Tracing method, device and device for producing area of wine and storage medium

Abstract

The invention provides a method, a device and a device for tracing a grape wine production place, and a storage medium, and relates to the technical field of tracing the grape wine production place, the grape wine production place is determined based on the grape wine brewing time, the grape wine brewing place and the grape wine brewing process chain, and multi-dimensional tracing is performed on the grape wine production place. And the traceability accuracy of the grape wine producing area is ensured. Therefore, the quality grade of the wine is determined based on the wine detection report, and the to-be-optimized project is determined according to the quality grade of the wine, the wine production place and the information set of each process in the wine making process chain; the optimization event is determined according to the to-be-optimized project, the grape picking season and the environment type of the grape wine production place, the quality grade of the grape wine is gradually improved, further optimization of the to-be-optimized project is introduced, improvement of the quality grade of the grape wine is guaranteed, and targeted optimization of the quality grade of the grape wine is achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of traceability methods, and in particular to a method, device, apparatus and storage medium for tracing the origin of wine. Background Art

[0002] With the development of science and technology, wine has gradually been applied to our lives. Wine is made from grapes. In the existing technology, wines produced in different wine-producing areas have different tastes, and the quality grades of wines also vary greatly. In the existing technology, the origin of wine is determined only by the label information of the wine, and the origin of wine is not traced in multiple dimensions, resulting in low traceability accuracy of the origin of wine. Summary of the Invention

[0003] Based on this, it is necessary to provide a wine origin traceability method, device, apparatus and storage medium to address the above technical issues.

[0004] A method for tracing the origin of wine comprises: determining multiple parameter combinations based on identification in a wine test report; determining the winemaking time based on the multiple parameter combinations and wine model information; determining the winemaking location based on the winemaking time, the winemaking location, and the winemaking process chain; determining the quality grade of the wine based on the wine test report, and determining items to be optimized based on the wine quality grade, the wine making location, and information sets of each process in the winemaking process chain; determining optimization events based on the items to be optimized, the grape picking season, and the environmental type of the wine making location, and gradually improving the quality grade of the wine.

[0005] A wine origin traceability system, applied to the above-mentioned wine origin traceability method, comprises:

[0006] A parameter combination module, used to determine multiple parameter combinations based on the identification of the wine test report;

[0007] A winemaking time module is used to determine the winemaking time based on a combination of multiple parameters and wine model information;

[0008] The wine origin module is used to determine the origin of wine based on the winemaking time, winemaking location and winemaking process chain;

[0009] The project to be optimized module is used to determine the quality grade of the wine based on the wine test report, and to determine the project to be optimized based on the quality grade of the wine, the origin of the wine, and the information set of each process in the winemaking process chain;

[0010] The optimization event module is used to determine optimization events based on the project to be optimized, the grape picking season, and the environmental type of the wine producing area, and gradually improve the quality level of the wine.

[0011] A device includes a memory and a processor, wherein the memory stores a computer program, and wherein the processor performs the following steps when executing the computer program:

[0012] A storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the following steps are implemented:

[0013] The above-mentioned wine origin traceability method, device, apparatus and storage medium determine multiple parameter combinations based on the identification of the wine test report; determine the winemaking time based on the multiple parameter combinations and the wine model information; determine the wine origin based on the winemaking time, winemaking place and winemaking process chain of the wine, and are compatible with the overall consideration of the winemaking time, winemaking place and winemaking process chain of the wine, and conduct multi-dimensional traceability of the wine origin, thereby ensuring the traceability accuracy of the wine origin.

[0014] Therefore, the quality grade of the wine is determined based on the wine inspection report, and the items to be optimized are determined based on the quality grade of the wine, the origin of the wine, and the information set of each process in the winemaking process chain; the optimization events are determined based on the items to be optimized, the grape picking season, and the environmental type of the wine origin, and the quality grade of the wine is gradually improved. The further optimization of the items to be optimized is introduced, which ensures the improvement of the quality grade of the wine and realizes the targeted optimization of the quality grade of the wine. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 1 is a flow chart of a method for tracing the origin of wine in one embodiment;

[0016] Figure 2 Schematic diagram of the process of step S11 in the method for tracing the origin of wine in one embodiment;

[0017] Figure 3 Schematic diagram of the process of step S12 in the method for tracing the origin of wine in one embodiment;

[0018] Figure 4 Schematic diagram of the process of step S13 in the method for tracing the origin of wine in one embodiment;

[0019] Figure 5 Schematic diagram of the process of step S14 in the method for tracing the origin of wine in one embodiment;

[0020] Figure 6Schematic diagram of the process of step S15 in the method for tracing the origin of wine in one embodiment;

[0021] Figure 7 FIG. 1 is a structural block diagram of a wine origin traceability system in one embodiment. DETAILED DESCRIPTION

[0022] In order to make the purpose, technical solutions and advantages of this application more clear, the following further describes this application in detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not intended to limit this application.

[0023] In this embodiment, please refer to Figures 1 to 6 A wine origin tracing method is applied to the wine origin tracing scenario. The wine origin tracing method includes:

[0024] Step S11: determining a plurality of parameter combinations based on the identification of the wine test report;

[0025] Step S12: determining the winemaking time of the wine according to the combination of multiple parameters and the model information of the wine;

[0026] Step S13: determining the origin of the wine based on the winemaking time, winemaking location, and winemaking process chain;

[0027] Step S14: if the quality grade of the wine is determined based on the wine test report, the project to be optimized is determined based on the information set of the quality grade of the wine, the origin of the wine, and each process in the winemaking process chain;

[0028] Step S15: Determine optimization events based on the project to be optimized, the grape picking season, and the environmental type of the wine producing area, and gradually improve the quality level of the wine.

[0029] In step S11, multiple parameter combinations are determined based on the identification of the wine test report;

[0030] In the specific implementation process of the present invention, the specific steps are:

[0031] S111: Determine corresponding test reports based on the simultaneous testing of each batch of wine, and determine multiple parameters based on the identification of the test reports, including pH value, taste level, color level, and ingredient ratio;

[0032] S112: Determine multiple parameter combinations based on multiple interactions of multiple parameters, wine prices, and wine years.

[0033] In an embodiment of the present application, a corresponding test report is determined based on the simultaneous detection of each batch of wine, and multiple parameters are determined according to the identification of the test report. The multiple parameters include pH value, taste grade, color grade and ingredient ratio. pH value, taste grade, color grade and ingredient ratio are introduced to control the pH value, taste grade, color grade and ingredient ratio as a whole.

[0034] At this time, wine samples from different batches and origins are collected; professional wine testing equipment and methods, such as gas chromatography, liquid chromatography, spectral analysis, etc., are used to simultaneously test the samples; and the test data of each batch of wine is recorded, including but not limited to chemical composition, physical properties, etc.

[0035] The test data of each batch is collated and analyzed to generate a test report. At the same time, key parameters in the test report are identified, such as pH value, taste grade, color grade and ingredient ratio; these parameters are quantified and classified for analysis and comparison in subsequent steps; optionally, the test report is used as a preset report, and covers the pH value, taste grade, color grade and ingredient ratio corresponding to the wine. Different wines correspond to different test reports.

[0036] Specifically, assume there are three batches of wine samples, one from France, one from Italy, and one from the United States. These three batches of samples are tested simultaneously, and corresponding test reports are generated.

[0037] Batch A (France): The test report shows that the pH value of this batch is 3.2, the taste level is mellow, the color level is dark ruby red, and the content of phenolic substances in the ingredient ratio is relatively high; Batch B (Italy): The test report shows that the pH value of this batch is 3.5, the taste level is refreshing, the color level is light ruby red, and the content of acidic substances in the ingredient ratio is relatively high; Batch C (United States): The test report shows that the pH value of this batch is 3.0, the taste level is rich, the color level is dark purple-red, and the sugar content in the ingredient ratio is relatively high.

[0038] By comparing the test reports of these three batches, it was found that there were significant differences in key parameters between them. These differences were caused by factors such as climatic conditions, soil characteristics, grape varieties and brewing processes in different production areas. These parameters will serve as an important reference for traceability and optimization in subsequent steps.

[0039] Therefore, multiple parameter combinations are determined based on multiple interactions of multiple parameters, wine prices, and wine years, thereby achieving multiple interactions of multiple parameters, wine prices, and wine years and ensuring the diversity of multiple parameter combinations.

[0040] At this point, we analyze how multiple parameters, wine prices, and vintages affect each other to form a unique parameter combination. At the same time, first, we clarify the impact of each parameter on the quality of the wine, such as pH value affecting taste, color grade reflecting maturity, and ingredient ratio determining flavor. Next, we consider price factors. High-priced wines often mean higher quality and more refined brewing processes, which affect the range of parameter values. Finally, we incorporate the vintage factor. The climatic conditions in different years affect the growth and maturity of grapes, which in turn affects the parameters of the wine.

[0041] Obtain multiple parameter values of wine from test reports, market data or professional databases; collect market price information of wine, including retail price, wholesale price or auction price, etc.; record the vintage information of wine to ensure the accuracy and consistency of data; at the same time, use neural network statistical methods to explore the correlation and interaction between various parameters; consider price and vintage as independent variables, and analyze how they affect the formation of parameter combinations; based on the analysis results, determine the parameter combination that is representative and distinctive.

[0042] Based on the results of the multiple interaction analysis, determine the parameter combinations that fully reflect wine quality and market demand. Select the most important parameter combinations based on the significance and practical significance of the analysis results. Ensure that the parameter combinations are interpretable and operational to facilitate subsequent application and optimization. Optionally, ensure the accuracy and completeness of the data when conducting multiple interaction analysis to avoid the introduction of noise and bias.

[0043] Specifically, suppose there is a dataset containing 100 wines of different batches, vintages, and prices. By performing multiple interactive analyses on these wines’ parameters (such as pH, taste level, color level, and component ratio), price, and vintage, we discovered the following important parameter combinations:

[0044] Combination A: high pH, medium taste level, dark color level, high phenolic content, medium price, and vintages within the past five years. This combination represents a medium-priced wine with moderate taste, bright color, and rich phenolic substances, suitable for daily drinking; Combination B: low pH, high taste level, light color level, high acid content, high price, and specific high-quality vintages (such as 2005). This combination represents a high-priced wine with a rich taste, moderate acidity, lighter color but unique flavor, suitable for collection or drinking on special occasions; Combination C: medium pH, medium taste level, medium color level, high sugar content, medium to low price, and a wide distribution of vintages. This combination represents a popular wine with balanced taste, moderate color, higher sweetness, and affordable price, suitable for wide consumption.

[0045] Through the combination of these parameters, we can gain a deeper understanding of the quality differences and market positioning of wines from different batches, years and prices, providing strong support for traceability, optimization and marketing in subsequent steps.

[0046] In one embodiment of this application, assume that there is the following wine sample data:

[0047]

[0048] Combination 1: pH value between 3.0-3.3, taste level is mellow or rich, color level is dark ruby red or dark purple red, phenolic content ≥15%, price ≥ US$50, year is 2015-2020; Combination 2: pH value between 3.3-3.6, taste level is refreshing or medium, color level is light ruby red or medium ruby red, phenolic content <15%, price < US$50, no year limit.

[0049] Therefore, combination 1: samples A and C (all rules are met); combination 2: samples B and D (the phenolic content of sample D is slightly lower than 15%, but according to actual needs, the rules are flexibly adjusted to include it in combination 2).

[0050] In step S12, the winemaking time of the wine is determined based on the combination of multiple parameters and the model information of the wine;

[0051] In the specific implementation process of the present invention, the specific steps are:

[0052] S121: collecting label information of the wine, and determining the model information of the wine based on the recognition of the label information of the wine;

[0053] S122: Determine multiple features based on the identification of multiple parameter combinations, and determine the winemaking time based on the multiple features, the wine model information, and the winemaking time learning model. At this time, the multiple features and the wine model information are used as input parameters, and the winemaking time is output through the preset winemaking time learning model.

[0054] In an embodiment of the present application, the label information of the wine is collected, and the model information of the wine is determined based on the identification of the label information of the wine, thereby ensuring the accuracy of the model information of the wine.

[0055] At this point, key information is obtained from the wine packaging or bottle, including brand, winery, origin, model (such as year, series name), alcohol content, capacity, etc.; optionally, a scanning device or camera technology is used to capture the label image for subsequent digital processing and identification; the collected information is organized into a structured format for subsequent analysis and identification.

[0056] Extract information directly related to the wine model from the collected label information, such as the specific brewing year, limited edition logo, the winery's specific product line, etc. At this time, identify and filter out information directly related to the model and exclude other non-critical information; determine the wine model based on the filtered information; optionally, verify the accuracy of the model information by comparing it with the winery's official website, industry database or expert opinions, and make necessary corrections.

[0057] Specifically, suppose you are processing a wine from the Bordeaux region of France, and the label information on the bottle is as follows: Brand: Chateau Lafite Rothschild; Origin: Bordeaux, France; Model: 2005; Alcohol content: 13.5% vol; Capacity: 750ml.

[0058] First, all of the above information was recorded through physical observation. Next, a smartphone was used to photograph the labels for subsequent digital processing. Finally, this information was organized into a structured format, such as a spreadsheet or database record. From this collected information, information directly related to the model number was selected: "2005." Based on Bordeaux wine naming conventions and professional knowledge, it was determined that "2005" refers to the year this wine was produced. By comparing the vintage information with the winery's official website and industry databases, the accuracy of the "2005" vintage was verified, and the model number of this wine was determined to be "Château Lafite Rothschild 2005."

[0059] Therefore, multiple features are determined based on the identification of multiple parameter combinations, and the winemaking time of the wine is determined based on the multiple features, the model information of the wine and the winemaking time learning model. At this time, multiple features and the model information of the wine are used as input parameters, and the winemaking time of the wine is output through the preset winemaking time learning model, thereby ensuring the traceability accuracy of the winemaking time.

[0060] In step S11 , a plurality of parameter combinations have been determined, and these parameter combinations reflect different properties and qualities of the wine; now, a plurality of key characteristics of the wine need to be further identified based on these parameter combinations.

[0061] At this point, the parameter combination determined in step S11 is reviewed and the impact of each parameter on the wine quality is analyzed. Based on the results of the parameter analysis, features that can represent the key qualities of the wine are extracted. These features include grape variety, brewing process, taste style, color intensity, aroma complexity, etc. The extracted features are integrated into a feature vector for subsequent model input.

[0062] Using a pre-set winemaking time learning model, combined with multiple features and wine model information, the winemaking time is predicted or estimated. Here, the winemaking time refers to the optimal drinking time for the wine. Ensure that the pre-set winemaking time learning model has been properly trained and validated, and has sufficient accuracy and generalization capabilities. Prepare the model by feeding the integrated feature vector and wine model information as input parameters. Enter the input parameters into the winemaking time learning model and run the model to obtain prediction results. Based on the model's output, interpret and determine the winemaking time, which involves further analysis or verification of the model output.

[0063] Specifically, assume that a wine from the Tuscany region of Italy is being processed, and its multiple parameter combinations have been determined through step S11, and the following key features have been extracted from the parameter combinations: Feature 1: Sangiovese grape variety; Feature 2: Classic Tuscan brewing process; Feature 3: Medium body, dry type, cherry and plum fruit aroma; Feature 4: Deep ruby red color, medium acidity; in addition, the model information of the wine is "2010 Reserva"; now, these features and model information are input into the preset winemaking time learning model.

[0064] The winemaking time learning model is built using machine learning methods and has been trained and validated using a large amount of historical data on Tuscan wines. The extracted features (Sangiovese grape variety, classic Tuscan winemaking process, medium-bodied, dry fruit aroma, deep ruby red color, and medium acidity) and model information ("2010 Reserva") are integrated into a feature vector and prepared for input into the winemaking time learning model. The feature vector is input into the model, and after running the model, a prediction result is output, indicating that the best time to drink this wine is around 8-10 years after brewing. Based on the model output, it is explained that the wine is brewed 8-10 years ago, which means that the taste, aroma, and overall quality of the wine will reach their optimal state within this period after brewing.

[0065] In one embodiment of the present application, first, multiple characteristics of the wine are identified and a weight is assigned to each characteristic, which weights reflect the importance of the characteristic to the winemaking time; based on the characteristics of the wine to be tested and the corresponding weights, a comprehensive score is calculated, and this score is calculated based on a linear combination of the characteristics, a nonlinear function or other complex models; using the scores and winemaking time data of known wines, a score-winery time mapping relationship is constructed (which is linear, nonlinear or classification-based); then, the score of the wine to be tested is mapped to the corresponding winemaking time.

[0066] Assume the following features and weights: grape variety (Syrah = 3, Cabernet Sauvignon = 2, Merlot = 1); taste style (dry = 2, off-dry = 1, sweet = 0); body (full = 3, medium = 2, light = 1); aroma complexity (complex = 3, medium = 2, simple = 1); score range 10-12: 6 years old; score range 13-15: 8 years old; score range 16-18: 10 years old.

[0067] Now, there is a wine to be tested, and its characteristic score is: Grape variety: Syrah (3 points); Tasting style: Dry (2 points); Wine body: Full (3 points); Aroma complexity: Complex (3 points); Total score = 3+2+3+3 = 11; Since 11 points falls within the range of 10-12 points, according to the mapping relationship, it is estimated that the wine is 6 years old.

[0068] In step S13, the origin of the wine is determined based on the winemaking time, the winemaking location, and the winemaking process chain;

[0069] In the specific implementation process of the present invention, the specific steps are:

[0070] S131: Collecting logistics information of the wine, and triggering primary traceability of the wine based on the wine model information and the wine logistics information, and determining the winemaking place of the wine based on the primary traceability of the wine;

[0071] S132: Determine the corresponding winemaking environment based on the winemaking records of the winemaking site and the wine model information, and construct a winemaking process chain based on the winemaking environment and the wine process information;

[0072] S133: Determine a first origin range based on the winemaking time and winemaking location of the wine, determine a second origin range based on the winemaking time and winemaking process chain of the wine, and determine the wine origin based on the first origin range, the second origin range and the wine model information.

[0073] In an embodiment of the present application, the logistics information of the wine is collected, and the primary traceability of the wine is triggered based on the model information of the wine and the logistics information of the wine. The winemaking place of the wine is determined based on the primary traceability of the wine, thereby realizing the primary traceability of the wine and ensuring the accuracy of the winemaking place of the wine.

[0074] At this point, the logistics information of the wine is collected. The logistics information comes from multiple data sources, including but not limited to the logistics company's database, Internet of Things devices (such as RFID tags, GPS trackers), supply chain management systems, etc. The collected logistics information includes the shipping location, receiving location, transportation method, transportation time, transfer station, temperature control records, etc. The logistics information collected from different data sources is integrated into a unified platform for subsequent analysis and traceability.

[0075] Using the wine's model information and logistics information, a traceability process is initiated to track the wine's production and logistics history. At this time, according to the wine's model information (such as brand, year, series, batch number, etc.), the corresponding production records are searched in the database; the collected logistics information is associated with the production records to form a complete chain from production to logistics; once the information is matched and associated, the system will automatically trigger the traceability process and start tracking the history of the wine.

[0076] Through primary traceability, determine at which specific winemaking site (such as winery, brewery) the wine was produced; carefully analyze all data collected in the traceability process, especially the information directly related to production records; based on the analysis results, determine the production location of the wine, that is, the winemaking site, which requires reference to official documents such as the winery or brewery's registration information and production license.

[0077] Specifically, suppose there is a bottle of wine from the Bordeaux region of France, and its model information is "Chateau Lafite Rothschild 2005". The transportation record of this bottle of wine is obtained from the logistics company, including the entire transportation process from the Bordeaux winery, passing through the Paris transit station, and finally arriving in Beijing, China. The record also includes the transportation method (air transport), transportation time (such as shipping date, arrival date) and temperature control records (to ensure that the wine is kept within the appropriate temperature range during transportation).

[0078] The model information "Chateau Lafite Rothschild 2005" is entered into the traceability system. Based on the model information, the system finds the corresponding production record in the database, indicating that the bottle of wine was produced at a well-known winery in Bordeaux. The system then links the logistics information with the production record, forming a complete chain from production to logistics.

[0079] By analyzing the traceability data, it was confirmed that the wine was produced at Chateau Lafite Rothschild in Bordeaux. This information is important for consumers because it guarantees the quality of the wine and the reliability of its source. At the same time, for the winery, this also helps to maintain its brand image and prevent the emergence of counterfeit and inferior products.

[0080] Furthermore, the wine-making environment of the corresponding wine is determined based on the wine-making records of the wine-making site and the model information of the wine, and the wine-making process chain of the wine is constructed based on the wine-making environment and the process information of the wine, which is compatible with the overall consideration of the wine-making environment and the process information of the wine, and ensures the accuracy of the wine-making process chain.

[0081] At this time, it is necessary to obtain the winemaking records of the winery. These records contain various parameters and data of the winemaking process, such as grape variety, picking time, fermentation temperature, aging conditions, etc.; match the wine model information with the winemaking records to find the corresponding production batches and winemaking conditions; based on the matched winemaking records and model information, analyze the natural environment (such as the climate conditions of the year, soil type, water quality) and man-made environment (such as the degree of modernization of the winemaking facilities, the winemaking technology and equipment used, etc.) in which the wine is located during the winemaking process.

[0082] Build a detailed winemaking process chain to describe the entire process from grape picking to finished wine, including the specific operations, time nodes and quality control points of each process; at this time, collect all process information in the wine production process from the winemaking records, such as grape picking, destemming and crushing, fermentation, aging, blending, bottling, etc.; combine each process with the corresponding winemaking environment, and analyze the impact of the environment on the process, such as how fermentation temperature affects yeast activity, how aging conditions affect the flavor development of wine, etc.; based on the collected process information and winemaking environment analysis, build a detailed winemaking process chain, including the input, output, operating conditions, time nodes and quality control points of each process.

[0083] For example, consider a bottle of Napa Valley Cabernet Sauvignon wine with the model number "XYZ Winery Cabernet Sauvignon 2018." First, XYZ Winery's winemaking records are reviewed to identify the 2018 Cabernet Sauvignon production batch. The records reveal that Napa Valley experienced favorable climatic conditions in 2018, with moderate rainfall and abundant sunshine, providing an ideal natural environment for grape growth. Furthermore, XYZ Winery utilizes modern winemaking facilities and techniques, such as temperature-controlled fermentation tanks and oak barrel aging.

[0084] We collected information on all the production processes for XYZ Winery's 2018 Cabernet Sauvignon, including grape harvesting (in September), destemming and crushing, temperature-controlled fermentation (at 25-28°C for 14 days), barrel aging (18 months in French oak barrels), blending (after aging), and bottling. We analyzed the impact of each process on wine quality, taking into account the winemaking environment. For example, temperature-controlled fermentation helps preserve the grape aroma and color, while oak barrel aging adds vanilla and caramel flavors to the wine. Based on this information, we constructed a detailed winemaking process chain, describing the entire process from grape harvest to finished wine, including the specific operations, time nodes, and quality control points of each process.

[0085] Therefore, the first origin range is determined according to the winemaking time and the winemaking place of the wine, the second origin range is determined according to the winemaking time and the winemaking process chain of the wine, and the wine origin is determined based on the first origin range, the second origin range and the model information of the wine. The overall consideration of the first origin range, the second origin range and the model information of the wine is compatible, thereby ensuring the accuracy of the wine origin.

[0086] At this time, the scope of the first origin of the wine is preliminarily determined through the winemaking time and winemaking location; for the first origin scope, the winemaking time (especially the year) is considered, because the climatic conditions in different years will affect the growth and quality of grapes, and thus affect the style and characteristics of the wine; combining the winemaking time with the winemaking location, considering the climatic conditions, soil type, adaptability of grape varieties and other factors of the location in a specific year, the scope of the first origin of the wine is preliminarily determined.

[0087] The second origin of wine can be further refined through the winemaking time and winemaking process chain; for the second origin range, the winemaking process chain is considered, especially those processes that are sensitive to origin, such as fermentation methods, aging conditions, blending technology, etc.; the winemaking process chain is combined with the winemaking time to analyze the impact of different processes on wine quality in a specific year, as well as the differences between these processes in different origins, so as to determine the second origin range.

[0088] The exact origin of the wine is finally determined by combining the first origin range, the second origin range and the model information of the wine; at this time, the information of the first origin range and the second origin range are integrated, taking into account the overlapping parts and differences between them; combined with the model information of the wine (such as brand, series, specific production area logo, etc.), the origin range is further narrowed; based on the integrated information and reference of the model information, the exact origin of the wine is finally determined.

[0089] Specifically, suppose there is a bottle of wine labeled "Bordeaux Blend 2010", whose winemaking process chain includes temperature-controlled fermentation, oak barrel aging and blending; for the first origin range, considering the winemaking time in 2010, it is known that the climatic conditions in the Bordeaux region in that year were suitable and the grapes grew well; combined with the fact that the winemaking site is located in Bordeaux, the first origin range is preliminarily determined to be the Bordeaux region.

[0090] Analyzing the winemaking process chain within the secondary origin range, temperature-controlled fermentation and oak barrel aging are typical processes of Bordeaux blends. However, the blending process of Bordeaux blends involves grape varieties from different production areas. However, considering the "Bordeaux blend" model information, it is inferred that the main grape varieties should come from the Bordeaux region. Combined with the winemaking time in 2010, the secondary origin range is further refined. It is still mainly based on the Bordeaux region, but also includes some surrounding production areas with similar climate and soil conditions.

[0091] By integrating the information of the first and second origin ranges, it was found that they were both mainly in the Bordeaux region; referring to the wine model information "Bordeaux Blend 2010", it was determined that the exact origin of this wine was the Bordeaux region; by considering multiple factors such as the winemaking time, winemaking location and winemaking process chain, the origin of the wine was determined more accurately.

[0092] In one embodiment of the present application, the wine origin matching table:

[0093]

[0094] This wine origin matching table lists different winemaking dates, winemaking locations, primary origin ranges, winemaking process chains, secondary origin ranges, model information, and wine origins. Each row represents a specific wine case, where the winemaking date and winemaking location are used to determine the primary origin range, the winemaking process chain is used to determine the secondary origin range, and the model information serves as auxiliary information.

[0095] By matching the information in the table, you can quickly determine the origin of the wine. For example, for a wine produced in Bordeaux in 2015, its first origin is the Bordeaux region, its winemaking process is temperature-controlled fermentation, its second origin is Bordeaux and its surrounding areas, and its model information is Bordeaux blend. Therefore, the wine's origin is determined to be Bordeaux.

[0096] In step S14, if the quality grade of the wine is determined based on the wine test report, and the items to be optimized are determined based on the information set of the quality grade of the wine, the origin of the wine, and each process in the winemaking process chain;

[0097] In the specific implementation process of the present invention, the specific steps are:

[0098] S141: Collecting a wine test report, and determining multiple taste parameters, color parameters, flavor parameters, and grape maturity based on the wine test report;

[0099] S142: Determining a first quality parameter based on the plurality of taste parameters, color parameters, flavor parameters, and grape maturity, determining a second quality parameter based on the wine model information and corresponding sales records, and determining a quality grade of the wine based on the first quality parameter and the second quality parameter;

[0100] S143: determining an information set of each process in the wine-making process chain based on the traceability of the wine-making process chain;

[0101] S144: Determine the nodes to be optimized based on multiple interactions of the information sets of the quality grade of the wine, the origin of the wine, and each process in the winemaking process chain, and determine the projects to be optimized based on the traceability of the nodes to be optimized.

[0102] In an embodiment of the present application, a wine test report is collected, and multiple taste parameters, color parameters, wine flavor parameters and grape maturity are determined based on the wine test report. Multiple taste parameters, color parameters, wine flavor parameters and grape maturity are introduced.

[0103] At this time, the wine test report is collected. The testing agency or sommelier will use professional instruments and methods to analyze the wine and record the results in the test report.

[0104] After obtaining the test report, you need to read and understand the information therein carefully; then, based on this information, determine the wine's taste parameters (such as sweetness, acidity, tannins, etc.), color parameters (such as hue, brightness, etc.), flavor parameters (such as fruitiness, floral aroma, spice, etc.) and the maturity of the grapes (such as inferred by pigment concentration, sugar content, etc.).

[0105] Taste parameters: For example, if the test report shows a high alcohol content and moderate total acidity, it can be inferred that the wine has a mellow taste and balanced acidity; Color parameters: Through the description of hue and brightness, the color characteristics of the wine, such as deep red, ruby red, etc., are understood; Flavor parameters: Based on the description in the sensory evaluation, the main flavor characteristics of the wine are determined, such as black currant aroma, cherry aroma, vanilla flavor, etc.; Grape maturity: Through the analysis of pigment concentration and sugar content, the maturity of the grapes at the time of picking can be inferred.

[0106] Specifically, let's assume a red wine test report from Bordeaux, France, which shows: Alcohol: 13.5%; Total Acidity: 6.0g / L; pH: 3.3; Residual Sugar: Very Low; Tannin Content: Medium to High; Pigment Concentration: High; Sensory Evaluation: Full-bodied, Balanced Acidity, Bright Deep Red Color, Rich Blackcurrant Aroma, and Light Vanilla.

[0107] Based on this information, the taste parameters of this red wine were determined to be mellow with balanced acidity, the color parameters to be deep red and bright, the flavor parameters to be black currant and vanilla, and the grapes to be relatively mature (inferred from the high pigment concentration and very low residual sugar content). This information is of great significance for subsequent quality evaluation and optimization.

[0108] Furthermore, a first quality parameter is determined based on multiple taste parameters, color parameters, wine flavor parameters and grape maturity, a second quality parameter is determined based on the wine model information and corresponding sales records, and the quality grade of the wine is determined based on the first quality parameter and the second quality parameter, thereby ensuring the accuracy of the wine's quality grade.

[0109] At this time, the wine's taste parameters (such as sweetness, acidity, tannins, aftertaste length, etc.), color parameters (such as hue, brightness, depth, etc.), flavor parameters (such as fruitiness, floral aroma, spice, oak flavor, etc.) and grape maturity (inferred through pigment concentration, sugar content, etc.) are comprehensively considered. These parameters together reflect the intrinsic quality of the wine and are an important basis for evaluating the quality of the wine.

[0110] Based on these parameters, a set of scoring criteria is developed, each parameter is scored, and the scores of all parameters are added up or weighted averaged to obtain the first quality parameter. This first quality parameter is a quantitative value used to measure the intrinsic quality level of the wine.

[0111] Specifically, based on industry experience and consumer preferences, a reasonable scoring range and scoring criteria are set for each parameter, and each parameter is scored according to the specific values and descriptions in the test report; calculate the first quality parameter: add up or take the weighted average of the scores of all parameters to obtain the first quality parameter.

[0112] Considering the wine model information (such as brand, production area, year, series, etc.) and the corresponding sales records (such as sales volume, price, consumer evaluation, market feedback, etc.), this information reflects the wine's performance in the market and consumer recognition, and is another important dimension for evaluating wine quality.

[0113] Based on this information, another set of scoring criteria is developed to evaluate the wine's brand influence, market acceptance, consumer satisfaction, etc., and a quantitative value is obtained as the second quality parameter, which measures the wine's market value and consumer preference.

[0114] Specifically, information such as wine sales volume, price, and consumer evaluation is extracted from sales data; consumer evaluations and feedback on wine are collected through social media, professional forums, and other channels; scoring criteria and weights are set for each evaluation indicator based on market conditions and consumer preferences, and scores are assigned; the scores of all evaluation indicators are added together or weighted averaged to obtain the second quality parameter.

[0115] Another approach is to combine the first quality parameter and the second quality parameter, taking into account the intrinsic quality and market performance of the wine, to determine the quality grade of the wine; the quality grade is a simple classification (such as grade A, grade B, grade C, etc.), and is also a specific value or range; at this time, a reasonable quality grade standard is formulated based on the distribution of the first quality parameter and the second quality parameter; the first quality parameter and the second quality parameter of the wine are compared with the quality grade standard to determine the quality grade of the wine.

[0116] Specifically, suppose there is a red wine from the Bordeaux region of France, whose first quality parameter (based on taste, color, flavor and grape maturity) scores 85 points, and the second quality parameter (based on brand influence, market acceptance and consumer satisfaction) scores 90 points; according to the established quality grade standards, wines with 85-90 points are classified as Grade A; therefore, the quality grade of this red wine is Grade A.

[0117] Furthermore, based on the traceability of the wine-making process chain, the information set of each process in the wine-making process chain is determined, thereby realizing the traceability of the wine-making process chain and ensuring the accuracy of the information set of each process in the wine-making process chain.

[0118] At this point, we first need to clarify the concept of the winemaking process chain; the winemaking process chain refers to the collection of a series of processes involved in the entire production process from grape picking to wine bottling and delivery; traceability refers to tracking the source, execution status and relationship between these processes.

[0119] Based on the understanding of the traceability of the winemaking process chain, it is necessary to specifically identify each process, including identifying key processes such as grape picking, destemming and crushing, fermentation, maceration, pressing, clarification, aging, blending, filtration, and bottling, and clarifying the sequence and logical relationship between them; at this time, refine the process flow chart: based on the preliminary process flow chart, further refine the specific content and operation details of each process; list the processes: according to the refined flow chart, list all key processes and assign a unique identifier to each process.

[0120] After determining each process, it is necessary to collect and organize detailed information for each process, including the input materials of the process (such as grape variety, picking date, fermentation agent type, etc.), operation process (such as fermentation temperature, time, stirring frequency, etc.), output products (such as fermented wine characteristics, yield, etc.) and quality control standards (such as physical and chemical indicators, sensory evaluation indicators, etc.); at this time, design a special information collection form for each process, listing all the information points that need to be collected; conduct field records and observations at the production site to ensure that the collected information is accurate and complete; organize and analyze the collected information to form an information set for each process.

[0121] Specifically, suppose you are conducting a traceability analysis of the winemaking process chain for a Pinot Noir red wine from Burgundy, France; you have collected the winery's winemaking process documents and conducted in-depth discussions with the winemaking team; and you have drawn a complete process flow chart from grape picking to bottling and shipment.

[0122] Key processes were identified, including grape picking, destemming and crushing, cold maceration, fermentation, pressing, malolactic fermentation, clarification, aging, blending, filtration and bottling; a unique identifier was assigned to each process, and a detailed process flow chart was developed.

[0123] An information collection form was introduced, including information points such as grape variety (Pinot Noir), picking date, fermentation agent type (natural yeast), fermentation temperature, time, stirring frequency, cold soaking conditions, pressing method, aging container and time, blending ratio, filtration medium and bottling date; field records and observations were carried out at the production site to ensure that the collected information was accurate and complete; the collected information was sorted and analyzed to form an information set for each process; for example, the information set of the fermentation process includes detailed information such as the fermentation temperature is controlled at 18-22℃, the fermentation time lasts for about two weeks, and the stirring frequency is twice a day.

[0124] Therefore, the nodes to be optimized are determined based on the multiple interactions of the information sets of the wine's quality grade, the wine's origin, and each process in the winemaking process chain, and the projects to be optimized are determined based on the traceability of the nodes to be optimized. The nodes to be optimized are introduced to accurately control each node to be optimized.

[0125] At this time, the quality grade of the wine, the origin information and the information set of each process in the winemaking process chain are comprehensively considered. There is a complex interactive relationship between these information, which together affect the final quality of the wine.

[0126] Multiple interaction analysis refers to an in-depth analysis of this information to find out the internal connections and potential problems between them, including analyzing the relationship between quality grade and origin characteristics, as well as the relationship between quality grade and operating parameters of each process.

[0127] At this point, the wine's quality grade, origin information, and information on each process are integrated into a database for subsequent analysis; correlation analysis is performed on this information to identify significantly correlated factors; and the interaction effects between different factors are evaluated to determine their joint impact on wine quality.

[0128] At the same time, based on multiple interaction analyses, it is necessary to determine which processes or operating parameters are the key factors affecting wine quality, that is, the nodes to be optimized. These nodes are certain operating parameters in a single process, and are also interfaces or synergies between multiple processes.

[0129] Based on the results of multiple interaction analyses, factors influencing wine quality are prioritized. Nodes for optimization are identified based on process importance and controllability. Once these nodes are identified, further tracing back to their source is necessary to identify specific optimization projects. This involves analyzing the root causes of these issues, determining optimization goals, and developing optimization plans. Tracing back to these targets requires a deep understanding of each link in the winemaking process chain and the interactions between them. Analyze the nodes to be optimized in depth to identify the root causes of the problems. Based on the results of the root cause analysis, specific optimization goals are set.

[0130] Specifically, assume that a quality optimization analysis is being conducted on a red wine from the Bordeaux region of France; the wine's quality grade (Grade A), origin information (Bordeaux region), and information sets of each process are integrated; through correlation analysis, it is found that fermentation temperature, maceration time, and aging conditions are significantly correlated with the quality of the wine; further interaction effect analysis shows that the interaction between fermentation temperature and maceration time has a significant impact on the aroma and taste of the wine.

[0131] Based on the results of multiple interaction analysis, the fermentation temperature and maceration time in the fermentation process were identified as nodes to be optimized. At the same time, it was also noted that the oak barrel type and aging time in the aging process had an important impact on the quality of the wine, so they were also listed as nodes to be optimized.

[0132] A traceability analysis of the fermentation temperature and maceration time revealed that the current operating parameters were too conservative, resulting in a less intense aroma in the wine. Therefore, an optimization goal was set: to increase the fermentation temperature and appropriately extend the maceration time to enhance the aroma and taste of the wine. For the aging process, the impact of different oak barrel types on wine quality was analyzed, and an optimization plan was developed: to select oak barrels that are more suitable for the style of Bordeaux red wines and adjust the aging time to achieve optimal quality.

[0133] In one embodiment of the present application, for a Class A wine from Bordeaux, its weighted score is calculated as follows: Quality grade score: 5*0.3=1.5; Origin score: assuming Bordeaux scores 4 points (because Bordeaux is famous for its high-quality wines)*0.2=0.8; Fermentation temperature score: assuming the actual temperature is 25°C, which is within the ideal range, the full score is 1 point*0.15=0.15; Maceration time score: assuming the actual time is 15 days, which is also within the ideal range, the full score is 1 point. *0.15=0.15; Pressing method score: assuming that airbag pressing gets a full score of 1 point*0.1=0.1; Aging condition score: assuming that oak barrel aging for 18 months gets a full score of 1 point (or adjust according to specific circumstances)*0.05=0.05; Weighted total score = 1.5+0.8+0.15+0.15+0.1+0.05=2.75; By comparing the weighted scores of different wines, find out the factors with lower scores or which deviate significantly from the ideal values. These are potential nodes for optimization.

[0134] Once the nodes to be optimized are determined, it is necessary to further trace these nodes to find the specific items to be optimized. Specifically, suppose it is found that the weighted score of a certain Bordeaux wine is low, mainly because the fermentation temperature and maceration time scores are not high; through traceability analysis, it is found that: the low score for fermentation temperature is because the actual temperature is too low, resulting in insufficient fermentation, affecting the flavor and aroma of the wine; the low score for maceration time is because the maceration time is too short, and the pigments and flavor substances in the grape skins are not fully extracted. Therefore, the items to be optimized are determined as follows: raising the fermentation temperature to the ideal range (for example, 26-27°C) to promote full fermentation; extending the maceration time to a more appropriate length of time (for example, 18-20 days) to fully extract flavors and pigments; through these optimization measures, it is expected that the quality and score of the wine will be improved.

[0135] In step S15, the optimization event is determined according to the project to be optimized, the grape picking season, and the environmental type of the wine producing area, and the quality level of the wine is gradually improved;

[0136] In the specific implementation process of the present invention, the specific steps are:

[0137] S151: Determine a grape picking batch based on the wine model information and the wine database, and determine a grape picking season based on the grape picking batch, grape picking records, and grape picking environment information during dynamic grape picking.

[0138] S152: collecting multiple environmental parameters of the wine producing area based on the matching of the wine producing area and the wine making time, and determining the environment type of the wine producing area according to the multiple environmental parameters of the wine producing area;

[0139] S153: Determine the optimization events based on the interaction between the project to be optimized, the grape picking season, and the environmental type of the wine-producing area. At this time, there are multiple optimization events. Based on the multiple optimization events, the corresponding weights of the optimization events, and the order of the winemaking process chain, the overall optimization logic of the multiple optimization events is determined, and the quality level of the wine is gradually improved.

[0140] In an embodiment of the present application, the grape picking batch is determined based on the wine model information and the wine database, and the grape picking season is determined based on the grape picking batch, grape picking records and environmental information of the grapes under dynamic picking, so as to accurately control the grape picking season.

[0141] At this time, the model information of the wine includes key information such as the winery name, wine series, grape variety, year, etc. This information is the basis for identifying specific wines and their production batches; the wine database is a database containing detailed records of the entire wine production process, including but not limited to grape picking batches, picking dates, grape varieties, yields, winery information, etc.; the database should be able to quickly retrieve the corresponding picking batches based on the model information.

[0142] By matching the wine model information with the records in the database, the grape picking batch corresponding to the wine model can be accurately found. This helps to track the source and picking time of the grapes, thereby understanding the maturity and flavor characteristics of the grapes.

[0143] In addition, grape picking records include picking date, picking quantity, grape maturity assessment, weather conditions at picking, etc.; picking records help to understand the growth of grapes and the environmental conditions at picking; the environmental information of grapes under dynamic picking refers to the real-time monitoring of environmental data during the picking process, such as temperature, humidity, light intensity, etc. These data can reflect the climatic conditions at the time of picking and have a direct impact on the quality of the grapes; combining the picking batches, picking records and environmental information, the grape picking season is inferred. The picking season is closely related to the growth cycle and climatic conditions of the grapes; for example, in the Northern Hemisphere, grapes are picked from late summer to early autumn; in the Southern Hemisphere, they are picked from late spring to early summer.

[0144] Specifically, suppose there is a Cabernet Sauvignon dry red wine from the Bordeaux region of France, model "Winery A 2020 Cabernet Sauvignon Dry Red"; in the wine database, the corresponding picking batch records are retrieved based on this information; assuming that the database shows that the grape picking batch of this model of wine is "September 15 to September 20, 2020, batch number B001", in this way, the grape picking batch of this wine is determined.

[0145] After determining that the picking batch was "September 15 to September 20, 2020, batch number B001", the picking records were further checked; the records showed that the weather during picking was sunny, the temperature was moderate, and the humidity was low, which was conducive to the ripening and preservation of grapes; at the same time, based on the environmental information under dynamic picking, it was learned that the average temperature during the picking period was 22°C, the average humidity was 60%, and the sunlight was sufficient. These conditions indicate that the grapes were picked under ideal seasonal conditions.

[0146] Combined with the climatic characteristics of the Bordeaux region (temperate maritime climate, warm and humid summers, cool and dry autumns), it can be inferred that the grapes for this Cabernet Sauvignon dry red wine were picked in autumn; specifically, the picking season is early autumn, around mid-September. The grapes picked in this season are more mature and have a rich flavor, making them suitable for making high-quality red wine.

[0147] Furthermore, multiple environmental parameters of the wine producing area are collected based on the matching of the wine producing area and the wine making time, and the environmental type of the wine producing area is determined based on the multiple environmental parameters of the wine producing area, thereby ensuring the accuracy of the environmental type of the wine producing area.

[0148] At this point, the wine's origin and winemaking time are collected. The wine's origin includes basic information such as the winery's geographical location, production area, longitude and latitude, and altitude. This information is the basis for identifying the characteristics of the wine's origin. Based on the wine's origin and winemaking time, it is necessary to collect multiple environmental parameters of the origin during that time period. These parameters include temperature, precipitation, light intensity, wind speed, soil type, soil moisture, pH value, etc. These parameters can fully reflect the climate and soil conditions of the origin and have a significant impact on the growth and brewing of wine.

[0149] After collecting the environmental parameters, they need to be analyzed and organized, which includes calculating statistical quantities such as mean, standard deviation, extreme value, and analyzing the correlation between parameters; formulating a set of environmental type standards based on the climate and soil characteristics of the wine producing area, these standards include temperature range, precipitation range, light intensity level, soil type classification, etc.; by comparing these standards with the collected environmental parameters, the environmental type of the producing area is determined; combining environmental parameter analysis and environmental type standards, the environmental type of the wine producing area is determined.

[0150] Specifically, suppose there is a Pinot Noir wine from the Burgundy region of France, which was produced from September 2021 to February 2022; in order to collect the environmental parameters of the Burgundy region during this period, the following operations are performed: daily temperature, precipitation, light intensity and other data in the Burgundy region from September 2021 to February 2022 are obtained from the meteorological station; soil type, soil moisture, pH value and other data of the main vineyards in the Burgundy region during this period are obtained from the soil testing laboratory; combined with satellite remote sensing data, the vegetation coverage, topography and other information of the Burgundy region during this period are analyzed; by integrating the above data sources, a set of environmental parameters of the Burgundy region from September 2021 to February 2022 is obtained.

[0151] After collecting environmental parameters in the Burgundy region from September 2021 to February 2022, the following analysis was conducted: In terms of temperature, the average temperature during this period was moderate, which is consistent with the characteristics of a temperate climate; in terms of precipitation, the precipitation was moderate and evenly distributed, which is conducive to the growth and ripening of grapes; in terms of light intensity, the light was sufficient but not too strong, which is conducive to the photosynthesis and accumulation of flavor substances in grapes; in terms of soil, the Burgundy region is mainly limestone soil, which is well-drained and rich in minerals, which is conducive to the growth of grape roots and the absorption of nutrients.

[0152] Based on the above analysis, it is determined that the environmental type in the Burgundy region from September 2021 to February 2022 is "temperate limestone soil climate", which is conducive to the growth of Pinot Noir grapes and the production of high-quality red wine.

[0153] Therefore, the optimization events are determined based on the interaction between the project to be optimized, the grape picking season, and the environmental type of the wine-producing area. At this time, there are multiple optimization events. Based on the multiple optimization events, the corresponding weights of the optimization events, and the order of the winemaking process chain, the overall optimization logic of the multiple optimization events is determined, and the quality level of the wine is gradually improved, thereby realizing the subsequent management and control of the optimization events and gradually improving the quality level of the wine.

[0154] At this point, the project to be optimized is a specific step or parameter in the winemaking process, such as fermentation temperature, maceration time, yeast type selection, oak barrel aging time, etc. These projects are identified through quality analysis, sensory evaluation or consumer feedback.

[0155] The grape picking season (e.g., spring, summer, autumn, etc.) and environmental type (e.g., temperate maritime climate, Mediterranean climate, continental climate, etc.) have a significant impact on wine quality. Grapes' maturity, flavor content, acidity, and other characteristics vary in different seasons and environments. Therefore, it's necessary to analyze the interactions between the optimization items and the picking season and environmental type to determine which factors need to be adjusted to optimize wine quality. Based on this analysis, specific optimization events are identified, including adjusting fermentation parameters, improving brewing techniques, and optimizing oak barrel selection.

[0156] Assign a weight to each optimization event based on its importance to improving wine quality; the weight reflects the relative importance of the event in the overall optimization process; the winemaking process chain is an orderly process, and each step depends on the result of the previous step; therefore, when determining the overall optimization logic, it is necessary to consider the order of the process chain to ensure that the implementation of the optimization event will not interfere with or disrupt the normal progress of other steps; combined with the weight of the optimization event and the order of the winemaking process chain, formulate a step-by-step optimization plan, which should clearly define the specific implementation steps, timetable and expected results of each optimization event.

[0157] Specifically, suppose that when analyzing a Syrah wine from the Rhône Valley in France, the following optimization issues are identified: excessively high fermentation temperature, resulting in an overly rich wine body; excessively long maceration time, resulting in excessive tannins; and excessively long oak barrel aging time, resulting in a strong oak flavor. Furthermore, it is known that the grapes for this wine were harvested in autumn, and the Rhône Valley has a Mediterranean climate with dry and sunny autumns.

[0158] Based on this information, the following optimization events were determined: lowering the fermentation temperature to reduce the fatness of the wine; shortening the maceration time to reduce the heavy tannins; and reducing the oak barrel aging time to reduce the oak flavor.

[0159] After determining the three optimization events mentioned above, assign weights to them; assuming that lowering the fermentation temperature is the most important optimization event (weight 0.5), followed by shortening the maceration time (weight 0.3), and finally reducing the oak barrel aging time (weight 0.2).

[0160] First, the fermentation parameters were adjusted, and the fermentation temperature was lowered to a more suitable range to reduce the fatness of the wine. Secondly, the maceration time during the skin stage was shortened to reduce the heavy tannins. This step needs to be carried out after fermentation because it depends on the characteristics of the fermentation products. Finally, the aging time in oak barrels was reduced to reduce the oak flavor. This step needs to be carried out after the skin maceration and fermentation are completed because it depends on the results of the first two steps. Through the gradual implementation of these optimization events, it is expected that the quality level of this Syrah wine will be improved, making it more balanced, elegant and in line with consumers' taste preferences.

[0161] In one embodiment of the present application, the interactive matching table:

[0162]

[0163] Based on the interaction matching table, optimization events for specific wine products can be quickly identified. For example, for a Syrah wine from the Rhône Valley region of France, harvested in autumn in a Mediterranean climate, the optimization events identified are "lowering the fermentation temperature to an appropriate range" and "changing to a yeast species suitable for low-temperature fermentation." Next, the order in which these optimization events are implemented is determined based on the winemaking process chain (e.g., harvesting → fermentation → maceration → aging).

[0164] In this embodiment, Figure 7 As shown, a wine origin traceability system is provided, including:

[0165] A parameter combination module 21 is used to determine a plurality of parameter combinations based on the identification of the wine test report;

[0166] A winemaking time module 22 is used to determine the winemaking time according to a combination of multiple parameters and the model information of the wine;

[0167] A wine origin module 23 is used to determine the origin of the wine based on the winemaking time, winemaking location and winemaking process chain;

[0168] The project to be optimized module 24 is used to determine the quality grade of the wine based on the wine test report, and determine the project to be optimized based on the quality grade of the wine, the origin of the wine, and the information set of each process in the winemaking process chain;

[0169] The optimization event module 25 is used to determine the optimization event according to the project to be optimized, the grape picking season and the environmental type of the wine producing area, and gradually improve the quality level of the wine.

[0170] In this embodiment, a device is provided. The device includes a processor, a memory, a network interface, a display screen, and an input device connected via a system bus. The processor of the device is used to provide computing and control capabilities. The memory of the device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program, and the non-volatile storage medium is deployed with a database, which is used to store user behavior data and user profiles. The internal memory provides an environment for the operation of the operating system and computer program in the non-volatile storage medium. The network interface of the device is used to communicate with other devices deployed with application software. When the computer program is executed by the processor, a method for tracing the origin of wine is implemented.

[0171] The above-described embodiments merely represent several implementation methods of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present invention. It should be noted that a person of ordinary skill in the art may make variations and improvements without departing from the spirit of the present application, and these variations and improvements fall within the scope of protection of the present application. Therefore, the scope of protection of the present patent application shall be determined by the appended claims.

Claims

1. A method for tracing the origin of wine, characterized in that: include: Determining a plurality of parameter combinations based on identification in a wine test report; Determining the winemaking time of the wine based on a combination of multiple parameters and wine model information; Determine the origin of the wine based on the winemaking time, winemaking location and winemaking process chain; Determine the quality grade of the wine based on the wine test report, and identify the items to be optimized based on the wine quality grade, wine origin, and information collection of each process in the winemaking process chain; Determine optimization events based on the project to be optimized, the grape picking season, and the environmental type of the wine producing area, and gradually improve the quality level of the wine.

2. The wine origin tracing method according to claim 1, characterized in that: The multiple parameter combinations are determined based on the identification of the wine test report, including: Based on the simultaneous testing of each batch of wine, a corresponding test report is determined, and multiple parameters are determined based on the identification of the test report, including pH value, taste level, color level and ingredient ratio; A plurality of parameter combinations are determined based on multiple interactions of the plurality of parameters, the price of the wine, and the year of the wine.

3. The wine origin tracing method according to claim 1, characterized in that: The method of determining the winemaking time of the wine based on a combination of multiple parameters and the model information of the wine includes: Collecting the label information of the wine, and determining the model information of the wine based on the recognition of the label information of the wine; Multiple features are determined based on the identification of multiple parameter combinations, and the winemaking time of the wine is determined based on the multiple features, the model information of the wine, and the winemaking time learning model. At this time, the multiple features and the model information of the wine are used as input parameters, and the winemaking time of the wine is output through the preset winemaking time learning model.

4. The wine origin tracing method according to claim 1, characterized in that: The determination of the origin of the wine based on the winemaking time, winemaking location and winemaking process chain includes: Collecting the logistics information of the wine, and triggering the primary traceability of the wine based on the wine model information and the wine logistics information, and determining the winemaking place based on the primary traceability of the wine; The wine-making environment of the corresponding wine is determined according to the wine-making records of the wine-making place and the model information of the wine, and the wine-making process chain of the wine is constructed according to the wine-making environment and the process information of the wine.

5. The wine origin tracing method according to claim 4, characterized in that: The determination of the origin of the wine based on the winemaking time, winemaking location and winemaking process chain also includes: The first origin range is determined according to the winemaking time and the winemaking location, the second origin range is determined according to the winemaking time and the winemaking process chain, and the wine origin is determined based on the first origin range, the second origin range and the wine model information.

6. The wine origin tracing method according to claim 1, characterized in that: If the quality grade of the wine is determined based on the wine test report, and the items to be optimized are determined based on the information set of the quality grade of the wine, the origin of the wine, and each process in the winemaking process chain, the following items are included: Collect wine test reports and determine multiple taste parameters, color parameters, flavor parameters and grape maturity based on the wine test reports; determining a first quality parameter based on a plurality of taste parameters, color parameters, flavor parameters, and grape maturity, determining a second quality parameter based on wine model information and corresponding sales records, and determining a quality grade of the wine based on the first quality parameter and the second quality parameter; Determine the information set of each process in the winemaking process chain based on the traceability of the winemaking process chain; The nodes to be optimized are determined based on the multiple interactions of the information sets of the quality grade of the wine, the origin of the wine, and each process in the winemaking process chain, and the projects to be optimized are determined based on the traceability of the nodes to be optimized.

7. The wine origin tracing method according to claim 1, characterized in that: The optimization events are determined based on the project to be optimized, the grape picking season, and the environmental type of the wine producing area, and the quality level of the wine is gradually improved, including: Determine the grape picking batch based on the wine model information and the wine database, and determine the grape picking season based on the grape picking batch, grape picking records, and environmental information of the grapes under dynamic picking; collecting a plurality of environmental parameters of the wine producing area based on the matching of the wine producing area and the wine making time, and determining the environmental type of the wine producing area according to the plurality of environmental parameters of the wine producing area; Optimization events are determined based on the interaction between the project to be optimized, the grape picking season, and the environmental type of the wine-producing area. At this time, there are multiple optimization events. Based on the multiple optimization events, their corresponding weights, and the order of the winemaking process chain, the overall optimization logic of the multiple optimization events is determined, and the quality level of the wine is gradually improved.

8. A wine origin traceability system, characterized by: The wine origin traceability system is applied to the wine origin traceability method according to any one of claims 1 to 7, and the wine origin traceability system includes: A parameter combination module, configured to determine a plurality of parameter combinations based on the identification of the wine test report; A winemaking time module is used to determine the winemaking time based on a combination of multiple parameters and wine model information; The wine origin module is used to determine the origin of wine based on the winemaking time, winemaking location and winemaking process chain; The project to be optimized module is used to determine the quality grade of the wine based on the wine test report, and to determine the project to be optimized based on the quality grade of the wine, the origin of the wine, and the information set of each process in the winemaking process chain; The optimization event module is used to determine optimization events based on the project to be optimized, the grape picking season, and the environmental type of the wine producing area, and gradually improve the quality level of the wine.

9. A device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images