E-commerce promotion method based on enterprise condition and market demand design

Abstract

The invention provides an electronic commerce promotion method based on enterprise conditions and market demand design, and relates to the technical field of marketing promotion. Market demand fluctuation factors such as search path complexity, social fission active indexes and a conversion competition rate are considered, so that a product popularization strategy is more accurate and flexible; the demand evaluation is corrected by analyzing a lag influence coefficient in a supply chain, so that a more accurate demand fluctuation prediction value is obtained, and a reliable basis is provided for formulating a final product sorting and popularization strategy; the accuracy of an electronic commerce promotion strategy can be remarkably improved, and the competitiveness of an enterprise in a dynamic environment can be improved.

Description

Technical Field

[0001] The present invention relates to the technical field of marketing promotion, and particularly to an e-commerce promotion method designed based on enterprise conditions and market demands. Background Art

[0002] The existing e-commerce promotion methods often have a relatively single analysis of the combination of market demands and enterprise conditions, lacking in-depth exploration of the multi-factor correlations in a dynamic market environment. These technical deficiencies restrict the competitiveness of enterprises in product promotion. Especially in the environment of multiple products and complex supply chains, it is difficult to comprehensively balance production pressure, market demand fluctuations, and promotion benefits.

[0003] In the prior art, the publication number is CN117237024B, and the name is a promotion method and system for marketing. When the system runs, it collects user behavior data, data on the popularity of products, and user cooperation data through online platform analysis tools to obtain the first data group, the second data group, and the third data group. Then it classifies users and builds user portraits to obtain the needs and preferences of different user groups. By combining and calculating the first data group, the second data group, and the third data group, it obtains: the marketing strategy index Yxcl, the product heat coefficient Sprd, and the user cooperation coefficient Yhph. By setting the user behavior expectation thresholds Z and X, setting the product heat expectation thresholds C and V, and setting the user cooperation expectation thresholds B and N, three strategy evaluation schemes are obtained. By continuously monitoring the system operation situation and the effect of promotion activities, and optimizing and adjusting the system according to the monitoring results.

[0004] The prior art cannot dynamically synchronize market demand fluctuations and enterprise production status. Especially in the scenario of promoting multiple products, there are relatively high requirements for the scientificity of priority ranking and adjustment strategies. The current promotion strategies are mostly simply stratified based on user portraits or mainly rely on static demand forecasting, making it difficult to dynamically adjust supply chain nodes and production priorities. At the same time, the prior art also has less discussion on lag impact factors in demand fluctuation prediction, resulting in insufficient fit between promotion strategies and the actual market.

[0005] The above information disclosed in the above background art section is only used to enhance the understanding of the background of the present disclosure. Therefore, it may include information that does not constitute the prior art known to those of ordinary skill in the art. Summary of the Invention

[0006] In view of the deficiencies in the prior art, the present invention provides an e-commerce promotion method designed based on enterprise conditions and market demands to solve the problems raised in the above background art.

[0007] The object of the present invention is achieved as follows: An e-commerce promotion method designed based on enterprise conditions and market demands, and the specific steps include:

[0008] Step S1: Collect the market demand fluctuation data and enterprise production status data of multiple target products. Among them, the enterprise production status data includes the proportion of product energy consumption and environmental protection cost in the current monitoring period and the product historical inventory backlog pressure coefficient;

[0009] The market demand fluctuation data includes the search path complexity index, social fission activity index, and conversion competition rate of users for similar competing products in the current monitoring period;

[0010] Step S2: Receive and analyze the enterprise production status data of each target product in the current monitoring period to generate a preliminary sorting coefficient. The preliminary sorting coefficient is used to sort the production priorities of multiple target products to obtain a preliminary sorting result;

[0011] Step S3: Receive and analyze the market demand fluctuation data of each target product in the current monitoring period to generate a demand fluctuation evaluation coefficient. The demand fluctuation evaluation coefficient is used to evaluate the market demand fluctuation trend of each target product;

[0012] Step S4: Determine the promotion nodes of the supply chain corresponding to each target product, and collect and analyze the lag impact data of these promotion nodes in the current monitoring period to comprehensively generate a lag impact coefficient representing the supply chain corresponding to each target product;

[0013] Step S5: Introduce the lag impact coefficient into the demand fluctuation evaluation coefficient for correction to obtain the predicted value of the demand fluctuation evaluation coefficient of each target product in the next monitoring period;

[0014] Step S6: According to the predicted value of the demand fluctuation evaluation coefficient of each target product in the next monitoring period, provide an adjustment strategy for the preliminary sorting result to obtain the final sorting result of each target product, and implement the e-commerce promotion strategy with corresponding weights based on the final sorting result.

[0015] Furthermore, uniquely index and mark multiple target products to form a mark set {1, 2,..., i,..., N}, where i represents the index mark of the target product and N represents the total number of target products;

[0016] Define the proportion of product energy consumption and environmental protection cost to represent the proportion of the environmental protection cost generated by the energy consumption and emission treatment of a single target product in the current monitoring period in the total production cost, and denote the proportion of product energy consumption and environmental protection cost of target product i as Set The value range is the interval (0, 1);

[0017] When approaches 0 more closely, it indicates that the impact of the energy consumption and environmental protection cost of the target product i on the total production cost is lower;

[0018] When approaches 1 more closely, it indicates that the impact of the energy consumption and environmental protection cost of the target product i on the total production cost is higher;

[0019] Define that the product historical inventory backlog pressure coefficient is used to characterize the backlog risk degree caused by the current inventory level relative to the sales level, and denote the product historical inventory backlog pressure coefficient of the target product i as , and set the value range is the interval (0, 1);

[0020] When approaches 0 more closely, it indicates that the "inventory level of the target product i is lower" and / or "the sales level is higher", and further represents that the backlog pressure of the target product i is lower;

[0021] When approaches 1 more closely, it indicates that the "inventory level of the target product i is higher" and / or "the sales level is lower", and further represents that the backlog pressure of the target product i is higher.

[0022] Furthermore, define the search path complexity index to characterize the complexity of the search path that the user experiences from the initial search to the final click to purchase for the target product i during the current monitoring period, and denote the search path complexity index of the target product i as , and set the value range is the interval (0, 1);

[0023] When approaches 1 more closely, it indicates that the complexity of the search path of the target product i is higher, indicating that the user hesitates more about the target product i or there are greater problems with the page navigation design;

[0024] When approaches 0 more closely, it indicates that the search path complexity of the target product i is lower, and the user has fewer unnecessary jumps and clicks;

[0025] Define the social fission activity index as the fission propagation ability of the target product i on social media during the current monitoring period, and denote the social fission activity index of the target product i as , and set the value range is the interval (0, 1);

[0026] When approaches 0 more closely, it indicates that during the current monitoring period, the fission propagation ability of the target product i on social media is stronger;

[0027] When When it approaches 1 more, it indicates that the fission propagation ability of the target product i on social media is weaker during the current monitoring time period;

[0028] Define the conversion competition rate of users for similar competing products as the distribution rate of the target product i when users purchase similar products during the current monitoring time period; and denote the conversion competition rate of the target product i as , set The value range is the interval (0, 1);

[0029] When When the value approaches 1 more, it indicates that the proportion of users purchasing the target product i from similar competing products is higher, and thus represents that the competitiveness of the target product i in the market is stronger;

[0030] When When the value approaches 0 more, it indicates that the proportion of users purchasing the target product i from similar competing products is lower, and thus represents that the competitiveness of the target product i in the market is weaker.

[0031] Furthermore, define the preliminary ranking coefficient of the target product i during the current monitoring time period as , and the calculation formula is as follows:

[0032]

[0033] Among them, The output value range is limited within the interval (0, 1);

[0034] is the proportion of the product energy consumption and environmental protection cost of the target product i;

[0035] is the product historical inventory backlog pressure coefficient of the target product i; , and are the weight coefficients of the corresponding parameters;

[0036] When When it approaches 1 more, it indicates that the priority of the target product i is higher;

[0037] When When it approaches 0 more, it indicates that the priority of the target product i is lower;

[0038] Calculate the preliminary ranking coefficients of each target product in the marker set {1, 2,..., i,..., N}, and sort them from large to small according to the calculated preliminary ranking coefficients, The larger the corresponding value, the higher the corresponding production priority;

[0039] When there are at least two target products with the same preliminary ranking coefficient, according to Sort the numerical values from smallest to largest, The smaller it is, the lower the backlog pressure of the corresponding target product;

[0040] Take the order of multiple target products after sorting as the preliminary sorting result.

[0041] Furthermore, define the calculation formula of the demand fluctuation evaluation coefficient as:

[0042]

[0043] Among them, is the demand fluctuation evaluation coefficient of target product i during the current monitoring period, The output value range is limited to the interval (0, 1);

[0044] is the search path complexity index of target product i; is the social fission activity index of target product i; is the conversion competition rate of target product i;

[0045] , and are the weight coefficients of the corresponding parameters, , and , and The values are within the interval (0, 1);

[0046] When gets closer to 1, it means that the demand fluctuation of target product i in the market is greater;

[0047] When gets closer to 0, it means that the demand fluctuation of target product i in the market is smaller.

[0048] Furthermore, the promotion nodes of the supply chain include distributors, retailers, advertising platforms, social media channels, and e-commerce platforms;

[0049] Represent these promotion nodes as a set {1, 2, …, j, …, 5}, where j represents the index mark of the promotion node, and 5 represents the number of promotion nodes; and when j takes the values of 1 or 2 or 3 or 4 or 5 respectively, it represents the distributor, retailer, advertising platform, social media channel, and e-commerce platform;

[0050] The lag effect data includes the promotion node fatigue index and the demand fission lag index;

[0051] Define the promotion node fatigue index as an indicator used to quantify the workload of each promotion node in the supply chain during the execution of promotion activities and the degree of decline in its effectiveness, and denote the promotion node fatigue index of the target product i as ;

[0052] The output value range is in the interval (0, 1). The larger the output value, the higher the promotion fatigue level of the promotion node corresponding to the target product i.

[0053] Calculate the average promotion node fatigue index of the target product i in the promotion node set {1, 2, …, 5}, and denote it as ;

[0054] Define the demand fission lag index as an indicator used to quantify the degree of delay in the demand response time when analyzing the impact of the promotion strategy on the demand of the target product, and denote the demand fission lag index of the target product i as ;

[0055] The output value range is limited to (0, 1). The higher the value, the greater the impact of the demand response lag of the target product i.

[0056] Calculate the average demand fission lag index of the target product i in the promotion node set {1, 2, …, 5}, and denote it as ;

[0057] Define the lag impact coefficient of the supply chain corresponding to the target product i as , and the calculation formula is as follows:

[0058]

[0059] Among them, and are the weight coefficients of the corresponding parameters respectively; and The values are both in the interval (0, 1), and ; The output value range of and / or is (0, 1); if The larger the output value of

[0060] Furthermore, introduce the lag impact coefficient into the demand fluctuation evaluation coefficient for correction to obtain the predicted value of the demand fluctuation evaluation coefficient of each target product in the next monitoring time period, specifically including:

[0061] Set the lag impact coefficient The judgment threshold range is ; It is included in the interval (0.2, 0.8);

[0062] When time, ;

[0063] When time, no correction is made to the demand fluctuation evaluation coefficient;

[0064] When time,

[0065] ;

[0066] Among them, is the predicted value of the demand fluctuation evaluation coefficient of the target product i in the next monitoring period.

[0067] Furthermore, an adjustment strategy is provided for the preliminary sorting result to obtain the final sorting result of each target product, and an e-commerce promotion strategy with corresponding weights is implemented based on this final sorting result, specifically including:

[0068] Obtain the predicted value of the demand fluctuation evaluation coefficient of each target product in the next monitoring period; and set the predicted value of the demand fluctuation evaluation coefficient corresponding to the target product i as ;

[0069] Only when the corresponding to the target product i

[0070] time, raise the sorting position of the target product i by one unit from the preliminary sorting result; and use the adjusted sorting result as the final sorting result;

[0071] Implement the first-weight e-commerce promotion strategy for the target products with the top two production priorities in the final sorting result;

[0072] Implement the second-weight e-commerce promotion strategy for the target products with the third to sixth production priorities in the final sorting result;

[0073] Implement the third-weight e-commerce promotion strategy for the target products with the seventh and subsequent production priorities in the final sorting result;

[0074] The promotion degrees of the first-weight e-commerce promotion strategy, the second-weight e-commerce promotion strategy, and the third-weight e-commerce promotion strategy decrease in turn.

[0075] Compared with the prior art, the beneficial effects of the present invention are:

[0076] 1. By introducing enterprise production status data such as the proportion of energy consumption and environmental protection costs and the inventory backlog pressure coefficient, and considering market demand fluctuation factors such as the complexity of the search path, the active index of social fission, and the conversion competition rate, the product promotion strategy becomes more accurate and flexible.

[0077] 2. By analyzing the lag impact coefficient in the supply chain to correct the demand evaluation, a more accurate demand fluctuation prediction value can be obtained, providing a reliable basis for formulating the final product ranking and promotion strategy; it can not only significantly improve the accuracy of e-commerce promotion strategies, but also enhance the competitiveness of enterprises in a dynamic environment, which is of great significance for improving resource utilization, reducing inventory pressure, and optimizing market investment. BRIEF DESCRIPTION OF THE DRAWINGS

[0078] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are only the embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained according to the provided drawings without creative efforts.

[0079] Figure 1 It is a schematic diagram of the overall method flow of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0080] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present invention.

[0081] Embodiment 1:

[0082] Please refer to Figure 1 , the present invention provides a technical solution:

[0083] An e-commerce promotion method designed based on enterprise conditions and market demand, which is applied to the e-commerce promotion strategies of multiple target products produced by the current enterprise. The specific steps include:

[0084] Step S1: Collect market demand fluctuation data and enterprise production status data of multiple target products. Among them, the enterprise production status data includes the proportion of product energy consumption and environmental protection costs and the product historical inventory backlog pressure coefficient in the current monitoring time period.

[0085] The market demand fluctuation data includes the search path complexity index, the social fission activity index, and the conversion competition rate of users for similar competing products during the current monitoring period;

[0086] Step S2: Receive and analyze the enterprise production status data of each target product during the current monitoring period to generate a preliminary ranking coefficient. The preliminary ranking coefficient is used to rank the production priorities of multiple target products to obtain a preliminary ranking result;

[0087] Step S3: Receive and analyze the market demand fluctuation data of each target product during the current monitoring period to generate a demand fluctuation evaluation coefficient. The demand fluctuation evaluation coefficient is used to evaluate the market demand fluctuation trend of each target product;

[0088] Step S4: Determine the promotion nodes of the supply chain corresponding to each target product, and collect and analyze the lag impact data of these promotion nodes during the current monitoring period to comprehensively generate a lag impact coefficient representing the supply chain corresponding to each target product;

[0089] Step S5: Introduce the lag impact coefficient into the demand fluctuation evaluation coefficient for correction to obtain the predicted value of the demand fluctuation evaluation coefficient of each target product in the next monitoring period;

[0090] Step S6: According to the predicted value of the demand fluctuation evaluation coefficient of each target product in the next monitoring period, provide an adjustment strategy for the preliminary ranking result to obtain the final ranking result of each target product, and implement the e-commerce promotion strategy with the corresponding weight based on the final ranking result.

[0091] Further explanation: Mark multiple target products with unique indexes to form a mark set {1, 2,..., i,..., N}, where i represents the index mark of the target product and N represents the total number of target products;

[0092] The proportion of product energy consumption and environmental protection cost is used to represent the proportion of the environmental protection cost generated by the energy consumption and emission treatment of a single target product during the current monitoring period in the total production cost, and the proportion of product energy consumption and environmental protection cost of target product i is denoted as , set The value range is the interval (0, 1);

[0093] Define The expression is as follows:

[0094]

[0095] Among them, is the proportion of product energy consumption and environmental protection cost of target product i during the current monitoring period;

[0096] is the sensitivity coefficient, which is used to control the steepness of the function, ; is the offset parameter, which is used to control the change of the response area of the function curve within the input interval, ;

[0097] and are determined by experimental fitting and will not be elaborated here;

[0098] is the unit energy consumption of the target product i in the current monitoring period (unit: kWh / piece), which is obtained through the factory energy consumption monitoring equipment;

[0099] is the environmental compliance cost of the target product i in the current monitoring period; the environmental compliance cost includes wastewater treatment and emission monitoring costs, which are obtained through environmental compliance records;

[0100] is the total production cost of the target product i in the current monitoring period, including all production-related costs of the target product i;

[0101] The formula derivation steps are as follows:

[0102] Calculate the proportion of the unit energy consumption of the target product i in the cost ;

[0103] Calculate the proportion of the environmental protection cost of the target product i in the total cost ;

[0104] Add the results of the two and take the average value to comprehensively reflect the energy consumption and environmental protection cost of the product;

[0105] When gets closer to 0, it means that the impact of the energy consumption and environmental protection cost of the target product i on the total production cost is lower; it indicates that the enterprise performs better in terms of energy efficiency and environmental protection;

[0106] When gets closer to 1, it means that the impact of the energy consumption and environmental protection cost of the target product i on the total production cost is higher; it is necessary to optimize the energy efficiency or adjust the production process to improve the impact on the environmental protection burden in the production priority ranking.

[0107] Furthermore, define that the product historical inventory backlog pressure coefficient is used to characterize the degree of backlog risk caused by the current inventory level relative to the sales level, and denote the product historical inventory backlog pressure coefficient of the target product i as , and set the value range to be the interval (0,1);

[0108] Define The expression is as follows:

[0109]

[0110] Wherein, is the inventory backlog pressure coefficient of the target product i in the current monitoring time period;

[0111] is the inventory quantity of the target product i in the current monitoring time period;

[0112] is the historical average inventory quantity of the target product i in the current monitoring time period; the historical average inventory quantity is obtained from the ERP system;

[0113] The ERP system is the abbreviation of the Enterprise Resource Planning system; the inventory management module in the Enterprise Resource Planning system ERP is used to record the incoming, outgoing, and inventory changes of various commodities in real time; provide real-time data on the current inventory status, such as the existing inventory quantity, inventory turnover rate, etc.; and can also generate historical inventory data reports to help enterprises evaluate the inventory health status.

[0114] is the sales quantity of the target product i in the current monitoring time period;

[0115] is the historical average sales quantity of the target product i in the current monitoring time period; the historical average sales quantity is obtained from the ERP system;

[0116] and are the weight coefficients of the corresponding parameters, and and both take values in the interval (0, 1), ; in this embodiment ;

[0117] The formula derivation steps are as follows:

[0118] Calculate the ratio of the current inventory quantity to the historical average inventory quantity: , and characterize as the inventory level;

[0119] Calculate the ratio of the current sales quantity to the historical average sales quantity: , and characterize as the sales level;

[0120] Use the difference-ratio analysis method to divide the two to characterize the backlog pressure of the inventory level relative to the sales level.

[0121] When gets closer to 0, it indicates that the "inventory level of target product i is lower" and / or "sales level is higher", and thus represents a lower backlog pressure for target product i;

[0122] When gets closer to 1, it indicates that the "inventory level of target product i is higher" and / or "sales level is lower", and thus represents a higher backlog pressure for target product i; it is necessary to quickly optimize the inventory and implement promotional measures for target product i to avoid the risk of inventory obsolescence or depreciation.

[0123] Furthermore, a search path complexity index is defined to characterize the complexity of the search path that users experience from the initial search to the final click and purchase of target product i during the current monitoring period, and the search path complexity index of target product i is denoted as , and it is set that the value range is the interval (0, 1);

[0124] The search path complexity index is calculated as follows:

[0125]

[0126] where is the search path complexity index of target product i during the current monitoring period;

[0127] is the total number of clicks generated by the user during the process from the initial search for target product i to the final click and purchase; it is collected through the user behavior logs of the online platform;

[0128] When increases, the value of the numerator of the formula increases as a whole, the exponent rises, reflecting a more complex search path;

[0129] is the number of jumps from one page to another when the user searches for target product i; the number of jumps is tracked through page access records;

[0130] When increases, it indicates that the number of clicks and the complexity also increase, reflecting a multi-page jump link;

[0131] is the total duration (unit: seconds) spent by the user in the complete search path from the initial search for target product i to the final click and purchase;

[0132] When the user's is close to , the weight of the numerator increases significantly and the complexity increases;

[0133] is the time (unit: second) of the longest search path of the entire target product i within the current monitoring time period, and is used for normalization 。

[0134] is the page information entropy of the search path of target product i, and is used to measure the complexity of the page content on the search path;

[0135] Page information entropy ,where is the frequency of page k2 being accessed in the search path, and K2 is the total number of pages;

[0136] If increases, it will cause the denominator of the formula to increase, and the overall complexity is smoothed;

[0137] are the weight coefficients of the corresponding parameters, and are respectively used to measure the impacts of the number of clicks, the number of jumps, the time consumption, and the page complexity on the overall complexity;

[0138] The values are all within the interval (0, 1), and ; The corresponding weights are determined by the entropy weight method and the fuzzy analytic hierarchy process (FAHP);

[0139] Search path complexity index The formula derivation steps are as follows:

[0140] Based on the total number of clicks of the user, more clicks represent a more complex path, and it is directly analyzed through access log records.

[0141] Use the weight to reflect the contribution of the total number of clicks to .

[0142] Number of jumps is a measure of the number of pages accessed by the user in the path. Each jump means that the user has lower confidence in the product or there are problems with the navigation;

[0143] reflects the importance of the jump path in the complexity.

[0144] By normalizing the total time spent in the search path and the time of the longest search path, the comparability of the indicators is ensured;

[0145] Weigh the impact of time on complexity.

[0146] Page information entropy Calculate the complexity of the pages accessed by the search path, measured by the page access distribution of the path; a higher information entropy indicates an even distribution of information for each page and an increase in navigation complexity.

[0147] Use the in the denominator Smooth the gain in path complexity to reduce the excessive impact of a single path on the final exponent.

[0148] When The closer it gets to 1, the higher the complexity of the search path for the target product i, indicating that users are more hesitant about the target product i or there are greater problems with the page navigation design;

[0149] Optimization strategies: Simplify the page navigation structure, reduce the number of redirected pages, and design a more intuitive and user-friendly search and purchase process.

[0150] When users spend too much time making decisions, the enterprise can promote the product or focus on optimizing the navigation layout to reduce the path complexity.

[0151] When The closer it gets to 0, the lower the complexity of the search path for the target product i, indicating fewer unnecessary redirects and clicks by users;

[0152] Optimization strategies: Do not intervene too much, but continue to maintain the user experience of high-quality products. At the same time, similar navigation methods can be copied to other target products.

[0153] Furthermore, define the social fission activity indicator as the fission propagation ability of the target product i on social media during the current monitoring period, and denote the social fission activity indicator of the target product i as , set The value range is the interval (0, 1);

[0154] The social fission activity indicator of the target product i The calculation formula is as follows:

[0155]

[0156] Among them, is the number of times the topic related to the target product i has been shared during the current monitoring period, obtained through the API of the social platform;

[0157] is the number of comments on the topic related to the target product i during the current monitoring period, obtained through the API of the social platform;

[0158] is the number of likes for topics related to target product i during the current monitoring period, obtained through the API of the social platform;

[0159] is the basic interaction quantity for topics related to target product i during the current monitoring period, used to standardize the activity;

[0160] The basic interaction quantity includes the combination of the number of shares, the number of comments, and the number of likes;

[0161] , , and are the weight coefficients of the corresponding parameters, respectively measuring the influence degrees of the number of shares, the number of comments, the number of likes, and the basic interaction quantity,

[0162] , , and take values within the interval (0, 1), and ;

[0163] , , and are determined by the entropy weight method and the fuzzy analytic hierarchy process (FAHP);

[0164] Use function, aiming to compress the data magnitude difference, avoid the influence of outliers, and ensure the non-negativity of the formula.

[0165] The basic interaction quantity is introduced into the denominator to smooth the activity index and avoid excessive increase of the exponent.

[0166] When gets closer to 0, it indicates that during the current monitoring period, the fission propagation ability of target product i on the social media is stronger;

[0167] When gets closer to 1, it indicates that during the current monitoring period, the fission propagation ability of target product i on the social media is weaker;

[0168] Furthermore, define the conversion competition rate of users for similar competing products as the distribution rate of target product i when users purchase similar products during the current monitoring period; and denote the conversion competition rate of target product i as , set the value range to be the interval (0, 1);

[0169] Define the conversion competition rate The calculation formula is as follows:

[0170]

[0171] Among them, is the number of times the user selects to purchase the target product i during the monitoring period; collected through distributed network tracking identifiers;

[0172] is the total number of times the user selects to purchase similar competing products during the monitoring period, compared through online sales data of competing products;

[0173] and are the weight coefficients of the corresponding parameters, and take values in the interval (0, 1), and ;

[0174] and are determined through the entropy weight method and the fuzzy analytic hierarchy process (FAHP);

[0175] When gets closer to 1, it means that the proportion of the user purchasing the target product i from similar competing products is higher, and thus represents that the target product i has stronger competitiveness in the market; traditional promotion investment can be reduced, and focus on maintaining brand evaluation and product quality;

[0176] When gets closer to 0, it means that the proportion of the user purchasing the target product i from similar competing products is lower, and thus represents that the target product i has weaker competitiveness in the market; brand exposure and market promotion budget need to be increased, product positioning needs to be re - examined, and product feature optimization and competitor analysis need to be strengthened.

[0177] Further explanation: Define the preliminary ranking coefficient of the target product i in the current monitoring period as , and the calculation formula is as follows:

[0178]

[0179] Among them, the output value range is limited to the interval (0, 1);

[0180] is the proportion of the product energy consumption and environmental protection cost of the target product i;

[0181] is the product historical inventory backlog pressure coefficient of the target product i;

[0182] , and is the weight coefficient of the corresponding parameter, , and takes values within the interval (0, 1), and ;

[0183] , and the corresponding weights are determined by the entropy weight method and the fuzzy analytic hierarchy process (FAHP);

[0184] indicates that the lower the proportion of product energy consumption and environmental protection cost, the higher; to reflect the excellent performance of the enterprise in environmental protection and energy efficiency; this expression increases the weight of lower energy consumption and cost;

[0185] indicates that the lower the coefficient of historical inventory backlog pressure of the product, the higher; the higher the priority of the corresponding target product i;

[0186] In the denominator, is used to smooth the priorities of different target products and avoid the excessive influence of extreme values on the sorting result;

[0187] When gets closer to 1, it indicates that the priority of target product i is higher; it shows that the target product i is more popular in the market and the enterprise has higher efficiency in the production process; the enterprise can choose to increase the production volume of this product or optimize the resource allocation to enhance competitiveness;

[0188] When gets closer to 0, it indicates that the priority of target product i is lower; furthermore, it characterizes that target product i has high energy consumption, environmental protection burden and high inventory pressure; the enterprise needs to re-evaluate the production strategy of this product and needs to reduce the production volume or conduct promotions to clear the inventory risk.

[0189] Calculate the preliminary sorting coefficients of each target product in the marker set {1, 2,..., i,..., N}, and sort them from large to small according to the calculated preliminary sorting coefficients, the larger the corresponding value, the higher the corresponding production priority;

[0190] When there are at least two target products with the same preliminary sorting coefficients, sort them from small to large according to the value, the smaller it is, the lower the backlog pressure of the corresponding target product;

[0191] Take the order of multiple sorted target products as the preliminary sorting result.

[0192] Further explanation: The calculation formula for defining the demand fluctuation evaluation coefficient is as follows:

[0193]

[0194] where, is the demand fluctuation evaluation coefficient of the target product i within the current monitoring time period, and its output value range is limited to the interval (0, 1);

[0195] is the search path complexity index of the target product i; is the social fission activity index of the target product i; is the conversion competition rate of the target product i;

[0196] , and are the weight coefficients of the corresponding parameters, , and , and take values within the interval (0, 1); , and are determined through the entropy weight method and the fuzzy analytic hierarchy process (FAHP);

[0197] Use to reflect the reverse change of the path complexity;

[0198] Use to represent the reverse change of the social fission activity index;

[0199] When gets closer to 1, it indicates that the demand fluctuation of the target product i in the market is greater;

[0200] When gets closer to 0, it indicates that the demand fluctuation of the target product i in the market is smaller.

[0201] Further explanation: The promotion nodes of the supply chain include distributors, retailers, advertising platforms, social media channels, and e-commerce platforms;

[0202] These promotion nodes are represented as a set {1, 2, …, j, …, 5}, where j represents the index mark of the promotion node, and 5 represents the number of promotion nodes; and when j takes values of 1 or 2 or 3 or 4 or 5 respectively, it represents the distributor, retailer, advertising platform, social media channel, and e-commerce platform;

[0203] Explanation for the distributor as a promotion node:

[0204] During the process of distributors transferring target products from producers to retailers, they will experience a certain fatigue index (such as the decline in the frequency and effectiveness of promotional activities). At the same time, their influence will also lead to the fission of product demand, with a lag, and the purchasing behavior triggered by the products that customers learn about through distributors.

[0205] Explanation of retailers as promotion nodes:

[0206] Retailers are the nodes that directly contact consumers, and their promotion and marketing strategies (specifically, promotional activities, display methods, etc.) will affect consumers' purchasing decisions. The fatigue index of retailers can reflect the changes in promotional effects, while the fluctuations in their inventory and sales can reflect the lag of demand fission.

[0207] Explanation of advertising platforms (such as search engines, social media advertising) as promotion nodes:

[0208] The audience of online advertising may be interested in the product, but the behavior of converting this interest into purchases is usually lagged. Advertising platforms can provide data such as ad click-through rates and conversion rates to calculate the fatigue index and the impact of demand fission lag.

[0209] Explanation of social media channels as promotion nodes:

[0210] The effects of sharing and recommending on social media may not be obvious in the short term. However, in the long run, the social fission effect will have a significant impact. Social media analysis tools can monitor the fatigue index of the frequency of content sharing and user engagement.

[0211] Explanation of e-commerce platforms as promotion nodes:

[0212] Promotional activities on these platforms (such as limited-time promotions, special offers) can quantify the effects and track their lagged impact on sales, especially when consumers see special offers and decide to make a purchase later.

[0213] The lagged impact data includes the promotion node fatigue index and the demand fission lag index;

[0214] Defining the promotion node fatigue index is an indicator used to quantify the workload of each promotion node in the supply chain when implementing promotional activities and the degree of decline in their effectiveness;

[0215] The calculation formula for defining the promotion node fatigue index is as follows:

[0216]

[0217] Among them, is the promotion node fatigue index of target product i in the current monitoring time period;

[0218] is the average daily operation load of the target product i during the current monitoring period; the average operation load represents the ratio between the actual promotion operation frequency executed by the promotion node and the maximum operation promotion frequency that can be achieved by this promotion node; the larger the value, the higher the promotion frequency and the better the promotion effect.

[0219] is the error during the peak period of the promotion work of the target product i during the current monitoring period; the error during the peak period of the promotion work refers to the ratio between the delay time of the promotion content and the time actually spent on promotion; the larger the value, the more time the promotion content spends and the better the promotion effect.

[0220] , and are the weight coefficients of the corresponding parameters, , and all take values within the interval (0, 1), and ;

[0221] , and are determined by the entropy weight method and the fuzzy analytic hierarchy process (FAHP) for the corresponding weights;

[0222] The output value range is within the interval (0, 1), the larger the output value, the higher the promotion fatigue level of the promotion node corresponding to the target product i;

[0223] Calculate the average promotion node fatigue index of the target product i in the promotion node set {1, 2, …, 5}, denoted as ;

[0224]

[0225] where, represents the promotion node fatigue index of the target product i at the promotion node j;

[0226] Define that the demand fission lag index is an index that quantifies the degree of delay in the demand response time when analyzing the impact of the promotion strategy on the demand of the target product;

[0227] Define the calculation formula of the demand fission lag index as follows:

[0228]

[0229] where, is the demand fission lag index of the target product i during the current monitoring period;

[0230] The output value range is limited to (0, 1), The higher the value, the greater the lagged impact of the demand response of target product i;

[0231] is the lag distribution of the demand response time of target product i;

[0232]

[0233] where, is the response time of the h-th user; is the start time of the promotion activity; is the total number of user responses;

[0234] The higher it is, the greater the lag in the distribution of user response time, and the impact of the promotion strategy on sales gradually spreads;

[0235] The lower it is, the more concentrated the user response, and the more quickly the promotion activity can reach users;

[0236] is the sales volume time-varying curve, indicating the time characteristics of demand changes;

[0237] The sales volume time-varying curve is used to describe the change pattern of sales volume over time to observe the sales volume fluctuations of the promotion activity in different time periods;

[0238] Record the sales volume data of target product i at different time periods through the e-commerce platform or distributors;

[0239] Let be the sales volume of the target product at time t; through the sales volume data, calculate the sales volume change rate within the time period, which is defined by the following formula:

[0240]

[0241] where, is the sales volume at the start time of the promotion activity; is the maximum sales volume within the observation window;

[0242] The higher it is, the greater the sales volume change or the greater the time change trend caused by the promotion activity;

[0243] The lower it is, the weaker the sales volume change of the promotion activity or the flatter the time change trend;

[0244] , and are the weight coefficients of the corresponding parameters, , and all take values within the interval (0, 1), and ;

[0245] , and the corresponding weights are determined by the entropy weight method and the fuzzy analytic hierarchy process (FAHP).

[0246] Calculate the average demand fission lag index of the target product i in the promotion node set {1, 2,..., 5}, denoted as ;

[0247]

[0248] where represents the demand fission lag index of the target product i at the promotion node j;

[0249] Define the lag impact coefficient of the supply chain corresponding to the target product i as , and the calculation formula is as follows:

[0250]

[0251] where and are the weight coefficients of the corresponding parameters respectively; and all take values within the interval (0, 1), and ; and the corresponding weights are determined by the entropy weight method and the fuzzy analytic hierarchy process (FAHP). The output value range of and / or is (0, 1); if the larger the output value of

[0252] Further explanation: The lag impact coefficient is introduced into the demand fluctuation evaluation coefficient for correction to obtain the predicted value of the demand fluctuation evaluation coefficient of each target product in the next monitoring time period, specifically including:

[0253] Set the judgment threshold range of the lag impact coefficient as ; is included in the interval (0.2, 0.8);

[0254] When , ;

[0255] Defining the lag impact coefficient has a proportional relationship with the predicted value of the demand fluctuation evaluation coefficient of target product i in the next monitoring time period. Since it has a high impact on the social fission activity index and conversion competition rate in the demand fluctuation evaluation coefficient, the predicted value of the demand fluctuation evaluation coefficient is in an increasing trend;

[0256] When then ;

[0257] Since it has a small impact on the social fission activity index and conversion competition rate in the demand fluctuation evaluation coefficient, and the demand activity is insufficient, the predicted value of the demand fluctuation evaluation coefficient of target product i in the next monitoring time period has a decreasing trend;

[0258] When then no correction is made to the demand fluctuation evaluation coefficient;

[0259] At this time, the promotion degree corresponding to the lag impact coefficient has a medium impact on the social fission activity index and conversion competition rate in the demand fluctuation evaluation coefficient, the demand activity is medium, and the fluctuation range of the predicted value of the demand fluctuation evaluation coefficient of target product i in the next monitoring time period is small and negligible. Therefore, no correction is made to the demand fluctuation evaluation coefficient;

[0260] Among them, is the predicted value of the demand fluctuation evaluation coefficient of target product i in the next monitoring time period;

[0261] The setting principle of the judgment threshold range is: when the output value of the lag impact coefficient is in the interval the influence degree on the value of the demand fluctuation evaluation coefficient is within 2%; It is specifically determined by the fuzzy analytic hierarchy process (FAHP) and will not be elaborated here.

[0262] Further explanation: Provide adjustment strategies for the preliminary ranking results to obtain the final ranking results of each target product, and implement e-commerce promotion strategies with corresponding weights based on the final ranking results. Specifically, it includes:

[0263] Obtain the predicted values of the demand fluctuation evaluation coefficients of each target product in the next monitoring time period;

[0264] And set the adjustment threshold of the predicted value of the demand fluctuation evaluation coefficient corresponding to target product i as , ;

[0265] Only when When it is, raise the sorting position of the target product i by one unit in the preliminary sorting result; and use the adjusted sorting result as the final sorting result;

[0266] Specifically: If the target product i is ranked 3 in the preliminary sorting result, when the When it is, the sorting position of the target product i is 2; that is, the production priority is the 2nd;

[0267] The target product i is not adjusted when it is ranked 1 in the preliminary sorting result.

[0268] Implement the e-commerce promotion strategy with corresponding weights, specifically:

[0269] Implement the first-weight e-commerce promotion strategy for the target products with the top two production priorities in the final sorting result;

[0270] The first-weight e-commerce promotion strategy includes, but is not limited to, search engine optimization, social media marketing, content marketing, email marketing, video marketing, online promotion activities, and precision advertising; the purpose of adjusting the first-weight e-commerce promotion strategy is to make The increase range is more than 20% of the current value;

[0271] Implement the second-weight e-commerce promotion strategy for the target products with the production priorities ranked third to sixth in the final sorting result;

[0272] The second-weight e-commerce promotion strategy includes social media marketing, content marketing, email marketing, and online promotion activities; the purpose of adjusting the second-weight e-commerce promotion strategy is to make The increase range is between 10% and 20% of the current value;

[0273] Implement the third-weight e-commerce promotion strategy for the target products with the production priorities ranked seventh and later in the final sorting result;

[0274] The third-weight e-commerce promotion strategy includes social media marketing and online promotion activities; the purpose of adjusting the second-weight e-commerce promotion strategy is to make The increase range is within 10% of the current value;

[0275] The promotion degrees of the first-weight e-commerce promotion strategy, the second-weight e-commerce promotion strategy, and the third-weight e-commerce promotion strategy decrease in turn.

[0276] Search engine optimization is to improve the ranking in search engines and increase natural traffic by optimizing website content and structure. Specifically, use specific keywords, create high-quality content, and obtain external links.

[0277] Social media marketing is to promote on social media platforms (such as Weibo, WeChat, Douyin, Instagram, etc.), and enhance brand awareness and promote product sales by posting content, advertisements or interacting with users.

[0278] Content marketing is to create valuable content, such as blog posts, videos, infographics, etc., to attract potential customers and increase brand trust. Providing educational content can enhance customers' understanding of products.

[0279] Email marketing is to keep in touch with potential and existing customers by sending regular newsletters and personalized promotional emails, and enhance customer loyalty and repeat purchase rate.

[0280] Video marketing is to produce short videos of product demonstrations, reviews or brand stories, and post them on video platforms (such as YouTube, Bilibili) to visually attract users and increase the interaction rate.

[0281] Online promotional activities are to organize promotional strategies such as special offers, limited-time discounts, group purchases, full reduction activities, etc., to attract consumers to make quick purchases.

[0282] Precision advertising placement is to use consumer data to implement precision marketing to ensure that advertisements are delivered to the most relevant target audience groups. Utilize big data analysis and machine learning technologies to optimize advertising effects.

[0283] Through the above description of the implementation methods, those skilled in the art can clearly understand that the present invention can be implemented by means of software and necessary general hardware. Of course, it can also be implemented by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as a floppy disk, read-only memory (ROM), random access memory (RAM), flash memory, hard disk or optical disc of a computer, etc., including several instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) to execute the methods of various embodiments of the present invention.

[0284] The logic and / or steps represented in the flowchart or otherwise described herein can, for example, be considered a definitional sequence of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, a system including a processor, or other systems that can fetch and execute instructions from the instruction execution system, apparatus, or device. As used in this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.

[0285] It should be understood that various parts of the present invention can be implemented by hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, any one or a combination of the following techniques well known in the art can be used: discrete logic circuits having logic gate circuits for implementing logical functions on data signals, application specific integrated circuits having appropriate combinational logic gate circuits, programmable gate arrays (PGAs), field programmable gate arrays (FPGAs), and the like. It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical solutions of the present invention, and they should all be covered by the scope of the claims of the present invention.

[0286] The description of the above embodiments is only used to help understand the method and its core idea of the present invention. It should be pointed out that for those of ordinary skill in the art, without departing from the principle of the present invention, several improvements and modifications can be made to the present invention, and these improvements and modifications also fall within the protection scope of the claims of the present invention.

Claims

1. An e-commerce promotion method designed based on enterprise conditions and market demands, which is applied to the e-commerce promotion strategies of multiple target products produced by current enterprises, and is characterized in that The specific steps include: Step S1: Collect the market demand fluctuation data and enterprise production status data of multiple target products. Among them, the enterprise production status data includes the product energy consumption and the proportion of environmental protection costs and the product historical inventory backlog pressure coefficient during the current monitoring period; The market demand fluctuation data includes the search path complexity index, the social fission activity index, and the conversion competition rate of users for similar competing products during the current monitoring period; Step S2: Receive and analyze the enterprise production status data of each target product during the current monitoring period to generate a preliminary sorting coefficient. The preliminary sorting coefficient is used to sort the production priorities of multiple target products to obtain a preliminary sorting result; Step S3: Receive and analyze the market demand fluctuation data of each target product during the current monitoring period to generate a demand fluctuation evaluation coefficient. The demand fluctuation evaluation coefficient is used to evaluate the market demand fluctuation trend of each target product; Step S4: Determine the promotion nodes of the supply chain corresponding to each target product, and collect and analyze the lag impact data of these promotion nodes during the current monitoring period to comprehensively generate a lag impact coefficient used to characterize the supply chain corresponding to each target product; Step S6: Introduce the lag impact coefficient into the demand fluctuation evaluation coefficient for correction to obtain the predicted value of the demand fluctuation evaluation coefficient of each target product in the next monitoring period; Step S7: According to the predicted value of the demand fluctuation evaluation coefficient of each target product in the next monitoring period, provide an adjustment strategy for the preliminary sorting result to obtain the final sorting result of each target product, and implement the e-commerce promotion strategy with corresponding weights based on the final sorting result; 2. The e-commerce promotion method designed based on enterprise conditions and market demands according to claim 1, wherein: Mark multiple target products with unique indexes to form a mark set {1, 2,..., i,..., N}, where i represents the index mark of the target product and N represents the total number of target products; Define the proportion of product energy consumption and environmental protection cost to characterize the proportion of the environmental protection cost generated by the energy consumption and emission treatment of a single target product in the current monitoring period to the total production cost, and denote the proportion of product energy consumption and environmental protection cost of target product i as , and set The value range is the interval (0, 1); When As it approaches 0 more and more, it means that the impact of the energy consumption and environmental protection cost of target product i on the total production cost is lower; When When it gets closer to 1, it means that the impact of the energy consumption and environmental protection cost of target product i on the total production cost is higher; Define that the product historical inventory backlog pressure coefficient is used to characterize the degree of backlog risk caused by the current inventory level relative to the sales level, and denote the product historical inventory backlog pressure coefficient of the target product i as , and set The value range is the interval (0, 1); When As it approaches 0 more and more, it means that the "inventory level of target product i is lower" and / or "sales level is higher", and further represents that the backlog pressure of target product i is lower; When As it approaches 1 more closely, it indicates that the "inventory level of target product i is higher" and / or "sales level is lower", and further represents that the backlog pressure of target product i is higher.

3. The e-commerce promotion method designed based on enterprise conditions and market demands according to claim 2, characterized in that: Define a search path complexity metric to characterize the complexity of the search path that users experience from the initial search to the final click and purchase of the target product i during the current monitoring time period, and denote the search path complexity metric of the target product i as , and set The value range is the interval (0, 1); When As it gets closer to 1, it indicates that the complexity of the search path for the target product i is higher, suggesting that the user hesitates more about the target product i or there are greater problems with the page navigation design; When When it gets closer to 0, it means that the search path complexity of the target product i is lower, and the user's redundant jumps and clicks are fewer; Define the social fission activity index as the fission propagation ability of target product i on social media during the current monitoring period, and denote the social fission activity index of target product i as , and set The value range is the interval (0, 1); When As it gets closer to 0, it indicates that the fission propagation ability of target product i on social media is stronger during the current monitoring time period; When The closer it is to 1, the weaker the fission propagation ability of the target product i on social media during the current monitoring time period; Define the conversion competition rate of users for similar competing products as the distribution rate of target product i when users purchase similar products during the current monitoring time period; and denote the conversion competition rate of target product i as , and set The value range is the interval (0, 1); When The closer the value is to 1, the higher the proportion of users purchasing the target product i from competing products of the same category, which in turn represents stronger competitiveness of the target product i in the market; When The closer the value is to 0, the lower the proportion of users purchasing the target product i from competing products of the same category, which in turn represents weaker competitiveness of the target product i in the market.

4. An e-commerce promotion method designed based on enterprise conditions and market demands according to claim 3, characterized in that: Define the preliminary ranking coefficient of the target product i within the current monitoring time period as , and the calculation formula is as follows: ； Among them, the output value range is limited within the interval (0, 1); is the proportion of the product energy consumption and environmental protection cost of the target product i; is the product historical inventory backlog pressure coefficient of target product i; , and are the weight coefficients of the corresponding parameters; When The closer it is to 1, the higher the priority of the target product i is; When As it approaches 0 more closely, it indicates that the priority of target product i is lower; Calculate the preliminary sorting coefficients of each target product in the calculation tag set {1, 2, …, i, …, N}, and sort them from largest to smallest according to the calculated preliminary sorting coefficients. The larger the corresponding value, the higher the corresponding production priority. When there are at least two initial sorting coefficients of the target products that are the same, according to the values, sort them from small to large, the smaller value represents that the backlog pressure of the corresponding target product is lower; Take the order of multiple sorted target products as the preliminary sorting result; 5. An e-commerce promotion method designed based on enterprise conditions and market demands according to claim 4, characterized in that: Define the calculation formula of the demand fluctuation evaluation coefficient as: ； Among them, is the demand fluctuation evaluation coefficient of the target product i during the current monitoring time period, and the output value range is limited to the interval (0, 1); is the search path complexity index of the target product i; is the social fission activity index of the target product i; is the conversion competition rate of the target product i; , and are the weight coefficients of the corresponding parameters, , and , and take values in the interval (0, 1); When As it approaches 1 more closely, it indicates that the demand fluctuation of target product i in the market is greater; When As it approaches 0 more and more, it means that the demand fluctuation of target product i in the market is smaller.

6. The e-commerce promotion method designed based on enterprise conditions and market demands according to claim 5, characterized in that: The promotion nodes of the supply chain include distributors, retailers, advertising platforms, social media channels, and e-commerce platforms; Represent these promotion nodes as a set {1, 2,..., j,..., 5}, where j represents the index mark of the promotion node and 5 represents the number of promotion nodes; and when j takes values of 1 or 2 or 3 or 4 or 5, it represents a distributor, a retailer, an advertising platform, a social media channel, and an e-commerce platform respectively; The lag impact data includes the promotion node fatigue index and the demand fission lag index; Define that the promotion node fatigue index is an indicator used to quantify the workload of each promotion node in the supply chain during the execution of promotion activities and the degree of decline in its effectiveness, and denote the promotion node fatigue index of the target product i as ; The output value range is in the interval (0, 1), The larger the output value, the higher the promotion fatigue level of the promotion node corresponding to the target product i; Calculate the average promotion node fatigue index of the target product i in the promotion node set {1, 2, …, 5}, denoted as ; Define the demand fission lag index as an indicator that quantifies the degree of delay in demand response time when analyzing the impact of promotion strategies on the demand for the target product, and denote the demand fission lag index of the target product i as ; The output value range is limited to (0, 1), The higher the value, the greater the lagged impact on the demand response of target product i; Calculate the average demand fission lag index of the target product i in the promotion node set {1, 2, …, 5}, denoted as ; Define the lag impact coefficient of the supply chain corresponding to the target product i as , and the calculation formula is as follows: ； Among them, and are the weight coefficients of the corresponding parameters respectively; and both take values in the interval (0, 1), and ; the output value range of and / or is (0, 1); if the larger the output value of and / or , the higher the "promotion fatigue level" and / or the greater the "impact of demand response lag" of the supply chain corresponding to the target product i.

7. An e-commerce promotion method designed based on enterprise conditions and market demands according to claim 6, characterized in that: Introduce the lag impact coefficient into the demand fluctuation evaluation coefficient for correction to obtain the predicted value of the demand fluctuation evaluation coefficient of each target product in the next monitoring period, specifically including: Set the hysteresis influence coefficient The judgment threshold range is ; Contained in the interval (0.2, 0.8); When then ; When it is not necessary to correct the evaluation coefficient for demand fluctuations; When then ； Among them, is the predicted value of the demand fluctuation evaluation coefficient of the target product i in the next monitoring time period.

8. An e-commerce promotion method designed based on enterprise conditions and market demands according to claim 7, characterized in that: Provide an adjustment strategy for the preliminary sorting result to obtain the final sorting result of each target product, and implement the e-commerce promotion strategy with corresponding weights based on the final sorting result, specifically including: Obtain the predicted value of the demand fluctuation evaluation coefficient of each target product in the next monitoring time period; and set the predicted value of the demand fluctuation evaluation coefficient corresponding to target product i The adjustment threshold of , ; Only when the following corresponding to the target product i is satisfied, the sorting position of the target product i is increased by one unit in the preliminary sorting result; and the adjusted sorting result is used as the final sorting result. Implement the e-commerce promotion strategy with corresponding weights, specifically: Implement the first weight e-commerce promotion strategy for the two target products with the highest production priorities in the final sorting result; Implement the second-weight e-commerce promotion strategy for the target products ranked third to sixth in production priority in the final sorting result; Implement the third-weight e-commerce promotion strategy for the target products ranked seventh and later in production priority in the final sorting result; The promotion degrees of the first-weight e-commerce promotion strategy, the second-weight e-commerce promotion strategy, and the third-weight e-commerce promotion strategy decrease in turn.

Images