Self-adaptive big data processing method and system

Abstract

The invention relates to the technical field of data processing, in particular to a self-adaptive big data processing method and system, and the method comprises the following steps: based on a big data platform, extracting sales data of tea leaves, combining quality standards of the tea leaves, analyzing the correlation between each quality standard and the sales data, and distributing a corresponding weight for each quality standard, and generating quality standard weight distribution information. According to the method, by extracting the tea sales data and analyzing the correlation between the tea sales data and the quality standards, the quality standards with low correlation are eliminated, so that the residual standards can reflect the tea quality more accurately, the data processing amount is reduced, the tea quality evaluation can be closer to reality, and the analysis of the tea quality evaluation and the storage environment change is combined, so that the tea quality evaluation accuracy is improved. The influence of the storage time period on the quality of the tea is predicted, scientific prediction is provided for keeping the quality of the tea in storage, and the tea is stored and sold under the optimal quality by adjusting storage environment parameters and optimizing storage conditions, so that the quality control and prediction of the tea are more efficient.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and particularly to an adaptive big data processing method and system. Background Art

[0002] The technical field of data processing involves methods and systems for storing, retrieving, transmitting, analyzing, and processing information data using computers and related hardware and software. This technical field encompasses data acquisition, storage, organization, management, as well as computing and analysis, with wide application scenarios including industries such as finance, healthcare, transportation, and manufacturing. The core objective is to enhance the efficiency and accuracy of data processing through algorithm optimization, computing architecture design, and resource management, thereby providing support for decision-making in complex problems.

[0003] Among them, the adaptive big data processing method is a method focused on enhancing the flexibility and efficiency of large-scale data processing. Its main purpose is to automatically adjust the processing strategy and resource allocation according to the dynamic changes in data scale, computing resources, and task priorities. By introducing an adaptive mechanism, this method can optimize resource utilization in a heterogeneous computing environment, reduce processing latency, and improve the processing ability for complex data tasks, and is applicable to scenarios that require real-time data processing and analysis under uncertain conditions.

[0004] Traditional processing methods have poor adaptability to heterogeneous computing resources and dynamic environmental changes. They are usually based on fixed algorithms and preset parameters, and the processing process lacks a real-time self-adjustment mechanism, resulting in the inability to effectively guarantee processing efficiency and accuracy in the face of complex and changing data scenarios. For example, in tea quality management and storage environment control, the existing technology fails to effectively combine quality assessment with real-time adjustment of environmental parameters for the long-term storage effect of tea. As a result, in large-scale data analysis, relying on a single fixed quality standard and an unchanging storage environment strategy, the processing method lacking an adaptive mechanism will lead to large quality assessment errors, thereby affecting the storage quality of the product and ultimately the sales and market performance. Another example is in the analysis of the relationship between sales data and tea quality standards. The existing technology fails to fully handle the correlation between various quality standards, resulting in inaccurate analysis results and the inability to accurately predict the sales impact, leading to incorrect decisions in market strategies and affecting the competitiveness of the product. Summary of the Invention

[0005] The purpose of the present invention is to solve the deficiencies existing in the prior art, and to propose an adaptive big data processing method and system.

[0006] To achieve the above objective, the present invention adopts the following technical solution: An adaptive big data processing method, comprising the following steps: S1: Based on the big data platform, extract the sales data of tea leaves. Combine with the quality standards of tea leaves, including color and luster, moisture content, tea polyphenol content, shape integrity, shape size, and process standards during processing. Analyze the correlation between each quality standard and the sales data, eliminate the quality standards with low correlation, and assign corresponding weights to each quality standard according to the correlation strength of the remaining quality standards to generate quality standard weight distribution information; S2: Based on the quality standard weight distribution information, call the quality parameter values of the current batch of tea leaves, including color and luster uniformity, moisture content percentage, tea polyphenol content mass fraction, shape integrity mean value, and process parameters. Evaluate the quality of the current batch of tea leaves according to the corresponding weights to obtain tea leaf quality evaluation information; S3: Based on the tea leaf quality evaluation information, extract the storage environment data of the tea leaves. Combine with the current tea leaf quality score, analyze the impact of storage time on the tea leaf quality, and predict the tea leaf quality in the target period under the current storage condition to obtain tea leaf quality prediction information; S4: Based on the tea leaf quality prediction information, retrieve the sales records of similar tea leaves, extract the quality data corresponding to the tea leaf sales records that reach the target sales volume, evaluate the deviation between the target quality and the predicted quality, and adjust the tea leaf storage environment parameters according to the deviation degree to obtain storage environment optimization information.

[0007] The improvement of the present invention is that the step of analyzing the correlation between each quality standard and the sales data is as follows: S111: Based on the big data platform, extract the sales data of tea leaves, including sales volume, total sales amount, and sales satisfaction. Eliminate abnormal data, clean and standardize the data to obtain sales data statistical information; S112: Based on the sales data statistical information, extract the tea leaf quality standards corresponding to each sales data, including color and luster, moisture content, tea polyphenol content, shape integrity, shape size, and processing process standards. Clean and standardize each quality standard data to obtain a quality standard data set; S113: Based on the sales data statistical information and the quality standard data set, conduct a correlation analysis on the sales data and the quality standard data. Through the formula: ; Calculate the correlation score to obtain the correlation evaluation result; Among them, is the correlation score between the quality standard and the sales data , is the value of the quality standard in the th record, is the th record of the sales data The value of is the quality standard of the average value, is the sales data of the average value, is the number of samples.

[0008] The improvement of the present invention is that the obtaining step of the quality standard weight distribution information is as follows: S121: Based on the correlation evaluation result, extract the correlation score of each quality standard for each sales data, through the formula: ; Calculate the total sales score of the quality standard; Among them, is the quality standard of the total sales score, is the quality standard and the sales data the correlation score between, is the sales data of the importance weight, is the total number of sales data; S122: Based on the total sales score of the quality standard, compare it with a preset score threshold, and eliminate the quality standards with scores lower than the preset score threshold to obtain the quality standard screening result; S123: Based on the quality standard screening result, through the formula: ; Calculate the normalized weight of the quality standard, assign corresponding weights to each quality standard, and obtain the quality standard weight distribution information; Among them, is the quality standard of the normalized weight, is the quality standard of the total sales score, is the total number of screened quality standards.

[0009] The improvement of the present invention is that the obtaining step of the tea quality evaluation information is as follows: S211: Based on the detection data of the current batch of tea, extract the quality parameter values of the current batch of tea, including the color uniformity degree, moisture content percentage, mass fraction of tea polyphenols, average value of the shape integrity, and process parameters, to obtain the quality standard parameter value set; S212: Based on the quality standard parameter value set and the quality standard weight distribution information, through the formula: ; Calculate the quality score of the current batch of tea to obtain tea quality assessment information; Among them, is the quality score of the current batch of tea, is the normalization weight of the quality standard , is the quality standard corresponding parameter value, is the total number of quality standards after screening.

[0010] The improvement of the present invention is that the steps for obtaining the tea quality prediction information are: S311: Based on the tea quality assessment information, collect the storage environment data of the current batch of tea, including the temperature, humidity, and light intensity change values of the storage environment, to obtain a tea quality change correlation data set; S312: Based on the tea quality change correlation data set, analyze the tea quality change over a period of time through the formula: ; Calculate the quality change rate; Among them, is the quality change rate, is the tea quality score at the end of the storage period, is the tea quality score at the beginning of the storage period, is the time point at the end of the storage period, is the time point at the beginning of the storage period; S313: Based on the quality change rate, according to the duration from the current time to the target period, through the formula: ; Calculate the predicted quality score to obtain tea quality prediction information; Among them, is the quality change rate, is the current tea quality score, is the duration from the current time to the target period, is the attenuation coefficient, is the base of the natural logarithm.

[0011] The improvement of the present invention is that the steps for evaluating the deviation between the target quality and the predicted quality are: S411: Based on the tea quality prediction information, according to the target sales volume of the tea, retrieve the sales records of the same type of tea, and extract the average quality score corresponding to the tea sales records that reach the target sales volume to obtain the target quality score extraction result; S412: Based on the target quality score extraction result, through the formula: ; Calculate the deviation index between the target quality and the predicted quality; Wherein, is the deviation index between the target quality and the predicted quality, is the target quality score of the tea, is the predicted quality score of the tea; S413: Based on the deviation index between the target quality and the predicted quality, evaluate the degree of quality deviation according to the magnitude of the deviation index, and obtain the quality deviation evaluation result.

[0012] The improvement of the present invention is that the step of obtaining the storage environment optimization information is as follows: S421: Based on the quality deviation evaluation result, extract the current storage environment parameters and theoretical optimal storage parameters of the tea, including temperature, humidity and light intensity, to obtain environment-related data; S422: Based on the environment-related data, through the formula: ; Calculate the adjusted storage environment parameters; Wherein, is the adjusted storage environment parameter, is the current storage environment parameter, is the theoretical optimal storage environment parameter, is the adjustment coefficient, is the deviation index between the target quality and the predicted quality; S423: Based on the adjusted storage environment parameters, adjust the tea storage environment to obtain the storage environment optimization information.

[0013] An adaptive big data processing system, which is used to execute the above-mentioned adaptive big data processing method, and the system includes: The quality standard analysis module extracts the sales data of the tea based on the big data platform, combines the quality standards of the tea, analyzes the correlation between each quality standard and the sales data, eliminates the quality standards with low correlation, and assigns corresponding weights to each quality standard according to the correlation strength of the remaining quality standards to generate quality standard weight distribution information; The batch quality evaluation module evaluates the quality of the current batch of tea according to the corresponding weights by calling the quality parameter values of the current batch of tea based on the quality standard weight distribution information to obtain tea quality evaluation information; The storage quality prediction module extracts the storage environment data of the tea based on the tea quality evaluation information, combines the current tea quality score, analyzes the influence of storage time on the tea quality, and predicts the tea quality in the target period under the current storage condition to obtain tea quality prediction information; Based on the tea quality prediction information, the stored data adjustment module retrieves the sales records of similar teas, extracts the quality data corresponding to the tea sales records that reach the target sales volume, evaluates the deviation between the target quality and the predicted quality, and adjusts the tea storage environment parameters according to the degree of deviation to obtain storage environment optimization information.

[0014] Compared with the prior art, the advantages and positive effects of the present invention are as follows: In the present invention, by extracting tea sales data and performing correlation analysis with quality standards, the quality standards with low correlation are eliminated, so that the remaining standards can more accurately reflect the tea quality and reduce the data processing volume. Through normalization processing and weight assignment, the evaluation of quality standards is quantified and refined, making the tea quality evaluation closer to the actual situation and improving the accuracy of the evaluation. By combining the analysis of tea quality evaluation and changes in the storage environment, the impact of the storage time period on tea quality is predicted, providing a scientific prediction for maintaining the quality of tea during storage. By adjusting the storage environment parameters and optimizing the storage conditions, it is ensured that the tea is stored and sold under the best quality. By considering multiple variables and factors, more accurate and flexible decision support can be provided. Through dynamic adjustment, the quality guarantee ability under uncertain conditions is improved, especially in the environment of big data and dynamic changes, making the tea quality control and prediction more efficient and reducing the risk of quality decline caused by improper storage conditions. Description of the Drawings

[0015] Figure 1 is the flowchart of the method of the present invention; Figure 2 is the flowchart of analyzing the correlation between each quality standard and sales data of the present invention; Figure 3 is the flowchart of obtaining the weight distribution information of quality standards of the present invention; Figure 4 is the flowchart of obtaining tea quality evaluation information of the present invention; Figure 5 is the flowchart of obtaining tea quality prediction information of the present invention; Figure 6 is the flowchart of evaluating the deviation between the target quality and the predicted quality of the present invention; Figure 7 is the flowchart of obtaining storage environment optimization information of the present invention. Detailed Embodiments

[0016] In order to make the objectives, technical solutions and advantages of the present invention clearer, the present invention will be further described in detail below with reference to the drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0017] In the description of the present invention, it should be understood that the orientation or positional relationship indicated by the terms "length", "width", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", etc. is based on the orientation or positional relationship shown in the drawings. It is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be construed as a limitation to the present invention. In addition, in the description of the present invention, the meaning of "a plurality of" is two or more, unless otherwise specifically defined.

[0018] Please refer to Figure 1 , the present invention provides a technical solution: an adaptive big data processing method, including the following steps: S1: Based on the big data platform, extract the sales data of tea, including the sales volume, total sales amount, and sales satisfaction. Combine the quality standards of tea, including color and luster, moisture content, tea polyphenol content, shape integrity, shape size, and process standards during processing, analyze the correlation between each quality standard and the sales data, eliminate the quality standards with low correlation, and according to the correlation strength of the remaining quality standards, through normalization processing, assign corresponding weights to each quality standard to generate quality standard weight distribution information; S2: Based on the quality standard weight distribution information, call the quality parameter values of the current batch of tea, including the color and luster uniformity degree, moisture content percentage, tea polyphenol content mass fraction, shape integrity average value, and process parameters, and evaluate the quality of the current batch of tea according to the corresponding weights to obtain tea quality evaluation information; S3: Based on the tea quality evaluation information, extract the storage environment data of tea, including the temperature, humidity, and light intensity change value of the storage environment. Combine the current tea quality score, analyze the influence of storage time on tea quality, predict the tea quality in the target period under the current storage condition to obtain tea quality prediction information; S4: Based on the tea quality prediction information, retrieve the sales records of similar tea, extract the quality data corresponding to the tea sales records that reach the target sales volume, evaluate the deviation between the target quality and the predicted quality, and according to the degree of deviation, adjust the tea storage environment parameters, including storage temperature, humidity, and light intensity, to obtain storage environment optimization information.

[0019] The quality standard weight distribution information includes color and luster weight, moisture content weight, tea polyphenol content weight, shape weight, and process weight. The tea quality evaluation information includes each weighted score, quality sub-item score ratio, and overall evaluation score. The tea quality prediction information includes trend fluctuation amplitude, trend change value within a time period, and trend fitting error. The storage environment optimization information includes environmental temperature adjustment value, environmental humidity adjustment value, and light intensity adjustment value.

[0020] Please refer toFigure 2 ,The steps to analyze the correlation between each quality standard and sales data are: S111: Based on the big data platform, extract the sales data of tea, including sales volume, total sales and sales satisfaction, remove abnormal data, clean and standardize the data, and obtain sales data statistical information; Collect tea sales data, including sales volume, total sales, and sales satisfaction. Sales volume refers to the total number of a certain tea product sold in a specific period of time. Total sales refers to the product of sales volume and unit price, that is, the total amount of all tea sold. Sales satisfaction is usually reflected by customer ratings, which come from customer evaluation systems, such as a 1 to 5 star rating system. Next, perform outlier detection on the data. Outliers can be identified by simple statistical methods, and values that are too high or too low can be eliminated. For example, if sales suddenly increase to values outside the normal range, it may be a data entry error. Clean the data, that is, remove duplicate records or fix erroneous values. Use standardization methods, such as Z-Score standardization or Min-Max standardization, so that the data is at the same level, and get sorted sales data statistics to prepare for subsequent analysis.

[0021] S112: Based on the sales data statistical information, extract the tea quality standard corresponding to each sales data, including color, moisture content, tea polyphenol content, shape integrity, shape size and processing technology standards, clean and standardize each quality standard data, and obtain a quality standard data set; According to the sales data statistics, the corresponding tea quality standards are extracted. Quality standards usually include the color of tea (for example, the color of tea ranges from green to dark green), moisture content (percentage, indicating the water content in tea), tea polyphenol content (usually expressed as a percentage, as an indicator of the antioxidant properties of tea), appearance integrity (whether there are fragments or damage), appearance size (the average length and width of tea), and processing technology standards (such as baking temperature, fermentation time, etc.). The data comes from laboratory tests of tea or quality reports provided by suppliers. For each quality standard data, clean it to ensure that there is no missing data or entry errors. Standardization is used to make different quality indicators comparable. For example, Z-Score standardization can be used to adjust each quality standard so that its mean is 0 and its standard deviation is 1. The process ensures the comparability of quality data and provides a standardized data set for subsequent correlation analysis.

[0022] S113: Based on the sales data statistical information and the quality standard data set, the sales data and the quality standard data are subjected to correlation analysis, using the formula: ; Calculate the correlation score and obtain the correlation evaluation result; Among them, is the quality standard and the correlation score with the sales data, is the value of the quality standard in the th record, is the value of the sales data in the th record, is the average value of the quality standard , is the average value of the sales data , is the number of samples.

[0023] Formula: ; The advantage of the formula is that by using this correlation calculation formula, the relationship between the tea quality standard and the sales data can be clarified, providing a quantitative basis for optimizing tea quality or improving sales strategies.

[0024] Detailed explanation of the formula and the derivation process of the formula calculation: : Represents the correlation score between the quality standard and the sales data . The value ranges from -1 to 1, indicating the strength and direction of the correlation between the two. : Represents the value of the quality standard in the th record, usually a specific value of a quality indicator, such as color, moisture content, etc. : Represents the value of the sales data in the th record, usually data such as sales volume, total sales, or sales satisfaction. : Is the average value of the quality standard ; : Is the average value of the sales data , and the calculation formula is: ; : Represents the number of samples.

[0025] For example, there are 3 records, and the values of the quality standard are: Color: ; Moisture content: ; Calculate the average value of each indicator: ; ; Molecular part: ; Calculate each term: For : ; For : ; For : ; The molecular part is: ; Denominator part: ; ; ; Substitute the above results into the formula: ; Correlation score is 0.951, which indicates a high positive correlation between the quality standard and the sales data. The calculated score results show that there is a certain correlation between the quality standard of tea and the sales data, and the sales strategy or quality control can be optimized through this correlation score.

[0026] Please refer to Figure 3 , the steps for obtaining the quality standard weight distribution information are: S121: Based on the correlation evaluation results, extract the correlation scores of each quality standard for each sales data through the formula: ; Calculate the total sales score of the quality standard; Among them, is the total sales score of the quality standard , is the correlation score between the quality standard and the sales data , is the importance weight of the sales data , is the total number of sales data; Formula: ; The advantage of the formula is that through this formula, the importance weights of sales data can be combined to calculate the comprehensive correlation score between each quality standard and various sales data, thereby providing a quantitative basis for quality standard evaluation.

[0027] Detailed explanation of the formula and the derivation process of formula calculation: : Represents the total sales score of quality standard , which is the comprehensive evaluation result of this quality standard and all sales data. : For quality standard and sales data The correlation score between them has been calculated in the aforementioned correlation analysis. : For sales data The importance weight of, usually set according to the type of sales data, its contribution to the final sales result, and the market analysis result. : Represents the total number of sales data, that is, the number of all sales data items considered.

[0028] For example, assume there are three sales data items (sales volume, sales amount, and sales satisfaction), and the weights of each data are , and , the correlation score , , and , can be substituted into the formula for calculation: ; This result indicates that the total sales score of quality standard is 0.7. This score can help identify which quality standards are most critical for improving sales data, thereby providing guidance for quality control and adjustment of sales strategies.

[0029] S122: Based on the total sales score of the quality standard, compare it with a preset score threshold, eliminate the quality standards with scores lower than the preset score threshold, and obtain the quality standard screening result; Based on the total sales score of the quality standard, set a preset score threshold. For example, the score threshold can be set to 0.6, which means that any quality standard with a total sales score lower than 0.6 will be regarded as unimportant and eliminated from the screening result. Then, compare the total sales score of each quality standard with this threshold to determine whether it meets the standard. For example, if the quality standard is greater than the threshold 0.6, it is retained; if the quality standard If it is less than the threshold of 0.6, it will be eliminated. Through this process, quality standards that have a significant impact on sales can be screened out. By comparing the scores of each quality standard with the threshold, a screening result is obtained, retaining the quality standards with scores higher than the preset threshold and eliminating those below the threshold, thus ensuring that only the quality standards with a greater impact on sales are focused on in the subsequent steps.

[0030] S123: Based on the screening result of quality standards, through the formula: ; Calculate the normalized weight of the quality standards, assign corresponding weights to each quality standard, and obtain the quality standard weight distribution information; Among them, is the normalized weight of the quality standard , is the total sales score of the quality standard , is the total number of screened quality standards; Formula: ; The advantage of the formula is that it can standardize the sales scores of each quality standard, making the scores of different quality standards comparable, thus providing a basis for weight assignment and further decision-making.

[0031] Detailed explanation of the formula and the derivation process of the formula calculation: : Represents the normalized weight of the quality standard , which is the ratio of this quality standard to all screened quality standards, : Is the total sales score of the quality standard , which has been calculated in the previous steps, : Represents the sum of the total sales scores of all screened quality standards, is the number of screened quality standards.

[0032] Suppose the number of screened quality standards is 3, and their corresponding total sales scores are: , , .

[0033] Calculate the sum of the total sales scores of all screened quality standards: ; Calculate the normalized weight of each quality standard: ; ; ; The normalized weights indicate that among the selected quality criteria, quality criterion has the greatest impact on sales, with a weight of 0.38, while quality criterion has the least impact, with a weight of 0.29. The steps help to assign relative weights to each quality criterion.

[0034] Please refer to Figure 4 for the steps to obtain tea quality assessment information: S211: Based on the test data of the current batch of tea, extract the quality parameter values of the current batch of tea, including color uniformity, moisture content percentage, mass fraction of tea polyphenol content, mean value of shape integrity, and process parameters, to obtain a set of quality standard parameter values; Based on the test data of the current batch of tea, extract the key quality parameters from the test data of the tea. The color uniformity can be quantified through visual inspection of the tea, usually scored according to the uniformity of the tea color. For example, through color difference analysis, the smaller the color difference value, the higher the uniformity. The moisture content percentage refers to the proportion of water in the tea, and the data is usually obtained through the drying method, that is, by heating the sample to a constant weight and calculating the percentage of water loss. The mass fraction of tea polyphenol content is the proportion of the mass of tea polyphenols in the total mass of the tea, and the data is usually determined by high-performance liquid chromatography. The mean value of shape integrity is evaluated through visual inspection to assess the integrity of the tea. Missing or damaged tea will be considered incomplete, and the shape integrity of the tea can be quantitatively analyzed through image processing technology. The process parameters include the processing temperature, humidity, fermentation time, etc. of the tea. The parameters are usually recorded in real time by tea production equipment or obtained through laboratory test analysis. Each parameter value is obtained through scientific instruments or laboratory methods and is appropriately standardized to ensure that the parameters are compared on the same order of magnitude. Integrate the parameter values into a set of quality standard parameter values to provide basic data for the calculation of subsequent quality scores.

[0035] S212: Based on the set of quality standard parameter values and the quality standard weight distribution information, through the formula: ; Calculate the quality score of the current batch of tea to obtain tea quality assessment information; where is the quality score of the current batch of tea, is the normalized weight of quality criterion , is the quality criterion corresponding parameter value, is the total number of selected quality criteria; Formula: ; The benefit of the formula is that through the formula, the normalized weight of each quality standard can be combined with its corresponding parameter value to obtain the comprehensive quality score of the current batch of tea, reflecting the comprehensive impact of different quality standards on the tea quality.

[0036] Detailed explanation of the formula and the derivation process of formula calculation: : Represents the quality score of the current batch of tea, which is a comprehensive index reflecting the overall quality of the current tea. : Is the quality standard The normalized weight of indicates the importance of this quality standard in the tea quality score. The normalized weight ensures that the influence degrees of different quality standards on the final score are relatively fair, and that the weight of a certain standard will not be too large. : Is the quality standard The corresponding parameter value of comes from the set of quality standard parameter values extracted above, such as the degree of color and luster uniformity, moisture content, tea polyphenol content, etc. : Is the total number of quality standards after screening, indicating the number of quality standards participating in the score calculation.

[0037] Suppose there are three quality standards after screening for the current batch of tea (degree of color and luster uniformity, moisture content, and tea polyphenol content), and their corresponding normalized weights are respectively , , , and the parameter values of each quality standard are respectively , , .

[0038] By substituting into the formula for calculation:

[0039] The result shows that the quality score of the current batch of tea is 6.24. Combining this score, the tea quality can be evaluated and compared with the preset quality standards to determine whether it meets the market requirements.

[0040] Please refer to Figure 5 , the steps for obtaining tea quality prediction information are as follows: S311: Based on the tea quality assessment information, collect the storage environment data of the current batch of tea, including the temperature, humidity, and light intensity change values of the storage environment, to obtain the tea quality change correlation dataset; Based on the tea quality assessment information, collect the storage environment data of the current batch of tea. The data includes the change values of temperature, humidity, and light intensity. Temperature and humidity are usually obtained through environmental monitoring devices. Temperature is in degrees Celsius, and humidity is expressed as a percentage of relative humidity. Light intensity can be measured by a light sensor and is usually in Lux. The environmental data needs to be collected in real-time and sorted. The change value of temperature is usually obtained by comparing the historical record of the storage environment with the current record. For example, if the current temperature is 25°C and the historical record temperature is 22°C, then the temperature change value is 3°C. The same calculation method is used for the humidity change value and the light change value. Combine the data with the aforementioned tea quality assessment information (such as color uniformity, moisture content, etc.) to obtain a tea quality change correlation data set, which will be used for subsequent quality change analysis to help determine the impact of the storage environment on tea quality.

[0041] S312: Based on the tea quality change correlation data set, analyze the tea quality change over a period of time through the formula: ; Calculate the quality change rate; Where, is the quality change rate, is the tea quality score at the end of the storage period, is the tea quality score at the start of the storage period, is the time point at the end of the storage period, is the time point at the start of the storage period; Formula: ; The benefit of the formula is that by calculating the quality change rate , it can quantify the change in tea quality during storage, thus providing a basis for tea quality prediction and optimization.

[0042] Detailed explanation of the formula and the formula calculation derivation process: : is the quality change rate, indicating the rate at which tea quality changes over time, with the unit of score unit / hour. : is the tea quality score at the end of the storage period, which is the score of tea quality at the end of the storage period. : is the tea quality score at the start of the storage period, which is the score of tea quality at the start of the storage period. : is the time point at the end of the storage period, usually a timestamp in hours. : is the time point at the start of the storage period, usually also a timestamp in hours.

[0043] For example, assume that the storage period starts from January and ends in the fifth month, and the quality score changes from 5 (at the start) to 3 (at the end). Then: Month; The results show that the quality score of the tea decreases at a rate of -0.5 score per hour within these 4 hours, indicating that the storage environment may have a negative impact on the tea quality.

[0044] S313: Based on the quality change rate, according to the duration from the current time to the target period, through the formula: ; Calculate the predicted quality score to obtain the tea quality prediction information; Where, is the quality change rate, is the current tea quality score, is the duration from the current time to the target period, is the attenuation coefficient, is the base of the natural logarithm; Formula: ; The advantage of the formula is that by combining factors such as the current quality score, quality change rate, and time decay factor, it predicts the tea quality at a future target period, thus providing a scientific basis for tea storage management.

[0045] Detailed explanation of the formula and the derivation process of the formula calculation: : is the predicted quality score, representing the future quality score calculated based on the current tea quality and the prediction model. : is the current tea quality score, which is the score of the tea quality at the current time point. : is the quality change rate, which is the rate of quality change per unit time calculated according to the previous formula. : is the duration from the current time to the target period, representing the time difference from the current time point to the target period, usually in hours. : is the attenuation coefficient, reflecting the attenuation speed of the tea quality change over time. : is the base of the natural logarithm, often used to handle attenuation or growth models.

[0046] For example, assume that the current tea quality score is 4, the quality change rate is -0.5 score unit / month, the target period is 10 months away from the current time, and the attenuation coefficient is 0.1. Then: ; The result shows that after 10 months, the predicted quality score of the tea is 2.16, indicating that the tea quality will further decline and corresponding storage management measures need to be taken to slow down the rate of quality decline.

[0047] Please refer to Figure 6 , and the steps to evaluate the deviation between the target quality and the predicted quality are as follows: S411: Based on the tea quality prediction information, according to the target sales volume of the tea, retrieve the sales records of similar teas, extract the average quality score corresponding to the tea sales records that reach the target sales volume, and obtain the target quality score extraction result; Based on the tea quality prediction information, filter out the sales records of similar teas with the same target sales volume according to the target sales volume of the tea. The records can be retrieved from the sales database and usually include the specific sales information, sales volume, and quality score of the tea. By calculating the average value of the quality scores of the sales records, the target quality score is obtained. The process involves summarizing the quality scores of each record and using the formula for calculating the average value for calculation, providing a benchmark for subsequent quality deviation analysis.

[0048] S412: Based on the target quality score extraction result, through the formula: ; Calculate the deviation index between the target quality and the predicted quality; Among them, is the deviation index between the target quality and the predicted quality, is the target quality score of the tea, is the predicted quality score of the tea; Formula: ; The benefit of the formula is that by calculating the deviation index between the target quality and the predicted quality, the deviation between the actual quality and the expected quality can be quantified, providing a basis for quality adjustment and strategy optimization.

[0049] Detailed explanation of the formula and the derivation process of the formula calculation: : is the deviation index between the target quality and the predicted quality, representing the relative difference between the target quality and the predicted quality, and is usually used to evaluate the prediction accuracy. : is the target quality score of the tea, which is the tea quality target set based on market demand, standards, or other factors. : is the predicted quality score of the tea, which comes from the calculation result of the aforementioned tea quality prediction method.

[0050] For example, assume that the target quality score of the tea is 8.0 ( ) and the predicted quality score is 7.5 ( ), the calculation deviation index is as follows: ; The result shows that there is a deviation of approximately 6.25% between the target quality and the predicted quality.

[0051] S413: Based on the deviation index between the target quality and the predicted quality, evaluate the degree of quality deviation according to the magnitude of the deviation index to obtain the quality deviation evaluation result; According to the calculated deviation index to evaluate the degree of quality deviation. The magnitude of the deviation index directly reflects the gap between the actual tea quality and the target quality. Generally, a smaller deviation index value indicates more accurate quality prediction, while a larger deviation index indicates that quality control measures need to be optimized. To evaluate the deviation index, a reasonable standard range needs to be set. For example, if , it is considered that the quality deviation is small and the quality control is good; if , the deviation is large and the links such as storage and transportation need to be optimized; if , it is considered that the quality deviation is significant. Through this method, the quality deviation can be flexibly evaluated according to the magnitude of the deviation index, and then corresponding quality improvement measures can be taken. For example, in the previous calculation, the obtained deviation index is 0.0625, which belongs to medium deviation (between 0.05 and 0.10), so some links in the storage process need to be optimized to reduce future quality deviation.

[0052] Please refer to Figure 7 , the steps for obtaining the storage environment optimization information are as follows: S421: Based on the quality deviation evaluation result, extract the current storage environment parameters and theoretical optimal storage parameters of the tea, including temperature, humidity, and light intensity, to obtain the environment-related data; According to the quality deviation assessment results, it is necessary to pay attention to the current storage environment parameters of the tea. The temperature, humidity, and light intensity of the current storage environment are usually obtained through an environmental monitoring system. The temperature is generally monitored using a temperature sensor, with the unit being degrees Celsius; the humidity is measured through a humidity sensor, in relative humidity percentage; the light intensity can be measured through a light sensor, in lux. After recording the environmental data, it is necessary to obtain the theoretical optimal storage environment parameters, which usually come from the research on the optimal storage conditions of tea or historical experience. For example, a certain type of tea may achieve the best quality under the conditions of a temperature of 30°C, a humidity of 70%, and a light intensity of 300 Lux. Compare the actual data of the current storage environment with the theoretical values of the optimal storage environment to determine whether the storage conditions need to be adjusted. If some parameters of the current storage environment (such as temperature, humidity, or light intensity) deviate from the range of the theoretical optimal storage conditions, it may lead to a decline in the quality of the tea, which can provide the necessary data support for subsequent adjustment of the storage environment.

[0053] S422: Based on the environment-related data, through the formula: ; Calculate the adjusted storage environment parameters; Where, is the adjusted storage environment parameter, is the current storage environment parameter, is the theoretical optimal storage environment parameter, is the adjustment coefficient, is the deviation index between the target quality and the predicted quality; Formula: ; The advantage of the formula is that through this formula, the storage environment parameters can be dynamically adjusted according to the deviation index between the target quality and the predicted quality, so as to optimize the storage conditions of the tea and achieve the purpose of improving the quality of the tea.

[0054] Detailed explanation of the formula and the derivation process of the formula calculation: : is the adjusted storage environment parameter, representing the value of the storage condition after adjustment, used to optimize the tea storage environment. : is the current storage environment parameter, representing the actually monitored storage environment parameters. : is the theoretical optimal storage environment parameter, representing the ideal value of the best storage conditions, usually obtained from experiments or historical data. : is the adjustment coefficient, representing the sensitivity of the adjustment, usually set through experiments or optimization algorithms to control the adjustment amplitude. : is the deviation index between the target quality and the predicted quality, representing the relative difference between the actual quality and the expected target quality.

[0055] For example, assume the current storage temperature is 28°C ( ), the theoretical optimal temperature is 30°C ( ), the quality deviation index is 0.0625 ( ), and the adjustment coefficient is 0.5 ( ). Then, we can substitute these values into the formula to calculate the adjusted storage temperature: ; The result shows that after adjustment, the temperature of the storage environment should be 28.0625°C, which is close to the theoretical optimal temperature, thus helping to improve the quality of the tea.

[0056] S423: Based on the adjusted storage environment parameters, adjust the tea storage environment to obtain storage environment optimization information; After adjusting the storage environment parameters, actually perform the adjustment operation. According to the previously calculated adjusted storage environment parameters (such as temperature, humidity, and light intensity), adjust the settings of the storage equipment. For example, if the storage temperature obtained through the adjustment formula is 28.0625°C, but the current setting of the equipment is 27°C, then the temperature control equipment needs to be adjusted to 28.0625°C; if the humidity is too high, then the dehumidification equipment needs to be turned on or the environmental air circulation needs to be adjusted; if the light intensity is too strong, then the light intensity needs to be reduced to ensure that the tea is in an ideal storage environment. The adjustments should be precisely made based on the monitoring equipment of the storage environment. The result of optimizing the storage environment is to achieve refined management of the tea storage environment through the coordinated work of multiple sensors and equipment, ensuring that the tea is stored under the best conditions and minimizing the risk of quality decline.

[0057] An adaptive big data processing system, which is used to execute the above-mentioned adaptive big data processing method. The system includes: The quality standard analysis module, based on the big data platform, extracts the sales data of the tea, combines with the quality standards of the tea, analyzes the correlation between each quality standard and the sales data, eliminates the quality standards with low correlation, and assigns corresponding weights to each quality standard through normalization processing according to the correlation strength of the remaining quality standards, generating quality standard weight distribution information; The batch quality evaluation module, based on the quality standard weight distribution information, calls the quality parameter values of the current batch of tea, and evaluates the quality of the current batch of tea according to the corresponding weights to obtain tea quality evaluation information; The storage quality prediction module, based on the tea quality evaluation information, extracts the storage environment data of the tea, combines with the current tea quality score, analyzes the impact of storage time on the tea quality, and predicts the tea quality in the target period under the current storage condition to obtain tea quality prediction information; Based on the tea quality prediction information, the stored data adjustment module retrieves the sales records of similar teas, extracts the quality data corresponding to the tea sales records that reach the target sales volume, evaluates the deviation between the target quality and the predicted quality, and adjusts the tea storage environment parameters according to the degree of deviation to obtain the storage environment optimization information.

[0058] The above are only the preferred embodiments of the present invention, and are not intended to limit the present invention in other forms. Any person skilled in the art may use the technical content disclosed above to make changes or modifications into equivalent embodiments with equivalent changes and apply them to other fields. However, as long as the content of the technical solution of the present invention is not departed from, any simple modification, equivalent change and modification made to the above embodiments based on the technical essence of the present invention still fall within the protection scope of the technical solution of the present invention.

Claims

1. An adaptive big data processing method, characterized in that, It includes the following steps: S1: Based on the big data platform, extract the sales data of tea leaves, and combine with the quality standards of tea leaves, including color, moisture content, tea polyphenol content, shape integrity, shape size, and process standards in processing. Analyze the correlation between each quality standard and the sales data, eliminate the quality standards with low correlation, and assign corresponding weights to each quality standard according to the correlation strength of the remaining quality standards to generate quality standard weight distribution information; S2: Based on the quality standard weight distribution information, call the quality parameter values of the current batch of tea leaves, including color uniformity, moisture content percentage, tea polyphenol content mass fraction, shape integrity mean value, and process parameters, and evaluate the quality of the current batch of tea leaves according to the corresponding weights to obtain tea leaf quality evaluation information; S3: Based on the tea leaf quality evaluation information, extract the storage environment data of the tea leaves, combine with the current tea leaf quality score, analyze the influence of storage time on the tea leaf quality, and predict the tea leaf quality at the target time period under the current storage condition to obtain tea leaf quality prediction information; S4: Based on the tea leaf quality prediction information, retrieve the sales records of the same type of tea leaves, extract the quality data corresponding to the tea leaf sales records that reach the target sales volume, evaluate the deviation between the target quality and the predicted quality, and adjust the tea leaf storage environment parameters according to the deviation degree to obtain storage environment optimization information.

2. The adaptive big data processing method according to claim 1, wherein The step of analyzing the correlation between each quality standard and the sales data is as follows: S111: Based on the big data platform, extract the sales data of tea leaves, including sales volume, total sales amount, and sales satisfaction, eliminate abnormal data, and perform cleaning and standardization processing on the data to obtain sales data statistical information; S112: Based on the sales data statistical information, extract the tea leaf quality standards corresponding to each sales data, including color, moisture content, tea polyphenol content, shape integrity, shape size, and processing technology standards, and perform cleaning and standardization processing on each quality standard data to obtain a quality standard data set; S113: Based on the sales data statistical information and the quality standard data set, perform a correlation analysis on the sales data and the quality standard data through the formula: ； Calculate the correlation score to obtain the correlation evaluation result; Among them, is the quality standard and the correlation score with the sales data, is the value of the quality standard in the th record, is the value of the sales data in the th record, is the sample size.

3. The adaptive big data processing method according to claim 2, wherein The step of obtaining the quality standard weight distribution information is as follows: S121: Based on the correlation evaluation result, extract the correlation score of each quality standard for each sales data through the formula: ； Calculate the total sales score of the quality standard; Among them, is the total sales score for the quality standard , is the correlation score between the quality standard and the sales data , is the importance weight of the sales data , is the total number of sales data; S122: Based on the total sales score of the quality standard, compare it with the preset score threshold, and eliminate the quality standards with scores lower than the preset score threshold to obtain the quality standard screening result; S123: Based on the quality standard screening result, through the formula: ； Calculate the normalized weight of the quality standard, assign corresponding weights to each quality standard, and obtain the quality standard weight distribution information; Among them, is the normalization weight of the quality standard , is the total sales score of the quality standard , is the total number of quality standards after screening.

4. The adaptive big data processing method according to claim 1, characterized in that The step of obtaining the tea leaf quality evaluation information is as follows: S211: Based on the detection data of the current batch of tea leaves, extract the quality parameter values of the current batch of tea leaves, including color uniformity, moisture content percentage, tea polyphenol content mass fraction, shape integrity mean value, and process parameters, to obtain a quality standard parameter value set; S212: Based on the set of quality standard parameter values and the quality standard weight distribution information, through the formula: ； Calculate the quality score of the current batch of tea leaves to obtain tea leaf quality evaluation information; Among them, is the quality score of the current batch of tea, is the quality standard of the normalized weight, is the quality standard corresponding parameter value, is the total number of quality standards after screening.

5. The adaptive big data processing method according to claim 1, wherein The steps for obtaining the tea leaf quality prediction information are as follows: S311: Based on the tea leaf quality evaluation information, collect the storage environment data of the current batch of tea leaves, including the temperature, humidity, and light intensity change values of the storage environment, to obtain a tea leaf quality change correlation data set; S312: Based on the tea leaf quality change correlation data set, analyze the tea leaf quality change over a period of time, through the formula: ； Calculate the quality change rate; Among them, is the mass change rate, is the tea quality score at the end of the storage period, is the tea quality score at the start of the storage period, is the time point at the end of the storage period, is the time point at the start of the storage period; S313: Based on the quality change rate, according to the time duration from the current time to the target time period, through the formula: ； Calculate the predicted quality score to obtain tea leaf quality prediction information; wherein, is the mass change rate, is the current tea quality score, is the duration from the current time to the target time period, is the attenuation coefficient, is the base of the natural logarithm.

6. The adaptive big data processing method according to claim 1, wherein The steps for evaluating the deviation between the target quality and the predicted quality are as follows: S411: Based on the tea leaf quality prediction information, according to the target sales volume of the tea leaves, retrieve the sales records of similar tea leaves, extract the average quality score corresponding to the tea leaf sales records that reach the target sales volume, to obtain the target quality score extraction result; S412: Based on the target quality score extraction result, through the formula: ； Calculate the deviation index between the target quality and the predicted quality; Among them, is the deviation index between the target quality and the predicted quality, is the target quality score of the tea, is the predicted quality score of the tea; S413: Based on the deviation index between the target quality and the predicted quality, according to the magnitude of the deviation index, evaluate the quality deviation degree to obtain the quality deviation evaluation result.

7. The adaptive big data processing method according to claim 6, wherein The steps for obtaining the storage environment optimization information are as follows: S421: Based on the quality deviation evaluation result, extract the current storage environment parameters and theoretical optimal storage parameters of the tea leaves, including temperature, humidity, and light intensity, to obtain environment correlation data; S422: Based on the environment correlation data, through the formula: ； Calculate the adjusted storage environment parameters; Among them, is the adjusted storage environment parameter, is the current storage environment parameter, is the theoretically optimal storage environment parameter, is the adjustment coefficient, is the deviation index between the target quality and the predicted quality; S423: Based on the adjusted storage environment parameters, adjust the tea leaf storage environment to obtain storage environment optimization information.

8. Adaptive big data processing system, characterized in that, According to the adaptive big data processing method according to any one of claims 1-7, the system includes: The quality standard analysis module, based on the big data platform, extracts the sales data of the tea leaves, combines with the quality standards of the tea leaves, analyzes the correlation between each quality standard and the sales data, eliminates the quality standards with low correlation, and assigns corresponding weights to each quality standard according to the correlation intensity of the remaining quality standards to generate quality standard weight distribution information; The batch quality evaluation module, based on the quality standard weight distribution information, calls the quality parameter values of the current batch of tea leaves, and evaluates the quality of the current batch of tea leaves according to the corresponding weights to obtain tea leaf quality evaluation information; The storage quality prediction module, based on the tea leaf quality evaluation information, extracts the storage environment data of the tea leaves, combines with the current tea leaf quality score, analyzes the influence of the storage time on the tea leaf quality, and predicts the tea leaf quality at the target time period under the current storage condition to obtain tea leaf quality prediction information; Based on the tea quality prediction information, the stored data adjustment module retrieves the sales records of similar teas, extracts the quality data corresponding to the tea sales records that reach the target sales volume, evaluates the deviation between the target quality and the predicted quality, and adjusts the tea storage environment parameters according to the degree of deviation to obtain the storage environment optimization information.

Images