Chromatogram analysis method and device based on artificial intelligence and computer equipment

Abstract

The invention provides a chromatogram analysis method and device based on artificial intelligence and computer equipment, and the method comprises the steps: training a deep learning neural network, and obtaining a chromatogram analysis model; receiving a digital chromatographic data image to be examined and analyzed through the chromatogram analysis model, and segmenting the digital chromatographic data image into regional images; performing image content state review identification on each area image through the chromatogram analysis model to obtain a review prediction area and performing image content state marking; evaluating, calculating and examining the image content state of the prediction area and the possible probability degree of the image content state to obtain a first ratio, and marking the image content state with the first ratio greater than a preset first threshold probability ratio with a specific color; and drawing a chromatographic review report and a chromatographic analysis report which can be referenced by detection personnel according to the on-going chromatographic experiment information, the to-be-detected sample information and the analysis information of the chromatogram analysis model. The method has the beneficial effect that the chromatographic analysis rate is greatly improved.

Description

Technical Field

[0001] The present invention relates to the technical field of chromatographic analysis, and in particular to a chromatogram analysis method, device and computer equipment based on artificial intelligence. Background Art

[0002] Chromatography is widely used in environment, chemical analysis, medicine and other fields. The chromatographic techniques used in practice include liquid chromatography, gas chromatography, gel chromatography and so on. These chromatographic techniques need to be carried out in a strict experimental environment. Because the chromatographic instrument is very sensitive, the chromatogram obtained in the actual experiment will be affected by the environmental factors of the experimental instrument, the current state of the instrument, the sample concentration and the experimental steps, and the peak shape will be distorted, deformed or the baseline drift, noise and other abnormal changes will occur, resulting in the chromatogram cannot be correctly analyzed. Therefore, no matter what kind of chromatographic detection, it requires a lot of professional training professionals to operate, and a lot of learning and time costs are required in chromatographic detection training. In actual situations, due to the influence of experimental instruments, experimental environment, test samples and so on, the chromatogram of each experiment will have different degrees of image distortion. Because the deformed chromatographic image will affect the subsequent quantitative analysis and calculation of chromatographic data processing, professional testers need to check the chromatographic instrument before each test and spend a lot of time on each test sample for detailed manual review and analysis. It can be seen that there are problems in chromatographic detection, such as time-consuming and labor-intensive manual review, strong subjectivity and poor repeatability. At the same time, the existing automated detection system basically uses the mathematical statistical calculation method integrated in the software to judge the state of the chromatogram, and is unable to automatically and accurately check whether the chromatogram has excessive deformation and distortion. Summary of the invention

[0003] The technical problem to be solved by the present invention is to provide a chromatogram analysis method, device and computer equipment based on artificial intelligence, aiming to improve the chromatographic analysis rate.

[0004] In order to solve the above technical problems, the technical solution adopted by the present invention is: a chromatogram analysis method based on artificial intelligence, comprising the steps of:

[0005] S10, training the deep learning neural network to obtain a chromatogram analysis model;

[0006] S20, receiving the digital chromatogram data image to be reviewed and analyzed through the chromatogram analysis model, and dividing the digital chromatogram data image into regional images;

[0007] S30, using the chromatogram analysis model to review and identify the image content status of each regional image to obtain a review prediction region, and marking the review prediction region with an image content status, wherein the image content status includes the highest peak, leading peak, tailing peak, broad peak, split peak, negative peak, peak with insufficient separation, baseline noise, and baseline drift of the chromatogram;

[0008] S40, evaluating and calculating the image content state of the review prediction area and the possible probability of the image content state to obtain a first ratio, and if the first ratio is greater than a preset first threshold probability ratio, screening it out and marking it with a specific color;

[0009] S50, drawing a chromatographic review report and a chromatographic analysis report for reference by test personnel based on the ongoing chromatographic experiment information, the sample information to be tested, and the analysis information of the chromatogram analysis model.

[0010] Further, step S10, training the deep learning neural network to obtain the chromatogram analysis model specifically includes:

[0011] S11. A training sample image with pre-labeled image content status is obtained through a deep learning neural network, and the digital chromatogram data image of the training set is segmented into regional images; the deep learning neural network adopts the DeepLabv3+ network; the backbone network of the DeepLabv3+ network is set to GhostNetv2;

[0012] S12, after performing row convolution and column convolution on the region image, standardize the feature parameters through batch normalization, and reduce the linearity of the feature parameters through nonlinear activation, so as to obtain a first feature image that compresses the length and width of the region image;

[0013] S13, inputting the first feature image into 7 channels of the ASPP encoder with expansion rates of 1, 6, 12, 18, 24, 28, and 32 respectively, the first feature image is convolved with convolution kernels expanded by 1, 6, 12, 18, 24, 28, and 32 times in the 7 channels respectively, extracting deep features, and compressing the extracted 7-channel deep features by point convolution to obtain a second feature image;

[0014] S14, using the first feature image and the second feature image as input features of the decoder, and obtaining the review prediction features by fusing the resizing, point convolution, and bilinear interpolation;

[0015] S15. Minimize the loss function calculation for the review prediction features and the labels corresponding thereto, and obtain the trained chromatogram analysis model when the loss value meets the convergence requirement.

[0016] Furthermore, in step S12, the formula used for performing row convolution and column convolution on the region image is:

[0017]

[0018] Among them, y i Represents the various values ​​on the output features, x represents the input features, w represents the convolution kernel, and r represents the step size.

[0019] Furthermore, in step S12, the feature parameters are standardized by batch standardization, and the formula is:

[0020]

[0021] Among them, Θ is the training network parameter, and the gradient is estimated for a total of N training data sets.

[0022] Furthermore, in step S12, the minimization loss function used by the nonlinear activation to reduce the linearity of the feature parameters adopts the ReLu function and the softmax function; the minimization loss function is:

[0023]

[0024] FocalLoss=-log p t (1-p t ) 2

[0025]

[0026] Among them, l n Affected by the set weights, it represents the average value of the predicted probability of the training data set; p t is the model's predicted probability for the target class, indicating the adjustment of the model's attention to positive samples in the training data set; P i and G i It is the value of the prediction result at the i-th pixel, which indicates the similarity between the prediction result of the training model and the true label.

[0027] Furthermore, the digital chromatographic data image is a two-dimensional gas / liquid chromatographic data graph, the unit of the x-axis is time, and the unit of the y-axis is signal value.

[0028] Further, step S50, based on the ongoing chromatographic experiment information, the sample information to be tested, and the analysis information of the chromatogram analysis model, a chromatographic review report and a chromatographic analysis report for reference by the testing personnel are drawn up, specifically including:

[0029] S51, drawing a chromatographic review report for reference by test personnel based on the information of the ongoing chromatographic experiment, the information of the sample to be tested, and the analysis information of the chromatogram analysis model;

[0030] S52, extracting the signal value of the qualified chromatogram without abnormal chromatographic peaks, and calculating the chromatographic analysis parameters by using the time parameters, wherein the chromatographic analysis parameters include the retention time t R , peak height h, peak area A, half peak height W 1 / 2 , peak width W, standard deviation σ, and draw a chromatographic analysis report for reference by testing personnel based on the chromatographic experiment information, sample information, and calculated analysis parameters.

[0031] The present invention also provides a chromatogram analysis device based on artificial intelligence, comprising:

[0032] A model training module is used to train the deep learning neural network to obtain a chromatogram analysis model;

[0033] An image segmentation module, used for receiving the digital chromatogram data image to be reviewed and analyzed through the chromatogram analysis model, and segmenting the digital chromatogram data image into regional images;

[0034] An image content status recognition module is used to review and identify the image content status of each regional image through a chromatogram analysis model to obtain a review prediction region, and mark the review prediction region with an image content status, wherein the image content status includes the highest peak, leading peak, tailing peak, broad peak, split peak, negative peak, peak with insufficient separation, baseline noise, and baseline drift of the chromatogram;

[0035] An image content state evaluation module is used to evaluate and calculate the image content state of the review prediction area and the possible probability of the image content state to obtain a first ratio. If the first ratio is greater than a preset first threshold probability ratio, the image content state is screened out and marked with a specific color.

[0036] The report generation module is used to draw a chromatographic review report and a chromatographic analysis report for reference by the testing personnel based on the ongoing chromatographic experiment information, the sample information to be tested, and the analysis information of the chromatogram analysis model.

[0037] The present invention also provides a computer device, which includes a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the chromatogram analysis method based on artificial intelligence as described in any one of the above items is implemented.

[0038] The present invention also provides a storage medium storing a computer program, which, when executed by a processor, can implement the chromatogram analysis method based on artificial intelligence as described in any one of the above items.

[0039] The beneficial effects of the present invention are as follows: the present invention provides a method for automatically troubleshooting the deformation and distortion of chromatograms and analyzing qualified chromatograms, and utilizes artificial intelligence technology to automatically review and analyze chromatograms. The automated chromatogram review and analysis technology can greatly improve the chromatographic analysis rate. Its automatic review and analysis function can reduce the subjectivity of manual review and shorten the detection and testing time of chromatographic detection experiments in different fields, effectively helping to speed up chromatographic detection experiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] The specific structure of the present invention is described in detail below in conjunction with the accompanying drawings.

[0041] Figure 1 The present invention is a flowchart of a chromatogram analysis method based on artificial intelligence.

[0042] Figure 2 A deep learning neural network training flow chart of an embodiment of the present invention;

[0043] Figure 3 A block diagram of a chromatogram analysis device based on artificial intelligence according to an embodiment of the present invention;

[0044] Figure 4 This is a block diagram of a model training module in an embodiment of the present invention;

[0045] Figure 5 A schematic block diagram of a computer device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0046] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0047] It should be understood that when used in this specification and the appended claims, the terms "include" and "comprises" indicate the presence of described features, integers, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or combinations thereof.

[0048] It should also be understood that the terms used in this specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. As used in the specification of the present invention and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include plural forms.

[0049] It should be further understood that the term "and / or" used in the present description and the appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0050] like Figure 1 As shown, the first embodiment of the present invention is: a chromatogram analysis method based on artificial intelligence, comprising the steps of:

[0051] S10, training the deep learning neural network to obtain a chromatogram analysis model;

[0052] S20, receiving the digital chromatogram data image to be reviewed and analyzed through the chromatogram analysis model, and dividing the digital chromatogram data image into regional images;

[0053] In this step, the digital chromatogram data refers to a data file in a chromatogram data format processed by a professional chromatogram detector and a digital chromatogram data image drawn by the data file in the chromatogram data format after data processing.

[0054] S30, using the chromatogram analysis model to review and identify the image content status of each regional image to obtain a review prediction region, and marking the review prediction region with an image content status, wherein the image content status includes the highest peak, leading peak, tailing peak, broad peak, split peak, negative peak, peak with insufficient separation, baseline noise, and baseline drift of the chromatogram;

[0055] S40, evaluating and calculating the image content state of the review prediction area and the possible probability of the image content state to obtain a first ratio, and if the first ratio is greater than a preset first threshold probability ratio, screening it out and marking it with a specific color;

[0056] In this step, the highest peak is marked with the color code #CD0000, the leading peak is marked with the color code #ECE513, the tailing peak is marked with the color code #2W8B57, the broad peak is marked with the color code #0000CD, the split peak is marked with the color code #CD853F, the negative peak is marked with the color code #9400D3, the peak with insufficient separation is marked with the color code #FF1493, and the baseline problem is marked with the color code #008000.

[0057] S50, drawing a chromatographic review report and a chromatographic analysis report for reference by test personnel based on the ongoing chromatographic experiment information, the sample information to be tested, and the analysis information of the chromatogram analysis model.

[0058] In this step, the chromatographic review report and chromatographic analysis report contain the common complete experimental information and their respective attribute data information, which can provide analytical guidance for testers and provide a standardized data transmission format for the subsequent new functions of the system. This can not only improve the detection efficiency of testers, but also provide a standardized data input format for the expansion and upgrade of the system.

[0059] This solution provides a method for automatically troubleshooting the deformation and distortion of chromatograms and analyzing qualified chromatograms. It uses artificial intelligence technology to automatically review and analyze chromatograms. The automated chromatogram review and analysis technology can greatly improve the chromatographic analysis rate. Its automatic review and analysis function can reduce the subjectivity of manual review and shorten the detection and testing time of chromatographic detection experiments in different fields, effectively helping to speed up chromatographic detection experiments.

[0060] like Figure 2 As shown, in a specific embodiment, step S10, training the deep learning neural network to obtain the chromatogram analysis model specifically includes:

[0061] S11. A training sample image with pre-labeled image content status is obtained through a deep learning neural network, and the digital chromatogram data image of the training set is segmented into regional images; the deep learning neural network adopts the DeepLabv3+ network; the backbone network of the DeepLabv3+ network is set to GhostNetv2;

[0062] S12, after performing row convolution and column convolution on the region image, standardize the feature parameters through batch normalization, and reduce the linearity of the feature parameters through nonlinear activation, so as to obtain a first feature image that compresses the length and width of the region image;

[0063] S13, inputting the first feature image into 7 channels of the ASPP encoder with expansion rates of 1, 6, 12, 18, 24, 28, and 32 respectively, the first feature image is convolved with convolution kernels expanded by 1, 6, 12, 18, 24, 28, and 32 times in the 7 channels respectively, extracting deep features, and compressing the extracted 7-channel deep features by point convolution to obtain a second feature image;

[0064] S14, using the first feature image and the second feature image as input features of the decoder, and obtaining the review prediction features by fusing the resizing, point convolution, and bilinear interpolation;

[0065] S15. Minimize the loss function calculation for the review prediction features and the labels corresponding thereto, and obtain the trained chromatogram analysis model when the loss value meets the convergence requirement.

[0066] In a specific embodiment, in step S12, the formula used for performing row convolution and column convolution on the regional image is:

[0067]

[0068] Among them, y i Represents the various values ​​on the output features, x represents the input features, w represents the convolution kernel, and r represents the step size.

[0069] In a specific embodiment, in step S12, the characteristic parameters are standardized by batch standardization, and the formula is:

[0070]

[0071] Among them, Θ is the training network parameter, and the gradient is estimated for a total of N training data sets.

[0072] In a specific embodiment, in step S12, the minimization loss function used by the nonlinear activation to reduce the linearity of the feature parameters uses the ReLu function and the softmax function; the minimization loss function is:

[0073]

[0074] FocalLoss=-log p t (1-p t ) 2

[0075]

[0076] Among them, l n Affected by the set weights, it represents the average value of the predicted probability of the training data set; p t is the model's predicted probability for the target class, indicating the adjustment of the model's attention to positive samples in the training data set; P i and G i It is the value of the prediction result at the i-th pixel, which indicates the similarity between the prediction result of the training model and the true label.

[0077] In this embodiment, the minimization loss function is classified by name, CE loss function, Focal loss function, and Dice loss function. Model training evaluation uses the method of minimizing the loss function to calculate the loss value. The chromatogram analysis model is obtained through repeated training. Each training will minimize the loss function calculation of the review prediction features and the corresponding labels. When the loss value meets the convergence requirements, the model training is completed; if the loss value does not meet the convergence requirements, it is necessary to iterate the training repeatedly until the loss value converges.

[0078] In a specific embodiment, the digital chromatographic data image is a two-dimensional gas / liquid chromatographic data graph, the unit of the x-axis is time, and the unit of the y-axis is signal value.

[0079] In a specific embodiment, step S50, drawing a chromatographic review report and a chromatographic analysis report for reference by the testing personnel based on the ongoing chromatographic experiment information, the sample information to be tested, and the analysis information of the chromatogram analysis model specifically includes:

[0080] S51, drawing a chromatographic review report for reference by test personnel based on the information of the ongoing chromatographic experiment, the information of the sample to be tested, and the analysis information of the chromatogram analysis model;

[0081] S52, extracting the signal value of the qualified chromatogram without abnormal chromatographic peaks, and calculating the chromatographic analysis parameters by using the time parameters, wherein the chromatographic analysis parameters include the retention time t R , peak height h, peak area A, half peak height W 1 / 2 , peak width W, standard deviation σ, and draw a chromatographic analysis report for reference by testing personnel based on the chromatographic experiment information, sample information, and calculated analysis parameters.

[0082] like Figure 3 As shown, another embodiment of the present invention is a chromatogram analysis device based on artificial intelligence, comprising:

[0083] A model training module is used to train the deep learning neural network to obtain a chromatogram analysis model;

[0084] An image segmentation module, used for receiving the digital chromatogram data image to be reviewed and analyzed through the chromatogram analysis model, and segmenting the digital chromatogram data image into regional images;

[0085] An image content status recognition module is used to review and identify the image content status of each regional image through a chromatogram analysis model to obtain a review prediction region, and mark the review prediction region with an image content status, wherein the image content status includes the highest peak, leading peak, tailing peak, broad peak, split peak, negative peak, peak with insufficient separation, baseline noise, and baseline drift of the chromatogram;

[0086] An image content state evaluation module is used to evaluate and calculate the image content state of the review prediction area and the possible probability of the image content state to obtain a first ratio. If the first ratio is greater than a preset first threshold probability ratio, the image content state is screened out and marked with a specific color.

[0087] The report generation module is used to draw a chromatographic review report and a chromatographic analysis report for reference by the testing personnel based on the ongoing chromatographic experiment information, the sample information to be tested, and the analysis information of the chromatogram analysis model.

[0088] like Figure 4 As shown, the model training module 10 specifically includes:

[0089] The image segmentation unit 11 is used to obtain a training sample image with image content status pre-labeled by a deep learning neural network, and segment the digital chromatogram data image of the training set into regional images; the deep learning neural network adopts the DeepLabv3+ network; the backbone network of the DeepLabv3+ network is set to GhostNetv2;

[0090] A first feature extraction unit 12 is used to perform row convolution and column convolution on the region image, standardize feature parameters through batch normalization, and reduce the linearity of feature parameters through nonlinear activation to obtain a first feature image that compresses the length and width of the region image;

[0091] The second feature extraction unit 13 is used to input the first feature image into 7 channels of the ASPP encoder with expansion rates of 1, 6, 12, 18, 24, 28, and 32 respectively, and the first feature image is convolved with convolution kernels expanded by 1, 6, 12, 18, 24, 28, and 32 times in the 7 channels respectively to extract deep features, and the extracted 7-channel deep features are compressed by point convolution to obtain a second feature image;

[0092] A feature fusion unit 14 is used to use the first feature image and the second feature image as input features of the decoder, and obtain the review prediction feature by fusing the resizing, point convolution, and bilinear interpolation;

[0093] The loss function calculation unit 15 is used to minimize the loss function calculation of the review prediction features and the labels corresponding thereto, and obtain the trained chromatogram analysis model when the loss value meets the convergence requirement.

[0094] It should be noted that technicians in the relevant field can clearly understand that the specific implementation process of the above-mentioned artificial intelligence-based chromatogram analysis device can refer to the corresponding description in the aforementioned method embodiment, and for the convenience and conciseness of the description, it will not be repeated here.

[0095] The above-mentioned chromatogram analysis device based on artificial intelligence can be implemented in the form of a computer program, and the computer program can be used in Figure 5 Runs on the computer device shown.

[0096] See also Figure 5 , Figure 55 is a schematic block diagram of a computer device provided in an embodiment of the present application. The computer device 500 may be a terminal or a server, wherein the terminal may be an electronic device with communication functions such as a smart phone, a tablet computer, a laptop computer, a desktop computer, a personal digital assistant, and a wearable device. The server may be an independent server or a server cluster composed of multiple servers.

[0097] See also Figure 5 The computer device 500 includes a processor 502 , a memory and a network interface 505 connected via a system bus 501 , wherein the memory may include a non-volatile storage medium 503 and an internal memory 504 .

[0098] The non-volatile storage medium 503 can store an operating system 5031 and a computer program 5032. The computer program 5032 includes program instructions, and when the program instructions are executed, the processor 502 can execute a chromatogram analysis method based on artificial intelligence.

[0099] The processor 502 is used to provide computing and control capabilities to support the operation of the entire computer device 500 .

[0100] The internal memory 504 provides an environment for the operation of the computer program 5032 in the non-volatile storage medium 503. When the computer program 5032 is executed by the processor 502, the processor 502 can execute a chromatogram analysis method based on artificial intelligence.

[0101] The network interface 505 is used to communicate with other devices over the network. Figure 5 The structure shown in the figure is merely a block diagram of a portion of the structure related to the solution of the present application, and does not constitute a limitation on the computer device 500 to which the solution of the present application is applied. The specific computer device 500 may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0102] The processor 502 is used to run the computer program 5032 stored in the memory to implement the chromatogram analysis method based on artificial intelligence as described above.

[0103] It should be understood that in the embodiment of the present application, the processor 502 may be a central processing unit (CPU), and the processor 502 may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Among them, the general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0104] It can be understood by those skilled in the art that all or part of the processes in the method for implementing the above embodiment can be completed by instructing the relevant hardware through a computer program. The computer program includes program instructions, and the computer program can be stored in a storage medium, which is a computer-readable storage medium. The program instructions are executed by at least one processor in the computer system to implement the process steps of the embodiment of the above method.

[0105] Therefore, the present invention also provides a storage medium. The storage medium may be a computer-readable storage medium. The storage medium stores a computer program, wherein the computer program includes program instructions. When the program instructions are executed by a processor, the processor executes the chromatogram analysis method based on artificial intelligence as described above.

[0106] The storage medium may be a USB flash drive, a mobile hard disk, a read-only memory (ROM), a magnetic disk, or an optical disk, or any other computer-readable storage medium that can store program codes.

[0107] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in terms of function in the above description. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0108] In the several embodiments provided by the present invention, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of each unit is only a logical function division, and there may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed.

[0109] The steps in the method of the embodiment of the present invention can be adjusted in order, combined and deleted according to actual needs. The units in the device of the embodiment of the present invention can be combined, divided and deleted according to actual needs. In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0110] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a storage medium. Based on this understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, terminal, or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention.

[0111] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed by the present invention, and these modifications or replacements should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be based on the protection scope of the claims.

Claims

1. A chromatogram analysis method based on artificial intelligence, characterized in that: Includes steps: S10, training the deep learning neural network to obtain a chromatogram analysis model; S20, receiving the digital chromatogram data image to be reviewed and analyzed through the chromatogram analysis model, and dividing the digital chromatogram data image into regional images; S30, using the chromatogram analysis model to review and identify the image content status of each regional image to obtain a review prediction region, and marking the review prediction region with an image content status, wherein the image content status includes the highest peak, leading peak, tailing peak, broad peak, split peak, negative peak, peak with insufficient separation, baseline noise, and baseline drift of the chromatogram; S40, evaluating and calculating the image content state of the review prediction area and the possible probability of the image content state to obtain a first ratio, and if the first ratio is greater than a preset first threshold probability ratio, screening it out and marking it with a specific color; S50, drawing a chromatographic review report and a chromatographic analysis report for reference by test personnel based on the ongoing chromatographic experiment information, the sample information to be tested, and the analysis information of the chromatogram analysis model.

2. The chromatogram analysis method based on artificial intelligence as claimed in claim 1, characterized in that: Step S10, training the deep learning neural network to obtain a chromatogram analysis model specifically includes: S11. A training sample image with pre-labeled image content status is obtained through a deep learning neural network, and the digital chromatogram data image of the training set is segmented into regional images; the deep learning neural network adopts the DeepLabv3+ network; the backbone network of the DeepLabv3+ network is set to GhostNetv2; S12, after performing row convolution and column convolution on the region image, standardize the feature parameters through batch normalization, and reduce the linearity of the feature parameters through nonlinear activation, so as to obtain a first feature image that compresses the length and width of the region image; S13, inputting the first feature image into 7 channels of the ASPP encoder with expansion rates of 1, 6, 12, 18, 24, 28, and 32 respectively, the first feature image is convolved with convolution kernels expanded by 1, 6, 12, 18, 24, 28, and 32 times in the 7 channels respectively, extracting deep features, and compressing the extracted 7-channel deep features by point convolution to obtain a second feature image; S14, using the first feature image and the second feature image as input features of the decoder, and obtaining the review prediction features by fusing the resizing, point convolution, and bilinear interpolation; S15. Minimize the loss function calculation for the review prediction features and the labels corresponding thereto, and obtain the trained chromatogram analysis model when the loss value meets the convergence requirement.

3. The chromatogram analysis method based on artificial intelligence as claimed in claim 2, characterized in that: In step S12, the formula used for performing row convolution and column convolution on the region image is: Among them, y i Represents the various values ​​on the output features, x represents the input features, w represents the convolution kernel, and r represents the step size.

4. The chromatogram analysis method based on artificial intelligence as claimed in claim 3, characterized in that: In step S12, the feature parameters are standardized by batch normalization, and the formula is: Among them, Θ is the training network parameter, and the gradient is estimated for a total of N training data sets.

5. The chromatogram analysis method based on artificial intelligence as claimed in claim 4, characterized in that: In step S12, the minimization loss function used by nonlinear activation to reduce the linearity of feature parameters adopts ReLu function and softmax function; the minimization loss function is: FocalLoss=-log p t (1-p t ) 2 Among them, l n Affected by the set weights, it represents the average value of the predicted probability of the training data set; p t is the model's predicted probability for the target class, indicating the adjustment of the model's attention to positive samples in the training data set; P i and G i It is the value of the prediction result at the i-th pixel, which indicates the similarity between the prediction result of the training model and the true label.

6. The chromatogram analysis method based on artificial intelligence as claimed in claim 1, characterized in that: The digital chromatographic data image is a two-dimensional gas / liquid chromatographic data graph, the x-axis of which is in units of time. y The units of the axes are signal values.

7. The chromatogram analysis method based on artificial intelligence as claimed in claim 1, characterized in that: Step S50, based on the ongoing chromatographic experiment information, the sample information to be tested, and the analysis information of the chromatogram analysis model, a chromatographic review report and a chromatographic analysis report are drawn for reference by the testing personnel, specifically including: S51, drawing a chromatographic review report for reference by test personnel based on the information of the ongoing chromatographic experiment, the information of the sample to be tested, and the analysis information of the chromatogram analysis model; S52, extracting the signal value of the qualified chromatogram without abnormal chromatographic peaks, and calculating the chromatographic analysis parameters by using the time parameters, wherein the chromatographic analysis parameters include the retention time t R , peak height h, peak area A, half peak height W 1 / 2 , peak width W, standard deviation σ, and draw a chromatographic analysis report for reference by testing personnel based on the chromatographic experiment information, sample information, and calculated analysis parameters.

8. A chromatogram analysis device based on artificial intelligence, characterized in that: include: A model training module is used to train the deep learning neural network to obtain a chromatogram analysis model; An image segmentation module, used for receiving the digital chromatogram data image to be reviewed and analyzed through the chromatogram analysis model, and segmenting the digital chromatogram data image into regional images; An image content status recognition module is used to review and identify the image content status of each regional image through a chromatogram analysis model to obtain a review prediction region, and mark the review prediction region with an image content status, wherein the image content status includes the highest peak, leading peak, tailing peak, broad peak, split peak, negative peak, peak with insufficient separation, baseline noise, and baseline drift of the chromatogram; An image content state evaluation module is used to evaluate and calculate the image content state of the review prediction area and the possible probability of the image content state to obtain a first ratio. If the first ratio is greater than a preset first threshold probability ratio, the image content state is screened out and marked with a specific color. The report generation module is used to draw a chromatographic review report and a chromatographic analysis report for reference by the testing personnel based on the ongoing chromatographic experiment information, the sample information to be tested, and the analysis information of the chromatogram analysis model.

9. A computer device, characterized in that: The computer device includes a memory and a processor, the memory stores a computer program, and the processor implements the artificial intelligence-based chromatogram analysis method as described in any one of claims 1 to 7 when executing the computer program.

10. A storage medium, characterized in that: The storage medium stores a computer program, and when the computer program is executed by a processor, the chromatogram analysis method based on artificial intelligence as described in any one of claims 1 to 7 can be implemented.

Images