Wine quality evaluation method and device based on pigeon flock optimization

Abstract

The embodiment of the invention provides a wine quality evaluation method and device based on pigeon flock optimization, and the wine quality evaluation method based on pigeon flock optimization comprises the steps: obtaining a wine sample, and collecting the near infrared spectrum of the wine sample; determining a target feature based on the near infrared spectrum; determining a target model through a pigeon flock optimization algorithm based on the target features; and evaluating the wine quality based on the target model to determine an evaluation result. The method comprises the following steps: acquiring a wine sample, and collecting a near infrared spectrum of the wine sample; determining a target feature based on the near infrared spectrum; determining a target model through a pigeon flock optimization algorithm based on the target features; and evaluating the wine quality based on the target model to determine an evaluation result, so that a prediction model can be established, and rapid and accurate evaluation of the wine quality is realized.

Description

Technical Field

[0001] The embodiments of this specification relate to the technical field of wine evaluation, and in particular to a wine quality evaluation method based on pigeon flock optimization. Background Art

[0002] Wine quality can be assessed based on several factors, including acidity, tannins, alcohol content, citric acid, residual sugar, chlorides, free sulfur dioxide, purity, fullness, and free sulfur dioxide. A high-quality wine should be clear and transparent, free of impurities and suspended matter. Turbidity or precipitation may indicate a quality issue. The chemical composition of wine is crucial for identifying its variety, but conventional testing methods are complex, tedious, and inaccurate. In the era of big data, a variety of methods are being applied to wine quality evaluation. Currently, these methods primarily include support vector machines, passive observers, parameter sensitivity analysis, and system cluster analysis.

[0003] Traditional wine quality evaluation methods rely primarily on sensory evaluation and chemical analysis, but these methods are subject to significant limitations, such as high subjectivity, cumbersome procedures, and time-consuming processes. Therefore, a better approach is urgently needed. Summary of the Invention

[0004] In light of this, embodiments of this specification provide a wine quality evaluation method based on pigeon flock optimization. One or more embodiments of this specification also include a wine quality evaluation device based on pigeon flock optimization, a computing device, a computer-readable storage medium, and a computer program to address technical deficiencies in the prior art.

[0005] According to a first aspect of the embodiments of this specification, a method for evaluating wine quality based on pigeon flock optimization is provided, comprising: obtaining a wine sample and collecting a near infrared spectrum of the wine sample; Determine target characteristics based on near-infrared spectroscopy; Determine the target model through the pigeon flock optimization algorithm based on the target features; The wine quality is evaluated based on the target model to determine the evaluation results.

[0006] In one possible implementation, determining target characteristics based on near-infrared spectroscopy includes: Performing preprocessing based on the near-infrared spectrum to determine a preprocessing spectrum; The characteristic wavelengths of the preprocessed spectrum are extracted to determine the target features.

[0007] In one possible implementation, the target model is determined based on the target features by using a pigeon flock optimization algorithm, including: Perform wavelet packet decomposition based on target features and determine the decomposition results; Reconstruct based on target features and determine the reconstruction result; Based on the decomposition results and reconstruction results, wavelet packet translation is performed to determine the evaluation index; The target model is determined based on evaluation indicators and pigeon flock optimization algorithm.

[0008] In one possible implementation, the target model is determined based on the evaluation index and the pigeon flock optimization algorithm, including: Search based on the evaluation index and pigeon flock optimization algorithm, update the speed parameters and position parameters, and determine the target speed parameters and target position parameters; determining a root mean square error based on the target velocity parameter; determining a dispersion coefficient based on a target position parameter and a target speed parameter; The target model is determined based on the root mean square error and the coefficient of dispersion.

[0009] In one possible implementation, wavelet packet decomposition is performed based on target features, and a decomposition result is determined, including:

[0010] in, is the convolution operator, represents the wavelet packet decomposition coefficient of layer i at node p, represents the conjugate mirror filter, It is the expected evaluation index of wine quality. It is an indicator for evaluating wine quality.

[0011] In one possible implementation, performing reconstruction based on target features and determining a reconstruction result includes:

[0012] in, is the convolution operator, represents the wavelet packet reconstruction coefficient of the p node i+1 layer, represents a conjugate mirror filter, and q represents a random coefficient.

[0013] In one possible implementation, evaluating wine quality based on the target model to determine an evaluation result includes: Determine the weights and primary and secondary relationships of the parameters in the target model through the entropy weight method; The evaluation results are determined based on parameters, weights and primary and secondary relationships.

[0014] According to a second aspect of the embodiments of this specification, a wine quality evaluation device based on pigeon flock optimization is provided, comprising: a spectrum acquisition module, configured to acquire a wine sample and collect a near-infrared spectrum of the wine sample; a feature determination module, configured to determine a target feature based on the near infrared spectrum; A model determination module is configured to determine a target model based on the target features by using a pigeon flock optimization algorithm; The evaluation and determination module is configured to evaluate the quality of the wine based on the target model and determine an evaluation result.

[0015] According to a third aspect of an embodiment of this specification, a computing device is provided, including: memory and processor; The memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions. When the computer-executable instructions are executed by the processor, the steps of the above-mentioned wine quality evaluation method based on pigeon flock optimization are implemented.

[0016] According to a fourth aspect of the embodiments of this specification, a computer-readable storage medium is provided, which stores computer-executable instructions, which, when executed by a processor, implement the steps of the above-mentioned wine quality evaluation method based on pigeon flock optimization.

[0017] According to a fifth aspect of the embodiments of this specification, a computer program is provided, wherein when the computer program is executed in a computer, the computer is caused to execute the steps of the above-mentioned wine quality evaluation method based on pigeon flock optimization.

[0018] The embodiments of this specification provide a wine quality evaluation method and device based on pigeon flock optimization, wherein the wine quality evaluation method based on pigeon flock optimization includes: obtaining a wine sample and collecting a near-infrared spectrum of the wine sample; determining a target feature based on the near-infrared spectrum; determining a target model based on the target feature using a pigeon flock optimization algorithm; and evaluating the wine quality based on the target model to determine an evaluation result. By obtaining a wine sample and collecting a near-infrared spectrum of the wine sample; determining a target feature based on the near-infrared spectrum; determining a target model based on the target feature using a pigeon flock optimization algorithm; and evaluating the wine quality based on the target model to determine an evaluation result, a prediction model can be established to achieve rapid and accurate evaluation of wine quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 This is a flow chart of a wine quality evaluation method based on pigeon flock optimization provided in one embodiment of this specification; Figure 2 This is a schematic diagram of an infrared spectrum of a wine quality evaluation method based on pigeon flock optimization provided in one embodiment of this specification; Figure 3 This is a schematic diagram of the discrete coefficient of a wine quality evaluation method based on pigeon flock optimization provided in one embodiment of this specification; Figure 4 This is a schematic structural diagram of a wine quality evaluation device based on pigeon flock optimization provided in one embodiment of this specification; Figure 5 This is a structural block diagram of a computing device provided by one embodiment of this specification. DETAILED DESCRIPTION

[0020] The following description sets forth many specific details to facilitate a thorough understanding of this specification. However, this specification can be implemented in many other ways than those described herein, and those skilled in the art can make similar generalizations without violating the scope of this specification. Therefore, this specification is not limited to the specific implementations disclosed below.

[0021] The terms used in one or more embodiments of this specification are for the purpose of describing specific embodiments only and are not intended to limit one or more embodiments of this specification. The singular forms "a," "an," and "the" used in one or more embodiments of this specification and the appended claims are also intended to include plural forms unless the context clearly indicates otherwise. It should also be understood that the term "and / or" used in one or more embodiments of this specification refers to and includes any or all possible combinations of one or more associated listed items.

[0022] It should be understood that although the terms first, second, etc. may be used to describe various information in one or more embodiments of this specification, such information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other. For example, without departing from the scope of one or more embodiments of this specification, the first may also be referred to as the second, and similarly, the second may also be referred to as the first. Depending on the context, the word "if" as used herein may be interpreted as "at the time of" or "when" or "in response to determining".

[0023] In this specification, a wine quality evaluation method based on pigeon flock optimization is provided. This specification also relates to a wine quality evaluation device based on pigeon flock optimization, a computing device, and a computer-readable storage medium, which are described in detail one by one in the following embodiments.

[0024] See also Figure 1 , Figure 1 A flowchart of a wine quality evaluation method based on pigeon flock optimization according to an embodiment of this specification is shown, which specifically includes the following steps.

[0025] Step 101: Obtain a wine sample and collect a near-infrared spectrum of the wine sample.

[0026] In practical applications, the instrument for acquisition must be prepared first, ensuring the infrared spectrometer is in normal working order. Preheating and calibration procedures are performed to ensure instrument stability and accuracy. Different types of infrared spectrometers may have different warm-up times and calibration procedures. For example, a Fourier transform infrared spectrometer (FTIR) typically requires a warm-up period ranging from 30 minutes to several hours.

[0027] Then, prepare the sample by dropping the liquid sample between two infrared transparent windows (such as NaCl, KBr, etc.) to form a uniform liquid film without generating bubbles.

[0028] Finally, place the prepared sample in the infrared spectrometer's sample cell or on the sample stage, ensuring it's positioned accurately and securely, and then start the spectrum acquisition process. During the measurement process, maintain a stable instrument environment to avoid factors such as vibration, temperature fluctuations, and electromagnetic interference that may affect the measurement results.

[0029] After acquisition, the infrared spectral data is processed, such as baseline correction, smoothing, and normalization, to improve spectral quality and comparability. The sample's composition and structure are then analyzed and identified by comparing it with a known standard spectral library or applying spectral analysis methods.

[0030] Step 102: Determine target characteristics based on the near-infrared spectrum.

[0031] In a possible implementation, determining the target feature based on the near-infrared spectrum includes: performing preprocessing based on the near-infrared spectrum to determine a preprocessed spectrum; and extracting characteristic wavelengths from the preprocessed spectrum to determine the target feature.

[0032] In practical applications, the above preprocessing methods include standard normal transformation preprocessing and multivariate scatter correction preprocessing.

[0033] Multiplicative Scatter Correction (MSC) is used in this scheme to correct spectral scattering problems caused by factors such as sample particle size and surface scattering, thereby improving the accuracy and reliability of spectral analysis.

[0034] Furthermore, specific wavelength information related to target substances or characteristics can be accurately identified and extracted from complex spectral data. These wavelengths typically correspond to characteristic absorption, emission, or scattering peaks of the substance. By analyzing them, we can understand the composition, structure, and properties of the substance. For example, when analyzing the quality of wine, we may focus on spectral characteristics at certain specific wavelengths to determine its maturity, sugar content, etc.

[0035] Among them, the extraction methods include the following, which are described in detail below.

[0036] Derivative spectroscopy: By calculating the first or second derivative of a spectrum, subtle characteristic changes in the spectrum can be enhanced, making previously subtle peaks and valleys more distinct, making it easier to determine the location of characteristic wavelengths. For example, in near-infrared spectroscopy, for some overlapping absorption peaks, derivative spectroscopy can effectively separate the locations of the individual peaks and extract accurate wavelength information.

[0037] Correlation Coefficient Method: The spectrum of an unknown sample is correlated with the spectrum of a known standard substance to calculate the correlation coefficient. The wavelength at which the correlation coefficient reaches a maximum or minimum is typically the characteristic wavelength associated with the target substance. For example, in pharmaceutical component analysis, the spectrum of the drug to be tested is correlated with the spectrum of a pure drug standard. The wavelength with the highest correlation is extracted and used to determine the drug's purity and composition.

[0038] Principal Component Analysis (PCA): This method reduces the dimensionality of multi-wavelength spectral data and converts it into a small number of principal components, which are linear combinations of the original spectral wavelengths. By analyzing the scores and loadings of the principal components, it is possible to identify wavelength combinations that are critical for sample classification or property determination. For example, in environmental monitoring, PCA analysis of spectra of water samples with varying degrees of contamination can extract characteristic wavelengths that can distinguish the type of contamination.

[0039] Successive Projection Algorithm (SPA): This algorithm progressively selects wavelengths to optimize the combination that provides the best prediction for a sample, while minimizing redundant information between wavelengths. In agricultural product quality testing, such as internal fruit quality testing, SPA can select the most representative wavelengths from a large spectral range to create a simple and effective prediction model.

[0040] Step 103: Determine the target model based on the target features through the pigeon flock optimization algorithm.

[0041] In one possible implementation, a target model is determined based on target features through a pigeon flock optimization algorithm, including: performing wavelet packet decomposition based on target features to determine decomposition results; performing reconstruction based on target features to determine reconstruction results; performing wavelet packet translation based on the decomposition results and reconstruction results to determine evaluation indicators; and determining the target model based on the evaluation indicators and the pigeon flock optimization algorithm.

[0042] In practical applications, in order to achieve accurate evaluation of wine quality, the improved pigeon flock optimization algorithm based on infrared spectroscopy analysis technology is used to evaluate wine quality. First, the test data obtained by wine quality is decomposed and reconstructed by multi-layer wavelet packets. (1) (2) Where, is the convolution operator, represents the wavelet packet decomposition coefficient of layer i at node p, represents the wavelet packet reconstruction coefficient of the p node i+1 layer, and represents the conjugate mirror filter, It is the expected evaluation index of wine quality. is the wine quality evaluation index, and q represents the random coefficient.

[0043] In order to ensure the integrity and validity of the wine quality data to be tested, the data to be tested is shifted by wavelet packets at the i-th and i+1-th layers at the p node. The wine quality evaluation index F must meet the frequency covered by the wavelet packet coefficients. (3) In one possible implementation, the target model is determined based on the evaluation index and the pigeon flock optimization algorithm, including: searching based on the evaluation index and the pigeon flock optimization algorithm, and updating the speed parameters and position parameters to determine the target speed parameters and target position parameters; determining the root mean square error based on the target speed parameters; determining the dispersion coefficient based on the target position parameters and the target speed parameters; and determining the target model based on the root mean square error and the dispersion coefficient.

[0044] In actual applications, when pigeons are searching for targets, they need to continuously iterate the data to be tested to meet the evaluation indicators. During the iteration process, the position and speed of each pigeon need to be initialized and updated. and location The update algorithm is expressed as, (4) (5) Where, represents a random function, represents the exponential function, represents the iterative gain, and Both are compensation controls adopted iteratively. represents the scale parameter of pigeon flight distribution, represents local parameters, Represents a sample of pigeon flocks.

[0045] After updating the position and speed of each pigeon, the root mean square error is used The data of wine quality prediction model was processed by using the dispersion coefficient R. (6) (7) Where k is a constant and n represents the total number of samples. The performance of wine quality prediction models is comprehensively evaluated by considering both the root mean square error (RMS) and the coefficient of variation (R), thereby selecting the optimal model for practical application. The closer the R coefficient of variation (R) is to 1, the more accurate the prediction.

[0046] Step 104: Evaluate the wine quality based on the target model to determine an evaluation result.

[0047] In one possible implementation, wine quality is evaluated based on a target model to determine an evaluation result, including: determining weights and primary and secondary relationships of parameters in the target model through an entropy weight method; and determining an evaluation result based on the parameters, weights, and primary and secondary relationships.

[0048] The parameters in the target model may be the root mean square error and the coefficient of dispersion.

[0049] In practical applications, the entropy weight method is used to evaluate the weights of different indicators in the wine quality prediction model system, confirm the primary and secondary relationships between indicators, and calculate the comprehensive score, providing a comprehensive reference for the evaluation of the multi-indicator system. The specific entropy weight method calculation formula is as follows: (8) Where, is the proportion of the jth indicator in the ith number of samples to be tested, i is the number of samples to be tested, j is the number of indicators, This is the fitness of each pigeon after standardization using the entropy weight method. This fitness corresponds to the optimal parameters of the prediction model, thereby completing the wine quality evaluation.

[0050] Further, Figure 2 The support vector machine method is used to obtain near-infrared spectral images and the improved pigeon flock algorithm preprocessed near-infrared spectrum of wine is shown. Figure 2 After the improved pigeon group optimization screening of the near-infrared spectrum characteristic wavelength, the dispersion coefficient was as high as 0.9876. Figure 3 shown.

[0051] In summary, the prediction model established by this method has significant advantages in parameter optimization. It can effectively improve the model's prediction accuracy and promptly respond to changes caused by time-varying parameters and load variability. This solves the problem of difficulty in establishing a prediction model for wine quality, optimizes the solution, and accurately obtains the global optimal solution for practical applications. The ability to achieve early prediction avoids the problem of falling into local optimality during cluster analysis optimization, speeds up the algorithm's convergence, and improves prediction accuracy. The optimized extraction process is stable, reliable, and reproducible, laying a foundation for wine quality control and industrial production.

[0052] The embodiments of this specification provide a wine quality evaluation method and device based on pigeon flock optimization, wherein the wine quality evaluation method based on pigeon flock optimization includes: obtaining a wine sample and collecting a near-infrared spectrum of the wine sample; determining a target feature based on the near-infrared spectrum; determining a target model based on the target feature using a pigeon flock optimization algorithm; and evaluating the wine quality based on the target model to determine an evaluation result. By obtaining a wine sample and collecting a near-infrared spectrum of the wine sample; determining a target feature based on the near-infrared spectrum; determining a target model based on the target feature using a pigeon flock optimization algorithm; and evaluating the wine quality based on the target model to determine an evaluation result, a prediction model can be established to achieve rapid and accurate evaluation of wine quality.

[0053] Corresponding to the above method embodiment, this specification also provides an embodiment of a wine quality evaluation device based on pigeon flock optimization. Figure 4 FIG1 shows a schematic diagram of a wine quality evaluation device based on pigeon flock optimization provided by an embodiment of this specification. Figure 4 As shown, the device includes: The spectrum acquisition module 401 is configured to obtain a wine sample and collect a near-infrared spectrum of the wine sample; a feature determination module 402 configured to determine target features based on the near infrared spectrum; A model determination module 403 is configured to determine a target model based on the target features by using a pigeon flock optimization algorithm; The evaluation and determination module 404 is configured to evaluate the wine quality based on the target model and determine an evaluation result.

[0054] In one possible implementation, determining target characteristics based on near-infrared spectroscopy includes: Performing preprocessing based on the near-infrared spectrum to determine a preprocessing spectrum; The characteristic wavelengths of the preprocessed spectrum are extracted to determine the target features.

[0055] In one possible implementation, the target model is determined based on the target features by using a pigeon flock optimization algorithm, including: Perform wavelet packet decomposition based on target features and determine the decomposition results; Reconstruct based on target features and determine the reconstruction result; Based on the decomposition results and reconstruction results, wavelet packet translation is performed to determine the evaluation index; The target model is determined based on evaluation indicators and pigeon flock optimization algorithm.

[0056] In one possible implementation, the target model is determined based on the evaluation index and the pigeon flock optimization algorithm, including: Search based on the evaluation index and pigeon flock optimization algorithm, update the speed parameters and position parameters, and determine the target speed parameters and target position parameters; determining a root mean square error based on the target velocity parameter; determining a dispersion coefficient based on a target position parameter and a target speed parameter; The target model is determined based on the root mean square error and the coefficient of dispersion.

[0057] In one possible implementation, wavelet packet decomposition is performed based on target features, and a decomposition result is determined, including:

[0058] in, is the convolution operator, represents the wavelet packet decomposition coefficient of layer i at node p, represents the conjugate mirror filter, It is the expected evaluation index of wine quality. It is an indicator for evaluating wine quality.

[0059] In one possible implementation, performing reconstruction based on target features and determining a reconstruction result includes:

[0060] in, is the convolution operator, represents the wavelet packet reconstruction coefficient of the p node i+1 layer, represents a conjugate mirror filter, and q represents a random coefficient.

[0061] In one possible implementation, evaluating wine quality based on the target model to determine an evaluation result includes: Determine the weights and primary and secondary relationships of the parameters in the target model through the entropy weight method; The evaluation results are determined based on parameters, weights and primary and secondary relationships.

[0062] The embodiments of this specification provide a wine quality evaluation method and device based on pigeon flock optimization, wherein the wine quality evaluation device based on pigeon flock optimization comprises: obtaining a wine sample and collecting a near-infrared spectrum of the wine sample; determining a target feature based on the near-infrared spectrum; determining a target model based on the target feature using a pigeon flock optimization algorithm; and evaluating the wine quality based on the target model to determine an evaluation result. By obtaining a wine sample and collecting a near-infrared spectrum of the wine sample; determining a target feature based on the near-infrared spectrum; determining a target model based on the target feature using a pigeon flock optimization algorithm; and evaluating the wine quality based on the target model to determine an evaluation result, a prediction model can be established to achieve rapid and accurate evaluation of wine quality.

[0063] The above is a schematic diagram of a wine quality evaluation device based on pigeon flock optimization according to this embodiment. It should be noted that the technical solution of this wine quality evaluation device based on pigeon flock optimization and the technical solution of the wine quality evaluation method based on pigeon flock optimization share the same concept. For details not described in detail in the technical solution of the wine quality evaluation device based on pigeon flock optimization, please refer to the description of the technical solution of the wine quality evaluation method based on pigeon flock optimization.

[0064] Figure 5 The block diagram of a computing device 500 according to one embodiment of the present disclosure is shown. Components of the computing device 500 include, but are not limited to, a memory 510 and a processor 520. The processor 520 is connected to the memory 510 via a bus 530, and a database 550 is used to store data.

[0065] The computing device 500 also includes an access device 540 that enables the computing device 500 to communicate via one or more networks 560. Examples of such networks include a public switched telephone network (PSTN), a local area network (LAN), a wide area network (WAN), a personal area network (PAN), or a combination of communication networks such as the Internet. The access device 540 may include one or more of any type of network interface (e.g., a network interface card (NIC)) whether wired or wireless, such as an IEEE 802.11 wireless local area network (WLAN) wireless interface, a Worldwide Interoperability for Microwave Access (Wi-MAX) interface, an Ethernet interface, a universal serial bus (USB) interface, a cellular network interface, a Bluetooth interface, or a near field communication (NFC) interface.

[0066] In one embodiment of the present specification, the above components of the computing device 500 and Figure 5 Other components not shown in the figure may also be connected to each other, for example, via a bus. Figure 5 The computing device structure block diagram shown is for illustrative purposes only and is not intended to limit the scope of this specification. Those skilled in the art may add or replace other components as needed.

[0067] Computing device 500 can be any type of stationary or mobile computing device, including a mobile computer or mobile computing device (e.g., a tablet computer, personal digital assistant, laptop computer, notebook computer, netbook computer, etc.), a mobile phone (e.g., a smartphone), a wearable computing device (e.g., a smartwatch, smart glasses, etc.), or other types of mobile devices, or a stationary computing device such as a desktop computer or personal computer (PC). Computing device 500 can also be a mobile or stationary server.

[0068] The processor 520 is configured to execute the following computer-executable instructions, which, when executed by the processor, implement the steps of the aforementioned method for evaluating wine quality based on pigeon flock optimization. The above is a schematic diagram of a computing device according to this embodiment. It should be noted that the technical solution of this computing device and the technical solution of the aforementioned method for evaluating wine quality based on pigeon flock optimization are based on the same concept. For details not described in detail in the technical solution of the computing device, please refer to the description of the technical solution of the aforementioned method for evaluating wine quality based on pigeon flock optimization.

[0069] An embodiment of the present specification further provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the steps of the above-mentioned wine quality evaluation method based on pigeon flock optimization.

[0070] The above is a schematic diagram of a computer-readable storage medium according to this embodiment. It should be noted that the technical solution of this storage medium is based on the same concept as the technical solution of the aforementioned method for evaluating wine quality based on pigeon flock optimization. For details not described in detail in the technical solution of the storage medium, please refer to the description of the technical solution of the aforementioned method for evaluating wine quality based on pigeon flock optimization.

[0071] An embodiment of the present specification further provides a computer program, wherein when the computer program is executed in a computer, the computer is caused to execute the steps of the above-mentioned wine quality evaluation method based on pigeon flock optimization.

[0072] The above is a schematic diagram of a computer program according to this embodiment. It should be noted that the technical solution of this computer program is based on the same concept as the technical solution of the aforementioned method for evaluating wine quality based on pigeon flock optimization. For details not described in detail in the technical solution of the computer program, please refer to the description of the technical solution of the aforementioned method for evaluating wine quality based on pigeon flock optimization.

[0073] The foregoing description of this specification describes specific embodiments. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims can be performed in an order different from that described in the embodiments and still achieve the desired results. Furthermore, the processes depicted in the accompanying drawings do not necessarily require the specific order shown or the sequential order to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0074] The computer instructions include computer program code, which may be in source code form, object code form, executable file, or some intermediate form. The computer-readable medium may include any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard drive, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal, and software distribution medium. It should be noted that the content of the computer-readable medium may be appropriately increased or decreased based on the requirements of legislation and patent practice within a jurisdiction. For example, in some jurisdictions, based on legislation and patent practice, computer-readable media does not include electric carrier signals and telecommunication signals.

[0075] It should be noted that for the aforementioned method embodiments, for the sake of simplicity of description, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the embodiments of this specification are not limited by the order of the actions described, because according to the embodiments of this specification, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in this specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the embodiments of this specification.

[0076] In the above embodiments, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0077] The preferred embodiments disclosed above are intended only to help illustrate this specification. The optional embodiments do not exhaustively describe all details, nor do they limit the invention to the specific embodiments described. Obviously, many modifications and variations can be made based on the content of the embodiments of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the embodiments of this specification, so that those skilled in the art can better understand and utilize this specification. This specification is limited only by the claims and their full scope and equivalents.

Claims

1. A wine quality evaluation method based on pigeon flock optimization, characterized in that: include: obtaining a wine sample, and collecting a near infrared spectrum of the wine sample; determining target characteristics based on the near infrared spectrum; Determine the target model through a pigeon flock optimization algorithm based on the target features; Evaluate the quality of the wine based on the target model and determine the evaluation result; Determining the target model by using a pigeon flock optimization algorithm based on the target feature includes: Perform wavelet packet decomposition based on the target features and determine a decomposition result; Reconstructing based on the target features and determining a reconstruction result; Perform wavelet packet translation based on the decomposition result and the reconstruction result to determine an evaluation index; The target model is determined based on the evaluation index and the pigeon flock optimization algorithm.

2. The method according to claim 1, characterized in that Determining target features based on the near infrared spectrum includes: Performing preprocessing based on the near infrared spectrum to determine a preprocessing spectrum; Characteristic wavelengths are extracted from the preprocessed spectrum to determine target features.

3. The method according to claim 1, characterized in that The determining of the target model based on the evaluation index and the pigeon flock optimization algorithm comprises: Searching based on the evaluation index and the pigeon flock optimization algorithm, and updating the speed parameter and the position parameter, and determining the target speed parameter and the target position parameter; determining a root mean square error based on the target speed parameter; determining a dispersion coefficient based on the target position parameter and the target speed parameter; A target model is determined based on the root mean square error and the coefficient of dispersion.

4. The method according to claim 1, characterized in that: Performing wavelet packet decomposition based on the target feature and determining a decomposition result includes: in, is the convolution operator, represents the i-layer wavelet packet decomposition coefficient at node p, represents the conjugate image filter, It is the expected evaluation index of wine quality. It is an indicator for evaluating wine quality.

5. The method according to claim 1, characterized in that The reconstructing based on the target feature and determining the reconstruction result includes: in, is the convolution operator, represents the reconstruction coefficient of the wavelet packet at the p node i+1 layer, represents a conjugate mirror filter, and q represents a random coefficient.

6. The method according to claim 1, characterized in that Evaluating the wine quality based on the target model and determining the evaluation result includes: Determine the weights and primary and secondary relationships of the parameters in the target model by using an entropy weight method; An evaluation result is determined based on the parameters, the weights, and the primary and secondary relationships.

7. A wine quality evaluation device based on pigeon flock optimization, used to implement the steps of the wine quality evaluation method based on pigeon flock optimization according to any one of claims 1 to 6, characterized in that: include: A spectrum acquisition module is configured to acquire a wine sample and collect a near infrared spectrum of the wine sample; a feature determination module, configured to determine a target feature based on the near infrared spectrum; A model determination module is configured to determine a target model through a pigeon flock optimization algorithm based on the target features; The evaluation and determination module is configured to evaluate the wine quality based on the target model to determine an evaluation result.

8. A computing device, characterized in that include: Memory and processor; The memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions. When the computer-executable instructions are executed by the processor, the steps of the wine quality evaluation method based on pigeon flock optimization as described in any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the steps of the wine quality evaluation method based on pigeon flock optimization as described in any one of claims 1 to 6.

Images