Data cleaning method, device, system and storage medium for interstellar molecules

Abstract

The present application relates to a data cleaning method, device, system and storage medium for interstellar molecules, wherein the data cleaning method for interstellar molecules includes: obtaining basic compound information of the interstellar molecules to be cleaned; inputting the basic compound information of the interstellar molecules into a plurality of preset large language models for preliminary cleaning, and obtaining the one-dimensional structure of the interstellar molecules under different large language models; comparing the one-dimensional structures of the interstellar molecules under different large language models, and inputting the one-dimensional structures of the interstellar molecules that meet the preset requirements into the molecular linear input specification program for final cleaning, and obtaining the one-dimensional structure of the target interstellar molecules; the preset requirement is that the similarity of the one-dimensional structures of the interstellar molecules under different large language models meets the preset requirements; and storing the one-dimensional structure of the target interstellar molecules in the corresponding server. Through the present application, the problem of low efficiency of interstellar molecule data cleaning is solved, and the efficiency of interstellar molecule data cleaning is improved.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to a data cleaning method, device, system and storage medium for interstellar molecules. Background Art

[0002] Interstellar molecules refer to inorganic and organic molecules that exist in interstellar space. The discovery of these molecules was a major breakthrough in the astronomical community in the 1960s. For a long time, people believed that interstellar space was almost a vacuum except for celestial matter such as stars, planets, and nebulae. However, later studies found that interstellar space is actually full of tiny interstellar dust, thin interstellar gas, cosmic rays, and particle flows. More than 50 types of interstellar molecules have been discovered so far, including hydroxyl, carbon monoxide, nitrogen monsulfide, hydrogen cyanide, methanol, acetaldehyde, propiolonitrile, methylamine, etc. The study of interstellar molecules is of great significance to disciplines such as astroevolution, galactic structure, and cosmochemistry. There are many types of interstellar molecules, including organic molecules and inorganic molecules, some of which are even natural samples that do not exist on Earth, and even molecules that are difficult to exist stably in the laboratory. In order to conduct further research on interstellar molecules, the structure of interstellar molecules needs to be processed and cleaned. Currently, interstellar chemical molecules are mainly processed and cleaned directly through the Molecular Linear Input Specification (SMILES) encoding. However, interstellar chemical molecules are different from stable compounds in the laboratory or inside the earth. They contain a large number of charged molecules, free radical molecules, isotope substituted molecules, etc. Directly using the molecular linear input specification is time-consuming and complicated to operate. In addition, the molecular linear input specification cannot handle isotope substituted molecules, etc., resulting in low data cleaning efficiency.

[0003] There is currently no effective solution to the problem of low efficiency in cleaning interstellar molecule data in related technologies. Summary of the invention

[0004] In this embodiment, a method, device, system and storage medium for cleaning data of an interstellar molecule are provided to solve the problem of low efficiency of cleaning data of an interstellar molecule in the related art.

[0005] In a first aspect, in this embodiment, a method for cleaning data of interstellar molecules is provided, comprising:

[0006] Obtain basic information on the compounds of the interstellar molecules to be cleaned;

[0007] Input the basic compound information of interstellar molecules into multiple preset large language models for preliminary cleaning, and obtain the one-dimensional structure of interstellar molecules under different large language models;

[0008] Compare the one-dimensional structures of interstellar molecules under different large language models, input the one-dimensional structures of interstellar molecules that meet the preset requirements into the molecular linear input specification program for final cleaning, and obtain the one-dimensional structure of the target interstellar molecule; the preset requirement is that the similarity of the one-dimensional structures of interstellar molecules under different large language models meets the preset requirements;

[0009] The one-dimensional structure of the target interstellar molecule is stored in the corresponding server.

[0010] In some of the embodiments, the basic information of the interstellar molecules to be cleaned includes the serial number and chemical formula of the interstellar molecules.

[0011] In some of the embodiments, obtaining basic information of the interstellar molecules to be cleaned includes:

[0012] According to the preset interstellar molecule data set, the number and chemical formula of the interstellar molecule to be cleaned are determined.

[0013] In some of the embodiments, the preset interstellar molecular data set includes at least one of the following: National Institute of Standards and Technology chemical kinetics data, astrochemical kinetics data, Cologne molecular spectroscopy data, high-resolution transmission molecular absorption data, and Jet Propulsion Laboratory molecular spectroscopy data.

[0014] In some of these embodiments, the one-dimensional structure of the interstellar molecule includes the types, isotopes, free radicals, and charges of atoms in the molecule.

[0015] In some of the embodiments, if the one-dimensional structure of the interstellar molecule under different large language models does not meet the preset requirements, the one-dimensional structure of the interstellar molecule is output to the user so that the user can adjust the one-dimensional structure of the interstellar molecule according to the obtained one-dimensional structure of the interstellar molecule under different large language models.

[0016] In some of the embodiments, the one-dimensional structure of the interstellar molecule that meets the preset requirements is input into the molecular linear input specification program for final cleaning to obtain the one-dimensional structure of the target interstellar molecule, including:

[0017] Inputting the one-dimensional structure of the interstellar molecule that meets the preset requirements into the molecular linear input specification program, and verifying whether the one-dimensional structure of the interstellar molecule that meets the preset requirements meets the preset requirements of the molecular linear input specification program;

[0018] If yes, the data format of the one-dimensional structure of the interstellar molecule that meets the preset requirements of the molecular linear input specification program is unified to obtain the one-dimensional structure of the target interstellar molecule;

[0019] Otherwise, the one-dimensional structure of the interstellar molecule that meets the preset requirements is output to the user so that the user can adjust the one-dimensional structure of the interstellar molecule that meets the preset requirements, and then the one-dimensional structure of the interstellar molecule adjusted by the user is input into the molecular linear input specification program for unified data format processing to obtain the target one-dimensional structure of the interstellar molecule.

[0020] In the second aspect, in this embodiment, a data cleaning device for interstellar molecules is provided, comprising: an acquisition module, a large model rough cleaning module, an interactive cleaning module and a storage module, wherein:

[0021] An acquisition module is used to obtain basic information of compounds of interstellar molecules to be cleaned;

[0022] The large model rough cleaning module is used to input the basic information of interstellar molecules into multiple preset large language models for preliminary cleaning, and obtain the one-dimensional structure of interstellar molecules under different large language models;

[0023] The interactive cleaning module is used to compare the one-dimensional structures of interstellar molecules under different large language models, and input the one-dimensional structures of interstellar molecules that meet the preset requirements into the molecular linear input specification program for final cleaning to obtain the target one-dimensional structure of interstellar molecules; the preset requirement is that the similarity of the one-dimensional structures of interstellar molecules under different large language models meets the preset requirements;

[0024] The storage module is used to store the one-dimensional structure of the target interstellar molecule in the corresponding server.

[0025] In a third aspect, in this embodiment, a data cleaning system for interstellar molecules is provided, which uses the data cleaning method for interstellar molecules described in the first aspect, including: an interaction subsystem and a storage subsystem; wherein:

[0026] The interactive subsystem includes an input unit, a judgment unit and an output unit, wherein:

[0027] An input unit is used to input the one-dimensional structure of interstellar molecules that meets the preset requirements output by various language models;

[0028] A judgment unit, used for making a structural rational judgment on the input one-dimensional structure of each interstellar molecule;

[0029] An output unit, used for outputting to a user an unreasonable one-dimensional structure of an interstellar molecule, or outputting a reasonable one-dimensional structure of a target interstellar molecule;

[0030] The storage subsystem is used to store chemical formulas and target interstellar one-dimensional structures during the interstellar molecule data cleaning process.

[0031] In a fourth aspect, a storage medium is provided in this embodiment, on which a computer program is stored, and when the program is executed by a processor, the interstellar molecule data cleaning method described in the first aspect is implemented.

[0032] Compared with the related art, the data cleaning method of interstellar molecules provided in this embodiment obtains the basic information of the compounds of the interstellar molecules to be cleaned; inputs the basic information of the compounds of the interstellar molecules into a plurality of preset large language models for preliminary cleaning to obtain the one-dimensional structures of the interstellar molecules under different large language models; compares the one-dimensional structures of the interstellar molecules under different large language models, inputs the one-dimensional structures of the interstellar molecules that meet the preset requirements into the molecular linear input specification program for final cleaning to obtain the one-dimensional structure of the target interstellar molecule; the preset requirement is that the similarity of the one-dimensional structures of the interstellar molecules under different large language models meets the preset requirements; and stores the one-dimensional structure of the target interstellar molecule in the corresponding server, which solves the problem of low efficiency of interstellar molecule data cleaning and improves the efficiency of interstellar molecule data cleaning.

[0033] Details of one or more embodiments of the present application are set forth in the following drawings and description to make other features, objects, and advantages of the present application more readily apparent. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0035] Figure 1 It is a hardware structure block diagram of a terminal of the interstellar molecule data cleaning method of this embodiment.

[0036] Figure 2 It is a flow chart of the data cleaning method of the interstellar molecule of this embodiment.

[0037] Figure 3 It is a flow chart of another method for cleaning data of interstellar molecules according to this embodiment.

[0038] Figure 4 It is a structural block diagram of the data cleaning device of the interstellar molecule of this embodiment.

[0039] Figure 5 It is a schematic diagram of the structure of the data cleaning system of the interstellar molecule of this embodiment. DETAILED DESCRIPTION

[0040] In order to more clearly understand the purpose, technical solutions and advantages of the present application, the present application is described and illustrated below in conjunction with the accompanying drawings and embodiments.

[0041] Unless otherwise defined, the technical terms or scientific terms involved in this application shall have the general meaning understood by people with general skills in the technical field to which this application belongs. The words "one", "a", "the", "these" and the like in this application do not indicate a quantitative limitation, and they may be singular or plural. The terms "include", "comprise", "have" and any variants thereof involved in this application are intended to cover non-exclusive inclusions; for example, a process, method and system, product or device comprising a series of steps or modules (units) is not limited to the listed steps or modules (units), but may include unlisted steps or modules (units), or may include other steps or modules (units) inherent to these processes, methods, products or devices. The words "connect", "connected", "coupled" and the like involved in this application are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. The "multiple" involved in this application refers to two or more. "And / or" describes the association relationship of associated objects, indicating that there may be three relationships, for example, "A and / or B" may mean: A exists alone, A and B exist at the same time, and B exists alone. Generally, the character " / " indicates that the objects associated with each other are in an "or" relationship. The terms "first", "second", "third", etc. in this application are only used to distinguish similar objects and do not represent a specific ordering of the objects.

[0042] The method embodiment provided in this embodiment can be executed in a terminal, a computer or a similar computing device. For example, running on a terminal, Figure 1 : is a hardware structure block diagram of a terminal of the interstellar molecule data cleaning method of this embodiment. Figure 1 As shown, the terminal may include one or more ( Figure 1 Only one is shown in the figure) a processor 102 and a memory 104 for storing data, wherein the processor 102 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA. The above terminal may also include a transmission device 106 and an input and output device 108 for communication functions. It can be understood by those skilled in the art that Figure 1 The structure shown is for illustration only and does not limit the structure of the above terminal. Figure 1 More or fewer components as shown, or with Figure 1 Different configurations shown.

[0043] The memory 104 can be used to store computer programs, for example, software programs and modules of application software, such as the computer program corresponding to the data cleaning method of interstellar molecules in this embodiment. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, that is, to implement the above method. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include a memory remotely arranged relative to the processor 102, and these remote memories may be connected to the terminal via a network. Examples of the above network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0044] The transmission device 106 is used to receive or send data via a network. The above network includes a wireless network provided by the communication provider of the terminal. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, referred to as NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 106 can be a radio frequency (Radio Frequency, referred to as RF) module, which is used to communicate with the Internet wirelessly.

[0045] In this embodiment, a method for cleaning data of interstellar molecules is provided. Figure 2 is a flow chart of the data cleaning method of the interstellar molecule of this embodiment, such as Figure 2 As shown, the process includes the following steps:

[0046] Step S201, obtaining basic compound information of the interstellar molecules to be cleaned.

[0047] According to the existing interstellar molecular data sets, the chemical formulas of interstellar chemical species are extracted and sorted out from the existing interstellar molecular data sets through the application of large language models. For example, the reaction species in astrochemical data sets such as the KInetic Database for Astrochemistry (KIDA), the National Institute of Standards and Technology Chemical Kinetics Database (NIST), the High-resolution transmission molecular absorption database (Hitran), the Cologne Database for Molecular Spectroscopy (CDMS), and the Jet Propulsion Laboratory (JPL) are trained through the large language model to obtain the chemical formulas of these interstellar chemical species. For example, from JPL, the molecular formulas of compounds such as methanol (CH3OH), ethanol (C2H5OH), dimethyl ether (C2H6O), and methyl cyanide (CH3CN) can be identified. Since the chemical formula formats of compounds given by different data sets are not necessarily the same, in order to improve the comparability of subsequent cleaning results, the formats of the chemical formulas of interstellar chemical species obtained by training these large language models are standardized and named uniformly, and the designated interstellar molecules are obtained from the interstellar chemical species after the unified format. The designated interstellar molecules are the interstellar molecules to be cleaned, and the basic information of the compounds of the interstellar molecules to be cleaned is extracted at the same time. Among them, the basic information of the compounds of the interstellar molecules to be cleaned includes the number and chemical formula of the compound, and the components of the interstellar molecules can be accurately obtained through the basic information of the compound. The acquisition process can be completed by a variety of terminal devices, such as desktop computers, laptops, and servers, etc., which are not specifically limited in this embodiment.

[0048] Step S202, inputting the basic compound information of the interstellar molecule into a plurality of preset large language models for preliminary cleaning, and obtaining the one-dimensional structure of the interstellar molecule under different large language models.

[0049] Specifically, in the prior art, data cleaning of interstellar molecules is performed by directly inputting the molecular linear input specification. The molecular linear input specification (SMILES) is a specification that uses an ASCII string to explicitly describe the molecular structure, which includes specifications for atomic representation, hydrogen atom omission, chemical bond representation, and branch and ring. For example, the specification for atomic representation is that atoms are represented by their atomic symbols, the second letter of the double-character symbol must be entered in lowercase letters, and each non-hydrogen atom is independently specified by its atomic symbol enclosed in square brackets "[]". For atoms such as boron (B) atoms, carbon (C) atoms, nitrogen (N) atoms, oxygen (O) atoms, phosphorus (P) atoms, sulfur (S) atoms, fluorine (F) atoms, chlorine (Cl) atoms, bromine (Br) atoms, and iodine (I) atoms, if the number of connected hydrogen atoms is the same as the lowest positive valence of the atom, then [] can be omitted. For example, the specification for chemical bond representation is single bonds, where single bonds can usually be omitted and adjacent atoms are connected by single bonds by default; double bonds, triple bonds, and aromatic bonds are represented by symbols "-", "=", and "#", respectively. Since the molecular linear input specification itself has many regulations, and interstellar molecules are different from stable compounds in the laboratory or inside the earth, interstellar molecules contain a large number of charged molecules, free radical molecules and isotope substituted molecules, such as many charged molecules in interstellar space, such as HCO+, HN2+ and HCS+. In SMILES coding, charged molecules need to be specially marked with charge states, such as HCO+ can be expressed as "[H][C@@](=O)[O+]"; in the processing of isotope substituted molecules, additional special processing is also required. The above makes the encoding of interstellar molecules under the molecular linear input specification in the prior art complicated and difficult, resulting in low data cleaning efficiency of interstellar molecules. In this embodiment, a large language model is used to perform preliminary cleaning of the basic compound information of the interstellar molecules to be cleaned, and the one-dimensional structure of the interstellar molecules is obtained through the large language model, and the work of obtaining the one-dimensional structure of the interstellar molecules is separated from the molecular linear input specification, thereby reducing the encoding work of the molecular linear input specification and improving the cleaning efficiency. Among them, in this embodiment, the basic compound information of the interstellar molecules to be cleaned is input into multiple large language models, among which the large language models used in this embodiment are Qwen2.5, chatgpt, Wenxinyiyan, kimi, etc. For the selection of a specific large language model, it can be selected according to the actual situation, and this embodiment does not make specific restrictions on this. The Qwen2.5 model contains a training set of 18T (trillion) tokens data, and is a model implemented using the self-attention mechanism and the Transformer architecture. The training set of ChatGPT-4o contains 13T (trillion) tokens (token is a word or sub-word unit in model training), which is a large language model implemented based on the Transformer architecture using the self-attention mechanism (Self-Attention).The Wenxinyiyan model contains a training set of about 15T (trillion) tokens data. Its core construction is based on the self-attention mechanism of Transformer. It is a model that supports efficient parallel computing, training optimization and multimodal processing. The Kimi model brings together a huge training set of 2 million Chinese characters (approximately 4 million tokens), and adopts the self-attention mechanism and Transformer architecture. The Kimi model also uses lossless compression technology to compress a large amount of text for reasoning. Through the auxiliary instructions of the large language model, the basic compound data of the interstellar molecule to be cleaned is input into different large language models and converted into the one-dimensional structure of the interstellar molecule under different large models. That is, the basic compound information of the interstellar molecule is input into different large language models for preliminary cleaning, and the one-dimensional structure of the interstellar molecule corresponding to the output of different large language models is obtained.

[0050] Step S203, compare the one-dimensional structures of interstellar molecules under different large language models, input the one-dimensional structures of interstellar molecules that meet the preset requirements into the molecular linear input specification program for final cleaning, and obtain the target one-dimensional structure of interstellar molecules; the preset requirement is that the similarity of the one-dimensional structures of interstellar molecules under different large language models meets the preset requirements.

[0051] Specifically, the corresponding one-dimensional structures of interstellar molecules are output by different large language models, and the one-dimensional structures of interstellar molecules output by different large language models are annotated through coding programs such as International Chemical Identifier (InChI) and molecular linear input specification SMILES. The differences of the one-dimensional structures of interstellar molecules output by different large language models are compared. From the differences in the comparison, it can be found whether there are isotope-substituted molecules, etc. Since it is currently impossible to automatically identify and process isotope-substituted molecules, the output of interstellar molecules with large differences is manually adjusted through comparison, and the one-dimensional structures of interstellar molecules with small differences are identified as interstellar molecules that meet the preset requirements. Small differences mean that the one-dimensional structures of interstellar molecules output by the major language models have high similarity, that is, the similarity is higher than the preset similarity threshold; similarly, large differences mean that the similarity is lower than the preset similarity threshold, wherein the similarity threshold can be set according to actual conditions, and this embodiment does not make specific restrictions on this. The one-dimensional structures of interstellar molecules that meet the requirements are input into the molecular linear input specification program for final cleaning. Since the one-dimensional structure of the interstellar molecule has been obtained, there is no need to obtain the one-dimensional structure of the interstellar molecule during the final cleaning in the molecular linear input specification program. It is only necessary to verify the format of the input one-dimensional structure of the interstellar molecule or the rationality of the structure, and the verified one-dimensional structure of the interstellar molecule is identified as the target one-dimensional structure of the interstellar molecule.

[0052] Step S204, storing the target interstellar molecule one-dimensional structure in the corresponding server.

[0053] Specifically, a unified storage format is determined, and data normalization is performed on the one-dimensional structure of the target interstellar molecule. The normalized data is uniformly stored in the corresponding server, wherein the normalized data can be saved in the disk or downloaded to the local disk, and this embodiment does not make any specific limitation to this.

[0054] Through the above steps S201 to S204, the basic information of the compound of the interstellar molecule to be cleaned is obtained; the basic information of the compound of the interstellar molecule is input into a plurality of preset large language models for preliminary cleaning, and the one-dimensional structure of the interstellar molecule under different large language models is obtained; the one-dimensional structures of the interstellar molecule under different large language models are compared, and the one-dimensional structure of the interstellar molecule that meets the preset requirements is input into the molecular linear input specification program for final cleaning, and the one-dimensional structure of the target interstellar molecule is obtained; the preset requirement is that the similarity of the one-dimensional structure of the interstellar molecule under different large language models meets the preset requirements; the one-dimensional structure of the target interstellar molecule is stored in the corresponding server. Compared with the prior art in which data is cleaned by directly inputting the interstellar molecule into the molecular linear input specification, the present embodiment inputs the basic information of the target interstellar compound into each major language model, outputs the one-dimensional structure of the interstellar molecule corresponding to each major language model through each major language model, compares the one-dimensional structure of the interstellar molecule corresponding to each major language model, and inputs the one-dimensional structure of the interstellar molecule that meets the requirements into the molecular linear input specification program to unify the data format, obtains the one-dimensional structure of the target interstellar molecule, and stores the one-dimensional structure of the target interstellar molecule in the corresponding server. Among them, the interstellar compounds that need to be cleaned are initially cleaned through various language models, which replaces the action of standardizing the molecular structure of interstellar molecules in the molecular linear input specification. Only the data format is unified in the molecular linear input specification, avoiding the problem of complex and inefficient cleaning caused by directly inputting interstellar molecules into the molecular linear input specification for cleaning, and improving the efficiency of interstellar molecular data cleaning.

[0055] In one embodiment, the basic information of the interstellar molecules to be cleaned includes the serial number and chemical formula of the interstellar molecules.

[0056] Specifically, the number of the interstellar molecule is a unique identifier assigned to the molecule for the convenience of identification and classification, wherein the number can be a simple sequence of numbers or a complex coding system, through which a specific molecule can be quickly referenced in a database or research. The number does not contain information about the chemical composition of the molecule and is a system designed for the convenience of management and retrieval. The chemical formula describes the expression of the atomic composition and quantity in a molecule. It provides the precise composition of the molecule, including which elements and the quantity of these elements. The chemical properties and reactivity of the molecule are understood through the chemical formula. In this embodiment, the basic information of the interstellar molecule to be cleaned includes the number and chemical formula of the interstellar molecule, wherein the specific molecule of the interstellar molecule to be cleaned is determined by the number of the interstellar molecule, and the specific component of the interstellar molecule to be cleaned is determined by the chemical formula, thereby obtaining accurate basic information of the interstellar molecule to be cleaned.

[0057] In another embodiment, obtaining basic information of the interstellar molecules to be cleaned includes:

[0058] The serial number and chemical formula of the interstellar molecule to be cleaned are determined according to a preset interstellar molecule data set, wherein the preset interstellar molecule data set includes at least one of the following: chemical kinetics data of the National Institute of Standards and Technology, astrochemical kinetics data, Cologne molecular spectroscopy data, high-resolution transmission molecular absorption data, and Jet Propulsion Laboratory molecular spectroscopy data.

[0059] Specifically, by collecting the reaction species in the preset interstellar molecule data set, inputting these reaction species into the large language model for training, obtaining the numbers and chemical formulas of the reaction species, and extracting the numbers and chemical formulas of the interstellar molecules to be cleaned from the numbers and chemical formulas of these reaction species. Among them, the preset interstellar molecule data set can be at least one of the following data sets: astrochemical kinetics data (KInetic Database for Astrochemistry, referred to as KIDA), chemical kinetics data of the National Institute of Standards and Technology (National Institute of Standardsand Technology Chemical Kinetics Database, referred to as NIST), high-resolution transmission molecular absorption data (High-resolution transmission molecular absorption database, referred to as Hitran), Cologne Database for Molecular Spectroscopy (The Cologne Database for Molecular Spectroscopy, referred to as CDMS), Jet Propulsion Laboratory molecular spectroscopy data (Jet Propulsion Laboratory, referred to as JPL). The numbers and chemical formulas of interstellar molecules can be extracted from one data set, or they can be extracted in combination with multiple data sets, which is not specifically limited in this embodiment.

[0060] NIST provides thermochemical data for more than 7,000 organic and small inorganic compounds, including information such as formation enthalpy, combustion enthalpy, specific heat capacity, entropy, phase change enthalpy and temperature, and vapor pressure. It provides infrared spectral data for more than 16,000 compounds. It provides mass spectral data for more than 33,000 compounds. It provides electronic and vibrational spectral data for more than 5,000 compounds.

[0061] KIDA is a database containing interstellar dust and aerosol data, which provides data on the physical and chemical properties of interstellar dust and aerosols.

[0062] CDMS is a molecular spectroscopy database that contains a large amount of molecular spectroscopy data.

[0063] JPL provides a database of interstellar and solar system molecules, which includes information such as the chemical formula and spectral properties of the molecules.

[0064] Hitran is a database containing spectral parameters of molecules in the atmosphere.

[0065] In one embodiment, the one-dimensional structure of an interstellar molecule includes the types, isotopes, free radicals, and charges of atoms in the molecule.

[0066] Through various language models, the numbers and chemical formulas of the interstellar molecules to be cleaned are converted into one-dimensional structures of interstellar molecules, wherein the one-dimensional structure of the interstellar molecules includes the types of atoms, isotopes, free radicals and charges in the molecules. By comparing the atomic types, isotopes, free radicals and charges of the one-dimensional structures of interstellar molecules output by various language models, it is determined whether the one-dimensional structure of the interstellar molecules meets the requirements. When these elements are the same, it is determined that the one-dimensional structure of the interstellar molecule meets the requirements.

[0067] In another embodiment, if the one-dimensional structure of the interstellar molecule under different large language models does not meet the preset requirements, the one-dimensional structure of the interstellar molecule is output to the user so that the user can adjust the one-dimensional structure of the interstellar molecule according to the obtained one-dimensional structure of the interstellar molecule under different large language models.

[0068] Specifically, the one-dimensional structure of the corresponding interstellar molecule is output through different large language models. When comparing the one-dimensional structures of interstellar molecules output by different large language models, if it is found that the isotopes in the one-dimensional structure of the interstellar molecule are different and there are large differences, that is, the one-dimensional structure of the interstellar molecule is determined to be not in compliance with the preset requirements, and the one-dimensional structure of the interstellar molecule with the difference is preferentially interacted with the user. The user manually confirms and adjusts the one-dimensional structure of the interstellar molecule according to the comparison result to the correct one-dimensional structure. After the adjustment, the one-dimensional structure of the interstellar molecule is input into the molecular linear input specification program for final cleaning. When other components in the one-dimensional structure of the interstellar molecule are different during the comparison, the same output processing is also performed, which will not be repeated here.

[0069] In some embodiments, the one-dimensional structure of the interstellar molecule that meets the preset requirements is input into the molecular linear input specification program for final cleaning to obtain the one-dimensional structure of the target interstellar molecule, including:

[0070] Inputting the one-dimensional structure of the interstellar molecule that meets the preset requirements into the molecular linear input specification program, and verifying whether the one-dimensional structure of the interstellar molecule that meets the preset requirements meets the preset requirements of the molecular linear input specification program;

[0071] If so, the data format of the one-dimensional structure of the interstellar molecule that meets the preset requirements of the molecular linear input specification program is unified to obtain the target one-dimensional structure of the interstellar molecule; otherwise, the one-dimensional structure of the interstellar molecule that meets the preset requirements is output to the user so that the user can adjust the one-dimensional structure of the interstellar molecule that meets the preset requirements, and then the one-dimensional structure of the interstellar molecule adjusted by the user is input into the molecular linear input specification program for data format unification processing to obtain the target one-dimensional structure of the interstellar molecule.

[0072] Specifically, after obtaining the one-dimensional structure of the interstellar molecule that meets the requirements, it is input into the molecular linear input specification program, and the molecular linear input specification program is used to verify whether the one-dimensional structure of the interstellar molecule meets the requirements of the molecular linear input specification program, including the rationality judgment of the one-dimensional structure. If it meets the requirements of the molecular linear input specification program, the one-dimensional structure of the interstellar molecule is unified in data format to obtain the cleaned one-dimensional structure of the interstellar molecule, that is, the target one-dimensional structure of the interstellar molecule. If the one-dimensional structure of the interstellar molecule does not meet the requirements of the molecular linear input specification program, such as the structure is not reasonable, at this time, the one-dimensional structure of the interstellar molecule is output to the user, and the user manually adjusts the one-dimensional structure of the interstellar molecule according to the requirements of the molecular linear input specification program, and the adjusted one-dimensional structure of the interstellar molecule is input into the molecular linear input specification program for format unification to obtain the cleaned one-dimensional structure of the interstellar molecule, that is, the target one-dimensional structure of the interstellar molecule.

[0073] This embodiment also provides a method for cleaning data of interstellar molecules. Figure 3 is a flow chart of another method for cleaning data of interstellar molecules in this embodiment. Figure 3 As shown, the process includes the following steps:

[0074] Step S301, determining the serial number and chemical formula of the interstellar molecule to be cleaned according to a preset interstellar molecule data set;

[0075] Step S302, inputting the basic information of the compound of the interstellar molecule into a plurality of preset large language models for preliminary cleaning, and obtaining the one-dimensional structure of the interstellar molecule under different large language models;

[0076] Step S303, determining whether the one-dimensional structures of interstellar molecules under different large language models meet the preset similarity requirements, if so, executing step S304, otherwise, executing step S308;

[0077] Step S304, inputting the one-dimensional structure of the interstellar molecule that meets the preset requirements into the molecular linear input specification program;

[0078] Step S305, determining whether the one-dimensional structure of the interstellar molecule that meets the preset requirements meets the preset requirements of the molecular linear input specification program, if so, executing step S306, otherwise, executing step S309;

[0079] Step S306, unifying the data format of the one-dimensional structure of the interstellar molecule that meets the preset requirements of the molecular linear input specification program to obtain the one-dimensional structure of the target interstellar molecule;

[0080] Step S307, storing the target interstellar molecule one-dimensional structure in the corresponding server.

[0081] Step S308, outputting the one-dimensional structure of the interstellar molecule to the user, so that the user can adjust the one-dimensional structure of the interstellar molecule according to the obtained one-dimensional structure of the interstellar molecule under different large language models to obtain the one-dimensional structure of the interstellar molecule that meets the preset requirements; and returning to execute step S304;

[0082] Step S309, outputting the one-dimensional structure of the interstellar molecule that meets the preset requirements to the user, so that the user can adjust the one-dimensional structure of the interstellar molecule that meets the preset requirements to obtain the one-dimensional structure of the interstellar molecule that meets the preset requirements of the molecular linear input specification program; and executing step S306.

[0083] Through the above steps S301 to S309, compared with the prior art of directly inputting interstellar molecules into the molecular linear input specification for data cleaning, this embodiment obtains the number and chemical formula of the target interstellar compound through a preset database, inputs the number and chemical formula of the target interstellar compound into various language models, outputs the one-dimensional structure of the interstellar molecule corresponding to each language model through each language model, compares the one-dimensional structure of the interstellar molecule corresponding to each language model, inputs the one-dimensional structure of the interstellar molecule that meets the requirements into the molecular linear input specification program to verify whether the structure is reasonable, unifies the data format of the rationalized one-dimensional structure of the interstellar molecule, obtains the one-dimensional structure of the target interstellar molecule, and stores the one-dimensional structure of the target interstellar molecule in the corresponding server. Among them, the interstellar molecules that need to be cleaned are preliminarily cleaned through various language models, replacing the action of performing molecular structure standardization on the interstellar molecules in the molecular linear input specification, and only unifying the data format in the molecular linear input specification, avoiding the problem of complex cleaning and low efficiency caused by directly inputting the interstellar molecules into the molecular linear input specification for cleaning, and improving the efficiency of interstellar molecule data cleaning.

[0084] In this embodiment, a data cleaning device for interstellar molecules is also provided, which is used to implement the above-mentioned embodiments and preferred implementation modes, and the descriptions that have been made will not be repeated. The terms "module", "unit", "subunit", etc. used below can be a combination of software and / or hardware that implements the predetermined functions. Although the devices described in the following embodiments are preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0085] Figure 4 is a structural block diagram of the data cleaning device for interstellar molecules of this embodiment, such as Figure 4 As shown, the device 40 includes: an acquisition module 41, a large model rough cleaning module 42, an interactive cleaning module 43 and a storage module 44, wherein:

[0086] An acquisition module 41 is used to acquire basic information of compounds of interstellar molecules to be cleaned;

[0087] A large model rough cleaning module 42 is used to input the basic information of the compound of the interstellar molecule into a plurality of preset large language models for preliminary cleaning, so as to obtain the one-dimensional structure of the interstellar molecule under different large language models;

[0088] The interactive cleaning module 43 is used to compare the one-dimensional structures of interstellar molecules under different large language models, and input the one-dimensional structures of interstellar molecules that meet the preset requirements into the molecular linear input specification program for final cleaning to obtain the target one-dimensional structure of interstellar molecules; the preset requirement is that the similarity of the one-dimensional structures of interstellar molecules under different large language models meets the preset requirements;

[0089] The storage module 44 is used to store the one-dimensional structure of the target interstellar molecule in the corresponding server.

[0090] It should be noted that the above modules can be functional modules or program modules, and can be implemented by software or hardware. For modules implemented by hardware, the above modules can be located in the same processor; or the above modules can be located in different processors in any combination.

[0091] Figure 5 : is a schematic diagram of the structure of the data cleaning system of the interstellar molecule of this embodiment. Figure 5 As shown, the system 50 includes: an interaction subsystem 51 and a storage subsystem 52; wherein,

[0092] The interaction subsystem 51 includes an input unit 511, a judgment unit 512 and an output unit 513, wherein:

[0093] An input unit 511 is used to input the one-dimensional structure of interstellar molecules that meets preset requirements output by various language models;

[0094] A judgment unit 512 is used to make a structural rationality judgment on each input one-dimensional structure of interstellar molecules;

[0095] An output unit 513 is used to output an unreasonable one-dimensional structure of an interstellar molecule to a user, or to output a reasonable one-dimensional structure of a target interstellar molecule;

[0096] The storage subsystem 52 is used to store the chemical formula and one-dimensional structure of the target interstellar molecule in the process of interstellar molecule data cleaning.

[0097] In this embodiment, an electronic device is further provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor is configured to run the computer program to execute the steps in any one of the above method embodiments.

[0098] Optionally, the electronic device may further include a transmission device and an input / output device, wherein the transmission device is connected to the processor, and the input / output device is connected to the processor.

[0099] Optionally, in this embodiment, the processor may be configured to perform the following steps through a computer program:

[0100] S1, obtain the basic information of the compounds of the interstellar molecules to be cleaned;

[0101] S2, inputting the basic information of the compounds of the interstellar molecules into multiple preset large language models for preliminary cleaning, and obtaining the one-dimensional structure of the interstellar molecules under different large language models;

[0102] S3, compare the one-dimensional structures of interstellar molecules under different large language models, input the one-dimensional structures of interstellar molecules that meet the preset requirements into the molecular linear input specification program for final cleaning, and obtain the one-dimensional structure of the target interstellar molecule; the preset requirement is that the similarity of the one-dimensional structures of interstellar molecules under different large language models meets the preset requirements;

[0103] S4, storing the one-dimensional structure of the target interstellar molecule in the corresponding server.

[0104] It should be noted that the specific examples in this embodiment can refer to the examples described in the above embodiments and optional implementation modes, and will not be repeated in this embodiment.

[0105] In addition, in combination with the data cleaning method for interstellar molecules provided in the above embodiments, a storage medium can also be provided in this embodiment to implement the method. The storage medium stores a computer program; when the computer program is executed by a processor, any of the data cleaning methods for interstellar molecules in the above embodiments is implemented.

[0106] It should be understood that the specific embodiments described herein are only used to explain the application, rather than to limit it. Based on the embodiments provided in this application, all other embodiments obtained by ordinary technicians in this field without creative work are within the protection scope of this application.

[0107] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties.

[0108] Obviously, the drawings are only some examples or embodiments of the present application. For ordinary technicians in the field, the present application can also be applied to other similar situations based on these drawings without creative work. In addition, it is understandable that although the work done in this development process may be complicated and lengthy, for ordinary technicians in the field, certain changes in design, manufacturing or production based on the technical content disclosed in this application are only conventional technical means and should not be regarded as insufficient content disclosed in this application.

[0109] The term "embodiment" in this application refers to a specific feature, structure or characteristic described in conjunction with the embodiment that can be included in at least one embodiment of the present application. The appearance of this phrase in various locations in the specification does not necessarily mean the same embodiment, nor does it mean that it is mutually exclusive with other embodiments and is independent or optional. It is clearly or implicitly understood by those of ordinary skill in the art that the embodiments described in this application can be combined with other embodiments without conflict.

[0110] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.

[0111] The above-mentioned embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of patent protection. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the scope of protection of the present application. Therefore, the scope of protection of the present application shall be subject to the attached claims.

Claims

1. A method for cleaning interstellar molecule data, characterized in that: include: Obtaining basic information of compounds of interstellar molecules to be cleaned; wherein the basic information of compounds of interstellar molecules to be cleaned includes the serial number and chemical formula of the interstellar molecules; Inputting the basic compound information of the interstellar molecule into a plurality of preset large language models for preliminary cleaning to obtain the one-dimensional structure of the interstellar molecule under different large language models; Comparing the one-dimensional structures of interstellar molecules under the different large language models, inputting the one-dimensional structures of interstellar molecules that meet the preset requirements into the molecular linear input specification program for final cleaning, and obtaining the one-dimensional structure of the target interstellar molecule; the preset requirement is that the similarity of the one-dimensional structures of interstellar molecules under the different large language models meets the preset requirements; The one-dimensional structure of the target interstellar molecule is stored in a corresponding server.

2. The data cleaning method of interstellar molecules according to claim 1, characterized in that: The basic information of the interstellar molecules to be cleaned includes the serial number and chemical formula of the interstellar molecules.

3. The data cleaning method of interstellar molecules according to claim 1, characterized in that: The basic information of the interstellar molecules to be cleaned is obtained, including: According to a preset interstellar molecule data set, the serial number and chemical formula of the interstellar molecule to be cleaned are determined.

4. The data cleaning method of interstellar molecules according to claim 3, characterized in that: The preset interstellar molecular data set includes at least one of the following: chemical kinetics data of the National Institute of Standards and Technology, astrochemical kinetics data, Cologne molecular spectroscopy data, high-resolution transmission molecular absorption data, and Jet Propulsion Laboratory molecular spectroscopy data.

5. The method for cleaning interstellar molecule data according to claim 1, characterized in that: The one-dimensional structure of the interstellar molecule includes the types, isotopes, free radicals and charges of atoms in the molecule.

6. The method for cleaning interstellar molecule data according to claim 1, characterized in that: The method further comprises: If the one-dimensional structure of the interstellar molecule under the different large language models does not meet the preset requirements, the one-dimensional structure of the interstellar molecule is output to the user, so that the user can adjust the one-dimensional structure of the interstellar molecule according to the obtained one-dimensional structure of the interstellar molecule under the different large language models.

7. The method for cleaning interstellar molecule data according to claim 1, characterized in that: The one-dimensional structure of the interstellar molecule that meets the preset requirements is input into the molecular linear input specification program for final cleaning to obtain the one-dimensional structure of the target interstellar molecule, including: Inputting the one-dimensional structure of the interstellar molecule that meets the preset requirements into the molecular linear input specification program, and verifying whether the one-dimensional structure of the interstellar molecule that meets the preset requirements meets the preset requirements of the molecular linear input specification program; If yes, then the data format of the one-dimensional structure of the interstellar molecule that meets the preset requirements of the molecular linear input specification program is unified to obtain the one-dimensional structure of the target interstellar molecule; Otherwise, the one-dimensional structure of the interstellar molecule that meets the preset requirements is output to the user so that the user can adjust the one-dimensional structure of the interstellar molecule that meets the preset requirements, and then the one-dimensional structure of the interstellar molecule adjusted by the user is input into the molecular linear input specification program for unified data format processing to obtain the target one-dimensional structure of the interstellar molecule.

8. A data cleaning device for interstellar molecules, characterized in that: include: Acquisition module, large model rough cleaning module, interactive cleaning module and storage module, among which, The acquisition module is used to acquire basic information of compounds of interstellar molecules to be cleaned; wherein the basic information of compounds of interstellar molecules to be cleaned includes the serial number and chemical formula of the interstellar molecules; The large model rough cleaning module is used to input the basic compound information of the interstellar molecule into a plurality of preset large language models for preliminary cleaning to obtain the one-dimensional structure of the interstellar molecule under different large language models; The interactive cleaning module is used to compare the one-dimensional structures of interstellar molecules under the different large language models, input the one-dimensional structures of interstellar molecules that meet the preset requirements into the molecular linear input specification program for final cleaning, and obtain the one-dimensional structure of the target interstellar molecule; the preset requirement is that the similarity of the one-dimensional structures of interstellar molecules under the different large language models meets the preset requirements; The storage module is used to store the one-dimensional structure of the target interstellar molecule in a corresponding server.

9. An interstellar molecule data cleaning system, using the interstellar molecule data cleaning method according to any one of claims 1 to 7, characterized in that: include: Interaction subsystem and storage subsystem; among them, The interaction subsystem includes an input unit, a judgment unit and an output unit, wherein: The input unit is used to input the one-dimensional structure of interstellar molecules that meets the preset requirements and is output by various language models; The judgment unit is used to make a structural rationalization judgment on each input one-dimensional structure of the interstellar molecule; The output unit is used to output the one-dimensional structure of the interstellar molecule with an unreasonable structure to the user, or to output the one-dimensional structure of the target interstellar molecule with a reasonable structure; The storage subsystem is used to store the chemical formula and one-dimensional structure of the target interstellar molecule in the process of interstellar molecule data cleaning.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the interstellar molecule data cleaning method according to any one of claims 1 to 7 are implemented.

Images