Black garlic quality evaluation method, system and equipment based on machine learning and medium
Through the black garlic quality evaluation method based on machine learning, sensory and biochemical indicators are used for pre-processing and scoring, the problems of low efficiency and high subjectivity of traditional manual assessment are solved, and the automation and accuracy of black garlic quality evaluation are achieved.
Patent Information
- Application Number
- CN202510312540.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-03-17
- Publication Date
- 2025-06-13
AI Technical Summary
The traditional black garlic quality assessment method relies on artificial sensory assessment, is susceptible to individual subjective factors, and has low evaluation efficiency, and lacks integrated and automated intelligent scoring methods to achieve comprehensive and accurate black garlic quality assessment.
The black garlic quality evaluation method based on machine learning is adopted. By obtaining the sensory quality indicators and biochemical quality indicators of black garlic, the evaluation data is preprocessed, and inputting it into the trained black garlic quality scoring model, the predicted values of sensory quality scores and biochemical quality scores are output, the comprehensive quality score is finally determined, and the fermentation process conditions are adjusted according to the scores.
The automation, accuracy and efficiency of black garlic quality evaluation have been improved, the subjective impact of manual and the comprehensiveness and accuracy of the evaluation have been improved.
Smart Images
Figure CN120146695A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the technical field of food quality detection and intelligent evaluation, and particularly relates to a method, system, device and medium for evaluating the quality of black garlic based on machine learning. Background Art
[0002] As a fermented food with multiple health care effects, black garlic has gradually received wide attention in the market in recent years. Among them, the quality of black garlic directly affects its market competitiveness. The traditional method for evaluating the quality of black garlic relies on manual sensory evaluation, which is easily affected by personal subjective factors and has low evaluation efficiency.
[0003] Although existing methods for evaluating the quality of black garlic can detect indicators such as the color, smell, taste and antioxidant capacity of black garlic, most methods still rely on manual detection or traditional image processing and physical and chemical analysis, lacking an integrated and automated intelligent scoring method to achieve a comprehensive and accurate evaluation of the quality of black garlic.
[0004] Therefore, developing a method for evaluating the quality of black garlic based on machine learning to achieve automatic, efficient and accurate quality evaluation has become an urgent technical problem to be solved. Summary of the Invention
[0005] The purpose of this application is to provide a method, system, device and medium for evaluating the quality of black garlic based on machine learning, which improves the accuracy and efficiency of black garlic quality evaluation.
[0006] To achieve the above purpose, this application provides the following solutions:
[0007] In the first aspect, this application provides a method for evaluating the quality of black garlic based on machine learning. The method for evaluating the quality of black garlic based on machine learning includes:
[0008] Under the current fermentation process conditions, obtain the sensory quality indicators and biochemical quality indicators of black garlic, and use the sensory quality indicators and biochemical quality indicators of black garlic as the data to be evaluated; the fermentation process conditions include: fermentation temperature, fermentation humidity and fermentation time;
[0009] Preprocess the data to be evaluated to obtain the preprocessed data to be evaluated;
[0010] Input the preprocessed data to be evaluated into the black garlic quality scoring model, and output the predicted value of the sensory quality score and the predicted value of the biochemical quality score of black garlic; the black garlic quality scoring model is obtained by training a machine learning model;
[0011] Based on the predicted value of the sensory quality score and the predicted value of the biochemical quality score of black garlic, determine the comprehensive quality score of black garlic;
[0012] Adjust the current fermentation process conditions based on the comprehensive quality score of black garlic.
[0013] Optionally, the sensory quality indicators include: color, odor, taste, and texture, and the biochemical quality indicators include: total phenol content, antioxidant capacity, and amino acid content.
[0014] Optionally, preprocess the data to be evaluated to obtain the preprocessed data to be evaluated, specifically including:
[0015] Standardize the data to be evaluated to obtain the standardized data to be evaluated;
[0016] Normalize the standardized data to be evaluated to obtain the preprocessed data to be evaluated.
[0017] Optionally, the training process of the black garlic quality scoring model specifically includes:
[0018] Obtain a training set; the training set includes: the sensory quality indicators, biochemical quality indicators, actual values of sensory quality scores, and actual values of biochemical quality scores of multiple sample black garlics;
[0019] Construct a machine learning model;
[0020] Use the training set to train the machine learning model to obtain the black garlic quality scoring model.
[0021] Optionally, using the training set to train the machine learning model to obtain the black garlic quality scoring model specifically includes:
[0022] Preprocess the sensory quality indicators and biochemical quality indicators of each sample black garlic to obtain the preprocessed sensory quality indicators and preprocessed biochemical quality indicators of each sample black garlic;
[0023] Use the preprocessed sensory quality indicators and preprocessed biochemical quality indicators of each sample black garlic as inputs, and the actual values of the sensory quality scores and actual values of the biochemical quality scores of the corresponding sample black garlics as outputs to train the machine learning model to obtain the black garlic quality scoring model.
[0024] Optionally, the machine learning model is a random forest model, a support vector machine model, or a neural network model.
[0025] Optionally, determine the comprehensive quality score of black garlic based on the predicted values of the sensory quality score and the predicted value of the biochemical quality score of black garlic, specifically including:
[0026] Perform weighted summation on the predicted value of the sensory quality score and the predicted value of the biochemical quality score of black garlic to obtain the comprehensive quality score of black garlic.
[0027] In a second aspect, the present application provides a black garlic quality evaluation system based on machine learning. The black garlic quality evaluation system based on machine learning is used to implement the black garlic quality evaluation method based on machine learning. The black garlic quality evaluation system based on machine learning includes:
[0028] A data acquisition unit, configured to acquire the sensory quality index and biochemical quality index of black garlic under the current fermentation process conditions, and use the sensory quality index and biochemical quality index of black garlic as data to be evaluated; the fermentation process conditions include: fermentation temperature, fermentation humidity, and fermentation time;
[0029] A preprocessing unit, configured to preprocess the data to be evaluated to obtain the preprocessed data to be evaluated;
[0030] A prediction unit, configured to input the preprocessed data to be evaluated into the black garlic quality scoring model, and output the predicted value of the sensory quality score and the predicted value of the biochemical quality score of black garlic; the black garlic quality scoring model is obtained by training a machine learning model;
[0031] A scoring determination unit, configured to determine the comprehensive quality score of black garlic based on the predicted value of the sensory quality score and the predicted value of the biochemical quality score of black garlic;
[0032] An adjustment unit, configured to adjust the current fermentation process conditions based on the comprehensive quality score of black garlic.
[0033] In a third aspect, the present application provides a computer device, including: a memory, a processor, and a computer program stored on the memory and executable on the processor. The processor executes the computer program to implement the black garlic quality evaluation method based on machine learning described in any one of the above.
[0034] In a fourth aspect, the present application provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, it implements the black garlic quality evaluation method based on machine learning described in any one of the above.
[0035] According to the specific embodiments provided by the present application, the present application has the following technical effects:
[0036] The present application discloses a method, system, device and medium for evaluating the quality of black garlic based on machine learning. First, under the current fermentation process conditions, the sensory quality index and biochemical quality index of black garlic are obtained, and the sensory quality index and biochemical quality index of black garlic are used as the data to be evaluated. Secondly, the data to be evaluated is preprocessed. Furthermore, the preprocessed data to be evaluated is input into the black garlic quality scoring model to output the predicted value of the sensory quality score and the predicted value of the biochemical quality score of black garlic. Then, based on the predicted value of the sensory quality score and the predicted value of the biochemical quality score of black garlic, the comprehensive quality score of black garlic is determined. Finally, based on the comprehensive quality score of black garlic, the current fermentation process conditions are adjusted. The present application scores the quality of black garlic based on the sensory quality index and biochemical quality index of black garlic combined with a machine learning model, effectively improving the accuracy and efficiency of black garlic quality evaluation. BRIEF DESCRIPTION OF THE DRAWINGS
[0037] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required in the embodiments. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.
[0038] Figure 1 Schematic flowchart of a method for evaluating the quality of black garlic based on machine learning provided by an embodiment of the present application;
[0039] Figure 2 Schematic diagram of the functional modules of a system for evaluating the quality of black garlic based on machine learning provided by an embodiment of the present application;
[0040] Figure 3 Schematic diagram of the structure of a computer device provided by an embodiment of the present application.
[0041] Reference numerals:
[0042] Data acquisition unit - 1, preprocessing unit - 2, prediction unit - 3, scoring determination unit - 4, adjustment unit - 5. DETAILED DESCRIPTION OF THE EMBODIMENTS
[0043] The following will clearly and completely describe the technical solutions in the embodiments of the present application with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some embodiments of the present application, rather than all embodiments. Based on the embodiments of the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present application.
[0044] To make the above objects, features, and advantages of the present application more obvious and understandable, the present application will be further described in detail below with reference to the accompanying drawings and specific embodiments.
[0045] In an exemplary embodiment, as Figure 1 shown, a black garlic quality evaluation method based on machine learning is provided, including the following steps. Among them:
[0046] Step S1, under the current fermentation process conditions, obtain the sensory quality indexes and biochemical quality indexes of black garlic, and use the sensory quality indexes and biochemical quality indexes of black garlic as the data to be evaluated; the fermentation process conditions include: fermentation temperature, fermentation humidity, and fermentation time.
[0047] As an optional implementation manner, in step S1, the sensory quality indexes include: color, odor, taste, and texture, and the biochemical quality indexes include: total phenol content, antioxidant capacity (DPPH free radical scavenging rate), and amino acid content.
[0048] Specifically, samples are selected from different varieties of garlic (such as purple-skinned garlic, white-skinned garlic), subjected to standardized fermentation treatment, and their quality indexes (color, odor, taste, texture, etc.) and biochemical quality indexes (total phenol content, antioxidant capacity, amino acid content) are collected. Among them, the black garlic sensory quality index evaluation form is shown in Table 1.
[0049] Table 1 Black garlic sensory quality index situation table
[0050]
[0051] Step S2, preprocess the data to be evaluated to obtain the preprocessed data to be evaluated.
[0052] As an optional implementation manner, step S2 specifically includes:
[0053] Step S21, standardize the data to be evaluated to obtain the standardized data to be evaluated.
[0054] Step S22, normalize the standardized data to be evaluated to obtain the preprocessed data to be evaluated.
[0055] Specifically, the purpose of preprocessing is to eliminate the dimensional differences between different indexes and ensure the consistency and comparability of the data in the machine learning model. Convert all data into values within the range of [0, 1], remove noise and redundant features.
[0056] Step S3, input the preprocessed data to be evaluated into the black garlic quality scoring model, and output the predicted values of the sensory quality score and the predicted values of the biochemical quality score of black garlic. The black garlic quality scoring model is obtained by training a machine learning model.
[0057] As an alternative implementation, in step S3, the training process of the black garlic quality scoring model specifically includes:
[0058] Step S31, obtain a training set. The training set includes: sensory quality indicators, biochemical quality indicators, actual values of sensory quality scores, and actual values of biochemical quality scores of multiple sample black garlics.
[0059] Step S32, construct a machine learning model.
[0060] Step S33, use the training set to train the machine learning model to obtain a black garlic quality scoring model.
[0061] As an alternative implementation, step S33 specifically includes:
[0062] Step S331, preprocess the sensory quality indicators and biochemical quality indicators of each sample black garlic to obtain the preprocessed sensory quality indicators and preprocessed biochemical quality indicators of each sample black garlic.
[0063] Step S332, use the preprocessed sensory quality indicators and preprocessed biochemical quality indicators of each sample black garlic as inputs, and the actual values of the sensory quality scores and biochemical quality scores of the corresponding sample black garlic as outputs to train the machine learning model to obtain a black garlic quality scoring model. Among them, optimize the model hyperparameters through methods such as cross-validation to ensure its good generalization ability and prediction accuracy.
[0064] As an alternative implementation, the machine learning model is a random forest model, a support vector machine model, or a neural network model.
[0065] Among them, by comparing multiple machine learning models (such as support vector machines and neural networks), it is found that the random forest model shows the best prediction accuracy when dealing with sensory quality indicators.
[0066] Step S4, determine the comprehensive quality score of black garlic based on the predicted values of the sensory quality score and the biochemical quality score of black garlic.
[0067] As an alternative implementation, step S4 specifically includes:
[0068] Perform weighted summation on the predicted values of the sensory quality score and the biochemical quality score of black garlic to obtain the comprehensive quality score of black garlic.
[0069] Step S5, adjust the current fermentation process conditions based on the comprehensive quality score Q of black garlic.
[0070] Specifically, optimization suggestions are provided based on the comprehensive quality score of black garlic, and the current fermentation process conditions are adjusted, such as adjusting the fermentation temperature, fermentation humidity, and fermentation time, so as to improve the overall quality of black garlic.
[0071] Among them, the adjustment of fermentation temperature: If the Q value is low and the indicators such as color, texture, and flavor in the sensory quality score value S are poor, it may be that the temperature is inappropriate; if the color is uneven or the flavor is insufficient, appropriately increase the temperature to 70°C to 80°C to promote the Maillard reaction and enzyme activity; if the black garlic is overripe or the flavor is too strong, appropriately reduce the temperature to 60°C to 70°C.
[0072] The adjustment of fermentation humidity: If the Q value is low and the indicators such as texture and taste in the sensory quality score value S are poor, it may be that the humidity is inappropriate; if the texture is uneven (such as a hard core or cracks), increase the humidity to 80% to 90% to keep the garlic cloves soft; if there are mildew spots or strange smells, reduce the humidity to 70% to 80% and strengthen ventilation.
[0073] The adjustment of fermentation time: If the Q value is low and the indicators such as antioxidant activity and total phenol content in the biochemical quality score value B are poor, it may be that the fermentation time is insufficient; if the biochemical indicators are low, extend the fermentation time to 30 to 40 days to promote the generation of total phenols and antioxidant substances; if the black garlic is overripe or the flavor is too strong, shorten the fermentation time to 20 to 30 days.
[0074] Advantages of the present application:
[0075] The present application has the characteristics of automation, intelligence, high efficiency, wide applicability, etc., and can be widely applied to the quality evaluation and production optimization process of black garlic and other fermented foods.
[0076] Based on the same inventive concept, the embodiment of the present application also provides a machine learning-based black garlic quality evaluation system for implementing the above-mentioned machine learning-based black garlic quality evaluation method. The implementation solutions provided by this system to solve problems are similar to the implementation solutions recorded in the above method. Therefore, the specific limitations in one or more embodiments of the machine learning-based black garlic quality evaluation system provided below can refer to the limitations on the machine learning-based black garlic quality evaluation method in the above text, and will not be repeated here.
[0077] In an exemplary embodiment, as Figure 2 shown, a machine learning-based black garlic quality evaluation system is provided, including:
[0078] A data acquisition unit 1, configured to obtain the sensory quality indicators and biochemical quality indicators of black garlic under the current fermentation process conditions, and use the sensory quality indicators and biochemical quality indicators of black garlic as data to be evaluated; the fermentation process conditions include: fermentation temperature, fermentation humidity, and fermentation time.
[0079] A preprocessing unit 2 for preprocessing the data to be evaluated to obtain the preprocessed data to be evaluated.
[0080] A prediction unit 3 for inputting the preprocessed data to be evaluated into the black garlic quality scoring model and outputting the predicted value of the sensory quality score and the predicted value of the biochemical quality score of the black garlic. The black garlic quality scoring model is obtained by training a machine learning model.
[0081] A scoring determination unit 4 for determining the comprehensive quality score of the black garlic based on the predicted value of the sensory quality score and the predicted value of the biochemical quality score of the black garlic.
[0082] An adjustment unit 5 for adjusting the current fermentation process conditions based on the comprehensive quality score of the black garlic.
[0083] In an exemplary embodiment, a computer device is provided, including: a memory, a processor, and a computer program stored on the memory and executable on the processor, and the processor executes the computer program to implement a method for evaluating the quality of black garlic based on machine learning.
[0084] In an exemplary embodiment, a computer-readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, a method for evaluating the quality of black garlic based on machine learning is implemented.
[0085] In an exemplary embodiment, a computer device is provided. The computer device may be a server or a terminal, and its internal structure diagram may be as Figure 3 shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, abbreviated as I / O), and a communication interface. Among them, the processor, the memory, and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used for exchanging information between the processor and external devices. The communication interface of the computer device is used for communicating with external terminals through a network connection. When the computer program is executed by the processor, a method for evaluating the quality of black garlic based on machine learning is implemented.
[0086] Those skilled in the art can understand, Figure 3The structure shown is only a block diagram of some structures related to the solution of this application, and does not constitute a limitation on the computer device to which the solution of this application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine some components, or have different component arrangements.
[0087] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use, and processing of relevant data need to comply with relevant regulations.
[0088] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, database, or other medium used in the embodiments provided in this application can include at least one of non-volatile and volatile memories. Non-volatile memories can include read-only memory (ROM), magnetic tapes, floppy disks, flash memories, optical memories, high-density embedded non-volatile memories, resistive random access memories (ReRAM), magnetoresistive random access memories (MRAM), ferroelectric random access memories (FRAM), phase change memories (PCM), graphene memories, etc. Volatile memories can include random access memory (RAM) or external cache memories, etc. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc.
[0089] The databases involved in the embodiments provided in this application can include at least one of relational databases and non-relational databases. Non-relational databases can include distributed databases based on blockchain, etc., and are not limited thereto. The processors involved in the embodiments provided in this application can be general-purpose processors, central processors, graphics processors, digital signal processors, programmable logics, data processing logics based on quantum computing, etc., and are not limited thereto.
[0090] The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity of description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as the scope recorded in this specification.
[0091] Specific examples are used in this article to elaborate on the principles and implementation manners of the present application. The description of the above embodiments is only used to help understand the method and its core idea of the present application; at the same time, for those of ordinary skill in the art, according to the idea of the present application, there will be changes in the specific implementation manners and application scopes. In summary, the content of this specification should not be construed as a limitation to the present application.
Claims
1. A black garlic quality assessment method based on machine learning, characterized in that: The black garlic quality assessment method based on machine learning includes: Under the current fermentation process conditions, the sensory quality index and biochemical quality index of black garlic are obtained, and the sensory quality index and biochemical quality index of black garlic are used as the data to be evaluated; the fermentation process conditions include: fermentation temperature, fermentation humidity and fermentation time; the fermentation process conditions include: fermentation temperature, fermentation humidity and fermentation time; Preprocessing the data to be evaluated to obtain preprocessed data to be evaluated; Inputting the pre-processed data to be evaluated into a black garlic quality scoring model, and outputting a predicted value of the sensory quality score and a predicted value of the biochemical quality score of the black garlic; the black garlic quality scoring model is obtained by training a machine learning model; Determining the comprehensive quality score of black garlic based on the predicted value of the sensory quality score and the predicted value of the biochemical quality score of black garlic; Based on the comprehensive quality score of black garlic, the current fermentation process conditions are adjusted.
2. The black garlic quality assessment method based on machine learning according to claim 1, characterized in that, The sensory quality indicators include: color, smell, taste and texture, and the biochemical quality indicators include: total phenol content, antioxidant capacity and amino acid content.
3. The black garlic quality assessment method based on machine learning according to claim 1, characterized in that, The data to be evaluated is preprocessed to obtain the preprocessed data to be evaluated, which specifically includes: Standardizing the data to be evaluated to obtain standardized data to be evaluated; The standardized data to be evaluated are normalized to obtain the preprocessed data to be evaluated.
4. The black garlic quality assessment method based on machine learning according to claim 3, characterized in that, The training process of the black garlic quality scoring model specifically includes: Obtaining a training set; the training set includes: sensory quality indicators, biochemical quality indicators, actual values of sensory quality scores, and actual values of biochemical quality scores of multiple samples of black garlic; Build machine learning models; The training set is used to train the machine learning model to obtain the black garlic quality scoring model.
5. The black garlic quality assessment method based on machine learning according to claim 4, characterized in that, The training set is used to train the machine learning model to obtain the black garlic quality scoring model, which specifically includes: Pre-treating the sensory quality index and biochemical quality index of each black garlic sample to obtain the sensory quality index and biochemical quality index of each black garlic sample after pre-treatment; The sensory quality index after pretreatment and the biochemical quality index after pretreatment of each sample of black garlic are used as input, and the actual value of the sensory quality score and the actual value of the biochemical quality score of the corresponding sample black garlic are used as output, and the machine learning model is trained to obtain the black garlic quality scoring model.
6. The black garlic quality assessment method based on machine learning according to claim 1, characterized in that, The machine learning model is a random forest model, a support vector machine model or a neural network model.
7. The black garlic quality assessment method based on machine learning according to claim 1, characterized in that, Based on the predicted value of the sensory quality score and the predicted value of the biochemical quality score of black garlic, the comprehensive quality score of black garlic is determined, including: The predicted values of the sensory quality score and the biochemical quality score of black garlic were weighted and summed to obtain the comprehensive quality score of black garlic.
8. A black garlic quality evaluation system based on machine learning, characterized in that: The black garlic quality assessment system based on machine learning is used to implement the black garlic quality assessment method based on machine learning according to any one of claims 1 to 7, and the black garlic quality assessment system based on machine learning comprises: A data acquisition unit is used to acquire the sensory quality index and biochemical quality index of black garlic under the current fermentation process conditions, and use the sensory quality index and biochemical quality index of black garlic as data to be evaluated; the fermentation process conditions include: fermentation temperature, fermentation humidity and fermentation time; A preprocessing unit, used for preprocessing the data to be evaluated to obtain the preprocessed data to be evaluated; A prediction unit, used for inputting the pre-processed data to be evaluated into a black garlic quality scoring model, and outputting a predicted value of a sensory quality score and a predicted value of a biochemical quality score of the black garlic; the black garlic quality scoring model is obtained by training a machine learning model; A score determination unit, used to determine the comprehensive quality score of the black garlic based on the predicted value of the sensory quality score and the predicted value of the biochemical quality score of the black garlic; The adjustment unit is used to adjust the current fermentation process conditions based on the comprehensive quality score of the black garlic.
9. A computer device comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the black garlic quality assessment method based on machine learning according to any one of claims 1 to 7.
10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the black garlic quality assessment method based on machine learning described in any one of claims 1 to 7 is implemented.