Treatment method and device for structural optimization of electrolyte formula components

Abstract

The embodiment of the invention relates to a processing method and device for carrying out structure optimization on electrolyte formula components. The method comprises the following steps: constructing a structure optimization model; constructing a first data set and a second data set; performing pre-training based on the first data set, and performing tuning based on the second data set; after the optimization is finished, taking an electrolyte formula input by a user as a current electrolyte formula, performing corresponding three-dimensional molecular structure modeling according to each component molecular sequence of the current electrolyte formula, and performing three-dimensional structure optimization on each component modeling structure based on a structure optimization model; forming a corresponding formula component structure optimization record by each component molecular sequence, the corresponding component type and the component optimization structure; and forming a corresponding formula structure optimization report by all the obtained formula component structure optimization records, and feeding back the report to a user. According to the method, the influence of human factors on the molecular structure modeling quality can be reduced, and the modeling quality and the modeling efficiency are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a processing method and device for optimizing the structure of electrolyte formula components. Background Art

[0002] The electrolyte formula consists of three components: solvent, electrolyte and additive, and each component corresponds to a molecular structure. When designing and developing the electrolyte formula, it is necessary to analyze the various physical and chemical properties corresponding to the formula. The analysis process is roughly divided into the following steps: first, the molecular structure of each formula component of the electrolyte formula is three-dimensionally modeled through chemical informatics tools (such as OpenBabel, RDKit, etc.), and then based on the molecular dynamics (MD) simulation tools (such as LAMMPS, GROMACS, openMM, etc.), molecular motion simulation and chemical reaction simulation are performed according to the formula component structure output by the modeling to obtain the corresponding solvation structure, and finally, quantum chemical calculation tools (such as Gaussian, GAMESS, etc.) are used to calculate the properties according to the solvation structure. In practice, we found that the worse the quality of molecular structure modeling, the lower the accuracy of the corresponding property analysis, and the quality of molecular structure modeling is closely related to the professional knowledge level and industry technical background of the modeler, that is, the quality of molecular structure modeling will be affected by human factors, which invisibly increases the difficulty of design and development and increases the cost of design and development. Summary of the invention

[0003] The purpose of the present invention is to provide a processing method, device, electronic device and computer-readable storage medium for structural optimization of electrolyte formula components in view of the defects of the prior art. The present invention constructs a structural optimization model based on the Uni-Mol model, which is used to perform three-dimensional structural optimization processing on the original molecular structure input by the model and output the corresponding optimized molecular structure; and constructs a pre-training data set, i.e., a first data set, through big data collection, and constructs a fine-tuning data set, i.e., a second data set, through molecular dynamics simulation; and pre-trains the structural optimization model based on the first data set, so that the structural optimization model can fully learn the optimal solution of the molecular structure of the compound; and after the pre-training, the structural optimization model is tuned based on the second data set, so that the structural optimization model can further fully learn the optimal solution of the molecular structure of various electrolyte components; and after the model tuning is completed, the molecular structure of the formula component of any electrolyte formula is optimized based on the structural optimization model. The structural optimization model of the present invention can output the optimized three-dimensional molecular structure end-to-end; if the structural optimization model of the present invention is used as an optimization tool for conventional molecular structure modeling, it can not only reduce the influence of human factors on the quality of molecular structure modeling, but also improve the modeling quality and modeling efficiency.

[0004] To achieve the above-mentioned purpose, a first aspect of an embodiment of the present invention provides a method for optimizing the structure of electrolyte formula components, the method comprising:

[0005] Constructing a structural optimization model; the structural optimization model is implemented based on the Uni-Mol model; the structural optimization model is used to perform three-dimensional structural optimization processing on the original molecular structure input by the model and output the corresponding optimized molecular structure;

[0006] constructing a corresponding first data set through big data collection; and constructing a corresponding second data set through molecular dynamics simulation;

[0007] Pre-training the structure optimization model based on the first data set; and after the pre-training, optimizing the structure optimization model based on the second data set;

[0008] After the model tuning is completed, the electrolyte formula input by the user is used as the corresponding current electrolyte formula; and the preset chemical informatics tool is used to perform corresponding three-dimensional molecular structure modeling according to the molecular sequences of each component of the current electrolyte formula to obtain the corresponding component modeling structure; and based on the structure optimization model, the three-dimensional structure optimization processing of each component modeling structure is performed to obtain the corresponding component optimization structure; and each component molecular sequence and the corresponding component type and the component optimized structure form a corresponding formula component structure optimization record; and all the obtained formula component structure optimization records form a corresponding formula structure optimization report to feedback to the user; the current electrolyte formula includes multiple formula components; each of the formula components includes a component type and a component molecular sequence; the component types include solvents, electrolytes and additives; the component molecular sequence is a one-dimensional SMILES sequence of solvent molecules, electrolyte molecules or additive molecules corresponding to the component type; the chemical informatics tool includes at least OpenBabel and RDKit.

[0009] Preferably, the original and optimized molecular structures input and output by the structural optimization model are composed of corresponding atomic tensors and chemical bond tensors;

[0010] The atomic tensor is composed of a plurality of atomic vectors; each of the atomic vectors corresponds to an atom; each of the atomic vectors at least includes an atomic identifier, an atomic element type and an atomic coordinate; the atomic coordinate is a three-dimensional coordinate; the atomic vectors in the original and optimized molecular structures are aligned one by one based on the atomic identifiers;

[0011] The chemical bond tensor is composed of a plurality of chemical bond vectors; each of the chemical bond vectors corresponds to a chemical bond; each of the chemical bond vectors at least includes a chemical bond identifier, a chemical bond length and two corresponding atom identifiers; the chemical bond vectors in the original and optimized molecular structures are aligned one by one based on the chemical bond identifiers;

[0012] The first data set includes a plurality of first data records; the first data records include a first training molecular structure and a first label molecular structure; each of the first data records corresponds to a three-dimensional molecular structure of a compound;

[0013] The second data set includes a plurality of second data records; the second data records include a second training molecular structure and a second label molecular structure; each of the second data records corresponds to a three-dimensional molecular structure of an electrolyte solvent, electrolyte or additive.

[0014] Preferably, the constructing the corresponding first data set through big data collection specifically includes:

[0015] A first collected data set corresponding to the three-dimensional molecular structure of a large number of compounds is collected through multiple public channels; the multiple public channels at least include a public compound molecular structure database and public technical literature / scientific journals / papers; the first collected data set includes a plurality of first three-dimensional molecular structures; the first three-dimensional molecular structure is composed of the corresponding atomic tensor and the chemical bond tensor;

[0016] Traversing all the first three-dimensional molecular structures of the first acquisition data set; and during the traversal, taking the first three-dimensional molecular structure currently traversed as the corresponding current molecular structure; and taking the current molecular structure as the corresponding first label molecular structure; and then randomly selecting one or more atomic vectors from the atomic tensor of the current molecular structure as the corresponding vectors to be masked; and modifying the atomic coordinates of each vector to be masked based on a preset coordinate perturbation rule, and replacing the atomic element type of each vector to be masked with a preset empty element type; and taking the modified current molecular structure as the corresponding first training molecular structure; and forming a corresponding first data record by the first training molecular structure and the first label molecular structure corresponding to the current molecular structure; and at the end of the traversal, forming the corresponding first data set by all the obtained first data records;

[0017] Among them, the coordinate perturbation rule is to take the atomic coordinate before modification as the center of a sphere, and use a preset perturbation radius r as the radius of the sphere to create a corresponding spherical space, denoted as the corresponding current perturbation space, and randomly select a point coordinate within the current perturbation space as the modified atomic coordinate; the preset perturbation radius r is less than or equal to

[0018] Preferably, constructing the corresponding second dataset through molecular dynamics simulation specifically includes:

[0019] Collecting a large number of electrolyte formulations through multiple public channels to form a corresponding second collection dataset; the multiple public channels at least include publicly available electrolyte formulation databases and publicly available technical literature / scientific journals / papers; the second collection dataset includes multiple first electrolyte formulations; the first electrolyte formulation includes multiple first formulation components; each of the first formulation components includes a first component type and a first component molecular sequence; the first component type includes solvents, electrolytes, and additives; the first component molecular sequence is a one-dimensional SMILES sequence of a solvent molecule, electrolyte molecule, or additive molecule corresponding to the first component type;

[0020] And using the cheminformatics tool to perform corresponding three-dimensional molecular structure modeling based on each of the first component molecular sequences to obtain a corresponding first modeling structure; the first modeling structure is composed of the corresponding atomic tensor and chemical bond tensor;

[0021] And using a preset molecular dynamics simulation tool to perform molecular motion simulation for A rounds of iteration on each of the first modeling structures according to a preset total number of first iterations A; and after the number of iterative simulations exceeds a preset first iteration number B, each time an iterative simulation is completed, the current simulation trajectory file is used as a corresponding first backup trajectory file and saved, 0 < B < A; and at the end of the iterative simulation, perform three-dimensional molecular structure recognition based on all the obtained first backup trajectory files to obtain a corresponding first recognition structure; the molecular dynamics simulation tool at least includes LAMMPS, GROMACS, openMM; the first recognition structure is composed of the corresponding atomic tensor and chemical bond tensor; the atomic vectors in the first modeling structure and the first recognition structure are aligned one by one based on the atomic identifier; the chemical bond vectors in the first modeling structure and the first recognition structure are aligned one by one based on the chemical bond identifier;

[0022] And using the first modeling structure and the first recognition structure corresponding to each of the first component molecular sequences as the corresponding second training molecular structure and second label molecular structure to form a corresponding second data record; and using all the obtained second data records to form the corresponding second dataset.

[0023] Further, performing three-dimensional molecular structure recognition according to all the first backup trajectory files obtained to obtain a corresponding first recognition structure specifically includes:

[0024] Atomic alignment is performed on all the first backup trajectory files and the corresponding first modeling structures; and after the atomic alignment is completed, each atom in the first first backup trajectory file is used as the corresponding first atom; and the atom identifier and the atomic element type corresponding to each first atom are set to the atom identifier and the atomic element type of the atomic vector aligned in the first modeling structure; and the trajectory coordinates of each first atom in all the first backup trajectory files are averaged and the calculation result is used as the corresponding atomic coordinate; and a new atomic vector is formed by the atomic identifier, the atomic element type and the atomic coordinates corresponding to each first atom; and a new atomic tensor is formed by all the atomic vectors corresponding to all the first atoms;

[0025] The chemical bond tensor of the first modeling structure is copied to obtain a new chemical bond tensor; each chemical bond vector of the new chemical bond tensor is traversed; and during the traversal, the chemical bond vector currently traversed is used as the corresponding current vector; the straight-line distance between the two atomic coordinates corresponding to the two first atoms corresponding to the two atomic identifiers of the current vector is calculated to obtain the corresponding first distance, and the chemical bond length of the current vector is reset based on the first distance;

[0026] After the traversal is completed, the newly generated atomic tensor and chemical bond tensor form the corresponding first recognition structure.

[0027] Preferably, the pre-training of the structure optimization model based on the first data set specifically includes:

[0028] Step 601, based on a preset first training evaluation ratio, the first data set is randomly divided into two data sets recorded as a corresponding first training set and a first evaluation set;

[0029] Wherein, both the first training set and the first evaluation set include a plurality of the first data records; the ratio of the total number of records in the first training set to the total number of records in the first evaluation set satisfies the first training evaluation ratio;

[0030] Step 602, taking the first first data record in the first training set as the corresponding current test record;

[0031] Step 603, extract the atomic identifier and the atomic element type of each atomic vector in the atomic tensor of the first label molecular structure of the current test record to form a corresponding first type label vector, and extract the atomic identifier and the atomic coordinate of each atomic vector to form a corresponding first coordinate label vector; and form a corresponding first type label tensor with all the obtained first type label vectors, and form a corresponding first coordinate label tensor with all the obtained first coordinate label vectors; and extract the chemical bond identifier and the chemical bond length of each chemical bond vector in the chemical bond tensor of the first label molecular structure to form a corresponding first bond length label vector, and form a corresponding first bond length label tensor with all the obtained first bond length label vectors;

[0032] Step 604, inputting the first training molecular structure of the current test record into the structure optimization model to perform three-dimensional structure optimization processing to obtain a corresponding first predicted molecular structure;

[0033] Wherein, the first predicted molecular structure includes the corresponding atomic tensor and the chemical bond tensor;

[0034] Step 605, extract the atom identifier and the atomic element type of each atom vector in the atom tensor of the first predicted molecular structure as a corresponding first type prediction vector, and extract the atom identifier and the atomic coordinate of each atom vector as a corresponding first coordinate prediction vector; and form a corresponding first type prediction tensor with all the obtained first type prediction vectors, and form a corresponding first coordinate prediction tensor with all the obtained first coordinate prediction vectors; and extract the chemical bond identifier and the chemical bond length of each chemical bond vector in the chemical bond tensor of the first predicted molecular structure to form a corresponding first bond length prediction vector, and form a corresponding first bond length prediction tensor with all the obtained first bond length prediction vectors;

[0035] Step 606, the obtained first type prediction tensor and the corresponding first type label tensor form a corresponding first prediction-label pair; the obtained first coordinate prediction tensor and the corresponding first coordinate label tensor form a corresponding second prediction-label pair; and the obtained first bond length prediction tensor and the corresponding first bond length label tensor form a corresponding third prediction-label pair;

[0036] Step 607: Substitute the first, second and third prediction-label pairs into the preset first, second and third loss functions to calculate the corresponding first, second and third loss values; and perform weighted sum calculation on the first, second and third loss values ​​and use the calculation result as the corresponding first total loss value;

[0037] Among them, the first loss function includes at least L1 loss function, L2 loss function and multi-classification cross entropy loss function; the second loss function includes at least L1 loss function, L2 loss function and MSE loss function; the third loss function includes at least L1 loss function, L2 loss function and MSE loss function;

[0038] Step 608, identifying whether the first loss value satisfies a preset first loss value range; if so, proceeding to step 609; if not, performing a round of parameter optimization on the structural optimization model in a direction of minimizing the first loss function based on a preset first model parameter optimizer, and returning to step 604 at the end of this round of parameter optimization;

[0039] Wherein, the first model parameter optimizer includes at least an SGD optimizer and an ADAM optimizer;

[0040] Step 609, identifying whether the second loss value satisfies a preset second loss value range; if so, proceeding to step 610; if not, performing a round of parameter optimization on the structural optimization model in a direction of minimizing the second loss function based on a preset second model parameter optimizer, and returning to step 604 at the end of this round of parameter optimization;

[0041] Wherein, the second model parameter optimizer includes at least an SGD optimizer and an ADAM optimizer;

[0042] Step 610, identifying whether the third loss value satisfies a preset third loss value range; if so, proceeding to step 611; if not, performing a round of parameter optimization on the structural optimization model in a direction of minimizing the third loss function based on a preset third model parameter optimizer, and returning to step 604 at the end of this round of parameter optimization;

[0043] Wherein, the third model parameter optimizer includes at least an SGD optimizer and an ADAM optimizer;

[0044] Step 611, identifying whether the first total loss value satisfies a preset fourth loss value range; if so, proceeding to step 612; if not, performing a round of parameter optimization on the structural optimization model in a direction of minimizing the first total loss value based on a preset fourth model parameter optimizer, and returning to step 604 at the end of this round of parameter optimization;

[0045] Wherein, the fourth model parameter optimizer includes at least an SGD optimizer and an ADAM optimizer;

[0046] Step 612, identifying whether the current test record is the last first data record in the first training set; if so, going to step 613; if not, taking the next first data record in the first training set as the new current test record and returning to step 603;

[0047] Step 613: Count the total number of the first data records in the first evaluation set to obtain the corresponding total number of records N; traverse all the first data records in the first evaluation set; and during the traversal, use the first data record currently traversed as the corresponding current evaluation record; and input the first training molecular structure of the current evaluation record into the structure optimization model to perform three-dimensional structure optimization processing to obtain the corresponding first sample prediction structure x p,i , 1≤index i≤N; and the first label molecular structure of the current evaluation record is used as the corresponding first sample label structure x t,i ; and the first sample prediction structure x corresponding to the current evaluation record p,i And the first sample label structure x t,i Form a corresponding first sample prediction-label pair;

[0048] Step 614, when the traversal of all the first data records of the first evaluation set is completed, all the first sample prediction-label pairs obtained are brought into a preset first evaluation function to calculate and obtain corresponding first evaluation values;

[0049] The first evaluation function is implemented based on the RMSD function, specifically:

[0050]

[0051] Step 615, identifying whether the first evaluation value satisfies a preset first evaluation value range; if not, returning to step 601 to continue training; if satisfied, stopping training and confirming the end of pre-training.

[0052] Preferably, the performing model tuning on the structural optimization model based on the second data set specifically includes:

[0053] Step 701, based on a preset second training evaluation ratio, the second data set is randomly divided into two data sets and recorded as corresponding second training sets and second evaluation sets;

[0054] Wherein, both the second training set and the second evaluation set include a plurality of second data records; the ratio of the total number of records in the second training set to the total number of records in the second evaluation set satisfies the second training evaluation ratio;

[0055] Step 702, taking the first second data record in the second training set as the corresponding current test record;

[0056] Step 703, extract the atomic identifier and the atomic element type of each atomic vector in the atomic tensor of the second label molecular structure of the current test record to form a corresponding second type label vector, and extract the atomic identifier and the atomic coordinate of each atomic vector to form a corresponding second coordinate label vector; and form a corresponding second type label tensor with all the obtained second type label vectors, and form a corresponding second coordinate label tensor with all the obtained second coordinate label vectors; and extract the chemical bond identifier and the chemical bond length of each chemical bond vector in the chemical bond tensor of the second label molecular structure to form a corresponding second bond length label vector, and form a corresponding second bond length label tensor with all the obtained second bond length label vectors;

[0057] Step 704, inputting the second training molecular structure of the current test record into the structure optimization model to perform three-dimensional structure optimization processing to obtain a corresponding second predicted molecular structure;

[0058] Wherein, the second predicted molecular structure includes the corresponding atomic tensor and the chemical bond tensor;

[0059] Step 705, extract the atom identifier and the atomic element type of each atom vector in the atom tensor of the second predicted molecular structure as a corresponding second type prediction vector, and extract the atom identifier and the atomic coordinate of each atom vector as a corresponding second coordinate prediction vector; and form a corresponding second type prediction tensor with all the obtained second type prediction vectors, and form a corresponding second coordinate prediction tensor with all the obtained second coordinate prediction vectors; and extract the chemical bond identifier and the chemical bond length of each chemical bond vector in the chemical bond tensor of the second predicted molecular structure to form a corresponding second bond length prediction vector, and form a corresponding second bond length prediction tensor with all the obtained second bond length prediction vectors;

[0060] Step 706, the obtained second type prediction tensor and the corresponding second type label tensor form a corresponding fourth prediction-label pair; the obtained second coordinate prediction tensor and the corresponding second coordinate label tensor form a corresponding fifth prediction-label pair; and the obtained second bond length prediction tensor and the corresponding second bond length label tensor form a corresponding sixth prediction-label pair;

[0061] Step 707, bringing the fourth, fifth and sixth prediction-label pairs into the preset fourth, fifth and sixth loss functions to calculate the corresponding fourth, fifth and sixth loss values; and performing weighted sum calculation on the fourth, fifth and sixth loss values ​​and using the calculation result as the corresponding second total loss value;

[0062] Among them, the fourth loss function at least includes L1 loss function, L2 loss function and multi-classification cross entropy loss function; the fifth loss function at least includes L1 loss function, L2 loss function and MSE loss function; the sixth loss function at least includes L1 loss function, L2 loss function and MSE loss function;

[0063] Step 708, identifying whether the fourth loss value satisfies a preset fifth loss value range; if so, proceeding to step 709; if not, performing a round of parameter fine-tuning on the structural optimization model in a direction of minimizing the fourth loss function based on a preset fifth model parameter optimizer, and returning to step 704 at the end of this round of parameter fine-tuning;

[0064] Wherein, the fifth model parameter optimizer includes at least RMSprop optimizer, ADAM optimizer, and AdamW optimizer;

[0065] Step 709, identifying whether the fifth loss value satisfies a preset sixth loss value range; if so, proceeding to step 710; if not, performing a round of parameter fine-tuning on the structural optimization model in a direction of minimizing the fifth loss function based on a preset sixth model parameter optimizer, and returning to step 704 at the end of this round of parameter fine-tuning;

[0066] Wherein, the sixth model parameter optimizer includes at least RMSprop optimizer, ADAM optimizer, and AdamW optimizer;

[0067] Step 710, identifying whether the sixth loss value satisfies the preset seventh loss value range; if so, proceeding to step 711; if not, performing a round of parameter fine-tuning on the structural optimization model in the direction of minimizing the sixth loss function based on the preset seventh model parameter optimizer, and returning to step 704 at the end of this round of parameter fine-tuning;

[0068] Wherein, the seventh model parameter optimizer includes at least RMSprop optimizer, ADAM optimizer, and AdamW optimizer;

[0069] Step 711, identifying whether the second total loss value satisfies a preset eighth loss value range; if so, proceeding to step 712; if not, performing a round of parameter fine-tuning on the structural optimization model in a direction of minimizing the second total loss value based on a preset eighth model parameter optimizer, and returning to step 704 at the end of this round of parameter fine-tuning;

[0070] Wherein, the eighth model parameter optimizer includes at least RMSprop optimizer, ADAM optimizer, and AdamW optimizer;

[0071] Step 712, identifying whether the current test record is the last second data record in the second training set; if so, going to step 713; if not, taking the next second data record in the second training set as the new current test record and returning to step 703;

[0072] Step 713: Count the total number of the second data records in the second evaluation set to obtain the corresponding total number of records M; traverse all the second data records in the second evaluation set; and during the traversal, use the second data record currently traversed as the corresponding current evaluation record; and input the second training molecular structure of the current evaluation record into the structure optimization model to perform three-dimensional structure optimization processing to obtain the corresponding second sample prediction structure x p,j , 1≤index j≤M; and the second label molecular structure of the current evaluation record is used as the corresponding second sample label structure x t,j ; and the second sample prediction structure x corresponding to the current evaluation record p,j And the second sample label structure x t,j Form a corresponding second sample prediction-label pair;

[0073] Step 714, when the traversal of all the second data records of the second evaluation set is completed, all the obtained second sample prediction-label pairs are brought into a preset second evaluation function to calculate and obtain corresponding second evaluation values;

[0074] The second evaluation function is implemented based on the RMSD function, specifically:

[0075]

[0076] Step 715, identifying whether the second evaluation value satisfies a preset second evaluation value range; if not, returning to step 701 to continue training; if satisfied, stopping training and confirming that the model tuning is complete.

[0077] A second aspect of an embodiment of the present invention provides a device for implementing the method for optimizing the structure of electrolyte formula components described in the first aspect, the device comprising: a model building module, a data preparation module, a model training module and a model application module;

[0078] The model building module is used to build a structure optimization model; the structure optimization model is implemented based on the Uni-Mol model; the structure optimization model is used to perform three-dimensional structure optimization processing on the original molecular structure input by the model and output the corresponding optimized molecular structure;

[0079] The data preparation module is used to construct a corresponding first data set through big data collection; and to construct a corresponding second data set through molecular dynamics simulation;

[0080] The model training module is used to pre-train the structure optimization model based on the first data set; and after the pre-training is completed, the structure optimization model is tuned based on the second data set;

[0081] The model application module is used to use the electrolyte formula input by the user as the corresponding current electrolyte formula after the model tuning is completed; and use the preset chemical informatics tool to perform corresponding three-dimensional molecular structure modeling according to the molecular sequences of each component of the current electrolyte formula to obtain the corresponding component modeling structure; and perform three-dimensional structure optimization processing on each component modeling structure based on the structure optimization model to obtain the corresponding component optimization structure; and each component molecular sequence and the corresponding component type and the component optimized structure form a corresponding formula component structure optimization record; and all the obtained formula component structure optimization records form a corresponding formula structure optimization report to feedback to the user; the current electrolyte formula includes multiple formula components; each of the formula components includes a component type and a component molecular sequence; the component types include solvents, electrolytes and additives; the component molecular sequence is a one-dimensional SMILES sequence of solvent molecules, electrolyte molecules or additive molecules corresponding to the component type; the chemical informatics tool includes at least OpenBabel and RDKit.

[0082] A third aspect of an embodiment of the present invention provides an electronic device, including: a memory, a processor, and a transceiver;

[0083] The processor is used to be coupled to the memory, read and execute instructions in the memory, so as to implement the method steps described in the first aspect above;

[0084] The transceiver is coupled to the processor, and the processor controls the transceiver to send and receive messages.

[0085] A fourth aspect of an embodiment of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer instructions. When the computer instructions are executed by a computer, the computer executes the instructions of the method described in the first aspect above.

[0086] The embodiment of the present invention provides a processing method, device, electronic device and computer-readable storage medium for structural optimization of electrolyte formula components. As can be seen from the above content, the embodiment of the present invention constructs a structural optimization model based on the Uni-Mol model, which is used to perform three-dimensional structural optimization processing on the original molecular structure input by the model and output the corresponding optimized molecular structure; and constructs a pre-training data set, i.e., a first data set, through big data collection, and constructs a fine-tuning data set, i.e., a second data set, through molecular dynamics simulation; and pre-trains the structural optimization model based on the first data set, so that the structural optimization model can fully learn the optimal solution of the molecular structure of the compound; and after the pre-training, the structural optimization model is tuned based on the second data set, so that the structural optimization model can further fully learn the optimal solution of the molecular structure of various electrolyte components; and after the model tuning is completed, the molecular structure of the formula component of any electrolyte formula is optimized based on the structural optimization model. The structural optimization model of the embodiment of the present invention can output the optimized three-dimensional molecular structure end-to-end; if the structural optimization model of the embodiment of the present invention is used as an optimization tool for conventional molecular structure modeling, it not only reduces the influence of human factors on the quality of molecular structure modeling, but also improves the modeling quality and modeling efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0087] Figure 1 A schematic diagram of a method for optimizing the structure of electrolyte formula components provided in Example 1 of the present invention;

[0088] Figure 2 A module structure diagram of a processing device for optimizing the structure of electrolyte formula components provided in the second embodiment of the present invention;

[0089] Figure 3 A schematic diagram of the structure of an electronic device provided in Embodiment 3 of the present invention. DETAILED DESCRIPTION

[0090] In order to make the purpose, technical solution and advantages of the present invention clearer, the present invention will be further described in detail below in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0091] Embodiment 1 of the present invention provides a method for optimizing the structure of electrolyte formulation components, such as Figure 1 As shown in the schematic diagram of a processing method for optimizing the structure of electrolyte formula components provided in the first embodiment of the present invention, the method mainly includes the following steps:

[0092] Step 1, constructing a structural optimization model;

[0093] Here, the structural optimization model of the embodiment of the present invention is implemented based on the Uni-Mol model, which is used to perform three-dimensional structural optimization processing on the original molecular structure input by the model and output the corresponding optimized molecular structure.

[0094] The detailed information of the Uni-Mol model can be understood based on the public technical document "UNI-MOL: A UNIVERSAL 3DMOLECULAR REPRESENTATION LEARNING FRAMEWORK", which will not be further elaborated here; it can be seen from the public document that the Uni-Mol model can construct a variety of business models based on a backbone network and a combination of different task head modules, one of which is an end-to-end three-dimensional structure optimization model: it is formed by connecting the backbone network with three parallel prediction task head modules, and the structure optimization model of the embodiment of the present invention is implemented with reference to this end-to-end three-dimensional structure optimization model; in addition, the backbone network of the Uni-Mol model is implemented based on the model structure of the transformer model, and the three parallel prediction task head modules connected to the backbone network are respectively an atom type prediction task head (Atom Type Head) module, an atom coordinate prediction task head (Coord Head) module and a chemical bond length prediction task head (Pair-dist Head) module;

[0095] The original and optimized molecular structures input and output by the structural optimization model of the embodiment of the present invention are composed of corresponding atomic tensors and chemical bond tensors; wherein,

[0096] The atomic tensor is composed of multiple atomic vectors; each atomic vector corresponds to an atom; each atomic vector includes at least an atomic identifier, an atomic element type, and an atomic coordinate; the atomic coordinate is a three-dimensional coordinate; it should be noted that the atomic vectors in the original and optimized molecular structures of the embodiment of the present invention are aligned one by one based on the atomic identifier;

[0097] The chemical bond tensor is composed of multiple chemical bond vectors; each chemical bond vector corresponds to a chemical bond; each chemical bond vector includes at least a chemical bond identifier, a chemical bond length and two corresponding atomic identifiers; it should be noted that the chemical bond vectors in the original and optimized molecular structures of the embodiments of the present invention are aligned one-to-one based on the chemical bond identifiers.

[0098] Step 2, constructing a corresponding first data set through big data collection; and constructing a corresponding second data set through molecular dynamics simulation;

[0099] Specifically comprising: step 21, constructing a corresponding first data set through big data collection;

[0100] The first data set includes a plurality of first data records; the first data records include a first training molecular structure and a first label molecular structure; each first data record corresponds to a three-dimensional molecular structure of a compound;

[0101] Specifically, it includes: step 211, collecting a first collection data set corresponding to the three-dimensional molecular structure composition of a large number of compounds through multiple public channels;

[0102] The multiple public channels at least include a public compound molecular structure database and public technical literature / scientific journals / papers; the first acquired data set includes a plurality of first three-dimensional molecular structures; the first three-dimensional molecular structure is composed of corresponding atomic tensors and chemical bond tensors;

[0103] Here, a large number of three-dimensional molecular structures can also be generated by chemical informatics tools (such as OpenBabel and RDKit) to add data items to the first collected data set;

[0104] Step 212, traverse all first three-dimensional molecular structures of the first acquisition data set; and during the traversal, take the currently traversed first three-dimensional molecular structure as the corresponding current molecular structure; and take the current molecular structure as a corresponding first label molecular structure; and then randomly select one or more atomic vectors from the atomic tensor of the current molecular structure as the corresponding vectors to be masked; and modify the atomic coordinates of each vector to be masked based on a preset coordinate perturbation rule, and replace the atomic element type of each vector to be masked with a preset empty element type; and take the modified current molecular structure as a corresponding first training molecular structure; and form a corresponding first data record by the first training molecular structure and the first label molecular structure corresponding to the current molecular structure; and at the end of the traversal, form a corresponding first data set by all the obtained first data records;

[0105] Here, the coordinate perturbation rule of the embodiment of the present invention is to make a corresponding spherical space with the atomic coordinates before modification as the sphere center and a preset perturbation radius r as the sphere radius, and record it as the corresponding current perturbation space, and select any point coordinate in the current perturbation space as the modified atomic coordinates; the empty element type is a preset integer, which is set to 0 or a negative number by default; the preset perturbation radius r is less than or equal to

[0106] Step 22, and constructing a corresponding second data set through molecular dynamics simulation;

[0107] The second data set includes a plurality of second data records; the second data records include a second training molecular structure and a second label molecular structure; each second data record corresponds to a three-dimensional molecular structure of an electrolyte solvent, electrolyte or additive;

[0108] Specifically, it includes: step 221, collecting a large number of second collected data sets corresponding to electrolyte formula compositions through multiple public channels;

[0109] The multiple public channels at least include a public electrolyte formula database and public technical literature / scientific journals / papers; the second acquisition data set includes multiple first electrolyte formulas; the first electrolyte formula includes multiple first formula components; each first formula component includes a first component type and a first component molecule sequence; the first component type includes a solvent, an electrolyte, and an additive; the first component molecule sequence is a one-dimensional SMILES sequence of solvent molecules, electrolyte molecules, or additive molecules corresponding to the first component type;

[0110] Step 222, using a preset chemical informatics tool to perform corresponding three-dimensional molecular structure modeling according to each first component molecular sequence to obtain a corresponding first modeling structure;

[0111] Wherein, the first modeling structure is composed of corresponding atomic tensors and chemical bond tensors;

[0112] Here, the chemical informatics tools of the embodiment of the present invention include at least OpenBabel and RDKit;

[0113] Step 223, and use a preset molecular dynamics simulation tool to perform A rounds of iterative molecular motion simulation on each first modeling structure according to a preset first total number of iterations A; and after the number of iterative simulations exceeds the preset first number of iterations B, each time an iterative simulation is completed, the current simulation trajectory file is saved as a corresponding first backup trajectory file; and at the end of the iterative simulation, three-dimensional molecular structure recognition is performed based on all the obtained first backup trajectory files to obtain the corresponding first recognition structure;

[0114] Here, the molecular dynamics simulation tools of the embodiments of the present invention at least include LAMMPS, GROMACS, and openMM; the total number of first iterations A and the number of first iterations B are two preset integers, where 0 < B < A; the first recognition structure is composed of corresponding atomic tensors and chemical bond tensors; the atomic vectors in the first modeling structure are aligned one-to-one with the atoms in the first recognition structure based on atomic identifiers; the chemical bond vectors in the first modeling structure are aligned one-to-one with the chemical bonds in the first recognition structure based on chemical bond identifiers.

[0115] Among them, performing three-dimensional molecular structure recognition on all the obtained first backup trajectory files to obtain the corresponding first recognition structure specifically includes:

[0116] Step A1, perform atomic alignment on all the first backup trajectory files and the corresponding first modeling structure; after completing the atomic alignment, take each atom in the first first backup trajectory file as the corresponding first atom; set the atomic identifier and atomic element type corresponding to each first atom to the atomic identifier and atomic element type of the aligned atomic vector in the first modeling structure; calculate the average value of the trajectory coordinates of each first atom in all the first backup trajectory files and use the calculation result as the corresponding atomic coordinate; form a new atomic vector from the atomic identifier, atomic element type, and atomic coordinate corresponding to each first atom; and form a new atomic tensor from all the atomic vectors corresponding to all the first atoms.

[0117] Step A2, copy the chemical bond tensor of the first modeling structure to obtain a new chemical bond tensor; traverse each chemical bond vector of the new chemical bond tensor; during the traversal, take the currently traversed chemical bond vector as the corresponding current vector; calculate the straight-line distance between the two atomic coordinates corresponding to the two atomic identifiers of the current vector to obtain the corresponding first distance, and reset the chemical bond length of the current vector based on the first distance.

[0118] Step A3, after the traversal ends, form the corresponding first recognition structure from the newly generated atomic tensor and chemical bond tensor this time.

[0119] Step 224, form a corresponding second data record from the first modeling structure and the first recognition structure corresponding to each first component molecular sequence as the corresponding second training molecular structure and second labeled molecular structure; and form the corresponding second data set from all the obtained second data records.

[0120] Step 3, pre-train the structure optimization model based on the first data set; and after the pre-training ends, tune the model of the structure optimization model based on the second data set.

[0121] Specifically comprising: step 31, pre-training the structure optimization model based on the first data set;

[0122] Specifically, it includes: step 3101, based on a preset first training evaluation ratio, randomly dividing the first data set into two data sets recorded as a corresponding first training set and a first evaluation set;

[0123] Here, the first training evaluation ratio is a preset ratio, such as 8:2; the first training set and the first evaluation set both include a plurality of first data records; the ratio of the total number of records in the first training set to the total number of records in the first evaluation set satisfies the first training evaluation ratio;

[0124] Step 3102, taking the first first data record in the first training set as the corresponding current test record;

[0125] Step 3103, extract the atomic identifier and atomic element type of each atomic vector in the atomic tensor of the first label molecular structure of the current test record to form a corresponding first type label vector, and extract the atomic identifier and atomic coordinate of each atomic vector to form a corresponding first coordinate label vector; and form a corresponding first type label tensor with all the obtained first type label vectors, and form a corresponding first coordinate label tensor with all the obtained first coordinate label vectors; and extract the chemical bond identifier and chemical bond length of each chemical bond vector in the chemical bond tensor of the first label molecular structure to form a corresponding first bond length label vector, and form a corresponding first bond length label tensor with all the obtained first bond length label vectors;

[0126] Step 3104, inputting the first training molecular structure of the current test record into the structure optimization model to perform three-dimensional structure optimization processing to obtain the corresponding first predicted molecular structure;

[0127] Wherein, the first predicted molecular structure includes corresponding atomic tensors and chemical bond tensors;

[0128] Step 3105, extract the atomic identifier and atomic element type of each atomic vector in the atomic tensor of the first predicted molecular structure as the corresponding first type prediction vector, and extract the atomic identifier and atomic coordinate of each atomic vector as the corresponding first coordinate prediction vector; and form the corresponding first type prediction tensor with all the obtained first type prediction vectors, and form the corresponding first coordinate prediction tensor with all the obtained first coordinate prediction vectors; and extract the chemical bond identifier and chemical bond length of each chemical bond vector in the chemical bond tensor of the first predicted molecular structure to form the corresponding first bond length prediction vector, and form the corresponding first bond length prediction tensor with all the obtained first bond length prediction vectors;

[0129] Step 3106, the obtained first type prediction tensor and the corresponding first type label tensor form a corresponding first prediction-label pair; the obtained first coordinate prediction tensor and the corresponding first coordinate label tensor form a corresponding second prediction-label pair; and the obtained first bond length prediction tensor and the corresponding first bond length label tensor form a corresponding third prediction-label pair;

[0130] Step 3107, bringing the first, second and third prediction-label pairs into the preset first, second and third loss functions to calculate the corresponding first, second and third loss values; and performing weighted sum calculation on the first, second and third loss values ​​and using the calculation result as the corresponding first total loss value;

[0131] Among them, the first loss function includes at least L1 loss function, L2 loss function and multi-classification cross entropy loss function; the second loss function includes at least L1 loss function, L2 loss function and MSE loss function; the third loss function includes at least L1 loss function, L2 loss function and MSE loss function;

[0132] Step 3108, identifying whether the first loss value satisfies a preset first loss value range; if so, proceeding to step 3109; if not, performing a round of parameter optimization on the structural optimization model in a direction of minimizing the first loss function based on a preset first model parameter optimizer, and returning to step 3104 at the end of this round of parameter optimization;

[0133] Here, the first loss value range is a preset loss value range, which defaults to 0; the first model parameter optimizer includes at least an SGD optimizer and an ADAM optimizer;

[0134] Step 3109, identifying whether the second loss value satisfies a preset second loss value range; if so, proceeding to step 3110; if not, performing a round of parameter optimization on the structural optimization model in a direction of minimizing the second loss function based on a preset second model parameter optimizer, and returning to step 3104 at the end of this round of parameter optimization;

[0135] Here, the second loss value range is a preset loss value range; the second model parameter optimizer includes at least an SGD optimizer and an ADAM optimizer;

[0136] Step 3110, identifying whether the third loss value satisfies a preset third loss value range; if so, proceeding to step 3111; if not, performing a round of parameter optimization on the structural optimization model in a direction of minimizing the third loss function based on a preset third model parameter optimizer, and returning to step 3104 at the end of this round of parameter optimization;

[0137] Here, the third loss value range is a preset loss value range; the third model parameter optimizer includes at least an SGD optimizer and an ADAM optimizer;

[0138] Step 3111, identifying whether the first total loss value satisfies a preset fourth loss value range; if so, proceeding to step 3112; if not, performing a round of parameter optimization on the structural optimization model in a direction of minimizing the first total loss value based on a preset fourth model parameter optimizer, and returning to step 3104 at the end of this round of parameter optimization;

[0139] Here, the fourth loss value range is a preset loss value range; the fourth model parameter optimizer includes at least an SGD optimizer and an ADAM optimizer;

[0140] Step 3112, identifying whether the current test record is the last first data record in the first training set; if so, going to step 3113; if not, taking the next first data record in the first training set as the new current test record and returning to step 3103;

[0141] Step 3113, the total number of first data records in the first evaluation set is counted to obtain the corresponding total number of records N; all first data records in the first evaluation set are traversed; and during the traversal, the first data record currently traversed is used as the corresponding current evaluation record; and the first training molecular structure of the current evaluation record is input into the structure optimization model for three-dimensional structure optimization processing to obtain the corresponding first sample prediction structure x p,i , 1≤index i≤N; and the first label molecular structure of the current evaluation record is taken as the corresponding first sample label structure x t,i ; and the first sample prediction structure x corresponding to the current evaluation record p,i And the first sample label structure x t,i Form a corresponding first sample prediction-label pair;

[0142] Step 3114, when the traversal of all first data records of the first evaluation set is completed, all first sample prediction-label pairs obtained are brought into a preset first evaluation function to calculate and obtain corresponding first evaluation values;

[0143] Among them, the first evaluation function is implemented based on the RMSD function, specifically:

[0144]

[0145] Step 3115, identifying whether the first evaluation value meets the preset first evaluation value range; if not, returning to step 3101 to continue training; if satisfied, stopping training and confirming the end of pre-training;

[0146] Here, the first evaluation value range is a preset evaluation value range;

[0147] Step 32: After the pre-training is completed, the structure optimization model is tuned based on the second data set;

[0148] Specifically, it includes: step 3201, based on a preset second training evaluation ratio, randomly dividing the second data set into two data sets recorded as corresponding second training sets and second evaluation sets;

[0149] Here, the second training evaluation ratio is a preset ratio, such as 7:3; the second training set and the second evaluation set both include a plurality of second data records; the ratio of the total number of records in the second training set to the total number of records in the second evaluation set satisfies the second training evaluation ratio;

[0150] Step 3202, taking the first second data record in the second training set as the corresponding current test record;

[0151] Step 3203, extract the atomic identifier and atomic element type of each atomic vector in the atomic tensor of the second label molecular structure of the current test record to form a corresponding second type label vector, and extract the atomic identifier and atomic coordinate of each atomic vector to form a corresponding second coordinate label vector; and form a corresponding second type label tensor with all the obtained second type label vectors, and form a corresponding second coordinate label tensor with all the obtained second coordinate label vectors; and extract the chemical bond identifier and chemical bond length of each chemical bond vector in the chemical bond tensor of the second label molecular structure to form a corresponding second bond length label vector, and form a corresponding second bond length label tensor with all the obtained second bond length label vectors;

[0152] Step 3204, inputting the second training molecular structure of the current test record into the structure optimization model to perform three-dimensional structure optimization processing to obtain the corresponding second predicted molecular structure;

[0153] The second predicted molecular structure includes corresponding atomic tensors and chemical bond tensors;

[0154] Step 3205, extract the atomic identifier and atomic element type of each atomic vector in the atomic tensor of the second predicted molecular structure as the corresponding second type prediction vector, and extract the atomic identifier and atomic coordinate of each atomic vector as the corresponding second coordinate prediction vector; and form the corresponding second type prediction tensor with all the obtained second type prediction vectors, and form the corresponding second coordinate prediction tensor with all the obtained second coordinate prediction vectors; and extract the chemical bond identifier and chemical bond length of each chemical bond vector in the chemical bond tensor of the second predicted molecular structure to form the corresponding second bond length prediction vector, and form the corresponding second bond length prediction tensor with all the obtained second bond length prediction vectors;

[0155] Step 3206, the obtained second type prediction tensor and the corresponding second type label tensor form a corresponding fourth prediction-label pair; the obtained second coordinate prediction tensor and the corresponding second coordinate label tensor form a corresponding fifth prediction-label pair; and the obtained second bond length prediction tensor and the corresponding second bond length label tensor form a corresponding sixth prediction-label pair;

[0156] Step 3207, bringing the fourth, fifth and sixth prediction-label pairs into the preset fourth, fifth and sixth loss functions to calculate the corresponding fourth, fifth and sixth loss values; and performing weighted sum calculation on the fourth, fifth and sixth loss values ​​and using the calculation result as the corresponding second total loss value;

[0157] Among them, the fourth loss function at least includes L1 loss function, L2 loss function and multi-classification cross entropy loss function; the fifth loss function at least includes L1 loss function, L2 loss function and MSE loss function; the sixth loss function at least includes L1 loss function, L2 loss function and MSE loss function;

[0158] Step 3208, identifying whether the fourth loss value satisfies the preset fifth loss value range; if so, proceeding to step 3209; if not, performing a round of parameter fine-tuning on the structural optimization model in the direction of minimizing the fourth loss function based on the preset fifth model parameter optimizer, and returning to step 3204 at the end of this round of parameter fine-tuning;

[0159] Here, the first loss value range is a preset loss value range, which defaults to 0; the fifth model parameter optimizer includes at least an RMSprop optimizer, an ADAM optimizer, and an AdamW optimizer;

[0160] Step 3209, identifying whether the fifth loss value satisfies the preset sixth loss value range; if so, proceeding to step 3210; if not, performing a round of parameter fine-tuning on the structural optimization model in the direction of minimizing the fifth loss function based on the preset sixth model parameter optimizer, and returning to step 3204 at the end of this round of parameter fine-tuning;

[0161] Here, the sixth loss value range is a preset loss value range; the sixth model parameter optimizer includes at least an RMSprop optimizer, an ADAM optimizer, and an AdamW optimizer;

[0162] Step 3210, identifying whether the sixth loss value satisfies the preset seventh loss value range; if so, proceeding to step 3211; if not, performing a round of parameter fine-tuning on the structural optimization model in the direction of minimizing the sixth loss function based on the preset seventh model parameter optimizer, and returning to step 3204 at the end of this round of parameter fine-tuning;

[0163] Here, the seventh loss value range is a preset loss value range; the seventh model parameter optimizer includes at least an RMSprop optimizer, an ADAM optimizer, and an AdamW optimizer;

[0164] Step 3211, identifying whether the second total loss value satisfies the preset eighth loss value range; if so, proceeding to step 3212; if not, performing a round of parameter fine-tuning on the structural optimization model in the direction of minimizing the second total loss value based on the preset eighth model parameter optimizer, and returning to step 3204 at the end of this round of parameter fine-tuning;

[0165] Here, the eighth loss value range is a preset loss value range; the eighth model parameter optimizer includes at least an RMSprop optimizer, an ADAM optimizer, and an AdamW optimizer;

[0166] Step 3212, identifying whether the current test record is the last second data record in the second training set; if so, going to step 3213; if not, taking the next second data record in the second training set as the new current test record and returning to step 3203;

[0167] Step 3213, the total number of second data records in the second evaluation set is counted to obtain the corresponding total number of records M; all second data records in the second evaluation set are traversed; and during the traversal, the second data record currently traversed is used as the corresponding current evaluation record; and the second training molecular structure of the current evaluation record is input into the structure optimization model for three-dimensional structure optimization processing to obtain the corresponding second sample prediction structure x p,j, 1≤index j≤M; and the second label molecular structure of the current evaluation record is used as the corresponding second sample label structure x t,j ; and the second sample prediction structure x corresponding to the current evaluation record p,j and the second sample label structure x t,j Form a corresponding second sample prediction-label pair;

[0168] Step 3214, when the traversal of all second data records of the second evaluation set is completed, all obtained second sample prediction-label pairs are brought into a preset second evaluation function to calculate and obtain corresponding second evaluation values;

[0169] The second evaluation function is implemented based on the RMSD function, specifically:

[0170]

[0171] Step 3215, identifying whether the second evaluation value satisfies the preset second evaluation value range; if not, returning to step 3201 to continue training; if satisfied, stopping training and confirming the end of model tuning.

[0172] Here, the second evaluation value range is a preset evaluation value range.

[0173] Step 4: After the model tuning is completed, the electrolyte formula input by the user is used as the corresponding current electrolyte formula; and the preset chemical informatics tool is used to perform corresponding three-dimensional molecular structure modeling according to the molecular sequences of each component of the current electrolyte formula to obtain the corresponding component modeling structure; and the three-dimensional structure optimization processing of each component modeling structure is performed based on the structure optimization model to obtain the corresponding component optimization structure; and each component molecular sequence and the corresponding component type and component optimization structure form a corresponding formula component structure optimization record; and all the obtained formula component structure optimization records form a corresponding formula structure optimization report to feedback to the user;

[0174] Among them, the current electrolyte formula includes multiple formula components; each formula component includes a component type and a component molecule sequence; the component type includes solvents, electrolytes and additives; the component molecule sequence is a one-dimensional SMILES sequence of solvent molecules, electrolyte molecules or additive molecules corresponding to the component type.

[0175] Figure 2 The module structure diagram of a processing device for optimizing the structure of electrolyte formula components provided in the second embodiment of the present invention, the device is a terminal device or server that implements the aforementioned method embodiment, and can also be a device that enables the aforementioned terminal device or server to implement the aforementioned method embodiment, for example, the device can be a device or chip system of the aforementioned terminal device or server. Figure 2As shown, the device includes: a model building module 201, a data preparation module 202, a model training module 203 and a model application module 204.

[0176] The model building module 201 is used to build a structure optimization model; the structure optimization model is implemented based on the Uni-Mol model; the structure optimization model is used to perform three-dimensional structure optimization processing on the original molecular structure input by the model and output the corresponding optimized molecular structure.

[0177] The data preparation module 202 is used to construct a corresponding first data set through big data collection; and to construct a corresponding second data set through molecular dynamics simulation.

[0178] The model training module 203 is used to pre-train the structure optimization model based on the first data set; and after the pre-training is completed, the structure optimization model is tuned based on the second data set.

[0179] The model application module 204 is used to use the electrolyte formula input by the user as the corresponding current electrolyte formula after the model tuning is completed; and use the preset chemical informatics tool to perform corresponding three-dimensional molecular structure modeling according to the molecular sequences of each component of the current electrolyte formula to obtain the corresponding component modeling structure; and perform three-dimensional structural optimization processing on each component modeling structure based on the structure optimization model to obtain the corresponding component optimization structure; and each component molecular sequence and the corresponding component type and component optimization structure form a corresponding formula component structure optimization record; and all the obtained formula component structure optimization records form a corresponding formula structure optimization report to feedback to the user; the current electrolyte formula includes multiple formula components; each formula component includes a component type and a component molecular sequence; the component type includes solvents, electrolytes and additives; the component molecular sequence is a one-dimensional SMILES sequence of solvent molecules, electrolyte molecules or additive molecules corresponding to the component type; the chemical informatics tools include at least OpenBabel and RDKit.

[0180] An embodiment of the present invention provides a processing device for structural optimization of electrolyte formula components, which can execute the method steps in the above method embodiment. Its implementation principle and technical effects are similar and will not be repeated here.

[0181] It should be noted that it should be understood that the division of the various modules of the above device is only a division of logical functions. In actual implementation, they can be fully or partially integrated into one physical entity, or they can be physically separated. And these modules can all be implemented in the form of software called by processing elements; they can also be all implemented in the form of hardware; some modules can also be implemented in the form of software called by processing elements, and some modules can be implemented in the form of hardware. For example, the model building module can be a separately established processing element, or it can be integrated in a chip of the above device. In addition, it can also be stored in the memory of the above device in the form of program code, and called and executed by a processing element of the above device. The function of the above-mentioned module is determined. The implementation of other modules is similar. In addition, these modules can be fully or partially integrated together, or they can be implemented independently. The processing element described here can be an integrated circuit with signal processing capabilities. In the implementation process, each step of the above method or each module above can be completed by an integrated logic circuit of hardware in the processor element or instructions in the form of software.

[0182] For example, the above modules may be one or more integrated circuits configured to implement the above methods, such as one or more application specific integrated circuits (ASIC), or one or more digital signal processors (DSP), or one or more field programmable gate arrays (FPGA). For another example, when a module above is implemented in the form of a processing element scheduling program code, the processing element may be a general-purpose processor, such as a central processing unit (CPU) or other processor that can call program code. For another example, these modules may be integrated together and implemented in the form of a system-on-a-chip (SOC).

[0183] In the above embodiments, all or part of the embodiments may be implemented by software, hardware, firmware or any combination thereof. When implemented by software, all or part of the embodiments may be implemented in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the above method embodiments are generated. The above computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The above-mentioned 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 above-mentioned 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.) methods. The above-mentioned 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 or data center that includes one or more available media integrated. The above-mentioned available medium can be a magnetic medium (such as a floppy disk, a hard disk, a tape), an optical medium (such as a DVD), or a semiconductor medium (such as a solid state disk (SSD)), etc.

[0184] Figure 3 This is a schematic diagram of the structure of an electronic device provided in Embodiment 3 of the present invention. The electronic device may be a terminal device or a server for implementing the method of the aforementioned embodiment, or may be a terminal device or a server for implementing the method of the aforementioned embodiment connected to the aforementioned terminal device or server. Figure 3 As shown, the electronic device may include: a processor 301 (such as a CPU), a memory 302, and a transceiver 303; the transceiver 303 is coupled to the processor 301, and the processor 301 controls the transceiver 303. Various instructions may be stored in the memory 302 to complete various processing functions and implement the processing steps described in the aforementioned embodiment method. Preferably, the electronic device involved in the embodiment of the present invention also 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 components. The above-mentioned communication port 306 is used for connecting and communicating between the electronic device and other peripherals.

[0185] exist Figure 3The system bus 305 mentioned in the figure 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 ease 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 clients, read-write libraries, and read-only libraries). The memory may include random access memory (RAM), and may also include non-volatile memory (Non-Volatile Memory), such as at least one disk storage.

[0186] The above-mentioned processor can be a general-purpose processor, including a central processing unit CPU, a network processor (Network Processor, NP), a graphics processing unit (Graphics Processing Unit, GPU), etc.; it can also be a digital signal processor DSP, an application-specific integrated circuit ASIC, a field programmable gate array FPGA or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

[0187] It should be noted that an embodiment of the present invention further provides a computer-readable storage medium, in which instructions are stored. When the computer-readable storage medium is run on a computer, the computer executes the method and processing process provided in the above embodiments.

[0188] The embodiment of the present invention provides a processing method, device, electronic device and computer-readable storage medium for structural optimization of electrolyte formula components. As can be seen from the above content, the embodiment of the present invention constructs a structural optimization model based on the Uni-Mol model, which is used to perform three-dimensional structural optimization processing on the original molecular structure input by the model and output the corresponding optimized molecular structure; and constructs a pre-training data set, i.e., a first data set, through big data collection, and constructs a fine-tuning data set, i.e., a second data set, through molecular dynamics simulation; and pre-trains the structural optimization model based on the first data set, so that the structural optimization model can fully learn the optimal solution of the molecular structure of the compound; and after the pre-training, the structural optimization model is tuned based on the second data set, so that the structural optimization model can further fully learn the optimal solution of the molecular structure of various electrolyte components; and after the model tuning is completed, the molecular structure of the formula component of any electrolyte formula is optimized based on the structural optimization model. The structural optimization model of the embodiment of the present invention can output the optimized three-dimensional molecular structure end-to-end; if the structural optimization model of the embodiment of the present invention is used as an optimization tool for conventional molecular structure modeling, it not only reduces the influence of human factors on the quality of molecular structure modeling, but also improves the modeling quality and modeling efficiency.

[0189] The professionals should further realize that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented by electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in the above description according to the function. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0190] The steps of the method or algorithm described in conjunction with the embodiments disclosed herein may be implemented using hardware, a software module executed by a processor, or a combination of the two. The software module may be placed in a random access memory (RAM), a memory, a read-only memory (ROM), an electrically programmable ROM, an electrically erasable programmable ROM, a register, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.

[0191] The specific implementation methods described above further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific implementation method of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A method for optimizing the structure of electrolyte formulation components, characterized in that: The method comprises: Constructing a structural optimization model; the structural optimization model is implemented based on the Uni-Mol model; the structural optimization model is used to perform three-dimensional structural optimization processing on the original molecular structure input by the model and output the corresponding optimized molecular structure; constructing a corresponding first data set through big data collection; and constructing a corresponding second data set through molecular dynamics simulation; Pre-training the structure optimization model based on the first data set; and after the pre-training, optimizing the structure optimization model based on the second data set; After the model tuning is completed, the electrolyte formula input by the user is used as the corresponding current electrolyte formula; and the preset chemical informatics tool is used to perform corresponding three-dimensional molecular structure modeling according to the molecular sequences of each component of the current electrolyte formula to obtain the corresponding component modeling structure; and based on the structure optimization model, the three-dimensional structure optimization processing of each component modeling structure is performed to obtain the corresponding component optimization structure; and each component molecular sequence and the corresponding component type and the component optimized structure form a corresponding formula component structure optimization record; and all the obtained formula component structure optimization records form a corresponding formula structure optimization report to feedback to the user; the current electrolyte formula includes multiple formula components; each of the formula components includes a component type and a component molecular sequence; the component types include solvents, electrolytes and additives; the component molecular sequence is a one-dimensional SMI LES sequence of solvent molecules, electrolyte molecules or additive molecules corresponding to the component type; the chemical informatics tool includes at least OpenBabel and RDKit.

2. The method for optimizing the structure of electrolyte formulation according to claim 1, characterized in that: The original and optimized molecular structures input and output by the structural optimization model are composed of corresponding atomic tensors and chemical bond tensors; The atomic tensor is composed of a plurality of atomic vectors; each of the atomic vectors corresponds to an atom; each of the atomic vectors at least includes an atomic identifier, an atomic element type and an atomic coordinate; the atomic coordinate is a three-dimensional coordinate; the atomic vectors in the original and optimized molecular structures are aligned one by one based on the atomic identifiers; The chemical bond tensor is composed of a plurality of chemical bond vectors; each of the chemical bond vectors corresponds to a chemical bond; each of the chemical bond vectors at least includes a chemical bond identifier, a chemical bond length and two corresponding atom identifiers; the chemical bond vectors in the original and optimized molecular structures are aligned one by one based on the chemical bond identifiers; The first data set includes a plurality of first data records; the first data records include a first training molecular structure and a first label molecular structure; each of the first data records corresponds to a three-dimensional molecular structure of a compound; The second data set includes a plurality of second data records; the second data records include a second training molecular structure and a second label molecular structure; each of the second data records corresponds to a three-dimensional molecular structure of an electrolyte solvent, electrolyte or additive.

3. The method for optimizing the structure of electrolyte formulation according to claim 2, characterized in that: The step of constructing a corresponding first data set through big data collection specifically includes: A first collected data set corresponding to the three-dimensional molecular structure of a large number of compounds is collected through multiple public channels; the multiple public channels at least include a public compound molecular structure database and public technical literature / scientific journals / papers; the first collected data set includes a plurality of first three-dimensional molecular structures; the first three-dimensional molecular structure is composed of the corresponding atomic tensor and the chemical bond tensor; Traversing all the first three-dimensional molecular structures of the first acquisition data set; and during the traversal, taking the first three-dimensional molecular structure currently traversed as the corresponding current molecular structure; and taking the current molecular structure as the corresponding first label molecular structure; and then randomly selecting one or more atomic vectors from the atomic tensor of the current molecular structure as the corresponding vectors to be masked; and modifying the atomic coordinates of each vector to be masked based on a preset coordinate perturbation rule, and replacing the atomic element type of each vector to be masked with a preset empty element type; and taking the modified current molecular structure as the corresponding first training molecular structure; and forming a corresponding first data record by the first training molecular structure and the first label molecular structure corresponding to the current molecular structure; and at the end of the traversal, forming the corresponding first data set by all the obtained first data records; The coordinate perturbation rule is to make a corresponding spherical space with the atomic coordinates before modification as the sphere center and a preset perturbation radius r as the sphere radius, and record it as the corresponding current perturbation space, and select any point coordinate in the current perturbation space as the modified atomic coordinates; the preset perturbation radius r is less than or equal to 4. The method for optimizing the structure of electrolyte formulation according to claim 2, characterized in that: The constructing of the corresponding second data set by molecular dynamics simulation specifically includes: A second collected data set corresponding to a large number of electrolyte formula compositions is collected through multiple public channels; the multiple public channels at least include a public electrolyte formula database and public technical literature / scientific journals / papers; the second collected data set includes multiple first electrolyte formulas; the first electrolyte formula includes multiple first formula components; each of the first formula components includes a first component type and a first component molecule sequence; the first component type includes a solvent, an electrolyte, and an additive; the first component molecule sequence is a one-dimensional SMI LES sequence of solvent molecules, electrolyte molecules, or additive molecules corresponding to the first component type; and using the chemical informatics tool to perform corresponding three-dimensional molecular structure modeling according to each of the first component molecular sequences to obtain a corresponding first modeling structure; the first modeling structure is composed of the corresponding atomic tensor and the chemical bond tensor; And use a preset molecular dynamics simulation tool to perform molecular motion simulations for A rounds of iteration on each of the first modeling structures according to the preset total number of first iteration times A; and after the number of iteration simulations exceeds the preset first iteration number B, each time an iteration simulation is completed, the current simulation trajectory file is used as a corresponding first backup trajectory file and saved, where 0 < B < A; and at the end of the iteration simulation, perform three-dimensional molecular structure recognition on all the obtained first backup trajectory files to obtain the corresponding first recognition structure; the molecular dynamics simulation tool includes at least LAMMPS, GROMACS, and openMM; the first recognition structure is composed of the corresponding atomic tensor and chemical bond tensor; the atomic vectors in the first modeling structure and the first recognition structure are aligned one by one based on the atomic identifiers; the chemical bond vectors in the first modeling structure and the first recognition structure are aligned one by one based on the chemical bond identifiers. And use the first modeling structure and the first recognition structure corresponding to each of the first component molecular sequences as the corresponding second training molecular structure and the second labeled molecular structure to form a corresponding second data record; and use all the obtained second data records to form the corresponding second data set.

5. The method for optimizing the structure of electrolyte formulation according to claim 4, characterized in that: The performing three-dimensional molecular structure recognition on all the obtained first backup trajectory files to obtain the corresponding first recognition structure specifically includes: Perform atomic alignment on all the first backup trajectory files and the corresponding first modeling structures; and after completing the atomic alignment, take each atom in the first first backup trajectory file as the corresponding first atom; and set the atomic identifier and atomic element type corresponding to each first atom to the atomic identifier and atomic element type of the aligned atomic vector in the first modeling structure; calculate the mean value of the trajectory coordinates of each first atom in all the first backup trajectory files and use the calculation result as the corresponding atomic coordinate; and form a new atomic vector from the atomic identifier, atomic element type, and atomic coordinate corresponding to each first atom; and form a new atomic tensor from all the atomic vectors corresponding to all the first atoms. And copy the chemical bond tensor of the first modeling structure to obtain a new chemical bond tensor; traverse each chemical bond vector of the new chemical bond tensor; and during the traversal, take the currently traversed chemical bond vector as the corresponding current vector; calculate the straight-line distance between the two atomic coordinates corresponding to the two atomic identifiers of the current vector for the two first atoms corresponding to the current vector to obtain the corresponding first distance, and reset the chemical bond length of the current vector based on the first distance. And after the traversal is completed, form the corresponding first recognition structure from the newly generated atomic tensor and chemical bond tensor in this time.

6. The method for optimizing the structure of electrolyte formulation according to claim 2, characterized in that: The pre-training of the structure optimization model based on the first data set specifically includes: Step 601, based on a preset first training evaluation ratio, the first data set is randomly divided into two data sets recorded as a corresponding first training set and a first evaluation set; Wherein, both the first training set and the first evaluation set include a plurality of the first data records; the ratio of the total number of records in the first training set to the total number of records in the first evaluation set satisfies the first training evaluation ratio; Step 602, taking the first first data record in the first training set as the corresponding current test record; Step 603, extract the atomic identifier and the atomic element type of each atomic vector in the atomic tensor of the first label molecular structure of the current test record to form a corresponding first type label vector, and extract the atomic identifier and the atomic coordinate of each atomic vector to form a corresponding first coordinate label vector; and form a corresponding first type label tensor with all the obtained first type label vectors, and form a corresponding first coordinate label tensor with all the obtained first coordinate label vectors; and extract the chemical bond identifier and the chemical bond length of each chemical bond vector in the chemical bond tensor of the first label molecular structure to form a corresponding first bond length label vector, and form a corresponding first bond length label tensor with all the obtained first bond length label vectors; Step 604, inputting the first training molecular structure of the current test record into the structure optimization model to perform three-dimensional structure optimization processing to obtain a corresponding first predicted molecular structure; Wherein, the first predicted molecular structure includes the corresponding atomic tensor and the chemical bond tensor; Step 605, extract the atom identifier and the atomic element type of each atom vector in the atom tensor of the first predicted molecular structure as a corresponding first type prediction vector, and extract the atom identifier and the atomic coordinate of each atom vector as a corresponding first coordinate prediction vector; and form a corresponding first type prediction tensor with all the obtained first type prediction vectors, and form a corresponding first coordinate prediction tensor with all the obtained first coordinate prediction vectors; and extract the chemical bond identifier and the chemical bond length of each chemical bond vector in the chemical bond tensor of the first predicted molecular structure to form a corresponding first bond length prediction vector, and form a corresponding first bond length prediction tensor with all the obtained first bond length prediction vectors; Step 606, the obtained first type prediction tensor and the corresponding first type label tensor form a corresponding first prediction-label pair; the obtained first coordinate prediction tensor and the corresponding first coordinate label tensor form a corresponding second prediction-label pair; and the obtained first bond length prediction tensor and the corresponding first bond length label tensor form a corresponding third prediction-label pair; Step 607: Substitute the first, second and third prediction-label pairs into the preset first, second and third loss functions to calculate the corresponding first, second and third loss values; and perform weighted sum calculation on the first, second and third loss values ​​and use the calculation result as the corresponding first total loss value; Among them, the first loss function includes at least L1 loss function, L2 loss function and multi-classification cross entropy loss function; the second loss function includes at least L1 loss function, L2 loss function and MSE loss function; the third loss function includes at least L1 loss function, L2 loss function and MSE loss function; Step 608, identifying whether the first loss value satisfies a preset first loss value range; if so, proceeding to step 609; if not, performing a round of parameter optimization on the structural optimization model in a direction of minimizing the first loss function based on a preset first model parameter optimizer, and returning to step 604 at the end of this round of parameter optimization; Wherein, the first model parameter optimizer includes at least an SGD optimizer and an ADAM optimizer; Step 609, identifying whether the second loss value satisfies a preset second loss value range; if so, proceeding to step 610; if not, performing a round of parameter optimization on the structural optimization model in a direction of minimizing the second loss function based on a preset second model parameter optimizer, and returning to step 604 at the end of this round of parameter optimization; Wherein, the second model parameter optimizer includes at least an SGD optimizer and an ADAM optimizer; Step 610, identifying whether the third loss value satisfies a preset third loss value range; if so, proceeding to step 611; if not, performing a round of parameter optimization on the structural optimization model in a direction of minimizing the third loss function based on a preset third model parameter optimizer, and returning to step 604 at the end of this round of parameter optimization; Wherein, the third model parameter optimizer includes at least an SGD optimizer and an ADAM optimizer; Step 611, identifying whether the first total loss value satisfies a preset fourth loss value range; if so, proceeding to step 612; if not, performing a round of parameter optimization on the structural optimization model in a direction of minimizing the first total loss value based on a preset fourth model parameter optimizer, and returning to step 604 at the end of this round of parameter optimization; Wherein, the fourth model parameter optimizer includes at least an SGD optimizer and an ADAM optimizer; Step 612, identifying whether the current test record is the last first data record in the first training set; if so, going to step 613; if not, taking the next first data record in the first training set as the new current test record and returning to step 603; Step 613: Count the total number of the first data records in the first evaluation set to obtain the corresponding total number of records N; traverse all the first data records in the first evaluation set; and during the traversal, use the first data record currently traversed as the corresponding current evaluation record; and input the first training molecular structure of the current evaluation record into the structure optimization model to perform three-dimensional structure optimization processing to obtain the corresponding first sample prediction structure x p,i , 1≤index i≤N; and the first label molecular structure of the current evaluation record is used as the corresponding first sample label structure x t,i ; and the first sample prediction structure x corresponding to the current evaluation record p,i And the first sample label structure x t,i Form a corresponding first sample prediction-label pair; Step 614, when the traversal of all the first data records of the first evaluation set is completed, all the first sample prediction-label pairs obtained are brought into a preset first evaluation function to calculate and obtain corresponding first evaluation values; The first evaluation function is implemented based on the RMSD function, specifically: Step 615, identifying whether the first evaluation value satisfies a preset first evaluation value range; if not, returning to step 601 to continue training; if satisfied, stopping training and confirming the end of pre-training.

7. The method for optimizing the structure of electrolyte formulation according to claim 2, characterized in that: The performing model tuning on the structural optimization model based on the second data set specifically includes: Step 701, based on a preset second training evaluation ratio, the second data set is randomly divided into two data sets and recorded as corresponding second training sets and second evaluation sets; Wherein, both the second training set and the second evaluation set include a plurality of second data records; the ratio of the total number of records in the second training set to the total number of records in the second evaluation set satisfies the second training evaluation ratio; Step 702, taking the first second data record in the second training set as the corresponding current test record; Step 703, extract the atomic identifier and the atomic element type of each atomic vector in the atomic tensor of the second label molecular structure of the current test record to form a corresponding second type label vector, and extract the atomic identifier and the atomic coordinate of each atomic vector to form a corresponding second coordinate label vector; and form a corresponding second type label tensor with all the obtained second type label vectors, and form a corresponding second coordinate label tensor with all the obtained second coordinate label vectors; and extract the chemical bond identifier and the chemical bond length of each chemical bond vector in the chemical bond tensor of the second label molecular structure to form a corresponding second bond length label vector, and form a corresponding second bond length label tensor with all the obtained second bond length label vectors; Step 704, inputting the second training molecular structure of the current test record into the structure optimization model to perform three-dimensional structure optimization processing to obtain a corresponding second predicted molecular structure; Wherein, the second predicted molecular structure includes the corresponding atomic tensor and the chemical bond tensor; Step 705, extract the atom identifier and the atomic element type of each atom vector in the atom tensor of the second predicted molecular structure as a corresponding second type prediction vector, and extract the atom identifier and the atomic coordinate of each atom vector as a corresponding second coordinate prediction vector; and form a corresponding second type prediction tensor with all the obtained second type prediction vectors, and form a corresponding second coordinate prediction tensor with all the obtained second coordinate prediction vectors; and extract the chemical bond identifier and the chemical bond length of each chemical bond vector in the chemical bond tensor of the second predicted molecular structure to form a corresponding second bond length prediction vector, and form a corresponding second bond length prediction tensor with all the obtained second bond length prediction vectors; Step 706, the obtained second type prediction tensor and the corresponding second type label tensor form a corresponding fourth prediction-label pair; the obtained second coordinate prediction tensor and the corresponding second coordinate label tensor form a corresponding fifth prediction-label pair; and the obtained second bond length prediction tensor and the corresponding second bond length label tensor form a corresponding sixth prediction-label pair; Step 707, bringing the fourth, fifth and sixth prediction-label pairs into the preset fourth, fifth and sixth loss functions to calculate the corresponding fourth, fifth and sixth loss values; and performing weighted sum calculation on the fourth, fifth and sixth loss values ​​and using the calculation result as the corresponding second total loss value; Among them, the fourth loss function at least includes L1 loss function, L2 loss function and multi-classification cross entropy loss function; the fifth loss function at least includes L1 loss function, L2 loss function and MSE loss function; the sixth loss function at least includes L1 loss function, L2 loss function and MSE loss function; Step 708, identifying whether the fourth loss value satisfies a preset fifth loss value range; if so, proceeding to step 709; if not, performing a round of parameter fine-tuning on the structural optimization model in a direction of minimizing the fourth loss function based on a preset fifth model parameter optimizer, and returning to step 704 at the end of this round of parameter fine-tuning; Wherein, the fifth model parameter optimizer includes at least RMSprop optimizer, ADAM optimizer, and AdamW optimizer; Step 709, identifying whether the fifth loss value satisfies a preset sixth loss value range; if so, proceeding to step 710; if not, performing a round of parameter fine-tuning on the structural optimization model in a direction of minimizing the fifth loss function based on a preset sixth model parameter optimizer, and returning to step 704 at the end of this round of parameter fine-tuning; Wherein, the sixth model parameter optimizer includes at least RMSprop optimizer, ADAM optimizer, and AdamW optimizer; Step 710, identifying whether the sixth loss value satisfies the preset seventh loss value range; if so, proceeding to step 711; if not, performing a round of parameter fine-tuning on the structural optimization model in the direction of minimizing the sixth loss function based on the preset seventh model parameter optimizer, and returning to step 704 at the end of this round of parameter fine-tuning; Wherein, the seventh model parameter optimizer includes at least RMSprop optimizer, ADAM optimizer, and AdamW optimizer; Step 711, identifying whether the second total loss value satisfies a preset eighth loss value range; if so, proceeding to step 712; if not, performing a round of parameter fine-tuning on the structural optimization model in a direction of minimizing the second total loss value based on a preset eighth model parameter optimizer, and returning to step 704 at the end of this round of parameter fine-tuning; Wherein, the eighth model parameter optimizer includes at least RMSprop optimizer, ADAM optimizer, and AdamW optimizer; Step 712, identifying whether the current test record is the last second data record in the second training set; if so, going to step 713; if not, taking the next second data record in the second training set as the new current test record and returning to step 703; Step 713: Count the total number of the second data records in the second evaluation set to obtain the corresponding total number of records M; traverse all the second data records in the second evaluation set; and during the traversal, use the second data record currently traversed as the corresponding current evaluation record; and input the second training molecular structure of the current evaluation record into the structure optimization model to perform three-dimensional structure optimization processing to obtain the corresponding second sample prediction structure x p,j , 1≤index j≤M; and the second label molecular structure of the current evaluation record is used as the corresponding second sample label structure x t,j ; and the second sample prediction structure x corresponding to the current evaluation record p,j And the second sample label structure x t,j Form a corresponding second sample prediction-label pair; Step 714, when the traversal of all the second data records of the second evaluation set is completed, all the obtained second sample prediction-label pairs are brought into a preset second evaluation function to calculate and obtain corresponding second evaluation values; The second evaluation function is implemented based on the RMSD function, specifically: Step 715, identifying whether the second evaluation value satisfies a preset second evaluation value range; if not, returning to step 701 to continue training; if satisfied, stopping training and confirming that the model tuning is complete.

8. A device for executing the method for optimizing the structure of electrolyte formula components according to any one of claims 1 to 7, characterized in that: The device comprises: a model building module, a data preparation module, a model training module and a model application module; The model building module is used to build a structure optimization model; the structure optimization model is implemented based on the Uni-Mol model; the structure optimization model is used to perform three-dimensional structure optimization processing on the original molecular structure input by the model and output the corresponding optimized molecular structure; The data preparation module is used to construct a corresponding first data set through big data collection; and to construct a corresponding second data set through molecular dynamics simulation; The model training module is used to pre-train the structure optimization model based on the first data set; and after the pre-training is completed, the structure optimization model is tuned based on the second data set; The model application module is used to use the electrolyte formula input by the user as the corresponding current electrolyte formula after the model tuning is completed; and use the preset chemical informatics tool to perform corresponding three-dimensional molecular structure modeling according to the molecular sequences of each component of the current electrolyte formula to obtain the corresponding component modeling structure; and based on the structure optimization model, perform three-dimensional structure optimization processing on each of the component modeling structures to obtain the corresponding component optimization structure; and each of the component molecular sequences and the corresponding component type and the component optimized structure form a corresponding formula component structure optimization record; and all the obtained formula component structure optimization records form a corresponding formula structure optimization report to feedback to the user; the current electrolyte formula includes multiple formula components; each of the formula components includes a component type and a component molecular sequence; the component types include solvents, electrolytes and additives; the component molecular sequence is a one-dimensional SMI LES sequence of solvent molecules, electrolyte molecules or additive molecules corresponding to the component type; the chemical informatics tool includes at least OpenBabel and RDKit.

9. An electronic device, characterized in that: include: memory, processors, and transceivers; The processor is used to couple with the memory, read and execute instructions in the memory, so as to implement the method according to any one of claims 1 to 7; The transceiver is coupled to the processor, and the processor controls the transceiver to send and receive messages.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and when the computer instructions are executed by a computer, the computer is enabled to execute the method according to any one of claims 1 to 7.

Images