program instructions (i.e., computer programs) for executing the above-mentioned material doping detection method, and can solve the technical problem of how to efficiently detect the results of material doping without damaging the sample. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in the present application are the same as the beneficial effects of the material doping detection method provided in the above-mentioned embodiment, and will not be repeated here.

[0158] The present application also provides a computer program product, including a computer program, which implements the steps of the material doping detection method as described above when executed by a processor.

[0159] The computer program product provided by the present application can solve the technical problem of how to efficiently detect the results of material doping without damaging the sample. Compared with the prior art, the beneficial effects of the computer program product provided by the present application are the same as the beneficial effects of the material doping detection method provided by the above embodiment, which will not be repeated here.

[0160] The above descriptions are only some embodiments of the present application, and are not intended to limit the patent scope of the present application. All equivalent structural changes made using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect applications in other related technical fields are included in the patent protection scope of the present application.

Claims

1. A material doping detection method, characterized in that: The material doping detection method comprises: Obtaining doping system information of the sample to be tested, the doping system information including: main material information, doping material information and doping standard information, the main material information is information related to the main material and doping, the doping material information is information about the material doped into the main material, and the doping standard information refers to information about the doping system formed after successful doping; Acquiring hyperspectral data of the sample to be tested after photoluminescence; Based on the hyperspectral data and the doping system information, obtaining a material doping detection result of the sample to be tested; The step of obtaining the material doping detection result of the sample to be tested based on the hyperspectral data and the doping system information includes: Determine the standard spectrum vector corresponding to the doping material information, and based on the hyperspectral data, obtain the pixel spectrum vector corresponding to each pixel contained in the sample to be tested, the spectrum vector is composed of Spectral response value at wavelength constitute, record , the standard spectrum vector of the nth doping material is recorded as , the pixel spectrum vector of the pth pixel is recorded as ; According to the angle parameter between each of the pixel spectrum vectors and the standard spectrum vector, the actual spectrum angle coordinates corresponding to each of the pixels are obtained; Obtaining the ideal spectral angle coordinates corresponding to each of the pixels, and calculating the Euler distance between each of the ideal spectral angle coordinates and each of the actual spectral angle coordinates; Each of the Euler distances is compared with a preset experimental ideal value to obtain a comparison result corresponding to each of the pixels, and a material doping detection result of the sample to be tested is obtained based on each of the comparison results.

2. The material doping detection method according to claim 1, characterized in that: Before the step of comparing each of the Euler distances with a preset experimental ideal value to obtain a comparison result corresponding to each of the pixels, the method further includes: Obtaining a weight correction coefficient, wherein the weight correction coefficient is used to adjust the weight of each doping material in the area represented by the pixel; Obtaining a new Euler distance according to the product of each of the Euler distances and the weight correction coefficient; The step of comparing each of the Euler distances with a preset experimental ideal value to obtain a comparison result corresponding to each of the pixels comprises: Each of the new Euler distances is compared with a preset experimental ideal value to obtain a comparison result corresponding to each of the pixels.

3. A material doping detection device, characterized in that: Applicable to the material doping detection method according to any one of claims 1 to 2, the material doping detection device comprises: an excitation light source, a light source coupling optical path, a hyperspectral camera, a detection coupling optical path, a semi-transparent and semi-reflective mirror, a microscope lens, a three-dimensional motion stage and a main control module, a sample to be tested is placed on the three-dimensional motion stage, and the main control module is communicatively connected with the excitation light source and the hyperspectral camera; The excitation light source emits laser light, which passes through the light source coupling optical path to reach the semi-transparent and semi-reflective mirror, is reflected by the semi-transparent and semi-reflective mirror to the microscope lens, and irradiates the sample to be tested, so that the sample to be tested is photoluminescent; The light emitted by the sample to be tested passes through the microscope lens to reach the semi-transparent and semi-reflective mirror, passes through the semi-transparent and semi-reflective mirror and the detection coupling optical path to reach the hyperspectral camera, and is collected by the hyperspectral camera to obtain hyperspectral data of the sample to be tested; The main control module receives and stores the hyperspectral signal, and analyzes the hyperspectral data.

4. An electronic device, characterized in that: The electronic device comprises: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the material doping detection method according to any one of claims 1 to 2.

5. A storage medium, characterized in that: The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the material doping detection method as described in any one of claims 1 to 2 are implemented.

Images