Cigarette economic index monitoring and early warning method and device

Abstract

The embodiment of the invention provides a cigarette economic index monitoring and early warning method, and the method comprises the steps: analyzing the historical data of a plurality of cigarette economic indexes based on an exploratory factor analysis model, and determining a plurality of key research indexes which are key economic indexes capable of explaining the change of cigarette economic data; analyzing the historical data of each key research index based on a preset analysis model, and determining a prediction model corresponding to each key research index; inputting the historical data of each key research index into a corresponding prediction model, and predicting future data of each key research index; dividing the historical data of each key research index into a plurality of state regions, and calculating a probability boundary of each state region based on the historical data of each key research index; and distributing the future data of each key research index to the corresponding state region according to the probability boundary, and carrying out early warning according to the state region where the future data of the key research index is located.

Description

Technical field:

[0001] The present application belongs to the technical field of economic data analysis in the tobacco industry, and specifically relates to a method and device for monitoring and early warning of cigarette economic indicators. Background technology:

[0002] With the continuous development of the tobacco industry, market competition is becoming increasingly fierce, and enterprises are facing more and more uncertain factors. In this environment, it is crucial for enterprises to accurately monitor and analyze cigarette economic indicators. At present, the economic operation status of tobacco enterprises mainly focuses on the implementation and analysis of established economic operation indicators, which provide a basic guarantee for the daily operation of enterprises.

[0003] However, the current implementation and analysis of established economic operating indicators lacks preliminary evaluation and forecasting of economic operations, making it difficult to grasp the future development trend of the cigarette business. Summary of the invention:

[0004] The purpose of the embodiment of the present application is to provide a cigarette economic indicator monitoring and early warning method and device, which can solve the problem of lack of early evaluation and prediction of cigarette economic indicators in related technologies, making it difficult for enterprises to grasp the future development trend of cigarette business.

[0005] In order to solve the above technical problems, this application adopts the following technical solutions:

[0006] In the first aspect, an embodiment of the present invention provides a cigarette economic indicator monitoring and early warning method, comprising: analyzing the historical data of multiple cigarette economic indicators based on an exploratory factor analysis model to determine multiple key research indicators, wherein the key research indicators are key economic indicators that can explain changes in cigarette economic data; analyzing the historical data of each of the key research indicators based on a preset analysis model to determine a prediction model corresponding to each of the key research indicators; inputting the historical data of each of the key research indicators into the corresponding prediction model to predict the future data of each of the key research indicators; dividing the historical data of each of the key research indicators into multiple state areas, and calculating the probability boundary of each state area based on the historical data of each of the key research indicators; allocating the future data of each of the key research indicators to the corresponding state area according to the probability boundary, and issuing an early warning based on the state area where the future data of the key research indicator is located.

[0007] In the second aspect, an embodiment of the present invention provides a cigarette economic indicator monitoring and early warning device, characterized in that it includes: a first determination module, used to analyze the historical data of multiple cigarette economic indicators based on an exploratory factor analysis model, and determine multiple key research indicators, wherein the key research indicators are key economic indicators that can explain changes in cigarette economic data; a second determination module, used to analyze the historical data of each of the key research indicators based on a preset analysis model, and determine the prediction model corresponding to each of the key research indicators; a prediction module, used to input the historical data of each of the key research indicators into the corresponding prediction model, and predict the future data of each of the key research indicators; a calculation module, which divides the historical data of each of the key research indicators into multiple state areas, and calculates the probability boundary of each state area based on the historical data of each of the key research indicators; an early warning module, which allocates the future data of each of the key research indicators to the corresponding state area according to the probability boundary, and issues an early warning according to the state area where the future data of the key research indicator is located.

[0008] In a third aspect, an embodiment of the present invention provides an electronic device comprising: a memory, a processor, and computer executable instructions stored in the memory and executable on the processor, wherein the computer executable instructions, when executed by the processor, implement the steps of the cigarette economic indicator monitoring and early warning method as described in the first aspect above.

[0009] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium for storing computer-executable instructions, which, when executed by a processor, implement the steps of the cigarette economic indicator monitoring and early warning method connected to a base station as described in the first aspect above.

[0010] The embodiment of the present application provides a method for monitoring and early warning of cigarette economic indicators. The key research indicators that can explain the changes in cigarette economic data are screened out through an exploratory factor analysis model, and a prediction model is established based on these indicators. This method improves the accuracy and reliability of future data prediction. The prediction model of the key research indicators obtained by the preset analysis model can predict the future trend of cigarette economic indicators in real time or regularly, and make early warnings accordingly, thereby helping decision makers to take timely measures to deal with potential risks. By dividing historical data into multiple state areas and calculating probability boundaries, the monitoring of cigarette economic indicators is made more detailed, which helps the management to formulate more targeted strategies according to the characteristics of different state areas. The state area warning mechanism based on key research indicators can effectively identify abnormal situations in economic activities, thereby optimizing the allocation and use of resources, reducing unnecessary waste, and improving overall economic benefits. In this way, cigarette economic indicators can be evaluated and predicted in advance, realizing the transformation from post-regulation to pre-prevention, and improving the quality and efficiency of economic operation statistics, prediction, and management. Description of the drawings:

[0011] Figure 1 It is a flow chart of the cigarette economic index monitoring and early warning method disclosed in the embodiment of the present application.

[0012] Figure 2 It is a structural schematic diagram of the cigarette economic index monitoring and early warning device disclosed in the embodiment of the present application.

[0013] Figure 3 It is a structural schematic diagram of an electronic device disclosed in an embodiment of the present application. Specific implementation method:

[0014] The following will be combined with the drawings in the embodiments of the present application to clearly describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, rather than all the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments in the present application belong to the scope of protection of this application.

[0015] The terms "first", "second", etc. in the specification and claims of the present application are used to distinguish similar objects, and are not used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable under appropriate circumstances, so that the embodiments of the present application can be implemented in an order other than those illustrated or described here, and the objects distinguished by "first", "second", etc. are generally of one type, and the number of objects is not limited. For example, the first object can be one or more. In addition, "and / or" in the specification and claims represents at least one of the connected objects, and the character " / " generally indicates that the objects associated with each other are in an "or" relationship.

[0016] In conjunction with the accompanying drawings, a cigarette economic indicator monitoring and early warning method provided by the embodiment of the present application is described in detail through specific embodiments and application scenarios.

[0017] Figure 1 1 is a flow chart of a method for monitoring and early warning of cigarette economic indicators disclosed in an embodiment of the present application. The method 100 can be executed by an electronic device. In other words, the method can be executed by software or hardware installed in the electronic device. Figure 1 As shown, the method may include the following steps.

[0018] S110: Analyze the historical data of multiple cigarette economic indicators based on the exploratory factor analysis model to determine multiple key research indicators, where the key research indicators are key economic indicators that can explain changes in cigarette economic data.

[0019] Specifically, Exploratory Factor Analysis (EFA) is a statistical method used to identify and summarize the potential structure between variables, especially to determine which variables can be attributed to potential unobservable factors. This method can help understand the relationship between a large number of variables and extract a few key factors to explain the changes in the data.

[0020] In the embodiment of the present application, the multiple cigarette economic indicators may include resident population, regional GDP, total retail sales of consumer goods, consumer price index, per capita disposable income, regional GDP of the primary industry, regional GDP of the secondary industry, regional GDP of the tertiary industry, cigarette sales, cigarette box sales, total number of retailers, price index, inventory-to-sales ratio, tax-profit growth rate, cigarette sales growth rate, cigarette single item sales growth rate and total number of retailers. It is worth noting that in the present application, the multiple cigarette economic indicators include but are not limited to the above indicators.

[0021] The historical data of cigarette economic indicators can be the data values ​​of each year and month of each cigarette economic indicator in the past ten years. The exploratory factor analysis model is used to perform exploratory factor analysis on the indicator data values ​​of each year and month of the above-mentioned cigarette economic indicators in the past ten years, and the key research indicators that can most affect the operation of cigarette economy are identified from the above-mentioned multiple cigarette economic indicators. The key research indicators can be multiple or a single indicator among the above-mentioned cigarette economic indicators.

[0022] S120: Analyze the historical data of each key research indicator based on a preset analysis model to determine a prediction model corresponding to each key research indicator.

[0023] The preset analysis model can be determined based on actual conditions. The historical data of key research indicators can be the data values ​​of each year and month of each key research indicator in the past ten years. After analyzing the data values ​​of each year and month of each key research indicator in the past ten years, the prediction model of each key research indicator is determined.

[0024] S130: Input the historical data of each key research indicator into the corresponding prediction model to predict the future data of each key research indicator.

[0025] The data values ​​of each year and month of each key research indicator in the past ten years are input into the corresponding prediction model to predict the future data of each key research indicator. For example, the data values ​​of cigarette sales in the past ten years are the sales data values ​​of each year and month from 2015 to 2024, and the predicted future data can be the sales data values ​​of each month and the whole year in 2025.

[0026] S140: Divide the historical data of each key research indicator into a plurality of state regions, and calculate the probability boundary of each state region based on the historical data of each key research indicator.

[0027] The historical data of key research indicators are divided into several state areas. Based on the data values ​​of each year and month of each key research indicator in the past ten years, the probability boundary of each state area is calculated. In this application, the number of state areas set can be five, including supercooled area, cold area, normal area, hot area and overheated area. But this is only an exemplary division, and the number of areas can be adjusted according to specific circumstances in actual operation. The probability boundary refers to the specific numerical boundary that defines these five state areas. This process helps to better understand the transitions between different state areas and the probability of their occurrence in a quantitative way.

[0028] S150: Allocate the future data of each key research indicator to a corresponding state area according to the probability boundary, and issue an early warning based on the state area where the future data of the key research indicator is located.

[0029] According to the calculated probability boundary, the future data of key research indicators, such as the data values ​​of each year and month of each key research indicator in the past ten years, are analyzed and assigned to the corresponding status area. In this way, effective early warning can be carried out according to the status area where the future data is located.

[0030] In the above process, the key research indicators that can explain the changes in cigarette economic data are screened out through the exploratory factor analysis model, and a prediction model is established based on these indicators. This method improves the accuracy and reliability of future data prediction. The prediction model of key research indicators obtained by the preset analysis model can predict the future trend of cigarette economic indicators in real time or regularly, and make early warnings based on this, so as to help decision makers take timely measures to deal with potential risks. By dividing historical data into multiple state areas and calculating probability boundaries, the monitoring of cigarette economic indicators is more detailed, which helps management to formulate more targeted strategies according to the characteristics of different state areas. The state area warning mechanism based on key research indicators can effectively identify abnormal situations in economic activities, thereby optimizing the allocation and use of resources, reducing unnecessary waste, and improving overall economic benefits. In this way, the transformation from post-regulation to pre-prevention can be achieved, the quality and efficiency of economic operation statistics, forecasting, and management can be steadily improved, and the cigarette economic operation can be promoted to a positive development.

[0031] In one possible implementation, S110 may include: obtaining historical data of multiple cigarette economic indicators, standardizing the historical data of multiple cigarette economic indicators to obtain standardized data; inputting the standardized data into an exploratory factor analysis model to identify common factors that affect changes in the data of multiple cigarette economic indicators; and determining multiple key research indicators by analyzing the common factors.

[0032] Specifically, the process of standardizing the historical data of multiple cigarette economic indicators includes two main steps: first, the preprocessing stage, converting the indicators involving annual growth rates into monthly growth rates, such as converting the tax and profit growth rate, cigarette sales growth rate, cigarette single sales growth rate, and total number of retailers growth rate into monthly growth rates; second, the standardization stage, using the Z-score standardization method to convert data of different dimensions into standardized data with the same dimension, namely, the Z-Score value.

[0033] Then the standardized data is input into the exploratory factor analysis model to identify the common factors that affect the changes in multiple cigarette economic indicators. Before inputting the standardized data into the exploratory factor analysis model, the KMO measure and Bart l ett sphericity test can also be used to check whether the standardized data is suitable for factor analysis. A KMO value close to 1 indicates that the data is very suitable for factor analysis, and the significance level of the Bart l ett sphericity test should be less than 0.05, indicating that there is a correlation between the variables and it is suitable for factor analysis. When the data is found to be suitable for factor analysis, the standardized data is input into the exploratory factor analysis model to identify the common factors that affect the changes in multiple cigarette economic indicators.

[0034] Then, by analyzing the common factors, multiple key research indicators are determined. Specifically, factor rotation is performed first to obtain the rotated factor loading coefficient, and then the indicators that are not strongly related to the cigarette economy are identified based on the rotated factor loading coefficient, and the indicators that are not strongly related to the cigarette economy are deleted, so as to determine the key research indicators. For example, the rotated factor loading coefficient table is given in Table 1.

[0035] Table 1. Factor loading coefficients after rotation

[0036]

[0037]

[0038] As shown in Table 1, after the standardized data were input into the exploratory factor analysis model for analysis, four common factors affecting the changes in the data of the above 17 cigarette economic indicators were identified, and the factor loading coefficients after rotation are given in the table. In statistics, factor loading refers to the degree of correlation between the observed variable and the latent factor. Generally speaking, the larger the absolute value of the factor loading coefficient, the stronger the relationship between the variable and the factor.

[0039] In the present application, the indicators with weak correlation with cigarette economic indicators are identified according to the rotation factor loading coefficient, and the deletion of the indicators with weak correlation with cigarette economic indicators may include: judging whether the absolute value of the rotation factor loading coefficient is greater than 0.6, when the absolute value of the rotation factor loading coefficient is greater than 0.6, judging that the factor has strong correlation with cigarette economic indicators, and when the absolute value of the rotation factor loading coefficient is not greater than 0.6, judging that the factor has weak correlation with cigarette economic indicators. From the analysis of Table 1, it is known that only the consumer price index has strong correlation with factor 3, and other cigarette economic indicators have weak correlation with factor 3, indicating that the consumer price index has weak correlation with cigarette economy, so the consumer price index indicator is deleted, and the remaining cigarette economic indicators are determined as key research indicators.

[0040] By standardizing the historical data of cigarette economic indicators, the comparison of data of different dimensions is ensured under the same benchmark, thereby improving the accuracy and reliability of subsequent factor analysis results. By identifying the key common factors that affect the changes in cigarette economic indicator data, the complexity of the model is simplified, allowing researchers to focus more on the core factors that truly affect the economic performance of cigarettes, thereby improving the efficiency of analysis. The factor loading matrix is ​​optimized using factor rotation technology, making the relationship between factors and original variables clearer, enhancing the interpretability of the analysis results, and helping decision makers better understand the influencing mechanisms behind various economic indicators. By screening out variables that are highly correlated with cigarette economic indicators and excluding irrelevant or weakly correlated factors, it can help companies or policymakers make effective strategic decisions based on more accurate data.

[0041] In the present application, the above-mentioned preset analysis model can be a seasonal autoregressive integrated moving average model (Seasonal Autoregressive Integrated Moving Average, SARIMA). Of course, the preset analysis model can also be a linear regression model or an autoregressive integrated moving average model (AutoRegressive IntegratedMovingAverage, Arima). In practical applications, it can be applied according to specific circumstances.

[0042] In a possible implementation, when the preset analysis model is the SArima model, analyzing the historical data of each key research indicator based on the preset analysis model to determine the prediction model corresponding to each key research indicator may include the following steps.

[0043] Step 1: Import the historical data of the first key research indicator into the SArima model for visualization to obtain the first time series graph, the first autocorrelation function graph and the first partial autocorrelation function graph.

[0044] Assuming that the first key research indicator is cigarette sales, the cigarette sales data for each year and month in the past ten years are imported into the SARIMA model as simulated time series data. The imported data is visualized as a time series and the first time series graph is plotted to intuitively show the trend of cigarette sales over time. The seasonal difference of the time series data is calculated with a time interval of 12 months to eliminate the seasonal effect. The first autocorrelation function graph and the first partial autocorrelation function graph are plotted to help identify the autocorrelation and partial autocorrelation patterns in the time series.

[0045] Step 2: Perform a stationarity test on the historical data of the first key research indicator.

[0046] In a possible implementation, the stationarity test of the historical data of the first key research indicator may include: performing a unit root test on the historical data of the first key research indicator, and judging that the historical data of the first key research indicator is stationary when the test statistic is less than the first critical value and the p-value is less than the second critical value; otherwise, it is non-stationary. Specifically, the unit root test in the PDF test method is performed on the time series data, that is, the cigarette sales data of each year and month in the past ten years, and the test statistic is calculated and compared with the preset first critical value, and the p-value is calculated and compared with the preset second critical value. The stationarity of the time series data is judged based on the relationship between the test statistic and the first critical value and the relationship between the p-value and the second critical value. If the test statistic is less than the first critical value and the p-value is less than the second critical value, the time series data is determined to be stationary. Otherwise, it is non-stationary.

[0047] Step three: When the historical data of the first key research indicator is stable, determine the initial parameter range of the SArima model according to the first time series graph, the first autocorrelation function graph and the first partial autocorrelation function graph; when the historical data of the first key research indicator is non-stationary, perform differential processing on the historical data of the first key research indicator to obtain the second time series graph, the second autocorrelation function graph and the second partial autocorrelation function graph, and determine the initial parameter range of the SArima model according to the second time series graph, the second autocorrelation function graph and the second partial autocorrelation function graph.

[0048] Step 4: Fit the SArima model according to the initial value range of the parameters of the SArima model to determine the optimal parameters of the SArima model.

[0049] Assuming that the time series data reaches a stable state after differential processing, the possible value ranges of the model parameters p, d, q, P, D, and Q can be obtained by analyzing the second time series graph, the second autocorrelation function graph, and the second partial autocorrelation function graph. Within the possible value range, the grid search method is used to iteratively explore different parameter combinations, and the information criterion AIC value of each combination is calculated respectively, and the parameter combination with the minimum AIC value is identified, and this combination is used as the optimal parameter of the selected time series model.

[0050] Step 5: Determine the SArima prediction model based on the optimal parameters.

[0051] According to the optimal parameters, the SARIMAX (p, d, q) x (P, D, Q, S) prediction model is selected as the best fitting model for the cigarette sales time series data, where p, d, q, P, D, Q, and S are the model parameters respectively.

[0052] In a possible implementation, after step five, the following steps may be included: evaluating the fit of the SArima prediction model and adjusting the value of the optimal parameter. Specifically, the maximum likelihood estimation is used to evaluate the optimal parameters, obtain the SArima prediction model coefficient table, and analyze the fit of the SArima prediction model to the data. If the fit is not high, the optimal parameters can be further adjusted to achieve a higher fit, so that the predicted data is more accurate.

[0053] Step 6: Perform steps 1 to 5 for each key research indicator to obtain the SArima prediction model for each key research indicator.

[0054] Similarly, each key research indicator is processed from step one to step five to obtain the SArima prediction model for each key research indicator, so that the future data of each key research indicator can be accurately predicted.

[0055] In a possible implementation, calculating the probability boundary of each state region based on the historical data of each key research indicator may include: calculating the mean and standard deviation of the historical data of each key research indicator;

[0056] According to the mean and standard deviation, the t distribution is used to perform interval estimation on the historical data of each key research indicator to obtain the probability boundary of each state area. Specifically, the mean and standard deviation of the historical data of each key research indicator divide the historical data of each key research indicator into five continuous state areas according to the probability distribution, and the state areas correspond to the supercooling area, the cold area, the normal area, the hot area and the overheating area respectively; the probability distribution ratios corresponding to the five state areas are given respectively, among which the supercooling area accounts for 10%, the cold area accounts for 15%, the normal area accounts for 50%, the hot area accounts for 15%, and the overheating area accounts for 10%; based on the t distribution, the probability boundary of the current economic indicator data is calculated using the mean and standard deviation.

[0057] In a possible implementation, the early warning is carried out according to the state area where the future data of the key research indicator is located, which may include: according to the preset regional alarm state, when the future data of the key research indicator is in different state areas, an alarm is triggered to prompt the user to take corresponding measures. Specifically, the preset regional alarm state can be represented by a signal light, and the corresponding early warning signal is determined according to which area of ​​the five state areas the current economic indicator data falls into, for example, the overcooling area corresponds to a blue light, the cold area corresponds to a light blue light, the normal area corresponds to a green light, the hot area corresponds to a yellow light, and the overheating area corresponds to a red light. The user can take corresponding measures according to the color representation. This embodiment monitors the state changes of the key research indicators in real time, and triggers an alarm when the indicator data falls into the preset state area, so that the user can understand the market changes in the first time, thereby improving the timeliness of decision-making. Using signal lights to represent different early warning levels allows users to quickly understand the state of the current economic indicators and make preliminary judgments without in-depth analysis of the data. According to different early warning signals, users can quickly identify the current risk level, and then choose appropriate strategies to avoid risks or seize opportunities, thereby enhancing the user's decision-making support capabilities. Continuous monitoring and early warning of key research indicators through automated means reduces the time and effort required for manual monitoring and improves work efficiency.

[0058] In summary, this application provides an efficient and reliable method for monitoring and early warning of cigarette economic indicators, which replaces traditional post-event regulation with pre-event prevention, which not only improves the quality and efficiency of economic operation statistics, forecasting and management, but also promotes the healthy development of the cigarette economy.

[0059] Based on the above cigarette economic index monitoring and early warning method, the present application embodiment discloses a cigarette economic index monitoring and early warning device 200, such as Figure 2 As shown, the device 200 mainly includes:

[0060] The first determination module 210 is used to analyze the historical data of multiple cigarette economic indicators based on the exploratory factor analysis model to determine multiple key research indicators, wherein the key research indicators are key economic indicators that can explain changes in cigarette economic data;

[0061] A second determination module 220 is used to analyze the historical data of each key research indicator based on a preset analysis model to determine a prediction model corresponding to each key research indicator;

[0062] Prediction module 230, used to input the historical data of each key research indicator into the corresponding prediction model to predict the future data of each key research indicator;

[0063] A calculation module 240 divides the historical data of each key research indicator into a plurality of state regions, and calculates a probability boundary of each state region based on the historical data of each key research indicator;

[0064] The early warning module 250 allocates the future data of each key research indicator to a corresponding state area according to the probability boundary, and issues an early warning according to the state area where the future data of the key research indicator is located.

[0065] In one possible implementation, the first determination module 210 is also used to obtain historical data of multiple cigarette economic indicators, standardize the historical data of multiple cigarette economic indicators to obtain standardized data; input the standardized data into an exploratory factor analysis model to identify common factors that affect the changes in the data of multiple cigarette economic indicators; and determine multiple key research indicators by analyzing the common factors.

[0066] In a possible implementation, the preset analysis model is a SArima model.

[0067] In a possible implementation, the second determining module 220 is further configured to perform the following steps. Step 1: Import the historical data of the first key research indicator into the SArima model for visualization processing to obtain the first time series graph, the first autocorrelation function graph and the first partial autocorrelation function graph; Step 2: Perform a stationarity test on the historical data of the first key research indicator; Step 3: When the historical data of the first key research indicator is stationary, determine the initial parameter value range of the SArima model according to the first time series graph, the first autocorrelation function graph and the first partial autocorrelation function graph; When the historical data of the first key research indicator is non-stationary, perform differential processing on the historical data of the first key research indicator to obtain the second time series graph, the second autocorrelation function graph and the second partial autocorrelation function graph, and determine the initial parameter value range of the SArima model according to the second time series graph, the second autocorrelation function graph and the second partial autocorrelation function graph; Step 4: Fit the SArima model according to the initial parameter value range of the SArima model to determine the optimal parameters of the SArima model; Step 5: Determine the SArima prediction model based on the optimal parameters; Step 6: Perform steps 1 to 5 on each key research indicator to obtain the SArima prediction model of each key research indicator.

[0068] In this possible implementation, the second determination module 220 is also used to perform a unit root test on the historical data of the first key research indicator. When the test statistic is less than the first critical value and the p-value is less than the second critical value, it is judged that the historical data of the first key research indicator is stationary; otherwise, it is non-stationary.

[0069] In this possible implementation, the second determination module 220 is also used to evaluate the fitness of the SArima prediction model and adjust the values ​​of the optimal parameters.

[0070] In a possible implementation, the state areas include an overcooling area, a relatively cold area, a normal area, a relatively hot area, and an overheating area.

[0071] In this possible implementation, the calculation module 240 is also used to calculate the mean and standard deviation of the historical data of each key research indicator; based on the mean and standard deviation, the t distribution is used to perform interval estimation on the historical data of each key research indicator to obtain the probability boundary of each state area.

[0072] In a possible implementation, the early warning module 250 is also used to trigger an alarm according to a preset regional alarm state when the future data of the key research indicator is in different status areas, prompting the user to take corresponding measures.

[0073] The cigarette economic index monitoring and early warning device 200 provided in the embodiment of the present application can execute the various methods described in the above method embodiments, and realize the functions and beneficial effects of the various methods described in the above method embodiments, which will not be repeated here.

[0074] Optional, such as Figure 3 As shown, the embodiment of the present application also provides an electronic device 300, including a processor 301, a memory 302, and a program or instruction stored in the memory 302 and executable on the processor 301. When the program or instruction is executed by the processor 301, each process of the above-mentioned cigarette economic indicator monitoring and early warning method embodiment is implemented, and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.

[0075] The embodiment of the present application also provides a readable storage medium, on which a program or instruction is stored. When the program or instruction is executed by a processor, each process of the above-mentioned cigarette economic indicator monitoring and early warning method embodiment is implemented, and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.

[0076] The processor 301 is the processor in the electronic device 300 described in the above embodiment. The readable storage medium includes a computer readable storage medium, such as a computer read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0077] An embodiment of the present application further provides a chip, which includes a processor and a communication interface, which are coupled to the processor. The processor is used to run network-side device programs or instructions to implement the various processes of the above-mentioned cigarette economic indicator monitoring and early warning method embodiment, and can achieve the same technical effect. To avoid repetition, it will not be repeated here.

[0078] The embodiment of the present application also provides a computer program product, which includes a processor, a memory, and a program or instruction stored in the memory and executable on the processor. When the program or instruction is executed by the processor, each process of the above-mentioned cigarette economic indicator monitoring and early warning method embodiment is implemented, and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.

[0079] The above embodiments of the present application focus on describing the differences between the various embodiments. As long as the different optimization features between the various embodiments are not contradictory, they can be combined to form a better embodiment. Considering the simplicity of the text, they will not be repeated here.

[0080] It should be noted that, in this article, the term "comprises", "includes" or any other variant thereof is intended to cover non-exclusive inclusion, so that the process, method, article or device including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "including one..." do not exclude the presence of other identical elements in the process, method, article or device including the element. In addition, it should be pointed out that the scope of the method and device in the embodiment of the present application is not limited, and the functions are performed in the order shown or discussed, and may also include performing the functions in a substantially simultaneous manner or in the opposite order according to the functions involved, for example, the described method may be performed in an order different from that described, and various steps may also be added, omitted, or combined. In addition, the features described with reference to certain examples may be combined in other examples.

[0081] The embodiments of the present application are described above in conjunction with the accompanying drawings, but the present application is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the guidance of the present application, ordinary technicians in this field can also make many forms without departing from the purpose of the present application and the scope of protection of the claims, all of which are within the protection of the present application.

Claims

1. A cigarette economic index monitoring and early warning method, characterized in that: include: Analyze the historical data of multiple cigarette economic indicators based on the exploratory factor analysis model to determine multiple key research indicators, wherein the key research indicators are key economic indicators that can explain changes in cigarette economic data; Analyze the historical data of each of the key research indicators based on a preset analysis model to determine a prediction model corresponding to each of the key research indicators; Inputting the historical data of each of the key research indicators into the corresponding prediction model to predict the future data of each of the key research indicators; Dividing the historical data of each of the key research indicators into a plurality of state regions, and calculating the probability boundary of each state region based on the historical data of each of the key research indicators; The future data of each of the key research indicators is allocated to a corresponding state area according to the probability boundary, and an early warning is issued according to the state area where the future data of the key research indicator is located.

2. The cigarette economic index monitoring and early warning method according to claim 1 is characterized in that: The exploratory factor analysis model is used to analyze the historical data of multiple cigarette economic indicators to determine multiple key research indicators, including: Acquiring historical data of the plurality of cigarette economic indicators, and performing standardization processing on the historical data of the plurality of cigarette economic indicators to obtain standardized data; Inputting the standardized data into an exploratory factor analysis model to identify common factors that affect the changes in the multiple cigarette economic indicator data; By analyzing the common factors, the multiple key research indicators are determined.

3. The cigarette economic index monitoring and early warning method according to claim 1 is characterized in that: The preset analysis model is the SArima model.

4. The cigarette economic index monitoring and early warning method according to claim 3 is characterized in that: The analyzing the historical data of each of the key research indicators based on the preset analysis model to determine the prediction model corresponding to each of the key research indicators includes: Step 1: Import the historical data of the first key research indicator into the SArima model for visualization, and obtain the first time series graph, the first autocorrelation function graph, and the first partial autocorrelation function graph; Step 2: Perform a stationarity test on the historical data of the first key research indicator; Step three: when the historical data of the first key research indicator is stable, determine the initial value range of the parameters of the SArima model according to the first time series graph, the first autocorrelation function graph and the first partial autocorrelation function graph; when the historical data of the first key research indicator is non-stationary, perform differential processing on the historical data of the first key research indicator to obtain a second time series graph, a second autocorrelation function graph and a second partial autocorrelation function graph, and determine the initial value range of the parameters of the SArima model according to the second time series graph, the second autocorrelation function graph and the second partial autocorrelation function graph; Step 4: Fitting the SArima model according to the initial value range of the parameters of the SArima model to determine the optimal parameters of the SArima model; Step 5: Determine the SArima prediction model according to the optimal parameters; Step 6: Perform steps 1 to 5 on each key research indicator to obtain the SArima prediction model for each key research indicator.

5. The cigarette economic index monitoring and early warning method according to claim 4 is characterized in that: The stationarity test of the historical data of the first key research indicator includes: A unit root test is performed on the historical data of the first key research indicator. When the test statistic is less than the first critical value and the p-value is less than the second critical value, the historical data of the first key research indicator is judged to be stable; otherwise, it is non-stationary.

6. The cigarette economic index monitoring and early warning method according to claim 4 or 5, characterized in that: After determining the SArima prediction model according to the optimal parameters, the method further includes: Evaluate the fitness of the SArima prediction model and adjust the values ​​of the optimal parameters.

7. The cigarette economic index monitoring and early warning method according to claim 1, characterized in that: The state areas include an overcooling area, a relatively cold area, a normal area, a relatively hot area and an overheating area.

8. The cigarette economic index monitoring and early warning method according to claim 7 is characterized in that: The calculation of the probability boundary of each state area based on the historical data of each key research indicator includes: Calculate the mean and standard deviation of the historical data of each of the key research indicators; According to the mean and the standard deviation, the historical data of each of the key research indicators is estimated using t distribution to obtain the probability boundary of each of the state areas.

9. The cigarette economic index monitoring and early warning method according to claim 1, characterized in that: The early warning according to the state area of ​​the future data of the key research indicator includes: According to the preset regional alarm status, when the future data of the key research indicator is in different status areas, an alarm is triggered to prompt the user to take corresponding measures.

10. A cigarette economic index monitoring and early warning device, characterized in that: include: A first determination module is used to analyze the historical data of multiple cigarette economic indicators based on an exploratory factor analysis model to determine multiple key research indicators, wherein the key research indicators are key economic indicators that can explain changes in cigarette economic data; A second determination module is used to analyze the historical data of each of the key research indicators based on a preset analysis model to determine a prediction model corresponding to each of the key research indicators; A prediction module, used for inputting the historical data of each of the key research indicators into the corresponding prediction model to predict the future data of each of the key research indicators; A calculation module, which divides the historical data of each of the key research indicators into a plurality of state regions, and calculates the probability boundary of each state region based on the historical data of each of the key research indicators; The early warning module allocates the future data of each of the key research indicators to a corresponding state area according to the probability boundary, and issues an early warning according to the state area where the future data of the key research indicator is located.

Images