Method and system for detecting vinegar fermentation based on component analysis technology

Abstract

This invention discloses a method and system for detecting vinegar fermentation based on component analysis technology, relating to the field of vinegar detection. The method includes the steps of: collecting raw material information and basic environmental information of a target vinegar; searching a vinegar fermentation detection library using raw material quality measurement results and environmental temperature as indices to obtain a first indicator influencing factor; matching a first detection cycle based on the first indicator influencing factor; performing component analysis on Q vinegar samples of the target vinegar to obtain a set of characteristic sequences for the Q vinegar samples; performing a binary time series analysis to obtain a first fermentation detection result; identifying stability using a stability identification device to obtain a first stability factor; and determining whether the first stability factor satisfies a preset stability factor, and if YES, setting the first fermentation detection result as the target fermentation detection result. This method solves the technical problem of low reliability of vinegar detection results in the prior art and achieves the technical effect of improving the production quality of vinegar.

Description

Technical Field

[0001] The present invention relates to the field of vinegar detection, and specifically to a method and system for detecting vinegar fermentation based on component analysis technology.

Background Art

[0002] In the modern food industry, vinegar is one of the important seasonings, and quality control and fermentation detection in its production process are particularly important. The fermentation of vinegar is a complex biochemical process that is affected by various factors including the quality of raw materials and basic environmental information such as environmental temperature. In the conventional vinegar fermentation process, quality control often depends on artificial experience and intuitive judgment, and there is a lack of systematic detection methods and standardized procedures. As a result, the reliability of the detection results of vinegar fermentation is low, and accordingly the quality fluctuates greatly, making it difficult to ensure the consistency and stability of each batch of products. In addition, the monitoring means of the conventional fermentation process is relatively lagging, and it is impossible to timely and accurately grasp the changes in the main parameters in the fermentation process, and it is difficult to give early warnings and timely interventions for potential problems.

Summary of the Invention

Problems to be Solved by the Invention

[0003] Embodiments of the present application provide a method and system for detecting vinegar fermentation based on component analysis technology to solve the technical problem of low reliability of vinegar detection results in the prior art.

Means for Solving the Problems

[0004] In view of the above problems, embodiments of the present application provide a method and system for detecting vinegar fermentation based on component analysis technology.

[0005] In a first aspect of an embodiment of the present application, a step of collecting raw material information and basic environmental information of target vinegar, wherein the basic environmental information includes environmental temperature, and the raw material information includes raw material quality measurement results, The steps include: using the raw material quality measurement results and ambient temperature as indices to search the vinegar fermentation detection library and obtain the first indicator influencing factor; A step of matching the first detection period based on the first indicator influencing factor, The first detection cycle, in a time series, sequentially performs component analysis on Q vinegar samples of the target vinegar according to a pre-set set of feature indicators, and obtains a set of feature sequences for the Q vinegar samples, wherein each set of feature sequences for each vinegar sample contains M vinegar feature sequences, and each vinegar feature sequence corresponds to one feature indicator in the pre-set set of feature indicators. The steps include performing a binary time series analysis on the set of characteristic sequences of the Q vinegar samples to obtain the first fermentation detection result for the target vinegar, The steps include: identifying the stability of the feature sequence set of Q vinegar samples using a stability identification device and obtaining a first stability factor; The present invention provides a method for detecting vinegar fermentation based on component analysis technology, which includes the step of determining whether the first stabilizing factor satisfies a predetermined stabilizing factor, and if the answer is YES, setting the first fermentation detection result as the target fermentation detection result.

[0006] In a second embodiment of the present invention, An information collection module for collecting raw material information and basic environmental information of a target vinegar, wherein the basic environmental information includes ambient temperature, and the raw material information includes raw material quality measurement results, A search module for obtaining the first indicator influencing factor by searching the vinegar fermentation detection library using the aforementioned raw material quality measurement results and ambient temperature as an index, A matching module for matching the first detection period based on the first indicator influencing factor, A component analysis module for performing component analysis on Q vinegar samples of a target vinegar sequentially in a time series according to the first detection cycle, according to a pre-set set of feature indicators, and obtaining a set of feature sequences for the Q vinegar samples, wherein each set of feature sequences for each vinegar sample contains M vinegar feature sequences, and each vinegar feature sequence corresponds to one feature indicator in the pre-set set of feature indicators, and the component analysis module A time series analysis module for performing a binary time series analysis on the set of feature sequences of the Q vinegar samples and obtaining the first fermentation detection result of the target vinegar, An identification module for identifying the stability of the feature sequence set of Q vinegar samples using a stability identification device and obtaining a first stability factor, The present invention provides a vinegar fermentation detection system based on component analysis technology, which includes a determination module that determines whether the first stabilizing factor satisfies a predetermined stabilizing factor, and if the result is YES, sets the first fermentation detection result as the target fermentation detection result. [Effects of the Invention]

[0007] One or more technical solutions relating to this application have at least the following technical effects or advantages.

[0008] By collecting raw material information and basic environmental information of the target vinegar, raw material quality measurement results and ambient temperature are obtained. Based on the raw material quality measurement results and ambient temperature, a vinegar fermentation detection library is searched to obtain the first indicator influencing factor and match it with the first detection cycle. Component analysis is performed sequentially on Q samples of the target vinegar according to this cycle to obtain a set of characteristic sequences for the vinegar samples. Binary time-series analysis is performed on these sample characteristic sequence sets to obtain the first fermentation detection result for the target vinegar. Subsequently, the stability of the sample characteristic sequence set is identified using a stability identification device to obtain the first stability factor. Finally, it is determined whether the first stability factor satisfies a predetermined stability factor; if YES, the first fermentation detection result is taken as the target fermentation detection result. This solves the technical problem of low reliability of vinegar detection results in conventional technology and achieves the technical effect of improving the production quality of vinegar.

[0009] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that need to be used in describing the embodiments will be briefly described below. Obviously, the drawings described below represent only a few embodiments of the present invention, and those skilled in the art can obtain other drawings based on these without any creative work. [Brief explanation of the drawing]

[0010] [Figure 1] This is a flowchart of a method for detecting vinegar fermentation based on the component analysis technique described in the embodiment of this application. [Figure 2] This is a schematic diagram of the configuration of a vinegar fermentation detection system based on the component analysis technology described in the embodiment of the present invention. [Modes for carrying out the invention]

[0011] The embodiments of this application provide a method and system for detecting vinegar fermentation based on component analysis technology, thereby solving the technical problem of low reliability of vinegar detection results in the prior art.

[0012] The technical solutions of the embodiments of the present application will be described clearly and completely below with reference to the drawings of the embodiments of the present application, and it is clear that the embodiments described are some, but not all, embodiments of the present application. All other embodiments that a person skilled in the art can obtain without creative work based on the embodiments of the present application are within the scope of protection of the present application.

[0013] The terms “includes,” “have,” and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or server that includes a set of steps or units may include, but is not limited to, those steps or units explicitly listed, other steps or modules that are not explicitly listed or that are specific to those processes, methods, products, or devices.

[0014] Example 1 As shown in Figure 1, the embodiment of the present invention provides a method for detecting vinegar fermentation based on component analysis technology, the method comprising the following steps.

[0015] The system collects raw material information and basic environmental information for the target vinegar, the basic environmental information including ambient temperature, and the raw material information including raw material quality measurement results.

[0016] In the vinegar production process, raw material information and basic environmental information are crucial factors influencing the quality of the final product. To ensure the quality stability of the vinegar and the controllability of the fermentation process, this basic information must be collected accurately and comprehensively. Raw material quality measurement results include indicators such as chemical composition analysis of the raw materials (e.g., sugars, proteins, fats), microbial contamination levels, moisture content, and impurity content. Fluctuations in environmental temperature can affect the fermentation rate, the balance of microbial populations, and the production of metabolites, and further significantly impact the flavor and quality of the vinegar.

[0017] The raw material quality measurement results and ambient temperature are used as indices to search the vinegar fermentation detection library and obtain the first indicator influencing factor.

[0018] The vinegar fermentation detection library is a database system that integrates a large amount of historical data, fermentation experience, and scientific knowledge. It can simulate and analyze the fermentation processes of various raw materials and the fermentation process under environmental conditions, and provide corresponding index influencing factors. Search the vinegar fermentation detection library using the raw material quality measurement results and environmental temperature to obtain the first index influencing factor. The first index influencing factor can quantify the influence degree of raw materials and environmental factors on the fermentation process.

[0019] Furthermore, the method includes: obtaining the raw material quality measurement results of a plurality of samples, the environmental temperatures of a plurality of samples, and the index influencing factors of a plurality of samples to construct a plurality of sample particles in the vinegar fermentation detection library; inputting the raw material quality measurement results and environmental temperature into the vinegar fermentation detection library to obtain target particles; based on the positions of the target particles in the vinegar fermentation detection library, matching k sample particles with the closest distance; performing analysis based on the k sample particles to generate the first index influencing factor.

[0020] The process of constructing a vinegar fermentation detection library and generating the first indicator influencing factor involves collecting raw material quality measurement results for multiple samples, including data such as the chemical composition, purity, and impurity content of the raw materials, as well as recording the ambient temperature corresponding to each sample. Next, the indicator influencing factor for each sample is calculated from the collected data. These raw material quality measurement results, ambient temperature, and indicator influencing factor are combined to construct multiple sample particles in the vinegar fermentation detection library. Each sample particle represents one specific fermentation condition and its corresponding set of influencing factors. When new raw material quality measurement results and ambient temperature data are available, inputting this data into the vinegar fermentation detection library retrieves a target particle, which represents a specific state under current production conditions. Next, the system searches for existing sample particles and finds the k sample particles closest to the target particle. These k sample particles provide information on the historical fermentation conditions and influencing factors most similar to the target particle. Finally, the first indicator influencing factor is generated by a weighted average based on the indicator influencing factors of these k matching sample particles.

[0021] Furthermore, the method is, The steps include constructing a framework for the vinegar fermentation detection library by using the raw material quality measurement results as the x-axis and the ambient temperature as the y-axis of the vinegar fermentation detection library, The steps include inputting the raw material quality measurement results of the multiple samples and the ambient temperature of the multiple samples into the framework of the vinegar fermentation detection library to obtain multiple initial sample particles, The method further includes the step of data marking the multiple initial sample particles using indicator influencing factors of multiple samples, and obtaining multiple sample particles.

[0022] In the process of constructing a vinegar fermentation detection library, a two-dimensional framework can be created in which raw material quality measurement results and ambient temperature are used as the x and y axes, respectively, and each point (x,y) in the coordinate system represents a specific combination of raw material quality measurement results and ambient temperature. Raw material quality measurement results for multiple samples and ambient temperatures for multiple samples are input into the framework of the vinegar fermentation detection library. Each sample data forms an initial sample particle, and its position in the coordinate system is determined according to its raw material quality measurement result and ambient temperature. For each initial sample particle, data marking is performed using the corresponding sample indicator influence factors, and, for example, an extra-dimensional dimension (e.g., color, size, or label) is added in the coordinate system to represent the values ​​of these influence factors. Once marking is complete, the initial sample particles are transformed into sample particles with richer information content, and these particles represent not only the raw material and environmental conditions but also the corresponding fermentation performance data.

[0023] Furthermore, the method is, The steps include retrieving the marking information of the k sample particles and obtaining the indicator influence factors for the k samples, The steps include: calculating the reciprocal of the ratio between the distances from the k sample particles to the target particle and the sum of the distances from the k sample particles to the target particle, and obtaining k distance coefficients; The method further includes the step of obtaining the first indicator influence factor by performing a weighted calculation on the indicator influence factors of k samples using k distance coefficients.

[0024] The marking information of the k sample particles closest to the previously determined target particle is retrieved from the vinegar fermentation detection library. This marking information includes the index influence factor for each sample particle, thereby obtaining the index influence factors for the k samples. For each sample particle, the ratio of the distance to the target particle to the sum of the distances from all k sample particles to the target particle is calculated, and then the reciprocal of the ratio is taken to obtain the distance coefficient. Sample particles with larger distance coefficients indicate that they are closer to the target particle and are given a greater weight in subsequent calculations. Finally, different weights are assigned to the index influence factor of each sample according to its corresponding distance coefficient, and a weighted calculation is performed on the index influence factors of the k samples using the obtained k distance coefficients. The result of the weighted calculation is the weighted average of the index influence factors of all samples, i.e., the first index influence factor.

[0025] The first detection cycle is matched based on the first indicator influencing factor.

[0026] In the vinegar fermentation process, the first indicator influencing factor is a quantitative indicator that comprehensively evaluates the current fermentation conditions. Based on this influencing factor, a corresponding first detection cycle can be matched, thereby ensuring timely monitoring and adjustment of the fermentation process. Generally, a high first indicator influencing factor means that the current fermentation conditions may have a significant impact on the quality of the final product. For example, if the quality of the basic raw materials is low, the first indicator influencing factor will be relatively high, and therefore detection should be performed more frequently. On the other hand, if the influencing factor is low, the detection frequency can be appropriately reduced. Specifically, several detection cycle thresholds can be set, each threshold corresponding to a different detection frequency. For example, three thresholds—high, medium, and low—can be set, corresponding to different frequencies such as daily, every other day, and weekly detection. The calculated first indicator influencing factor is compared with the set detection cycle thresholds to determine the detection cycle to be adopted under the current fermentation conditions. If the influencing factor is above the high threshold, the highest frequency detection cycle (e.g., daily detection) is selected; if the influencing factor is below the low threshold, the lowest frequency detection cycle (e.g., weekly detection) is selected; and if the influencing factor is between the two thresholds, a moderate frequency detection cycle (e.g., every other day detection) is selected.

[0027] In accordance with the first detection cycle, component analysis is performed sequentially on Q vinegar samples of the target vinegar according to a pre-set set of feature indicators in a time series, and feature sequence sets are obtained for each of the Q vinegar samples. Each feature sequence set for each vinegar sample contains M vinegar feature sequences, and each vinegar feature sequence corresponds to one feature indicator in the pre-set set of feature indicators.

[0028] In the vinegar fermentation process, periodic component analysis is performed on the target vinegar according to a set time sequence based on the determined first detection cycle. Specifically, a set of feature indicators must be pre-defined, containing multiple key feature indicators for evaluating the vinegar sample, such as moisture content, acidity, saccharifying enzyme activity, yeast cell count, germination rate, reducing sugars, and alcohol content. Q samples of the target vinegar are collected sequentially according to the first detection cycle, with each sample representing the state of the vinegar at a specific point in time. Component analysis is performed on each collected vinegar sample, and each feature indicator of the sample can be measured using methods such as mass spectrometry. After the analysis of each sample is complete, the acquired feature indicator data is organized to form a feature sequence. Each feature sequence set for each vinegar sample contains M vinegar feature sequences, and each feature sequence corresponds to one specific feature indicator in the pre-defined feature indicator set. Therefore, for Q vinegar samples, Q feature sequence sets are ultimately obtained, and each set reflects the performance of the corresponding sample based on multiple feature indicators.

[0029] A binary time-series analysis is performed on the feature sequence set of the Q vinegar samples to obtain the first fermentation detection result for the target vinegar.

[0030] After obtaining a set of feature sequences from Q vinegar samples, a binary time-series analysis is performed on these feature sequence sets to obtain the first fermentation detection result for the target vinegar. The binary time-series analysis is a two-directional analysis: one analyzes the fermentation uniformity of multiple vinegar samples over the same period, and the other analyzes the overall fermentation level of the samples at the final point in time. The results of the two types of analysis are combined to obtain the first fermentation detection result for the target vinegar.

[0031] Furthermore, a binary time-series analysis was performed on the set of characteristic sequences of the Q vinegar samples to obtain the first fermentation detection result for the target vinegar. The method is as follows: The steps include performing the same time-series analysis on the set of characteristic sequences of the Q vinegar samples and obtaining the degree of same time-series bias of the Q vinegar samples, The steps include: extracting the features of the vinegar sample at the last point in time from the feature sequence set of Q vinegar samples; performing central trend analysis on the feature index values ​​of the extracted Q vinegar samples; and obtaining the feature index value of the target vinegar sample. The method further includes the step of using the degree of same-time series bias of the Q vinegars and the characteristic index value of the target vinegar sample as the first fermentation detection result.

[0032] Performing a time-series bias analysis on a set of Q vinegar samples means comparing the differences between characteristic index values ​​of different samples at the same point in time (i.e., the same time series). By calculating the standard deviation of the characteristic index values ​​of each sample at each point in time, the degree of dispersion of different samples at the same fermentation stage can be quantified. From the set of Q vinegar samples' characteristic sequences, the characteristics of the vinegar samples at the final point in time (i.e., at the end of fermentation or just before the end) are extracted. Central trend analysis is performed on the characteristic index values ​​of the Q vinegar samples extracted at the final point in time to calculate the mean, median, etc., and a single target vinegar sample characteristic index value that reflects the typical characteristic performance of all samples at the end of fermentation can be obtained. The time-series bias of the above Q vinegars and the characteristic index value of the target vinegar sample are combined to form the first fermentation detection result.

[0033] Furthermore, the method is, The steps include: extracting identical time-series data from the Q feature sequence sets of vinegar samples to obtain P identical time-series sample datasets, wherein each identical time-series sample dataset contains M vinegar feature index values; The steps include traversing the P identical time-series sample datasets, calculating the degree of bias of the vinegar feature index, and obtaining P index bias degree sets, wherein each index bias degree set includes the degree of bias of M vinegar feature indexes in each identical time-series sample dataset, The steps include: performing an average value operation on each of the P sets of indicator bias degrees to obtain P identical time-series bias degrees; The method further includes the step of performing a weighted calculation on the degree of identical time-series bias of P items to obtain the degree of identical time-series bias of Q items of vinegar.

[0034] Data is extracted from the feature sequence sets of Q vinegar samples according to the same time point in the time series to form P identical time-series sample datasets. P represents a different time point or stage in the time series, and each identical time-series sample dataset contains M vinegar feature index values ​​for all Q samples at that time point. This can be obtained by traversing the P identical time-series sample datasets, calculating the degree of bias for the M vinegar feature indexes in each dataset, and calculating each feature index value relative to the mean value of the index for all samples using statistics such as standard deviation or absolute deviation. In this way, P index bias degree sets are obtained, each set containing the degree of bias of the M vinegar feature indexes at the corresponding time point. By performing an averaging process on the degree of bias in each index bias degree set, i.e., calculating the mean of all feature index bias degrees in each set, a single identical time-series bias degree value is obtained that represents the overall level of all feature index bias degrees at that time point. P identical time-series bias values ​​are obtained, and each bias value corresponds to a specific point in time or stage in the time series. A weighted calculation is performed on the P identical time-series bias values ​​to obtain the final Q identical time-series bias values ​​for vinegar.

[0035] Furthermore, the method is, The steps include: calculating the average value of the characteristic index values ​​of the Q vinegar samples and obtaining the average characteristic index value of the vinegar samples; The steps include using the average value of the characteristic index of the vinegar sample as an index, searching for the characteristic index values ​​of the Q vinegar samples according to a predetermined concentration step, and obtaining the concentrated value of the characteristic index of the first vinegar sample, The steps include determining whether the concentration of the average value of the characteristic index of the vinegar sample is greater than the concentration of the characteristic index concentration of the first vinegar sample, and if the answer is YES, updating the average value of the characteristic index of the vinegar sample to the characteristic index concentration of the first vinegar sample according to a certain probability, The process further includes the step of using the index feature concentration value of the first vinegar sample as an index, continuing the search until a predetermined number of searches is met, and using the index feature concentration value of the first vinegar sample corresponding to the maximum concentration in the search process as the characteristic index value of the target vinegar sample.

[0036] In the vinegar fermentation process, iterative search and concentration comparison methods can be employed to determine the characteristic index value of one representative target vinegar sample. Specifically, the average of the characteristic index values ​​of Q vinegar samples is calculated to obtain the average characteristic index value of the vinegar samples. Using the average characteristic index value of the vinegar samples as an index, the characteristic index values ​​of Q vinegar samples are searched according to a predetermined concentration step. The concentration step is a self-defined distance traveled during the search, i.e., the difference from the average characteristic index value of the vinegar samples. The purpose of the search is to find a single more concentrated value, the characteristic index concentration value of the first vinegar sample, whose concentration in the original data is higher than the current average. The concentration of the average characteristic index value of the vinegar samples is compared with the concentration of the characteristic index concentration value of the first vinegar sample. The concentration is calculated as the ratio of the number of index values ​​to the area of ​​a region constructed with the average characteristic index value of the vinegar samples as the center and the predetermined concentration step as the radius. It reflects the density of index values ​​gathered around the average characteristic index value of the vinegar samples, and a higher concentration indicates higher representativeness of the corresponding index value. If the concentration of the feature index concentration value of the first vinegar sample is higher, the average value of the feature index of the vinegar sample is updated to this more concentrated value according to a certain probability. The updated feature index concentration value of the first vinegar sample is used as the new index, and the search continues to find the next more concentrated value. This process is repeated until a predetermined number of searches are met, updating the index value with each iteration and comparing the concentration of the newly found concentration value with the current index value. After the iterative search is complete, the feature index concentration value of the first vinegar sample corresponding to the maximum concentration in the search process is set as the feature index value of the target vinegar sample.

[0037] The stability of the feature sequence set of the Q vinegar samples is identified using a stability identification device, and the first stability factor is obtained.

[0038] In the vinegar fermentation process, a stability discriminator can be used to analyze the stability of feature sequence sets from different samples. A stability discriminator suited to the characteristics of the vinegar fermentation data can be constructed based on a neural network model, and Q feature sequence sets from vinegar samples are provided as input to the stability discriminator. The stability discriminator analyzes the data in each feature sequence set, identifies stable modes, trends, or periodic changes, and generates a first stability factor according to the analysis results. This first stability factor is used to evaluate the stability of the vinegar fermentation process.

[0039] The system determines whether the first stabilizing factor satisfies a predetermined stabilizing factor, and if the result is YES, the first fermentation detection result is taken as the target fermentation detection result.

[0040] Before analyzing the fermentation process, it is necessary to pre-define a stability factor that can reflect an acceptable level of stability in the vinegar fermentation process. The calculated first stability factor is compared to the pre-defined stability factor criterion. If the first stability factor meets or exceeds the pre-defined stability factor criterion, it indicates that the stability of the vinegar sample's characteristic sequence set is within an acceptable range, and in this case, the current fermentation process is determined to be stable. If the first stability factor falls below the pre-defined criterion, it may mean that there are unstable factors or potential problems in the fermentation process. If the first stability factor meets the pre-defined stability factor, the previously obtained first fermentation detection result can be used as the final target fermentation detection result.

[0041] As described above, the embodiments of the present application have at least the following technical effects.

[0042] By collecting raw material information and basic environmental information of the target vinegar, raw material quality measurement results and ambient temperature are obtained. Based on the raw material quality measurement results and ambient temperature, a vinegar fermentation detection library is searched to obtain the first indicator influencing factor and match it with the first detection cycle. Component analysis is performed sequentially on Q samples of the target vinegar according to this cycle to obtain a set of characteristic sequences for the vinegar samples. Binary time-series analysis is performed on these sample characteristic sequence sets to obtain the first fermentation detection result for the target vinegar. Subsequently, the stability of the sample characteristic sequence set is identified using a stability identification device to obtain the first stability factor. Finally, it is determined whether the first stability factor satisfies a predetermined stability factor; if YES, the first fermentation detection result is taken as the target fermentation detection result. This solves the technical problem of low reliability of vinegar detection results in conventional technology and achieves the technical effect of improving the production quality of vinegar.

[0043] Example 2 Based on the same inventive idea as the method for detecting vinegar fermentation based on component analysis technology described in the aforementioned embodiment, the present application provides a system for detecting vinegar fermentation based on component analysis technology, as shown in Figure 2, and the system in the embodiment of the present application is based on the same inventive idea as the method embodiment. The system is, An information collection module 11 for collecting raw material information and basic environmental information of a target vinegar, wherein the basic environmental information includes ambient temperature, and the raw material information includes raw material quality measurement results, A search module 12 searches the vinegar fermentation detection library using the raw material quality measurement results and ambient temperature as indices to obtain the first indicator influencing factor, A matching module 13 for matching the first detection period based on the first indicator influencing factor, A component analysis module 14 for performing component analysis on Q vinegar samples of a target vinegar sequentially in a time series according to the first detection cycle, according to a preset set of feature indicators, and obtaining a set of feature sequences for the Q vinegar samples, wherein each set of feature sequences for each vinegar sample contains M vinegar feature sequences, and each vinegar feature sequence corresponds to one feature indicator in the preset set of feature indicators, and the component analysis module 14 A time series analysis module 15 performs a binary time series analysis on the set of characteristic sequences of the Q vinegar samples to obtain the first fermentation detection result of the target vinegar, A stability identification device is used to identify the stability of the feature sequence set of Q vinegar samples and to obtain a first stability factor. An identification module 16 is used for this purpose. The system includes a determination module 17 that determines whether the first stabilizing factor satisfies a predetermined stabilizing factor, and if the result is YES, determines that the first fermentation detection result is the target fermentation detection result.

[0044] Furthermore, the search module 12, A method for constructing multiple sample particles in the vinegar fermentation detection library by obtaining raw material quality measurement results for multiple samples, ambient temperature for multiple samples, and indicator influencing factors for multiple samples, and A method for obtaining target particles by inputting the raw material quality measurement results and ambient temperature into the vinegar fermentation detection library, A method for matching the k closest sample particles based on the position of the target particles in the aforementioned vinegar fermentation detection library, This method is used to perform an analysis based on the k sample particles and generate the first indicator influencing factor.

[0045] Furthermore, the search module 12, A method for constructing the framework of the vinegar fermentation detection library, wherein the raw material quality measurement results are used as the x-axis of the vinegar fermentation detection library, and the ambient temperature is used as the y-axis of the vinegar fermentation detection library, A method for obtaining multiple initial sample particles by inputting the raw material quality measurement results of the multiple samples and the ambient temperature of the multiple samples into the framework of the vinegar fermentation detection library, and This method is used to perform data marking on multiple initial sample particles using indicator influencing factors of multiple samples, and to obtain multiple sample particles.

[0046] Furthermore, the search module 12, A method for retrieving the marking information of the k sample particles and obtaining the indicator influence factors of the k samples, A method for obtaining k distance coefficients by calculating the reciprocal of the ratio between the distances from the k sample particles to the target particle and the sum of the distances from the k sample particles to the target particle, and This method is used to obtain the first indicator influence factor by performing a weighted calculation on the indicator influence factors of k samples using k distance coefficients.

[0047] Furthermore, the time series analysis module 15 is A method for performing a time-series bias analysis on the feature sequence set of Q vinegar samples and obtaining the degree of time-series bias of the Q vinegar samples, A method for obtaining the feature index value of a target vinegar sample by extracting the features of the vinegar sample at the last point in time of the feature sequence set of Q vinegar samples, performing central trend analysis on the feature index values ​​of the extracted Q vinegar samples, and This method is used to perform the first fermentation detection result, which involves determining the degree of same-time series bias of the Q vinegars and the characteristic index value of the target vinegar sample.

[0048] Furthermore, the time series analysis module 15 is A method for extracting identical time-series data from the Q feature sequence sets of vinegar samples and obtaining P identical time-series sample datasets, wherein each identical time-series sample dataset contains M vinegar feature index values. A method for traversing P identical time-series sample datasets, calculating the degree of bias of vinegar feature indicators, and obtaining P sets of indicator bias degrees, wherein each set of indicator bias degrees includes the degree of bias of M vinegar feature indicators in each identical time-series sample dataset, A method for obtaining P identical time-series biases by performing an average value operation on each of the P sets of indicator biases, This method is used to perform a weighted calculation on the degree of bias of P identical time series data and obtain the degree of bias of Q identical vinegars.

[0049] Furthermore, the time series analysis module 15 is A method for calculating the average value of the characteristic index values ​​of the Q vinegar samples and obtaining the average characteristic index value of the vinegar samples, A method for obtaining a concentrated value of the characteristic index of the first vinegar sample by using the average value of the characteristic index of the vinegar sample as an index, searching for the characteristic index values ​​of the Q vinegar samples according to a predetermined concentration step, and A method for determining whether the concentration of the average value of the characteristic index of the vinegar sample is greater than the concentration of the characteristic index concentration of the first vinegar sample, and if the answer is YES, updating the average value of the characteristic index of the vinegar sample to the characteristic index concentration of the first vinegar sample according to a certain probability, This method is used to perform the following actions: use the index feature concentration value of the first vinegar sample as an index, continue searching until a predetermined number of searches are met, and set the index feature concentration value of the first vinegar sample corresponding to the maximum concentration in the search process as the characteristic index value of the target vinegar sample.

[0050] The order of the embodiments described above is for illustrative purposes only and does not indicate any superiority or inferiority among the embodiments. Specific embodiments of this specification have been described above. Other embodiments are within the scope of the appended claims. In some cases, the operations or steps described in the claims may be performed in a different order than that in the embodiments, and the desired results can be achieved similarly. Furthermore, the processes shown in the drawings do not necessarily require a specific or sequential order to achieve the desired results. In some embodiments, multitasking and parallel processing may be possible or advantageous.

[0051] The foregoing are merely preferred embodiments of the present application and do not limit it. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of the present application should also be included in the scope of protection.

[0052] This specification and the drawings are merely illustrative descriptions of the Application and are deemed to cover any and all modifications, variations, combinations or equivalents within the scope of the Application. Clearly, a person skilled in the art can make various modifications and variations of the Application without departing from its scope. Accordingly, if such modifications and variations of the Application fall within the technical scope of the Application and its equivalents, the Application is intended to include such modifications and variations. [Explanation of Symbols]

[0053] Information gathering module 11 Search Module 12 Matching Module 13 Component analysis module 14 Time Series Analysis Module 15 Identification module 16 Decision module 17

Claims

1. A method for detecting vinegar fermentation based on component analysis technology, A step of collecting raw material information and basic environmental information of a target vinegar, wherein the basic environmental information includes ambient temperature, and the raw material information includes raw material quality measurement results. The steps include: using the raw material quality measurement results and ambient temperature as indices to search the vinegar fermentation detection library and obtain the first indicator influencing factor; A step of matching the first detection period based on the first indicator influencing factor, The steps include: performing component analysis on Q vinegar samples of the target vinegar sequentially in a time series according to the first detection cycle, according to a pre-set set of feature indicators, and obtaining a set of feature sequences for the Q vinegar samples, wherein each set of feature sequences for each vinegar sample contains M vinegar feature sequences, and each vinegar feature sequence corresponds to one feature indicator in the pre-set set of feature indicators; The steps include performing a binary time-series analysis on the set of characteristic sequences of the Q vinegar samples to obtain the first fermentation detection result for the target vinegar, The steps include: identifying the stability of the feature sequence set of Q vinegar samples using a stability identification device and obtaining a first stability factor; A method for detecting vinegar fermentation based on component analysis technology, characterized by comprising the step of determining whether the first stabilizing factor satisfies a predetermined stabilizing factor, and if YES, setting the first fermentation detection result as the target fermentation detection result.

2. The steps include obtaining raw material quality measurement results for multiple samples, ambient temperature for multiple samples, and indicator influencing factors for multiple samples to construct multiple sample particles in the vinegar fermentation detection library, The steps include inputting the raw material quality measurement results and ambient temperature into the vinegar fermentation detection library to obtain target particles, The steps include matching the k closest sample particles based on the position of the target particles in the vinegar fermentation detection library, The method according to claim 1, further comprising the step of performing an analysis based on the k sample particles to generate the first indicator influencing factor.

3. The steps include constructing a framework for the vinegar fermentation detection library by using the raw material quality measurement results as the x-axis and the ambient temperature as the y-axis of the vinegar fermentation detection library, The steps include inputting the raw material quality measurement results of the multiple samples and the ambient temperature of the multiple samples into the framework of the vinegar fermentation detection library to obtain multiple initial sample particles, The method according to claim 2, further comprising the step of data marking the plurality of initial sample particles using indicator influencing factors of the plurality of samples, and obtaining the plurality of sample particles.

4. The steps include retrieving the marking information of the k sample particles and obtaining the indicator influence factors for the k samples, The steps include: calculating the reciprocal of the ratio between the distances from the k sample particles to the target particle and the sum of the distances from the k sample particles to the target particle, and obtaining k distance coefficients; The method according to the 2nd, further comprising the step of obtaining the first indicator influence factor by performing a weighted calculation on the indicator influence factors of k samples using k distance coefficients.

5. A binary time-series analysis is performed on the set of characteristic sequences of the Q vinegar samples to obtain the first fermentation detection result for the target vinegar, and the method is as follows: The steps include performing a time-series bias analysis on the feature sequence set of Q vinegar samples and obtaining the degree of time-series bias of the Q vinegar samples, The steps include: extracting the features of the vinegar sample at the last point in time from the feature sequence set of Q vinegar samples, performing central trend analysis on the feature index values ​​of the extracted Q vinegar samples, and obtaining the feature index value of the target vinegar sample; The method according to claim 1, further comprising the step of using the degree of same-time-series bias of the Q vinegars and the characteristic index value of the target vinegar sample as the first fermentation detection result.

6. The steps include: extracting identical time-series data from the Q feature sequence sets of vinegar samples to obtain P identical time-series sample datasets, wherein each identical time-series sample dataset contains M vinegar feature index values; The steps include traversing the P identical time-series sample datasets, calculating the degree of bias of the vinegar feature index, and obtaining P index bias degree sets, wherein each index bias degree set includes the degree of bias of M vinegar feature indexes in each identical time-series sample dataset, The steps include: performing an average value operation on each of the P sets of indicator bias degrees to obtain P identical time-series bias degrees; The method according to claim 5, further comprising the step of performing a weighted calculation on P identical time-series biases to obtain Q identical time-series biases for vinegars.

7. The steps include: calculating the average value of the characteristic index values ​​of the Q vinegar samples and obtaining the average characteristic index value of the vinegar samples; The steps include using the average value of the characteristic index of the vinegar sample as an index, searching for the characteristic index values ​​of the Q vinegar samples according to a predetermined concentration step, and obtaining the concentrated value of the characteristic index of the first vinegar sample, The steps include determining whether the concentration of the average value of the characteristic index of the vinegar sample is greater than the concentration of the characteristic index concentration of the first vinegar sample, and if YES, updating the average value of the characteristic index of the vinegar sample to the characteristic index concentration of the first vinegar sample according to a certain probability, The method according to claim 5, further comprising the steps of: using the index feature concentration value of the first vinegar sample as an index, continuing the search until a predetermined number of searches is met, and using the index feature concentration value of the first vinegar sample corresponding to the maximum concentration in the search process as the characteristic index value of the target vinegar sample.

8. A system for detecting vinegar fermentation based on component analysis technology, used to carry out a method for detecting vinegar fermentation based on component analysis technology described in any one of claims 1 to 7, An information collection module for collecting raw material information and basic environmental information of a target vinegar, wherein the basic environmental information includes ambient temperature, and the raw material information includes raw material quality measurement results, A search module for obtaining the first indicator influencing factor by searching the vinegar fermentation detection library using the aforementioned raw material quality measurement results and ambient temperature as an index, A matching module for matching the first detection period based on the first indicator influencing factor, A component analysis module for performing component analysis on Q vinegar samples of a target vinegar sequentially in a time series according to the first detection cycle, according to a pre-set set of feature indicators, and obtaining a set of feature sequences for the Q vinegar samples, wherein each set of feature sequences for each vinegar sample contains M vinegar feature sequences, and each vinegar feature sequence corresponds to one feature indicator in the pre-set set of feature indicators, and the component analysis module A time series analysis module for performing a binary time series analysis on the set of characteristic sequences of the Q vinegar samples and obtaining the first fermentation detection result of the target vinegar, An identification module for identifying the stability of the feature sequence set of Q vinegar samples using a stability identification device and obtaining a first stability factor, A vinegar fermentation detection system based on component analysis technology, characterized by including a determination module that determines whether the first stabilizing factor satisfies a predetermined stabilizing factor, and if YES, sets the first fermentation detection result as the target fermentation detection result.

Images