Influence analysis method for promotion commodity combination

CN120912265APending Publication Date: 2025-11-07SHENZHEN PARTNER NETWORK SERVICE TECHNOLOGY CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202511085432.1
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-08-04
Publication Date
2025-11-07

Smart Images

  • Figure CN120912265A_ABST
    Figure CN120912265A_ABST
Patent Text Reader

Abstract

The invention relates to the field of promotion commodity data analysis, in particular to an influence analysis method for a promotion commodity combination. The method comprises the steps of obtaining a food material normal weekly sales data set and a food material combination, analyzing the food material normal weekly sales data set based on the food material combination, and determining a food material combination basic influence value; acquiring a real-time food material combination and current regional information, and based on the current regional information, analyzing food material information of the real-time food material combination, determining a regional influence factor, analyzing component information of the real-time food material combination, determining a component influence factor, analyzing freshness information of the real-time food material combination, and determining a freshness influence factor; and according to the regional influence factor, the component influence factor and the freshness influence factor, performing weighted calculation on the basic influence value of the food material combination, and determining a real-time influence value of the food material combination. According to the method, the comprehensiveness and the accuracy of the influence analysis of the promotion food material combination are effectively improved, and a scientific basis is provided for formulating a targeted promotion strategy.
Need to check novelty before this filing date? Find Prior Art

Description

TECHNICAL FIELD

[0001] The present application relates to the field of promotion commodity data analysis, in particular to a method for analyzing the influence of a promotion commodity combination. BACKGROUND

[0002] With the rapid development of the retail and catering industries, commodity combination promotion, as an important means to improve sales and meet the diverse needs of consumers, is widely used in food material sales scenarios. A reasonable food material combination can effectively drive food material sales and improve customer repurchase rates. Therefore, accurately analyzing the influence of food material combinations is of great significance for formulating scientific promotion strategies.

[0003] However, the current methods for analyzing the influence of food material combinations have obvious shortcomings. These methods often fail to fully combine the correlation characteristics of food material combinations and food material single products in basic sales data, and ignore the dynamic influence of real-time factors such as regional preferences, portioning, and food material freshness on combination influence, resulting in deviations between analysis results and actual market performance, making it difficult to accurately support promotion decisions. SUMMARY

[0004] The present application provides a method for analyzing the influence of a promotion commodity combination to solve the above technical problems.

[0005] The present application provides a method for analyzing the influence of a promotion commodity combination, which comprises: Obtaining food material normal weekly sales data set and food material combination, based on the food material combination, coupling analysis of combination sales data and single product sales data in the food material normal weekly sales data set, determining the food material combination basic influence value; obtaining real-time food material combination and current regional information, based on the current regional information, analyzing the food material information of the real-time food material combination, determining the regional influence factor, analyzing the portion information of the real-time food material combination, determining the portion influence factor, analyzing the freshness information of the real-time food material combination, determining the freshness influence factor; according to the regional influence factor, the portion influence factor and the freshness influence factor, weighting calculation of the food material combination basic influence value, determining the real-time influence value of the food material combination.

[0006] Through the scheme, the normal weekly sales data set of the food materials and the food material combination are acquired, the combination sales data and the single product sales data are coupled and analyzed to determine the basic influence value of the food material combination, the one-sidedness caused by separately analyzing single data is avoided, a reliable basis is provided for subsequent analysis, meanwhile, the real-time food material combination and the current regional information are combined to respectively determine the regional influence factor, the component influence factor and the freshness influence factor, the influence of real-time factors such as regional preference, component rationality and food material freshness on sales is comprehensively captured, and then the real-time influence value of the food material combination is determined by combining the real-time factors and the basic influence value through weighted calculation, so that the evaluation result can not only reflect the inherent sales potential of the food material combination, but also accurately reflect the real-time market dynamics, the comprehensiveness and accuracy of the influence analysis of the promotion food material combination are effectively improved, and a scientific basis is provided for formulating a targeted promotion strategy.

[0007] Optionally, the obtaining of the normal weekly sales data set of the food materials comprises: obtaining a historical sales data set of the food materials, historical adverse weather information and historical activity information; the historical sales data set of the food materials is split and summarized by week to determine a weekly historical sales data set of the food materials; the weekly historical sales data set of the food materials is analyzed based on the historical adverse weather information to determine a weather-affected weekly historical sales data set of the food materials; the weekly historical sales data set of the food materials is analyzed based on the historical activity information to determine an activity-affected weekly historical sales data set of the food materials; the weather-affected weekly historical sales data set of the food materials and the activity-affected weekly historical sales data set of the food materials are deleted from the weekly historical sales data set of the food materials to obtain the normal weekly sales data set of the food materials.

[0008] Through the scheme, the data is split by week, the actual consumption habit of high purchase frequency on weekends is fitted, the data is more accurate to reflect the weekly characteristics of the sales of the food materials; meanwhile, the abnormal weekly data affected by adverse weather and activities is removed, external interference is effectively excluded, the normal weekly sales data set of the food materials can truly reflect the sales trend under normal circumstances, the baseline data fitting the consumption law and without interference is provided for subsequent analysis of the basic influence value of the food material combination, which is helpful to more accurately evaluate the inherent influence of the food material combination and provide a reliable basis for the formulation of the promotion strategy.

[0009] Optionally, the coupling analysis of the combination sales data, the single product sales data in the normal week sales data set of the food materials based on the food material combination comprises: extracting the combination sales data corresponding to the food material combination and the single product sales data corresponding to each food material involved in the food material combination from the normal week sales data set of the food materials; the combination sales data comprises combination sales volume, combination repeat purchase rate and combination total profit; the single product sales data comprises single product sales volume, single product repeat purchase rate and single product total profit; taking the ratio of the combination sales volume to the sum of the single product sales volume of all food materials involved in the food material combination as the sales coupling coefficient; calculating the average of the single product repeat purchase rate of all food materials involved in the food material combination to determine the average repeat purchase rate, and taking the ratio of the combination repeat purchase rate to the average repeat purchase rate as the repeat purchase coupling coefficient; taking the ratio of the combination total profit to the sum of the single product total profit of all food materials involved in the food material combination as the profit balance index; obtaining a preset weight value, and performing weighted calculation on the sales coupling coefficient and the repeat purchase coupling coefficient based on the preset weight value to obtain a basic coupling value; and multiplying the basic coupling value and the profit balance index to obtain the basic influence value of the food material combination.

[0010] Through the scheme, the sales coupling coefficient and the repeat purchase coupling coefficient are calculated, the sales and repeat purchase correlation of the combination and the single product are comprehensively considered, the profit balance index is introduced, the profitability is considered, the weight of the sales and the repeat purchase is dynamically adjusted combined with the preset weight value, the characteristics of different sales periods are adapted, and finally the basic influence value of the food material combination fully reflects the sales driving, customer stickiness and profitability of the combination, provides a scientific basis for subsequent real-time influence value calculation, and improves the systematicness and accuracy of the promotion combination evaluation.

[0011] Optionally, the obtaining of the preset weight value comprises: obtaining holiday information set and current sales period; if the current sales period contains a date in the holiday information set, a first weight value is given to the sales coupling coefficient and a second weight value is given to the repeat purchase coupling coefficient; the first weight value is greater than the second weight value; if the current sales period does not contain a date in the holiday information set, a third weight value is given to the sales coupling coefficient and a fourth weight value is given to the repeat purchase coupling coefficient; the third weight value is less than the fourth weight value.

[0012] Through the scheme, the weight of the sales coupling coefficient and the repeat purchase coupling coefficient is dynamically adjusted according to whether the current sales period contains a holiday, the preset weight value can accurately match the core elements of the combination influence evaluation in different periods, and the calculation of the basic coupling value is more in line with the actual sales characteristics, thereby providing a reasonable basis for determining the basic influence value of the food material combination, and improving the pertinence and accuracy of the food material combination influence analysis.

[0013] Optionally, the real-time food material combination is analyzed based on the current regional information to determine a regional influence factor, including: analyzing the food material information in the real-time food material combination to determine a combination dish; the combination dish includes food material information and food material cooking combination information; obtaining a set of regional dietary preference information; the set of regional dietary preference information includes food material preference scores of each food material and food material cooking combination preference scores of each food material combination; based on the set of regional dietary preference information, the combination dish is analyzed to obtain the food material preference scores of each food material and the food material cooking combination preference scores of the food material cooking combination in the current region; the food material preference scores of each food material and the food material cooking combination preference scores of the food material cooking combination in the real-time food material combination are weighted and summed to obtain an acceptance coefficient of the combination dish in the current region; and the acceptance coefficient is taken as the regional influence factor.

[0014] Through the scheme, by combining the current regional information and the set of regional dietary preference information, the food material preference scores and the food material cooking combination preference scores are accurately extracted, and the acceptance coefficient (regional influence factor) calculated can truly reflect the acceptance degree of local consumers to the real-time food material combination, which makes up for the evaluation deviation caused by ignoring regional differences, so that the real-time influence value of the food material combination calculated based on the regional influence factor is more in line with the local market demand, providing a reliable basis for formulating targeted promotion strategies, and helping to improve the attractiveness and sales volume of the food material combination in the local market, and fully exerting the promotion effect of regional adaptability on promotion.

[0015] Optionally, the quantity information of the real-time food material combination is analyzed to determine a quantity influence factor, including: analyzing the combination dish to determine a set of standard quantity information of food materials; the set of standard quantity information of food materials is a set of information of standard quantities of each food material used for making dishes; extracting real-time quantity information of each food material in the real-time food material combination; taking the ratio of the real-time quantity information of each food material to the corresponding quantity in the set of standard quantity information of food materials as a quantity influence coefficient of each food material; and performing weighted calculation on the quantity influence coefficients of each food material in the real-time food material combination to determine the quantity influence factor.

[0016] Through the scheme, the set of standard quantity information of food materials is established to provide a reference benchmark for quantity rationality, and the quantity influence coefficient calculated based on the real-time quantity information can accurately reflect the deviation degree of the quantity of each food material from the standard; and the quantity influence factor obtained by weighting comprehensively quantifies the effect of quantity matching on the influence of the combination, avoiding the evaluation deviation caused by unbalanced quantity; this makes the real-time influence value of the food material combination calculated subsequently more in line with the actual demand of consumers for quantity, helping to optimize the quantity ratio of the food material combination, improve the purchase desire of consumers, and enhance the targeting and effectiveness of the promotion strategy.

[0017] Optionally, the analysis of the freshness information of the real-time food material combination, and the determination of the freshness influence factor, comprises: obtaining a total food material information set, analyzing the freshness change characteristics of each food material in the total food material information set, and determining a freshness change characteristic set; determining a real-time freshness calculation function set based on the freshness change characteristic set; analyzing the real-time food material combination, and determining the sold time and the standard preservation time length of each food material; taking the ratio of the sold time to the standard preservation time length as the independent variable of the calculation function of the real-time freshness calculation function set; analyzing the freshness change characteristics of each food material in the real-time food material combination, and matching the calculation function in the real-time freshness calculation function set, substituting the ratio of the sold time to the standard preservation time length, and calculating the individual preservation factor of each food material; and performing weighted calculation on the individual preservation factors of each food material in the real-time food material combination, and determining the freshness influence factor.

[0018] According to the freshness change characteristics of the food material, the corresponding freshness calculation function is matched, so that the calculation of the individual preservation factor is more in line with the actual freshness change rule of the food material, and deviation caused by the unified calculation method is avoided. By taking the ratio of the sold time to the standard preservation time length as the independent variable of the freshness calculation function, the change of the freshness during the selling cycle of the food material is fully reflected, and the freshness influence factor obtained based on this can accurately reflect the freshness state of the real-time food material combination.

[0019] Optionally, the freshness change characteristic set comprises a freshness linear reduction type characteristic and a freshness exponential reduction type characteristic; the real-time freshness calculation function set comprises a freshness linear reduction function and a freshness exponential reduction function; in the freshness linear reduction function, the freshness of the food material linearly decreases with the independent variable; and in the freshness exponential reduction function, the freshness of the food material exponentially decreases with the independent variable.

[0020] According to the freshness linear reduction type and the freshness exponential reduction type characteristics of the food material, the corresponding freshness calculation function is matched, so that the calculation of the individual preservation factor is more in line with the actual freshness change rule of the food material, and deviation caused by the unified calculation method is avoided. The freshness influence factor obtained based on this can accurately reflect the freshness state of the real-time food material combination, and provides a reliable basis for subsequent calculation of the real-time influence value of the food material combination. This is helpful for accurately evaluating the attractiveness of the food material combination, optimizing the consideration of the freshness in the promotion strategy, improving the satisfaction of consumers on the freshness of the food material, and enhancing the promotion effect.

[0021] Optionally, the method further comprises: analyzing the real-time food material combination to determine the storage information of each food material; the storage information comprises temperature information and humidity information; determining the temperature difference between the temperature information of each food material and the standard storage temperature and the humidity difference between the humidity information of each food material and the standard storage humidity based on the standard storage temperature and the standard storage humidity of each food material; performing weighted summation on the temperature difference and the humidity difference of each food material to determine a food material storage coefficient; determining the weighting value of each food material in the real-time food material combination according to the size of the component value of the real-time component information of each food material; performing weighted calculation on the food material storage coefficient of each food material in the real-time food material combination to determine a storage effect correction factor; and multiplying the freshness influence factor and the storage effect correction factor to correct the freshness influence factor.

[0022] By the scheme, the standard storage temperature and humidity are introduced as a reference, and the food material storage coefficient and the storage effect correction factor are calculated based on the real-time storage information, which effectively quantifies the influence of the actual storage condition on the freshness of the food material and makes up for the limitation of evaluating the freshness only based on time. The corrected freshness influence factor can more truly reflect the actual freshness state of the food material, and the real-time influence value of the food material combination calculated subsequently is more accurate, which helps to develop a more practical promotion strategy, reduces the misjudgment of freshness caused by storage conditions, and improves the recognition and purchase willingness of consumers on the quality of food materials.

[0023] Optionally, the weighting calculation of the food material combination basic influence value based on the regional influence factor, the component influence factor and the freshness influence factor to determine the real-time influence value of the food material combination comprises: analyzing the periodic characteristics of each food material in the real-time food material combination to determine periodic products and non-periodic products; obtaining a food material sales stage, the food material sales stage comprising a non-production period sales stage, an initial production period sales stage, a peak production period sales stage and a final production period sales stage; assigning a seasonal coefficient to each sales stage of the food material to form a food material seasonal coefficient set; the food material seasonal coefficient set comprising a non-production period seasonal coefficient, an initial production period seasonal coefficient, a peak production period seasonal coefficient and a final production period seasonal coefficient; if the food material in the real-time food material combination belongs to the periodic product, obtaining current sales time information and analyzing the current sales time information based on the food material seasonal coefficient set to determine a real-time seasonal coefficient of the food material; if the food material in the real-time food material combination belongs to the non-periodic product, the real-time seasonal coefficient of the food material is fixed as a seasonal baseline value; performing weighted calculation on the real-time seasonal coefficient of each food material in the real-time food material combination to determine a combination seasonal correction coefficient; performing weighted calculation on the regional influence factor, the component influence factor and the freshness influence factor to determine a comprehensive influence factor; and performing product calculation on the food material combination basic influence value, the comprehensive influence factor and the combination seasonal correction coefficient to determine the real-time influence value of the food material combination.

[0024] By the scheme, the periodic and non-periodic products are distinguished, the seasonal coefficient is set in combination with the sales stage, the real-time seasonal coefficient of the food material can accurately reflect the seasonal degree of the food material, the combined seasonal correction coefficient obtained by weighting comprehensively quantifies the overall seasonal influence of the combination, and the real-time influence value of the food material combination is combined with the comprehensive influence factor and the combined seasonal correction coefficient, so that the real-time influence value not only covers the effects of the region, the quantity, and the freshness, but also fully reflects the influence of the seasonal characteristics, and avoids the evaluation deviation caused by ignoring the periodicity. This makes the real-time influence value more in line with market demand, provides a reliable basis for formulating a targeted promotion strategy, helps to highlight the advantages of the seasonal combination, and improves the purchase willingness of consumers and the sales effect. BRIEF DESCRIPTION OF DRAWINGS

[0025] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or the prior art description. Obviously, the drawings in the following description are some embodiments of the present application, and those skilled in the art can obtain other drawings according to these drawings without creative labor.

[0026] Figure 1 An application scenario schematic diagram provided by an embodiment of the present application; Figure 2 A flowchart of an influence analysis method for promoting a combination of goods provided by an embodiment of the present application. DETAILED DESCRIPTION

[0027] In order to make the purpose, technical solutions and advantages of the embodiments of the present application clearer, the following will combine the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are some embodiments of the present application, not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0028] In addition, the term "and / or" in this paper is only to describe the association relationship of the associated objects, which means that there can be three relationships, for example, A and / or B, which can represent the three cases of A alone, A and B together, and B alone. In addition, the character " / " in this paper generally represents an "or" relationship between the associated objects unless otherwise specified.

[0029] The embodiments of the present application will be further described in detail below in combination with the drawings of the specification.

[0030] The prior art often fails to fully combine the correlation characteristics of food material combinations and food material single products in basic sales data, and ignores the dynamic influence of real-time factors such as regional preferences, portion collocations, and food material freshness on the influence of combinations, resulting in a deviation between analysis results and actual market performance, and difficulty in accurately supporting promotion decisions.

[0031] Based on this, the application provides a method for analyzing the influence of a promotion product combination, acquires a food material normal weekly sales data set and a food material combination, and performs coupling analysis on combination sales data and single product sales data to determine a food material combination basic influence value, thereby avoiding the one-sidedness of evaluation caused by separate analysis of single data and providing a reliable basis for subsequent analysis. At the same time, regional influence factors, portion influence factors, and freshness influence factors are determined in combination with real-time food material combinations and current regional information, thereby fully capturing the influence of real-time factors such as regional preferences, portion rationality, and food material freshness on sales. Then, real-time influence values of food material combinations are determined by weighting calculation of these real-time factors and the basic influence value, so that the evaluation results can reflect not only the inherent sales potential of food material combinations but also real-time market dynamics, thereby effectively improving the comprehensiveness and accuracy of promotion product combination influence analysis and providing a scientific basis for formulating targeted promotion strategies.

[0032] Figure 1 An application scenario provided by the application is provided in a promotion food material combination influence analysis scenario, and the method provided by the application is applied to effectively improve the comprehensiveness and accuracy of promotion food material combination influence analysis and provide a scientific basis for formulating targeted promotion strategies.

[0033] Specifically, the method provided by the application is applied in any server, which communicates with a sales system, acquires a food material normal weekly sales data set, a food material combination, real-time food material combinations, and current regional information provided by the sales system, performs coupling analysis on combination sales data and single product sales data to determine a food material combination basic influence value by acquiring a food material normal weekly sales data set and a food material combination, thereby avoiding the one-sidedness of evaluation caused by separate analysis of single data and providing a reliable basis for subsequent analysis. At the same time, regional influence factors, portion influence factors, and freshness influence factors are determined in combination with real-time food material combinations and current regional information, thereby fully capturing the influence of real-time factors such as regional preferences, portion rationality, and food material freshness on sales. Then, real-time influence values of food material combinations are determined by weighting calculation of these real-time factors and the basic influence value, so that the evaluation results can reflect not only the inherent sales potential of food material combinations but also real-time market dynamics, thereby effectively improving the comprehensiveness and accuracy of promotion food material combination influence analysis and providing a scientific basis for formulating targeted promotion strategies. The specific implementation mode can refer to the following embodiments.

[0034] Figure 2A flowchart of a method for analyzing the influence of a promotional product combination is provided for an embodiment of the present application. The method of the embodiment can be applied to the server in the above scenario. As shown in Figure 2 the method includes: S201, obtaining a normal weekly sales data set of food materials and a food material combination, coupling and analyzing combination sales data and single product sales data in the normal weekly sales data set of food materials based on the food material combination, and determining a basic influence value of the food material combination.

[0035] The normal weekly sales data set of food materials can refer to a set of weekly sales data reflecting normal sales conditions obtained by excluding abnormal weekly data affected by bad weather and activities from the historical sales data of food materials. The source is the result of screening and summarizing the historical sales data set of food materials in the sales system. The food material combination can refer to a set of multiple food materials combined together for promotional purposes. The source is the sales system. The combination sales data can refer to sales-related data generated in the sales process of the food material combination as a whole. The single product sales data can refer to sales-related data generated in the sales process of each single food material in the food material combination. The basic influence value of the food material combination can refer to a value reflecting the basic influence of the food material combination obtained by coupling and analyzing the combination sales data and the single product sales data of the food material combination.

[0036] Specifically, when evaluating the influence of a food material combination, the prior art often analyzes the combination sales data or the single product sales data separately, ignoring the coupling relationship between the two, resulting in one-sided evaluation of the basic influence and difficulty in accurately reflecting the true promotional effect of the combination. By obtaining a normal weekly sales data set of food materials and clearly identifying the food material combination to be analyzed, the combination sales data corresponding to the food material combination and the single product sales data of each food material included in the combination are selected from the normal weekly sales data set of food materials. Then, the correlation between the combination sales data and the single product sales data is analyzed, such as the correlation between the combination sales volume and the sum of the sales volumes of each single product, the correlation between the combination repeat purchase situation and the single product repeat purchase situation, and the correlation between the combination profit and the sum of the single product profits. Finally, the coupling relationship of these correlations is comprehensively considered to calculate the basic influence value of the food material combination. By coupling and analyzing the combination sales data and the single product sales data, the interaction (sales volume, repeat purchase rate, and profit) between the food material combination and each single product sales is comprehensively considered, avoiding the evaluation deviation caused by analyzing a certain type of data alone, making the obtained basic influence value of the food material combination more in line with the actual sales situation, providing a reliable basis for subsequent calculation of real-time influence values combined with real-time factors, and improving the scientificity of the evaluation of the influence of promotional combinations.

[0037] S202, obtain real-time food material combination and current regional information, analyze food material information of the real-time food material combination based on the current regional information, determine a regional influence factor, analyze component information of the real-time food material combination, determine a component influence factor, analyze freshness information of the real-time food material combination, and determine a freshness influence factor.

[0038] The real-time food material combination can refer to a food material combination that is currently being promoted or to be evaluated, and the source is the promotion food material combination data updated in real time in the sales system. The current regional information can refer to geographic regional information of a place where the real-time food material combination is sold, and the source is regional data obtained by the sales system. The regional influence factor can refer to a value reflecting the acceptance of the food material combination in the region after analyzing the food material information of the real-time food material combination based on the current regional information. The component influence factor can refer to a value reflecting the rationality of the component combination after analyzing the component information of each food material in the real-time food material combination. The freshness influence factor can refer to a value reflecting the freshness degree of the food material after analyzing the freshness information of each food material in the real-time food material combination.

[0039] Specifically, in the prior art, when evaluating the real-time influence of a food material combination, regional differences, component rationality, and freshness are often ignored, and only basic sales data is relied on, resulting in that the evaluation result of the influence of the food material combination is inconsistent with the actual market acceptance, and the attraction of the combination under different regions, different component combinations, and freshness cannot be accurately reflected. Real-time food material combinations and current regional information are obtained through a sales system; regional acceptance is calculated by comparing the types and combinations of food materials in the real-time food material combination with the dietary preference data of the region based on the current regional information to determine a regional influence factor; component rationality is analyzed by comparing the component data of each food material in the real-time food material combination with the standard component of the corresponding food material to determine a component influence factor; and the freshness degree of the food material is evaluated by collecting the sold time and preservation time of each food material and combining the freshness change characteristics to determine a freshness influence factor. By analyzing the regional adaptability, component rationality, and freshness, the influence of real-time factors on the food material combination is comprehensively captured, and the three influence factors accurately reflect the real-time market demand, providing a reliable basis for subsequent calculation of real-time influence values, improving the timeliness and accuracy of promotion combination evaluation, and helping to optimize promotion strategies.

[0040] S203, according to the regional influence factor, the component influence factor, and the freshness influence factor, the base influence value of the food material combination is weighted and calculated to determine a real-time influence value of the food material combination.

[0041] The real-time influence value of the food material combination can refer to a value reflecting the current real-time promotion influence of the food material combination after weighting and calculating the base influence value of the food material combination by the regional influence factor, the component influence factor, and the freshness influence factor.

[0042] Specifically, the prior art often only relies on the basic impact value when evaluating the impact of food material combinations, ignoring the influence of real-time factors such as regional adaptability, reasonable quantity, and freshness on current sales, resulting in evaluation results that cannot reflect real-time market dynamics. Collect the determined regional impact factor, quantity impact factor, freshness impact factor, and food material combination basic impact value; according to the actual scene and experience of food material sales, determine the weight of each of the three impact factors (such as the regional impact factor weight is higher when the regional difference is larger); according to the determined weight, the three impact factors are weighted and summed to obtain a comprehensive impact factor; then the comprehensive impact factor is calculated with the food material combination basic impact value to obtain the real-time impact value of the food material combination. By combining the real-time impact factors of region, quantity, and freshness to weight and adjust the basic impact value, the obtained real-time impact value of the food material combination can accurately reflect the current market acceptance and attractiveness of the combination, providing a reliable basis for real-time adjustment of promotion strategies, and improving the flexibility and pertinence of promotion management.

[0043] Through the scheme, the food material normal weekly sales data set and the food material combination are obtained, the combination sales data and the single product sales data are coupled and analyzed to determine the food material combination basic impact value, which avoids the one-sidedness of evaluation caused by separate analysis of single data, and provides a reliable basis for subsequent analysis. At the same time, by combining real-time food material combinations and current regional information, regional impact factors, quantity impact factors, and freshness impact factors are determined respectively, and the influence of real-time factors such as regional preference, reasonable quantity, and food material freshness on sales is fully captured. Then, by weighting calculation, the real-time impact value of the food material combination is determined by combining these real-time factors and the basic impact value, so that the evaluation results can not only reflect the inherent sales potential of the food material combination, but also accurately reflect the real-time market dynamics, effectively improving the comprehensiveness and accuracy of the promotion food material combination impact analysis, and providing a scientific basis for formulating targeted promotion strategies.

[0044] In some embodiments, a food material historical sales data set, historical adverse weather information, and historical activity information are obtained; the food material historical sales data set is split and summarized by week to determine a weekly food material historical sales data set; based on the historical adverse weather information, the weekly food material historical sales data set is analyzed to determine a weather-affected weekly food material historical sales data set; based on the historical activity information, the weekly food material historical sales data set is analyzed to determine an activity-affected weekly food material historical sales data set; the weather-affected weekly food material historical sales data set and the activity-affected weekly food material historical sales data set are deleted from the weekly food material historical sales data set to obtain a food material normal weekly sales data set.

[0045] The historical sales data set of food materials can refer to a collection of original records of sales of food materials in a past period of time (such as a month, a quarter, or a year), including sales time, sales volume, repeat purchase rate, and profit of each food material, and the source is historical transaction data stored in a sales system. The historical severe weather information can refer to records of past extreme weather that may affect the sales of food materials, including the occurrence time and area of weather such as heavy rain, heavy snow, and high temperature, and the source is historical meteorological data from a meteorological department. The historical activity information can refer to records of past activities that may affect the sales of food materials, such as promotion activities and festival activities, including activity time and activity content, and the source is the activity planning and execution archives of the merchant. The historical sales data set of food materials by week can refer to a collection of sales data by week after the historical sales data set of food materials is split and summarized by natural week. The historical sales data set of food materials by week affected by weather can refer to a collection of weekly sales data in the historical sales data set of food materials by week that is affected by historical severe weather and leads to abnormal sales volume. The historical sales data set of food materials by week affected by activities can refer to a collection of weekly sales data in the historical sales data set of food materials by week that is affected by historical activities and leads to abnormal sales volume.

[0046] Specifically, in the prior art, when processing sales data of food materials, the data is usually summarized by day, without considering the weekly regularity of food material sales (for example, the purchase frequency on weekends is significantly higher than that on weekdays), resulting in that the data cannot accurately reflect the actual consumption habits. At the same time, if the weekly data containing the influence of severe weather and activities is directly used, the abnormal fluctuations will mask the normal sales trend, making it difficult to distinguish the influence of the combination itself and the effect of external interference based on the analysis, and unable to provide a reliable basis for the evaluation of food material combinations. First, the historical sales data set of food materials is retrieved from the sales system, covering daily sales records in a past period of time (one month, one quarter, or one year); at the same time, historical severe weather information in the same period is obtained from a meteorological database, such as the specific time and area of a snowstorm, and historical activity information is extracted from the activity archives of the merchant, such as a festival promotion activity on a certain day; then the historical sales data set of food materials is split by week, and the sales volume, repeat purchase rate, and profit data of each week are summarized to form the historical sales data set of food materials by week; then the historical severe weather information is compared with the historical sales data set of food materials by week, and the weeks in which the severe weather occurs are found out, and the sales data of these weeks are classified into the historical sales data set of food materials by week affected by weather; similarly, combined with the historical activity information, the weeks in which the activities are carried out are screened out, and the sales data of these weeks are classified into the historical sales data set of food materials by week affected by activities; finally, the two types of abnormal week data are removed from the historical sales data set of food materials by week, and the remaining part is the normal weekly sales data set of food materials.

[0047] According to the scheme, the data is split by week, which conforms to the actual consumption habit of high purchase frequency during weekends, so that the data can more accurately reflect the weekly characteristics of food sales; at the same time, the abnormal weekly data affected by bad weather and activities are excluded, which effectively eliminates external interference, so that the normal weekly sales data set of food can truly reflect the sales trend under normal circumstances, and provides benchmark data without interference and in line with consumption rules for subsequent analysis of the basic influence value of food combination, which helps to more accurately evaluate the inherent influence of food combination and provides a reliable basis for promotion strategy.

[0048] In some embodiments, from the normal weekly sales data set of food, the corresponding combination sales data of the food combination and the single product sales data corresponding to each food involved in the food combination are extracted; the combination sales data includes combination sales volume, combination repeat purchase rate and combination total profit; the single product sales data includes single product sales volume, single product repeat purchase rate and single product total profit; the ratio of the combination sales volume to the sum of the single product sales volumes of all the foods involved in the food combination is taken as the sales coupling coefficient; the single product repeat purchase rates of all the foods involved in the food combination are averaged to determine the average repeat purchase rate, and the ratio of the combination repeat purchase rate to the average repeat purchase rate is taken as the repeat purchase coupling coefficient; the ratio of the combination total profit to the sum of the single product total profits of all the foods involved in the food combination is taken as the profit balance index; a preset weight value is obtained, and the sales coupling coefficient and the repeat purchase coupling coefficient are weighted based on the preset weight value to obtain a basic coupling value; the basic coupling value is multiplied by the profit balance index to obtain the basic influence value of the food combination.

[0049] The sales coupling coefficient can be the ratio of the combination sales volume of the food combination to the sum of the single product sales volumes of all the foods involved in the combination, which reflects the influence of sales on the influence value of the food combination, and the larger the ratio, the better the combination sales performance. The average repeat purchase rate can be the arithmetic mean of the single product repeat purchase rates of all the foods involved in the food combination, which reflects the overall repeat purchase level of the single product. The repeat purchase coupling coefficient can be the ratio of the combination repeat purchase rate of the food combination to the average repeat purchase rate, which reflects the influence of the repeat purchase rate on the influence value of the food combination, and the larger the ratio, the more likely the combination to trigger repeat purchase. The profit balance index can be the ratio of the combination total profit of the food combination to the sum of the single product total profits of all the foods involved in the combination, which reflects the influence of profit on the influence value of the food combination. The preset weight value can be a numerical value preset according to the sales period (such as holidays or non-holidays) to weigh the importance of the sales coupling coefficient and the repeat purchase coupling coefficient. The basic coupling value can be a value obtained by weighting the sales coupling coefficient and the repeat purchase coupling coefficient based on the preset weight value.

[0050] Specifically, the prior art often only considers sales or repeat purchase rate when analyzing the basic influence of food material combinations, ignores the synergistic effect of the two, and does not take into account the profit factor, resulting in one-sided evaluation results; for example, only looking at sales may overestimate combinations with low profits, and only looking at repeat purchase rate may overlook the value of short-term sales explosion, while the importance of sales and repeat purchase rate differs in different sales periods (such as holidays and non-holidays), and there is a lack of dynamic weight adjustment, further affecting the accuracy of the evaluation. First, from the normal weekly sales data of food materials, the corresponding combination sales data of the target food material combination (including combination sales, combination repeat purchase rate, and combination total profit) and the single product sales data of each food material involved in the combination (including single product sales, single product repeat purchase rate, and single product total profit) are extracted; then the sales coupling coefficient is calculated, which is the ratio of combination sales to the sum of all single product sales; the average of the repeat purchase rate is calculated, which is the average of each single product repeat purchase rate; the ratio of the combination repeat purchase rate to the average of the repeat purchase rate is taken as the repeat purchase coupling coefficient; the profit balance index is calculated, which is the ratio of the combination total profit to the sum of all single product total profits; then the preset weight value is obtained, if the current sales period contains holidays, the weight value given to the sales coupling coefficient is greater than the weight value given to the repeat purchase coupling coefficient; if it does not contain holidays, the opposite is true; based on the preset weight value, the sales coupling coefficient and the repeat purchase coupling coefficient are weighted to obtain the basic coupling value; finally, the basic coupling value is multiplied by the profit balance index to obtain the basic influence value of the food material combination; Specifically, taking the "chicken wing + cola" combination as an example, from the normal weekly sales data of food materials, the combination sales data (for example, combination sales of 500, combination repeat purchase rate of 40%, and combination total profit of 3000 yuan) and single product sales data (for example, chicken wing single product sales of 300, repeat purchase rate of 30%, and total profit of 1800 yuan; cola single product sales of 400, repeat purchase rate of 20%, and total profit of 800 yuan) are extracted; the sales coupling coefficient is calculated: 500 ÷ (300 + 400) ≈ 0.71, reflecting the proportion of combination sales to total single product sales; the average of the repeat purchase rate is calculated: (30% + 20%) ÷ 2 = 25%, representing the overall single product repeat purchase level; the repeat purchase coupling coefficient is: 40% ÷ 25% = 1.6, reflecting that the combination repeat purchase is better than the average of the single product; the profit balance index is calculated: 3000 ÷ (1800 + 800) ≈ 1.15, representing that the combination profit is higher than the sum of the single products; if it is a holiday, the preset weight value of the sales coupling coefficient is 0.7 and the repeat purchase coupling coefficient is 0.3, and the basic coupling value = 0.71 × 0.7 + 1.6 × 0.3 ≈ 0.50 + 0.48 = 0.98; the final basic influence value of the food material combination = 0.98 × 1.15 ≈ 1.13.

[0051] By the scheme, the sales coupling coefficient and the repurchase coupling coefficient are calculated, the sales and the repurchase correlation of the combination and the single product are comprehensively considered, the profit balance index is introduced, the profitability is considered, the weight of the sales and the repurchase is dynamically adjusted combined with the preset weight value, the characteristics of different sales periods are adapted, and finally the obtained food material combination basic influence value comprehensively reflects the sales driving, customer stickiness and profitability of the combination, provides a scientific basic reference for subsequent real-time influence value calculation, and improves the systematicness and accuracy of the promotion combination evaluation.

[0052] In some embodiments, a holiday information set and a current sales period are acquired; if the current sales period contains a date in the holiday information set, a first weight value is given to the sales coupling coefficient and a second weight value is given to the repurchase coupling coefficient; the first weight value is greater than the second weight value; if the current sales period does not contain a date in the holiday information set, a third weight value is given to the sales coupling coefficient and a fourth weight value is given to the repurchase coupling coefficient; the third weight value is less than the fourth weight value.

[0053] The holiday information set can refer to a set containing dates of various statutory holidays, traditional holidays and the like, and the source is pre-collected and stored holiday date data. The current sales period can refer to a specific sales time period when the food material combination influence analysis is performed.

[0054] Specifically, in determining the weight of the sales coupling coefficient and the repurchase coupling coefficient, the prior art does not consider the difference between sales periods, and uniformly gives a fixed weight, which cannot accurately match the evaluation focus in holidays (at this time, sales can better reflect the influence of the combination) and non-holidays (at this time, repurchase can better reflect the influence of the combination), so that the calculation of the basic coupling value is out of line with the actual sales law, affecting the accuracy of the food material combination basic influence value. The preset holiday information set is called, which contains the specific dates of statutory holidays (such as the Spring Festival, the National Day), traditional holidays (such as the Mid-Autumn Festival, the Dragon Boat Festival) and promotion holidays (such as store anniversary) set by the merchant throughout the year; then the current sales period, i.e. the time period in which the sales of the food material combination to be analyzed, is determined; then it is judged whether the current sales period contains any date in the holiday information set: if it contains, it means that the sales of the combination at this time period is more critical to the reflection of the influence of the combination, therefore a first weight value (for example, 0.7 as mentioned above) is given to the sales coupling coefficient and a second weight value (for example, 0.3 as mentioned above) is given to the repurchase coupling coefficient, and the first weight value is greater than the second weight value; if it does not contain, it means that the repurchase rate of the combination can better reflect the long-term influence of the combination, therefore a third weight value is given to the sales coupling coefficient and a fourth weight value is given to the repurchase coupling coefficient, and the third weight value is less than the fourth weight value; in this way, the preset weight value suitable for the current sales period is determined.

[0055] According to the scheme, the weights of the sales coupling coefficient and the repurchase coupling coefficient are dynamically adjusted according to whether the current sales period contains a holiday, so that the preset weight value can accurately match the core elements of the combination influence evaluation in different periods, thereby ensuring that the calculation of the basic coupling value is more in line with the actual sales characteristics, providing a reasonable basis for determining the basic influence value of the food material combination, and improving the pertinence and accuracy of the analysis of the influence of the food material combination.

[0056] In some embodiments, the food material information in the real-time food material combination is analyzed to determine a combination dish; the combination dish includes food material information and food material cooking combination information; a set of regional dietary preference information is obtained; the set of regional dietary preference information includes food material preference scores of each region for each food material and food material cooking combination preference scores of each food material combination; based on the set of regional dietary preference information, the combination dish is analyzed to obtain the food material preference scores of each food material and the food material cooking combination preference scores of the food material cooking combination of the combination dish in the current region; the food material preference scores of each food material and the food material cooking combination preference scores of the food material cooking combination in the real-time food material combination are weighted and summed to obtain an acceptance coefficient of the combination dish in the current region; and the acceptance coefficient is used as a regional influence factor.

[0057] The food material cooking combination information can refer to the cooking combination mode of each food material in the combination dish and the combination logic between food materials. The set of regional dietary preference information can include the preference degree scores (food material preference scores) of different regions for each type of food material and the preference degree scores (food material cooking combination preference scores) of each type of food material cooking combination, which are obtained by investigating and statistically analyzing the dietary habits of consumers in each region. The food material preference score can refer to the preference degree quantitative score of the current region for each food material in the real-time food material combination, which is derived from the score record of the corresponding region for the food material in the set of regional dietary preference information. The food material cooking combination preference score can refer to the preference degree quantitative score of the current region for the cooking combination mode of the real-time food material combination, which is derived from the score record of the corresponding region for the cooking combination in the set of regional dietary preference information. The acceptance coefficient can be a value obtained by weighting and summing the food material preference scores of each food material and the food material cooking combination preference scores of its cooking combination in the real-time food material combination, which reflects the overall acceptance degree of the combination dish in the current region.

[0058] Specifically, due to the differences in dietary culture and taste habits, consumers in different regions have different preferences for food materials and cooking combinations. The existing analysis of the influence of food material combinations often ignores the differences in regional preferences and evaluates the influence of combinations uniformly, resulting in evaluation results that are inconsistent with the actual needs of local consumers. By analyzing the real-time food material combination information, the specific composition of the combination dish is determined, and the food material information (such as food material types such as chili, chicken, and ginger) and food material cooking combination information (such as "chicken stir-fried chili with ginger") are clarified. Then, a set of regional dietary preference information is obtained through pre-research and statistics, which covers multiple regions such as Sichuan, Guangdong, and Shandong. Each region records the food material preference scores for common food materials (such as chili, chicken, and ginger) and the food material cooking combination preference scores for common cooking combinations (such as "chicken stir-fried chili" and "chicken steamed with ginger"). Then, based on the current regional information (such as the current region being Sichuan), the food material preference scores for each food material in the combination dish in the Sichuan region (such as chili 85 points, chicken 70 points, and ginger 65 points) and the food material cooking combination preference score for the cooking combination "chicken stir-fried chili with ginger" (such as 80 points) are extracted from the set of regional dietary preference information. Then, according to the importance of the food materials in the combination, the corresponding weights of the food material preference scores are assigned (such as chili weight 0.3, chicken weight 0.4, and ginger weight 0.3), and the weight of the food material cooking combination preference score is assigned (such as 0.5). The weighted sum of the above scores is calculated to obtain the acceptance coefficient of the current region for the combination dish, which is used as the regional influence factor.

[0059] Through this scheme, by combining the current regional information and the set of regional dietary preference information, the food material preference scores and the food material cooking combination preference scores are accurately extracted, and the acceptance coefficient (regional influence factor) calculated can truly reflect the acceptance degree of local consumers for the real-time food material combination, making up for the evaluation deviation caused by ignoring regional differences. This makes the real-time influence value of the food material combination calculated based on the regional influence factor more in line with the local market demand, providing a reliable basis for formulating targeted promotion strategies, and helping to improve the attractiveness and sales volume of the food material combination in the local market, fully playing the role of regional adaptability in promoting the promotion effect.

[0060] In some embodiments, the combination dish is analyzed to determine a set of food material standard quantity information; the set of food material standard quantity information is a set of information of standard quantities of each food material used to make a dish; the real-time quantity information of each food material in the real-time food material combination is extracted; the ratio of the real-time quantity information of each food material to the corresponding quantity in the set of food material standard quantity information is used as the quantity influence coefficient of each food material; and the quantity influence coefficients of each food material in the real-time food material combination are calculated to determine the quantity influence factor.

[0061] The food material standard portion information set can refer to a set of information of standard portions of each food material when used to make a specific combination dish, such as a standard ratio of portions of shrimp and garlic when making "shrimp with garlic", which is determined by investigating the conventional cooking requirements and consumption habits of the combination dish. The real-time portion information can refer to the actual portion information of each food material in the real-time food material combination, such as the specific weights of shrimp and garlic in the current "shrimp with garlic" combination, which is derived from the detection or recording of the portions of the real-time food material combination. The portion influence coefficient can refer to the ratio of the real-time portion information of each food material to the corresponding standard portion in the food material standard portion information set, which is used to measure the deviation of the portion of a single food material from the standard portion.

[0062] Specifically, whether the portion collocation of the food material combination is reasonable directly affects the purchase willingness of consumers, and the existing analysis often ignores the influence of the portion ratio on the combination. For example, if the portion of garlic in the "shrimp with garlic" combination far exceeds the standard, it will lead consumers to feel that the collocation of food materials is unbalanced and has low practicality, thereby reducing the purchase desire. Analyzing the corresponding combination dish of the real-time food material combination, taking "shrimp with garlic" as an example, the food material standard portion information set is determined by investigating the conventional cooking amount and the generally accepted ratio of the dish, for example, the standard portion of shrimp is set to 500 grams, and the standard portion of garlic is set to 100 grams; then, the real-time portion information of each food material in the current real-time food material combination is extracted, assuming that the actual portion of shrimp in the current "shrimp with garlic" combination is 500 grams, and the actual portion of garlic is 200 grams; the portion influence coefficient of each food material is calculated: the portion influence coefficient of shrimp is the ratio of its real-time portion to the standard portion, i.e. 500÷500=1; the portion influence coefficient of garlic is 200÷100=2; according to the importance of each food material in the combination, for example, the weight of shrimp as the main food material is 0.7, and the weight of garlic as the auxiliary food material is 0.3, the portion influence coefficients are weighted and calculated: 1×0.7+2×0.3=1.3, which is the portion influence factor of the real-time food material combination.

[0063] Through the scheme, the food material standard portion information set is established, providing a reference benchmark for portion rationality, and the portion influence coefficient calculated based on the real-time portion information can accurately reflect the deviation of each food material portion from the standard; the portion influence factor obtained by weighting comprehensively quantifies the influence of portion collocation on the combination, avoiding evaluation deviation caused by unbalanced portions; this makes the subsequent calculation of the real-time influence value of the food material combination more in line with the actual needs of consumers for portions, helps to optimize the portion ratio of the food material combination, improves the purchase desire of consumers, and enhances the pertinence and effectiveness of the promotion strategy.

[0064] In some embodiments, a total food material information set is obtained, the freshness change characteristics of each food material in the total food material information set are analyzed, and a freshness change characteristic set is determined; based on the freshness change characteristic set, a real-time freshness calculation function set is determined; the sold time and the standard preservation time length of each food material are determined by analyzing the real-time food material combination; the ratio of the sold time to the standard preservation time length is taken as the independent variable of the calculation function of the real-time freshness calculation function set; the freshness change characteristics of each food material in the real-time food material combination are analyzed, and the calculation function in the real-time freshness calculation function set is matched, and the ratio of the sold time to the standard preservation time length is substituted to calculate the individual preservation factor of each food material; the individual preservation factors of each food material in the real-time food material combination are weighted and calculated to determine the freshness influence factor.

[0065] The total food material information set can refer to an information set containing the basic attributes of various food materials, covering food material names, types, freshness related characteristics, etc., and is derived from a food material database or a category management system. The freshness change characteristic can refer to the law of the change of the freshness of the food material over time during storage and sales. The freshness change characteristic set can be a set composed of the freshness change characteristics of all food materials. The real-time freshness calculation function set can be a function set for calculating the freshness of food materials. The sold time can refer to the cumulative time of the food material from entering the sales link to the current time. The standard preservation time length can refer to the longest time that the food material can maintain good freshness under standard storage conditions. The individual preservation factor can refer to the real-time freshness quantitative value of a single food material, which is calculated by substituting the ratio of the sold time to the standard preservation time length into the corresponding freshness reduction function, and reflects the current freshness state of the food material.

[0066] Specifically, the freshness change laws of different food materials are significantly different, and existing analysis often uses a unified freshness calculation method, ignoring such characteristic differences, resulting in a large deviation between the freshness evaluation and the actual situation. The total food material information set is obtained, covering the basic information of common food materials such as potatoes, shrimps, and green vegetables, the freshness change characteristics of each kind of food material in the set are analyzed, and a freshness change characteristic set is formed; based on the freshness change characteristic set, a real-time freshness calculation function set is constructed; the sold time (assuming that the potato has been sold for 2 days and the shrimp has been sold for 12 hours) and the standard preservation time length (assuming that the standard preservation time length of the potato is 7 days and that of the shrimp is 24 hours) of each food material are extracted by analyzing the real-time food material combination (such as a potato + shrimp combination); the ratio of the sold time to the standard preservation time length is calculated, which is 2 / 7 for the potato and 12 / 24=0.5 for the shrimp; the corresponding function is matched according to the characteristics of the food materials, and the individual preservation factors of the two are calculated respectively; finally, the individual preservation factors are weighted and calculated according to the proportion of the two kinds of food materials in the combination (such as a potato weight of 0.4 and a shrimp weight of 0.6), to obtain the freshness influence factor of the combination.

[0067] By the scheme, the corresponding freshness calculation function is matched according to the freshness change characteristics of the food materials, so that the calculation of the individual preservation factor is more in line with the actual freshness change law of the food materials, and deviation caused by the unified calculation method is avoided; by taking the ratio of the sold time of the food materials to the standard preservation time as the independent variable of the freshness calculation function, the change of the freshness during the selling cycle of the food materials is fully reflected, and the freshness influence factor obtained based on this can accurately reflect the freshness state of the real-time food material combination.

[0068] In some embodiments, the set of freshness change characteristics includes a freshness linear reduction characteristic and a freshness exponential reduction characteristic; the set of real-time freshness calculation functions includes a freshness linear reduction function and a freshness exponential reduction function; in the freshness linear reduction function, the freshness of the food material linearly decreases with the independent variable; in the freshness exponential reduction function, the freshness of the food material exponentially decreases with the independent variable.

[0069] The freshness linear reduction characteristic can refer to that the freshness of the food material linearly decreases with time, such as potatoes, radishes and other storage-resistant food materials. The freshness exponential reduction characteristic can refer to that the freshness of the food material exponentially decreases with time, such as shrimps, meats and other perishable food materials. The freshness linear reduction function can be a function for calculating the freshness of food materials with a freshness linear reduction characteristic, whose freshness linearly decreases with the independent variable (the ratio of the sold time to the standard preservation time). The freshness exponential reduction function can be a function for calculating the freshness of food materials with a freshness exponential reduction characteristic, whose freshness exponentially decreases with the independent variable (the ratio of the sold time to the standard preservation time).

[0070] Specifically, the freshness change laws of different food materials are significantly different, such as potatoes and other storage-resistant food materials whose freshness linearly decreases with time, and shrimps and other perishable food materials whose freshness exponentially decreases rapidly after the critical point of deterioration. The existing analysis usually adopts a unified freshness calculation method, ignoring such characteristic differences, resulting in a large deviation between the freshness evaluation and the actual situation. It is determined that potatoes, radishes and other food materials have a freshness linear reduction characteristic (the freshness uniformly decreases with time), and shrimps, meats and other food materials have a freshness exponential reduction characteristic (the freshness slowly decreases in the early stage and rapidly deteriorates near the critical point of deterioration). The freshness linear reduction function (the freshness linearly decreases with time) is matched for food materials with a linear reduction characteristic (such as potatoes), and the freshness exponential reduction function (the freshness exponentially decreases with time) is matched for food materials with an exponential reduction characteristic (such as shrimps). The individual preservation factors of the two are calculated respectively.

[0071] By the scheme, the freshness degree of food materials is distinguished between linear and exponential reduction characteristics, and corresponding freshness calculation functions are matched, so that the calculation of a single preservation factor is more in line with the actual freshness change rule of food materials, and deviation caused by unified calculation is avoided. The freshness influence factor obtained based on this can accurately reflect the freshness state of the real-time food material combination, and provide a reliable basis for subsequent calculation of real-time influence value of food material combination. This helps to accurately evaluate the attractiveness of food material combination, optimize the consideration of freshness in promotion strategy, improve the satisfaction of consumers on the freshness of food materials, and enhance the promotion effect.

[0072] In some embodiments, the real-time food material combination is analyzed to determine the preservation information of each food material; the preservation information includes temperature information and humidity information; based on the standard preservation temperature and the standard preservation humidity of each food material, the temperature difference between the temperature information of each food material and the standard preservation temperature, and the humidity difference between the humidity information of each food material and the standard preservation humidity are determined; the temperature difference and the humidity difference of each food material are weighted and summed to determine a food material preservation coefficient; the weighting value of each food material in the real-time food material combination is determined according to the size of the component value of the real-time component information of each food material; the preservation effect correction factor is determined by weighted calculation of the food material preservation coefficient of each food material in the real-time food material combination; and the freshness influence factor is multiplied by the preservation effect correction factor to correct the freshness influence factor.

[0073] The standard preservation temperature can refer to the appropriate temperature reference value required by each food material during storage to maintain freshness, such as the standard preservation temperature of meat being 0-4℃, which is derived from food material preservation research data and industry standard specifications. The standard preservation humidity can refer to the appropriate humidity reference value required by each food material during storage to maintain freshness, such as the standard preservation humidity of leafy vegetables being 85%-95%, which is derived from food material preservation research data and industry standard specifications. The food material preservation coefficient can be a value obtained by weighted sum of the temperature difference and the humidity difference of the real-time preservation of the food material, which is used to quantify the deviation of the actual preservation condition of a single food material from the standard condition. The preservation effect correction factor can be a value obtained by weighted calculation of the food material preservation coefficient of each food material in the real-time food material combination, and the weight is determined according to the real-time component of each food material, which is used to correct the freshness influence factor to make it more in line with the actual preservation effect.

[0074] Specifically, the freshness is not only affected by the selling time and the standard preservation time, but also closely related to the actual preservation conditions; for example, if the meat is stored in an environment with a temperature higher than the standard preservation temperature, even if the selling time has not reached the standard preservation time, the freshness will decrease rapidly; if the humidity of leafy vegetables is insufficient, it will wither prematurely; the existing method of calculating the freshness influence factor only by time ratio does not consider the influence of preservation conditions such as temperature and humidity, resulting in deviation between the freshness evaluation and the actual situation, and further affecting the accurate judgment of the influence of food material combination. Analyze each food material in the real-time food material combination to determine its standard preservation temperature and standard preservation humidity; taking the "pork + lettuce" combination as an example, the standard preservation temperature of pork is 0-4℃, and the standard preservation humidity is 70%-80%, the standard preservation temperature of lettuce is 0-2℃, and the standard preservation humidity is 90%-95%; then, the real-time preservation information of each food material in the combination is obtained (assuming that the current storage temperature of pork is 8℃, and the humidity is 60%, the current storage temperature of lettuce is 5℃, and the humidity is 80%); calculate the temperature difference and humidity difference of each food material, the temperature difference of pork is 8-4=4℃ (exceeding the upper limit of the standard), and the humidity difference is 70%-60%=10% (lower than the lower limit of the standard); the temperature difference and humidity difference are assigned weights (such as temperature weight 0.6, humidity weight 0.4), and the food material preservation coefficient is calculated: the preservation coefficient of pork is 4×0.6+10×0.4=2.4+4=6.4; the preservation coefficient of lettuce is 3×0.6+10×0.4=1.8+4=5.8; according to the real-time component, the weight is determined (such as pork component proportion 60%, lettuce 40%), and the food material preservation coefficient is weighted and calculated: 6.4×0.6+5.8×0.4=3.84+2.32=6.16, which is the preservation effect correction factor; finally, the freshness influence factor is multiplied by the preservation effect correction factor to complete the correction of the freshness influence factor.

[0075] By this scheme, the standard preservation temperature and humidity are introduced as the reference, and the food material preservation coefficient and the preservation effect correction factor are calculated combined with the real-time preservation information, which effectively quantifies the influence of the actual preservation conditions on the freshness of the food material, and makes up for the limitations of evaluating the freshness only according to the time. The corrected freshness influence factor can better reflect the actual freshness state of the food material, making the real-time influence value of the food material combination calculated subsequently more accurate, which is helpful for formulating a promotion strategy more in line with the actual situation, reducing the misjudgment of freshness caused by preservation conditions, and improving the recognition and purchase willingness of consumers to the quality of food materials.

[0076] In some embodiments, the periodic characteristics of each food material in the real-time food material combination are analyzed to determine periodic products and non-periodic products; the sales stages of the food materials are obtained, including a non-production stage, an initial production stage, a peak production stage, and a final production stage; a seasonal coefficient is assigned to each sales stage of the food materials to form a food material seasonal coefficient set; the food material seasonal coefficient set includes a non-production seasonal coefficient, an initial production seasonal coefficient, a peak production seasonal coefficient, and a final production seasonal coefficient; if the food materials in the real-time food material combination are periodic products, current sales time information is obtained, and based on the food material seasonal coefficient set, the current sales time information is analyzed to determine a real-time seasonal coefficient of the food materials; if the food materials in the real-time food material combination are non-periodic products, the real-time seasonal coefficient of the food materials is fixed as a seasonal benchmark value; the real-time seasonal coefficient of each food material in the real-time food material combination is weighted to determine a combination seasonal correction coefficient; the regional influence factor, the component influence factor, and the freshness influence factor are weighted to determine a comprehensive influence factor; and the food material combination basic influence value is multiplied by the comprehensive influence factor and the combination seasonal correction coefficient to determine a real-time influence value of the food material combination.

[0077] Periodic products can refer to food materials with a clear supply cycle, such as crawfish, which are only supplied in specific seasons or time periods, and their characteristics come from the supply rules of food material markets. Non-periodic products can refer to food materials with no obvious production cycle, such as pork, which can be produced stably throughout the year, and their characteristics come from the supply rules of food material markets. Food material sales stages can refer to different periods of periodic products in the sales process, including non-production period sales stage (not in the production season), initial production period sales stage (just entering the production season), peak production period sales stage (production season), and end production period sales stage (end of production season), based on the production cycle of periodic products. Food material seasonality coefficient set can refer to a set of seasonality coefficients assigned to each food material sales stage, used to quantify the seasonality of different sales stages, based on market acceptance and quality characteristics of food materials in each stage; non-production period seasonality coefficient can be the coefficient in the food material seasonality coefficient set corresponding to the non-production period sales stage; initial production period seasonality coefficient can be the coefficient in the food material seasonality coefficient set corresponding to the initial production period sales stage; peak production period seasonality coefficient can be the coefficient in the food material seasonality coefficient set corresponding to the peak production period sales stage; end production period seasonality coefficient can be the coefficient in the food material seasonality coefficient set corresponding to the end production period sales stage. Food material real-time seasonality coefficient can be the real-time seasonality coefficient of food material, for periodic products, based on the sales stage where the current sales time is located, the coefficient matched from the food material seasonality coefficient set; for non-periodic products, it is fixed as a seasonality benchmark value, used to quantify the real-time seasonality of a single food material. Seasonality benchmark value can be a fixed seasonality coefficient set for non-periodic products, based on the market performance of non-periodic products. Combination seasonality correction coefficient can be a value obtained by weighting the food material real-time seasonality coefficients of each food material in the real-time food material combination, used to correct the seasonality influence of the combination. Comprehensive influence factor can be a value obtained by weighting the regional influence factor, component influence factor and freshness influence factor, which comprehensively reflects the combined effect of region, component and freshness on the real-time influence of the combination, and the weight is preset based on the importance of each factor.

[0078] Specifically, the periodicity of food materials (whether in season) has a significant impact on consumer purchasing willingness. Seasonal food materials in the peak production period are more popular due to their high quality and sufficient supply, while non-seasonal food materials have decreased appeal. Existing analyses often ignore this characteristic and evaluate both periodic and non-periodic products uniformly, which fails to fully reflect the advantages of seasonal food material combinations and the disadvantages of non-seasonal combinations, causing the real-time influence value of food material combinations to deviate from the actual market demand. This may result in promotional strategies that do not accurately match the seasonal characteristics of food materials, reducing the market appeal of combinations and affecting sales. Analyzing the periodicity of each food material in a real-time food material combination (such as the "small lobster + cucumber" combination, where cucumbers are often used as a side dish for spicy lobster): determine that small lobsters are periodic products (summer is the peak production period), and cucumbers are non-periodic products (greenhouse cultivation, four seasons of supply); obtain the sales stage of food materials, set the sales stage of small lobsters to include the non-production period (winter), the initial production period (early summer), the peak production period (midsummer), and the final production period (early autumn), and construct a set of food material seasonality coefficients: non-production seasonality coefficient 0.3, initial production seasonality coefficient 0.8, peak production seasonality coefficient 1.4, and final production seasonality coefficient 0.6; set the seasonality reference value of non-periodic products to 1.0 (cucumbers are supplied all year round, and their seasonality is stable); if the current sales time is midsummer (the peak production period of small lobsters), the real-time seasonality coefficient of small lobsters is the peak production seasonality coefficient 1.4; cucumbers are non-periodic products, and their real-time seasonality coefficient is fixed at the seasonality reference value 1.0; according to the proportion of the two food materials in the combination (assuming that small lobsters account for 80% and cucumbers account for 20%), calculate the combination seasonality correction coefficient by weighting the real-time seasonality coefficients of the food materials: 1.4 x 0.8 + 1.0 x 0.2 = 1.32; obtain the regional influence factor (such as the current regional preference for spicy taste, the regional influence factor for small lobster combination is 0.9), the component influence factor (the component ratio of small lobsters and cucumbers is reasonable, the component influence factor is 1.1), and the freshness influence factor (small lobsters are fresh and cucumbers are fresh, the freshness influence factor is 1.2), calculate the comprehensive influence factor according to the preset weight (region 0.3, component 0.3, freshness 0.4): 0.9 x 0.3 + 1.1 x 0.3 + 1.2 x 0.4 = 1.08; assuming that the basic influence value of the food material combination is 0.95, multiply it by the comprehensive influence factor and the combination seasonality correction coefficient: 0.95 x 1.08 x 1.32 ≈ 1.35, to obtain the real-time influence value of the "small lobster + cucumber" combination.

[0079] By the scheme, the seasonal degree of the food material is accurately reflected by distinguishing the periodic and non-periodic products, setting the seasonal coefficient combined with the sales stage, and weighting the combination seasonal correction coefficient to comprehensively quantify the overall seasonal influence of the combination. Meanwhile, the combination real-time influence value is obtained by combining the comprehensive influence factor and the combination seasonal correction coefficient, which not only covers the effects of region, quantity and freshness, but also fully reflects the influence of the seasonal characteristics, avoiding the evaluation deviation caused by ignoring the periodicity. This makes the real-time influence value more in line with market demand, providing a reliable basis for formulating targeted promotion strategies, and helping to highlight the advantages of the seasonal combination and improve the purchase willingness of consumers and the sales effect.

Claims

1. An influence analysis method for promoting a product combination, characterized by, The method comprises the following steps: obtaining a normal weekly sales data set of food materials and a food material combination, performing coupling analysis on combination sales data and single product sales data in the normal weekly sales data set of food materials based on the food material combination, and determining a basic influence value of the food material combination; obtaining real-time food material combination and current regional information, analyzing food material information of the real-time food material combination based on the current regional information, determining a regional influence factor, analyzing component information of the real-time food material combination, determining a component influence factor, analyzing freshness information of the real-time food material combination, and determining a freshness influence factor; performing weighted calculation on the basic influence value of the food material combination according to the regional influence factor, the component influence factor and the freshness influence factor, and determining a real-time influence value of the food material combination.

2. The method of claim 1, wherein, The method comprises the following steps: obtaining a normal weekly sales data set of food materials and a food material combination, performing coupling analysis on combination sales data and single product sales data in the normal weekly sales data set of food materials based on the food material combination, and determining a basic influence value of the food material combination; obtaining a normal weekly sales data set of food materials and a food material combination, performing coupling analysis on combination sales data and single product sales data in the normal weekly sales data set of food materials based on the food material combination, and determining a basic influence value of the food material combination; obtaining a normal weekly sales data set of food materials and a food material combination, performing coupling analysis on combination sales data and single product sales data in the normal weekly sales data set of food materials based on the food material combination, and determining a basic influence value of the food material combination; obtaining a normal weekly sales data set of food materials and a food material combination, performing coupling analysis on combination sales data and single product sales data in the normal weekly sales data set of food materials based on the food material combination, and determining a basic influence value of the food material combination; obtaining a normal weekly sales data set of food materials and a food material combination, performing coupling analysis on combination sales data and single product sales data in the normal weekly sales data set of food materials based on the food material combination, and determining a basic influence value of the food material combination.

3. The method of claim 2, wherein, The method comprises the following steps: extracting the combination sales data corresponding to the food material combination and the single product sales data corresponding to each food material involved in the food material combination from the normal weekly sales data set of food materials; the combination sales data comprises combination sales volume, combination repeat purchase rate and combination total profit; the single product sales data comprises single product sales volume, single product repeat purchase rate and single product total profit; the ratio of the combination sales volume to the sum of the single product sales volume of all food materials involved in the food material combination is taken as a sales coupling coefficient; the average of the single product repeat purchase rates of all food materials involved in the food material combination is calculated to determine a repeat purchase rate average value, and the ratio of the combination repeat purchase rate to the repeat purchase rate average value is taken as a repeat purchase coupling coefficient; the ratio of the combination total profit to the sum of the single product total profit of all food materials involved in the food material combination is taken as a profit balance index; obtaining a preset weight value, performing weighted calculation on the sales coupling coefficient and the repeat purchase coupling coefficient based on the preset weight value to obtain a basic coupling value; the product of the basic coupling value and the profit balance index is taken to obtain the basic influence value of the food material combination.

4. The method of claim 3, wherein, The method comprises the following steps: obtaining a holiday information set and a current sales period; if the current sales period contains a date in the holiday information set, a first weight value is assigned to the sales coupling coefficient and a second weight value is assigned to the repeat purchase coupling coefficient. The first weight value is greater than the second weight value; If the current sales period does not contain the date in the holiday information set, a third weight value is assigned to the sales coupling coefficient, and a fourth weight value is assigned to the repeat purchase coupling coefficient; The third weight value is less than the fourth weight value.

5. The method of claim 4, wherein, The regional influence factor is determined based on the current regional information and the analysis of the real-time food material combination information. The combination dish is analyzed to determine the food material information and the food material cooking combination information. Each regional dietary preference information set is obtained. The regional dietary preference information set includes food material preference scores of each food material and food material cooking combination preference scores of each food material combination in each region. Based on the regional dietary preference information set, the combination dish is analyzed to obtain the food material preference scores of each food material and the food material cooking combination preference scores of the food material cooking combination in the current region. The food material preference scores of each food material and the food material cooking combination preference scores of the food material cooking combination in the real-time food material combination are weighted and summed to obtain an acceptance coefficient of the combination dish in the current region. The acceptance coefficient is used as the regional influence factor. The component influence factor is determined by analyzing the component information of the real-time food material combination.

6. The method of claim 5, wherein, The combination dish is analyzed to determine a food material standard component information set. The food material standard component information set is a collection of information about the standard components of each food material used to make dishes. Real-time component information of each food material in the real-time food material combination is extracted. The ratio of the real-time component information of each food material to the corresponding component in the food material standard component information set is used as the component influence coefficient of each food material. The component influence coefficients of each food material in the real-time food material combination are weighted and calculated to determine the component influence factor. The freshness influence factor is determined by analyzing the freshness information of the real-time food material combination.

7. The method of claim 6, wherein, A total food material information set is obtained, and the freshness change characteristics of each food material in the total food material information set are analyzed to determine a freshness change characteristic set. Based on the freshness change characteristic set, a real-time freshness calculation function set is determined. The sold time and standard preservation time of each food material in the real-time food material combination are determined. The ratio of the sold time to the standard preservation time is used as the independent variable of the calculation function in the real-time freshness calculation function set. The freshness change characteristics of each food material in the real-time food material combination are analyzed, and the calculation function in the real-time freshness calculation function set is matched and substituted with the ratio of the sold time to the standard preservation time to calculate the individual preservation factor of each food material. The individual preservation factors of each food material in the real-time food material combination are weighted and calculated to determine the freshness influence factor. Further comprising:

8. The method of claim 7, wherein, The freshness change characteristic set includes freshness linear reduction characteristics and freshness exponential reduction characteristics. The real-time freshness calculation function set includes a freshness linear reduction function and a freshness exponential reduction function. In the freshness linear reduction function, the freshness of the food material decreases linearly with the independent variable. ​ The freshness index decreases exponentially with the independent variable.

9. The method of claim 8, wherein, Also included are: Analyzing the real-time food material combination to determine the storage information of each food material; The storage information includes temperature information and humidity information; Based on the standard storage temperature and the standard storage humidity of each food material, determine the temperature difference between the temperature information of each food material and the standard storage temperature, and the humidity difference between the humidity information of each food material and the standard storage humidity; Weighted sum of the temperature difference and the humidity difference of each food material to determine the food material storage coefficient; According to the size of the component value of the real-time component information of each food material, determine the weighting value of each food material in the real-time food material combination; Weighted calculation of the food material storage coefficient of each food material in the real-time food material combination to determine the storage effect correction factor; Multiply the freshness influence factor and the storage effect correction factor to correct the freshness influence factor.

10. The method of claim 9, wherein, The real-time influence value of the food material combination is determined by weighted calculation of the regional influence factor, the component influence factor and the freshness influence factor, including: Analyzing the periodic characteristics of each food material in the real-time food material combination to determine periodic products and non-periodic products; Obtain the food material sales stage, the food material sales stage includes non-production period sales stage, initial production period sales stage, peak production period sales stage and end production period sales stage; Assign a seasonal coefficient to each sales stage of the food material to form a food material seasonal coefficient set; The food material seasonal coefficient set includes non-production period seasonal coefficient, initial production period seasonal coefficient, peak production period seasonal coefficient and end production period seasonal coefficient; If the food material in the real-time food material combination belongs to the periodic product, obtain the current sales time information, and analyze the current sales time information based on the food material seasonal coefficient set to determine the real-time seasonal coefficient of the food material; If the food material in the real-time food material combination belongs to the non-periodic product, the real-time seasonal coefficient of the food material is fixed as the seasonal benchmark value; Weighted calculation of the real-time seasonal coefficient of each food material in the real-time food material combination to determine the combination seasonal correction coefficient; Weighted calculation of the regional influence factor, the component influence factor and the freshness influence factor to determine the comprehensive influence factor; The real-time influence value of the food material combination is determined by multiplying the food material combination basic influence value and the comprehensive influence factor and the combination seasonal correction coefficient.