Method and device for identifying unknown mass molecule structure
By detecting and processing infrared spectra, using linear regression decision tree model to identify unknown mass molecules, the problem of difficulty in identification and classification in the prior art is solved, and rapid and accurate identification and classification is achieved.
Patent Information
- Application Number
- CN202510184952.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-02-19
- Publication Date
- 2025-06-13
AI Technical Summary
The prior art is difficult to quickly identify and classify unknown molecular structures through infrared spectrograms, resulting in difficulty in identifying and classifying them.
By detecting the absorption intensity of infrared light of different wavelengths of substance molecules, the infrared absorption spectrum is obtained, and normalized processing is performed to obtain the feature set. Then, the feature set is processed using a pre-established linear regression decision tree model to determine the species of matter molecules.
It realizes rapid identification and classification of infrared spectra of unknown mass molecules structures, improves recognition accuracy, reduces workload, and improves work efficiency.
Smart Images
Figure CN120142210A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of information processing, and particularly to a method and device for identifying the structure of unknown mass molecules. Background Art
[0002] For some groups or chemical bonds in a molecule, the corresponding band wave numbers in different compounds are basically fixed or only vary within a small wavelength range. Therefore, many organic functional groups, such as methyl, methylene, carbonyl, cyano, hydroxyl, amino, etc., have characteristic absorptions in the infrared spectrum. By measuring the infrared spectrum, people can determine which organic functional groups are present in an unknown sample, which lays a foundation for ultimately determining the chemical structure of the unknown substance. When a beam of infrared light with continuous wavelengths passes through a substance, when the vibration frequency or rotation frequency of a certain group in the substance molecule is the same as the frequency of the infrared light, the molecule absorbs energy and transitions from the original ground-state vibration (rotation) energy level to a higher vibration energy level. After the molecule absorbs infrared radiation, transitions of vibration and rotation energy levels occur, and the light of that wavelength is absorbed by the substance. Based on this, infrared spectroscopy is commonly used to determine the structure of substance molecules and identify compounds according to information such as the relative vibration between atoms inside the molecule and molecular rotation. Due to the different contents of various substances, the near-infrared spectra are also different. It is very difficult to use the differences existing in such spectra to identify and classify the structures of unknown mass molecules. Summary of the Invention
[0003] The main object of the present invention is to provide a method and device for identifying the structure of unknown mass molecules to solve the deficiencies existing in the related technologies.
[0004] To achieve the above object, according to the first aspect of the present invention, a method for identifying the structure of unknown mass molecules is provided, including detecting the absorption intensity of a substance molecule for infrared light of different wavelengths and obtaining the infrared absorption spectrum of the substance molecule; performing normalization processing on the infrared absorption spectrum to obtain a specified feature set of the substance molecule; and using a pre-established linear regression decision tree model to process the feature set to obtain the type of the substance molecule.
[0005] Optionally, performing normalization processing on the infrared absorption spectrum to obtain a specified feature set of the substance molecule includes: performing normalization processing on the infrared absorption spectrum to obtain a strong peak information set corresponding to the substance molecule, the wavelength of the maximum absorption peak, the wavelength of the minimum absorption peak, the maximum molar absorption coefficient, and the number, position, and inflection point information set of the absorption peaks.
[0006] Optionally, the processing of the feature set using the pre-established linear regression decision tree model to obtain the type of the substance molecule includes: processing the feature set using the pre-established linear regression decision tree model to obtain the type of the substance molecule, and calling the pre-stored standard spectral data corresponding to different known substance molecules from the standard library; processing the feature set and the standard spectral data using the pre-established linear regression decision tree model to obtain the type of the substance molecule.
[0007] Optionally, the normalization processing of the infrared absorption spectrum to obtain the specified feature set of the substance molecule includes: analyzing the infrared absorption spectrum to obtain the first strong peak; based on the first strong peak, further analyzing to obtain the second strong peak and the third strong peak; wherein, the processing of the feature set using the pre-established linear regression decision tree model to obtain the type of the substance molecule includes: if the type of the substance molecule cannot be determined based on the first strong peak, the second strong peak, and the third strong peak, then using the pre-established linear regression decision tree model to determine the type of the substance molecule.
[0008] Optionally, using the pre-established linear regression decision tree model to determine the type of the substance molecule includes: for the substance molecule with interacting functional groups, using the pre-established linear regression decision tree model to determine the type of the substance molecule; wherein, obtaining the maximum absorption peak wavelength, the minimum absorption peak wavelength, the maximum molar absorption coefficient, and the information set of the number, position, and inflection point of the absorption peak as the input information; inputting the input information into the linear regression decision tree model and outputting a decision suggestion.
[0009] According to the second aspect of the present invention, there is provided an unknown substance molecule structure recognition device, including a detection unit for detecting the absorption intensity of the substance molecule to infrared light of different wavelengths and obtaining the infrared absorption spectrum of the substance molecule; a processing unit for normalizing the infrared absorption spectrum to obtain the specified feature set of the substance molecule; and an identification unit for processing the feature set using the pre-established linear regression decision tree model to obtain the type of the substance molecule.
[0010] Optionally, the normalization processing of the infrared absorption spectrum to obtain the specified feature set of the substance molecule includes: normalizing the infrared absorption spectrum to obtain the strong peak information set, the maximum absorption peak wavelength, the minimum absorption peak wavelength, the maximum molar absorption coefficient, and the information set of the number, position, and inflection point of the absorption peak corresponding to the substance molecule.
[0011] Optionally, the processing of the feature set using the pre-established linear regression decision tree model to obtain the types of the substance molecules includes: processing the feature set using the pre-established linear regression decision tree model to obtain the types of the substance molecules; calling the pre-stored standard spectral data corresponding to different known substance molecules from a standard library; processing the feature set and the standard spectral data using the pre-established linear regression decision tree model to obtain the types of the substance molecules
[0012] According to a third aspect of the present invention, there is provided a computer-readable storage medium storing computer instructions for causing a computer to execute the method according to any one of the first aspect.
[0013] According to a fourth aspect of the present invention, there is provided an electronic device including: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor to cause the at least one processor to execute the method according to any one of the implementation manners of the first aspect.
[0014] The method and device for identifying the structure of an unknown substance molecule in this embodiment, wherein the method includes detecting the absorption intensity of a substance molecule for infrared light of different wavelengths and obtaining the infrared absorption spectrum of the substance molecule; performing normalization processing on the infrared absorption spectrum to obtain a specified feature set of the substance molecule; processing the feature set using a pre-established linear regression decision tree model to obtain the type of the substance molecule. The infrared spectrum of the unknown substance molecule structure is quickly identified and classified by the linear regression decision tree, which improves the accuracy of cognition, and at the same time can reduce the workload of workers and improve work efficiency. Description of the Drawings
[0015] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following will briefly introduce the drawings required for use in the description of the specific embodiments or the prior art. Obviously, the following drawings are some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.
[0016] Figure 1 is a flowchart of the method for identifying the structure of an unknown substance molecule according to an embodiment of the present invention;
[0017] Figure 2 is a schematic diagram of the electronic device according to an embodiment of the present invention. Detailed Embodiments
[0018] To enable those skilled in the art to better understand the solution of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the scope of protection of the present invention.
[0019] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and do not necessarily need to describe a specific order or sequence. It should be understood that such data can be interchanged under appropriate circumstances so as to describe the embodiments of the present invention here. In addition, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device comprising a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products or devices.
[0020] It should be noted that, without conflict, the embodiments in the present invention and the features in the embodiments can be combined with each other. The present invention will be described in detail below with reference to the drawings and in conjunction with the embodiments.
[0021] According to an embodiment of the present invention, a method for identifying the structure of an unknown mass molecule is provided, as Figure 1 shown, including the following steps 101 to 103:
[0022] Step 101: Detect the absorption intensity of the substance molecule for infrared light of different wavelengths, and obtain the infrared absorption spectrum of the substance molecule.
[0023] In this step, the absorption intensity of the substance molecule for infrared light of different wavelengths is obtained, so as to obtain the data and information of the infrared absorption spectrum of the substance. Infrared absorption spectroscopy is when infrared light of a certain wavelength irradiates a substance. If the frequency of the infrared light can meet the transition frequency conditions of the vibration energy levels of certain groups in the substance molecule, then the molecule absorbs the radiation energy of this wavelength of infrared light, causing a change in the dipole moment, and transitioning from the ground state vibration energy level to a higher energy excited state vibration energy level. By detecting the absorption intensity of the substance molecule for infrared light of different wavelengths, the infrared absorption spectrum of the substance can be obtained.
[0024] Step 102: Perform normalization processing on the infrared absorption spectrum to obtain the specified feature set of the substance molecule.
[0025] As an optional implementation manner of this embodiment, normalize the infrared absorption spectrum to obtain the specified feature set of the substance molecules, including: normalizing the infrared absorption spectrum to obtain the strong peak information set corresponding to the substance molecules, the maximum absorption peak wavelength, the minimum absorption peak wavelength, the maximum molar absorptivity, and the number, position, and inflection point information set of the absorption peaks.
[0026] In this step, normalize the infrared spectrum data and information of different wavelengths corresponding to the molecules of different substances obtained to obtain the characteristic information sets of the first, second, and third strong peaks in the characteristic regions to which the molecules of different substances belong, as well as the maximum absorption peak wavelength, the minimum absorption peak wavelength, the maximum molar absorptivity, and the number, position, and inflection point information set of the absorption peaks, etc.
[0027] Step 103: Process the feature set using a pre-established linear regression decision tree model to obtain the type of the substance molecules.
[0028] In this step, when establishing the standard information library, the infrared absorption spectra of different substance molecules can be determined in the manner of steps 101 and 102, and the characteristic information sets of the first, second, and third strong peaks in the characteristic regions to which the molecules of different substances belong, as well as the maximum absorption peak wavelength, the minimum absorption peak wavelength, the maximum molar absorptivity, and the number, position, and inflection point information set of the absorption peaks, etc., can be determined, so as to establish a standard information library of infrared spectra of different wavelengths corresponding to different substance molecules.
[0029] As an optional implementation manner of this embodiment, the process of using a pre-established linear regression decision tree model to process the feature set to obtain the type of the substance molecules includes: using a pre-established linear regression decision tree model to process the feature set to obtain the type of the substance molecules, and calling the pre-stored standard spectral data corresponding to different known substance molecules from the standard library; using a pre-established linear regression decision tree model to process the feature set and the standard spectral data to obtain the type of the substance molecules.
[0030] In this alternative implementation, an unknown molecular structure's infrared spectrum is recognized and identified through a learning model. In statistics, linear regression is a regression analysis that models the relationship between one or more independent variables and a dependent variable using a least-squares function called a linear regression equation. This function is a linear combination of one or more model parameters called regression coefficients. The case with only one independent variable is called simple regression, and the case with more than one independent variable is called multiple regression. The idea of a decision tree is as follows. Suppose there are two attributes A and B, each with two values 0 and 1. When A = 0 and B = 0, it is a chicken; when A = 0 and B = 1, it is a duck; when A = 1 and B = 0, it is a cat; when A = 1 and B = 1, it is a dog. From this reasoning, if the maximum absorption peak wavelength, minimum absorption peak wavelength, maximum molar absorptivity, and the number, position, and inflection points of the absorption peaks of the ultraviolet absorption spectrum of the unknown molecular structure are exactly the same as the standard spectral data, it can be considered the same compound. Otherwise, it is other organic compounds.
[0031] As an alternative implementation of this embodiment, the infrared absorption spectrum is normalized to obtain the specified characteristic set of the substance molecules, including: parsing the infrared absorption spectrum to obtain the first strong peak; based on the first strong peak, continuing to parse to obtain the second strong peak and the third strong peak; among them, using a pre-established linear regression decision tree model to process the characteristic set to obtain the type of the substance molecule, including: if the type of the substance molecule cannot be determined based on the first strong peak, the second strong peak, and the third strong peak, then use the pre-established linear regression decision tree model to determine the type of the substance molecule.
[0032] In this alternative implementation, the infrared spectra of different substances are different, mainly including the stretching vibration peak and bending vibration peak of the Si-O bond, the Si-OH characteristic peak, the Si-O-Si characteristic peak, the vibration and stretching characteristic peak of -OH, etc. Spectral analysis starts from the first strong peak in the characteristic region to confirm the possible attribution, and then finds the peaks related to the first strong peak. After the first strong peak is confirmed, the second strong peak and the third strong peak in the characteristic region are parsed again using the same method. For simple spectra, generally parsing one or two groups of related peaks can determine the molecular structure of the unknown substance. For the spectra of complex compounds, due to the mutual influence of functional groups, the analysis is difficult. After a rough analysis, the standard spectrum can be checked or a comprehensive spectral analysis can be carried out.
[0033] Based on the aforementioned linear regression decision tree model, if the maximum absorption peak wavelength, minimum absorption peak wavelength, maximum molar absorptivity, and the number, position, and inflection points of the absorption peaks of the ultraviolet absorption spectrum of the unknown molecular structure are exactly the same as the standard spectral data, it can be considered the same compound. Otherwise, it is other organic compounds.
[0034] For example, different functional groups exhibit peaks at different wavelengths, and the numbers represent the wavelengths of the peaks. For instance, if a carbonyl group is present in the molecular structure, there will be a strong absorption peak at a wavelength of 1680. Another example is the important characteristic of aromatic compounds: generally, four peaks with varying intensities may appear at 1600, 1580, 1500, and 1450 cm-1. The out-of-plane bending vibration absorption of C-H in the range of 880 - 680 cm-1 varies depending on the number and position of substituents on the benzene ring. In the analysis of the infrared spectra of aromatic compounds, the absorption in this frequency range is often used to distinguish isomers.
[0035] During analysis, attention should be paid to linking the relevant peaks describing each functional group to accurately determine the presence of the functional group. For example, the three peaks at 2820, 2720, and 1750 - 1700 cm-1 indicate the presence of an aldehyde group.
[0036] As an alternative implementation of this embodiment, determining the type of a substance molecule using a pre-established linear regression decision tree model includes: for a substance molecule with interacting functional groups, using the pre-established linear regression decision tree model to determine the type of the substance molecule; wherein, obtaining the maximum absorption peak wavelength, the minimum absorption peak wavelength, the maximum molar absorptivity, as well as the set of information on the number, position, and inflection points of the absorption peaks as input information; inputting the input information into the linear regression decision tree model, and outputting a decision recommendation.
[0037] In this alternative implementation, when the model is established
[0038] 1), input x = [x1, x2, x3, x4], where x1 is the maximum absorption peak wavelength; x2 is the minimum absorption peak wavelength; x3 is the maximum molar absorptivity; x4 is the number of absorption peaks, x5 is the position of the absorption peaks, x6 is the inflection point of the absorption peaks, etc.;
[0039] 2), measure m sets of input data and denote i = 1 ~ m;
[0040] 3), define the sigmoid function and the classification boundary function to integrate into the logistic regression model function;
[0041] 4), define the cost function, and use the gradient descent method to solve for the maximum or minimum value of the cost function, where i = 1, 2,..., m is the number of samples, and j = 1, 2,..., n is the number of features;
[0042] 5), substitute θ into the logistic regression model function and draw the classification boundary;
[0043] 6), substitute the newly measured sample to obtain the value of its output y(i + 1);
[0044] 7), if yi + 1 = 0, then output the decision recommendation as "the same compound";
[0045] 8) If yi+1 = 1, then it is necessary to calculate the outputs for the corresponding new samples by imitating Steps 2 to 4 respectively:
[0046] When yi+1 = 1, the output decision recommendation is "not the same compound";
[0047] When yi+1 = 0, the output decision recommendation is "other isomers";
[0048] Step 8: Add the (i + 1)-th measurement result into the logistic regression model function, and repeat Steps 2 to 5 to calculate a new classification boundary.
[0049] Perform registration and cognitive analysis on the provided infrared spectrum information and data of the unknown molecular structure according to the above model, and generate the results of infrared spectrum recognition and classification of the corresponding unknown molecular structure. For example, analyze the C-H stretching vibration absorption in the region of 3300 - 2800 cm-1. Taking 3000 cm-1 as the boundary: above 3000 cm-1 is the unsaturated carbon C-H stretching vibration absorption, which may be alkenes, alkynes, or aromatic compounds, while below 3000 cm-1 is generally the saturated C-H stretching vibration absorption; if there is absorption slightly above 3000 cm-1, then in the frequency range of 2250 - 1450 cm-1, analyze the characteristic peaks of the stretching vibration absorption of unsaturated carbon-carbon bonds, among which: alkynes are at 2200 - 2100 cm-1; alkenes are at 1680 - 1640 cm-1; aromatic rings are at 1600, 1580, 1500, 1450 cm-1; if it has been determined to be an alkene or aromatic compound, then further analyze the fingerprint region, that is, the frequency range of 1000 - 650 cm-1, to determine the number and position of substituents; after determining the carbon skeleton type, then based on other functional groups, such as the characteristic absorptions of C=O, O-H, C-N, etc., to determine the functional groups of the compound. Here, when analyzing, it should be noted to connect the relevant peaks describing each functional group to accurately determine the existence of the functional group. For example, the three peaks at 2820, 2720, and 1750 - 1700 cm-1 indicate the existence of an aldehyde group.
[0050] It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although the logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in a different order than here.
[0051] According to an embodiment of the present invention, there is also provided a device for identifying the structure of an unknown substance molecule, including a detection unit configured to detect the absorption intensity of a substance molecule for infrared light of different wavelengths and obtain the infrared absorption spectrum of the substance molecule; a processing unit configured to perform normalization processing on the infrared absorption spectrum to obtain a specified feature set of the substance molecule; and an identification unit configured to process the feature set by using a pre-established linear regression decision tree model to obtain the type of the substance molecule.
[0052] As an optional implementation manner of this embodiment, performing normalization processing on the infrared absorption spectrum to obtain a specified feature set of the substance molecule includes: performing normalization processing on the infrared absorption spectrum to obtain a strong peak information set corresponding to the substance molecule, the wavelength of the maximum absorption peak, the wavelength of the minimum absorption peak, the maximum molar absorption coefficient, and the number, position, and inflection point information set of the absorption peaks.
[0053] As an optional implementation manner of this embodiment, the processing the feature set by using a pre-established linear regression decision tree model to obtain the type of the substance molecule includes: processing the feature set by using a pre-established linear regression decision tree model to obtain the type of the substance molecule; calling pre-stored standard spectral data corresponding to different known substance molecules from a standard library; and processing the feature set and the standard spectral data by using a pre-established linear regression decision tree model to obtain the type of the substance molecule.
[0054] According to an embodiment of the present invention, there is also provided an electronic device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and when the instructions are executed by the at least one processor, the at least one processor is enabled to implement the method described in any of the above embodiments.
[0055] According to an embodiment of the present invention, there is also provided a readable storage medium storing computer instructions for enabling a computer to implement the method described in any of the above embodiments when executed.
[0056] According to an embodiment of the present invention, there is also provided a computer program product, which can implement the method described in any of the above embodiments when executed by a processor.
[0057] Figure 2FIG. 0 shows a schematic block diagram of an exemplary electronic device 300 that can be used to implement embodiments of the present invention. The electronic device is intended to represent various forms of digital computers, such as, for example, laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as, for example, personal digital assistants, cellular phones, smart phones, wearable devices, and other similar computing devices.
[0058] As Figure 2 shown, the electronic device 300 includes a computing unit 301 that can perform various appropriate actions and processes in accordance with a computer program stored in a read-only memory (ROM) 302 or a computer program loaded from a storage unit 308 into a random access memory (RAM) 303. In the RAM 303, various programs and data required for the operation of the electronic device 300 can also be stored. The computing unit 301, the ROM 302, and the RAM 303 are connected to each other via a bus 304. An input / output (I / O) interface 305 is also connected to the bus 304.
[0059] A plurality of components in the electronic device 300 are connected to the I / O interface 305, including: an input unit 306, such as a keyboard, a mouse, etc.; an output unit 307, such as various types of displays, speakers, etc.; a storage unit 308, such as a magnetic disk, an optical disk, etc.; and a communication unit 309, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 309 allows the electronic device 300 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.
[0060] The computing unit 301 can be various general-purpose and / or special-purpose processing components having processing and computing capabilities. Some examples of the computing unit 301 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 301 executes the various methods and processes described above, such as the object matching method. For example, in some embodiments, the object matching method can be implemented as a computer software program that is tangibly embodied in a machine-readable medium, such as the storage unit 308. In some embodiments, part or all of the computer program can be loaded and / or installed onto the electronic device 300 via the ROM 302 and / or the communication unit 309. When the computer program is loaded into the RAM 303 and executed by the computing unit 301, one or more steps of the methods described above can be executed.
[0061] The various embodiments of the systems and techniques described above in this specification can be implemented in digital electronic circuitry, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on a chip (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include: being implemented in one or more computer programs that are executable and / or interpretable on a programmable system including at least one programmable processor, which can be a special-purpose or general-purpose programmable processor that receives data and instructions from, and transmits data and instructions to, a storage system, at least one input device, and at least one output device.
[0062] The program code for implementing the methods of the present invention can be written in any combination of one or more programming languages. These program codes can be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the program codes, when executed by the processor or controller, cause the functions / operations specified in the flowchart and / or block diagram to be implemented. The program code can execute entirely on the machine, partly on the machine, as a stand-alone software package partly on the machine and partly on a remote machine or entirely on the remote machine or server.
[0063] In the context of the present invention, a machine-readable medium can be a tangible medium that can contain or store a program for use by or in connection with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
Claims
1. A method for identifying the molecular structure of an unknown substance, characterized in that: include: Detecting the absorption intensity of infrared light of different wavelengths by the substance molecules and obtaining the infrared absorption spectrum of the substance molecules; Normalizing the infrared absorption spectrum to obtain a specified feature set of the substance molecules; The feature set is processed using a pre-established linear regression decision tree model to obtain the type of the substance molecule.
2. The method for identifying the molecular structure of an unknown substance according to claim 1, characterized in that: The infrared absorption spectrum is normalized to obtain the specified feature set of the substance molecule, including: The infrared absorption spectrum is normalized to obtain a strong peak information set, a maximum absorption peak wavelength, a minimum absorption peak wavelength, a maximum molar absorption coefficient, and the number, position, and inflection point information set of the absorption peaks corresponding to the substance molecules.
3. The method for identifying the molecular structure of an unknown substance according to claim 2, characterized in that: The pre-established linear regression decision tree model is used to process the feature set to obtain the types of the substance molecules, including: The feature set is processed using a pre-established linear regression decision tree model to obtain the type of the substance molecule and to call pre-stored standard spectral data corresponding to different known substance molecules from a standard library; The feature set and the standard spectrum data are processed using a pre-established linear regression decision tree model to obtain the type of the substance molecule.
4. The method for identifying the molecular structure of an unknown substance according to claim 3, characterized in that: The infrared absorption spectrum is normalized to obtain the specified feature set of the substance molecule, including: The infrared absorption spectrum is analyzed to obtain the first strong peak; Based on the first strong peak, continue to analyze to obtain the second strong peak and the third strong peak; Among them, using a pre-established linear regression decision tree model to process the feature set to obtain the type of the substance molecule includes: if the type of the substance molecule cannot be determined based on the first strong peak, the second strong peak, and the third strong peak, then using a pre-established linear regression decision tree model to determine the type of the substance molecule.
5. The method for identifying the molecular structure of an unknown substance according to claim 4, characterized in that: Determining the type of substance molecules by using a pre-established linear regression decision tree model includes: determining the type of substance molecules by using a pre-established linear regression decision tree model for substance molecules with mutually influencing functional groups; wherein, obtaining a maximum absorption peak wavelength, a minimum absorption peak wavelength, a maximum molar absorptivity, and the number, position, and inflection point information set of absorption peaks as input information; The input information is input into a linear regression decision tree model to output a decision suggestion.
6. A device for identifying the molecular structure of an unknown substance, characterized in that: include: A detection unit, used to detect the absorption intensity of the substance molecules to infrared light of different wavelengths, and obtain the infrared absorption spectrum of the substance molecules; A processing unit, used for normalizing the infrared absorption spectrum to obtain a specified feature set of the substance molecules; The identification unit is used to process the feature set using a pre-established linear regression decision tree model to obtain the type of the substance molecule.
7. The unknown substance molecular structure recognition device according to claim 6, characterized in that: The infrared absorption spectrum is normalized to obtain the specified feature set of the substance molecule, including: The infrared absorption spectrum is normalized to obtain a strong peak information set, a maximum absorption peak wavelength, a minimum absorption peak wavelength, a maximum molar absorption coefficient, and the number, position, and inflection point information set of the absorption peaks corresponding to the substance molecules.
8. The unknown substance molecular structure recognition device according to claim 7, characterized in that: The pre-established linear regression decision tree model is used to process the feature set to obtain the types of the substance molecules, including: The feature set is processed using a pre-established linear regression decision tree model to obtain the type of the substance molecule and to call pre-stored standard spectral data corresponding to different known substance molecules from a standard library; The feature set and the standard spectrum data are processed using a pre-established linear regression decision tree model to obtain the type of the substance molecule.
9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable the computer to execute the method according to any one of claims 1 to 5.
10. An electronic device, characterized in that: include: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor executes the method described in any one of claims 1-5.