An e-commerce promotion method based on enterprise conditions and market demand design

Abstract

This invention provides an e-commerce promotion method based on enterprise conditions and market demand, belonging to the field of marketing and promotion technology. By introducing enterprise production status data such as energy consumption and environmental protection cost ratios, and inventory backlog pressure coefficients, and considering market demand fluctuation factors such as search path complexity, social media viral activity indicators, and conversion competition rates, this invention makes product promotion strategies more precise and flexible. By analyzing the lag effect coefficient in the supply chain to correct demand evaluation, it obtains more accurate demand fluctuation predictions, providing a reliable basis for formulating final product ranking and promotion strategies. This not only significantly improves the accuracy of e-commerce promotion strategies but also enhances the enterprise's competitiveness in a dynamic environment.

Description

Technical Field

[0001] This invention relates to the field of marketing and promotion technology, specifically to an e-commerce promotion method designed based on the company's situation and market demand. Background Technology

[0002] Existing e-commerce promotion methods often present a simplistic analysis of market demand and company circumstances, lacking in-depth exploration of the multi-factor relationships within a dynamic market environment. These technological deficiencies constrain a company's competitiveness in product promotion, especially in multi-product, complex supply chain environments, making it difficult to comprehensively balance production pressures, market demand fluctuations, and promotional effectiveness.

[0003] In the prior art, under announcement number CN117237024B, entitled "A Promotion Method and System for Marketing," the system collects user behavior data, product popularity data, and user cooperation data through online platform analysis tools to obtain a first data group, a second data group, and a third data group. Users are then categorized and user profiles are created to obtain the needs and preferences of different user groups. By combining the first, second, and third data groups, the system calculates: a marketing strategy index Yxcl, a product popularity coefficient Sprd, and a user cooperation coefficient Yhph. By setting expected thresholds Z and X for user behavior, C and V for product popularity, and B and N for user cooperation, three strategy evaluation schemes are obtained. The system continuously monitors its operation and the effectiveness of promotional activities, and optimizes and adjusts the system based on the monitoring results.

[0004] Existing technologies cannot dynamically synchronize market demand fluctuations with enterprise production status, especially in multi-product promotion scenarios, where the scientific requirements for prioritization and adjustment strategies are high. Current promotion strategies are mostly based on simple user profile segmentation or static demand forecasting, making it difficult to dynamically adjust supply chain nodes and production priorities. At the same time, existing technologies have limited discussion on lagging factors in demand fluctuation forecasting, resulting in insufficient alignment between promotion strategies and the actual market.

[0005] The information disclosed in the background section above is only intended to enhance the understanding of the background of this disclosure, and therefore may include information that does not constitute prior art known to those skilled in the art. Summary of the Invention

[0006] In view of the shortcomings of the existing technology, the present invention provides an e-commerce promotion method designed based on the enterprise situation and market demand, so as to solve the problems mentioned in the background technology.

[0007] The objective of this invention is achieved as follows: an e-commerce promotion method designed based on enterprise circumstances and market demand, comprising the following specific steps:

[0008] Step S1: Collect market demand fluctuation data and enterprise production status data for multiple target products. The enterprise production status data includes the proportion of product energy consumption and environmental protection costs and the historical inventory backlog pressure coefficient of the product during the current monitoring period.

[0009] Market demand fluctuation data includes search path complexity metrics, social sharing activity metrics, and user conversion rates against similar competing products during the current monitoring period.

[0010] Step S2: Receive and analyze the enterprise production status data of each target product during the current monitoring period to generate preliminary ranking coefficients. The preliminary ranking coefficients are used to rank the production priorities of multiple target products to obtain preliminary ranking results.

[0011] 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 assess 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 during the current monitoring period to comprehensively generate a lag impact coefficient for characterizing the supply chain corresponding to each target product.

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

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

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

[0016] The product energy consumption and environmental cost ratio is defined to characterize the proportion of the environmental costs generated by energy consumption and emission treatment of a single target product in the total production cost during the current monitoring period, and is denoted as the product energy consumption and environmental cost ratio of target product i. ,set up The range is the interval (0,1);

[0017] when The closer it is to 0, the lower the impact of the energy consumption and environmental protection costs of the target product i on the total production cost.

[0018] when The closer it is to 1, the higher the impact of the energy consumption and environmental protection costs of the target product i on the total production cost.

[0019] The historical inventory backlog pressure coefficient is defined as a factor used to characterize the degree of backlog risk caused by the current inventory level relative to the sales level, and is denoted as follows: ,set up The range is the interval (0,1);

[0020] when The closer it is to 0, the lower the "inventory level" and / or the higher the "sales level" of target product i, which in turn represents the lower the backlog pressure of target product i.

[0021] when The closer it is to 1, the higher the "inventory level" and / or the lower the "sales level" of target product i, which in turn represents the higher the backlog pressure of target product i.

[0022] Furthermore, a search path complexity metric is defined to characterize the search path complexity experienced by a user from initial search to final purchase click for target product i within the current monitoring period. The search path complexity metric for target product i is then defined as follows: ,set up The range is the interval (0,1);

[0023] when The closer it is to 1, the higher the complexity of the search path for target product i, indicating that users are more hesitant about target product i or that there are greater problems with the page navigation design.

[0024] when The closer it is to 0, the lower the complexity of the search path for the target product i, and the fewer unnecessary jumps and clicks the user makes.

[0025] Define the social viral spread activity metric as the viral spread capability of target product i on social media within the current monitoring period, and label the social viral spread activity metric of target product i as follows: ,set up The range is the interval (0,1);

[0026] when The closer the value is to 0, the stronger the viral spread of target product i on social media during the current monitoring period.

[0027] when The closer the value is to 1, the weaker the viral spread of target product i on social media during the current monitoring period.

[0028] Define the user conversion rate of competing products as the distribution rate of users choosing target product i when purchasing similar products during the current monitoring period; and denote the conversion rate of target product i as... ,set up The range is the interval (0,1);

[0029] when The closer the value is to 1, the higher the proportion of users purchasing target product i from similar competing products, which in turn represents the stronger competitiveness of target product i in the market.

[0030] when The closer the value is to 0, the lower the proportion of users purchasing target product i from similar competing products, which in turn indicates that target product i is less competitive in the market.

[0031] Furthermore, the preliminary ranking coefficient of target product i within the current monitoring period is defined as follows: The calculation formula is as follows:

[0032]

[0033] in, The output range is limited to the interval (0,1);

[0034] It represents the ratio of energy consumption to environmental protection costs for target product i.

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

[0036] when The closer it is to 1, the higher the priority of target product i.

[0037] when The closer it is to 0, the lower the priority of target product i.

[0038] Calculate the initial ranking coefficient for each target product in the label set {1,2,…,i,…,N}, and sort them from largest to smallest according to the calculated initial ranking coefficient. The larger the corresponding value, the higher the production priority;

[0039] When at least two target products have the same initial ranking coefficient, according to Sort the values ​​in ascending order. The smaller the value, the lower the inventory pressure of the corresponding target product;

[0040] The order of the multiple target products after sorting is used as the preliminary sorting result.

[0041] Furthermore, the formula for calculating the demand fluctuation evaluation coefficient is defined as follows:

[0042]

[0043] in, It is the demand fluctuation evaluation coefficient for target product i during the current monitoring period. The output range is limited to the interval (0,1);

[0044] It is an indicator of the search path complexity of target product i; It is a social sharing activity metric for target product i; It is the conversion rate of target product i;

[0045] , and These are the weighting coefficients of the corresponding parameters. ,and , and The value is within the interval (0,1);

[0046] when The closer it is to 1, the greater the fluctuation in market demand for target product i.

[0047] when The closer it is to 0, the smaller the fluctuation in demand for target product i in the market.

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

[0049] These promotion nodes are represented as a set {1,2,…,j,…,5}, where j represents the index of the promotion node and 5 represents the number of promotion nodes; and when j takes the values ​​1, 2, 3, 4 or 5, they represent distributors, retailers, advertising platforms, social media channels and e-commerce platforms, respectively.

[0050] Lagging impact data include the promotion node fatigue index and the demand fission lag index;

[0051] The promotion node fatigue index is defined as an indicator used to quantify the workload and the degree of decline in effectiveness of each promotion node in the supply chain when performing promotional activities. The promotion node fatigue index for target product i is denoted as... ;

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

[0053] Calculate the average promotion node fatigue index of target product i across the promotion node set {1,2,…,5}, denoted as . ;

[0054] The demand fission lag index is defined as an indicator that quantifies the delay in demand response time when analyzing the impact of promotion strategies on the demand for a target product. The demand fission lag index for target product i is denoted as... ;

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

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

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

[0058]

[0059] in, and These are the weighting coefficients of the corresponding parameters; and The values ​​all fall within the interval (0,1), and ; The output range is (0,1); if and / or The larger the output value, The larger the output value, the higher the "promotion fatigue level" and / or the greater the "demand response lag effect" of the supply chain corresponding to the target product i.

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

[0061] Setting the lag effect coefficient The judgment threshold range is ; It is contained within the interval (0.2, 0.8);

[0062] when hour, ;

[0063] when At that time, no correction was made for the evaluation coefficient of demand fluctuation;

[0064] when hour,

[0065] ;

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

[0067] Furthermore, adjustment strategies are provided based on the preliminary ranking results to obtain the final ranking results for each target product. Based on these final ranking results, e-commerce promotion strategies with corresponding weights are implemented, specifically including:

[0068] Obtain the predicted value of the demand fluctuation evaluation coefficient for each target product in the next monitoring period; and set the predicted value of the demand fluctuation evaluation coefficient corresponding to target product i. The adjustment threshold is , ;

[0069] Only if the target product i corresponds to When the initial sorting result is reached, the sorting position of target product i is increased by one unit; and the adjusted sorting result is used as the final sorting result.

[0070] Implement e-commerce promotion strategies with corresponding weights, specifically:

[0071] The top two target products in the final ranking will be subject to the first-weight e-commerce promotion strategy.

[0072] For the target products ranked third to sixth in the final ranking results, implement a second-weighted e-commerce promotion strategy;

[0073] For target products ranked seventh or lower in the final ranking results, a third-weight e-commerce promotion strategy will be implemented.

[0074] The promotional intensity of the first-weighted e-commerce promotion strategy, the second-weighted e-commerce promotion strategy, and the third-weighted e-commerce promotion strategy decreases in that order.

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

[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 search path complexity, social fission activity indicators, and conversion competition rate, product promotion strategies become more precise and flexible.

[0077] 2. By analyzing the lag effect coefficient in the supply chain to correct demand evaluation, more accurate demand fluctuation forecasts can be obtained, providing a reliable basis for formulating final product ranking and promotion strategies. This not only significantly improves the accuracy of e-commerce promotion strategies but also enhances the competitiveness of enterprises in dynamic environments. It is of great significance for improving resource utilization, reducing inventory pressure, and optimizing market investment. Attached Figure Description

[0078] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0079] Figure 1 This is a schematic diagram of the overall method flow of the present invention. Detailed Implementation

[0080] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0081] Example 1:

[0082] Please see Figure 1 The present invention provides a technical solution:

[0083] An e-commerce promotion method designed based on the company's situation and market demand, applied to the e-commerce promotion strategy of multiple target products currently produced by the company, includes the following steps:

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

[0085] Market demand fluctuation data includes search path complexity metrics, social sharing activity metrics, and user conversion rates against 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 preliminary ranking coefficients. The preliminary ranking coefficients are used to rank the production priorities of multiple target products to obtain preliminary ranking results.

[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 assess 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 for characterizing the supply chain corresponding to each target product.

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

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

[0091] Further explanation: Multiple target products are uniquely indexed and labeled to form a label set {1,2,...,i,...,N}, where i represents the index label of the target product and N represents the total number of target products;

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

[0093] definition The expression is as follows:

[0094]

[0095] in, It represents the ratio of product energy consumption to environmental protection costs for target product i during the current monitoring period.

[0096] It is a sensitivity coefficient used to control the steepness of the function. ; This is the offset parameter, used to control the variation of the function curve's response region within the input interval. ;

[0097] and The determination was made through experimental fitting, and will not be elaborated further.

[0098] It is the unit energy consumption (unit, kilowatt-hour / unit) of target product i during the current monitoring period, obtained through the factory energy consumption monitoring equipment;

[0099] This refers to the environmental compliance costs of the target product i during the current monitoring period; environmental compliance costs include wastewater treatment and discharge monitoring costs, which are obtained through environmental compliance records.

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

[0101] The derivation steps of the formula are as follows:

[0102] Calculate the proportion of unit energy consumption to cost for target product i. ;

[0103] Calculate the proportion of environmental costs to total costs for target product i. ;

[0104] The results of the two are added together and averaged to comprehensively reflect the product's energy consumption and environmental costs;

[0105] when The closer the value is to 0, the lower the impact of energy consumption and environmental costs of target product i on the total production cost; indicating that the company performs better in energy efficiency and environmental protection.

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

[0107] Furthermore, the historical inventory backlog pressure coefficient is defined as a coefficient used to characterize the degree of backlog risk caused by the current inventory level relative to the sales level, and the historical inventory backlog pressure coefficient of target product i is denoted as... ,set up The range is the interval (0,1);

[0108] definition The expression is as follows:

[0109]

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

[0111] This is the inventory quantity of target product i during the current monitoring period;

[0112] This is the historical average inventory level of target product i during the current monitoring period; the historical average inventory level is obtained from the ERP system.

[0113] ERP system is short for Enterprise Resource Planning system; the inventory management module in an ERP system is used to record the inbound, outbound, and inventory changes of various goods in real time; it provides real-time data on the current inventory status, such as current inventory level and inventory turnover rate; and it can also generate historical inventory data reports to help companies assess the health of their inventory.

[0114] It represents the sales volume of target product i during the current monitoring period;

[0115] It is the historical average sales volume of target product i during the current monitoring period; the historical average sales volume is obtained from the ERP system.

[0116] and These are the weighting coefficients for the corresponding parameters, and and The values ​​all fall within the interval (0,1). This embodiment ;

[0117] The derivation steps of the formula are as follows:

[0118] Calculate the ratio of current inventory level to historical average inventory level: and will This is represented by inventory levels;

[0119] Calculate the ratio of current sales volume to historical average sales volume: and will This is represented by sales levels;

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

[0121] when The closer it is to 0, the lower the "inventory level" and / or the higher the "sales level" of target product i, which in turn represents the lower the backlog pressure of target product i.

[0122] when The closer the value is to 1, the higher the "inventory level" and / or the lower the "sales level" of target product i, which in turn indicates a higher backlog pressure for target product i. It is necessary to quickly optimize the inventory and implement promotional measures for target product i in order to avoid the risk of inventory obsolescence or loss.

[0123] Furthermore, a search path complexity metric is defined to characterize the search path complexity experienced by a user from initial search to final purchase click for target product i within the current monitoring period. The search path complexity metric for target product i is then defined as follows: ,set up The range is the interval (0,1);

[0124] Search path complexity metrics The calculation formula is as follows:

[0125]

[0126] in, It is the search path complexity metric for target product i during the current monitoring period;

[0127] This refers to the total number of clicks generated by a user from the initial search for a target product to the final purchase decision; collected through user behavior logs on the online platform.

[0128] when When the value increases, the numerator of the formula increases overall. The rise in the index reflects a more complex search path.

[0129] This refers to the number of times a user navigates from one page to another when searching for a target product i; the number of page jumps is tracked through page access records.

[0130] when When the number increases, it indicates the number of clicks, and the complexity also increases, reflecting the multi-page navigation path;

[0131] It is the total time (in seconds) that a user spends on the complete search path from initially searching for the target product i to finally clicking to purchase.

[0132] When the user near At this time, the molecular weight increases significantly, and the complexity increases;

[0133] This is the time (in seconds) of the longest search path for the entire target product i within the current monitoring period, used for normalization. .

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

[0135] Page information entropy ,in This represents the frequency with which page k2 is accessed in the search path, where K2 is the total number of pages.

[0136] like Increase, will lead to The denominator of the formula is increased, and the overall complexity is smoothed out;

[0137] These are the weighting coefficients for the corresponding parameters, used to measure the impact of click count, redirect count, time consumption, and page complexity on the overall complexity.

[0138] The values ​​all fall within the interval (0,1), and ; The corresponding weights are determined using the entropy weight method and the fuzzy hierarchical analysis method (FAHP).

[0139] Search path complexity metrics The derivation steps of the formula are as follows:

[0140] Based on the user's total number of clicks More clicks indicate a more complex path, which can be analyzed directly through access logs.

[0141] Use weights Reflecting the total number of clicks . contributions.

[0142] Number of jumps It is a measure of the number of pages a user visits in the path. Each jump indicates that the user has low confidence in the product or that there is a problem with the navigation.

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

[0144] By comparing the total time spent in the search path with the time of the longest search path Normalization is performed to ensure the comparability of indicators;

[0145] Weigh the impact of time on complexity.

[0146] Page information entropy The complexity of the pages accessed by the search path is calculated and measured by the distribution of page access along the path; higher information entropy indicates that the information distribution on each page is more even, and the navigation complexity increases.

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

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

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

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

[0151] when The closer it is to 0, the lower the complexity of the search path for the target product i, and the fewer unnecessary jumps and clicks the user makes.

[0152] Optimization strategy: No excessive intervention is needed, but the user experience of high-quality products should continue to be maintained, while similar navigation methods can be replicated to other target products.

[0153] Furthermore, the social viral marketing activity metric is defined as the viral spread capability of target product i on social media within the current monitoring period, and the social viral marketing activity metric of target product i is marked as follows: ,set up The range is the interval (0,1);

[0154] Social sharing activity metrics for target product i The calculation formula is as follows:

[0155]

[0156] in, This refers to the number of times topics related to the target product i were shared during the current monitoring period, obtained through the social media platform's API.

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

[0158] It is the number of likes on topics related to the target product i within the current monitoring period, obtained through the social platform's API;

[0159] It is the basic number of interactions with topics related to target product i during the current monitoring period, used to standardize activity level;

[0160] The basic interaction count includes a combination of the number of shares, comments, and likes.

[0161] , , and These are the weighting coefficients for the corresponding parameters, which respectively measure the impact of the number of shares, comments, likes, and basic interaction count.

[0162] , , and The values ​​all fall within the interval (0,1), and ;

[0163] , , and The corresponding weights are determined using the entropy weight method and the fuzzy hierarchical analysis method (FAHP).

[0164] use The purpose of this function is to compress differences in data magnitude, avoid the influence of outliers, and ensure the non-negativity of the formula.

[0165] The denominator incorporates the basic number of interactions to smooth out the activity index and prevent the index from increasing excessively.

[0166] when The closer the value is to 0, the stronger the viral spread of target product i on social media during the current monitoring period.

[0167] when The closer the value is to 1, the weaker the viral spread of target product i on social media during the current monitoring period.

[0168] Furthermore, the conversion rate of users competing for similar products is defined as the distribution rate of users choosing target product i when purchasing similar products during the current monitoring period; and the conversion rate of target product i is denoted as... ,set up The range is the interval (0,1);

[0169] Define the conversion rate of target product i The calculation formula is as follows:

[0170]

[0171] in, This refers to the number of times a user selects to purchase target product i within the monitoring period; data is collected through distributed network tracking identifiers.

[0172] It is the total number of times a user chooses to purchase similar competing products within the monitoring period, which is compared using the online sales data of competing products.

[0173] and These are the weighting coefficients of the corresponding parameters. and The value is within the interval (0,1), and ;

[0174] and The corresponding weights are determined using the entropy weight method and the fuzzy hierarchical analysis method (FAHP).

[0175] when The closer the value is to 1, the higher the proportion of users purchasing target product i from similar competing products, which in turn indicates that target product i is more competitive in the market; it can reduce traditional promotion investment and focus on maintaining brand reputation and product quality;

[0176] when The closer the value is to 0, the lower the proportion of users purchasing target product i from similar competing products, which in turn indicates that target product i is less competitive in the market; it is necessary to increase brand exposure and marketing budget, re-examine product positioning, and increase product feature optimization and competitor analysis.

[0177] Further explanation: The preliminary ranking coefficient of target product i within the current monitoring period is defined as follows: The calculation formula is as follows:

[0178]

[0179] in, The output range is limited to the interval (0,1);

[0180] It represents the ratio of energy consumption to environmental protection costs for target product i.

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

[0182] , and These are the weighting coefficients of the corresponding parameters. , and The value is within the interval (0,1), and ;

[0183] , and The corresponding weights are determined using the entropy weight method and the fuzzy hierarchical analysis method (FAHP).

[0184] This indicates that the lower the proportion of energy consumption and environmental costs in a product, the better. The higher the value, the better it reflects the company's superior performance in environmental protection and energy efficiency; this expression gives greater weight to lower energy consumption and costs.

[0185] The lower the historical inventory backlog pressure coefficient of a product, the better. The higher the priority, the higher the priority of the corresponding target product i.

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

[0187] when The closer the value is to 1, the higher the priority of target product i; this indicates that target product i is more popular in the market and the company is more efficient in the production process; the company can choose to increase the production volume of this product or optimize resource allocation to enhance its competitiveness.

[0188] when The closer the value is to 0, the lower the priority of target product i. This indicates that target product i has high energy consumption, environmental burden and high inventory pressure. The company needs to re-evaluate the production strategy of this product and needs to reduce output or carry out promotions to clear inventory risks.

[0189] Calculate the initial ranking coefficient for each target product in the label set {1,2,…,i,…,N}, and sort them from largest to smallest according to the calculated initial ranking coefficient. The larger the corresponding value, the higher the production priority;

[0190] When at least two target products have the same initial ranking coefficient, according to Sort the values ​​in ascending order. The smaller the value, the lower the inventory pressure of the corresponding target product;

[0191] The order of the multiple target products after sorting is used as the preliminary sorting result.

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

[0193]

[0194] in, It is the demand fluctuation evaluation coefficient for target product i during the current monitoring period. The output range is limited to the interval (0,1);

[0195] It is an indicator of the search path complexity of target product i; It is a social sharing activity metric for target product i; It is the conversion rate of target product i;

[0196] , and These are the weighting coefficients of the corresponding parameters. ,and , and The value is within the interval (0,1); , and The corresponding weights are determined using the entropy weight method and the fuzzy hierarchical analysis method (FAHP).

[0197] use This reflects the inverse change in path complexity;

[0198] use This indicates a reverse change in the social fission activity index;

[0199] when The closer it is to 1, the greater the fluctuation in market demand for target product i.

[0200] when The closer it is to 0, the smaller the fluctuation in demand for target product i in the market.

[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 of the promotion node and 5 represents the number of promotion nodes; and when j takes the values ​​1, 2, 3, 4 or 5, they represent distributors, retailers, advertising platforms, social media channels and e-commerce platforms, respectively.

[0203] Explanation regarding distributors as promotional nodes:

[0204] Distributors experience fatigue as they transfer target products from manufacturers to retailers (e.g., a decrease in the frequency and effectiveness of promotional activities). Simultaneously, their influence can lead to a lag in product demand, with purchasing behavior triggered by customers learning about the product through distributors.

[0205] Explanation regarding retailers as promotional nodes:

[0206] Retailers are the direct point of contact with consumers, and their promotional and marketing strategies (specifically, promotional activities, display methods, etc.) influence consumers' purchasing decisions. Retailer fatigue index can reflect changes in promotional effectiveness, while fluctuations in inventory and sales can reflect the lag in demand shifts.

[0207] Explanation regarding advertising platforms (such as search engines and social media ads) as promotion nodes:

[0208] While online advertising may generate interest in a product, the conversion of that interest into a purchase is often delayed. Advertising platforms can provide data such as click-through rates and conversion rates to calculate fatigue levels and the impact of delayed demand.

[0209] Explanation regarding social media channels as promotional nodes:

[0210] The effects of sharing and recommending on social media may not be immediately apparent; however, in the long run, the social fission effect can have a significant impact. Social media analytics tools can track the frequency of content sharing and user engagement fatigue levels.

[0211] Explanation regarding e-commerce platforms as promotional nodes:

[0212] Promotional activities on these platforms (such as limited-time offers and special deals) can be quantified and their lagged impact on sales can be tracked, especially when consumers see special offers and decide to buy later.

[0213] Lagging impact data include the promotion node fatigue index and the demand fission lag index;

[0214] The promotion node fatigue index is defined as an indicator used to quantify the workload and the degree of decline in effectiveness of each promotion node in the supply chain when performing promotion activities.

[0215] The formula for calculating the fatigue index of promotion nodes is defined as follows:

[0216]

[0217] in, It is the fatigue index of the target product i at the promotion stage during the current monitoring period;

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

[0219] This is the peak promotional error for target product i during the current monitoring period. The peak promotional error is the ratio between the delay time of the promotional content and the actual time spent on promotion. The larger the value, the more time the promotional content takes and the better the promotional effect.

[0220] , and These are the weighting coefficients of the corresponding parameters. , and The values ​​all fall within the interval (0,1), and ;

[0221] , and The corresponding weights are determined using the entropy weight method and the fuzzy hierarchical analysis method (FAHP).

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

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

[0224]

[0225] in, This represents the fatigue index of target product i at promotion node j.

[0226] The Demand Fission Lag Index is defined as an indicator that quantifies the degree of delay in demand response time when analyzing the impact of promotion strategies on the demand for target products.

[0227] The formula for calculating the demand fission lag index is defined as follows:

[0228]

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

[0230] The output range is limited to (0,1). A higher value indicates a greater lag in the demand response of target product i.

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

[0232]

[0233] in, This is the response time for the h-th user; This is the start time of the promotional campaign; This is the total number of user responses;

[0234] The higher the value, the greater the lag in the distribution of user response time, and the more gradually the promotion strategy affects sales.

[0235] The lower the value, the more concentrated the user response, and the faster the promotional campaign can reach users;

[0236] It is a sales volume change curve over time, indicating the time characteristics of demand changes;

[0237] Sales time variation curves are used to describe the pattern of sales changes over time, in order to observe sales fluctuations during different time periods of a promotional campaign.

[0238] Sales data of target product i at different time periods are recorded through e-commerce platforms or distributors;

[0239] set up Let be the sales volume of the target product at time t; using the sales data, calculate the sales change rate over the time period, defined by the following formula:

[0240]

[0241] in, This refers to sales volume at the start time of the promotional campaign. It is the maximum sales value within the observation window;

[0242] The higher the value, the greater the sales change or the stronger the trend over time caused by the promotional activity;

[0243] The lower the value, the weaker the sales fluctuations or the more gradual the trend over time during the promotional campaign.

[0244] , and These are the weighting coefficients of the corresponding parameters. , and The values ​​all fall within the interval (0,1), and ;

[0245] , and The corresponding weights are determined using the entropy weight method and the fuzzy hierarchical analysis method (FAHP).

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

[0247]

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

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

[0250]

[0251] in, and These are the weighting coefficients of the corresponding parameters; and The values ​​all fall within the interval (0,1), and ; and The corresponding weights are determined using the entropy weight method and the fuzzy hierarchical analysis method (FAHP). The output range is (0,1); if and / or The larger the output value, The larger the output value, the higher the "promotion fatigue level" and / or the greater the "demand response lag effect" of the supply chain corresponding to the target product i.

[0252] Further explanation: The lag effect coefficient is incorporated into the demand fluctuation evaluation coefficient for correction, in order to obtain the predicted value of the demand fluctuation evaluation coefficient for each target product in the next monitoring period. Specifically, this includes:

[0253] Setting the lag effect coefficient The judgment threshold range is ; It is contained within the interval (0.2, 0.8);

[0254] when hour, ;

[0255] The lag effect coefficient is defined to have a positive proportional relationship with the predicted value of the demand fluctuation evaluation coefficient for target product i in the next monitoring period. It will have a high impact on the social fission activity index and conversion competition rate in the demand fluctuation evaluation coefficient, so the predicted value of the demand fluctuation evaluation coefficient is on an increasing trend.

[0256] when hour, ;

[0257] because The impact on the social fission activity index and conversion competition rate in the demand fluctuation evaluation coefficient is small, and the demand activity is insufficient. Therefore, the predicted value of the demand fluctuation evaluation coefficient of target product i in the next monitoring period shows a downward trend.

[0258] when At that time, no correction was made for the evaluation coefficient of demand fluctuation;

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

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

[0261] Determine the threshold range The setting principle is: the output value of the lag effect coefficient is within the range At that time, the impact on the value of the demand fluctuation evaluation coefficient was within 2%; The specific determination is made using the fuzzy hierarchical analysis method (FAHP), which will not be elaborated upon here.

[0262] Further explanation: Adjustment strategies are provided based on the initial ranking results to obtain the final ranking results for each target product. Based on these final ranking results, e-commerce promotion strategies with corresponding weights are implemented, specifically including:

[0263] Obtain the predicted value of the demand fluctuation evaluation coefficient for each target product in the next monitoring period;

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

[0265] Only when target product i When the initial sorting result is reached, the sorting position of target product i is increased by one unit; and the adjusted sorting result is used as the final sorting result.

[0266] Specifically: If target product i is ranked 3 in the preliminary ranking results, when target product i's At that time, the sorting position of target product i is 2; that is, the production priority is 2.

[0267] If target product i is ranked 1 in the initial ranking results, no adjustment will be made.

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

[0269] The top two target products in the final ranking will be subject to the first-weight e-commerce promotion strategy.

[0270] First-weight e-commerce promotion strategies include, but are not limited to, search engine optimization (SEO), social media marketing, content marketing, email marketing, video marketing, online promotional campaigns, and targeted advertising; the purpose of adjusting first-weight e-commerce promotion strategies is to... The increase is more than 20% of the current value;

[0271] For the target products ranked third to sixth in the final ranking results, implement a second-weighted e-commerce promotion strategy;

[0272] The second-weighted e-commerce promotion strategy includes social media marketing, content marketing, email marketing, and online promotional campaigns; the purpose of adjusting the second-weighted e-commerce promotion strategy is to... The increase will be between 10% and 20% of the current value;

[0273] For target products ranked seventh or lower in the final ranking results, a third-weight e-commerce promotion strategy will be implemented.

[0274] The third weighting of e-commerce promotion strategies includes social media marketing and online promotional activities; the second weighting of e-commerce promotion strategies aims to adjust... The increase should be within 10% of the current value;

[0275] The promotional intensity of the first-weighted e-commerce promotion strategy, the second-weighted e-commerce promotion strategy, and the third-weighted e-commerce promotion strategy decreases in that order.

[0276] Search engine optimization (SEO) improves a website's ranking in search engines and increases organic traffic by optimizing its content and structure. Specifically, it involves using specific keywords, creating high-quality content, and acquiring backlinks.

[0277] Social media marketing involves promoting a brand on social media platforms such as Weibo, WeChat, Douyin, and Instagram by publishing content, advertising, or interacting with users to increase brand awareness and boost product sales.

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

[0279] Email marketing involves maintaining contact with potential and existing customers by sending regular newsletters and personalized promotional emails, thereby increasing customer loyalty and repeat purchase rates.

[0280] Video marketing involves creating short videos that demonstrate, review, or tell brand stories and publishing them on video platforms (such as YouTube and Bilibili) to visually attract users and increase engagement.

[0281] Online promotional activities involve organizing special offers, limited-time discounts, group buying, and spending-based reductions to attract consumers to make quick purchases.

[0282] Precision advertising utilizes consumer data to implement targeted marketing, ensuring that ads are delivered to the most relevant target audience. It leverages big data analytics and machine learning technologies to optimize advertising effectiveness.

[0283] Based on the above description of the implementation methods, those skilled in the art can clearly understand that the present invention can be implemented using software and necessary general-purpose hardware, and of course, it can also be implemented using hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention, 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 computer floppy disk, read-only memory (ROM), random access memory (RAM), flash memory, hard disk, or optical disk, etc., including several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods of the various embodiments of the present invention.

[0284] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-including system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device.

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

[0286] The above description of the embodiments is only for the purpose of helping to understand the method and core ideas of the present invention. It should be noted that those skilled in the art can make several improvements and modifications to the present invention without departing from the principles of 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 situation and market demand, applied to the e-commerce promotion strategy of multiple target products currently produced by the enterprise, characterized in that... The specific steps include: Step S1: Collect market demand fluctuation data and enterprise production status data for multiple target products. The enterprise production status data includes the proportion of product energy consumption and environmental protection costs and the historical inventory backlog pressure coefficient of the product during the current monitoring period. Multiple target products are uniquely indexed and labeled to form a label set {1,2,…,i,…,N}, where i represents the index label of the target product and N represents the total number of target products; The product energy consumption and environmental cost ratio is defined to characterize the proportion of the environmental costs generated by energy consumption and emission treatment of a single target product in the total production cost during the current monitoring period, and is denoted as the product energy consumption and environmental cost ratio of target product i. ,set up The range is the interval (0,1); when The closer it is to 0, the lower the impact of the energy consumption and environmental protection costs of the target product i on the total production cost. when The closer it is to 1, the higher the impact of the energy consumption and environmental protection costs of the target product i on the total production cost. The historical inventory backlog pressure coefficient is defined as a factor used to characterize the degree of backlog risk caused by the current inventory level relative to the sales level, and is denoted as follows: ,set up The range is the interval (0,1); when The closer it is to 0, the lower the "inventory level" and / or the higher the "sales level" of target product i, which in turn represents the lower the backlog pressure of target product i. when The closer it is to 1, the higher the "inventory level" and / or the lower the "sales level" of target product i, which in turn represents the higher the backlog pressure of target product i. Market demand fluctuation data includes search path complexity metrics, social sharing activity metrics, and user conversion rates against similar competing products during the current monitoring period. Define a search path complexity metric to characterize the search path complexity experienced by a user from initial search to final purchase click for target product i within the current monitoring period, and denote the search path complexity metric for target product i as follows: ,set up The range is the interval (0,1); when The closer it is to 1, the higher the complexity of the search path for target product i, indicating that users are more hesitant about target product i or that there are greater problems with the page navigation design. when The closer it is to 0, the lower the complexity of the search path for the target product i, and the fewer unnecessary jumps and clicks the user makes. Define the social viral spread activity metric as the viral spread capability of target product i on social media within the current monitoring period, and label the social viral spread activity metric of target product i as follows: ,set up The range is the interval (0,1); when The closer the value is to 0, the stronger the viral spread of target product i on social media during the current monitoring period. when The closer the value is to 1, the weaker the viral spread of target product i on social media during the current monitoring period. Define the user conversion rate of competing products as the distribution rate of users choosing target product i when purchasing similar products during the current monitoring period; and denote the conversion rate of target product i as... ,set up The range is the interval (0,1); when The closer the value is to 1, the higher the proportion of users purchasing target product i from similar competing products, which in turn represents the stronger competitiveness of target product i in the market. when The closer the value is to 0, the lower the proportion of users purchasing target product i from similar competing products, which in turn indicates that target product i is less competitive in the market. Step S2: Receive and analyze the enterprise production status data of each target product during the current monitoring period to generate preliminary ranking coefficients. The preliminary ranking coefficients are used to rank the production priorities of multiple target products to obtain preliminary ranking results. Define the initial ranking coefficient of target product i within the current monitoring period as: The calculation formula is as follows: in, The output range is limited to the interval (0,1); It represents the ratio of energy consumption to environmental protection costs for target product i. It is the historical inventory backlog pressure coefficient of target product i; , and These are the weighting coefficients of the corresponding parameters; when The closer it is to 1, the higher the priority of target product i. when The closer it is to 0, the lower the priority of target product i. Calculate the preliminary ranking coefficient for each target product in the label set {1,2,…,i,…,N}, and sort them from largest to smallest according to the calculated preliminary ranking coefficient. The larger the corresponding value, the higher the production priority; When at least two target products have the same initial ranking coefficient, according to Sort the values ​​in ascending order. The smaller the value, the lower the inventory pressure of the corresponding target product; The sorted order of multiple target products is used as the initial 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 assess 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 for characterizing the supply chain corresponding to each target product. Step S5: Introduce the lag effect coefficient into the demand fluctuation evaluation coefficient for correction, so as to obtain the predicted value of the demand fluctuation evaluation coefficient for each target product in the next monitoring period. Step S6: Based on the predicted value of the demand fluctuation evaluation coefficient of each target product in the next monitoring period, provide adjustment strategies for the preliminary ranking results, obtain the final ranking results of each target product, and implement e-commerce promotion strategies with corresponding weights based on the final ranking results.

2. The e-commerce promotion method based on enterprise situation and market demand as described in claim 1, characterized in that: The formula for calculating the demand fluctuation evaluation coefficient is defined as follows: in, It is the demand fluctuation evaluation coefficient for target product i during the current monitoring period. The output range is limited to the interval (0,1); It is an indicator of the search path complexity of target product i; It is a social sharing activity metric for target product i; It is the conversion rate of target product i; , and These are the weighting coefficients of the corresponding parameters. ,and , and The value is within the interval (0,1); when The closer it is to 1, the greater the fluctuation in market demand for target product i. when The closer it is to 0, the smaller the fluctuation in demand for target product i in the market.

3. The e-commerce promotion method based on enterprise situation and market demand as described in claim 2, characterized in that: The promotion nodes of the supply chain include distributors, retailers, advertising platforms, social media channels, and e-commerce platforms; These promotion nodes are represented as a set {1,2,…,j,…,5}, where j represents the index of the promotion node and 5 represents the number of promotion nodes; and when j takes the values ​​1, 2, 3, 4 or 5, they represent distributors, retailers, advertising platforms, social media channels and e-commerce platforms, respectively. Lagging impact data include the promotion node fatigue index and the demand fission lag index; The promotion node fatigue index is defined as an indicator used to quantify the workload and the degree of decline in effectiveness of each promotion node in the supply chain when performing promotional activities. The promotion node fatigue index for target product i is denoted as... ; The output range is in the interval (0,1). The larger the output value, the higher the promotion fatigue level of the promotion node corresponding to target product i. Calculate the average promotion node fatigue index of target product i in the promotion node set {1,2,…,5}, denoted as . ; The demand fission lag index is defined as an indicator that quantifies the delay in demand response time when analyzing the impact of promotion strategies on the demand for a target product. The demand fission lag index for target product i is denoted as... ; The output range is limited to (0,1). A higher value indicates a greater lag in the demand response of target product i. Calculate the average demand fission lag index of target product i in the promotion node set {1,2,…,5}, denoted as ; Define the lag effect coefficient of the supply chain corresponding to target product i as follows: The calculation formula is as follows: in, and These are the weighting coefficients of the corresponding parameters; and The values ​​all fall within the interval (0,1), and ; The output range is (0,1); if and / or The larger the output value, The larger the output value, the higher the "promotion fatigue level" and / or the greater the "demand response lag effect" of the supply chain corresponding to the target product i.

4. The e-commerce promotion method designed based on enterprise conditions and market demand according to claim 3, characterized in that: The lag effect coefficient is incorporated into the demand fluctuation evaluation coefficient for correction, so as to obtain the predicted value of the demand fluctuation evaluation coefficient for each target product in the next monitoring period, specifically including: Setting the lag effect coefficient The judgment threshold range is ; It is contained within the interval (0.2, 0.8); when hour, ; when At that time, no correction was made for the evaluation coefficient of demand fluctuation; when hour, ； in, It is the predicted value of the demand fluctuation evaluation coefficient for target product i in the next monitoring period.

5. The e-commerce promotion method based on enterprise situation and market demand as described in claim 4, characterized in that: Adjustment strategies are provided based on the initial ranking results to obtain the final ranking results for each target product. Based on these final ranking results, corresponding weighted e-commerce promotion strategies are implemented, specifically including: Obtain the predicted value of the demand fluctuation evaluation coefficient for each target product in the next monitoring period; and set the predicted value of the demand fluctuation evaluation coefficient corresponding to target product i. The adjustment threshold is , ; Only if the target product i corresponds to When the initial sorting result is reached, the sorting position of target product i is increased by one unit; and the adjusted sorting result is used as the final sorting result. Implement e-commerce promotion strategies with appropriate weighting, specifically as follows: The top two target products in the final ranking will be subject to the first-weight e-commerce promotion strategy. For the target products ranked third to sixth in the final ranking results, a second-weighted e-commerce promotion strategy will be implemented; For target products ranked seventh or lower in the final ranking results, a third-weight e-commerce promotion strategy will be implemented. The promotional intensity of the first-weighted e-commerce promotion strategy, the second-weighted e-commerce promotion strategy, and the third-weighted e-commerce promotion strategy decreases in that order.

Images