Functional group identification method, device, and storage medium based on infrared spectroscopy

Abstract

This invention discloses a method, apparatus, and storage medium for functional group identification based on infrared spectroscopy, relating to the field of infrared spectroscopy analysis technology. The method includes: determining spectral data based on the infrared spectrum of the compound to be tested, the spectral data including the observed peak position and observed peak intensity of at least one observed peak; identifying the number of supporting peaks associated with candidate functional groups based on the observed peak intensity; calculating supporting peak support scores based on the number of supporting peaks; matching the observed peak position with the standard center wavenumber of the candidate functional group to obtain a peak position matching score; mapping the observed peak intensity to a peak intensity score, and matching the peak intensity score with the typical peak intensity score of the candidate functional group to obtain a peak intensity matching score; performing a weighted summation of the peak position matching score, peak intensity matching score, and supporting peak support score to obtain a comprehensive score; normalizing the comprehensive score to obtain the confidence level of the candidate functional group; and determining the target functional group matching the compound to be tested based on the confidence levels of multiple candidate functional groups.

Description

Technical Field

[0001] This invention relates to the field of infrared spectroscopy analysis technology, and in particular to a method, apparatus and storage medium for functional group identification based on infrared spectroscopy. Background Technology

[0002] With the development of infrared spectroscopy, the identification of organic compounds is increasingly aided by infrared spectroscopy. The principle of infrared spectroscopy is to obtain functional group characteristic information by the absorption of infrared radiation of specific frequencies by molecules.

[0003] Current automated identification methods based on infrared spectroscopy cannot accurately identify the functional groups of organic compounds represented by infrared spectra. Therefore, how to accurately identify the functional groups of organic compounds based on infrared spectroscopy has become an urgent problem to be solved. Summary of the Invention

[0004] This invention provides a method, apparatus, and storage medium for functional group identification based on infrared spectroscopy, in order to solve the problem of inaccurate identification of functional groups in organic compounds.

[0005] According to one aspect of the present invention, a functional group identification method based on infrared spectroscopy is provided, comprising:

[0006] Based on the infrared spectrum of the compound to be tested, determine the spectral data, which includes the observed peak position and observed peak intensity of at least one observed peak.

[0007] The number of supporting peaks associated with candidate functional groups is identified based on the observed peak intensity; the supporting peak support score is calculated based on the number of supporting peaks.

[0008] The observed peak position is matched with the standard center wavenumber of the candidate functional group to obtain the peak position matching score;

[0009] The observed peak intensity is mapped to a peak intensity score, and the peak intensity score is matched with the typical peak intensity scores of the candidate functional groups to obtain a peak intensity matching score.

[0010] The comprehensive score is obtained by weighted summation of the peak position matching score, the peak strength matching score, and the supporting peak score.

[0011] The confidence level of the candidate functional group is obtained by normalizing the comprehensive score; the target functional group matching the test compound is determined based on the confidence levels of multiple candidate functional groups.

[0012] According to another aspect of the present invention, a functional group recognition device based on infrared spectroscopy is provided, comprising:

[0013] The observation module is used to determine spectral data based on the infrared spectrum of the compound to be tested. The spectral data includes the observation peak position and observation peak intensity of at least one observation peak.

[0014] The corroborating peak score calculation module is used to identify the number of corroborating peaks related to candidate functional groups based on the observed peak intensity; and to calculate the corroborating peak support score based on the number of corroborating peaks.

[0015] The peak position matching score determination module is used to match the observed peak position with the standard center wavenumber of the candidate functional group to obtain the peak position matching score.

[0016] The peak intensity matching score determination module is used to map the observed peak intensity to a peak intensity score, and match the peak intensity score with the typical peak intensity score of the candidate functional group to obtain the peak intensity matching score.

[0017] The comprehensive score determination module is used to perform a weighted summation based on the peak position matching score, the peak strength matching score, and the supporting peak score to obtain a comprehensive score.

[0018] The target functional group determination module is used to normalize the comprehensive score to obtain the confidence level of the candidate functional group; and to determine the target functional group that matches the test compound based on the confidence levels of multiple candidate functional groups.

[0019] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0020] At least one processor; and

[0021] A memory communicatively connected to the at least one processor; wherein,

[0022] The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the functional group identification method based on infrared spectroscopy according to any embodiment of the present invention.

[0023] According to another aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions for causing a processor to execute and implement the functional group identification method based on infrared spectroscopy as described in any embodiment of the present invention.

[0024] The technical solution of this invention determines the observation peak position and intensity of at least one observation peak based on infrared spectroscopy, and calculates the supporting peak score, peak position matching score, and peak intensity matching score, respectively. A weighted sum of these three scores yields a comprehensive score corresponding to the candidate functional group, thus evaluating the similarity between the candidate functional group and the test compound from three dimensions. The confidence level of the candidate functional group is obtained through normalization. By comparing the confidence levels of multiple candidate functional groups, the candidate functional group with the highest confidence level is selected as the target functional group, improving the accuracy of functional group identification.

[0025] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0026] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0027] Figure 1 A flowchart illustrating a functional group identification method based on infrared spectroscopy provided in an embodiment of the present invention;

[0028] Figure 2 A flowchart illustrating another functional group identification method based on infrared spectroscopy provided in an embodiment of the present invention;

[0029] Figure 3 A schematic diagram of a functional group recognition device based on infrared spectroscopy provided in an embodiment of the present invention;

[0030] Figure 4 A schematic diagram of the structure of an electronic device for implementing the functional group identification method based on infrared spectroscopy in this embodiment of the invention. Detailed Implementation

[0031] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0032] It should be noted that the terms "comprising" and "having" and any variations thereof in the specification, claims and accompanying drawings of this invention are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are explicitly listed, but may include other steps or units that are not explicitly listed or that are inherent to such processes, methods, products or devices.

[0033] The inventors discovered that with the development of infrared spectroscopy technology, the identification of organic compounds is increasingly aided by infrared spectroscopy technology. The principle of infrared spectroscopy technology is to obtain functional group characteristic information by the absorption of infrared radiation of specific frequencies by molecules.

[0034] Current automated identification methods based on infrared spectroscopy cannot accurately identify the functional groups of organic compounds represented by infrared spectra. Therefore, how to accurately identify the functional groups of organic compounds based on infrared spectroscopy has become an urgent problem to be solved.

[0035] Figure 1 This is a schematic flowchart of a functional group identification method based on infrared spectroscopy provided by an embodiment of the present invention. This embodiment is applicable to the identification of functional groups in organic compounds based on infrared spectra. The method can be executed by an infrared spectroscopy-based functional group identification device, which can be implemented in hardware and / or software and can be configured in electronic devices such as personal computers, laptops, smart devices, mobile devices, or servers. Figure 1 As shown, the method includes:

[0036] Step S101: Determine the spectral data based on the infrared spectrum of the compound to be tested. The spectral data includes the observation peak position (w_obs) and observation peak intensity (I_obs) of at least one observation peak.

[0037] Optionally, the spectral data can be determined based on the infrared spectrum of the compound to be tested, which can be done in the following ways:

[0038] The infrared spectrum of the compound to be tested is preprocessed, including baseline correction, smoothing and denoising, and numerical normalization.

[0039] The peak height of each observation peak is determined by identifying the absorbance at the peak position based on the preprocessed infrared spectrum. The relative intensity of each observation peak is obtained by normalizing the highest peak in the infrared spectrum. The peak height and the relative intensity together constitute the peak intensity. The observation peak position of each observation peak is also determined by identifying the peak position based on the preprocessed infrared spectrum.

[0040] Infrared spectroscopy preprocessing includes baseline correction, smoothing and denoising, and numerical normalization. Specifically, baseline correction eliminates baseline irregularities caused by sample scattering, instrument drift, etc. Smoothing and denoising uses algorithms such as sliding window algorithms based on least-squares polynomial fitting (e.g., Savitzky-Golay smoothing algorithm) to reduce spectral noise. Numerical normalization normalizes the spectral intensity to a uniform range, eliminating the influence of factors such as sample concentration.

[0041] Based on the above preprocessing, peak intensity data can also be identified in the infrared spectrum. Specifically, absorption peaks in the spectrum are automatically identified, and for each identified absorption peak, the following two types of peak intensity information are extracted: Observed peak height (PeakHeight): the absorbance value at the peak position, in AU. Relative intensity (Relative Intensity): the percentage of the current peak's intensity after normalizing the highest peak intensity of all peaks in the spectrum to 100%. The observed peak height and relative intensity together constitute the observed peak intensity (I_obs). The observed peak position (w_obs) refers to the position of the observed peak (also known as the absorption peak) in wavenumber or wavelength.

[0042] The above-described embodiments can preprocess the infrared spectrum and represent the observed peak intensity by the observed peak height and the relative intensity, thereby increasing the observed peak intensity by increasing the peak height and relative intensity, making the observed peak intensity more accurate.

[0043] The execution order of steps S102, S103, and S104 is not important; they can be executed sequentially or simultaneously. Before executing steps S102, S103, and S104, the characteristic data of each functional group is pre-constructed, including: the standard central wavenumber (w_std), peak position deviation standard deviation (σ_w), typical peak intensity (I_std), strong peak interval, weak peak interval, and weighting coefficients (w_w, w_I, w_e) for each functional group.

[0044] Step S102: Identify the number of supporting peaks associated with candidate functional groups based on the observed peak intensity; calculate the supporting peak support score (S_e) based on the number of supporting peaks.

[0045] Optionally, the number of supporting peaks associated with candidate functional groups can be identified based on the observed peak intensity, which can be done in the following way:

[0046] Obtain multiple attribution peaks contained in candidate functional groups;

[0047] Within the strong peak interval, the number of observed peaks matching the attributed main peak is identified as the number of strong supporting peaks; within the weak peak interval, the number of observed peaks matching the attributed main peak is identified as the number of weak supporting peaks; the lower limit of the strong peak interval is greater than or equal to the upper limit of the weak peak interval.

[0048] Optionally, the peak range can be 4000. ~1330 The weak peak range can be 1330. ~400 .

[0049] The above implementation method can count the number of observed peaks and the assigned main peak in the strong peak interval and the weak peak interval respectively, obtain the number of strong supporting peaks and the number of weak supporting peaks, realize the identification of auxiliary feature peaks other than the main peak, and obtain auxiliary structural information other than the main peak.

[0050] Optionally, the supporting score for the supporting peaks can be calculated based on the number of supporting peaks, which can be implemented in the following manner:

[0051] The support score of the evidence peaks is obtained by weighted summation of the number of strong evidence peaks n_strong, the weight of the strong evidence peaks w_strong, the number of weak evidence peaks n_weak, and the weight of the weak evidence peaks w_weak, where the weight of the strong evidence peaks is greater than the weight of the weak evidence peaks.

[0052] S_e = w_strong × n_strong + w_weak × n_weak

[0053] Where w_strong represents the weight of strong corroborating peaks and w_weak represents the weight of weak corroborating peaks. Optional values ​​are w_strong = 0.7 and w_weak = 0.3. n_strong represents the number of strong corroborating peaks and n_weak represents the number of weak corroborating peaks.

[0054] The above implementation method achieves accurate calculation of the support score of the evidence peak by weighted summation, so that the support score of the evidence peak can more accurately express the matching situation of the evidence peak.

[0055] Step S103: Match the observed peak position (w_obs) with the standard central wavenumber (w_std) of the candidate functional group to obtain the peak position matching score (S_w).

[0056] Optionally, the observed peak position (w_obs) can be matched with the standard central wavenumber (w_std) of the candidate functional group to obtain the peak position matching score (S_w), which can be implemented in the following way:

[0057] The peak position difference is determined based on the observed peak position and the standard central wavenumber of the candidate functional group.

[0058] The peak position matching score is calculated based on the peak position difference and the standard deviation of the peak position deviation.

[0059] The peak matching score (S_w) can be calculated using the following formula:

[0060] S_w = exp[-(w_obs - w_std)² / (2σ_w²)]

[0061] Where σ_w is the standard deviation of peak position deviation, used to control the tolerance of peak position matching. For example, the value of σ_w can be 5-50. w_obs represents the observed peak position, and w_std represents the standard center wavenumber of the candidate functional group. For example, for functional groups with broad peak shapes and susceptible to hydrogen bonding, such as OH, the standard deviation of the peak position deviation can be a larger value (e.g., 20-50). For functional groups with sharp peaks and stable peak positions, such as C≡N, the standard deviation of peak position deviation can be taken as a small value (e.g., 5-10). ).

[0062] The above implementation method can accurately calculate the peak position matching score through the formula, so that the peak position matching score can accurately represent the degree of proximity between the observed peak and the standard peak position of the candidate functional group.

[0063] Step S104: Map the observed peak intensity (I_obs) to a peak intensity score (I_score), and match the peak intensity score (I_score) with the typical peak intensity score (I_std) of the candidate functional group to obtain the peak intensity matching score (S_I).

[0064] Optionally, mapping the observed peak intensity to peak intensity fractions can be implemented in the following manner:

[0065] The peak intensity score is determined according to the preset peak intensity score mapping relationship to match the observed peak height and the relative intensity.

[0066] The preset peak intensity fraction mapping relationship is shown in Table 1.

[0067] Table 1

[0068]

[0069] The observed peak intensity (I_obs) can be mapped to a peak intensity score (I_score) of 1-5 using the following rules.

[0070] If the peak height is used for calculation, the rules are as follows:

[0071] When the observed peak height is ≥ 0.8, the peak intensity score I_score = 5. When 0.5 ≤ observed peak height < 0.8, the peak intensity score I_score = 4. When 0.3 ≤ observed peak height < 0.5, the peak intensity score I_score = 3. When 0.1 ≤ observed peak height < 0.3, I_score = 2. When the observed peak height < 0.1, the peak intensity score I_score = 1.

[0072] If relative intensity is used for calculation, the rules are as follows:

[0073] When the relative intensity is ≥ 80%, the peak intensity score I_score = 5. When 60% ≤ relative intensity < 80%, the peak intensity score I_score = 4. When 40% ≤ relative intensity < 60%, the peak intensity score I_score = 3. When 20% ≤ relative intensity < 40%, the peak intensity score I_score = 2. When the relative intensity < 20%, the peak intensity score I_score = 1.

[0074] The above implementation method can accurately determine the peak intensity fraction through the preset peak intensity fraction mapping relationship shown in Table 1, thereby improving the accuracy of the peak intensity fraction.

[0075] Optionally, a peak intensity matching score (S_I) can be obtained by matching the peak intensity score (I_score) with the typical peak intensity score (I_std) of the candidate functional group. This can be implemented in the following way:

[0076] The peak intensity difference is determined based on the peak intensity score (I_score) and the typical peak intensity score (I_std) of the candidate functional group;

[0077] The peak intensity matching score is calculated based on the peak intensity difference and the maximum permissible deviation (d_I).

[0078] The mapped observed peak intensity score (I_score) is matched with the typical peak intensity score (I_std) of the candidate functional group, calculated using the following formula:

[0079] S_I = max(0, 1 - |I_score - I_std| / d_I)

[0080] Where d_I is the maximum permissible deviation, used to limit the tolerance for peak intensity matching, typically ranging from 1 to 4. The maximum permissible deviation d_I can be adjusted according to the importance attached to peak intensity features. I_score is the peak intensity score, and I_std is the typical peak intensity score of the candidate functional group.

[0081] The above implementation method can accurately calculate the peak intensity matching score through the formula, so that the peak intensity matching score can more accurately represent the degree of agreement between the observed peak intensity and the typical peak intensity.

[0082] Step S105: Perform a weighted summation of the peak position matching score (S_w), the peak strength matching score (S_I), and the supporting peak score (S_e) to obtain the comprehensive score (S_total).

[0083] The total score (S_total) can be calculated using the following formula:

[0084] S_total = w_w × S_w + w_I × S_I + w_e × S_e

[0085] Where w_w is the weight of the peak position matching score, w_I is the weight of the peak strength matching score, and w_e is the weight of the corroborating peak support score. w_w + w_I + w_e = 1. For example, w_w takes the largest value, such as w_w=0.5, w_I=0.3, w_e=0.2.

[0086] Step S106: Normalize the comprehensive score to obtain the confidence level (C) of the candidate functional group; determine the target functional group that matches the test compound based on the confidence levels of multiple candidate functional groups.

[0087] Confidence level C = S_total / S_total_max

[0088] Where S_total_max is the sum of the comprehensive scores of all candidate functional groups, and S_total is the comprehensive score of the current functional group. The above formula normalizes the comprehensive score to the 0-1 interval, intuitively representing the probability of the functional group's existence.

[0089] Furthermore, the results can be output and visualized in the following ways. Based on the confidence level, a preset number of most likely functional groups and their confidence levels are output, and the following visualization methods are provided: 1. List display: Displaying functional group names, confidence levels, characteristic peak information, etc., in tabular form; 2. Spectral overlay: Highlighting the identified functional group characteristic peaks on the original spectrum; 3. Report generation: Automatically generating a report containing the identification results and detailed analysis.

[0090] The functional group identification method based on infrared spectroscopy in this invention determines the observation peak position and intensity of at least one observed peak based on the infrared spectrum, and calculates the supporting peak score, peak position matching score, and peak intensity matching score, respectively. These three scores are weighted and summed to obtain a comprehensive score corresponding to the candidate functional group, thus evaluating the similarity between the candidate functional group and the test compound from three dimensions. The confidence level of the candidate functional group is obtained through normalization. By comparing the confidence levels of multiple candidate functional groups, the candidate functional group with the highest confidence level is selected as the target functional group, improving the accuracy of functional group identification.

[0091] Figure 2 This is a flowchart illustrating a functional group identification method based on infrared spectroscopy provided in an embodiment of the present invention. As a further explanation of the above embodiment, the method includes:

[0092] Step S201: Preprocess the infrared spectrum of the compound to be tested. The preprocessing includes baseline correction, smoothing and denoising, and numerical normalization.

[0093] Step S202: Identify the absorbance at the peak position of each observation peak according to the preprocessed infrared spectrum to determine the peak height of the observation peak; normalize the highest peak of all observation peaks in the infrared spectrum to obtain the relative intensity of each observation peak; the peak height and the relative intensity constitute the observation peak intensity; identify the observation peak position of each observation peak according to the preprocessed infrared spectrum.

[0094] Step S203: Obtain multiple primary peaks belonging to the candidate functional groups. Within the strong peak interval, identify the number of observed peaks matching the primary peak as the number of strong supporting peaks; within the weak peak interval, identify the number of observed peaks matching the primary peak as the number of weak supporting peaks; the lower limit of the strong peak interval is greater than or equal to the upper limit of the weak peak interval.

[0095] Step S204: Perform a weighted summation based on the number of strong corroborating peaks, the weight of the strong corroborating peaks, the number of weak corroborating peaks, and the weight of the weak corroborating peaks to obtain the corroborating peak support score, wherein the weight of the strong corroborating peaks is greater than the weight of the weak corroborating peaks.

[0096] Step S205: Determine the peak position difference based on the observed peak position and the standard central wavenumber of the candidate functional group, and calculate the peak position matching score based on the peak position difference and the standard deviation of the peak position deviation.

[0097] Step S206: Determine the peak intensity score that matches the observed peak height and the relative intensity according to the preset peak intensity score mapping relationship. Determine the peak intensity difference based on the peak intensity score and the typical peak intensity score of the candidate functional group; calculate the peak intensity matching score based on the peak intensity difference and the maximum allowable deviation.

[0098] Step S207: Perform a weighted summation of the peak position matching score, the peak strength matching score, and the supporting peak score to obtain a comprehensive score.

[0099] Step S208: Normalize the comprehensive score to obtain the confidence level of the candidate functional group; determine the target functional group that matches the test compound based on the confidence levels of multiple candidate functional groups.

[0100] Example 1: The recognition process of hydroxyl (OH) and amino (NH) groups is as follows.

[0101] 1. Experimental Background: An unknown compound at 3400 There is a strong absorption peak at this point, which needs to be determined to be either the stretching vibration of OH or NH.

[0102] 2. Parameter settings:

[0103] Observation peak: 3400 Observed peak intensity: strong (corresponding to peak intensity fraction 4); σ_w: 30 (OH and NH peaks are relatively broad); d_I: 2; w_strong=0.7, w_weak=0.3; w_w=0.5, w_I=0.3, w_e=0.2.

[0104] 3. Calculation process:

[0105] For hydroxyl (OH):

[0106] Standard peak position w_std=3400 Typical peak intensity I_std=4.

[0107] Peak position matching score: S_w = exp[-(3400-3400)² / (2×30²)] = exp(0) = 1.0.

[0108] Peak strength matching score: S_I = max(0, 1-|4-4| / 2) = 1.0.

[0109] Assuming the existence of a CO stretching vibration corroborating peak, the corroborating peak support score is: S_e = 0.7×1 + 0.3×0 = 0.7.

[0110] Overall score: S_total = 0.5×1.0 + 0.3×1.0 + 0.2×0.7 = 0.94.

[0111] For amino groups (NH):

[0112] Standard peak position w_std=3350 Typical peak intensity I_std=3.

[0113] Peak position matching score: S_w = exp[-(3400-3350)² / (2×30²)] = exp[-2500 / 1800] =exp(-1.389) ≈ 0.249.

[0114] Peak strength matching score: S_I = max(0, 1-|4-3| / 2) = 0.5.

[0115] Assuming the existence of an NH bending vibration corroborating peak, the corroborating peak support score is: S_e = 0.7×1 + 0.3×0 = 0.7.

[0116] Overall score: S_total = 0.5×0.249 + 0.3×0.5 + 0.2×0.7 = 0.125 + 0.15 +0.14 = 0.415.

[0117] 4. Confidence level calculation:

[0118] Overall score: 0.94 + 0.415 = 1.355; OH confidence level: 0.94 / 1.355 ≈ 69.4%; NH confidence level: 0.415 / 1.355 ≈ 30.6%.

[0119] 5. Results Analysis: The 3400 The strong absorption peak at that point is more likely to be attributed to the stretching vibration of the hydroxyl group (OH), with a confidence level of 69.4%.

[0120] Example 2: The process of recognizing carbonyl groups (C=O) and ester groups (-COO-) in complex mixtures is as follows.

[0121] 1. Experimental Background: The spectrum of the mixture is at 1720... There is a strong absorption peak at this point; it is necessary to determine whether it is C=O or -COO-.

[0122] 2. Parameter settings:

[0123] Peak position observed: 1720 Observed peak intensity: strong (peak intensity fraction 4); σ_w: 10 (C=O peak is sharp); d_I: 2; w_strong=0.7, w_weak=0.3; w_w=0.5, w_I=0.3, w_e=0.2.

[0124] 3. Calculation process:

[0125] For carbonyl groups (C=O):

[0126] Standard peak position w_std=1715 Typical peak intensity I_std=4.

[0127] Peak position matching score: S_w = exp[-(1720-1715)² / (2×10²)] = exp[-25 / 200] = exp(-0.125) ≈ 0.882.

[0128] Peak strength matching score: S_I = max(0, 1-|4-4| / 2) = 1.0.

[0129] Assuming the presence of an aldehyde / ketone C=O supporting peak, the supporting peak score is: S_e = 0.7×1 + 0.3×0 = 0.7.

[0130] Overall score: S_total = 0.5×0.882 + 0.3×1.0 + 0.2×0.7 = 0.441 + 0.3 +0.14 = 0.881.

[0131] For ester groups (-COO-):

[0132] Standard peak position w_std=1740 Typical peak intensity I_std=4.

[0133] Peak position matching score: S_w = exp[-(1720-1740)² / (2×10²)] = exp[-400 / 200] = exp(-2.0) ≈ 0.135.

[0134] Peak strength matching score: S_I = max(0, 1-|4-4| / 2) = 1.0.

[0135] Assuming the existence of a CO stretching vibration corroborating peak, the corroborating peak support score is: S_e = 0.7×1 + 0.3×0 = 0.7.

[0136] Overall score: S_total = 0.5×0.135 + 0.3×1.0 + 0.2×0.7 = 0.068 + 0.3 +0.14 = 0.508.

[0137] 4. Confidence level calculation:

[0138] Total overall score: 0.881 + 0.508 = 1.389;

[0139] C=O confidence level: 0.881 / 1.389 ≈ 63.4%;

[0140] -COO- confidence level: 0.508 / 1.389 ≈ 36.6%.

[0141] 6. Results Analysis: The 1720 The strong absorption peak at that point is more likely to be attributed to the carbonyl (C=O) stretching vibration, with a confidence level of 63.4%.

[0142] Example 3: The process of identifying the out-of-plane bending vibration of CH in aromatic compounds is as follows.

[0143] 1. Experimental Background: An unknown compound was detected in the fingerprint region 700-900. The region contains characteristic peaks, and it is necessary to identify the out-of-plane bending vibrations of aromatic CH4.

[0144] 2. Parameter settings:

[0145] Observation peak: 750 Observed peak intensity: moderate (peak intensity fraction 3); σ_w: 15 ; d_I: 2; w_strong=0.7, w_weak=0.3; w_w=0.4, w_I=0.3, w_e=0.3 (the supporting peaks for aromatic compounds are more important).

[0146] 3. Calculation process:

[0147] For the out-of-plane bending vibration of aromatic CH4:

[0148] Standard peak position w_std=750 Typical peak intensity I_std=3.

[0149] Peak position matching score: S_w = exp[-(750-750)² / (2×15²)] = exp(0) = 1.0.

[0150] Peak strength matching score: S_I = max(0, 1-|3-3| / 2) = 1.0.

[0151] Assuming the existence of corroborating peaks for benzene ring skeletal vibrations, the corroborating peak support score is: S_e = 0.7×1 + 0.3×0 = 0.7.

[0152] Overall score: S_total = 0.4×1.0 + 0.3×1.0 + 0.3×0.7 = 0.4 + 0.3 + 0.21 = 0.91.

[0153] 4. Confidence Calculation: The confidence level of the out-of-plane bending vibration of aromatic CH is significantly higher than that of other functional groups.

[0154] 5. Results Analysis: The out-of-plane bending vibration characteristics of CH in aromatic compounds were successfully identified.

[0155] Example 4: Identification and semi-quantitative analysis of proteins and lipids in biological samples are as follows.

[0156] 1. Experimental background: FTIR analysis of cancer cell extracts to study the relative changes in protein and lipid content.

[0157] 2. Key absorption peak:

[0158] ~1650 : Protein amide I band (C=O stretching vibration).

[0159] ~1540 Protein amide II band (NH bending and CN stretching).

[0160] ~1740 : Lipid ester carbonyl (C=O) stretching vibration.

[0161] 3. Parameter settings:

[0162] σ_w: 15 ;d_I: 2; w_strong=0.7, w_weak=0.3; w_w=0.5, w_I=0.3, w_e=0.2.

[0163] 4. Calculation process:

[0164] For proteins (amide I band):

[0165] Observation peak 1650 Standard peak position w_std=1650 Typical peak intensity I_std=5 (extremely strong).

[0166] Peak position matching score: S_w = exp(0) = 1.0.

[0167] Peak strength matching score: S_I = max(0, 1-|5-5| / 2) = 1.0.

[0168] There are 1540 Amide II shows a supporting peak, and the supporting peak score is: S_e = 0.7×1 + 0.3×0 = 0.7.

[0169] Overall score: S_total = 0.5×1.0 + 0.3×1.0 + 0.2×0.7 = 0.94.

[0170] For lipids (ester groups):

[0171] Observation peak 1740 Standard peak position w_std=1740 Typical peak strength I_std=4 (strong).

[0172] Peak position matching score: S_w = exp(0) = 1.0.

[0173] Peak strength matching score: S_I = max(0, 1-|4-4| / 2) = 1.0.

[0174] There is a CH2 stretching vibration corroborating peak, and the corroborating peak supports the score: S_e = 0.7×1 + 0.3×0 = 0.7.

[0175] Overall score: S_total = 0.5×1.0 + 0.3×1.0 + 0.2×0.7 = 0.94.

[0176] 5. Semi-quantitative analysis: By comparing the relative scores of proteins and lipids, their relative content changes can be assessed. If the protein score is significantly higher than that of lipids, it indicates a higher protein content in the sample.

[0177] 6. Results Analysis: The above scheme can not only identify key biomacromolecules, but also perform preliminary semi-quantitative analysis through the relative size of the scores, providing valuable clues for biomedical research.

[0178] Example 5: Identification of Plasticizers in Polymer Materials

[0179] 1. Experimental background: Analysis of polyvinyl chloride (PVC) samples to identify possible phthalate plasticizers.

[0180] 2. Key absorption peak:

[0181] 1720 Nearby: characteristic peak of ester group C=O.

[0182] 700-800 Region: Characteristic peaks of the benzene ring structure of phthalic acid esters.

[0183] 3. Parameter settings:

[0184] σ_w: 10 ;d_I: 2; w_strong=0.7, w_weak=0.3; w_w=0.5, w_I=0.3, w_e=0.2.

[0185] 4. Calculation process:

[0186] For ester group C=O:

[0187] Observation peak 1720 Standard peak position w_std=1720 Typical peak intensity I_std=4.

[0188] Peak position matching score: S_w = exp(0) = 1.0.

[0189] Peak strength matching score: S_I = max(0, 1-|4-4| / 2) = 1.0.

[0190] There are corroborating peaks for CO stretching vibration and benzene ring skeletal vibration, and the corroborating peaks support the score: S_e = 0.7×1 + 0.3×1 = 1.0.

[0191] Overall score: S_total = 0.5×1.0 + 0.3×1.0 + 0.2×1.0 = 1.0.

[0192] For polyvinyl chloride (C-Cl):

[0193] Observation peak 650 Standard peak position w_std=650 Typical peak intensity I_std=4.

[0194] Peak position matching score: S_w = exp(0) = 1.0.

[0195] Peak strength matching score: S_I = max(0, 1-|4-4| / 2) = 1.0.

[0196] There are supporting peaks for CH stretching and CH2 bending, and the supporting peak score is: S_e = 0.7×1 + 0.3×1 = 1.0.

[0197] Overall score: S_total = 0.5×1.0 + 0.3×1.0 + 0.2×1.0 = 1.0.

[0198] 5. Results Analysis: By quantitatively assessing the confidence level of the C=O functional group of the ester group, it is possible to quickly determine whether phthalate plasticizers are present in the sample, providing a basis for material quality control.

[0199] The functional group identification method based on infrared spectroscopy provided in this invention integrates multi-dimensional features such as peak position, peak intensity, and supporting peaks, avoiding the limitations of single-feature judgment. It is particularly suitable for the analysis of complex compounds, significantly improving identification accuracy. It provides a quantitative confidence level between 0 and 1, eliminating the influence of subjective human judgment and enhancing the reliability and objectivity of identification. The entire process from data input to result output is automated, greatly improving analytical efficiency and achieving highly efficient automated functional group analysis. It can be applied to the analysis of various organic compounds, and parameter adjustments can be made to adapt to different needs, improving versatility and flexibility.

[0200] Figure 3 This is a schematic diagram of a functional group identification device based on infrared spectroscopy provided in an embodiment of the present invention. This embodiment is applicable to the identification of functional groups of organic compounds from their infrared spectra. This infrared spectroscopy-based functional group identification device can be implemented in hardware and / or software, and can be configured in electronic devices such as personal computers, laptops, smart devices, mobile devices, or servers. Figure 3 As shown, the device includes: an observation module 31, a corroborating peak score calculation module 32, a peak position matching score determination module 33, a peak intensity matching score determination module 34, a comprehensive score determination module 35, and a target functional group determination module 36.

[0201] The observation module 31 is used to determine spectral data based on the infrared spectrum of the compound to be tested, wherein the spectral data includes the observation peak position and observation peak intensity of at least one observation peak.

[0202] The corroborating peak score calculation module 32 is used to identify the number of corroborating peaks related to candidate functional groups based on the observed peak intensity; and to calculate the corroborating peak support score based on the number of corroborating peaks.

[0203] The peak position matching score determination module 33 is used to match the observed peak position with the standard center wavenumber of the candidate functional group to obtain the peak position matching score.

[0204] Peak intensity matching score determination module 34 is used to map the observed peak intensity to a peak intensity score, and match the peak intensity score with the typical peak intensity score of the candidate functional group to obtain the peak intensity matching score.

[0205] The comprehensive score determination module 35 is used to perform a weighted summation based on the peak position matching score, the peak strength matching score and the supporting peak score to obtain a comprehensive score.

[0206] The target functional group determination module 36 is used to normalize the comprehensive score to obtain the confidence level of the candidate functional group; and to determine the target functional group that matches the test compound based on the confidence levels of multiple candidate functional groups.

[0207] Based on the above embodiments, optionally, the corroborating peak score calculation module 32 is used to identify the number of corroborating peaks related to candidate functional groups based on the observed peak intensity, including:

[0208] Obtain multiple attribution peaks contained in candidate functional groups;

[0209] Within the strong peak range, identify the number of observed peaks that match the attributed main peak, as the number of strong corroborating peaks;

[0210] Within the weak peak range, the number of observed peaks that match the attributed main peak is identified as the number of weak corroborating peaks.

[0211] The lower limit of the strong peak interval is greater than or equal to the upper limit of the weak peak interval.

[0212] Based on the above embodiments, optionally, the corroborating peak score calculation module 32 is used to calculate the corroborating peak support score according to the number of corroborating peaks, including:

[0213] The support score for the evidence peaks is obtained by weighting and summing the number of strong evidence peaks, the weight of the strong evidence peaks, the number of weak evidence peaks, and the weight of the weak evidence peaks. The weight of the strong evidence peaks is greater than the weight of the weak evidence peaks.

[0214] Based on the above embodiments, optionally, the peak position matching score determination module 33 is used for:

[0215] The peak position difference is determined based on the observed peak position and the standard center wavenumber of the candidate functional group, and the peak position matching score is calculated based on the peak position difference and the standard deviation of the peak position deviation.

[0216] Based on the above embodiments, optionally, the peak intensity matching score determination module 34 is used to match the peak intensity score with the typical peak intensity score of the candidate functional group to obtain the peak intensity matching score, including:

[0217] The peak intensity difference is determined based on the peak intensity score and the typical peak intensity score of the candidate functional group;

[0218] The peak intensity matching score is calculated based on the peak intensity difference and the maximum permissible deviation.

[0219] Based on the above embodiments, optionally, the observation module 31 is used for:

[0220] The infrared spectrum of the compound to be tested is preprocessed, including baseline correction, smoothing and denoising, and numerical normalization.

[0221] The peak height of each observation peak is determined by identifying the absorbance at the peak position of each observation peak based on the preprocessed infrared spectrum. The relative intensity of each observation peak is obtained by normalizing the highest peak in the infrared spectrum. The peak height and the relative intensity together constitute the observation peak intensity.

[0222] The observation peak position of each observation peak was identified based on the preprocessed infrared spectrum.

[0223] Based on the above embodiments, optionally, the peak intensity matching score determination module 34 is used to map the observed peak intensity to a peak intensity score, including:

[0224] The peak intensity score is determined according to the preset peak intensity score mapping relationship to match the observed peak height and the relative intensity.

[0225] The functional group identification device based on infrared spectroscopy of this invention includes an observation module 31, used to determine spectral data based on the infrared spectrum of the compound to be tested, the spectral data including the observation peak position and observation peak intensity of at least one observation peak; a supporting peak score calculation module 32, used to identify the number of supporting peaks related to candidate functional groups based on the observation peak intensity; and to calculate the supporting peak support score based on the number of supporting peaks; and a peak position matching score determination module 33, used to match the observation peak position with the standard center wavenumber of the candidate functional group to obtain a peak position matching score; and a peak intensity matching score. The peak intensity determination module 34 maps the observed peak intensity to a peak intensity score, and matches the peak intensity score with the typical peak intensity scores of candidate functional groups to obtain a peak intensity matching score. The comprehensive score determination module 35 performs a weighted summation of the peak position matching score, the peak intensity matching score, and the supporting peak score to obtain a comprehensive score. The target functional group determination module 36 normalizes the comprehensive score to obtain the confidence level of the candidate functional group. Based on the confidence levels of multiple candidate functional groups, the target functional group matching the test compound is determined. The observed peak position and peak intensity of at least one observed peak are determined based on the infrared spectrum, and the supporting peak score, peak position matching score, and peak intensity matching score are calculated respectively. A weighted summation of these three scores yields the comprehensive score corresponding to the candidate functional group, realizing the evaluation of the similarity between the candidate functional group and the test compound from three dimensions. The confidence level of the candidate functional group is obtained through normalization. By comparing the confidence levels of multiple candidate functional groups, the candidate functional group with the highest confidence level is selected as the target functional group, thereby improving the accuracy of functional group identification.

[0226] The functional group identification device based on infrared spectroscopy provided in this embodiment of the invention can execute the functional group identification method based on infrared spectroscopy provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the method.

[0227] Figure 4This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. The electronic device 10 is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (such as helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0228] like Figure 4 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 can also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0229] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as a camera, ultrasonic sensor, infrared sensor, etc.; output unit 17, such as various types of speakers, etc.; storage unit 18, such as a disk, solid-state drive, etc.; and communication unit 19, such as a network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0230] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as the functional group identification method based on infrared spectroscopy.

[0231] In some embodiments, the infrared spectroscopy-based functional group identification method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the infrared spectroscopy-based functional group identification method described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform the infrared spectroscopy-based functional group identification method by any other suitable means (e.g., by means of firmware).

[0232] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0233] Computer programs for implementing the infrared spectroscopy-based functional group identification method of the present invention can be written in any combination of one or more programming languages. These computer programs can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the functions / operations specified in the flowcharts and / or block diagrams are implemented. The computer programs can be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0234] This invention also provides a computer-readable storage medium storing computer instructions for causing a processor to execute a functional group identification method based on infrared spectroscopy, the method comprising:

[0235] Based on the infrared spectrum of the compound to be tested, determine the spectral data, which includes the observed peak position and observed peak intensity of at least one observed peak.

[0236] The number of supporting peaks associated with candidate functional groups is identified based on the observed peak intensity; the supporting peak support score is calculated based on the number of supporting peaks.

[0237] The observed peak position is matched with the standard center wavenumber of the candidate functional group to obtain the peak position matching score;

[0238] The observed peak intensity is mapped to a peak intensity score, and the peak intensity score is matched with the typical peak intensity scores of the candidate functional groups to obtain a peak intensity matching score.

[0239] The comprehensive score is obtained by weighted summation of the peak position matching score, the peak strength matching score, and the supporting peak score.

[0240] The confidence level of the candidate functional group is obtained by normalizing the comprehensive score; the target functional group matching the test compound is determined based on the confidence levels of multiple candidate functional groups.

[0241] Based on the above embodiments, optionally, the number of supporting peaks related to candidate functional groups can be identified according to the observed peak intensity, including:

[0242] Obtain multiple attribution peaks contained in candidate functional groups;

[0243] Within the strong peak range, identify the number of observed peaks that match the attributed main peak, as the number of strong corroborating peaks;

[0244] Within the weak peak range, the number of observed peaks that match the attributed main peak is identified as the number of weak corroborating peaks.

[0245] The lower limit of the strong peak interval is greater than or equal to the upper limit of the weak peak interval.

[0246] Based on the above embodiments, optionally, the supporting score for the supporting peaks is calculated according to the number of supporting peaks, including:

[0247] The support score for the evidence peaks is obtained by weighting and summing the number of strong evidence peaks, the weight of the strong evidence peaks, the number of weak evidence peaks, and the weight of the weak evidence peaks. The weight of the strong evidence peaks is greater than the weight of the weak evidence peaks.

[0248] Based on the above embodiments, optionally, the observed peak position is matched with the standard central wavenumber of the candidate functional group to obtain a peak position matching score, including:

[0249] The peak position difference is determined based on the observed peak position and the standard central wavenumber of the candidate functional group;

[0250] The peak position matching score is calculated based on the peak position difference and the standard deviation of the peak position deviation.

[0251] Based on the above embodiments, optionally, a peak intensity matching score is obtained by matching the peak intensity score with the typical peak intensity scores of the candidate functional groups, including:

[0252] The peak intensity difference is determined based on the peak intensity score and the typical peak intensity score of the candidate functional group;

[0253] The peak intensity matching score is calculated based on the peak intensity difference and the maximum permissible deviation.

[0254] Based on the above embodiments, optionally, spectral data can be determined according to the infrared spectrum of the compound to be tested, including:

[0255] The infrared spectrum of the compound to be tested is preprocessed, including baseline correction, smoothing and denoising, and numerical normalization.

[0256] The peak height of each observation peak is determined by identifying the absorbance at the peak position of each observation peak based on the preprocessed infrared spectrum. The relative intensity of each observation peak is obtained by normalizing the highest peak in the infrared spectrum. The peak height and the relative intensity together constitute the observation peak intensity.

[0257] The observation peak position of each observation peak was identified based on the preprocessed infrared spectrum.

[0258] Based on the above embodiments, optionally, mapping the observed peak intensity to a peak intensity fraction includes:

[0259] The peak intensity score is determined according to the preset peak intensity score mapping relationship to match the observed peak height and the relative intensity.

[0260] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0261] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0262] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or middleware components (e.g., application servers), or frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0263] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0264] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0265] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A functional group identification method based on infrared spectroscopy, characterized in that, include: Based on the infrared spectrum of the compound to be tested, determine the spectral data, which includes the observed peak position and observed peak intensity of at least one observed peak. The number of supporting peaks associated with candidate functional groups is identified based on the observed peak intensity; the supporting peak support score is calculated based on the number of supporting peaks. The observed peak position is matched with the standard center wavenumber of the candidate functional group to obtain the peak position matching score; The observed peak intensity is mapped to a peak intensity score, and the peak intensity score is matched with the typical peak intensity scores of the candidate functional groups to obtain a peak intensity matching score. The comprehensive score is obtained by weighted summation of the peak position matching score, the peak strength matching score, and the supporting peak score. The confidence level of the candidate functional group is obtained by normalizing the comprehensive score; the target functional group matching the test compound is determined based on the confidence levels of multiple candidate functional groups.

2. The method according to claim 1, characterized in that, The number of supporting peaks associated with candidate functional groups is identified based on the observed peak intensity, including: Obtain multiple attribution peaks contained in candidate functional groups; Within the strong peak range, identify the number of observed peaks that match the attributed main peak, as the number of strong corroborating peaks; Within the weak peak range, the number of observed peaks that match the attributed main peak is identified as the number of weak corroborating peaks. The lower limit of the strong peak interval is greater than or equal to the upper limit of the weak peak interval.

3. The method according to claim 2, characterized in that, The supporting score for the supporting peaks is calculated based on the number of supporting peaks, including: The support score for the evidence peaks is obtained by weighting and summing the number of strong evidence peaks, the weight of the strong evidence peaks, the number of weak evidence peaks, and the weight of the weak evidence peaks. The weight of the strong evidence peaks is greater than the weight of the weak evidence peaks.

4. The method according to claim 1, characterized in that, The observed peak position is matched with the standard center wavenumber of the candidate functional group to obtain the peak position matching score, including: The peak position difference is determined based on the observed peak position and the standard central wavenumber of the candidate functional group; The peak position matching score is calculated based on the peak position difference and the standard deviation of the peak position deviation.

5. The method according to claim 1, characterized in that, Peak intensity matching scores are obtained by matching the peak intensity scores with the typical peak intensity scores of candidate functional groups, including: The peak intensity difference is determined based on the peak intensity score and the typical peak intensity score of the candidate functional group; The peak intensity matching score is calculated based on the peak intensity difference and the maximum permissible deviation.

6. The method according to claim 1, characterized in that, Based on the infrared spectrum of the compound to be tested, determine the spectral data, including: The infrared spectrum of the compound to be tested is preprocessed, including baseline correction, smoothing and denoising, and numerical normalization. The peak height of each observation peak is determined by identifying the absorbance at the peak position of each observation peak based on the preprocessed infrared spectrum. The relative intensity of each observation peak is obtained by normalizing the highest peak in the infrared spectrum. The peak height and the relative intensity together constitute the observation peak intensity. The observation peak position of each observation peak was identified based on the preprocessed infrared spectrum.

7. The method according to claim 6, characterized in that, Mapping the observed peak intensity to peak intensity fractions includes: The peak intensity score is determined according to the preset peak intensity score mapping relationship to match the observed peak height and the relative intensity.

8. A functional group recognition device based on infrared spectroscopy, characterized in that, include: The observation module is used to determine spectral data based on the infrared spectrum of the compound to be tested. The spectral data includes the observation peak position and observation peak intensity of at least one observation peak. The corroborating peak score calculation module is used to identify the number of corroborating peaks related to candidate functional groups based on the observed peak intensity; and to calculate the corroborating peak support score based on the number of corroborating peaks. The peak position matching score determination module is used to match the observed peak position with the standard center wavenumber of the candidate functional group to obtain the peak position matching score. The peak intensity matching score determination module is used to map the observed peak intensity to a peak intensity score, and match the peak intensity score with the typical peak intensity score of the candidate functional group to obtain the peak intensity matching score. The comprehensive score determination module is used to perform a weighted summation based on the peak position matching score, the peak strength matching score, and the supporting peak score to obtain a comprehensive score. The target functional group determination module is used to normalize the comprehensive score to obtain the confidence level of the candidate functional group; and to determine the target functional group that matches the test compound based on the confidence levels of multiple candidate functional groups.

9. An electronic device, characterized in that, The electronic device includes: 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, which enables the at least one processor to perform the functional group identification method based on infrared spectroscopy as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that cause a processor to execute the functional group identification method based on infrared spectroscopy as described in any one of claims 1-7.

Images