Wine body component analysis method, device and equipment and storage medium

Abstract

The invention relates to a wine body component analysis method, device and equipment and a storage medium. According to the main technical scheme, the method comprises the following steps: acquiring component detection data corresponding to various wine body samples to construct a wine body component data set; determining key substance components related to wine body quality in different wine body types through the wine body component data set; determining interval ranges of the key substance components in different wine body types through an interval estimation method; determining a wine body analysis standard according to the key substance components in different wine body types and the interval range of the key substance components, and analyzing a target wine body according to the wine body analysis standard. The wine body analysis efficiency and accuracy can be improved.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence technology, and particularly to a method, device, equipment and storage medium for analyzing the components of liquor body. Background Art

[0002] In the field of liquor quality control, traditional methods mainly rely on manual experience and sensory evaluation. Specifically, wine tasters evaluate the liquor body through senses such as smell and taste, and combine the general qualified ranges of conventional physical and chemical indexes such as alcohol content, total acid, and total ester to control the quality. Taking Maotai-flavor liquor as an example, although more than a thousand kinds of substance components have been detected in it, the traditional quality control method seems powerless in the face of complex and diverse trace components.

[0003] The defects of the existing technology are mainly reflected in the following aspects: the traditional method relies too much on the personal sensory judgment of wine tasters, and different wine tasters may cause deviations in the judgment results due to factors such as experience and physiological state, lacking objectivity and consistency; in the face of up to a thousand kinds of trace components in liquor, the traditional method is difficult to comprehensively and accurately control the content and proportion of each component, and cannot meet the requirements of modern refined liquor production for multi-component collaborative control; to ensure the stable quality of liquor bodies in different batches, a large amount of tasting and physical and chemical detection work needs to be carried out, which is time-consuming and laborious, and it is difficult to achieve real-time and efficient quality control.

[0004] Therefore, there is an urgent need for a method for analyzing the components of liquor body that combines advanced analysis techniques to improve the quality and efficiency of liquor body component analysis. Summary of the Invention

[0005] Based on this, the present application provides a method, device, equipment and storage medium for analyzing the components of liquor body to solve the problems existing in the prior art.

[0006] In the first aspect, a method for analyzing the components of liquor body is provided, and the method includes:

[0007] Obtain the component detection data corresponding to a variety of liquor body samples to construct a liquor body component data set;

[0008] Determine the key substance components related to the liquor body quality in different liquor body types through the liquor body component data set;

[0009] Determine the interval range of the key substance components in different liquor body types through the interval estimation method;

[0010] Determine the liquor body analysis standard through the key substance components and the interval range of the key substance components in different liquor body types, and analyze the target liquor body through the liquor body analysis standard.

[0011] According to an implementable manner in the embodiments of the present application, determining the key substance components related to the wine body quality in different wine body types through the wine body component data set includes:

[0012] Training a wine body classification model through the wine body component data set;

[0013] Obtaining the contribution degree of each component substance in any wine body type to the model through the wine body classification model, and arranging the contribution degrees of each component substance to the model in descending order;

[0014] Accumulating the contribution degrees of each component substance to the model in sequence based on the arrangement;

[0015] Determining all the component substances before the cumulative contribution degree reaches the preset range as the key substance components in any wine body type.

[0016] According to an implementable manner in the embodiments of the present application, training a wine body classification model through the wine body component data set includes:

[0017] Taking the wine body component data set as the model input, and adjusting the model parameters based on the gradient boosting algorithm;

[0018] Optimizing the model parameters through multiple rounds of iteration until the model accuracy reaches the preset threshold;

[0019] Taking the model with the accuracy reaching the preset threshold as the wine body classification model.

[0020] According to an implementable manner in the embodiments of the present application, obtaining the component detection data corresponding to multiple wine body samples to construct a wine body component data set includes:

[0021] Determining the component detection data in multiple wine body samples through a gas chromatography and / or mass spectrometry detection device;

[0022] Determining the set of each wine body sample and the corresponding component detection data as the wine body component data set.

[0023] According to an implementable manner in the embodiments of the present application, determining the interval range of the key substance components in different wine body types through the interval estimation method includes:

[0024] Obtaining the detection data of the key substance components in different wine body types;

[0025] Obtaining the preset confidence level value;

[0026] Calculating the confidence interval based on the detection data and the confidence level value;

[0027] Determining the interval range of the key substance components in different wine body types based on the confidence interval.

[0028] According to an implementable manner in the embodiments of the present application, determining the wine body analysis standard through the key substance components and the range of the key substance components in different wine body types, and analyzing the target wine body through the wine body analysis standard includes:

[0029] Determining the wine body analysis standard through the key substance components and the range of the key substance components in different wine body types;

[0030] Obtaining the component detection data of the target wine body;

[0031] Analyzing the target wine body based on the component detection data of the target wine body and the wine body analysis standard.

[0032] According to an implementable manner in the embodiments of the present application, the preset confidence level value is 90%.

[0033] In a second aspect, a wine body component analysis device is provided, and the device includes:

[0034] A collection module: used to obtain the component detection data corresponding to a variety of wine body samples to construct a wine body component data set;

[0035] A first calculation module: used to determine the key substance components related to the wine body quality in different wine body types through the wine body component data set;

[0036] A second calculation module: used to determine the range of the key substance components in different wine body types through the interval estimation method;

[0037] An analysis module: determining the wine body analysis standard through the key substance components and the range of the key substance components in different wine body types, and analyzing the wine body components through the wine body analysis standard.

[0038] In a third aspect, a computer device is provided, including:

[0039] At least one processor; and

[0040] A memory communicatively connected to the at least one processor; wherein,

[0041] The memory stores computer instructions executable by the at least one processor, and the computer instructions are executed by the at least one processor so that the at least one processor can execute the method described in the first aspect above.

[0042] In a fourth aspect, a computer-readable storage medium is provided, on which computer instructions are stored, and the computer instructions are characterized in that the computer instructions are used to cause a computer to execute the method described in the first aspect above.

[0043] According to the technical content provided by the embodiments of the present application, by obtaining the component detection data corresponding to multiple wine body samples to construct a wine body component data set, determining the key substance components related to the wine body quality in different wine body types through the wine body component data set, determining the interval range of the key substance components in different wine body types through the interval estimation method, determining the wine body analysis standard through the key substance components and the interval range of the key substance components in different wine body types, and analyzing the target wine body through the wine body analysis standard. By constructing a multi-type wine body component data set, systematically integrating the information of different wine body characteristic substances, further screening the key substance components, accurately identifying the core indicators strongly related to the wine body quality, using the interval estimation method to determine the distribution range of the key components, and then determining the wine body analysis standard, and analyzing the target wine body through the wine body analysis standard, the efficiency and accuracy of wine body analysis are improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Figure 1 is a schematic flowchart of a wine body component analysis method in an embodiment;

[0045] Figure 2 is a flowchart of a wine body component analysis method in an embodiment;

[0046] Figure 3 is a structural block diagram of a wine body component analysis device in an embodiment;

[0047] Figure 4 is a schematic structural diagram of a computer device in an embodiment. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0048] The following further details the present application in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0049] Figure 1 is a flowchart of a wine body component analysis method provided by an embodiment of the present application, as Figure 1 shown, and in conjunction with Figure 2 , the method may include the following steps:

[0050] Step 101: Obtain the component detection data corresponding to multiple wine body samples to construct a wine body component data set;

[0051] Specifically, taking Maotai-flavor liquor as an example, up to thousands of substance components have been detected at the present stage. However, for a long time, among these complex trace components, it has always been difficult to determine which ones are the key factors for distinguishing different liquor products and styles. At present, by widely collecting quality inspection data of various types and batches and then integrating machine learning algorithms and interval estimation methods, a new journey has been launched to explore the key substance components that affect the quality of the liquor body, providing a new opportunity and effective way for deeply analyzing the mystery of liquor and accurately controlling its quality. In this step, component detection data corresponding to multiple liquor body samples are obtained to construct a liquor body component data set.

[0052] Step 102: Determine the key substance components related to the quality of the liquor body in different liquor body types through the liquor body component data set;

[0053] Specifically, based on the historical full-scale trace component data of the liquor body type, that is, the liquor body component data set, the key substance components related to the quality of the liquor body in different liquor body types are determined by means of artificial intelligence and other methods.

[0054] Step 103: Determine the interval range of the key substance components in different liquor body types by the interval estimation method;

[0055] Specifically, different from traditional technologies, traditional technologies lack scientific and quantitative liquor body quality control standards, especially there is no systematic determination method for the quality key indicators and reasonable interval ranges of different types of liquor bodies. In this step, the interval estimation method is used to comprehensively consider factors such as the distribution characteristics, mean value, and standard deviation of the data, and determine the reasonable interval range of the key substance component content in different types of liquor bodies, so as to form a range control standard.

[0056] Step 104: Determine the liquor body analysis standard through the key substance components and the interval range of the key substance components in different liquor body types, and analyze the target liquor body through the liquor body analysis standard.

[0057] Specifically, according to the above steps, the reasonable interval range of the key substance component content in each different classified liquor body is estimated. The quality key indicators and reasonable interval ranges of different types of liquor bodies constitute the chromatographic index control standard for different liquor body qualities. Thus, it provides a very solid and scientific quantitative basis for quality control, type evaluation, and process optimization in the liquor production process, effectively ensuring the stability and consistency of product quality and improving the production and quality management levels.

[0058] It can be seen that in the embodiments of the present application, a wine body component dataset is constructed by obtaining component detection data corresponding to multiple wine body samples. The key substance components related to the wine body quality in different wine body types are determined through the wine body component dataset. The interval range of the key substance components in different wine body types is determined by the interval estimation method. The wine body analysis standard is determined through the key substance components and the interval range of the key substance components in different wine body types. The target wine body is analyzed through the wine body analysis standard. By constructing a multi-type wine body component dataset, the information of different wine body characteristic substances is systematically integrated, and the key substance components are further screened, so as to accurately identify the core indicators strongly related to the wine body quality. The interval estimation method is used to determine the distribution range of the key components, and then the wine body analysis standard is determined. The target wine body is analyzed through the wine body analysis standard, improving the efficiency and accuracy of the wine body analysis.

[0059] In an embodiment of the present application, a wine body classification model is trained through the wine body component dataset, including: using the wine body component dataset as the model input, and adjusting the model parameters based on the gradient boosting algorithm; optimizing the model parameters through multiple rounds of iteration until the model accuracy reaches a preset threshold; using the model with the accuracy reaching the preset threshold as the wine body classification model.

[0060] Specifically, based on the historical full-volume trace component data of the wine body types, it is used as the input data for model training, and the gradient boosting algorithm XGBoost is applied to construct a wine body classification model. During the training process, the model parameters are continuously adjusted and optimized through multiple rounds of iteration until the classification accuracy of the model on the training set stably reaches a preset threshold, such as more than 98%. In addition, the classification accuracy of the model on the validation dataset also reaches the preset threshold, such as 98% and above. The model with the accuracy reaching the preset threshold is used as the wine body classification model.

[0061] The embodiments of the present application are different from the traditional technologies. In terms of wine body classification and quality assessment, they mostly rely on manual experience or simple statistical analysis and lack a high-precision classification model based on advanced algorithms. In this embodiment, the gradient boosting algorithm XGBoost is applied to construct a wine body classification model, and the model parameters are optimized through multiple rounds of iteration to achieve a high classification accuracy. The XGBoost algorithm has strong feature learning and classification capabilities, and can extract key classification features from complex trace component data. By continuously adjusting the parameters and iteratively optimizing, the model can accurately identify the categories and quality grades of different wine bodies. Compared with the traditional methods, it can classify and evaluate the quality of wine bodies more scientifically and objectively, reducing the influence of human errors and subjective judgments.

[0062] In one embodiment of the present application, key substance components related to liquor body quality are determined from the liquor body component dataset, including: training a liquor body classification model using the liquor body component dataset; obtaining the contribution degree of each component substance in any liquor body type to the model through the liquor body classification model, and arranging the contribution degrees of each component substance to the model in descending order; cumulatively adding the contribution degrees of each component substance to the model in order based on the arrangement; and determining all component substances before the cumulative contribution degree reaches a preset range as the key substance components in any liquor body type.

[0063] Specifically, a liquor body classification model is trained using the liquor body component dataset, and the contribution degree of each component substance in any liquor body type to the model is obtained through the liquor body classification model. The contribution degrees of each component substance to the model are arranged in descending order, the contribution degrees of each component substance to the model are cumulatively added in order based on the arrangement, and all component substances before the cumulative contribution degree reaches a preset range are determined as the key substance components in any liquor body type. The contribution degrees of physical and chemical substance indicators are arranged in descending order, where the indicators are the physical and chemical indicators constituting the liquor body, the contribution degrees of the indicators are added up, and trace component substances before the cumulative contribution degree reaches 90% are determined as the substance components having a key influence on the liquor body quality.

[0064] The embodiment of the present application is different from the traditional technology in accurately determining the substance components having a key influence on the liquor body quality, which is often a rough judgment based on experience or limited research. In this embodiment, by arranging the contribution degrees of the model in descending order and cumulatively adding them, trace component substances before the cumulative contribution degree reaches 90% are determined as the key substance components. Based on the data-driven and model analysis method, it is possible to accurately screen out the substances that play a key role in the liquor body quality from numerous trace components, providing a clear target for subsequent quality control and process optimization for these key substances, making the quality control more targeted and effective, and improving the accuracy of production and quality management.

[0065] In one embodiment of the present application, component detection data corresponding to multiple liquor body samples are obtained to construct a liquor body component dataset, including: determining the component detection data in multiple liquor body samples through a gas chromatography and / or mass spectrometry detection device; and determining the set of each liquor body sample and its corresponding component detection data as the liquor body component dataset.

[0066] Specifically, the product samples of each batch are sent to the inspection department in a timely manner, and gas chromatography and mass spectrometry detection technologies are used to comprehensively analyze the liquor body, accurately detect and obtain detailed data of various trace components in the liquor body. A liquor body classification trace component database is constructed, and through continuously collecting, sorting, and storing the accurate data obtained from the gas chromatography and mass spectrometry detections of each batch of products, systematic accumulation and integration of the liquor body trace component information are realized.

[0067] In one embodiment of the present application, the interval range of key substance components in different liquor body types is determined by the interval estimation method, including: obtaining the detection data of key substance components in different liquor body types; obtaining the preset confidence level value; calculating the confidence interval based on the detection data and the confidence level value; and determining the interval range of key substance components in different liquor body types based on the confidence interval.

[0068] Specifically, taking the key substance components extracted by the liquor body classification model as the core index basis, further analysis is carried out on the trace component data of different types of products. Using the interval estimation method, interval estimation is a statistical method for inferring population parameters based on sample data. Its core is to construct a confidence interval (Confidence Interval, CI), which expresses the range within which the true value of the parameter may fall in the form of probability, rather than providing a single definite value.

[0069] Mathematical expression and assumptions:

[0070]

[0071] Sample mean;

[0072] σ: is the population standard deviation (if unknown, it can be replaced by the sample standard deviation s);

[0073] n: sample size;

[0074] Z a / 2 : Quantile of the standard normal distribution (e.g., at a 90% confidence level, α = 0.1α = 0.1, Z 0.05 = 1.645);

[0075] Taking the physical and chemical index analysis of soy sauce-flavored liquor as an example: at a 90% confidence level, the confidence interval of the ethyl acetate content in a specific liquor body is [2340mg / L, 3120mg / L]. Therefore, considering various factors such as the distribution characteristics, mean, and standard deviation of the data, a reasonable interval range of the key substance components in each different classified liquor body is estimated.

[0076] The embodiment of the present application uses the interval estimation method, comprehensively considers factors such as the distribution characteristics, mean, and standard deviation of the data, and determines the technical method of the substance components that have a key influence on the liquor body quality through model contribution degree analysis, determines the reasonable interval range of the key substance components in different types of liquor bodies, thereby constituting a range control standard. This control standard provides a quantitative basis for quality control, evaluation, and process optimization in the liquor production process, enables clear reference standards for quality control in the production process, can effectively ensure the stability and consistency of product quality, improve the overall production and quality management level, and avoid the fuzziness and uncertainty of quality control in traditional technologies.

[0077] In one embodiment of the present application, the wine body analysis standard is determined by the key substance components and the range of the key substance components in different wine body types, and the target wine body is analyzed through the wine body analysis standard, including: determining the wine body analysis standard by the key substance components and the range of the key substance components in different wine body types; obtaining the component detection data of the target wine body; and analyzing the target wine body based on the component detection data of the target wine body and the wine body analysis standard.

[0078] Specifically, the quality key indicators and the reasonable range of the indicators of different types of wine bodies constitute the chromatographic index control standard for the quality of different wine bodies. Determine the wine body analysis standard by the key substance components and the range of the key substance components in different wine body types; obtain the component detection data of the target wine body; analyze the target wine body based on the component detection data of the target wine body and the wine body analysis standard. Thus, it provides an extremely solid and scientific quantitative basis for quality control, type evaluation, and process optimization in the liquor production process, effectively ensuring the stability and consistency of product quality and improving the production and quality management levels.

[0079] The embodiment of the present application uses the interval estimation method, comprehensively considers factors such as the distribution characteristics, mean value, and standard deviation of the data, and determines the reasonable range of the key substance components in different types of wine bodies, thereby constituting the range control standard. This control standard provides a quantitative basis for quality control, evaluation, and process optimization in the liquor production process, making the quality control in the production process have a clear reference standard, effectively ensuring the stability and consistency of product quality, improving the overall production and quality management levels, and avoiding the fuzziness and uncertainty of quality control in traditional technologies.

[0080] The embodiment of the present application has at least the following advantages:

[0081] The present invention comprehensively analyzes the wine body with the detection data of gas chromatography and mass spectrometry, obtains detailed trace component data, and constructs a base wine physical and chemical substance index database and a wine body classification model based on this. Compared with the prior art that relies on manual experience or simple detection methods for quality assessment, this technology can more accurately determine the key substance components and content ranges of different types of wine bodies, thereby realizing precise quality control and classification evaluation. It can make a correct, comprehensive, and scientific judgment on the quality, overcome the drawbacks of the traditional sensory wine evaluation method of "only can be understood, inconvenient to express", enable the evaluation and identification to be fast, convenient, and accurate; avoid classification misjudgment caused by human judgment errors, and improve the accuracy and reliability of product quality classification.

[0082] The micro-component control standards established by the present invention can clarify the key quality indicators and reasonable range for different types of wine bodies for enterprises, making the quality monitoring in the production process more convenient and efficient. In the blending combination, the "computer-aided blending" technology can be combined with the control standards for comparison to promptly detect quality abnormalities and take measures. Compared with the prior art, the process of manual experience judgment is reduced, and the number of quality inspections is decreased. For example, the traditional technology may require a large amount of time and manpower for multiple rounds of tasting and index detection of the wine body, while the detection and judgment process of the present invention is pre-posed, enabling more wine body samples to be processed in a shorter time, greatly improving the overall efficiency of production and quality management.

[0083] It should be understood that although Figure 1 the steps in the flowchart of Figure 1 are shown in sequence according to the indication of the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless there is a clear description in this application, the execution of these steps has no strict order limit, and these steps can be executed in other orders. Moreover,

[0084] Figure 3 is a schematic structural diagram of a wine body component analysis device provided by an embodiment of the present application. As Figure 3 shown, the device may include:

[0085] A collection module 301: used to obtain component detection data corresponding to a variety of wine body samples to construct a wine body component data set;

[0086] A first calculation module 302: used to determine key substance components related to the quality of different wine body types through the wine body component data set;

[0087] A second calculation module 303: used to determine the range of the key substance components in different wine body types through the interval estimation method;

[0088] An analysis module 304: used to determine the wine body analysis standard through the key substance components and the range of the key substance components in different wine body types, and analyze the wine body components through the wine body analysis standard.

[0089] In an embodiment of the present application, the first calculation module 302: is further used to train a wine body classification model through the wine body component data set;

[0090] Obtain the contribution degree of each component substance in any wine body type to the model through the wine body classification model, and arrange the contribution degrees of each component substance to the model in descending order;

[0091] Based on the arrangement, accumulate the contribution degrees of each component substance to the model in sequence;

[0092] Determine all component substances before the cumulative contribution degree reaches the preset range as the key substance components in any wine body type.

[0093] In an embodiment of the present application, the first calculation module 302: is further configured to use the wine body component data set as the model input, and adjust the model parameters based on the gradient boosting algorithm;

[0094] Optimize the model parameters through multiple rounds of iteration until the model accuracy reaches the preset threshold;

[0095] Use the model with the accuracy reaching the preset threshold as the wine body classification model.

[0096] In an embodiment of the present application, the acquisition module 301: is further configured to determine the component detection data in a variety of wine body samples through a gas chromatography and / or mass spectrometry detection device;

[0097] Determine the set of each wine body sample and the corresponding component detection data as the wine body component data set.

[0098] In an embodiment of the present application, the second calculation module 303: is used to obtain the detection data of the key substance components in different wine body types;

[0099] Obtain the preset confidence level value;

[0100] Calculate the confidence interval based on the detection data and the confidence level value;

[0101] Determine the interval range of the key substance components in different wine body types based on the confidence interval.

[0102] In an embodiment of the present application, the analysis module 304: is used to determine the wine body analysis standard through the key substance components in different wine body types and the interval range of the key substance components;

[0103] Obtain the component detection data of the target wine body;

[0104] Analyze the target wine body based on the component detection data of the target wine body and the wine body analysis standard.

[0105] According to the specific embodiments provided by the present application, the technical solutions provided by the present application may have the following advantages:

[0106] The present invention comprehensively analyzes the wine body by using the detection data of gas chromatography and mass spectrometry, obtains detailed trace component data, and constructs a physical and chemical substance index database of base wine and a wine body classification model based on this. Compared with the prior art that relies on manual experience or simple detection methods for quality assessment, this technology can more accurately determine the key substance components and content ranges of different types of wine bodies, so as to achieve precise quality control and classification evaluation. It can make a correct, comprehensive and scientific judgment on the quality, overcome the disadvantages of the traditional sensory wine evaluation method of "only can be understood but not easily described", and make the evaluation and identification fast, convenient and accurate; avoid the classification misjudgment caused by human judgment errors, and improve the accuracy and reliability of product quality classification.

[0107] The trace component control standard established by the present invention can clarify the key quality indicators and reasonable range of different types of wine bodies for enterprises, making the quality monitoring in the production process more convenient and efficient. In the blending combination, the "microcomputer-aided blending" technology can be combined with the control standard for comparison to timely detect quality abnormalities and take measures. Compared with the prior art, it reduces the process of manual experience judgment and the number of quality inspections. For example, the traditional technology may require a lot of time and manpower to conduct multiple rounds of tasting and index detection on the wine body, while the detection and judgment process of the present invention is pre-posed, and more wine body samples can be processed in a shorter time, greatly improving the overall efficiency of production and quality management.

[0108] It can be understood that implementing any method or product of this application does not necessarily need to achieve all the above advantages at the same time.

[0109] For the same or similar parts among the above embodiments, reference can be made to each other. Each embodiment focuses on the differences from other embodiments. In particular, for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can refer to the partial description of the method embodiment.

[0110] It should be noted that the use of user data may be involved in the embodiments of this application. In actual applications, within the scope permitted by applicable laws and regulations (such as when the user clearly consents, gives a practical notice to the user, and the user clearly authorizes, etc.), user-specific personal data can be used in the solutions described in this article within the scope permitted by applicable laws and regulations.

[0111] According to the embodiments of this application, this application also provides a computer device and a computer-readable storage medium.

[0112] As Figure 4As shown, it is a block diagram of a computer device according to an embodiment of the present application. The computer device is intended to represent various forms of digital computers or mobile devices. Among them, the digital computer may include a desktop computer, a portable computer, a workbench, a personal digital assistant, a server, a mainframe computer, and other suitable computers. The mobile device may include a tablet computer, a smart phone, a wearable device, etc.

[0113] As Figure 4 shown, the device 400 includes a computing unit 401, a ROM 402, a RAM 403, a bus 404, and an input / output (I / O) interface 405. The computing unit 401, the ROM 402, and the RAM 403 are connected to each other through the bus 404. The input / output (I / O) interface 405 is also connected to the bus 404.

[0114] The computing unit 401 can execute various processes in the method embodiments of the present application according to the computer instructions stored in the read-only memory (ROM) 402 or the computer instructions loaded from the storage unit 408 into the random access memory (RAM) 403. The computing unit 401 can be various general-purpose and / or dedicated processing components with processing and computing capabilities. The computing unit 401 may include, but is not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. In some embodiments, the method provided by the embodiments of the present application can be implemented as a computer software program, which is tangibly contained in a computer-readable storage medium, such as the storage unit 408.

[0115] The RAM 403 can also store various programs and data required for the operation of the device 400. Part or all of the computer programs can be loaded and / or installed onto the device 400 via the ROM 802 and / or the communication unit 409.

[0116] The input unit 406, the output unit 407, the storage unit 408, and the communication unit 409 in the device 400 can be connected to the I / O interface 405. Among them, the input unit 406 can be, for example, a keyboard, a mouse, a touch screen, a microphone, etc.; the output unit 407 can be, for example, a display, a speaker, an indicator light, etc. The device 400 can exchange information, data, etc. with other devices through the communication unit 409.

[0117] It should be noted that the device may also include other components necessary for normal operation. It may also only include the components necessary to implement the solution of the present application, and does not necessarily include all the components shown in the figure.

[0118] The various embodiments of the systems and techniques described herein can be implemented in digital electronic circuitry, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on a chip (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof.

[0119] The computer instructions for implementing the methods of the present application can be written in any combination of one or more programming languages. These computer instructions can be provided to the computing unit 401 such that when the computer instructions are executed by the computing unit 401, such as a processor, the steps involved in the method embodiments of the present application are executed.

[0120] The computer-readable storage medium provided by the present application can be a tangible medium that can contain or store computer instructions for executing the steps involved in the method embodiments of the present application. The computer-readable storage medium can include, but is not limited to, storage media in the forms of electronic, magnetic, optical, electromagnetic, etc.

[0121] The above specific embodiments do not constitute a limitation on the protection scope of the present application. 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 the present application shall be included within the protection scope of the present application.

Claims

1. A method for analyzing the components of a wine body, characterized in that, The method includes: Obtaining component detection data corresponding to multiple wine body samples to construct a wine body component data set; Determining key substance components related to wine body quality in different wine body types through the wine body component data set; Determining the interval range of the key substance components in different wine body types through the interval estimation method; Determining a wine body analysis standard through the key substance components and the interval range of the key substance components in different wine body types, and analyzing the target wine body through the wine body analysis standard.

2. The method for analyzing the composition of the wine body according to claim 1, wherein The determining of the key substance components related to wine body quality in different wine body types through the wine body component data set includes: Training a wine body classification model through the wine body component data set; Obtaining the contribution degree of each component substance in any wine body type to the model through the wine body classification model, and arranging the contribution degrees of the component substances to the model in descending order; Cumulatively adding the contribution degrees of the component substances to the model in sequence based on the arrangement; Determining all component substances before the cumulative contribution degree reaches the preset range as the key substance components in any wine body type.

3. The method for analyzing the body liquid composition according to claim 2, characterized in that The training of the wine body classification model through the wine body component data set includes: Taking the wine body component data set as the model input and adjusting the model parameters based on the gradient boosting algorithm; Optimizing the model parameters through multiple rounds of iteration until the model accuracy reaches the preset threshold; Taking the model with the accuracy reaching the preset threshold as the wine body classification model.

4. The method for analyzing the body liquor composition according to claim 1, characterized in that, The obtaining of component detection data corresponding to multiple wine body samples to construct a wine body component data set includes: Determining the component detection data in multiple wine body samples through a gas chromatograph and / or mass spectrometer detection device; Determining the set of each wine body sample and the corresponding component detection data as the wine body component data set.

5. The method for analyzing the composition of wine body according to claim 1, wherein The determining of the interval range of the key substance components in different wine body types through the interval estimation method includes: Obtaining the detection data of the key substance components in different wine body types; Obtaining the preset confidence level value; Calculating the confidence interval based on the detection data and the confidence level value; Determining the interval range of the key substance components in different wine body types based on the confidence interval.

6. The method for analyzing the body liquor composition according to claim 1, wherein The determining of the wine body analysis standard through the key substance components and the interval range of the key substance components in different wine body types, and analyzing the target wine body through the wine body analysis standard includes: Determining the wine body analysis standard through the key substance components and the interval range of the key substance components in different wine body types; Obtaining the component detection data of the target wine body; Analyzing the target wine body based on the component detection data of the target wine body and the wine body analysis standard.

7. The method for analyzing the body liquor composition according to claim 1, wherein The preset confidence level value is 90%.

8. A device for analyzing the components of a liquor body, characterized in that, The device includes: A collection module: used for obtaining component detection data corresponding to multiple wine body samples to construct a wine body component data set; A first calculation module: used for determining key substance components related to wine body quality in different wine body types through the wine body component data set; A second calculation module: used for determining the interval range of the key substance components in different wine body types through the interval estimation method; Analysis module: Determine the wine body analysis standard based on the key substance components and the range of the key substance components in different wine body types, and analyze the wine body components according to the wine body analysis standard.

9. A computer device, comprising: At least one processor; And A memory communicatively connected to the at least one processor; wherein, The memory stores computer instructions executable by the at least one processor, and the computer instructions are executed by the at least one processor so that the at least one processor can execute the method according to any one of claims 1-7.

10. A computer-readable storage medium having computer instructions stored thereon, characterized in that, The computer instructions are used to cause a computer to execute the method according to any one of claims 1 to 7.

Images