A method and apparatus for predictive analysis of emission spectral profiles

Abstract

The embodiment of the present application relates to a kind of prediction analysis method and device of emission spectrum curve, the method comprises: constructing an emission intensity prediction model for predicting emission intensity;And based on a first data set constructed by data acquisition training emission intensity prediction model;After training, the task type and task configuration parameters are extracted from the prediction analysis task input by user;If it is the first type, then the three types of curve characteristics (maximum peak point, full width at half maximum and half peak wavelength range) of the emission spectrum prediction curve of specified molecule are analyzed under the condition that temperature is invariable but illumination intensity is different;If it is the second type, then the three types of curve characteristics of specified molecule are analyzed under the condition that illumination intensity is invariable but temperature is different;If it is the third type, then the three types of curve characteristics of two specified molecules are analyzed under the condition that temperature and illumination intensity are invariable;The present application can improve prediction analysis efficiency, improve data analysis convenience.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of data processing, in particular to a prediction analysis method and device for emission spectrum curve. BACKGROUND

[0002] For the organic photovoltaics (OPV) material applied to the flexible light-emitting device, it is necessary to predict and analyze the emission spectrum curve of each material molecule. The emission spectrum curve mentioned here is a two-dimensional curve with emission intensity (or simply intensity) as the ordinate and wavelength as the abscissa. At present, the prediction and analysis method for the emission spectrum curve of organic molecules is mostly realized based on quantum chemical calculation means (such as density functional theory calculation). However, it is known from practical experience that this conventional prediction and analysis method has problems of high calculation complexity, long processing time, and low processing efficiency. SUMMARY

[0003] The purpose of the present application is to provide a prediction analysis method and device for emission spectrum curve, electronic equipment and computer readable storage medium, which can reduce the processing complexity of the prediction analysis task, shorten the processing time, and improve the processing efficiency. The present application customizes an emission intensity prediction model for predicting the emission intensity according to the model input of the molecular structure, temperature, light intensity and wavelength, and trains the model. After the training is completed, the prediction analysis task (composed of task type and task configuration parameters) input by the user is analyzed. If the task type is the first type, the emission spectrum curves of a specified molecule are predicted based on the prediction model and the task configuration parameters under the condition that the temperature is the same but the light intensity is different, and the three curve characteristics (maximum peak point, full width at half maximum, and half maximum wavelength range) of each predicted curve are analyzed to obtain the first analysis data table for feedback to the user. If it is the second type, the emission spectrum curves of a specified molecule are predicted based on the prediction model and the task configuration parameters under the condition that the light intensity is the same but the temperature is different, and the three curve characteristics of each predicted curve are analyzed to obtain the second analysis data table for feedback to the user. If it is the third type, the emission spectrum curves of two specified molecules are predicted based on the prediction model and the task configuration parameters under the condition that the temperature and the light intensity are unchanged, and the three curve characteristics of the two predicted curves are analyzed to obtain the third analysis data table for feedback to the user. The present application can reduce the processing complexity of the prediction analysis task, shorten the processing time, and improve the processing efficiency through a customized emission intensity prediction model. On the other hand, the purpose of improving the data analysis convenience can be achieved through three types of customized analysis means.

[0004] To achieve the above object, the first aspect of the embodiment of the present application provides a prediction analysis method for emission spectrum curve, which comprises:

[0005] constructing an emission intensity prediction model for performing emission intensity prediction; the emission intensity prediction model is configured to perform emission intensity prediction processing according to a model input of a molecular structure M, a temperature x, an illumination intensity y and a wavelength z and output a corresponding predicted emission intensity u;

[0006] constructing a first data set for model training through data acquisition; and performing model training on the emission intensity prediction model according to the first data set;

[0007] after the model training is completed, receiving a prediction analysis task input by a user and extracting a corresponding task type and task configuration parameters therefrom; the prediction analysis task comprises the task type and the task configuration parameters; the task type comprises a first type, a second type and a third type; when the task type is the first type, the corresponding task configuration parameters comprise a first molecular structure, a first set temperature, a first illumination intensity sequence and a first wavelength sequence; when the task type is the second type, the corresponding task configuration parameters comprise a second molecular structure, a first set illumination intensity, a first temperature sequence and a second wavelength sequence; when the task type is the third type, the corresponding task configuration parameters comprise a third molecular structure, a fourth molecular structure, a second set temperature, a second set illumination intensity and a third wavelength sequence;

[0008] if the task type is the first type, under a set condition that a plurality of temperatures are consistent but illumination intensities are different, performing prediction on a plurality of emission spectrum curves of a specified molecule based on the emission intensity prediction model and the task configuration parameters and performing data analysis on maximum peak points, full width at half maximum and half maximum wavelength ranges of each predicted curve to obtain a corresponding first analysis data table;

[0009] if the task type is the second type, under a set condition that a plurality of illumination intensities are consistent but temperatures are different, performing prediction on a plurality of emission spectrum curves of a specified molecule based on the emission intensity prediction model and the task configuration parameters and performing data analysis on maximum peak points, full width at half maximum and half maximum wavelength ranges of each predicted curve to obtain a corresponding second analysis data table;

[0010] if the task type is the third type, under a set condition that temperatures and illumination intensities are consistent, performing prediction on emission spectrum curves of two specified molecules respectively based on the emission intensity prediction model and the task configuration parameters and performing data analysis on maximum peak points, full width at half maximum and half maximum wavelength ranges of the two predicted curves to obtain a corresponding third analysis data table;

[0011] feeding back the first, second or third analysis data table obtained this time to a current user.

[0012] Preferably, the molecular structure M comprises a plurality of atoms mi 1≤ atomic index i≤N M N M is the total number of atoms of the molecular structure M; each of the atoms m i is composed of a corresponding atomic type and three-dimensional atomic coordinates;

[0013] The first data set includes a plurality of first data records; the first data record includes a first training molecular structure, a first training temperature, a first training light intensity, a first training wavelength sequence, and a first emission intensity label sequence; the data structure type of the first training molecular structure is consistent with the data structure type of the molecular structure M; the first training wavelength sequence is composed of a plurality of first training wavelengths; the first emission intensity label sequence is composed of a plurality of first emission intensity labels; the first emission intensity label corresponds to the first training wavelength one by one;

[0014] When the task type is the first type, the first light intensity sequence of the task configuration parameter is sorted in order of intensity from small to large by a plurality of first light intensities; when the task type is the second type, the first temperature sequence of the task configuration parameter is sorted in order of temperature from low to high by a plurality of first temperatures; when the task type is the first, second, or third type, the corresponding first, second, or third wavelength sequence in the task configuration parameter is sorted in order of wavelength from small to large by a plurality of corresponding first, second, or third wavelengths;

[0015] The data structure types of the first, second, third, and fourth molecular structures are consistent with the data structure type of the molecular structure M;

[0016] The first analysis data table is composed of a plurality of first analysis data records; the record field of the first analysis data record is composed of a molecular structure field, a temperature field, a light intensity field, a curve data sequence field, a maximum peak point field, a full width at half maximum field, and a half-peak wavelength range field; the total number of records of the first analysis data record is consistent with the total number of the first light intensities of the corresponding first light intensity sequence;

[0017] The second analysis data table is composed of a plurality of second analysis data records; the record field of the second analysis data record is composed of a molecular structure field, a temperature field, a light intensity field, a curve data sequence field, a maximum peak point field, a full width at half maximum field, and a half-peak wavelength range field; the total number of records of the second analysis data record is consistent with the total number of the first temperatures of the corresponding first temperature sequence;

[0018] The third analysis data table is composed of two third analysis data records; the record fields of the third analysis data records are composed of a molecular structure field, a temperature field, an illumination intensity field, a curve data sequence field, a maximum peak point field, a full width at half maximum field, and a half peak wavelength range field; the two third analysis data records correspond one-to-one to the third and fourth molecular structures.

[0019] Preferably, the first model input end of the emission intensity prediction model is used to receive the molecular structure M as the model input, the second model input end is used to receive the temperature x as the model input, the third model input end is used to receive the illumination intensity y as the model input, and the fourth model input end is used to receive the wavelength z as the model input; the model output end of the emission intensity prediction model is used to output the corresponding predicted emission intensity u;

[0020] The emission intensity prediction model comprises an embedding coding module, a molecular structure coding module, a first Gaussian kernel module, a first vector mapping module, a second Gaussian kernel module, a second vector mapping module, a third Gaussian kernel module, a third vector mapping module, a feature fusion module, and an emission intensity prediction module; the molecular structure coding module is implemented based on a Uni-Mol model or a type of graph neural network satisfying SE(3) equivariance; the first, second, and third vector mapping modules and the emission intensity prediction module are all implemented based on an MLP model;

[0021] The input end of the embedding coding module is connected to the first model input end, and the output end is connected to the input end of the molecular structure coding module; the output end of the molecular structure coding module is connected to the first input end of the feature fusion module; the input end of the first Gaussian kernel module is connected to the second model input end, and the output end is connected to the input end of the first vector mapping module; the output end of the first vector mapping module is connected to the second input end of the feature fusion module; the input end of the second Gaussian kernel module is connected to the third model input end, and the output end is connected to the input end of the second vector mapping module; the output end of the second vector mapping module is connected to the third input end of the feature fusion module; the input end of the third Gaussian kernel module is connected to the fourth model input end, and the output end is connected to the input end of the third vector mapping module; the output end of the third vector mapping module is connected to the fourth input end of the feature fusion module; the output end of the feature fusion module is connected to the input end of the emission intensity prediction module; the output end of the emission intensity prediction module is connected to the model output end;

[0022] The embedding encoding module is used to encode the molecular structure M input to the model according to the embedding encoding rules of the molecular structure encoding module and send the encoding result to the molecular structure encoding module. Specifically, when the molecular structure encoding module is implemented based on the Uni-Mol model, the embedding encoding module encodes each atom m of the molecular structure M according to the atom type one-hot encoding rules of the Uni-Mol model. i Perform one-hot encoding of the atom type to obtain the corresponding atom encoding vector, and then use the obtained N... M The aforementioned atomic encoding vectors form a corresponding atomic encoding tensor, and the encoding is performed according to the pairwise feature initialization rule of the Uni-Mol model based on the coordinates of all three-dimensional atoms of the molecular structure M to obtain a tensor with shape N. M ×N M The pairwise encoded tensors are obtained, and the obtained atom encoded tensors and the pairwise encoded tensors are sent to the molecular structure encoding module; the embedding encoding module, when the molecular structure encoding module is implemented based on a type of graph neural network that satisfies SE(3) equivariance, is composed of each atom m of the molecular structure M. i As the corresponding first node and obtained from N M Each of the first nodes forms a corresponding set of first nodes, and a directed edge is drawn from each of the first nodes to any other node, denoted as the corresponding first edge. The edge relationship of each first edge is set as two corresponding atoms m. i The coordinate difference vector between them, and obtained by N M ×(N M -1) The first edge forms a corresponding first edge set, and the obtained first node set and the first edge set form a corresponding first graph structure, which is sent to the molecular structure encoding module;

[0023] When the molecular structure encoding module is based on the Uni-Mol model, it is used to perform atomic feature and pairwise feature extraction processing on the input atomic encoding tensor and the pairwise encoding tensor to obtain the corresponding latent feature tensor H, which is then sent to the feature fusion module; the latent feature tensor H is generated by N M Hidden feature vectors h i Composition, the hidden feature vector h i With the atom m i One-to-one correspondence;

[0024] When the molecular structure encoding module is implemented based on a type of graph neural network that satisfies SE(3) equivariance, it is used to perform feature update processing on the node features and edge features of each first node and each first edge in the input first graph structure through the message passing mechanism of the graph neural network to obtain the corresponding hidden feature tensor H and send it to the feature fusion module.

[0025] The first Gaussian kernel module is configured to preset a plurality of first Gaussian kernel functions in the module;

[0026] The first Gaussian kernel module is further configured to perform corresponding kernel function calculation on the temperature x of the model input according to each of the first Gaussian kernel functions, and take the calculated numerical result as a corresponding first result value; and all the first result values obtained are used to form a corresponding temperature encoding vector, which is sent to the first vector mapping module; the vector length of the temperature encoding vector is consistent with the total number of the first Gaussian kernel functions;

[0027] The first vector mapping module is configured to map the hidden feature vector h i to a corresponding vector space as a target vector space, and perform target vector space mapping on the temperature encoding vector to obtain a corresponding temperature mapping vector, which is sent to the feature fusion module; the temperature mapping vector is consistent with the feature dimension of the hidden feature vector h i ;

[0028] The second Gaussian kernel module is configured to preset a plurality of second Gaussian kernel functions in the module;

[0029] The second Gaussian kernel module is further configured to perform corresponding kernel function calculation on the illumination intensity y of the model input according to each of the second Gaussian kernel functions, and take the calculated numerical result as a corresponding second result value; and all the second result values obtained are used to form a corresponding illumination intensity encoding vector, which is sent to the second vector mapping module; the vector length of the illumination intensity encoding vector is consistent with the total number of the second Gaussian kernel functions;

[0030] The second vector mapping module is configured to map the hidden feature vector h i to a corresponding vector space as a target vector space, and perform target vector space mapping on the illumination intensity encoding vector to obtain a corresponding illumination intensity mapping vector, which is sent to the feature fusion module; the illumination intensity mapping vector is consistent with the feature dimension of the hidden feature vector h i ;

[0031] The third Gaussian kernel module is configured to preset a plurality of third Gaussian kernel functions in the module;

[0032] The third Gaussian kernel module is further configured to perform corresponding kernel function calculation on the wavelength z of the model input according to each of the third Gaussian kernel functions, and take the calculated numerical result as a corresponding third result value; and all the third result values obtained are used to form a corresponding wavelength encoding vector, which is sent to the third vector mapping module; the vector length of the wavelength encoding vector is consistent with the total number of the third Gaussian kernel functions.

[0033] The third vector mapping module is configured to map the hidden feature vector h i to a corresponding vector space as a target vector space; and map the wavelength encoding vector to a corresponding wavelength mapping vector as a target vector space, and send the wavelength mapping vector to the feature fusion module; the wavelength mapping vector and the hidden feature vector h i have the same feature dimension;

[0034] The feature fusion module is configured to sequentially splice each hidden feature vector h i of the hidden feature tensor H with the temperature mapping vector, the illumination intensity mapping vector, and the wavelength mapping vector, and take the spliced vector as a corresponding fusion feature vector r i ; and take the N M fusion feature vectors r i to form a corresponding fusion feature tensor R, and send the fusion feature tensor R to the emission intensity prediction module;

[0035] The emission intensity prediction module is configured to perform emission intensity regression calculation according to the input fusion feature tensor R, and output the calculation result as a corresponding predicted emission intensity u.

[0036] Preferably, the first data set for model training is constructed through data acquisition, specifically including:

[0037] Step 41, a large amount of data acquisition is performed on the organic molecular structure of the organic photovoltaic material of the light emitting device and its corresponding emission spectrum curve, and the temperature and illumination intensity information corresponding to the current curve through multiple data acquisition channels to obtain multiple first acquisition data;

[0038] The multiple data acquisition channels at least include multiple public molecular databases in the field of organic photovoltaic materials, all public literature and experimental databases in the field of organic photovoltaic materials;

[0039] The first acquisition data at least includes first acquisition structure, first acquisition curve data sequence, first acquisition temperature, and first acquisition illumination intensity; the first acquisition structure is the molecular structure of an organic molecule, and its data structure is consistent with the data structure type of the molecular structure M; the first acquisition curve data sequence is a discretized sampling point data sequence corresponding to the emission spectrum curve of the current organic molecule, which is composed of multiple first sampling points, each of which is composed of a sampling point wavelength and its corresponding sampling point emission intensity; the first acquisition temperature and the first acquisition illumination intensity are the ambient temperature and the ambient illumination intensity corresponding to the current emission spectrum curve, respectively;

[0040] Step 42, a round of traversal is performed on all the first collection data; and during the round of traversal, the first collection data currently traversed is taken as corresponding current collection data; and the first collection structure, the first collection temperature and the first collection light intensity of the current collection data are taken as corresponding first training molecular structure, first training temperature and first training light intensity; and each sampling point wavelength of the current collection data is taken as a corresponding first training wavelength, and each sampling point emission intensity is taken as a corresponding first emission intensity label; and all the first training wavelengths obtained are sorted in the sorting order of the first sampling points to obtain a corresponding first training wavelength sequence; and all the first emission intensity labels obtained are sorted in the sorting order of the first sampling points to obtain a corresponding first emission intensity label sequence; and the first training molecular structure, the first training temperature, the first training light intensity, the first training wavelength sequence and the first emission intensity label sequence corresponding to the current collection data form a corresponding first data record; and at the end of the round of traversal, all the first data records obtained form a corresponding first data set.

[0041] Preferably, the model training of the emission intensity prediction model according to the first data set specifically includes:

[0042] Step 51, the first data set is divided into two sub-data sets based on a preset first segmentation ratio, which are taken as a corresponding first training set and a first evaluation set;

[0043] Wherein, the first training set and the first evaluation set are both composed of a plurality of first data records; the total number of records of the first training set and the first evaluation set satisfies the first segmentation ratio;

[0044] Step 52, the first data record of the first training set is taken as a corresponding current training record;

[0045] Step 53, the first training molecular structure, the first training temperature and the first training light intensity of the current training record are taken as the current molecular structure M, the temperature x and the light intensity y;

[0046] Step 54, count the total number of the first training wavelengths of the current training record to obtain a corresponding first total number N1; and perform a round of traversal on the N1 first training wavelengths of the current training record; and during the current round of traversal, take the first training wavelength currently traversed as the current wavelength z; and input the current molecular structure M, the temperature x, the light intensity y and the wavelength z into the emission intensity prediction model for emission intensity prediction processing, and take the predicted emission intensity u output by this processing as a corresponding predicted intensity y pre,j ,1≤indexj≤N1; and take the first emission intensity label corresponding to the first training wavelength currently traversed in the current training record as a corresponding label intensity y tag,j ; and the predicted intensity y pre,j and the corresponding label intensity y tag,j comprise a corresponding first prediction-label pair (y pre,j , y tag,j );

[0047] Step 55, bring the obtained N1 first prediction-label pairs (y pre,j , y tag,j ) into a preset first model loss function L a ; and based on a preset first model optimizer, modulate the model parameters of the emission intensity prediction model in a direction towards minimizing the first model loss function L a ;

[0048] The first model loss function L a is:

[0049]

[0050] The first model optimizer at least includes an Adam optimizer, an SGD optimizer;

[0051] Step 56, identify whether the current training record is the last first data record of the first training set, if yes, go to step 57, if not, take the next first data record of the first training set as a new current training record and return to step 53 to continue training;

[0052] Step 57, a round of traversal is performed on all the first data records of the first evaluation set; and during the round of traversal, the first data record currently traversed is taken as a corresponding current evaluation record; the first training molecular structure, the first training temperature and the first training light intensity of the current evaluation record are taken as the current molecular structure M, the temperature x and the light intensity y; each first training wavelength of the current evaluation record is taken in turn as a corresponding current wavelength z, and the current molecular structure M, the temperature x, the light intensity y and the wavelength z are input into the emission intensity prediction model for emission intensity prediction processing, and the predicted emission intensity u output by the processing is taken as a corresponding first predicted intensity; and the first emission intensity label in the current evaluation record corresponding to each first predicted intensity is taken as a corresponding first label intensity; and each first predicted intensity of the current evaluation record and its corresponding first label intensity form a corresponding second prediction-label pair;

[0053] Step 58, after the round of traversal of all the first data records of the first evaluation set is completed, the total number of the second prediction-label pairs obtained is counted to obtain a corresponding second total number N2; and the first predicted intensity and the first label intensity of each second prediction-label pair are taken as a corresponding group of predicted intensity y pre,k and label intensity y tag,k , 1≤index k≤N2; and the N2 groups of predicted intensity y pre,k and label intensity y tag,k obtained are brought into a preset first model evaluation function S a to obtain a corresponding first evaluation value;

[0054] wherein, the first model evaluation function S a is:

[0055]

[0056] Step 59, whether the first evaluation value meets a preset first evaluation value range is identified; if not, returning to step 52 for continuing training; if yes, stopping training and confirming that the model training is completed.

[0057] Preferably, based on the emission intensity prediction model and the task configuration parameters, a plurality of emission spectrum curves of a specified molecule are predicted, and the maximum peak position, the full width at half maximum and the half peak wavelength range of each predicted curve are analyzed to obtain a corresponding first analysis data table, specifically including:

[0058] extracting the corresponding first molecular structure, the first set temperature, the first light intensity sequence and the first wavelength sequence from the current task configuration parameters; and taking the first molecular structure and the first set temperature as the current molecular structure M and the temperature x; and counting the total number of the first light intensity of the first light intensity sequence to obtain the corresponding total number N R1 ;

[0059] and taking each of the first light intensity of the first light intensity sequence as the corresponding current light intensity y in turn; and performing a round of traversal on all the first wavelengths of the first wavelength sequence; and in the current round of traversal, taking the first wavelength being currently traversed as the corresponding current wavelength z; and inputting the current molecular structure M, the temperature x, the light intensity y and the wavelength z into the emission intensity prediction model for emission intensity prediction processing and taking the predicted emission intensity u output by the current processing as a corresponding current predicted emission intensity; and taking the current wavelength z and the current predicted emission intensity as a set of corresponding curve point wavelength and curve point emission intensity to form a corresponding curve point; and at the end of the current round of traversal, arranging all the curve points corresponding to the current light intensity y in ascending order of the curve point wavelength to form a corresponding curve data sequence;

[0060] and performing a round of traversal on the N R1 first light intensities of the first light intensity sequence; and in the current round of traversal, taking the first light intensity being currently traversed as the corresponding current light intensity; and taking the first molecular structure, the first set temperature and the curve data sequence corresponding to the current light intensity as the corresponding current molecular structure, current set temperature and current curve data sequence; and based on the current curve data sequence, performing maximum peak position, full width at half maximum and half maximum wavelength range analysis to obtain the corresponding current maximum peak position, current full width at half maximum and current half maximum wavelength range; and taking the current molecular structure, the current set temperature, the current light intensity, the current curve data sequence, the current maximum peak position, the current full width at half maximum and the current half maximum wavelength range as the corresponding molecular structure field, temperature field, light intensity field, curve data sequence field, maximum peak position field, full width at half maximum field and half maximum wavelength range field to form a corresponding first analysis data record;

[0061] and after the current round of traversal on the N R1 first light intensities of the first light intensity sequence, taking the N R1 first analysis data records obtained to form a corresponding first analysis data table.

[0062] Preferably, the step of predicting multiple emission spectrum curves of a specified molecule based on the emission intensity prediction model and the task configuration parameters, and performing data analysis on the maximum peak position, full width at half maximum (FWHM), and wavelength range of each predicted curve to obtain a corresponding second analysis data table, specifically includes:

[0063] Extract the corresponding second molecular structure, first set light intensity, first temperature sequence, and second wavelength sequence from the current task configuration parameters; and use the first molecular structure and first set light intensity as the current molecular structure M and light intensity y; and count the total number of the first temperatures in the first temperature sequence to obtain the corresponding total number N. R2 ;

[0064] The first temperature of the first temperature sequence is sequentially taken as the corresponding current temperature x; all the second wavelengths of the second wavelength sequence are traversed once; during this traversal, the currently traversed second wavelength is taken as the corresponding current wavelength z; the current molecular structure M, the temperature x, the light intensity y, and the wavelength z are input into the emission intensity prediction model for emission intensity prediction processing, and the predicted emission intensity u output by the current processing is taken as a corresponding current predicted emission intensity; the current wavelength z and the current predicted emission intensity are taken as a set of corresponding curve point wavelengths and curve point emission intensities to form a corresponding curve point; and at the end of this traversal, all the curve points corresponding to the current temperature x are sorted in ascending order of the curve point wavelengths to form a corresponding curve data sequence;

[0065] And for N of the first temperature sequence R2 The system iterates through the first temperature once; and during this iteration, the first temperature currently being iterated through is taken as the current temperature; the first molecular structure, the first set light intensity, and the curve data sequence corresponding to the current temperature are taken as the current molecular structure, the current set light intensity, and the current curve data sequence; and based on the current curve data sequence, the maximum peak position, full width at half maximum (FWHM), and half-peak wavelength range are analyzed to obtain the current maximum peak position, current FWHM, and current half-peak wavelength range; and the current molecular structure, the current temperature, the current set light intensity, the current curve data sequence, the current maximum peak position, the current FWHM, and the current half-peak wavelength range are taken as the corresponding molecular structure field, temperature field, light intensity field, curve data sequence field, maximum peak position field, FWHM field, and half-peak wavelength range field to form a corresponding second analysis data record;

[0066] and at the end of the current round of iteration of N R2 first temperatures, the resulting N R2 second analysis data table is composed of the corresponding N

[0067] Preferably, the emission spectrum curves of the two specified molecules are respectively predicted based on the emission intensity prediction model and the task configuration parameters, and the maximum peak position, full width at half maximum, and half maximum wavelength range of the two predicted curves are analyzed to obtain a corresponding third analysis data table, specifically including:

[0068] The corresponding third molecular structure, fourth molecular structure, second set temperature, second set illumination intensity, and third wavelength sequence are extracted from the current task configuration parameters, and the second set temperature and the second set illumination intensity are taken as the current temperature x and the current illumination intensity y;

[0069] The third and fourth molecular structures are taken in turn as the corresponding current molecular structure M, and all the third wavelengths of the third wavelength sequence are iterated once. During the current iteration, the current iterated third wavelength is taken as the corresponding current wavelength z, and the current molecular structure M, temperature x, illumination intensity y, and wavelength z are input into the emission intensity prediction model for emission intensity prediction processing, and the predicted emission intensity u output by the processing is taken as a corresponding current predicted emission intensity. The current wavelength z and the current predicted emission intensity are taken as a group of corresponding curve point wavelengths and curve point emission intensities to form a corresponding curve point. At the end of the current round of iteration, all the curve points corresponding to the current molecular structure M are sorted in ascending order of the curve point wavelengths to form a corresponding curve data sequence;

[0070] The third and fourth molecular structures are taken in turn as the corresponding current molecular structure, and the second set temperature, the second set illumination intensity, and the curve data sequence corresponding to the current molecular structure are taken as the corresponding current set temperature, current set illumination intensity, and current curve data sequence. Based on the current curve data sequence, the maximum peak position, full width at half maximum, and half maximum wavelength range are analyzed to obtain the current maximum peak position, current full width at half maximum, and current half maximum wavelength range. The current molecular structure, current set temperature, current set illumination intensity, current curve data sequence, current maximum peak position, current full width at half maximum, and current half maximum wavelength range are taken as the corresponding molecular structure field, temperature field, illumination intensity field, curve data sequence field, maximum peak position field, full width at half maximum field, and half maximum wavelength range field to form a corresponding third analysis data record.

[0071] and the corresponding third analysis data table is composed of the two obtained third analysis data records.

[0072] Further, the maximum peak position, full width at half maximum, and half maximum wavelength range analysis based on the current curve data sequence obtains the corresponding current maximum peak position, current full width at half maximum, and current half maximum wavelength range, specifically including:

[0073] A two-dimensional coordinate plane is constructed as a corresponding emission spectrum curve plane with emission intensity I as the ordinate and wavelength λ as the abscissa; and a two-dimensional curve fitting is performed on the emission spectrum curve plane based on the current curve data sequence, and the obtained fitting curve is taken as the corresponding current emission spectrum curve;

[0074] and the maximum emission intensity position on the current emission spectrum curve is taken as the corresponding maximum peak position P max ; and the corresponding emission intensity and wavelength of the maximum peak position P max are denoted as the corresponding emission intensity I max and wavelength λ max ;

[0075] and the curve portions on the left and right sides of the maximum peak position P max on the current emission spectrum curve are denoted as the corresponding left curve and right curve, respectively; and the curve positions with emission intensity I max / 2 on the left and right curves are denoted as the corresponding left and right candidate positions; and the left candidate position farthest from the maximum peak position P max is taken as the corresponding left half peak position p1, and the right candidate position farthest from the maximum peak position P max is taken as the corresponding right half peak position p2; and the corresponding wavelengths of the left and right half peak positions p1 and p2 are denoted as the corresponding wavelengths λ1 and λ2; and the wavelength range width between the wavelengths λ1 and λ2 is identified to obtain the corresponding full width at half maximum W = λ2 - λ1; and the wavelength range with the wavelengths λ1 and λ2 as the left and right boundaries is taken as the corresponding half maximum wavelength range [λ1, λ2];

[0076] and the maximum peak position P max , the full width at half maximum W, and the half maximum wavelength range [λ1, λ2] obtained this time are taken as the corresponding current maximum peak position, the current full width at half maximum, and the current half maximum wavelength range.

[0077] The second aspect of the embodiment of the present application provides a device for implementing the prediction analysis method of the emission spectrum curve as described in the first aspect, and the device comprises a model construction module, a model training module, a prediction analysis task data receiving module, a prediction analysis task processing module and a prediction analysis task feedback module;

[0078] The model construction module is configured to construct an emission intensity prediction model for performing emission intensity prediction; the emission intensity prediction model is configured to perform emission intensity prediction processing according to the model input of the molecular structure M, the temperature x, the light intensity y and the wavelength z and output the corresponding predicted emission intensity u;

[0079] The model training module is configured to construct a first data set for model training through data acquisition; and perform model training on the emission intensity prediction model according to the first data set;

[0080] The prediction analysis task data receiving module is configured to receive a prediction analysis task input by a user and extract the corresponding task type and task configuration parameters therefrom after the model training is completed; the prediction analysis task comprises the task type and the task configuration parameters; the task type comprises a first type, a second type and a third type; when the task type is the first type, the corresponding task configuration parameters comprise a first molecular structure, a first set temperature, a first light intensity sequence and a first wavelength sequence; when the task type is the second type, the corresponding task configuration parameters comprise a second molecular structure, a first set light intensity, a first temperature sequence and a second wavelength sequence; when the task type is the third type, the corresponding task configuration parameters comprise a third molecular structure, a fourth molecular structure, a second set temperature, a second set light intensity and a third wavelength sequence;

[0081] The prediction analysis task processing module is configured to, when the task type is the first type, perform prediction on a plurality of emission spectrum curves of a specified molecule under the set condition that a plurality of temperatures are consistent but light intensities are different, based on the emission intensity prediction model and the task configuration parameters, and perform data analysis on the maximum peak point, the full width at half maximum and the half peak wavelength range of each predicted curve to obtain a corresponding first analysis data table;

[0082] The prediction analysis task processing module is further configured to, when the task type is the second type, perform prediction on a plurality of emission spectrum curves of a specified molecule under the set condition that a plurality of light intensities are consistent but temperatures are different, based on the emission intensity prediction model and the task configuration parameters, and perform data analysis on the maximum peak point, the full width at half maximum and the half peak wavelength range of each predicted curve to obtain a corresponding second analysis data table;

[0083] The prediction analysis task processing module is further configured to, when the task type is a third type, under a set condition that temperature and illumination intensity remain consistent, respectively predict emission spectrum curves of two specified molecules based on the emission intensity prediction model and the task configuration parameters, and perform data analysis on maximum peak points, full width at half maximum, and half peak wavelength ranges of the two predicted curves to obtain corresponding third analysis data tables.

[0084] The prediction analysis task feedback module is configured to feed back the first, second, or third analysis data table obtained this time to a current user.

[0085] The third aspect of the embodiment of the present application provides an electronic device, including a memory, a processor, and a transceiver.

[0086] The processor is configured to be coupled with the memory, read and execute instructions in the memory, so as to realize the method steps of the first aspect described above.

[0087] The transceiver is coupled with the processor, and the transceiver is controlled by the processor to perform message transceiving.

[0088] The fourth aspect of the embodiment of the present application provides a computer readable storage medium, and the computer readable storage medium stores computer instructions. When the computer instructions are executed by a computer, the computer instructions make the computer execute the instructions of the method of the first aspect described above.

[0089] The embodiment of the present application provides a prediction analysis method and device of emission spectrum curve, electronic equipment and computer readable storage medium. From the above content, it can be known that the embodiment of the present application customizes an emission intensity prediction model for predicting the emission intensity according to the model input of molecular structure, temperature, illumination intensity and wavelength, and trains the emission intensity prediction model through a first data set obtained by big data collection; and after the training is completed, a prediction analysis task (composed of a task type and a task configuration parameter) input by a user is analyzed; if the task type is the first type, then under the setting condition that multiple temperatures are consistent but illumination intensities are different, multiple emission spectrum curves of a specified molecule are predicted based on the emission intensity prediction model and the task configuration parameter, and three types of curve characteristics (maximum peak point, full width at half maximum and half peak wavelength range) of each predicted curve are analyzed to obtain a first analysis data table to feed back to the current user; if the task type is the second type, then under the setting condition that multiple illumination intensities are consistent but temperatures are different, multiple emission spectrum curves of a specified molecule are predicted based on the emission intensity prediction model and the task configuration parameter, and three types of curve characteristics of each predicted curve are analyzed to obtain a second analysis data table to feed back to the current user; if the task type is the third type, then under the setting condition that the temperature and the illumination intensity are consistent, the emission spectrum curves of two specified molecules are respectively predicted based on the emission intensity prediction model and the task configuration parameter, and three types of curve characteristics of two predicted curves are analyzed to obtain a third analysis data table to feed back to the current user. The embodiment of the present application reduces the processing complexity of the prediction analysis task, shortens the processing time and improves the processing efficiency on the one hand through a customized emission intensity prediction model; and on the other hand, the data analysis convenience is improved through three types of customized emission spectrum curve analysis means. BRIEF DESCRIPTION OF DRAWINGS

[0090] Figure 1 A prediction analysis method of emission spectrum curve provided for the embodiment one of the present application;

[0091] Figure 2 A module structure diagram of the emission intensity prediction model provided for the embodiment one of the present application;

[0092] Figure 3 A data structure diagram of the first analysis data table, the second analysis data table and the third analysis data table provided for the embodiment one of the present application;

[0093] Figure 4 A schematic diagram of the emission spectrum curve, the maximum peak point, the left half peak point, the right half peak point, the full width at half maximum and the half peak wavelength range provided for the embodiment one of the present application;

[0094] Figure 5 A module structure diagram of a prediction analysis device of emission spectrum curve provided for the embodiment two of the present application;

[0095] Figure 6 This is a schematic diagram of the structure of an electronic device provided in Embodiment 3 of the present invention. Detailed Implementation

[0096] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are merely some embodiments of this invention, and not all embodiments. Based on the embodiments of this invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this invention.

[0097] Embodiment 1 of the present invention provides a method for predicting and analyzing emission spectrum curves, such as... Figure 1 The schematic diagram shows a method for predicting and analyzing emission spectrum curves provided in Embodiment 1 of the present invention. The method mainly includes the following steps:

[0098] Step 1: Construct a emission intensity prediction model for emission intensity prediction.

[0099] Here, the emission intensity prediction model of this invention is used to perform emission intensity prediction processing based on the molecular structure M, temperature x, illumination intensity y, and wavelength z input to the model, and output the corresponding predicted emission intensity u. The molecular structure M includes multiple atoms m. i 1 ≤ atomic index i ≤ N M N M M represents the total number of atoms in the molecular structure; m represents the number of atoms per atom. i The atomic parameters are all composed of the corresponding atom type and three-dimensional atomic coordinates.

[0100] like Figure 2 As shown in the module structure diagram of the emission intensity prediction model provided in Embodiment 1 of the present invention, the first model input terminal of the emission intensity prediction model is used to receive the molecular structure M input by the model, the second model input terminal is used to receive the temperature x input by the model, the third model input terminal is used to receive the light intensity y input by the model, and the fourth model input terminal is used to receive the wavelength z input by the model; the model output terminal of the emission intensity prediction model is used to output the corresponding predicted emission intensity u.

[0101] like Figure 2As shown, the model components of the emission intensity prediction model include: an embedding encoding module, a molecular structure encoding module, a first Gaussian kernel module, a first vector mapping module, a second Gaussian kernel module, a second vector mapping module, a third Gaussian kernel module, a third vector mapping module, a feature fusion module, and an emission intensity prediction module. It should be noted that the molecular structure encoding module of the embodiment of the present application is implemented based on a Uni-Mol model or a type of graph neural network satisfying SE(3) equivariance; the first, second, and third vector mapping modules and the emission intensity prediction module of the embodiment of the present application are each implemented based on an MLP model. The Uni-Mol model mentioned above is an encoder model for atom-level feature encoding of a molecular structure, and the detailed model structure, model inference principle, atom type one-hot encoding rule, pair feature initialization encoding rule, and model pre-training scheme of the Uni-Mol model are explicitly described in the published technical document A “Uni-Mol: A Universal 3D Molecular Representation Learning Framework”. The type of graph neural network satisfying SE(3) equivariance mentioned above can be specifically an EGNN model or an SE(3)-Transformers model, and the embodiment of the present application preferably uses the EGNN model. It should also be noted that whether the molecular structure encoding module of the embodiment of the present application is implemented based on the Uni-Mol model or the type of graph neural network satisfying SE(3) equivariance, the currently used Uni-Mol model or graph neural network has been pre-trained based on the respective corresponding conventional pre-training scheme, and the pre-training schemes of the Uni-Mol model, EGNN model, and SE(3)-Transformers model have been published through public documents, which will not be further elaborated here.

[0102] As Figure 2As shown, the connection relationships of the components of the emission intensity prediction model are as follows: the input of the embedding coding module is connected to the input of the first model, and its output is connected to the input of the molecular structure coding module; the output of the molecular structure coding module is connected to the first input of the feature fusion module; the input of the first Gaussian kernel module is connected to the input of the second model, and its output is connected to the input of the first vector mapping module; the output of the first vector mapping module is connected to the second input of the feature fusion module; the input of the second Gaussian kernel module is connected to the input of the third model, and its output is connected to the input of the second vector mapping module; the output of the second vector mapping module is connected to the third input of the feature fusion module; the input of the third Gaussian kernel module is connected to the input of the fourth model, and its output is connected to the input of the third vector mapping module; the output of the third vector mapping module is connected to the fourth input of the feature fusion module; the output of the feature fusion module is connected to the input of the emission intensity prediction module; and the output of the emission intensity prediction module is connected to the model output.

[0103] The functions of each component of the radiation intensity prediction model are shown below.

[0104] 1) Embedded encoding module:

[0105] The embedding encoding module of this embodiment of the invention is used to encode the molecular structure M input to the model according to the embedding encoding rules of the molecular structure encoding module and send the encoding result to the molecular structure encoding module, specifically:

[0106] a. If the molecular structure encoding module is implemented based on the Uni-Mol model, then the embedding encoding module is used to encode each atom m of the molecular structure M according to the one-hot encoding rules of the atom type in the Uni-Mol model. i Perform one-hot encoding of the atom type to obtain the corresponding atom encoding vector, and then use the obtained N... M Each atom encoding vector forms a corresponding atom encoding tensor; and according to the pairwise feature initialization encoding rule of the Uni-Mol model, encoding is performed based on the coordinates of all three-dimensional atoms of the molecular structure M to obtain a tensor with shape N. M ×N M The paired encoded tensors are obtained; and the resulting atomic encoded tensors and paired encoded tensors are sent to the molecular structure encoding module;

[0107] b. If the molecular structure encoding module is implemented based on a graph neural network that satisfies SE(3) equivariance, then the embedding encoding module consists of each atom m of the molecular structure M. i As the corresponding first node and obtained from N M Each first node forms a corresponding set of first nodes; a directed edge is drawn from each first node to any other node, denoted as the corresponding first edge; and the edge relationship of each first edge is set as two corresponding atoms m.i coordinate difference vectors between the atoms; and a corresponding first edge set composed of N M ×(N M -1) first edges; and a corresponding first graph structure composed of the first node set and the first edge set.

[0108] 2) The molecular structure encoding module:

[0109] If the molecular structure encoding module is implemented based on the Uni-Mol model, the molecular structure encoding module is configured to perform atom feature and pair feature extraction processing according to the input atom encoding tensor and pair encoding tensor according to the encoding mechanism of the Uni-Mol model to obtain a corresponding hidden feature tensor H, and send the hidden feature tensor H to the feature fusion module; the hidden feature tensor H is composed of N M hidden feature vectors h i , and the hidden feature vector h i corresponds to the atom m i .

[0110] If the molecular structure encoding module is implemented based on a type of graph neural network satisfying SE(3) equivariance, the molecular structure encoding module is configured to perform feature update processing on the node features and edge features of each first node and each first edge in the input first graph structure through the message passing mechanism of the graph neural network to obtain a corresponding hidden feature tensor H, and send the hidden feature tensor H to the feature fusion module; the hidden feature tensor H is also composed of N M hidden feature vectors h i , and the hidden feature vector h i corresponds to the atom m i .

[0111] 3) The first Gaussian kernel module and the first vector mapping module:

[0112] The first Gaussian kernel module is configured to preset a plurality of first Gaussian kernel functions in the module. The first Gaussian kernel module is further configured to perform corresponding kernel function calculation on the temperature x input to the model according to each first Gaussian kernel function, and take the calculated numerical result as a corresponding first result value; and a corresponding temperature encoding vector composed of all the first result values is sent to the first vector mapping module; here, the vector length of the temperature encoding vector is consistent with the total number of the first Gaussian kernel functions.

[0113] The first vector mapping module is configured to take the corresponding vector space of the hidden feature vector h i as a target vector space, and perform target vector space mapping on the temperature encoding vector to obtain a corresponding temperature mapping vector, which is sent to the feature fusion module. Here, the temperature mapping vector and the hidden feature vector hi The feature dimensions remain consistent.

[0114] 4) Second Gaussian kernel module and second vector mapping module:

[0115] The second Gaussian kernel module in this embodiment of the invention is used to preset multiple second Gaussian kernel functions within the module. This second Gaussian kernel module is also used to perform corresponding kernel function calculations on the light intensity y input to the model according to each second Gaussian kernel function, and use the calculated numerical results as the corresponding second result values; and to send a corresponding light intensity encoding vector composed of all the obtained second result values ​​to the second vector mapping module. Here, the vector length of the light intensity encoding vector is consistent with the total number of second Gaussian kernel functions.

[0116] The second vector mapping module in this embodiment of the invention is used to map the latent feature vector h i The corresponding vector space is used as the target vector space; and the light intensity encoding vector is mapped to the target vector space to obtain a corresponding light intensity mapping vector, which is then sent to the feature fusion module. Here, the light intensity mapping vector and the latent feature vector h are... i The feature dimensions remain consistent.

[0117] 5) Third Gaussian kernel module and third vector mapping module:

[0118] The third Gaussian kernel module in this embodiment of the invention is used to preset multiple third Gaussian kernel functions within the module. This third Gaussian kernel module is also used to perform corresponding kernel function calculations on the wavelength z of the model input according to each third Gaussian kernel function, and use the calculated numerical results as the corresponding third result values; and to send a corresponding wavelength encoding vector composed of all the obtained third result values ​​to the third vector mapping module. Here, the vector length of the wavelength encoding vector is consistent with the total number of third Gaussian kernel functions.

[0119] The third vector mapping module in this embodiment of the invention is used to map the latent feature vector h i The corresponding vector space is used as the target vector space; and a corresponding wavelength mapping vector is obtained by mapping the wavelength encoding vector to the target vector space and sent to the feature fusion module. Here, the wavelength mapping vector and the latent feature vector h are... i The feature dimensions remain consistent.

[0120] 6) Feature fusion module:

[0121] The feature fusion module in this embodiment of the invention is used to fuse the various latent feature vectors h of the latent feature tensor H. i The temperature mapping vector, light intensity mapping vector, and wavelength mapping vector are sequentially concatenated, and the resulting concatenated vector is used as a corresponding fused feature vector r. i ; and from the obtained NM a fusion feature vector r i The corresponding fusion feature tensor R is sent to the emission intensity prediction module.

[0122] 7) the emission intensity prediction module:

[0123] The emission intensity prediction module of the embodiment of the present application is used for emission intensity regression calculation according to the input fusion feature tensor R and outputs the calculation result as the corresponding predicted emission intensity u.

[0124] Step 2, a first data set for model training is constructed through data acquisition; and the emission intensity prediction model is model trained according to the first data set;

[0125] Specifically, step 21, a first data set for model training is constructed through data acquisition;

[0126] The first data set includes a plurality of first data records; the first data record includes a first training molecular structure, a first training temperature, a first training light intensity, a first training wavelength sequence and a first emission intensity label sequence; the data structure type of the first training molecular structure is consistent with the data structure type of the molecular structure M; the first training wavelength sequence is composed of a plurality of first training wavelengths; the first emission intensity label sequence is composed of a plurality of first emission intensity labels; the first emission intensity label corresponds to the first training wavelength one by one;

[0127] Specifically, step 211, a plurality of first acquisition data are obtained by performing big data acquisition on the organic molecular structure of the organic photovoltaic material of the light emitting equipment and the emission spectrum curve corresponding thereto and the temperature and light intensity information corresponding to the current curve through a plurality of data acquisition channels.

[0128] Here, the plurality of data acquisition channels of the embodiment of the present application at least include a plurality of public molecular databases in the field of organic photovoltaic materials, all public literatures and experimental databases in the field of organic photovoltaic materials;

[0129] The first acquisition data of the embodiment of the present application at least include a first acquisition structure, a first acquisition curve data sequence, a first acquisition temperature and a first acquisition light intensity; wherein the first acquisition structure is a molecular structure of an organic molecule, and the data structure thereof is consistent with the data structure type of the molecular structure M; the first acquisition curve data sequence is a discretized sampling point data sequence corresponding to the emission spectrum curve of the current organic molecule, which is composed of a plurality of first sampling points, each of which is composed of a sampling point wavelength and a sampling point emission intensity corresponding thereto; the first acquisition temperature and the first acquisition light intensity are respectively an environmental temperature and an environmental light intensity corresponding to the current emission spectrum curve;

[0130] Step 212, a round of traversal is performed on all first collection data; and in the round of traversal, the first collection data currently traversed is taken as the corresponding current collection data; the first collection structure, the first collection temperature and the first collection light intensity of the current collection data are taken as the corresponding first training molecular structure, the first training temperature and the first training light intensity; the wavelengths of each sampling point of the current collection data are taken as a corresponding first training wavelength, and the emission intensity of each sampling point is taken as a corresponding first emission intensity label; the obtained all first training wavelengths are sorted according to the sorting order of the first sampling points to obtain a corresponding first training wavelength sequence; the obtained all first emission intensity labels are sorted according to the sorting order of the first sampling points to obtain a corresponding first emission intensity label sequence; and a corresponding first data record is formed by the first training molecular structure, the first training temperature, the first training light intensity, the first training wavelength sequence and the first emission intensity label sequence corresponding to the current collection data; and at the end of the round of traversal, all the first data records obtained form a corresponding first data set;

[0131] Step 22, the emission intensity prediction model is trained according to the first data set;

[0132] Specifically, step 221, the first data set is divided into two sub-data sets according to a preset first segmentation ratio, which are denoted as a corresponding first training set and a first evaluation set;

[0133] Here, the first segmentation ratio of the embodiment of the application is a pre-set ratio parameter, for example, 8:2; the first training set and the first evaluation set are both composed of a plurality of first data records; the total number ratio of the records of the first training set and the first evaluation set satisfies the first segmentation ratio;

[0134] Step 222, the first data record of the first training set is taken as a corresponding current training record;

[0135] Step 223, the first training molecular structure, the first training temperature and the first training light intensity of the current training record are taken as the current molecular structure M, the temperature x and the light intensity y;

[0136] Step 224, the total number of the first training wavelengths of the current training record is counted to obtain a corresponding first total number N1; and a round of traversal is performed on the N1 first training wavelengths of the current training record; and in the round of traversal, the first training wavelength currently traversed is taken as the current wavelength z; the current molecular structure M, the temperature x, the light intensity y and the wavelength z are input into the emission intensity prediction model for emission intensity prediction processing, and the predicted emission intensity u output by this processing is taken as a corresponding predicted intensity y pre,j,1≤indexj≤N1; and taking the first emission intensity label in the current training record corresponding to the first training wavelength being currently traversed as a corresponding label intensity y tag,j ; and taking the predicted intensity y pre,j and the corresponding label intensity y tag,j as a corresponding first prediction-label pair (y pre,j , y tag,j );

[0137] Step 225, taking the obtained N1 first prediction-label pairs (y pre,j , y tag,j ) into a preset first model loss function L a ; and based on a preset first model optimizer, modulating the model parameters of the emission intensity prediction model in a direction of making the first model loss function L a reach a minimum value;

[0138] Here, the first model loss function L a of the embodiment of the application is:

[0139]

[0140] The first model optimizer of the embodiment of the application at least includes an Adam optimizer, an SGD optimizer;

[0141] Step 226, identifying whether the current training record is the last first data record of the first training set, if yes, going to step 227, if not, taking the next first data record of the first training set as a new current training record and returning to step 223 to continue training;

[0142] Step 227, traversing all first data records of the first evaluation set for one round; and in the process of the round of traversal, taking the first data record being currently traversed as a corresponding current evaluation record; and taking the first training molecular structure, the first training temperature and the first training illumination intensity of the current evaluation record as the current molecular structure M, the temperature x and the illumination intensity y; and taking each first training wavelength of the current evaluation record in turn as a corresponding current wavelength z, and inputting the current molecular structure M, the temperature x, the illumination intensity y and the wavelength z into the emission intensity prediction model to perform emission intensity prediction processing and taking the predicted emission intensity u output by the processing as a corresponding first predicted intensity; and taking the first emission intensity label in the current evaluation record corresponding to each first predicted intensity as a corresponding first label intensity; and taking each first predicted intensity of the current evaluation record and the corresponding first label intensity as a corresponding second prediction-label pair;

[0143] Step 228, after the end of the current round of traversal of all first data records in the first evaluation set, the total number of the obtained second prediction-label pairs is counted to obtain a corresponding second total number N2; and the first prediction strength and the first label strength of each second prediction-label pair are recorded as a corresponding group of prediction strengths y pre,k and label strengths y tag,k , 1≤index k≤N2; and the obtained N2 groups of prediction strengths y pre,k and label strengths y tag,k are brought into a preset first model evaluation function S a to obtain a corresponding first evaluation value;

[0144] Here, the first model evaluation function S a of the embodiment of the application is:

[0145]

[0146] Step 229, whether the first evaluation value satisfies a preset first evaluation value range is identified; if not, the step 222 is returned to continue training; if yes, the training is stopped and it is confirmed that the model training is ended.

[0147] Here, the first evaluation value range of the embodiment of the application is a pre-set numerical range.

[0148] Step 3, after the model training is ended, a prediction analysis task input by a user is received and a corresponding task type and task configuration parameter are extracted therefrom.

[0149] Here, the prediction analysis task of the embodiment of the application includes a task type and a task configuration parameter; wherein the task type includes a first type, a second type and a third type; and the specific parameter content of the task configuration parameter has a corresponding relationship with the specific type of the task type:

[0150] 1) when the task type is the first type, the corresponding task configuration parameter includes a first molecular structure, a first set temperature, a first light intensity sequence and a first wavelength sequence; the data structure type of the first molecular structure is consistent with the data structure type of the molecular structure M; the first light intensity sequence is sorted by multiple first light intensities in the order of intensity from small to large; and the first wavelength sequence is sorted by multiple first wavelengths in the order of wavelength from small to large;

[0151] when the task type is the second type, the corresponding task configuration parameter includes a second molecular structure, a first set light intensity, a first temperature sequence and a second wavelength sequence; the data structure type of the second molecular structure is consistent with the data structure type of the molecular structure M; the first temperature sequence is sorted by multiple first temperatures in the order of temperature from low to high; and the second wavelength sequence is sorted by multiple second wavelengths in the order of wavelength from small to large;

[0152] When the task type is the third type, the corresponding task configuration parameters include a third molecular structure, a fourth molecular structure, a second set temperature, a second set light intensity, and a third wavelength sequence; the data structure types of the third and fourth molecular structures are consistent with the data structure type of the molecular structure M; and the third wavelength sequence is sorted by multiple third wavelengths in ascending order of wavelength.

[0153] Step 4, if the task type is the first type, under the set conditions that multiple temperatures are consistent but light intensities are different, multiple emission spectrum curves of a specified molecule are predicted based on the emission intensity prediction model and the task configuration parameters, and data analysis is performed on the maximum peak point, the full width at half maximum, and the half maximum wavelength range of each predicted curve to obtain a corresponding first analysis data table;

[0154] The first analysis data table is composed of multiple first analysis data records; the record fields of the first analysis data record include a molecular structure field, a temperature field, a light intensity field, a curve data sequence field, a maximum peak point field, a full width at half maximum field, and a half maximum wavelength range field; and the total number of the first analysis data records is consistent with the total number of the first light intensities of the corresponding first light intensity sequence;

[0155] Specifically, step 41 includes: extracting the corresponding first molecular structure, first set temperature, first light intensity sequence, and first wavelength sequence from the current task configuration parameters; taking the first molecular structure and the first set temperature as the current molecular structure M and temperature x; and counting the total number of the first light intensities of the first light intensity sequence to obtain the corresponding total number N R1 ;

[0156] Step 42 includes: taking each first light intensity of the first light intensity sequence as the corresponding current light intensity y in turn; performing a round of traversal on all first wavelengths of the first wavelength sequence; taking the currently traversed first wavelength as the corresponding current wavelength z during the round of traversal; inputting the current molecular structure M, temperature x, light intensity y, and wavelength z into the emission intensity prediction model for emission intensity prediction processing, and taking the predicted emission intensity u output by the processing as a corresponding current predicted emission intensity; taking the current wavelength z and the current predicted emission intensity as a set of corresponding curve point wavelength and curve point emission intensity to form a corresponding curve point; and when the round of traversal ends, taking all curve points corresponding to the current light intensity y to form a corresponding curve data sequence in ascending order of curve point wavelength.

[0157] Step 43 includes: taking the N R1a first analysis data record corresponding to the first molecular structure, the first set temperature, the first light intensity, the first curve data sequence, the current maximum peak position, the current full width at half maximum, and the current half peak wavelength range; and the first analysis data table is composed of the N first analysis data records.

[0158] Step 44, and after the N R1 first analysis data records are obtained, the N R1 first analysis data records are used to form a corresponding first analysis data table.

[0159] Figure 3 The data structure of the first analysis data table, the second analysis data table, and the third analysis data table provided by the first embodiment of the present application is shown in the figure, which can be intuitively understood by the data structure of the first analysis data table obtained by the first embodiment of the present application. Figure 3

[0160] Step 5, if the task type is the second type, under the set condition that the multiple light intensities are consistent but the temperatures are different, the multiple emission spectrum curves of a specified molecule are predicted based on the emission intensity prediction model and the task configuration parameters, and the maximum peak position, the full width at half maximum, and the half peak wavelength range of each predicted curve are analyzed to obtain a corresponding second analysis data table.

[0161] The second analysis data table is composed of multiple second analysis data records, and the record fields of the second analysis data record include a molecular structure field, a temperature field, a light intensity field, a curve data sequence field, a maximum peak position field, a full width at half maximum field, and a half peak wavelength range field. The total number of the second analysis data records is consistent with the total number of the first temperatures of the first temperature sequence.

[0162] Specifically, step 51 includes: extracting the second molecular structure, the first set light intensity, the first temperature sequence, and the second wavelength sequence from the current task configuration parameters; taking the first molecular structure and the first set light intensity as the current molecular structure M and the light intensity y; and counting the total number of the first temperatures of the first temperature sequence to obtain the total number N R2 .​

[0163] Step 52: The first temperatures of the first temperature sequence are sequentially used as the corresponding current temperatures x; all second wavelengths of the second wavelength sequence are iterated once; during this iteration, the currently iterated second wavelength is used as the corresponding current wavelength z; the current molecular structure M, temperature x, light intensity y, and wavelength z are input into the emission intensity prediction model for emission intensity prediction processing, and the predicted emission intensity u output by this processing is used as a corresponding current predicted emission intensity; the current wavelength z and the current predicted emission intensity are used as a set of corresponding curve point wavelengths and curve point emission intensities to form a corresponding curve point; at the end of this iteration, all curve points corresponding to the current temperature x are sorted in ascending order of curve point wavelength to form a corresponding curve data sequence.

[0164] Step 53, and for N of the first temperature sequence R2 The system iterates through the first temperature once; during this iteration, the first temperature is taken as the current temperature; the first molecular structure, the first set light intensity, and the curve data sequence corresponding to the current temperature are taken as the current molecular structure, the current set light intensity, and the current curve data sequence; based on the current curve data sequence, the maximum peak position, full width at half maximum (FWHM), and half-peak wavelength range are analyzed to obtain the current maximum peak position, current FWHM, and current half-peak wavelength range; and the current molecular structure, current temperature, current set light intensity, current curve data sequence, current maximum peak position, current FWHM, and current half-peak wavelength range are taken as the corresponding molecular structure field, temperature field, light intensity field, curve data sequence field, maximum peak position field, FWHM field, and half-peak wavelength range field to form a corresponding second analysis data record;

[0165] Step 54, and in the N of the first temperature sequence R2 At the end of this round of traversal of the first temperature, the obtained N R2 Each second analysis data record forms a corresponding second analysis data table.

[0166] This can be accessed via Figure 3 The data structure of the second analysis data table obtained in the embodiments of the present invention can be intuitively understood.

[0167] Step 6: If the task type is the third type, under the condition that the temperature and light intensity are kept consistent, the emission spectrum curves of the two specified molecules are predicted separately based on the emission intensity prediction model and the task configuration parameters, and the maximum peak position, full width at half maximum (FWHM), and wavelength range of the two predicted curves are analyzed to obtain the corresponding third analysis data table.

[0168] The third analysis data table is composed of two third analysis data records; the record field of the third analysis data record is composed of a molecular structure field, a temperature field, an illumination intensity field, a curve data sequence field, a maximum peak point field, a full width at half maximum field, and a half peak wavelength range field; and the two third analysis data records correspond to the third and fourth molecular structures one by one.

[0169] Specifically, step 61 extracts the corresponding third and fourth molecular structures, the second set temperature, the second set illumination intensity, and the third wavelength sequence from the current task configuration parameters; and takes the second set temperature and the second set illumination intensity as the current temperature x and the current illumination intensity y.

[0170] Step 62 takes the third and fourth molecular structures as the corresponding current molecular structure M in turn; performs a round of traversal on all third wavelengths of the third wavelength sequence; takes the current third wavelength being traversed as the corresponding current wavelength z during the round of traversal; inputs the current molecular structure M, the temperature x, the illumination intensity y, and the wavelength z into the emission intensity prediction model to perform emission intensity prediction processing, and takes the predicted emission intensity u output by the processing as a corresponding current predicted emission intensity; and takes the current wavelength z and the current predicted emission intensity as a group of corresponding curve point wavelength and curve point emission intensity to form a corresponding curve point; and sorts all curve points corresponding to the current molecular structure M in ascending order of curve point wavelength to form a corresponding curve data sequence when the round of traversal ends.

[0171] Step 63 takes the third and fourth molecular structures as the corresponding current molecular structure in turn; takes the second set temperature, the second set illumination intensity, and the curve data sequence corresponding to the current molecular structure as the corresponding current set temperature, the current set illumination intensity, and the current curve data sequence; performs maximum peak point, full width at half maximum, and half peak wavelength range analysis based on the current curve data sequence to obtain the corresponding current maximum peak point, the current full width at half maximum, and the current half peak wavelength range; and takes the current molecular structure, the current set temperature, the current set illumination intensity, the current curve data sequence, the current maximum peak point, the current full width at half maximum, and the current half peak wavelength range as the corresponding molecular structure field, the temperature field, the illumination intensity field, the curve data sequence field, the maximum peak point field, the full width at half maximum field, and the half peak wavelength range field to form a corresponding third analysis data record.

[0172] Step 64 forms a corresponding third analysis data table from the two obtained third analysis data records.

[0173] Here, the third analysis data table can be obtained by Figure 3 The data structure of the third analysis data table obtained by the embodiment of the present application can be intuitively understood.

[0174] It should be noted that in sub-step 43 of step 4, sub-step 53 of step 5, and sub-step 63 of step 6, the same technique for analyzing the maximum peak position, full width at half maximum (FWHM), and wavelength range at half WHM based on the curve data sequence was used. The detailed processing steps of this technique are as follows:

[0175] Based on the current curve data sequence, the analysis of the maximum peak position, full width at half maximum (FWHM), and wavelength range at FWHM yields the corresponding current maximum peak position, current FWHM, and current wavelength range at FWHM. Specifically, this includes:

[0176] Step A1: Construct a two-dimensional coordinate plane with emission intensity I as the ordinate and wavelength λ as the abscissa as the corresponding emission spectrum curve plane; and perform two-dimensional curve fitting on the emission spectrum curve plane based on the current curve data sequence, and use the fitted curve as the corresponding current emission spectrum curve;

[0177] Figure 4 This is a schematic diagram of the emission spectrum curve, maximum peak location, left half-peak location, right half-peak location, full width at half maximum (FWHM), and wavelength range at half WHM provided in Embodiment 1 of the present invention. This can be based on... Figure 4 To gain an intuitive understanding of the emission spectrum curve plane and the current emission spectrum curve;

[0178] Step A2, and take the site with the highest emission intensity on the current emission spectrum curve as the corresponding maximum peak site P. max ; and the maximum peak point P max The corresponding emission intensity and wavelength are denoted as the corresponding emission intensity I. max and wavelength λ max ;

[0179] Here, it can be based on Figure 4 For the maximum peak point P max and its corresponding emission intensity I max and wavelength λ max To gain an intuitive understanding;

[0180] Step A3, and then select the maximum peak location P on the current emission spectrum curve. max The curves on the left and right sides are denoted as the corresponding left curve and right curve, respectively; and the emission intensity on the left and right curves is I. max The curve points of / 2 are recorded as the corresponding left and right candidate points; and the distance from the maximum peak point P is... max The furthest left candidate site is designated as the corresponding left half peak site p1, and the site is located at the maximum distance from the peak site P. maxThe farthest right candidate site is taken as the corresponding right half-peak site p2; the corresponding wavelengths of the left and right half-peak sites p1 and p2 are recorded as the corresponding wavelengths λ1 and λ2; the wavelength range width between the wavelengths λ1 and λ2 is identified to obtain the corresponding half-peak full width W = λ2-λ1; and the wavelength range with the wavelengths λ1 and λ2 as the left and right boundaries is taken as the corresponding half-peak wavelength range [λ1, λ2];

[0181] Here, the user can identify the corresponding relationship between the emission spectrum curve shape and the environmental illumination intensity based on the first analysis data table, and directly analyze whether the emission spectrum curve of the current organic molecule will be blue / red shifted and the corresponding blue / red shift trend in the case that the environmental illumination intensity changes; the user can identify the corresponding relationship between the emission spectrum curve shape and the environmental temperature based on the second analysis data table, and directly analyze whether the emission spectrum curve of the current organic molecule will be blue / red shifted and the corresponding blue / red shift trend in the case that the environmental temperature changes; and the user can identify the differentiated characteristics of the emission spectrum curve shape and the maximum emission intensity / maximum peak position / half-peak full width / half-peak wavelength range of the two kinds of organic molecules corresponding to the third and fourth molecular structures based on the third analysis data table, and directly compare the light emission properties of the two kinds of organic molecules based on the differentiated characteristics. Figure 4 The left half-peak site p1 and the corresponding wavelength λ1, the right half-peak site p2 and the corresponding wavelength λ2, the half-peak full width W, and the half-peak wavelength range [λ1, λ2] are intuitively understood.

[0182] Step A4, and the maximum peak site P max obtained this time is taken as the corresponding current maximum peak site, the current half-peak full width, and the current half-peak wavelength range.

[0183] Step 7, the first, second, or third analysis data table obtained this time is fed back to the current user.

[0184] Here, the user can identify the corresponding relationship between the emission spectrum curve shape and the environmental illumination intensity based on the first analysis data table, and directly analyze whether the emission spectrum curve of the current organic molecule will be blue / red shifted and the corresponding blue / red shift trend in the case that the environmental illumination intensity changes; the user can identify the corresponding relationship between the emission spectrum curve shape and the environmental temperature based on the second analysis data table, and directly analyze whether the emission spectrum curve of the current organic molecule will be blue / red shifted and the corresponding blue / red shift trend in the case that the environmental temperature changes; and the user can identify the differentiated characteristics of the emission spectrum curve shape and the maximum emission intensity / maximum peak position / half-peak full width / half-peak wavelength range of the two kinds of organic molecules corresponding to the third and fourth molecular structures based on the third analysis data table, and directly compare the light emission properties of the two kinds of organic molecules based on the differentiated characteristics.

[0185] Figure 5 A module structure diagram of an emission spectrum curve prediction and analysis device provided for the second embodiment of the present application, the device being a terminal device or a server for implementing the foregoing method embodiments, or a device capable of enabling the foregoing terminal device or server to implement the foregoing method embodiments, for example, the device can be a device or a chip system of the foregoing terminal device or server. As shown in FIG. 2, the device comprises a data receiving module 21, a data processing module 22, and a data output module 23.Figure 5 As shown, the device comprises a model construction module 201, a model training module 202, a prediction analysis task data receiving module 203, a prediction analysis task processing module 204, and a prediction analysis task feedback module 205.

[0186] The model construction module 201 is configured to construct an emission intensity prediction model for performing emission intensity prediction; the emission intensity prediction model is configured to perform emission intensity prediction processing according to the model input molecular structure M, temperature x, illumination intensity y, and wavelength z, and output the corresponding predicted emission intensity u.

[0187] The model training module 202 is configured to construct a first data set for model training through data acquisition; and perform model training on the emission intensity prediction model according to the first data set.

[0188] The prediction analysis task data receiving module 203 is configured to receive a prediction analysis task input by a user after the model training is completed, and extract the corresponding task type and task configuration parameters therefrom; the prediction analysis task comprises the task type and the task configuration parameters; the task type comprises a first type, a second type, and a third type; when the task type is the first type, the corresponding task configuration parameters comprise a first molecular structure, a first set temperature, a first illumination intensity sequence, and a first wavelength sequence; when the task type is the second type, the corresponding task configuration parameters comprise a second molecular structure, a first set illumination intensity, a first temperature sequence, and a second wavelength sequence; when the task type is the third type, the corresponding task configuration parameters comprise a third molecular structure, a fourth molecular structure, a second set temperature, a second set illumination intensity, and a third wavelength sequence.

[0189] The prediction analysis task processing module 204 is configured to, when the task type is the first type, under the set condition that multiple temperatures are consistent but illumination intensities are different, perform prediction on multiple emission spectrum curves of a specified molecule based on the emission intensity prediction model and the task configuration parameters, and perform data analysis on the maximum peak point, full width at half maximum, and half maximum wavelength range of each predicted curve to obtain a corresponding first analysis data table.

[0190] The prediction analysis task processing module 204 is further configured to, when the task type is the second type, under the set condition that multiple illumination intensities are consistent but temperatures are different, perform prediction on multiple emission spectrum curves of a specified molecule based on the emission intensity prediction model and the task configuration parameters, and perform data analysis on the maximum peak point, full width at half maximum, and half maximum wavelength range of each predicted curve to obtain a corresponding second analysis data table.

[0191] The prediction analysis task processing module 204 is further configured to, when the task type is the third type, under the set condition that the temperature and the illumination intensity remain consistent, respectively predict the emission spectrum curves of the two specified molecules based on the emission intensity prediction model and the task configuration parameters, and perform data analysis on the maximum peak points, the full width at half maximum and the half peak wavelength range of the two predicted curves to obtain corresponding third analysis data tables.

[0192] The prediction analysis task feedback module 205 is configured to feed back the first, second or third analysis data table obtained this time to the current user.

[0193] The prediction analysis device for the emission spectrum curve provided by the embodiment of the present application can execute the method steps in the method embodiment, and has similar implementation principles and technical effects, which will not be described here again.

[0194] It should be noted that the division of each module of the above device is only a logical function division, and all or part of the modules can be integrated into one physical entity, or can be physically separated. Moreover, the modules can all be implemented in the form of software called by a processing element; or all be implemented in the form of hardware; or part of the modules are implemented in the form of software called by a processing element, and part of the modules are implemented in the form of hardware. For example, the model construction module can be a separately set processing element, or can be integrated in a chip of the above device, in addition, the model construction module can also be stored in the form of program code in the memory of the above device, and the function of the model construction module is called and executed by a processing element of the above device. The implementation of other modules is similar. Moreover, all or part of the modules can be integrated together, or can be independently implemented. The processing element described herein can be an integrated circuit having a signal processing capability. In the implementation process, each step of the above method or each module can be completed by the integrated logic circuit of hardware or the instruction of software in the processing element.

[0195] For example, the above modules can be one or more integrated circuits configured to implement the above methods, such as one or more Application Specific Integrated Circuits (ASICs), or one or more Digital Signal Processors (DSPs), or one or more Field Programmable Gate Arrays (FPGAs), etc. For another example, when a certain module above is implemented in the form of a processing element scheduling code, the processing element can be a general purpose processor, such as a Central Processing Unit (CPU) or other processor that can invoke code. For another example, the modules can be integrated together to implement in the form of a System-on-a-chip (SOC).

[0196] In the above embodiments, all or part of the embodiments can be implemented by software, hardware, firmware or any combination thereof. When implemented by software, all or part of the embodiments can be implemented in the form of a computer program product. The computer program product includes one or more computer instructions. When loaded and executed by a computer, the computer program instructions generate the processes or functions described in the above method embodiments, all or part of the computer can be a general purpose computer, a special purpose computer, a computer network, or other programmable devices. The above computer instructions can be stored in a computer readable storage medium or transmitted from one computer readable storage medium to another computer readable storage medium, for example, the computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center through wired (such as coaxial cable, optical fiber, Digital Subscriber Line (DSL)) or wireless (such as infrared, wireless, Bluetooth, microwave, etc.) mode. The above computer readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server, data center, etc. integrated with one or more available media. The above available medium can be a magnetic medium (such as a floppy disk, a hard disk, a magnetic tape), an optical medium (such as a DVD), or a semiconductor medium (such as a solid state disk (SSD)), etc.

[0197] Figure 6 A structural schematic diagram of an electronic device is provided for Embodiment Three of the present application. The electronic device can be a terminal device or a server that implements the method of the above embodiments, or a terminal device or a server connected to the terminal device or the server that implements the method of the above embodiments. As shown in FIG. 3, the electronic device includes a processor 301, a memory 302, a transceiver 303 and the like. The processor 301 can be a general purpose processor, such as a Central Processing Unit (CPU) or other processor that can invoke code. The memory 302 can be a computer readable storage medium, such as a volatile memory (e.g., a random access memory (RAM)) and / or a non-volatile memory (e.g., a read-only memory (ROM), a hard disk, a solid state disk, or a floppy disk). The transceiver 303 can be configured to transmit and / or receive data, and can include a transmitter and / or a receiver. The transceiver 303 can be configured to transmit and / or receive data via a wired (such as a coaxial cable, an optical fiber, a Digital Subscriber Line (DSL)) or a wireless (such as infrared, wireless, Bluetooth, microwave, etc.) mode. Figure 6As shown, the electronic device can include a processor 301 (such as a CPU), a memory 302, a transceiver 303; the transceiver 303 is coupled to the processor 301, and the processor 301 controls the transceiving action of the transceiver 303. The memory 302 can store various instructions for completing various processing functions and implementing the processing steps described in the foregoing embodiment method description. Preferably, the electronic device related to the embodiments of the present application further includes a power supply 304, a system bus 305, and a communication port 306. The system bus 305 is used to realize the communication connection between elements. The above-mentioned communication port 306 is used for connection communication between the electronic device and other peripherals.

[0198] In Figure 6 The system bus 305 mentioned in the foregoing can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. The system bus can be divided into an address bus, a data bus, a control bus, etc. For the sake of representation, only one thick line is used in the figure, but it does not mean that there is only one bus or one type of bus. The communication interface is used to realize the communication between the database access device and other devices (such as a client, a read-write library and a read-only library). The memory can contain a Random Access Memory (RAM), and can also include a Non-Volatile Memory, such as at least one disk memory.

[0199] The above-mentioned processor can be a general-purpose processor, including a Central Processing Unit (CPU), a Network Processor (NP), a Graphics Processing Unit (GPU), etc.; can also be a Digital Signal Processor (DSP), an Application-Specific Integrated Circuit (ASIC), a Field-Programmable Gate Array (FPGA) or other programmable logic device, a discrete gate or transistor logic device, a discrete hardware component.

[0200] It should be noted that the embodiments of the present application also provide a computer readable storage medium, which stores instructions, when running on a computer, causes the computer to execute the method and processing procedure provided in the above embodiments.

[0201] The embodiment of the present application provides a prediction analysis method and device of emission spectrum curve, electronic equipment and computer readable storage medium. From the above content, it can be known that the embodiment of the present application customizes an emission intensity prediction model for predicting the emission intensity according to the model input of molecular structure, temperature, illumination intensity and wavelength, and trains the emission intensity prediction model through a first data set obtained by big data collection; and after the training is completed, a prediction analysis task (composed of a task type and a task configuration parameter) input by a user is analyzed; if the task type is the first type, then under the setting condition that multiple temperatures are consistent but illumination intensities are different, multiple emission spectrum curves of a specified molecule are predicted based on the emission intensity prediction model and the task configuration parameter, and three types of curve characteristics (maximum peak point, full width at half maximum and half peak wavelength range) of each predicted curve are analyzed to obtain a first analysis data table to feed back to the current user; if the task type is the second type, then under the setting condition that multiple illumination intensities are consistent but temperatures are different, multiple emission spectrum curves of a specified molecule are predicted based on the emission intensity prediction model and the task configuration parameter, and three types of curve characteristics of each predicted curve are analyzed to obtain a second analysis data table to feed back to the current user; if the task type is the third type, then under the setting condition that the temperature and the illumination intensity are consistent, the emission spectrum curves of two specified molecules are respectively predicted based on the emission intensity prediction model and the task configuration parameter, and three types of curve characteristics of two predicted curves are analyzed to obtain a third analysis data table to feed back to the current user. On the one hand, the embodiment of the present application reduces the processing complexity of the prediction analysis task, shortens the processing time and improves the processing efficiency through a customized emission intensity prediction model; on the other hand, the data analysis convenience is improved through three types of customized emission spectrum curve analysis means.

[0202] The steps of a method or algorithm described in connection with the embodiments disclosed herein can be embodied directly in hardware, in a software module executed by a processor, or in a combination of the two. A software module can reside in random access memory (RAM), flash memory, read-only memory (ROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), registers, hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.

[0203] The above specific embodiments further illustrate the purpose, technical solutions and beneficial effects of the present application, and it should be understood that the above specific embodiments are only specific embodiments of the present application and are not used to limit the protection scope of the present application, and any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A method of predictive analysis of an emission spectrum profile, characterized in that, The method comprises: constructing an emission intensity prediction model for performing emission intensity prediction; the emission intensity prediction model is used for performing emission intensity prediction processing according to model input molecular structure M, temperature x, light intensity y and wavelength z and outputting corresponding predicted emission intensity u; constructing a first data set for model training through data acquisition; and performing model training on the emission intensity prediction model according to the first data set; after the model training is completed, receiving a user input prediction analysis task and extracting a corresponding task type and task configuration parameter therefrom; the prediction analysis task comprises the task type and the task configuration parameter; the task type comprises a first type, a second type and a third type; when the task type is the first type, the corresponding task configuration parameter comprises a first molecular structure, a first set temperature, a first light intensity sequence and a first wavelength sequence; when the task type is the second type, the corresponding task configuration parameter comprises a second molecular structure, a first set light intensity, a first temperature sequence and a second wavelength sequence; when the task type is the third type, the corresponding task configuration parameter comprises a third molecular structure, a fourth molecular structure, a second set temperature, a second set light intensity and a third wavelength sequence; if the task type is the first type, under the set condition that multiple temperatures are consistent but light intensities are different, multiple emission spectrum curves of a specified molecule are predicted based on the emission intensity prediction model and the task configuration parameter, and maximum peak points, full-width-at-half-maximum and half-peak wavelength ranges of each predicted curve are analyzed to obtain corresponding first analysis data table; if the task type is the second type, under the set condition that multiple light intensities are consistent but temperatures are different, multiple emission spectrum curves of a specified molecule are predicted based on the emission intensity prediction model and the task configuration parameter, and maximum peak points, full-width-at-half-maximum and half-peak wavelength ranges of each predicted curve are analyzed to obtain corresponding second analysis data table; if the task type is the third type, under the set condition that temperature and light intensity are consistent, emission spectrum curves of two specified molecules are respectively predicted based on the emission intensity prediction model and the task configuration parameter, and maximum peak points, full-width-at-half-maximum and half-peak wavelength ranges of the two predicted curves are analyzed to obtain corresponding third analysis data table; the first, second or third analysis data table obtained this time is fed back to the current user.

2. The emission spectrum curve prediction analysis method according to claim 1, characterized in that, The molecular structure M includes a plurality of atoms m i , 1≤atom index i≤N M , N M is the total number of atoms of the molecular structure M; each atom parameter of the atoms m i is composed of a corresponding atom type and three-dimensional atomic coordinates; The first data set includes a plurality of first data records; the first data record includes a first training molecular structure, a first training temperature, a first training light intensity, a first training wavelength sequence, and a first emission intensity label sequence; the data structure type of the first training molecular structure is consistent with the data structure type of the molecular structure M; the first training wavelength sequence is composed of a plurality of first training wavelengths; the first emission intensity label sequence is composed of a plurality of first emission intensity labels; the first emission intensity label corresponds to the first training wavelength one by one; When the task type is the first type, the first light intensity sequence of the task configuration parameter is sorted in order of intensity from small to large by a plurality of first light intensities; when the task type is the second type, the first temperature sequence of the task configuration parameter is sorted in order of temperature from low to high by a plurality of first temperatures; when the task type is the first, second or third type, the corresponding first, second or third wavelength sequence in the task configuration parameter is sorted in order of wavelength from small to large by a plurality of corresponding first, second or third wavelengths; The data structure types of the first, second, third and fourth molecular structures are consistent with the data structure type of the molecular structure M; The first analysis data table is composed of a plurality of first analysis data records; the record field of the first analysis data record is composed of a molecular structure field, a temperature field, a light intensity field, a curve data sequence field, a maximum peak point field, a full width at half maximum field, and a half peak wavelength range field; the total number of records of the first analysis data record is consistent with the total number of the first light intensity of the corresponding first light intensity sequence; The second analysis data table is composed of a plurality of second analysis data records; the record field of the second analysis data record is composed of a molecular structure field, a temperature field, a light intensity field, a curve data sequence field, a maximum peak point field, a full width at half maximum field, and a half peak wavelength range field; the total number of records of the second analysis data record is consistent with the total number of the first temperature of the corresponding first temperature sequence; The third analysis data table is composed of two third analysis data records; the record field of the third analysis data record is composed of a molecular structure field, a temperature field, a light intensity field, a curve data sequence field, a maximum peak point field, a full width at half maximum field, and a half peak wavelength range field; the two third analysis data records correspond to the third and fourth molecular structures one by one.

3. The emission spectrum curve prediction analysis method according to claim 1, wherein the first model input end of the emission intensity prediction model is used to receive the model input of the molecular structure M, the second model input end is used to receive the model input of the temperature x, the third model input end is used to receive the model input of the light intensity y, and the fourth model input end is used to receive the model input of the wavelength z; the model output end of the emission intensity prediction model is used to output the corresponding predicted emission intensity u. The emission intensity prediction model comprises an embedding coding module, a molecular structure coding module, a first Gaussian kernel module, a first vector mapping module, a second Gaussian kernel module, a second vector mapping module, a third Gaussian kernel module, a third vector mapping module, a feature fusion module, and an emission intensity prediction module; the molecular structure coding module is realized based on a Uni-Mol model or a type of graph neural network satisfying SE(3) equivariance; the first, second, and third vector mapping modules and the emission intensity prediction module are all realized based on an MLP model; The input end of the embedding coding module is connected with the first model input end, and the output end is connected with the input end of the molecular structure coding module; the output end of the molecular structure coding module is connected with the first input end of the feature fusion module; the input end of the first Gaussian kernel module is connected with the second model input end, and the output end is connected with the input end of the first vector mapping module; the output end of the first vector mapping module is connected with the second input end of the feature fusion module; the input end of the second Gaussian kernel module is connected with the third model input end, and the output end is connected with the input end of the second vector mapping module; the output end of the second vector mapping module is connected with the third input end of the feature fusion module; the input end of the third Gaussian kernel module is connected with the fourth model input end, and the output end is connected with the input end of the third vector mapping module; the output end of the third vector mapping module is connected with the fourth input end of the feature fusion module; the output end of the feature fusion module is connected with the input end of the emission intensity prediction module; the output end of the emission intensity prediction module is connected with the model output end; The embedding encoding module is used to encode the molecular structure M input to the model according to the embedding encoding rules of the molecular structure encoding module and send the encoding result to the molecular structure encoding module. Specifically, when the molecular structure encoding module is implemented based on the Uni-Mol model, the embedding encoding module encodes each atom m of the molecular structure M according to the atom type one-hot encoding rules of the Uni-Mol model. i Perform one-hot encoding of the atom type to obtain the corresponding atom encoding vector, and then use the obtained N... M The aforementioned atomic encoding vectors form a corresponding atomic encoding tensor, and the encoding is performed according to the pairwise feature initialization rule of the Uni-Mol model based on the coordinates of all three-dimensional atoms of the molecular structure M to obtain a tensor with shape N. M ×N M The pairwise encoded tensors are obtained, and the obtained atom encoded tensors and the pairwise encoded tensors are sent to the molecular structure encoding module; the embedding encoding module, when the molecular structure encoding module is implemented based on a type of graph neural network that satisfies SE(3) equivariance, is composed of each atom m of the molecular structure M. i As the corresponding first node and obtained from N M Each of the first nodes forms a corresponding set of first nodes, and a directed edge is drawn from each of the first nodes to any other node, denoted as the corresponding first edge. The edge relationship of each first edge is set as two corresponding atoms m. i The coordinate difference vector between them, and obtained by N M ×(N M -1) The first edge forms a corresponding first edge set, and the obtained first node set and the first edge set form a corresponding first graph structure, which is sent to the molecular structure encoding module; When the molecular structure encoding module is based on the Uni-Mol model, the feature fusion module is configured to receive a corresponding hidden feature tensor H from the atomic feature and pair feature extraction processing based on the input atomic encoding tensor and the pair encoding tensor; the hidden feature tensor H is composed of N M hidden feature vectors h i , and the hidden feature vector h i corresponds to the atom m i . When the molecular structure coding module is realized based on a type of graph neural network satisfying SE(3) equivariance, it is used for performing feature updating processing on the node features and edge features of each first node and each first edge in the input first graph structure through the message passing mechanism of the graph neural network to obtain the corresponding hidden feature tensor H and send it to the feature fusion module; The first Gaussian kernel module is used for presetting a plurality of first Gaussian kernel functions in the module; The first Gaussian kernel module is also used for performing corresponding kernel function calculation on the temperature x input to the model according to each first Gaussian kernel function, taking the calculated numerical result as a corresponding first result numerical value, and sending a corresponding temperature coding vector composed of all the first result numerical values to the first vector mapping module; the vector length of the temperature coding vector is consistent with the total number of the first Gaussian kernel functions; The first vector mapping module is configured to map the hidden feature vector h i The corresponding vector space is taken as a target vector space, and a corresponding temperature mapping vector is obtained by mapping the temperature coding vector to the target vector space and sent to the feature fusion module. The temperature mapping vector and the hidden feature vector h i have the same feature dimension. The second Gaussian kernel module is used for presetting a plurality of second Gaussian kernel functions in the module; The second Gaussian kernel module is further configured to perform kernel function calculation on the light intensity y of the model input according to each of the second Gaussian kernel functions, and take the calculated numerical result as a corresponding second result value; and a corresponding light intensity encoding vector is formed by all the obtained second result values, and is sent to the second vector mapping module; the vector length of the light intensity encoding vector is consistent with the total number of the second Gaussian kernel functions; The second vector mapping module is configured to map the hidden feature vector h i The corresponding vector space is taken as a target vector space, and a corresponding illumination intensity mapping vector is obtained by mapping the illumination intensity encoding vector to the target vector space and sent to the feature fusion module. The illumination intensity mapping vector and the hidden feature vector h i have consistent feature dimensions. The third Gaussian kernel module is configured to preset a plurality of third Gaussian kernel functions in the module; The third Gaussian kernel module is further configured to perform kernel function calculation on the wavelength z of the model input according to each of the third Gaussian kernel functions, and take the calculated numerical result as a corresponding third result value; and a corresponding wavelength encoding vector is formed by all the obtained third result values, and is sent to the third vector mapping module; the vector length of the wavelength encoding vector is consistent with the total number of the third Gaussian kernel functions; The third vector mapping module is configured to map the hidden feature vector h i The corresponding vector space is taken as a target vector space, and a corresponding wavelength mapping vector is obtained by mapping the wavelength encoding vector to the target vector space and sent to the feature fusion module. The wavelength mapping vector and the hidden feature vector h i have the same feature dimension. The feature fusion module is configured to sequentially splice each of the hidden feature vectors h of the hidden feature tensor H with the temperature mapping vector, the illumination intensity mapping vector and the wavelength mapping vector to obtain a corresponding fused feature vector r i i ; and send the N M i fused feature vectors r to the emission intensity prediction module.​​ The emission intensity prediction module is configured to perform emission intensity regression calculation according to the input fusion feature tensor R, and output the calculated result as a corresponding predicted emission intensity u.

4. The method of predictive analysis of emission spectral profiles according to claim 2, wherein, The first data set for model training is constructed through data collection, and specifically includes: Step 41, collecting a plurality of first collection data by collecting the organic molecular structure of the organic photovoltaic material of the light emitting device and the corresponding emission spectrum curve and the temperature and light intensity information corresponding to the current curve through a plurality of data collection channels; The plurality of data collection channels at least include a plurality of public molecular databases in the field of organic photovoltaic materials, all public literature and experimental databases in the field of organic photovoltaic materials; The first collection data at least includes first collection structure, first collection curve data sequence, first collection temperature and first collection light intensity; the first collection structure is the molecular structure of an organic molecule, and its data structure is consistent with the data structure type of the molecular structure M; the first collection curve data sequence is a discretized sampling point data sequence corresponding to the emission spectrum curve of the current organic molecule, which is composed of a plurality of first sampling points, each of which is composed of a sampling point wavelength and its corresponding sampling point emission intensity; the first collection temperature and the first collection light intensity are the ambient temperature and the ambient light intensity corresponding to the current emission spectrum curve, respectively; Step 42, a round of traversal is performed on all the first collection data; and during the round of traversal, the first collection data currently traversed is taken as corresponding current collection data; the first collection structure, the first collection temperature and the first collection light intensity of the current collection data are taken as corresponding first training molecular structure, first training temperature and first training light intensity; each sampling point wavelength of the current collection data is taken as a corresponding first training wavelength, and each sampling point emission intensity is taken as a corresponding first emission intensity label; all the first training wavelengths obtained are sorted in the order of the first sampling points to obtain a corresponding first training wavelength sequence; all the first emission intensity labels obtained are sorted in the order of the first sampling points to obtain a corresponding first emission intensity label sequence; the first training molecular structure, the first training temperature, the first training light intensity, the first training wavelength sequence and the first emission intensity label sequence corresponding to the current collection data form a corresponding first data record; and at the end of the round of traversal, all the first data records obtained form a corresponding first data set.

5. The method of predictive analysis of emission spectral profiles according to claim 2, wherein, The model training of the emission intensity prediction model according to the first data set specifically includes: Step 51, the first data set is divided into two sub-data sets based on a preset first segmentation ratio, which are denoted as a corresponding first training set and a first evaluation set; The first training set and the first evaluation set both consist of a plurality of first data records; the total number ratio of records of the first training set and the first evaluation set satisfies the first segmentation ratio; Step 52, the first data record of the first training set is taken as a corresponding current training record; Step 53, the first training molecular structure, the first training temperature and the first training light intensity of the current training record are taken as the current molecular structure M, the temperature x and the light intensity y; Step 54, count the total number of the first training wavelengths of the current training record to obtain a corresponding first total number N1; and perform a round of traversal on the N1 first training wavelengths of the current training record; and in the current round of traversal, take the first training wavelength currently traversed as the current wavelength z; and input the current molecular structure M, the temperature x, the light intensity y and the wavelength z into the emission intensity prediction model to perform emission intensity prediction processing, and take the predicted emission intensity u output by this processing as a corresponding predicted intensity y pre,j ,1≤index j≤N1; and take the first emission intensity label corresponding to the first training wavelength currently traversed in the current training record as a corresponding label intensity y tag,j ; and a corresponding first prediction-label pair (y pre,j , y tag,j ) is composed of the predicted intensity y pre,j and the corresponding label intensity y tag,j . Step 55, taking the obtained N1 first prediction-label pairs (y pre,j ,y tag,j ) into a preset first model loss function L a ; and based on a preset first model optimizer, performing a round of modulation on model parameters of the emission intensity prediction model in a direction of minimizing the first model loss function L a ; The first model loss function L a is: The first model optimizer at least includes an Adam optimizer and an SGD optimizer; Step 56, whether the current training record is the last first data record of the first training set is identified; if yes, step 57 is turned to; if not, the next first data record of the first training set is taken as a new current training record, and step 53 is returned to continue training; Step 57, a round of traversal is performed on all the first data records of the first evaluation set; during the round of traversal, the first data record currently traversed is taken as a corresponding current evaluation record; the first training molecular structure, the first training temperature and the first training light intensity of the current evaluation record are taken as the current molecular structure M, the temperature x and the light intensity y; each first training wavelength of the current evaluation record is taken in turn as a corresponding current wavelength z, and the current molecular structure M, the temperature x, the light intensity y and the wavelength z are input into the emission intensity prediction model for emission intensity prediction processing, and the predicted emission intensity u output by the processing is taken as a corresponding first predicted intensity; the first emission intensity label corresponding to each first predicted intensity in the current evaluation record is taken as a corresponding first label intensity; and each first predicted intensity of the current evaluation record and its corresponding first label intensity form a corresponding second prediction-label pair; Step 58, after the end of the current round of traversal of all the first data records of the first evaluation set, the total number of the second prediction-label pairs obtained is counted to obtain a corresponding second total number N2; and the first prediction strength and the first label strength of each second prediction-label pair are recorded as a corresponding group of prediction strengths y pre,k and label strengths y tag,k , 1≤index k≤N2; and the N2 groups of prediction strengths y pre,k and label strengths y tag,k obtained are brought into a preset first model evaluation function S a to obtain a corresponding first evaluation value; wherein the first model evaluation function S a is: Step 59, whether the first evaluation value meets a preset first evaluation value range is identified; if not, the training is continued in step 52; if yes, the training is stopped and it is confirmed that the model training is completed.

6. The method of predictive analysis of emission spectral profiles according to claim 2, wherein, The first analysis data table is obtained by predicting a plurality of emission spectrum curves of a specified molecule based on the emission intensity prediction model and the task configuration parameters, and performing data analysis on the maximum peak position, full width at half maximum and half maximum wavelength range of each predicted curve, specifically including: extracting the corresponding first molecular structure, the first set temperature, the first light intensity sequence and the first wavelength sequence from the current task configuration parameters; and taking the first molecular structure and the first set temperature as the current molecular structure M and the temperature x; and counting the total number of the first light intensity of the first light intensity sequence to obtain the corresponding total number N R1 ; each first wavelength of the first wavelength sequence is taken in turn as a corresponding current wavelength z; the current molecular structure M, the temperature x, the light intensity y and the wavelength z are input into the emission intensity prediction model for emission intensity prediction processing, and the predicted emission intensity u output by the processing is taken as a corresponding current predicted emission intensity; the current wavelength z and the current predicted emission intensity form a corresponding curve point position wavelength and curve point position emission intensity, and a corresponding curve point position is formed; when the round of traversal ends, all the curve point positions corresponding to the current light intensity y are sorted in ascending order of the curve point position wavelength to form a corresponding curve data sequence; and a round of traversal is performed on N R1 first light intensities of the first light intensity sequence; and during the round of traversal, the first light intensity being currently traversed is taken as a corresponding current light intensity; the first molecular structure, the first set temperature, and the curve data sequence corresponding to the current light intensity are taken as a corresponding current molecular structure, a current set temperature, and a current curve data sequence; maximum peak position, full width at half maximum, and half peak wavelength range analysis are performed based on the current curve data sequence to obtain a corresponding current maximum peak position, a current full width at half maximum, and a current half peak wavelength range; and the current molecular structure, the current set temperature, the current light intensity, the current curve data sequence, the current maximum peak position, the current full width at half maximum, and the current half peak wavelength range are taken as a corresponding molecular structure field, a temperature field, a light intensity field, a curve data sequence field, a maximum peak position field, a full width at half maximum field, and a half peak wavelength range field to form a corresponding first analysis data record. and after the end of the current round of iteration of N R1 first light intensity of the first light intensity sequence, the resulting N R1 first analysis data records form a corresponding first analysis data table.

7. The method of predictive analysis of emission spectral profiles according to claim 2, wherein, The second analysis data table is obtained by predicting a plurality of emission spectrum curves of a specified molecule based on the emission intensity prediction model and the task configuration parameters, and performing data analysis on the maximum peak position, full width at half maximum and half maximum wavelength range of each predicted curve, specifically including: extracting the corresponding second molecular structure, the first set light intensity, the first temperature sequence and the second wavelength sequence from the current task configuration parameters; and taking the first molecular structure and the first set light intensity as the current molecular structure M and the light intensity y; and counting the total number of the first temperatures of the first temperature sequence to obtain the corresponding total number N R2 ; and the second wavelength sequence is traversed; and during the current traversal, the second wavelength being currently traversed is taken as a corresponding current wavelength z; and the current molecular structure M, the temperature x, the light intensity y, and the wavelength z are input into the emission intensity prediction model for emission intensity prediction processing, and the predicted emission intensity u output by the current processing is taken as a corresponding current predicted emission intensity; and the current wavelength z and the current predicted emission intensity are taken as a set of corresponding curve point wavelength and curve point emission intensity to form a corresponding curve point; and when the current traversal ends, all the curve points corresponding to the current temperature x are sorted in ascending order of the curve point wavelength to form a corresponding curve data sequence; and a round of traversal is performed on N R2 first temperatures of the first temperature sequence; and during the round of traversal, the first temperature being currently traversed is taken as a corresponding current temperature; the first molecular structure, the first set light intensity, and the curve data sequence corresponding to the current temperature are taken as a corresponding current molecular structure, a current set light intensity, and a current curve data sequence; maximum peak position, full width at half maximum, and half peak wavelength range analysis are performed based on the current curve data sequence to obtain a corresponding current maximum peak position, a current full width at half maximum, and a current half peak wavelength range; and the current molecular structure, the current temperature, the current set light intensity, the current curve data sequence, the current maximum peak position, the current full width at half maximum, and the current half peak wavelength range are taken as a corresponding molecular structure field, a temperature field, a light intensity field, a curve data sequence field, a maximum peak position field, a full width at half maximum field, and a half peak wavelength range field to form a corresponding second analysis data record. and at the end of the current pass through N R2 first temperatures of the first temperature sequence, a corresponding second analysis data table is composed of the resulting N R2 second analysis data records.

8. The method of predictive analysis of emission spectral profiles according to claim 2, wherein, The emission spectrum curves of two specified molecules are predicted based on the emission intensity prediction model and the task configuration parameters, and the maximum peak point, full width at half maximum, and half maximum wavelength range of the two predicted curves are analyzed to obtain corresponding third analysis data, specifically including: The third molecular structure, the fourth molecular structure, the second set temperature, the second set light intensity, and the third wavelength sequence are extracted from the current task configuration parameters; and the second set temperature and the second set light intensity are taken as the current temperature x and the light intensity y; and the third, fourth molecular structure is taken in turn as a corresponding current molecular structure M; and all the third wavelengths of the third wavelength sequence are traversed; and during the current traversal, the third wavelength being currently traversed is taken as a corresponding current wavelength z; and the current molecular structure M, the temperature x, the light intensity y, and the wavelength z are input into the emission intensity prediction model for emission intensity prediction processing, and the predicted emission intensity u output by the current processing is taken as a corresponding current predicted emission intensity; and the current wavelength z and the current predicted emission intensity are taken as a set of corresponding curve point wavelength and curve point emission intensity to form a corresponding curve point; and when the current traversal ends, all the curve points corresponding to the current molecular structure M are sorted in ascending order of the curve point wavelength to form a corresponding curve data sequence; And the third, fourth molecular structure in turn as the corresponding current molecular structure; And the second set temperature, the second set of light intensity and the current molecular structure corresponding to the curve data sequence as the corresponding current set temperature, current set light intensity and current curve data sequence; And based on the current curve data sequence for maximum peak point, full width at half maximum and half peak wavelength range analysis to obtain the corresponding current maximum peak point, current full width at half maximum and current half peak wavelength range; And the current molecular structure, the current set temperature, the current set light intensity, the current curve data sequence, the current maximum peak point, the current full width at half maximum and the current half peak wavelength range as the corresponding molecular structure field, temperature field, light intensity field, curve data sequence field, maximum peak point field, full width at half maximum field and half peak wavelength range field to form a corresponding third analysis data record; And the two third analysis data records obtained form a corresponding third analysis data table.

9. The method of predictive analysis of emission spectral profiles according to any one of claims 6-8, characterized in that, The maximum peak point, full width at half maximum and half peak wavelength range analysis based on the current curve data sequence to obtain the corresponding current maximum peak point, current full width at half maximum and current half peak wavelength range, specifically includes: A two-dimensional coordinate plane is constructed as a corresponding emission spectrum curve plane with emission intensity I as the ordinate and wavelength λ as the abscissa; And based on the current curve data sequence, a two-dimensional curve fitting is performed on the emission spectrum curve plane, and the obtained fitting curve is taken as the corresponding current emission spectrum curve; and the maximum emission intensity site on the current emission spectrum curve is taken as the corresponding maximum peak site P max ; and the maximum peak site P max corresponding emission intensity and wavelength are recorded as the corresponding emission intensity I max and wavelength λ max ; and the curve point on the current emission spectrum curve at the maximum peak position P max The left and right curve portions are respectively recorded as the corresponding left curve and right curve; and the curve points on the left and right curves with the emission intensity I max / 2 are recorded as the corresponding left and right candidate points; and the left candidate point farthest from the maximum peak position P max is recorded as the corresponding left half-peak position p1, and the right candidate point farthest from the maximum peak position P max is recorded as the corresponding right half-peak position p2; and the corresponding wavelengths of the left and right half-peak positions p1 and p2 are recorded as the corresponding wavelengths λ1 and λ2; and the wavelength range width between the wavelengths λ1 and λ2 is identified to obtain the corresponding full width at half maximum W = λ2 - λ1; and the wavelength range with the wavelengths λ1 and λ2 as the left and right boundaries is recorded as the corresponding half-peak wavelength range [λ1, λ2]; and the maximum peak position P obtained this time is taken as the current maximum peak position P max the full width at half maximum W and the half peak wavelength range [λ1, λ2] are taken as the current full width at half maximum W and the current half peak wavelength range [λ1, λ2].

10. An apparatus for performing the method of predictive analysis of an emission spectrum curve according to any one of claims 1 to 9, characterized in that The device comprises a model construction module, a model training module, a prediction analysis task data receiving module, a prediction analysis task processing module and a prediction analysis task feedback module; The model construction module is used to construct an emission intensity prediction model for emission intensity prediction; The emission intensity prediction model is used to perform emission intensity prediction processing according to the model input molecular structure M, temperature x, light intensity y and wavelength z and output the corresponding predicted emission intensity u; The model training module is used to construct a first data set for model training through data acquisition; And the emission intensity prediction model is trained based on the first data set; The prediction analysis task data receiving module is used to receive the prediction analysis task input by the user after the model training is completed and extract the corresponding task type and task configuration parameters therefrom; The prediction analysis task comprises the task type and the task configuration parameters; The task type comprises a first type, a second type and a third type; When the task type is the first type, the corresponding task configuration parameters comprise a first molecular structure, a first set temperature, a first light intensity sequence and a first wavelength sequence; When the task type is the second type, the corresponding task configuration parameters comprise a second molecular structure, a first set light intensity, a first temperature sequence and a second wavelength sequence; When the task type is the third type, the corresponding task configuration parameters comprise a third molecular structure, a fourth molecular structure, a second set temperature, a second set light intensity and a third wavelength sequence; The prediction analysis task processing module is configured to, when the task type is a first type, predict a plurality of emission spectrum curves of a specified molecule based on the emission intensity prediction model and the task configuration parameters under a plurality of setting conditions in which the temperature is consistent but the illumination intensity is different, and perform data analysis on the maximum peak position, full width at half maximum, and half maximum wavelength range of each predicted curve to obtain a corresponding first analysis data table. The prediction analysis task processing module is further configured to, when the task type is a second type, predict a plurality of emission spectrum curves of a specified molecule based on the emission intensity prediction model and the task configuration parameters under a plurality of setting conditions in which the illumination intensity is consistent but the temperature is different, and perform data analysis on the maximum peak position, full width at half maximum, and half maximum wavelength range of each predicted curve to obtain a corresponding second analysis data table. The prediction analysis task processing module is further configured to, when the task type is a third type, predict emission spectrum curves of two specified molecules based on the emission intensity prediction model and the task configuration parameters under a setting condition in which the temperature and the illumination intensity are consistent, and perform data analysis on the maximum peak position, full width at half maximum, and half maximum wavelength range of the two predicted curves to obtain a corresponding third analysis data table. The prediction analysis task feedback module is configured to feed back the first, second, or third analysis data table obtained this time to the current user.

11. An electronic device, comprising: comprises: a memory, a processor, and a transceiver; the processor is configured to couple with the memory, read and execute instructions in the memory, to implement the method of any one of claims 1-9; the transceiver is coupled with the processor, and is controlled by the processor to perform message transceiving.

12. A computer-readable storage medium, characterized in that, The computer readable storage medium stores computer instructions, when the computer instructions are executed by a computer, the computer executes the method of any one of claims 1-9.

Images