A user consumption data analysis method and system based on big data

Abstract

The present invention relates to the technical field of consumer behavior analysis, specifically a user consumption data analysis method and system based on big data, comprising the following steps: collecting and collating user consumption data, including purchase time, price, preference and product availability, calculating the correlation coefficient between purchase time and price, analyzing the correlation degree between preference data and product availability, and obtaining a correlation evaluation result. In the present invention, a consumption model is constructed by differential equations, and consumer behaviors at different time points are simulated by the Euler method, so that changes in consumption trends can be foreseen in a complex market environment, the flexibility and adaptability of data analysis are improved, and the ability to formulate and adjust market strategies is effectively enhanced, which plays an important role in grasping consumption peaks and troughs, helping enterprises to gain advantages in fierce market competition, optimize resource allocation, and improve customer satisfaction and loyalty.

Description

Technical Field

[0001] The present invention relates to the technical field of consumer behavior analysis, and in particular to a user consumption data analysis method and system based on big data. Background Art

[0002] The field of consumer behavior analysis technology mainly studies consumer purchasing behavior and consumption patterns in order to better understand market dynamics and consumer demand. This field uses statistical, psychological and sociological methods to analyze various factors in the consumer decision-making process, such as personal preferences, social influences, price sensitivity, and brand loyalty. With the development of big data and machine learning technology, consumer behavior analysis has been able to reveal deep patterns and trends in consumer behavior through massive consumer data, such as shopping history, online browsing habits, and social media behavior, helping companies develop more effective marketing strategies and product development plans.

[0003] Among them, the user consumption data analysis method of big data refers to the use of big data technology to process and analyze a large amount of user consumption data to identify patterns and trends in consumer behavior. Research on this topic can help companies understand the needs of the target market more accurately, predict market changes, and optimize product positioning and marketing strategies. In addition, this analysis method can also be used to improve customer satisfaction and loyalty. Through a deep understanding of consumer behavior, companies can provide more personalized services and products to attract and retain more consumers.

[0004] In practical applications, existing consumer behavior analysis technologies mainly rely on static data analysis methods, which are not able to capture the variability and complexity of consumption patterns. This static analysis ignores the timeliness and dynamic changes of consumer behavior, resulting in companies not being able to respond to market changes in a timely or accurate manner. For example, in the face of rapidly changing consumer trends, traditional analysis methods are unable to adjust market strategies in a timely manner, resulting in missed market opportunities or misinvestment of resources. Existing technologies fail to fully utilize emerging big data technologies and advanced mathematical models, making the analysis results seem inadequate in the modern market environment where consumer data is huge and complex, making it difficult to accurately predict the subtle differences in consumer behavior, affecting the effectiveness of products and marketing strategies formulated by companies. The limitations of these technologies have led to a loss of market share and profitability for companies in a highly competitive market. Summary of the invention

[0005] The purpose of the present invention is to solve the shortcomings of the prior art and to propose a user consumption data analysis method and system based on big data.

[0006] In order to achieve the above object, the present invention adopts the following technical solution, a user consumption data analysis method based on big data, comprising the following steps:

[0007] S1: Collect and organize users’ consumption data, including purchase time, price, preference and product availability, calculate the correlation coefficient between purchase time and price, analyze the correlation between preference data and product availability, and obtain the correlation evaluation results;

[0008] S2: Using the correlation evaluation results, setting the consumption rate as the dependent variable of the differential equation, and taking time as the independent variable, designing the differential equation according to consumption preferences and product prices, and constructing a dynamic consumption model;

[0009] S3: Through the dynamic consumption model, the Euler method is selected to continuously simulate the consumption data, verify that the simulated time span covers the data points, simulate the purchase behavior of consumers at different time points, and generate a simulated consumption path;

[0010] S4: by using the simulated consumption path and big data, analyzing the influence of multiple parameters on the simulated consumption path, adjusting the coefficients of the differential equation, identifying the real-time market situation, and obtaining a parameter optimization model;

[0011] S5: Based on the parameter optimization model, predict the consumption pattern under differentiated market changes, calculate the deviation between the predicted data and the real-time consumption data, and obtain the consumption trend prediction result;

[0012] S6: Utilize the consumption trend prediction results and big data to design marketing strategies, compare the market data before and after the market strategy adjustment, evaluate the impact on the peaks and troughs of consumption data, and generate marketing strategy evaluation results.

[0013] As a further solution of the present invention, the correlation evaluation results include correlation coefficients of numerical values, classified correlation levels and influencing factors of differentiated product categories; the dynamic consumption model includes mathematical expressions, consumption rate change functions and definitions of time variables; the simulated consumption path includes time series consumption records, predicted consumption amounts at each time point and types of selected products; the parameter optimization model includes adjusted coefficient values, key variables identified during the adjustment process and optimized prediction consistency indicators; the consumption trend prediction results include peak consumption periods, trough consumption periods and consumption fluctuation ranges in the target time period; the market strategy evaluation results include comparisons of market data before and after strategy implementation, changing trends in consumption and the effects of strategy impact.

[0014] As a further solution of the present invention, the steps of collecting and collating the consumption data of users, including purchase time, price, preference and product availability, calculating the correlation coefficient between purchase time and price, analyzing the correlation degree between preference data and product availability, and obtaining the correlation evaluation result are specifically as follows:

[0015] S101: Collecting the user's consumption data, including purchase time, price, preference and product availability, collating the data, and performing synchronous updates to obtain the user's consumption records;

[0016] S102: extracting purchase time and price information from the user's consumption record, using time series analysis, and performing correlation calculation, drawing scatter plots and trend lines to identify data change patterns, and generating time-price correlation analysis results;

[0017] S103: Based on the time-price correlation analysis result, based on the user consumption preference data and product availability information, a classification statistical method is used to perform a multi-dimensional analysis, identify preference change trends, evaluate the relationship between product demand and supply, and obtain a correlation evaluation result.

[0018] As a further solution of the present invention, the above-mentioned correlation evaluation result is used to set the consumption rate as the dependent variable of the differential equation, and time is used as the independent variable. The differential equation is designed according to consumption preference and product price, and the steps of constructing a dynamic consumption model are specifically as follows:

[0019] S201: Based on the correlation evaluation result, analyze the relationship between consumption rate and time, select time series data, identify key consumption trends and cyclical changes, take time as the independent variable and consumption rate as the dependent variable, and build a data relationship framework;

[0020] S202: According to the data relationship framework, consumer preferences and product prices are introduced as key influencing factors, and the impact of key factors on consumption rate is analyzed in combination with consumption data, and the interactive relationship between factors is recorded to obtain a differential equation expression;

[0021] S203: Using the differential equation expression, applying a numerical solution method to calculate the consumption rate at differentiated time points, and performing dynamic simulation to track changes in consumption behavior in real time and build a dynamic consumption model.

[0022] As a further solution of the present invention, the Euler method is selected to continuously simulate the consumption data through the dynamic consumption model, verify that the simulated time span covers the data points, simulate the purchase behavior of consumers at different time points, and generate the simulated consumption path in the following steps:

[0023] S301: adopting the dynamic consumption model, according to the changes in the actual economic environment, using a stochastic control algorithm, introducing random factors into the differential equations in the dynamic consumption model for discretization, and generating a numerical solution data set;

[0024] S302: Based on the numerical solution data set, analyze the time span covered by the simulated consumption data, verify that each data point is simulated, check and adjust the consumption data points, check the continuity of the simulation and the integrity of the data, and generate a time coverage verification result;

[0025] S303: Use the time coverage verification result to simulate the purchasing behavior of consumers at different time points, monitor the changes in consumption behavior by adjusting the time points, analyze and optimize the consumption path, and generate a simulated consumption path.

[0026] As a further solution of the present invention, the formula of the random control algorithm is as follows:

[0027] ;

[0028] Among them, C(t) represents the consumption rate at time t, C0 represents the initial consumption rate, which represents the exponential growth factor from the initial time t0 to time t, e is a natural constant, k is the consumption growth rate, α is the adjustment coefficient of random fluctuations, and C avg Represents the average consumption rate.

[0029] As a further solution of the present invention, by simulating the consumption path, using big data, analyzing the influence of multiple parameters on the simulated consumption path, adjusting the coefficients of the differential equation, identifying the real-time market situation, and obtaining the parameter optimization model, the specific steps are:

[0030] S401: Based on the simulated consumption path, using big data, collecting and integrating multiple parameters, including market trend data, product change records and consumer feedback, identifying key influencing factors, and generating multi-parameter analysis results;

[0031] S402: According to the multi-parameter analysis results, the coefficients of the differential equations are adjusted in the dynamic consumption model, the model regression analysis is performed using experimental data, the consistency of the coefficients is verified through iterative testing, and an adjusted differential equation is generated;

[0032] S403: Apply the adjusted differential equation to test the adaptability of the model by comparing consumption data and prediction results, match the real-time changing market environment, and generate a parameter optimization model.

[0033] As a further solution of the present invention, based on the parameter optimization model, the consumption pattern under differentiated market changes is predicted, the deviation between the predicted data and the real-time consumption data is calculated, and the steps of obtaining the consumption trend prediction result are specifically as follows:

[0034] S501: Using the parameter optimization model, setting differentiated market change scenarios, including price fluctuations, new product launches, and changes in the economic environment, simulating and predicting consumption patterns within the next month, and generating a predicted consumption pattern data set;

[0035] S502: Based on the predicted consumption pattern data set, collect real-time consumption data, record sales volume and customer online behavior data, calculate the deviation between the predicted data and the real-time data through statistical analysis, and generate a deviation analysis result;

[0036] S503: Utilizing the deviation analysis results, analyzing the key sources and patterns of deviations, analyzing the trend changes of user consumption data, predicting consumption peak and trough time periods, and generating consumption trend prediction results.

[0037] As a further solution of the present invention, the consumption trend prediction results are used to design a market strategy using big data, and the market data before and after the market strategy adjustment are compared to evaluate the impact on the peak and trough of consumption data. The steps of generating the market strategy evaluation results are specifically as follows:

[0038] S601: Based on the consumption trend prediction results, using big data, designing a marketing strategy, including pricing adjustment, promotion activity plan and target market segmentation, and generating a marketing strategy design plan;

[0039] S602: Implement the marketing strategy design plan, promote the new strategy in the market, and collect market data before and after the strategy implementation, including sales peaks, troughs, and customer feedback, conduct data comparison and analysis, and generate market data comparison results;

[0040] S603: Using the market data comparison results, evaluate the impact of the new market strategy on consumption peaks and troughs, evaluate the effectiveness of the strategy and aspects that require iterative optimization, and generate market strategy evaluation results.

[0041] A user consumption data analysis system based on big data, the user consumption data analysis system based on big data is used to execute the user consumption data analysis method based on big data, the system comprises:

[0042] The data sorting module collects users’ purchase time, price, preference and product availability, calculates the correlation between purchase time and price, analyzes the correlation between preference data and product availability, and generates correlation evaluation results;

[0043] The differential equation design module sets the consumption rate as the dependent variable of the differential equation and the time as the independent variable based on the correlation evaluation result, designs the differential equation, and establishes a dynamic consumption model;

[0044] The consumption simulation analysis module uses the dynamic consumption model and the Euler method to continuously simulate the consumption data, covers the consumption data points at different time points, and generates a simulated consumption path;

[0045] The parameter adjustment module uses big data to analyze the simulated consumption path, adjusts the differential equation coefficients, performs multi-parameter analysis on the influencing factors, and obtains a parameter optimization model;

[0046] The strategy implementation module predicts consumption patterns under market changes based on the parameter optimization model, calculates the deviation between the predicted data and the real-time consumption data, designs and evaluates the effects of market strategies, and generates market strategy evaluation results.

[0047] Compared with the prior art, the advantages and positive effects of the present invention are:

[0048] In the present invention, by collecting and collating consumption data, and establishing a dynamic consumption model for continuous simulation, the simulation results are further subjected to multi-parameter analysis, so as to achieve a more accurate prediction and understanding of market dynamics and consumption behavior. In particular, the consumption model is constructed using differential equations, and the consumption behavior at different time points is simulated by the Euler method, so that changes in consumption trends can be foreseen in a complex market environment, which not only improves the flexibility and adaptability of data analysis, but also further improves the accuracy and real-time response capability of the model by optimizing the parameters of the differential equations. It effectively enhances the formulation and adjustment capabilities of market strategies, plays an important role in grasping consumption peaks and troughs, helps enterprises gain an advantage in fierce market competition, optimizes resource allocation, and improves customer satisfaction and loyalty. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] Figure 1 It is a schematic diagram of the workflow of the present invention;

[0050] Figure 2 This is a detailed flow chart of S1 of the present invention;

[0051] Figure 3 This is a detailed flow chart of S2 of the present invention;

[0052] Figure 4 This is a detailed flow chart of S3 of the present invention;

[0053] Figure 5 This is a detailed flow chart of S4 of the present invention;

[0054] Figure 6 This is a detailed flow chart of S5 of the present invention;

[0055] Figure 7 This is a detailed flow chart of S6 of the present invention;

[0056] Figure 8 It is a system flow chart of the present invention. DETAILED DESCRIPTION

[0057] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0058] In the description of the present invention, it should be understood that the terms "length", "width", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside" and the like indicate positions or positional relationships based on the positions or positional relationships shown in the drawings, and are 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 cannot be understood as limiting the present invention. In addition, in the description of the present invention, "multiple" means two or more, unless otherwise clearly and specifically defined.

[0059] See also Figure 1 The present invention provides a technical solution, a method for analyzing user consumption data based on big data, comprising the following steps:

[0060] S1: Collect and organize users’ consumption data, including purchase time, price, preference and product availability, calculate the correlation coefficient between purchase time and price one by one, and analyze the correlation between preference data and product availability to obtain the correlation evaluation results;

[0061] S2: Using the correlation evaluation results, set the consumption rate as the dependent variable of the differential equation, and use time as the independent variable. Design the differential equation based on consumption preferences and product prices to build a dynamic consumption model.

[0062] S3: Through the dynamic consumption model, the Euler method is selected to continuously simulate the consumption data, verify that the simulated time span covers the data points, simulate the consumer's purchase behavior at different time points, and generate a simulated consumption path;

[0063] S4: By simulating the consumption path and using big data, we analyze the impact of multiple parameters on the simulated consumption path, adjust the coefficients of the differential equation, identify the real-time market situation, and obtain a parameter optimization model;

[0064] S5: Based on the parameter optimization model, predict the consumption pattern under differentiated market changes, calculate the deviation between the predicted data and the real-time consumption data, and avoid the prediction error by adjusting the model parameters to obtain the consumption trend prediction results;

[0065] S6: Utilize the consumption trend forecast results and big data to design marketing strategies, compare the market data before and after the market strategy adjustment, analyze the impact of differentiation strategies on the peaks and troughs of consumption data, and generate marketing strategy evaluation results.

[0066] The results of the correlation evaluation include the correlation coefficient of the numerical value, the correlation level of the classification and the influencing factor of the differentiated product category. The dynamic consumption model includes the mathematical expression, the consumption rate change function and the definition of the time variable. The simulated consumption path includes the consumption records of the time series, the predicted consumption amount at each time point and the types of selected products. The parameter optimization model includes the adjusted coefficient value, the key variables identified during the adjustment process and the optimized forecast consistency index. The consumption trend prediction results include the peak consumption period, the trough consumption period and the consumption fluctuation range in the target time period. The market strategy evaluation results include the comparison of market data before and after the implementation of the strategy, the changing trend of consumption volume and the effect of the strategy.

[0067] See also Figure 2 , collect and organize users' consumption data, including purchase time, price, preference and product availability, calculate the correlation coefficient between purchase time and price, analyze the correlation between preference data and product availability, and obtain the correlation evaluation results in the following steps:

[0068] S101: Collect the user's consumption data, including purchase time, price, preference and product availability, organize the data, and perform synchronous updates to obtain the user's consumption record. The execution process is as follows;

[0069] Collect user consumption data and organize this data, including purchase time, price, preference and product availability. This information will serve as the basis for building a consumer behavior model. Each purchase activity is recorded and updated synchronously based on new purchase events to ensure the real-time and accuracy of the data. The record of purchase time and price information is crucial for subsequent analysis, helping companies understand the time distribution and price sensitivity of consumer purchasing behavior. Preference data reveals consumers' selection tendencies for different products, while product availability information reflects market supply conditions and potential inventory challenges. The combined use of this data not only helps companies optimize inventory, but also better meet consumer needs. Through such data updates and synchronous processing, companies can continuously track and respond to market changes and form user consumption records.

[0070] S102: Extract purchase time and price information from user consumption records, use time series analysis, perform correlation calculation, draw scatter plots and trend lines to identify data change patterns, and generate time-price correlation analysis results. The execution process is as follows;

[0071] Using time series analysis and correlation calculation, according to the formula , calculate the correlation between purchase time and price. In the formula, X t represents the time point t in the time series, P t Representative time The price, and Represents the sample mean of time and price respectively. Formula explanation and formula calculation derivation process: Determine the data points of purchase time X and price P, for example, X=[1, 2, 3, 4, 5], and P=[100, 102, 98, 106, 110], calculate the mean =3 and = 103.2. Calculate the sum of the products of the differences =26.8, and similarly calculate the sum of the squared differences of X and P, we get , substituting these values ​​into the formula to calculate the correlation coefficient, we get =0.874, indicating that there is a strong positive correlation between purchase time and price, which shows that price changes are closely related to purchase time.

[0072] S103: Based on the time-price correlation analysis results, based on the user consumption preference data and product availability information, a classification statistical method is used to perform multi-dimensional analysis, identify preference change trends, evaluate product demand and supply relationships, and obtain the correlation evaluation results. The execution process is as follows;

[0073] According to the results of time-price correlation analysis, the changing trends of consumer preferences are identified and the relationship between product demand and supply is evaluated. Based on consumer preference data and product availability information, this information is analyzed in multiple dimensions through classification and statistical methods. During the analysis, companies can identify which product types are popular with consumers and which need to enhance supply. The combination of preference data and availability information allows companies to dynamically adjust product lines and inventory strategies to more effectively meet market demand. In this way, companies can accurately grasp market dynamics, optimize products and services to adapt to changes in consumer purchasing behavior and market demand, and form correlation evaluation results.

[0074] See also Figure 3 , using the correlation evaluation results, setting the consumption rate as the dependent variable of the differential equation, and taking time as the independent variable, designing the differential equation based on consumption preferences and product prices, the steps to construct a dynamic consumption model are as follows:

[0075] S201: Based on the correlation evaluation results, analyze the relationship between consumption rate and time, select time series data, identify key consumption trends and cyclical changes, take time as the independent variable and consumption rate as the dependent variable, and construct the data relationship framework. The execution process is as follows;

[0076] Based on the correlation evaluation results, the relationship between consumption rate and time is analyzed. Time series data is selected, with time as the independent variable and consumption rate as the dependent variable. Key consumption trends and cyclical changes are identified. The analysis helps determine the main patterns and cycles of consumer behavior, such as consumption peaks during holidays or promotions. Time series data can not only reveal past consumption patterns, but also predict future trends, enabling companies to adjust marketing strategies and inventory levels at appropriate times. With reference to the continuity of time and the volatility of consumption rates, consumption peaks and troughs in future time periods are predicted through in-depth analysis of past data, providing companies with a basis for formulating strategies and building a data relationship framework.

[0077] S202: According to the data relationship framework, consumer preferences and product prices are introduced as key influencing factors. Combined with consumption data, the impact of key factors on consumption rate is analyzed, and the interactive relationship between factors is recorded. The execution process of the differential equation expression is obtained as follows;

[0078] Introducing consumer preferences and product prices as key influencing factors, according to the formula , calculate the change in consumption rate. In the formula, C represents consumption rate, t represents time, P t represents the product price at time t, H t represents the consumption preference at time t, k and α represent the influence coefficients of price and preference respectively. t = 100 units, consumption preference H t =0.75, influence coefficient k=0.5 and α=1.5. Substituting these values ​​into the formula, we get 0.5×(100-1.5×0.75)=48.875, which means that under the current parameters, the consumption rate increases by about 48.875 units per unit time. This model accurately captures the instantaneous changes in consumption rate by considering the dynamic interaction between consumer preferences and product prices, helping companies adjust their market strategies in real time.

[0079] S203: Using differential equation expressions, applying numerical solutions to calculate consumption rates at differentiated time points, and performing dynamic simulations to track changes in consumption behavior in real time, the execution process of building a dynamic consumption model is as follows;

[0080] Using differential equation expressions, the model is updated through a real-time data feedback mechanism based on the time variable to ensure the accuracy of the prediction and the timeliness of the response. The numerical solution allows the model to accurately calculate the changes in consumption rate at different time points, enabling companies to gain insight into the real-time dynamics of consumer behavior. Based on actual consumption data, it provides a thorough understanding of market changes, enabling companies to respond quickly to market changes, optimize strategies and operations, and more effectively meet consumer needs, bringing greater flexibility and competitive advantages to companies and building dynamic consumption models.

[0081] See also Figure 4 , through the dynamic consumption model, the Euler method is selected to continuously simulate the consumption data, verify that the simulated time span covers the data points, simulate the consumer's purchase behavior at different time points, and generate the simulated consumption path in the following steps:

[0082] S301: Adopting a dynamic consumption model, according to the changes in the actual economic environment, adopting a stochastic control algorithm, by introducing random factors into the differential equations in the dynamic consumption model for discretization, the execution process of generating a numerical solution data set is as follows;

[0083] The formula of the stochastic control algorithm is as follows:

[0084] ;

[0085] Among them, C(t) represents the consumption rate at time t, C0 represents the initial consumption rate, represents the exponential growth factor from the initial time t0 to time t, e is a natural constant, k is the consumption growth rate, α is the adjustment coefficient of random fluctuations, C avg Represents the average consumption rate.

[0086] Detailed explanation of the formula and the process of formula calculation: Considering a specific numerical example, the initial consumption rate C0 is set to 100 units, the initial time t0 is 0, the target time t is 5 years, and the consumption growth rate k is 0.05 per year, that is, 5% per year. The average consumption rate C avg The adjustment coefficient α of random fluctuation is set to 0.1, which is based on the survey of the sensitivity of consumption fluctuations. This coefficient indicates that as the fluctuation increases, the model needs to be adjusted appropriately to balance the rapid changes in consumption rate.

[0087] calculate :The calculation formula of the exponential factor is , substitute and ,get:

[0088] ;

[0089] This represents an exponential growth of 28.4% in consumption over a five-year time span.

[0090] calculate : Update the initial consumption rate using an exponential growth factor:

[0091] ;

[0092] The consumption rate after five years is 128.4 units.

[0093] Calculate the absolute value term : The absolute value of the difference between the initial consumption rate and the average rate after growth:

[0094] ;

[0095] Calculate the square root term : Take the square root of the absolute value of the difference calculated in the previous step:

[0096] ;

[0097] Evaluate the integral expression in the denominator :Consider the volatility adjustment coefficient:

[0098] ;

[0099] Calculate C(t):

[0100] ;

[0101] The results show that after five years, the actual consumption rate is adjusted to about 87.6 units per year, reflecting the adaptive adjustment of the consumption rate relative to the historical average under the set growth rate and fluctuation adjustment. This numerical result helps to understand how to manage long-term consumption policies to cope with economic fluctuations. In this way, the model provides a way to quantify consumption behavior and enhance adaptability to future economic conditions.

[0102] S302: Based on the numerical solution data set, analyze the time span covered by the simulated consumption data, verify that each data point is simulated, check and adjust the consumption data points, check the continuity of the simulation and the integrity of the data, and generate the execution process of the time coverage verification result as follows;

[0103] Based on the numerical solution of the data set, the time span covered by the simulated consumption data is analyzed, and each data point is verified to be simulated. The consumption data points are checked and adjusted to ensure the continuity and integrity of the data set. The time span analysis reveals the overall scope of data coverage and potential data gaps. Simulation verification enhances the reliability of the data by identifying and adjusting abnormal or missing values ​​in the data. By systematically checking each data point, the continuity of the simulation is ensured, reflecting the real dynamics of consumption behavior throughout the observation period. Ensuring data integrity provides a solid foundation for further analysis and generates time coverage verification results.

[0104] S303: Use the time coverage verification result to simulate the purchasing behavior of consumers at different time points, monitor the changes in consumption behavior by adjusting the time points, analyze and optimize the consumption path, and generate the execution process of the simulated consumption path as follows;

[0105] Use time coverage to verify the results, simulate the purchasing behavior of consumers at different time points, and monitor changes in consumer behavior by adjusting the time points. The process helps understand consumers' purchasing preferences and behavior patterns at different time points. Through dynamic simulation, companies can observe consumption trends at specific time points, analyze and optimize consumption paths, and verify the results through accurate time coverage to ensure that the simulated data accurately reflects actual consumption. Through this method, companies can identify key moments that affect consumer purchasing decisions, such as promotions or before and after holidays, optimize marketing strategies and inventory management, improve efficiency and consumer satisfaction, enable companies to more effectively respond to market changes and consumer needs, and generate simulated consumption paths.

[0106] See also Figure 5 , by simulating the consumption path, using big data, analyzing the impact of multiple parameters on the simulated consumption path, adjusting the coefficients of the differential equation, identifying the real-time market situation, and obtaining the parameter optimization model. The specific steps are:

[0107] S401: Based on the simulated consumption path, using big data, collecting and integrating multiple parameters, including market trend data, product change records and consumer feedback, identifying key influencing factors, and generating multi-parameter analysis results. The execution process is as follows;

[0108] Data collection based on simulated consumption paths integrates market trend data, product change records and consumer feedback to identify key influencing factors. This process includes the use of big data technology. Data integration requires not only sensitive capture of external market data, but also efficient collaboration of internal data management systems. Data is processed and parsed through analytical models to ensure that each data update is accurately recorded and fed back. Product change records need to be detailed to every small modification to ensure that specific product change points can be accurately traced when analyzing consumer feedback. This method can systematically analyze data and discover subtle changes in consumer demand, and obtain multi-parameter analysis results.

[0109] S402: According to the multi-parameter analysis results, the coefficients of the differential equations are adjusted in the dynamic consumption model, the model regression analysis is performed using experimental data, the consistency of the coefficients is verified through iterative testing, and the execution flow of generating the adjusted differential equations is as follows;

[0110] According to the results of multi-parameter analysis, the coefficients of the differential equation are adjusted according to the formula Calculate the adjusted differential equation. In the formula, p(t) represents the coefficient of time variation and q(t) represents the free term. Detailed explanation of the formula and the derivation process of the formula calculation: In this example, p(t) and q(t) can be estimated by experimental data. For example, in the preliminary test, p(t) is estimated to be 0.05 and q(t) is -0.3. Then the differential equation can be expressed as =0.05y-0.3. If the initial value y(0)=10, use the Euler method for numerical solution with a step size of h=0.1. In the first step, we can calculate y(0.1)≈10+0.1×(0.05×10-0.3)=9.97. After that, we can iteratively solve the approximate solution of y(t) to verify the consistency of the coefficients.

[0111] S403: Apply the adjusted differential equation, compare the consumption data and the forecast results, test the adaptability of the model, match the real-time changing market environment, and generate the execution process of the parameter optimization model as follows;

[0112] The adjusted differential equation is used to compare consumption data with the forecast results. The process involves adaptability testing to the real-time market environment. The adjusted model must be able to reflect the latest changes in consumption data. The accuracy of the forecast results is directly related to the practicality of the model. Through continuous iterative testing, the model is optimized and adjusted to ensure that each model update can match the actual market situation. Through real-time data feedback, the model parameters are adjusted to maintain the high efficiency and high accuracy of the model in the ever-changing market environment, and a parameter optimization model is generated.

[0113] See also Figure 6 Based on the parameter optimization model, the consumption patterns under differentiated market changes are predicted, the deviation between the predicted data and the real-time consumption data is calculated, and the steps to obtain the consumption trend prediction results are as follows:

[0114] S501: Using the parameter optimization model, setting differentiated market change scenarios, including price fluctuations, new product launches, and changes in the economic environment, simulate and predict the consumption pattern in the next month, and generate the execution process of the predicted consumption pattern data set as follows;

[0115] The parameter optimization model is used to simulate and predict consumption patterns in the next month. The process requires setting up multiple market change scenarios, such as price fluctuations, new product launches, and changes in the economic environment. The simulation prediction not only involves complex market analysis, but also requires a high degree of data accuracy and processing capabilities. By setting different market scenarios, consumer behaviors and reactions in various situations are predicted, reflecting consumption patterns under various conditions, providing a basis for market strategies, and generating a predicted consumption pattern data set.

[0116] S502: Based on the predicted consumption pattern data set, real-time consumption data is collected, sales volume and customer online behavior data are recorded, and the deviation between the predicted data and the real-time data is calculated through statistical analysis to generate the deviation analysis results. The execution process is as follows;

[0117] Collect real-time consumption data and sales volume, according to the formula Calculate the deviation between the predicted data and the real-time data. Represents the forecast data, Represents actual data. Detailed explanation of the formula and the process of formula calculation: Take a simplified example to illustrate, set the predicted value p=[100, 200, 150, 300, 250] of five data points and the actual value a=[95, 205, 145, 310, 240], and the sum of the squares of the deviations is (100-95) 2 +(200-205) 2 +(150-145) 2 +(300-310) 2 +(250-240) 2 =25+25+25+100+100=275. This calculation allows quantifying the deviation between prediction and reality, which is a key indicator of the accuracy of the forecast model.

[0118] S503: Using the deviation analysis results, analyzing the key sources and patterns of the deviations, analyzing the trend changes of user consumption data, predicting the consumption peak and valley time periods, and generating the consumption trend prediction results. The execution process is as follows;

[0119] The results of deviation analysis are used to predict consumption trends. This process not only analyzes the key sources of deviation, but also includes in-depth analysis of the trend changes in user consumption data. Through these analyses, the peak and trough time periods of consumption can be effectively predicted, providing important time windows and strategic recommendations for marketing and product supply chain optimization. These prediction results will be used to guide companies to adjust their market strategies, respond to potential market changes, optimize products and services to meet changes in consumer demand, and generate consumption trend prediction results.

[0120] See also Figure 7 , using the consumption trend forecast results, adopting big data, designing market strategies, and comparing the market data before and after the market strategy adjustment, evaluating the impact on the peak and trough of consumption data. The specific steps to generate the market strategy evaluation results are as follows:

[0121] S601: Based on the consumption trend forecast results, using big data, designing market strategies, including pricing adjustments, promotion activity plans and target market segmentation, the execution process of generating market strategy design solutions is as follows;

[0122] Design marketing strategy according to formula Calculate the market strategy design. In the formula, W J represents the strategy weight, x JRepresents the characteristics of the strategy. Detailed explanation of the formula and the process of formula calculation: Consider a simplified case. The strategy includes three aspects: price adjustment, promotional activities and market segmentation. The weight of each strategy is set as w=[0.5, 0.3, 0.2], and the quantitative value of the strategy characteristic is x=「1.2, 0.8, 1.5], which represents the execution intensity or range of different strategies. Then the comprehensive score C of the market strategy is calculated as 0.5×1.2+0.3×0.8+0.2×1.5=0.6+0.24+0.3=1.14. This score reflects the implementation intensity and potential market influence of the comprehensive strategy, and is a key quantitative evaluation in the strategy design process.

[0123] S602: Implement the market strategy design plan, promote the new strategy in the market, and collect market data before and after the strategy implementation, including sales peaks, troughs and customer feedback, and conduct data comparison and analysis to generate the market data comparison results. The execution process is as follows;

[0124] Implement market strategy design plans, promote new strategies and record market data at the same time, including sales peaks, troughs and customer feedback before and after strategy implementation, and conduct detailed data comparison and analysis. The process involves a large amount of data collection and processing. Through these data, the direct effect of the strategy and market response can be clarified, and the actual effect of the strategy can be quantitatively evaluated. These data comparisons will help decision makers understand which strategies are most effective and which need to be adjusted, and generate market data comparison results.

[0125] S603: Using the market data comparison results, evaluate the impact of the new market strategy on consumption peaks and valleys, evaluate the effectiveness of the strategy and the aspects that need iterative optimization, and generate the execution process of the market strategy evaluation results as follows;

[0126] By comparing the results of market data, we can evaluate the impact of new market strategies, especially their effects on consumption peaks and troughs. The evaluation not only reflects the effectiveness of the strategy, but also points out areas that require iterative optimization. Through these analyses, companies can better adjust their market strategies to adapt to changing market conditions and consumer demands, optimize overall market performance, influence the company's decision-making and strategy adjustments, and generate market strategy evaluation results.

[0127] See also Figure 8 A user consumption data analysis system based on big data is used to perform the above-mentioned user consumption data analysis method based on big data. The system includes:

[0128] The data sorting module collects users’ purchase time, price, preference and product availability, calculates the correlation between purchase time and price, analyzes the correlation between preference data and product availability, and generates correlation evaluation results;

[0129] Based on the correlation evaluation results, the differential equation design module sets the consumption rate as the dependent variable of the differential equation and time as the independent variable, designs the differential equation, and establishes a dynamic consumption model;

[0130] The consumption simulation analysis module uses the dynamic consumption model and the Euler method to continuously simulate consumption data, covering consumption data points at different time points and generating simulated consumption paths;

[0131] The parameter adjustment module uses big data analysis to simulate consumption paths, adjust differential equation coefficients, conduct multi-parameter analysis of influencing factors, and obtain a parameter optimization model;

[0132] The strategy implementation module is based on a parameter optimization model to predict consumption patterns under market changes, calculate the deviation between predicted data and real-time consumption data, design and evaluate the effectiveness of market strategies, and generate market strategy evaluation results.

[0133] The above are only preferred embodiments of the present invention and are not intended to limit the present invention in other forms. Any technician familiar with the profession may use the technical contents disclosed above to change or modify them into equivalent embodiments with equivalent changes and apply them to other fields. However, any simple modification, equivalent change and modification made to the above embodiments based on the technical essence of the present invention without departing from the technical solution of the present invention still falls within the protection scope of the technical solution of the present invention.

Claims

1. A user consumption data analysis method based on big data, characterized in that: The following steps are involved: Collect and organize users' consumption data, including purchase time, price, preference and product availability, calculate the correlation coefficient between purchase time and price, analyze the correlation between preference data and product availability, and obtain correlation evaluation results; Using the correlation evaluation results, setting the consumption rate as the dependent variable of the differential equation, and taking time as the independent variable, designing the differential equation according to consumption preference and product price, and constructing a dynamic consumption model; Through the dynamic consumption model, the Euler method is selected to continuously simulate the consumption data, verify that the simulated time span covers the data points, simulate the purchase behavior of consumers at different time points, and generate a simulated consumption path; By using the simulated consumption path and big data, the influence of multiple parameters on the simulated consumption path is analyzed, the coefficients of the differential equation are adjusted, the real-time market situation is identified, and a parameter optimization model is obtained; Based on the parameter optimization model, the consumption pattern under the differentiated market changes is predicted, the deviation between the predicted data and the real-time consumption data is calculated, and the consumption trend prediction result is obtained; Using the consumption trend forecast results and big data, designing marketing strategies, and comparing market data before and after the market strategy adjustment, evaluating the impact on the peaks and troughs of consumption data, and generating marketing strategy evaluation results; The dynamic consumption model is adopted, according to the changes in the actual economic environment, a random control algorithm is used, and a random factor is introduced into the differential equation in the dynamic consumption model for discretization processing to generate a numerical solution data set; Based on the numerical solution data set, analyze the time span covered by the simulated consumption data, verify that each data point is simulated, check and adjust the consumption data points, check the continuity of the simulation and the integrity of the data, and generate a time coverage verification result; Using the time coverage verification results, simulating the purchasing behavior of consumers at different time points, monitoring changes in consumer behavior by adjusting the time points, analyzing and optimizing the consumption path, and generating a simulated consumption path; The formula of the stochastic control algorithm is as follows: ； Among them, C(t) represents the consumption rate at time t, C0 represents the initial consumption rate, represents the exponential growth factor from the initial time t0 to time t, e is a natural constant, k is the consumption growth rate, α is the adjustment coefficient of random fluctuations, C avg Represents the average consumption rate.

2. The user consumption data analysis method based on big data according to claim 1 is characterized in that: The correlation evaluation results include the correlation coefficient of the numerical value, the correlation level of the classification and the influencing factor of the differentiated product category. The dynamic consumption model includes the mathematical expression, the consumption rate change function and the definition of the time variable. The simulated consumption path includes the consumption records of the time series, the predicted consumption amount at each time point and the types of selected products. The parameter optimization model includes the adjusted coefficient value, the key variables identified during the adjustment process and the optimized prediction consistency index. The consumption trend prediction results include the peak consumption period, the trough consumption period and the consumption fluctuation range in the target time period. The market strategy evaluation results include the comparison of market data before and after the implementation of the strategy, the trend of consumption changes and the effect of the strategy.

3. The user consumption data analysis method based on big data according to claim 1 is characterized in that: Collect and organize user consumption data, including purchase time, price, preference and product availability, calculate the correlation coefficient between purchase time and price, analyze the correlation between preference data and product availability, and obtain the correlation evaluation results in the following steps: Collect user consumption data, including purchase time, price, preferences and product availability, organize the data, perform synchronous updates, and obtain user consumption records; Extracting purchase time and price information from the user's consumption records, using time series analysis and performing correlation calculations, drawing scatter plots and trend lines to identify data change patterns, and generating time-price correlation analysis results; According to the time-price correlation analysis results, based on user consumption preference data and product availability information, a classification statistical method is used to conduct a multi-dimensional analysis, identify preference change trends, evaluate the relationship between product demand and supply, and obtain correlation evaluation results.

4. The user consumption data analysis method based on big data according to claim 1 is characterized in that: Using the correlation evaluation results, setting the consumption rate as the dependent variable of the differential equation, and taking time as the independent variable, designing the differential equation according to consumption preferences and product prices, the steps of constructing a dynamic consumption model are as follows: Based on the correlation evaluation results, analyze the relationship between consumption rate and time, select time series data, identify key consumption trends and cyclical changes, take time as the independent variable and consumption rate as the dependent variable, and build a data relationship framework; According to the data relationship framework, consumer preferences and product prices are introduced as key influencing factors. Combined with consumption data, the impact of key factors on consumption rate is analyzed, the interactive relationship between factors is recorded, and the differential equation expression is obtained; Using the differential equation expression, a numerical solution is applied to calculate the consumption rate at differentiated time points, and dynamic simulation is performed to track changes in consumption behavior in real time and build a dynamic consumption model.

5. The user consumption data analysis method based on big data according to claim 1 is characterized in that: Through the simulated consumption path, using big data, analyzing the impact of multiple parameters on the simulated consumption path, adjusting the coefficients of the differential equation, identifying the real-time market situation, and obtaining the parameter optimization model, the specific steps are: Based on the simulated consumption path, using big data, multiple parameters are collected and integrated, including market trend data, product change records and consumer feedback, to identify key influencing factors and generate multi-parameter analysis results; According to the multi-parameter analysis results, the coefficients of the differential equations are adjusted in the dynamic consumption model, the model regression analysis is performed using experimental data, the consistency of the coefficients is verified through iterative testing, and the adjusted differential equations are generated; By applying the adjusted differential equation, the adaptability of the model is tested by comparing consumption data and forecast results, matching the real-time changing market environment, and generating a parameter optimization model.

6. The user consumption data analysis method based on big data according to claim 1 is characterized in that: Based on the parameter optimization model, the consumption pattern under differentiated market changes is predicted, the deviation between the predicted data and the real-time consumption data is calculated, and the steps of obtaining the consumption trend prediction result are as follows: Using the parameter optimization model, differentiated market change scenarios are set, including price fluctuations, new product launches, and changes in the economic environment, to simulate and predict consumption patterns in the next month and generate a predicted consumption pattern data set; Based on the predicted consumption pattern data set, real-time consumption data is collected, sales volume and customer online behavior data are recorded, and the deviation between the predicted data and the real-time data is calculated through statistical analysis to generate deviation analysis results; Utilize the deviation analysis results to analyze the key sources and patterns of deviations, analyze the trend changes of user consumption data, predict consumption peak and trough time periods, and generate consumption trend prediction results.

7. The user consumption data analysis method based on big data according to claim 1 is characterized in that: Using the consumption trend prediction results, adopting big data, designing market strategies, and comparing the market data before and after the market strategy adjustment, evaluating the impact on the peak and trough of consumption data, the steps for generating market strategy evaluation results are as follows: Based on the consumption trend forecast results, use big data to design market strategies, including pricing adjustments, promotional activity plans and target market segmentation, and generate market strategy design plans; Implement the marketing strategy design, promote the new strategy in the market, and collect market data before and after the implementation of the strategy, including sales peaks, troughs and customer feedback, conduct data comparison and analysis, and generate market data comparison results; Utilize the market data comparison results to evaluate the impact of new market strategies on consumption peaks and troughs, evaluate the effectiveness of strategies and areas that require iterative optimization, and generate market strategy evaluation results.

8. A user consumption data analysis system based on big data, characterized in that: According to the user consumption data analysis method based on big data according to any one of claims 1 to 7, the system comprises: The data sorting module collects users’ purchase time, price, preference and product availability, calculates the correlation between purchase time and price, analyzes the correlation between preference data and product availability, and generates correlation evaluation results; The differential equation design module sets the consumption rate as the dependent variable of the differential equation and the time as the independent variable based on the correlation evaluation result, designs the differential equation, and establishes a dynamic consumption model; The consumption simulation analysis module uses the dynamic consumption model and the Euler method to continuously simulate the consumption data, covers the consumption data points at different time points, and generates a simulated consumption path; The parameter adjustment module uses big data to analyze the simulated consumption path, adjusts the differential equation coefficients, performs multi-parameter analysis on the influencing factors, and obtains a parameter optimization model; The deviation analysis module predicts the consumption pattern under market changes based on the parameter optimization model, calculates the deviation between the predicted data and the real-time consumption data, and obtains the consumption trend prediction result; The strategy implementation module designs a market strategy based on the consumption trend prediction results, analyzes the impact of the market strategy on consumption, evaluates the effect of the market strategy, and generates a market strategy evaluation result.

Images