A tobacco extract identification method, device, electronic equipment and storage medium

Abstract

The application discloses a tobacco extract identification method and device, electronic equipment and a storage medium. The method comprises the following steps: determining a first tobacco extract and a first origin; the first tobacco extract is a tobacco extract that needs to be identified for authenticity, and the first origin is the origin of the raw material of the first tobacco extract; based on the first origin, a second extract identification model is determined in each first extract identification model; mass spectrum data of the first tobacco extract is determined, and a first characteristic ion is determined in the mass spectrum data of the first tobacco extract; the first characteristic ion is input into the pre-trained second extract identification model, and it is determined whether the origin of the first tobacco extract is the first origin. By using the technical solution of the application, the unique organic molecules in the product can be comprehensively utilized to accurately judge the authenticity of the tobacco extract.

Description

Technical Field

[0001] This invention relates to the field of product authenticity verification technology, and in particular to a method, apparatus, electronic device, and storage medium for identifying tobacco extracts. Background Technology

[0002] Tobacco extracts are irreplaceable flavoring ingredients for cigarette flavoring and the development of new tobacco products, and are an important component of the core technology for cigarette flavoring in the industry. Tobacco extracts are prepared from tobacco leaves, tobacco dust, tobacco fragments, etc., through various extraction, separation, and concentration processes such as solvent extraction, supercritical extraction, steam distillation, membrane separation, and molecular distillation.

[0003] Currently, domestic and international methods for tracing the origin of tobacco leaves or tobacco extracts are mostly based on gas chromatography-mass spectrometry (GC-MS) analysis of volatile components, as well as information on some non-volatile components obtained through derivatization or chemometrics. Natural products contain thousands or even tens of thousands of organic molecules, while GC-MS can only obtain information on dozens to hundreds. Therefore, the analytical data typically covers only 1% or even less of all molecular components in a sample, making it difficult to accurately determine the authenticity of tobacco extracts. Summary of the Invention

[0004] This invention provides a method, apparatus, electronic device, and storage medium for identifying tobacco extracts, in order to solve the problem that traditional methods are unable to accurately determine the authenticity of tobacco extracts.

[0005] According to one aspect of the present invention, a method for identifying tobacco extracts is provided, the method comprising: The first tobacco extract and the first place of origin are determined; the first tobacco extract is the tobacco extract that needs to be verified for authenticity, and the first place of origin is the place of origin of the raw materials of the first tobacco extract. Based on the primary place of origin, the identification model for the second extract is determined among the various identification models for the primary extract; Determine the mass spectrometry data of the first tobacco extract, and identify the first characteristic ion in the mass spectrometry data of the first tobacco extract; The first characteristic ion is input into a pre-trained second extract identification model to determine whether the origin of the first tobacco extract is the first origin.

[0006] According to another aspect of the present invention, a tobacco extract identification apparatus is provided, the apparatus comprising: The extract acquisition module is used to determine the first tobacco extract and the first place of origin; the first tobacco extract is the tobacco extract that needs to be verified for authenticity, and the first place of origin is the place of origin of the raw materials of the first tobacco extract; The model selection module is used to determine the second extract identification model based on the first place of origin among various first extract identification models; The feature ion screening module is used to determine the mass spectrometry data of the first tobacco extract and to identify the first feature ion in the mass spectrometry data of the first tobacco extract. The origin verification module is used to input the first characteristic ion into the pre-trained second extract identification model to determine whether the origin of the first tobacco extract is the first origin.

[0007] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising: At least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by at least one processor, such that the at least one processor is able to perform the tobacco extract identification method according to any embodiment of the present invention.

[0008] According to another aspect of the present invention, a computer-readable storage medium is provided, which stores computer instructions for causing a processor to execute and implement the tobacco extract identification method of any embodiment of the present invention.

[0009] According to another aspect of the present invention, a computer program product is provided, comprising a computer program that, when executed by a processor, implements the tobacco extract identification method of any embodiment of the present invention.

[0010] The technical solution of this invention involves determining a first tobacco extract and a first place of origin; the first tobacco extract is the tobacco extract for which authenticity verification is required, and the first place of origin is the origin of the raw materials for the first tobacco extract; based on the first place of origin, a second extract identification model is determined among various first extract identification models; the mass spectrometry data of the first tobacco extract is determined, and a first characteristic ion is identified in the mass spectrometry data of the first tobacco extract; the first characteristic ion is input into the pre-trained second extract identification model to determine whether the origin of the first tobacco extract is the first place of origin. This method can comprehensively utilize the unique organic molecules in the product to accurately determine the authenticity of the tobacco extract.

[0011] 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

[0012] 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.

[0013] Figure 1 This is a flowchart of a method for identifying tobacco extracts provided in an embodiment of the present invention; Figure 2 This is a flowchart of another method for identifying tobacco extracts provided in an embodiment of the present invention; Figure 3 This is a schematic diagram of the structure of a tobacco extract identification device provided in an embodiment of the present invention; Figure 4 This is a structural block diagram of an electronic device for a method of identifying tobacco extracts provided in an embodiment of the present invention. Detailed Implementation

[0014] 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.

[0015] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0016] In one embodiment, Figure 1 This is a flowchart of a method for identifying tobacco extracts according to an embodiment of the present invention. This embodiment is applicable to the identification of the authenticity of tobacco extracts. The method can be executed by a tobacco extract identification device, which can be implemented in hardware and / or software and can be configured in an electronic device with data processing capabilities. Figure 1 As shown, the method includes: S110. Determine the first tobacco extract and the first place of origin; the first tobacco extract is the tobacco extract that needs to be verified for authenticity, and the first place of origin is the place of origin of the raw materials of the first tobacco extract.

[0017] Tobacco can be an annual herbaceous economic crop belonging to the Solanaceae family and the Nicotiana genus. The main part used is the leaves, which, after processing through methods such as curing, sun-drying, and air-drying, can be processed into tobacco products such as cigarettes, cigars, and shredded tobacco. Tobacco can be classified according to its place of origin, including but not limited to Zimbabwean tobacco and Yunnan tobacco. It can also be classified according to its processing method, including but not limited to flue-cured tobacco, Burley tobacco, aromatic tobacco / Oriental tobacco, sun-cured tobacco, air-dried tobacco, yellow-flowered tobacco, and cigar tobacco. Tobacco extracts can be complex mixtures containing characteristic tobacco aroma components, nicotine, and other endogenous substances, obtained by extracting and enriching tobacco (including leaves, stems, and dust) through physical / chemical processes such as solvent extraction, distillation, supercritical CO2 extraction, pyrolysis, concentration, and separation purification. Tobacco extracts include Zimbabwean tobacco extracts and Yunnan tobacco extracts. The first tobacco extract can be a tobacco extract for which it is necessary to determine whether the place of origin is the first place of origin claimed by the tobacco extract.

[0018] S120. Based on the first place of origin, determine the second extract identification model among the various first extract identification models.

[0019] The first extract identification model can be a pre-trained model used to determine the authenticity of tobacco extracts. The model construction of various first extract identification models differs, including but not limited to random forest models, XGBoost models, and SVM support vector machines.

[0020] Since different first extract identification models may have different accuracy rates when identifying tobacco extracts from different origins, the corresponding first extract identification model can be selected as the second extract identification model when identifying tobacco extracts, thereby ensuring the accuracy of the final results.

[0021] Among these, based on the primary place of origin, the identification model for the second extract is determined from various primary extract identification models, including: Determine the accuracy of each first extract identification model for verifying the authenticity of tobacco extracts from the first place of origin, and determine the second extract identification model based on the accuracy.

[0022] Optionally, the process of constructing the first extract identification model includes: Determine the training sample data; the training sample data consists of the second characteristic ion corresponding to each second tobacco extract and the second place of origin corresponding to each second tobacco extract. Based on the training sample data, the random forest classification model is trained to generate the first extract identification model.

[0023] Random forest classification models are parallel decision tree ensemble models based on ensemble learning, consisting of a large number of independent decision trees. Multiple differential decision trees are generated through double random sampling of samples and features, and the outputs of all trees are finally aggregated to obtain the overall prediction result. The random forest classification model uses a voting process among all decision trees, selecting the class with the most votes as the prediction result.

[0024] For constructing the first extract identification model, a random forest classification model can be built as the initial model, and trained using training sample data. The random forest classification model employs a bootstrap aggregation strategy for training, randomly extracting features at each decision tree node split to ensure the independence of each decision tree. During training, hyperparameters such as the number of decision trees, maximum number of splits, and minimum leaf node sample size are dynamically optimized. To address the issue of imbalanced sample sizes, a custom cost matrix is ​​introduced. After the cost matrix is ​​converted into class weights, the training penalty weight for a single fraudulent sample is much higher than that for a normal sample, imposing a high penalty weight on false negative results.

[0025] Optionally, training a random forest classification model based on training sample data to generate a first extract identification model also includes: Regularization constraints are introduced to suppress overfitting in the random forest classification model.

[0026] During model training, overfitting can occur if the model excessively learns from training set noise, outliers, and local details. This means that while the model may achieve extremely high accuracy on training data, its performance drops significantly on test and real-world business data, resulting in poor generalization ability. Overfitting is further exacerbated in scenarios involving imbalanced samples and high-dimensional feature verification. To address this, regularization constraints are introduced during the training of the random forest classification model to suppress overfitting.

[0027] Optionally, regularization constraints can be applied when training the random forest classification model, including: The Bayesian optimization algorithm is used to search for the optimal hyperparameters of the random forest classification model, and regularization constraints are introduced to suppress model overfitting.

[0028] Traditional grid search and random search for traversing hyperparameters are inefficient, and a large number of invalid parameter combinations will repeatedly train the model, resulting in high computational costs. Furthermore, they do not utilize the validation effect of past parameters and cannot actively converge to the optimal parameter region, making it difficult to quickly find the optimal hyperparameter combination. Therefore, when training a random forest classification model, the Bayesian optimization algorithm is used to search for the optimal hyperparameters of the random forest classification model, which shortens the model training time and improves the model training effect.

[0029] Optionally, the process of constructing the first extract identification model includes: Determine the training sample data; the training sample data consists of the second characteristic ion corresponding to each second tobacco extract and the second place of origin corresponding to each second tobacco extract. Based on the training sample data, the radial basis kernel support vector machine model is trained to generate the first extract identification model.

[0030] Radial Basis Kernel Support Vector Machine (RBF-SVM) is a linear classifier. The radial basis kernel (RBF kernel, Gaussian kernel) is the most commonly used non-linear kernel function. The combination of the two results in RBF-SVM, which is used to handle the classification of linearly inseparable samples and the determination of the authenticity of data.

[0031] For the first extract identification model, a radial basis function (RBF) kernel support vector machine (SVM) model can also be selected for training. This can be achieved by training the SVM model using training sample data. Before calculating the RBF distance, the training sample data is centered and standardized. The objective function is iterated 30 times to optimize the penalty coefficient C and the kernel scale γ. After model parameter tuning, the model performance is comprehensively evaluated on a 20% independent test set.

[0032] Optionally, determine the training sample data, including: Identify several second tobacco extracts and the second place of origin for each second tobacco extract; Mass spectrometry analysis was performed on the second tobacco extract to generate mass spectrometry data; Based on a pre-built random forest model, mass spectrometry data are screened to determine several characteristic ions of each second tobacco extract.

[0033] When constructing training sample data, it is necessary to first obtain second tobacco extracts from different origins. If some origins lack second tobacco extracts, tobacco leaves from those origins are collected, and real tobacco extract samples are prepared using solvent extraction. Methanol is used as the solvent, and the tobacco extracts are diluted at a certain ratio and centrifuged to separate the supernatant, which is then used for analysis. All samples are mixed in equal volumes to prepare QC samples. Ultra-high performance liquid chromatography-tandem mass spectrometry (UHPLC-MS / MS) is used to detect all second tobacco extract samples, obtaining mass spectrometry data for different samples. Samples are grouped according to origin, and based on a pre-built random forest model, the mass spectrometry data are screened to determine several characteristic ions for each second tobacco extract.

[0034] S130. Determine the mass spectrometry data of the first tobacco extract, and identify the first characteristic ion in the mass spectrometry data of the first tobacco extract.

[0035] Mass spectrometry analysis was performed on the first tobacco extract to determine its mass spectrometry data. Then, the characteristic ion corresponding to the first place of origin was identified from the mass spectrometry data and used as the first characteristic ion.

[0036] For the determination of characteristic ions, the true molecular characteristics are obtained according to the principle that the signal can be detected in 100% of the samples. Matrix interference is eliminated, and characteristic ions are extracted according to the principle that the ion intensity is higher than 1000 and the difference between the ions in the target origin and non-target origin is higher than 2 times.

[0037] The selection of characteristic ions can be achieved by first identifying the ion types that belong to the characteristic ion type of the origin, and then using the ion type to screen and determine the ion type from the mass spectrometry results.

[0038] S140. Input the first characteristic ion into the pre-trained second extract identification model to determine whether the origin of the first tobacco extract is the first origin.

[0039] The first characteristic ion is input into a pre-trained second extract identification model, which then determines whether the origin of the first tobacco extract is the first origin it claims. Since the soil, climate, precipitation, altitude, soil and water elements, and isotope ratios of tobacco leaves are geographically unique, they will stably change the entire set of chemical components inside the tobacco leaves. After extraction to make an extract, this set of regional characteristics will be completely preserved and cannot be completely replicated by artificial blending or mixing with other raw materials. Therefore, it can be identified by the characteristic ions of the tobacco extract.

[0040] Optionally, if the first tobacco extract does not have a first place of origin, the first characteristic ion of the first tobacco extract is input into each first extract identification model, and the place of origin of the first tobacco extract is determined according to the identification results of each first extract identification model.

[0041] In the absence of a primary origin, the first characteristic ion of the first tobacco extract can be input into each primary extract identification model, and each primary extract identification model can perform identification. If there is a primary extract identification model that identifies the primary origin of the first tobacco extract, then the primary origin of the first tobacco extract can be determined.

[0042] For example, there are two first extract identification models, A and B. First extract identification model A is used to identify tobacco extracts from origin a, and first extract identification model B is used to identify tobacco extracts from origin b. At this time, the first characteristic ion of the first tobacco extract is input into first extract identification model A and first extract identification model B respectively. If the output result of first extract identification model A is "yes" and the output result of first extract identification model B is "no", then the origin of the first tobacco extract can be determined to be origin a.

[0043] The technical solution provided by this invention determines a first tobacco extract and a first place of origin; the first tobacco extract is the tobacco extract for which authenticity verification is required, and the first place of origin is the raw material origin of the first tobacco extract; based on the first place of origin, a second extract identification model is determined among various first extract identification models; the mass spectrometry data of the first tobacco extract is determined, and a first characteristic ion is determined in the mass spectrometry data of the first tobacco extract; the first characteristic ion is input into the pre-trained second extract identification model to determine whether the origin of the first tobacco extract is the first place of origin, which can comprehensively utilize the unique organic molecules in the product to accurately determine the authenticity of the tobacco extract.

[0044] In one embodiment, Figure 2 This is a flowchart of another method for identifying tobacco extracts provided by an embodiment of the present invention. The relationship between this embodiment and the above embodiments is further explained in the process prior to determining the first tobacco extract and the first place of origin. Figure 2 As shown, the method includes: S210. Determine the accuracy of each first extract identification model for the identification results of tobacco extracts from each origin.

[0045] S220. Based on the accuracy of the identification results of tobacco extracts from various origins using each first extract identification model, determine the origin corresponding to the first extract identification model.

[0046] Because several first extract identification models will be trained during the training process, and different first extract identification models may have different accuracy rates for identifying tobacco extracts from different origins, it is necessary to determine a separate first extract identification model for identifying tobacco extracts from different origins.

[0047] To this end, the accuracy of the identification results of each first extract identification model for tobacco extracts from the same origin was determined, and the first extract identification model with the highest accuracy was selected as the second extract identification model for tobacco extracts from that origin.

[0048] S230. Determine the first tobacco extract and the first place of origin; the first tobacco extract is the tobacco extract that needs to be verified for authenticity, and the first place of origin is the place of origin of the raw materials of the first tobacco extract.

[0049] S240. Based on the first place of origin, determine the second extract identification model among the various first extract identification models.

[0050] S250. Determine the mass spectrometry data of the first tobacco extract, and identify the first characteristic ion in the mass spectrometry data of the first tobacco extract.

[0051] S260. Input the first characteristic ion into the pre-trained second extract identification model to determine whether the origin of the first tobacco extract is the first origin.

[0052] By adopting the technical solution of this application, the accuracy of the identification results of each first extract identification model for tobacco extracts from various origins is determined; based on the accuracy of the identification results of each first extract identification model for tobacco extracts from various origins, the origin corresponding to the first extract identification model is determined, and a dedicated second extract identification model is set for tobacco extracts from different origins, thereby further ensuring the accuracy of the identification results.

[0053] In one embodiment, Figure 3 This is a schematic diagram of the structure of a tobacco extract identification device provided in an embodiment of the present invention. Figure 3 As shown, the device includes: an extract acquisition module 310, a model selection module 320, a characteristic ion screening module 330, and an origin verification module 340, wherein: The extract acquisition module 310 is used to determine the first tobacco extract and the first place of origin; the first tobacco extract is the tobacco extract that needs to be verified for authenticity, and the first place of origin is the place of origin of the raw materials from which the first tobacco extract is generated; The model selection module 320 is used to determine the second extract identification model based on the first place of origin among various first extract identification models; The feature ion screening module 330 is used to determine the mass spectrometry data of the first tobacco extract and to identify the first feature ion in the mass spectrometry data of the first tobacco extract. The origin verification module 340 is used to input the first characteristic ion into the pre-trained second extract identification model to determine whether the origin of the first tobacco extract is the first origin.

[0054] In one embodiment, optionally, the process of constructing the first extract identification model includes: Determine the training sample data; the training sample data consists of the second characteristic ion corresponding to each second tobacco extract and the second place of origin corresponding to each second tobacco extract. Based on the training sample data, the random forest classification model is trained to generate the first extract identification model.

[0055] In one embodiment, optionally, the process of constructing the first extract identification model includes: Determine the training sample data; the training sample data consists of the second characteristic ion corresponding to each second tobacco extract and the second place of origin corresponding to each second tobacco extract. Based on the training sample data, the radial basis kernel support vector machine model is trained to generate the first extract identification model.

[0056] In one embodiment, optionally, determining the training sample data includes: Identify several second tobacco extracts and the second place of origin for each second tobacco extract; Mass spectrometry analysis was performed on the second tobacco extract to generate mass spectrometry data; Based on a pre-built random forest model, mass spectrometry data are screened to determine several characteristic ions of each second tobacco extract.

[0057] In one embodiment, optionally, training a random forest classification model based on training sample data to generate a first extract identification model further includes: Regularization constraints are introduced to suppress overfitting in the random forest classification model.

[0058] In one embodiment, optionally, regularization constraints are applied when training the random forest classification model, including: The Bayesian optimization algorithm is used to search for the optimal hyperparameters of the random forest classification model, and regularization constraints are introduced to suppress model overfitting.

[0059] In one embodiment, optionally, before determining the first tobacco extract and the first place of origin, the method further includes: Determine the accuracy of each primary extract identification model for the identification results of tobacco extracts from various origins; Based on the accuracy of each first extract identification model in identifying tobacco extracts from various origins, the origin corresponding to each first extract identification model is determined.

[0060] The tobacco extract identification device provided in this embodiment of the invention can execute the tobacco extract identification method provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the method.

[0061] In one embodiment, Figure 4 This is a structural block diagram of an electronic device for a method of identifying tobacco extracts provided in an embodiment of the present invention, as shown below. Figure 4 The diagram illustrates a schematic representation of an electronic device 10 that can be used to implement embodiments of the present invention. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., 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.

[0062] 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, a random access memory (RAM) 13, etc., which is communicatively connected to the at least one processor 11. The memory stores a computer program that can be executed by the at least one processor 11, and the computer program is executed by the at least one processor 11 to enable the at least one processor 11 to perform the tobacco extract identification method provided by the present invention.

[0063] The processor 11 can perform various appropriate actions and processes based on a computer program stored in the read-only memory (ROM) 12 or a computer program loaded from the storage unit 18 into the random access memory (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.

[0064] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as 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.

[0065] Processor 11 can be various 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, digital signal processors (DSPs), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as the tobacco extract identification method provided by this invention.

[0066] In some embodiments, the methods provided herein 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 mounted 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 methods described above may be performed. Alternatively, in other embodiments, processor 11 may be configured by any other suitable means (e.g., by means of firmware) to perform the tobacco extract identification method.

[0067] 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 parts (ASSPs), systems-on-chip (SoCs), complex 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.

[0068] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may 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 computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0069] In the context of this invention, a computer-readable storage medium stores computer instructions that are used to cause a processor to execute and implement the tobacco extract identification method provided by this invention.

[0070] The present invention also provides a computer program product comprising a computer program that, when executed by a processor, implements the method provided according to embodiments of the present invention. A computer-readable storage medium may 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. The 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, the 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.

[0071] 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).

[0072] 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.

[0073] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through a communication network. 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.

[0074] This invention also provides a computer program product, including a computer program that, when executed by a processor, can implement the methods provided in any embodiment of this application.

[0075] In the implementation of the computer program product, computer program code for performing the operations of this application can be written in one or more programming languages ​​or a combination thereof. Programming languages ​​include object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as C or similar languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0076] 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.

[0077] 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 method for identifying tobacco extracts, characterized in that, include: The first tobacco extract and the first place of origin are determined; the first tobacco extract is the tobacco extract that needs to be verified for authenticity, and the first place of origin is the place of origin of the raw materials from which the first tobacco extract is generated; Based on the first place of origin, determine the second extract identification model among the various first extract identification models; Determine the mass spectrometry data of the first tobacco extract, and identify the first characteristic ion in the mass spectrometry data of the first tobacco extract; The first characteristic ion is input into a pre-trained second extract identification model to determine whether the origin of the first tobacco extract is the first origin.

2. The method according to claim 1, characterized in that, The construction process of the first extract identification model includes: Determine the training sample data; the training sample data consists of the second characteristic ion corresponding to each second tobacco extract and the second place of origin corresponding to each second tobacco extract. Based on the training sample data, the random forest classification model is trained to generate the first extract identification model.

3. The method according to claim 1, characterized in that, The construction process of the first extract identification model includes: Determine the training sample data; the training sample data consists of the second characteristic ion corresponding to each second tobacco extract and the second place of origin corresponding to each second tobacco extract. Based on the training sample data, the radial basis kernel support vector machine model is trained to generate the first extract identification model.

4. The method according to claim 2 or 3, characterized in that, Determine the training sample data, including: Determine a number of second tobacco extracts and the second place of origin for each of the second tobacco extracts; The second tobacco extract was subjected to mass spectrometry analysis to generate mass spectrometry data; Based on a pre-built random forest model, mass spectrometry data are screened to determine several characteristic ions of each second tobacco extract.

5. The method according to claim 2, characterized in that, Based on the training sample data, the random forest classification model is trained to generate the first extract identification model, which also includes: Regularization constraints are introduced to suppress overfitting in the random forest classification model.

6. The method according to claim 5, characterized in that, When training the random forest classification model, regularization constraints are applied, including: The Bayesian optimization algorithm is used to search for the optimal hyperparameters of the model, and regularization constraints are introduced to suppress model overfitting.

7. The method according to claim 1, characterized in that, Before determining the first tobacco extract and the first place of origin, the following is also included: Determine the accuracy of each primary extract identification model for the identification results of tobacco extracts from various origins; Based on the accuracy of the identification results of tobacco extracts from various origins using each first extract identification model, the origin corresponding to the first extract identification model is determined.

8. A device for identifying tobacco extracts, characterized in that, include: The extract acquisition module is used to determine the first tobacco extract and the first place of origin; the first tobacco extract is the tobacco extract that needs to be verified for authenticity, and the first place of origin is the place of origin of the raw materials of the first tobacco extract; The model selection module is used to determine the second extract identification model based on the first place of origin among various first extract identification models; The feature ion screening module is used to determine the mass spectrometry data of the first tobacco extract and to identify the first feature ion in the mass spectrometry data of the first tobacco extract. The origin verification module is used to input the first characteristic ion into a pre-trained second extract identification model to determine whether the raw material origin of the first tobacco extract is the first origin.

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 that can be executed by the at least one processor to enable the at least one processor to perform the tobacco extract identification method according to 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 method for determining the authenticity of tobacco extracts according to any one of claims 1-7.

Images