New product putting method, device and equipment based on big data

Through the big data-based delivery method, retail user evaluation scores are calculated and delivery plans are dynamically adjusted, the problem of formulating new cigarette product delivery strategies has been solved, and precise delivery and economic benefits have been achieved.

CN118941364APending Publication Date: 2024-11-12CHINA TOBACCO GUANGXI IND
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411031674.8
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-30
Publication Date
2024-11-12

AI Technical Summary

Technical Problem

In the early stages of the launch of new cigarette products, due to the lack of sufficient historical placement, ordering and sales data support, it is difficult to formulate scientific placement strategies. The limitations of traditional methods make it impossible to accurately evaluate the brand market performance and formulate reasonable brand expansion strategies.

Method used

Using a new product delivery method based on big data, by obtaining the historical delivery data of cigarette products, calculating the evaluation scores of retailers, forming an initial delivery plan, and adjusting the number and regional proportion of retailers based on the initial delivery data, dynamically updating the delivery plan, to Achieve precise market placement and optimal resource allocation.

Benefits of technology

It has achieved precise market launch of new cigarette products in the early stages of listing, improving the efficiency and economic benefits of supply, ensuring optimal allocation of resources, rapidly promoting market penetration and shareholding, and enhancing market competitiveness.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118941364A_ABST
    Figure CN118941364A_ABST
Patent Text Reader

Abstract

The invention relates to the technical field of computers, and discloses a new product putting method, device and equipment based on big data, and the method comprises the steps: obtaining a list of initial and all retailers and historical putting data of similar cigarette products, carrying out the analysis to obtain a plurality of evaluation indexes, calculating the evaluation scores of all retailers according to a preset weight, and obtaining the evaluation scores of all retailers; the method comprises the following steps: selecting a list of initial retailers, sorting from high to low, forming an initial delivery scheme based on the list of the initial retailers, and carrying out initial delivery to obtain initial delivery data for adjusting the number of the retailers and the proportion of the regions, and according to the adjusted number of the retailers and the proportion of the regions, sending the initial delivery data to a server. And screening the retailers with the corresponding number and proportion to form a new product delivery list. According to the method, by mining and analyzing consumption big data, a scientific basis is provided for accurate point selection and delivery of new cigarette products in the early stage of marketing, so that resource allocation is optimized, and delivery efficiency and economic benefits are improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to a method, device and equipment for launching new products based on big data. Background Art

[0002] In the process of profound transformation of the domestic tobacco industry, the industry has entered a new stage of brand competition. Faced with the current situation of nearly 2,400 cigarette brands, how to accurately evaluate brand market performance and formulate reasonable brand expansion strategies has become a challenge that needs to be solved urgently. The scientific launch of cigarette products is a key link in the operation of tobacco companies, and its rationality is directly related to the economic benefits of the company.

[0003] Traditional cigarette launch plans are mainly determined based on direct economic indicators such as sales volume and amount. However, this method is particularly limited when launching new cigarette products. Compared with mature products in the market, new products lack sufficient historical launch, ordering and sales data support, so it is difficult to directly formulate launch strategies through time series data analysis or algorithm model prediction. In particular, new products should avoid over-distribution in the early stage of listing, and the traditional launch model based on retailer positions and label combinations cannot be directly applied. Summary of the invention

[0004] In view of this, the present invention provides a new product launch method, device and equipment based on big data to solve the problem that it is difficult to formulate a scientific launch strategy for new cigarette products due to the lack of sufficient historical launch, ordering and sales data support.

[0005] In a first aspect, the present invention provides a method for launching a new product based on big data, the method comprising:

[0006] Obtaining the product type of the target cigarette product and the historical launch data of cigarette products of the product type;

[0007] Based on the evaluation indicators, the evaluation score of each retailer is calculated according to the historical delivery data;

[0008] According to the evaluation scores of each retailer, a ranking list of retailers is obtained;

[0009] Selecting initial retailers from various retailers to form an initial launch plan;

[0010] Carry out initial delivery according to the initial delivery plan to obtain initial delivery data;

[0011] According to the initial launch data, the number of retailers and the ratio of the regions where the retailers are located in the initial launch plan are adjusted to obtain the adjusted number of retailers and the ratio of the regions where the retailers are located;

[0012] Based on the adjusted number of retailers and the proportion of their regions, retailers with corresponding numbers and proportions in the retailer ranking table are screened from high to low to update the initial delivery plan.

[0013] The new product launch method based on big data provided in the embodiment of the present invention mines and analyzes consumer big data, sorts retailers based on evaluation indicators, and forms an initial launch plan for launch. After obtaining the initial launch data, dynamic adjustments are made to update the launch plan, so as to achieve accurate market launch of new cigarette products in the early stage of listing, ensure that resources are optimally allocated, and thus improve the efficiency of launch and the overall economic benefits.

[0014] In an optional embodiment, the evaluation indicators include: cigarette sales volume in each price segment, non-holiday cigarette sales volume, comprehensive potential index, current potential index, comprehensive operating capacity index, matching operating capacity index, additional operating capacity index, average price of products and at least one of geographical location.

[0015] The new product launch method based on big data provided by the embodiment of the present invention is based on the historical launch data of related cigarette products of the same type as the new cigarette product to be launched, not only including the existing feature fields, but also creating new derivative features through feature engineering technology, thereby expanding the indicator system for measuring the sales performance of retailers, and comprehensively analyzing various evaluation indicators to obtain a comprehensive and scientific evaluation of the sales ability of retailers, so as to accurately grasp the business judgment of new product launch and avoid potential volatility risks caused by over-reliance on a single indicator.

[0016] In an optional implementation, each retailer is sorted according to the historical delivery data to obtain a retailer sorting table, including:

[0017] Assign weights based on the importance of evaluation indicators;

[0018] The weighted sum of several evaluation indicators is performed according to the weights to obtain the score of the retailer's business ability evaluation;

[0019] According to the different types of all retailers, the corresponding indicators are brought in and weighted summed according to the preset weights to obtain the market feedback evaluation score;

[0020] The retailer's business capability evaluation score and the market feedback evaluation score are summed according to the preset weights to obtain the evaluation score;

[0021] Sort by rating.

[0022] The new product launch method based on big data provided in the embodiment of the present invention ranks retailers based on their evaluation scores, and divides the retailer evaluation scores into two dimensions, namely, the retailer business capability evaluation score and the market feedback evaluation score. Finally, the evaluation score is calculated based on preset weights. According to the scores, the model ranks the target retailers, thereby providing a clear recommendation list to accurately locate the target market, improve market response speed, and quickly launch new products to the market, which helps to accelerate the market penetration of new products and increase market share.

[0023] In an optional implementation, based on the adjusted number of retailers and the proportion of their regions, retailers with corresponding numbers and proportions in the retailer ranking table are screened from high to low to update the initial delivery plan, which is carried out according to a preset adjustment cycle.

[0024] The new product launch method based on big data provided in the embodiment of the present invention adjusts the number of existing retailers and regional proportions according to a preset cycle to enhance market adaptability, so that the launch strategy of new products keeps pace with the market and better meets the needs and preferences of consumers in different regions, thereby enhancing market competitiveness. At the same time, it can flexibly respond to market changes. Through the preset adjustment cycle and flexible adjustment mechanism, cigarette companies can seize market opportunities and achieve sustainable development.

[0025] In an optional implementation, the manner of adjusting the number of retailers includes a leap manner, a linear manner, and an exponential manner;

[0026] The leap approach is to first maintain the number of retailers in the initial launch plan until the preset conditions are met, and then expand the number of retailers in the initial launch plan to the target number of retailers; the linear approach is to increase the number of retailers linearly within a preset time range; the exponential approach is to increase the number of retailers exponentially within a preset time range.

[0027] The method for launching new products based on big data provided by the embodiment of the present invention selects an appropriate method to adjust the number of retailers in response to real-time market conditions. For example, when market demand surges or competitors exit the market, the number of retailers can be increased in a leap-forward manner to quickly fill the market gap and achieve rapid market penetration of products, which is conducive to seizing market opportunities and rapidly expanding brand influence. The linear method is suitable for steadily increasing the number of retailers within a preset time, which helps the market gradually accept new products, reduce market impact, and maintain a stable brand image. The exponential method helps to accelerate expansion to capture opportunities for explosive market growth.

[0028] In an optional implementation, adjusting the ratio of the regions where the retailers are located includes:

[0029] Calculate the recent sales power index of each retailer based on the initial launch data;

[0030] According to the recent sales force index of each retailer, the sales force index of the area where each retailer is located is obtained;

[0031] Sort by sales force index of each region from high to low;

[0032] The regional proportions corresponding to the preset sorting range are adjusted upward or downward to obtain the adjusted regional proportions of the retailers.

[0033] The new product launch method based on big data provided by the embodiment of the present invention uses the recent sales force index as a measurement factor, selects the best retailers in each region based on the retailer scores, and makes dynamic adjustments based on market conditions, so that the new products to be launched can be continuously revised under the real market evolution, improve the accuracy of decision-making, and screen and match the most suitable market area for the product.

[0034] In a second aspect, the present invention provides a device for launching new products based on big data, the device comprising:

[0035] An acquisition module, used to acquire the product type of a target cigarette product and the historical launch data of cigarette products of the product type;

[0036] A calculation module is used to calculate the evaluation score of each retailer based on the evaluation indicators and historical delivery data;

[0037] A ranking module is used to obtain a ranking table of retailers according to the evaluation scores of each retailer;

[0038] A formation module is used to select initial retailers from various retailers and form an initial placement plan;

[0039] A delivery module is used to perform initial delivery according to the initial delivery plan to obtain initial delivery data;

[0040] An adjustment module, for adjusting the number of retailers and the ratio of the regions where the retailers are located in the initial delivery plan according to the initial delivery data, to obtain the adjusted number of retailers and the ratio of the regions where the retailers are located;

[0041] The update module is used to filter out the corresponding number and proportion of retailers in the retailer ranking table from high to low according to the adjusted number of retailers and the proportion of the regions where they are located, so as to update the initial delivery plan.

[0042] In a third aspect, the present invention provides a computer device, comprising: a memory and a processor, the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the method for launching new products based on big data according to the first aspect or any corresponding embodiment thereof by executing the computer instructions.

[0043] In a fourth aspect, the present invention provides a computer-readable storage medium having computer instructions stored thereon, the computer instructions being used to enable a computer to execute the method for launching new products based on big data according to the first aspect or any corresponding embodiment thereof.

[0044] In a fifth aspect, the present invention provides a computer program product, including computer instructions, which are used to enable a computer to execute the method for launching new products based on big data according to the first aspect or any corresponding embodiment thereof. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0046] Figure 1 is a flow chart of a method for launching a new product based on big data according to an embodiment of the present invention;

[0047] Figure 2 is a schematic diagram of evaluation indicators and their weight distribution according to an embodiment of the present invention;

[0048] Figure 3 is a structural block diagram of a device for launching new products based on big data according to an embodiment of the present invention;

[0049] Figure 4 It is a schematic diagram of the hardware structure of a computer device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0050] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0051] The formulation of traditional cigarette launch strategies often relies too much on intuitive and easily quantifiable economic indicators such as sales volume and amount. This approach may work for products with mature markets, but its limitations are clearly revealed in the context of launching new cigarette products.

[0052] The lack of historical data for new products, including key information such as launch records, ordering patterns, and sales performance, makes it particularly difficult to make accurate predictions through time series analysis or complex algorithm models. What is even more difficult is that cautious strategies must be adopted in the early stages of new product launches to avoid blindly expanding the scope of distribution, so as to avoid inventory backlogs due to market response that does not meet expectations. At the same time, since the market positioning, consumer acceptance, and potential demand of new products are all unknown or to be verified, directly applying the traditional launch model based on the existing gear and label combination of retailers may not only fail to effectively reach the target consumer group, but may also miss opportunities due to ignoring market differences and product characteristics.

[0053] The embodiments of the present invention provide a method, device, equipment and storage medium for the placement of new products based on big data. By mining and analyzing consumer big data, a scientific basis is provided for the precise selection of locations for the placement of new cigarette products in the early stages of their launch, so as to achieve the goals of precise placement, efficient coverage and continuous optimization.

[0054] According to an embodiment of the present invention, an embodiment of a method for launching new products based on big data is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0055] In this embodiment, a method for launching new products based on big data is provided, which can be used in mobile terminals, such as mobile phones, tablet computers, etc. Figure 1 is a flow chart of a method for launching a new product based on big data according to an embodiment of the present invention. Figure 1 As shown, the process includes the following steps:

[0056] Step S101, obtaining the product type of a target cigarette product and historical launch data of cigarette products of this product type.

[0057] Specifically, the cigarette products of this product type refer to other cigarette products of the same type as the target cigarette products to be launched.

[0058] Furthermore, the historical delivery data includes retailer information, ordering data, and sales data.

[0059] Optionally, the historical delivery data specifically includes a retailer information table, including fields such as the retailer name, the retailer's location, the retailer's marketing department, the retailer's business format, the retailer's size, and the geographical location type; a product specification table, including fields such as the product specification name, purchase price, and retail price; a sales volume table, including fields such as the retailer name, product specification name, time, and sales volume, as well as a business district information table.

[0060] Step S102, based on the evaluation indicators, the evaluation score of each retailer is calculated according to the historical delivery data.

[0061] Specifically, we need to first calculate the specific scores of each retailer under different indicators.

[0062] Furthermore, after normalizing the specific scores of each retailer under different indicators to a percentage system, the scores of each indicator of the retailer are weighted and summarized according to preset weights to calculate the evaluation score of each retailer.

[0063] Step S103, obtaining a retailer ranking table based on the evaluation scores of each retailer.

[0064] Specifically, the retailers are ranked from high to low based on their evaluation scores.

[0065] Optionally, a ranking list of retailers in each region is formed separately according to different regions.

[0066] Step S104, selecting initial retailers from various retailers to form an initial investment plan.

[0067] Specifically, the initial launch plan includes the initial number of retailers and the proportion of their regions.

[0068] Step S105, performing initial delivery according to the initial delivery plan to obtain initial delivery data.

[0069] Step S106, adjusting the number of retailers and the ratio of the regions where the retailers are located in the initial delivery plan according to the initial delivery data, and obtaining the adjusted number of retailers and the ratio of the regions where the retailers are located.

[0070] Specifically, the adjustment to the number of retailers refers to an increase or decrease in the number of placements, and the adjustment to the proportion of a region refers to an increase or decrease in the proportion of a certain region in the total placement.

[0071] Specifically, the number of retailers and the proportion of the regions where the retailers are located are adjusted by analyzing the similarity of the retailers and the ordering and sales data of the retailers in the initial launch data.

[0072] Step S107, based on the adjusted number of retailers and the proportion of the regions where they are located, select retailers with corresponding numbers and proportions in the retailer ranking table from high to low to update the initial delivery plan.

[0073] Specifically, the specific number of retailers in a region is obtained by calculating the product of the adjusted total number of retailers in a region and the ratio of the regions where the retailers are located.

[0074] Furthermore, according to the specific quantity, the list of retailers with the corresponding quantity is screened out from high to low by comparing with the sorting table to update the initial delivery plan.

[0075] This embodiment collects and analyzes the historical launch data of other cigarette products of the same type as the cigarette product to be launched, analyzes and obtains various evaluation indicators, evaluates the scores of each evaluation indicator for each retailer, and assigns weights, performs weighted summation of the scores of each indicator, obtains the evaluation score, and sorts from high to low based on the evaluation score to obtain a ranking table of retailers. Select the initial retailers according to the ranking table, calculate the number of retailers and the proportion of the regions where they are located, and then launch the product. After obtaining the initial launch data, analyze it, adjust the number of users and the proportion of the regions where they are located, and update the initial launch plan.

[0076] In some optional embodiments, the evaluation indicators include: cigarette sales volume in each price segment, non-holiday cigarette sales volume, comprehensive potential index, current potential index, comprehensive operating capacity index, matching operating capacity index, additional operating capacity index, average price of products and at least one of geographical location.

[0077] Specifically, the sales volume of cigarettes in each price segment is an optimized evaluation standard based on the "five categories and eight grades" classification standard commonly used in the industry, which divides cigarette products into five grades and thirteen segments according to the price range. By analyzing the sales data of cigarette products in different price segments, setting different indicator weights for each price grade, and comprehensively calculating the scores of each retailer in the evaluation index, the sales capacity of each retailer is distinguished from the price dimension, so as to more accurately grasp the market demand dynamics and consumption trends.

[0078] The non-holiday cigarette sales index standard deducts the impact of holiday sales on total sales peaks from total sales. Especially during major holidays such as New Year's Day and Spring Festival, tobacco product sales usually increase significantly. This growth is often driven by temporary factors and is not habitual. Therefore, these sales peaks do not fully reflect the sales capabilities of retailers during non-holiday periods. By setting this indicator, the purpose is to increase the weight of retailers who can still maintain high sales of high-end cigarettes during non-holiday periods. At the same time, this indicator helps to reduce the impact of retailers whose sales increase only during holidays due to a sudden increase in orders. This method is an optimization strategy of "cutting peaks and filling valleys", which helps to achieve a balance between holiday and weekday sales, and provides a more balanced perspective for evaluating retailers' daily sales performance.

[0079] Comprehensive potential index reflects the average operating capacity of retailers in the past year through quantitative methods. Generally, the retailer's cigarette sales volume in the past 12 months is used, and descending weights are set according to the price range from high to low. The score after multiplying the sales volume and the weight is calculated and the potential ranking is carried out.

[0080] The current potential indicator takes into account the tobacco sales data of retailers in different time periods. It aims to reflect the ordering potential of retailers in the same period of previous years and improve the robustness of the results.

[0081] Optionally, this indicator calculates the sum of the cigarette sales in the current month and the previous month, and adds it to the sum of the sales in the corresponding month of the same period last year. After aggregation, the potential ranking is performed after multiplying the price segment weights according to the method of indicator 3.

[0082] Specifically, let S y,m is the cigarette sales volume of the current month of the year, S y,m-1 is the cigarette sales volume in the first month of the current year, S y-1,m is the cigarette sales volume in the current month last year, S y-1,m-1 is the cigarette sales volume in the first month of last year; W j is the original weight of the jth price segment. Then the sum of the cigarette sales of the current month and the previous month and the sum of the cigarette sales of the current month and the previous month last year are added together (S′ 总 ):

[0083] S′ 总 =(S y,m +S y,m-1 )+(S y-1,m +S y-1,m-1 )

[0084] Normalize and get the weight (w j ):

[0085]

[0086] The total sales volume and weight are multiplied to get the score (R 1 ):

[0087] R 1 =S′ 总 × j

[0088] The comprehensive operating capacity index can reflect the overall operating trend of a retailer's tobacco sales. The operating capacity of a retailer is evaluated by calculating the average growth rate of its tobacco sales in the past 12 months. This index helps identify retailers that have stable performance or growth potential in tobacco sales.

[0089] An optional calculation method is to set S m is the cigarette sales volume in a certain month in the past 12 months. 总 ):

[0090]

[0091] Calculate the monthly sales difference and growth rate. Subtract the sales of the next month from the sales of the next month to get the sales difference; then divide this difference by the sales of the next month minus the previous month to get the corresponding growth rate (G m ):

[0092] ΔS 1 =S m+2 -S m+1

[0093] ΔS=S m+1 -S m

[0094]

[0095] Calculate the average growth rate (G avg ):

[0096]

[0097] Divide the average growth rate by the total sales volume in the past 12 months to get the corresponding indicator value (Z):

[0098]

[0099] Matching business capability indicators, in order to more accurately measure and feedback the business capability of retailers in terms of sales growth rate, a method based on the time-series price-sales climbing rule is adopted. By using the price segment weight multiplication sorting method in the comprehensive potential index, the average sales growth rate is sorted by price segment weight to feedback the business capability matching the sales growth rate.

[0100] An optional calculation method is to set Sj,m is the cigarette sales volume of a certain price range in a certain month in the past 12 months, then the cigarette sales volume of a certain price range in the previous month is S j,m-1 , W j is the original weight of the jth price segment. Then the sales growth rate of a certain price segment in each month of the past year relative to the previous month (r j,m ):

[0101]

[0102] Calculate the average sales growth rate (r j,avg ):

[0103]

[0104] Multiply the average sales growth rate of each price segment by the corresponding price segment weight and add them up to get the corresponding indicator value (P):

[0105]

[0106] The additional operating capacity index is based on the sales growth rate of each price segment in each month obtained by matching the operating capacity index, multiplied and accumulated by the price segment weight, and then sorted, which complements the matching operating capacity index. Calculate the average growth of the same price cigarette from the last month to the previous month in the past year.

[0107] The average price index of product specifications is used to represent the average price of cigarettes ordered by retailers. The higher the value, the stronger the tendency to sell high-priced cigarettes.

[0108] The geographical location indicator is used to characterize the geographical location bonus item of retailers. It is a fixed bonus item for urban retailers. Since the user's preliminary list is almost entirely composed of urban retailers, this indicator is set to lower the ranking of other non-urban retailers.

[0109] In some optional implementations, each retailer is sorted according to the historical delivery data to obtain a retailer sorting table, including:

[0110] Assign weights based on the importance of evaluation indicators;

[0111] The weighted sum of several evaluation indicators is performed according to the weights to obtain the score of the retailer's business ability evaluation;

[0112] According to the different types of all retailers, the corresponding indicators are brought in and weighted summed according to the preset weights to obtain the market feedback evaluation score;

[0113] The retailer's business capability evaluation score and the market feedback evaluation score are summed according to the preset weights to obtain the evaluation score;

[0114] Sort by rating.

[0115] The evaluation score of a retailer is composed of the score of the retailer's business ability evaluation and the market feedback evaluation score. The score of the retailer's business ability evaluation is based on at least one of the above-mentioned evaluation indicators, namely, cigarette sales volume in each price segment, non-holiday cigarette sales volume, comprehensive potential index, current potential index, comprehensive business ability index, matching business ability index, additional business ability index, average price of product specifications, and geographical location. The specific results of each retailer entity under different indicators are first obtained, and then the indicators are weighted according to their importance and then weighted summed. The specific weight distribution of each indicator is as follows: Figure 2 shown.

[0116] The market feedback evaluation scores are divided into four types according to the different types of retailers, and are calculated according to different evaluation indicators and preset weights.

[0117] An optional calculation method is shown in Table 1:

[0118]

[0119] Among them, the order-full rate indicator can reflect the retailer's willingness to order. The data quality of this indicator is high and has important reference value, so it is worth using as an evaluation feature. In addition, in addition to the retailer's own ordering willingness, it is necessary to evaluate the retailer's real sales ability. Therefore, the introduction of the sales-to-order ratio and inventory-to-sales ratio can reflect the market acceptance of the retailer's region.

[0120] The similarity index compares the correlation coefficients of each retailer with a high-quality retailer based on external features, calculates the vector composed of each external feature by comparison, and finally takes the average of the coefficients of each high-quality retailer to obtain the similarity of the non-delivered retailers.

[0121] For the second evaluation model, keep the weight of 15 for the full order rate, and design the remaining weight of 15 according to the evaluation method for retailers that have not yet been put into use. The specific calculation formula is:

[0122]

[0123] In addition, considering that the order-full rate cannot be calculated due to the lack of delivery volume data in some cases, a third type of evaluation is set up at the same time to convert the order-full rate in mode 2 into an order volume indicator with the same weight. The specific calculation formula is:

[0124]

[0125] By scientifically setting evaluation indicators, the scoring mechanism for retailers has been further refined to achieve a comprehensive quantitative evaluation of retail performance. First, the specific results of each retail entity under different indicators are obtained. In order to ensure that the scoring system can fully reflect the comprehensive performance of retailers, each indicator is weighted according to its importance. The indicator results after weight allocation and rule calculation are summarized to form a score for the evaluation of retailer operating ability. The specific weight allocation of each indicator is as follows: Figure 2 shown.

[0126] Finally, the retailer's business capability evaluation model and the market feedback evaluation model are assigned 70 points and 30 points or other preset weights respectively, and the weighted sum is taken to obtain the final score of the retailer in the new product launch.

[0127] In some optional implementations, based on the adjusted number of retailers and the proportion of the regions where they are located, retailers with corresponding numbers and proportions in the retailer ranking table are screened from high to low to update the initial launch plan, which is carried out according to a preset adjustment cycle. The adjustment cycle is adjusted according to the market launch situation and can be one week or one month to enhance market adaptability, so that the launch strategy of new products keeps up with the market pace and better meets the needs and preferences of consumers in different regions, thereby enhancing market competitiveness. At the same time, it can flexibly respond to market changes. Through the preset adjustment cycle and flexible adjustment mechanism, cigarette companies can seize market opportunities and achieve sustainable development.

[0128] In some optional implementations, the manner of adjusting the number of retailers includes a leap manner, a linear manner, and an exponential manner;

[0129] The leap method is to first maintain the number of retailers in the initial launch plan until the preset conditions are met, and then expand the number of retailers in the initial launch plan to the target number of retailers; the linear method is to increase the number of retailers linearly within a preset time range; the exponential method is to increase the number of retailers exponentially within a preset time range.

[0130] One optional method for planning the number of retail households is, for example, to initially deploy 500 households in a certain area, 2,000 households after 2 months, 5,000 households after 4 months, and 10,000 households after 8 months. After setting this rule, the number of households is selected at the corresponding time. This quantity determination rule includes a leap method, a linear method, and an exponential method, which can provide a flexible and quick confirmation tool. Among them, the leap method means keeping the number of retail households unchanged within the previous preset adjustment cycle (one week or one month), and directly increasing it to the preset number when the preset conditions for expanding the households are met. The linear method means that between two deployment time nodes, linear growth is carried out according to the preset adjustment cycle. The exponential method means that between two deployment times, it can be determined by mathematical formulas such as exponentials or quadratic equations, and it also supports business personnel to freely determine according to actual conditions. This allows you to choose an appropriate way to adjust the number of retailers in response to real-time market conditions. For example, when market demand surges or competitors exit the market, you can increase the number of retailers in a leapfrog manner to quickly fill the market gap and achieve rapid market penetration of products, which is conducive to seizing market opportunities and rapidly expanding brand influence. The linear method is suitable for steadily increasing the number of retailers within a preset time, which helps the market gradually accept new products, reduce market shocks, and maintain a stable brand image. The exponential method helps accelerate expansion to capture opportunities for explosive market growth.

[0131] In some optional implementations, the ratio of the regions where the retailers are located is adjusted, including:

[0132] Calculate the recent sales power index of each retailer based on the initial launch data;

[0133] According to the recent sales force index of each retailer, the sales force index of the area where each retailer is located is obtained;

[0134] Sort by sales force index of each region from high to low;

[0135] The regional proportions corresponding to the preset sorting range are adjusted upward or downward to obtain the adjusted regional proportions of the retailers.

[0136] Combined with the initial launch data, the market sales and ordering data of the initial retailers in the last four weeks are collected. If the data is missing, the ordering and launch data are used to calculate the sales power index of the retailer set.

[0137] An optional calculation method is as follows:

[0138] I 零售户组 =10%×I 近4周S +20% × I 近3周S +10%×I 近2周S +10%×I 近1周S

[0139] Among them, I 近4周S ——The total sales-to-order ratio or total order-fulfillment rate of the retail group in the previous four weeks;

[0140] I 近3周S ——The total sales-to-order ratio or total order-fulfillment rate of the retail group in the previous three weeks;

[0141] I 近2周S ——The total sales-to-order ratio or total order-fulfillment rate of the retail group in the previous two weeks;

[0142] I 近1周S ——The total sales-to-order ratio or total order-fulfillment rate of the retail group in the previous week.

[0143] In the whole region, calculate the I value of each subdivision area and sort them from high to low. The larger the value, the better the market sales in the region, and vice versa, the lower the market response in the region. Similarly, calculate the sales power index of each district in each city and sort them.

[0144] One optional way to adjust the proportion of the region is to increase the actual number of retailers in the three regions with the highest I values ​​by 10% based on the previous preset period, and decrease the actual number of retailers in the three regions with the lowest I values ​​by 10% based on the previous preset period. The number of retailers in the remaining regions remains unchanged, and the proportion of retailers in each region is recalculated based on this adjustment as the proportion of the next preset period.

[0145] In an optional implementation, after the list of retailers is determined, the new product launch plan also includes dynamically adjusting the number of new products launched to the retailers. The specific steps are as follows:

[0146] For the list of retailers confirmed in this period, the historical preset release cycle of the retailer's new product is determined. If the retailer is a new customer who is trying out a new product for the first time, the preset release volume will be given.

[0147] If the retailer's historical launch cycle of new products is less than 4, the retailer's recent sales power index will be determined. If the sales power index ranks in the top 20% in the region, the total order fulfillment rate is 100%, and the historical launch cycle is ≥ 2, the launch volume will be increased; otherwise, the current launch volume will be maintained.

[0148] If a retailer’s historical new product launch cycle is ≥4, the retailer’s recent sales power index will be determined. If the sales power index is in the top 20% of the region and the total order fill rate is >90%, the launch volume will be increased; if the sales power index is in the bottom 20% of the region and the total order fill rate is <60%, the launch volume will be reduced; otherwise, the current launch volume will be maintained.

[0149] The above-mentioned delivery quantity and order fulfillment rate boundaries can be adjusted based on the actual delivery effect and are not limited to these values.

[0150] In this embodiment, a device for launching new products based on big data is also provided, which is used to implement the above-mentioned embodiments and preferred implementation modes, and will not be repeated hereafter. As used below, the term "module" can implement a combination of software and / or hardware of a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0151] This embodiment provides a new product delivery device based on big data, such as Figure 3 As shown, including:

[0152] The acquisition module 501 is used to acquire the product type of the target cigarette product and the historical delivery data of the cigarette products of the product type.

[0153] The calculation module 502 is used to calculate the evaluation score of each retailer based on the evaluation index and the historical delivery data.

[0154] The ranking module 503 is used to obtain a ranking table of retailers according to the evaluation scores of each retailer.

[0155] The forming module 504 is used to select initial retailers from various retailers to form an initial delivery plan.

[0156] The delivery module 505 is used to perform initial delivery according to the initial delivery plan to obtain initial delivery data.

[0157] The adjustment module 506 is used to adjust the number of retailers and the ratio of the regions where the retailers are located in the initial delivery plan according to the initial delivery data, so as to obtain the adjusted number of retailers and the ratio of the regions where the retailers are located.

[0158] The updating module 507 is used to filter out the retailers with the corresponding number and proportion in the retailer ranking table from high to low according to the adjusted number of retailers and the proportion of the regions where they are located, so as to update the initial delivery plan.

[0159] In some optional implementations, the sorting module 503 includes:

[0160] The allocation submodule is used to allocate weights according to the importance of evaluation indicators.

[0161] The business capability submodule is used to perform weighted summation of several evaluation indicators according to their weights to obtain the score of the retailer's business capability evaluation.

[0162] The market feedback submodule is used to input corresponding indicators according to the different types of all retailers, perform weighted summation according to preset weights, and obtain the market feedback evaluation score.

[0163] The summing submodule is used to sum the retailer's business capability evaluation score and the market feedback evaluation score according to preset weights to obtain an evaluation score.

[0164] The rating sorting submodule is used to sort according to the rating.

[0165] In some optional implementations, the adjustment module 506 includes:

[0166] The calculation index submodule is used to calculate the recent sales power index of each retailer based on the initial delivery data.

[0167] The regional index submodule is used to obtain the sales power index of the region where each retailer is located based on the recent sales power index of each retailer.

[0168] The index sorting submodule is used to sort the sales power index of each region from high to low.

[0169] The proportion adjustment submodule is used to adjust the regional proportion corresponding to the preset sorting range upward or downward to obtain the adjusted regional proportion of the retail households.

[0170] The further functional description of each of the above modules and units is the same as that of the above corresponding embodiments and will not be repeated here.

[0171] The new product launch device based on big data in this embodiment is presented in the form of a functional unit, where the unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and memory that executes one or more software or fixed programs, and / or other devices that can provide the above functions.

[0172] The embodiment of the present invention also provides a computer device having the above Figure 4 The device for launching new products based on big data is shown.

[0173] See also Figure 4 , Figure 4 is a schematic diagram of the structure of a computer device provided by an optional embodiment of the present invention, such as Figure 4As shown, the computer device includes: one or more processors 10, a memory 20, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. Various components are connected to each other using different buses for communication, and can be installed on a common mainboard or installed in other ways as needed. The processor can process the instructions executed in the computer device, including instructions stored in or on the memory to display the graphical information of the GUI on an external input / output device (such as, a display device coupled to the interface). In some optional embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Similarly, multiple computer devices can be connected, and each device provides some necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system). Figure 4 A processor 10 is taken as an example.

[0174] The processor 10 may be a central processing unit, a network processor or a combination thereof. The processor 10 may further include a hardware chip. The hardware chip may be a dedicated integrated circuit, a programmable logic device or a combination thereof. The programmable logic device may be a complex programmable logic device, a field programmable gate array, a general purpose array logic or any combination thereof.

[0175] The memory 20 stores instructions executable by at least one processor 10, so that at least one processor 10 executes the method shown in the above embodiment.

[0176] The memory 20 may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function; the data storage area may store data created according to the use of the computer device, etc. In addition, the memory 20 may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some optional embodiments, the memory 20 may optionally include a memory remotely arranged relative to the processor 10, and these remote memories may be connected to the computer device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0177] The memory 20 may include a volatile memory, such as a random access memory; the memory may also include a non-volatile memory, such as a flash memory, a hard disk or a solid state drive; the memory 20 may also include a combination of the above types of memory.

[0178] The computer device also includes an input device 30 and an output device 40. The processor 10, the memory 20, the input device 30 and the output device 40 may be connected via a bus or other means. Figure 4 The example of connecting through bus is taken in the following.

[0179] The input device 30 can receive input digital or character information, and generate key signal input related to the user settings and function control of the computer device, such as a touch screen, a keypad, a mouse, a track pad, a touch pad, an indicator bar, one or more mouse buttons, a trackball, a joystick, etc. The output device 40 may include a display device, an auxiliary lighting device (e.g., an LED) and a tactile feedback device (e.g., a vibration motor), etc. The above-mentioned display device includes but is not limited to a liquid crystal display, a light emitting diode, a display and a plasma display. In some optional embodiments, the display device can be a touch screen.

[0180] The embodiment of the present invention also provides a computer-readable storage medium. The method according to the embodiment of the present invention can be implemented in hardware, firmware, or can be implemented as a computer code that can be recorded in a storage medium, or can be implemented as a computer code that is originally stored in a remote storage medium or a non-temporary machine-readable storage medium and will be stored in a local storage medium through a network download, so that the method described herein can be stored in such software processing on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only storage memory, a random access memory, a flash memory, a hard disk or a solid-state hard disk, etc.; further, the storage medium can also include a combination of the above types of memories. It can be understood that a computer, a processor, a microprocessor controller, or programmable hardware includes a storage component that can store or receive software or computer code. When the software or computer code is accessed and executed by a computer, a processor, or hardware, the method shown in the above embodiment is implemented.

[0181] A part of the present invention may be applied as a computer program product, such as a computer program instruction, which, when executed by a computer, can call or provide the method and / or technical solution according to the present invention through the operation of the computer. Those skilled in the art should understand that the existence of the computer program instruction in a computer-readable medium includes, but is not limited to, a source file, an executable file, an installation package file, etc., and accordingly, the way in which the computer program instruction is executed by the computer includes, but is not limited to: the computer directly executes the instruction, or the computer compiles the instruction and then executes the corresponding compiled program, or the computer reads and executes the instruction, or the computer reads and installs the instruction and then executes the corresponding installed program. Here, the computer-readable medium may be any available computer-readable storage medium or communication medium accessible to the computer.

[0182] Although the embodiments of the present invention have been described in conjunction with the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present invention, and such modifications and variations are all within the scope defined by the appended claims.

Claims

1. A method for launching new products based on big data, characterized in that: The method comprises: Obtaining the product type of the target cigarette product and the historical launch data of cigarette products of the product type; Based on the evaluation indicators, the evaluation score of each retailer is calculated according to the historical delivery data; Obtaining a ranking list of retailers according to the evaluation scores of the retailers; Selecting initial retailers from the retailers to form an initial launch plan; Performing initial delivery according to the initial delivery plan to obtain initial delivery data; According to the initial delivery data, the number of retailers and the ratio of the regions where the retailers are located in the initial delivery plan are adjusted to obtain the adjusted number of retailers and the ratio of the regions where the retailers are located; According to the adjusted number of retailers and the proportion of the regions where they are located, the retailers with corresponding number and proportion in the retailer ranking table are screened from high to low to update the initial delivery plan.

2. The method according to claim 1, characterized in that The evaluation indicators include: cigarette sales volume in each price segment, non-holiday cigarette sales volume, comprehensive potential index, current potential index, comprehensive operating capacity index, matching operating capacity index, additional operating capacity index, average price of products and at least one of geographical location.

3. The method according to claim 2, characterized in that According to the historical delivery data, each retailer is sorted to obtain a retailer sorting table, including: Allocate weights according to the importance of the evaluation indicators; The evaluation indicators are weighted and summed according to the weights to obtain a score for the retailer's business capability evaluation; According to the different types of retailers, corresponding indicators are brought in and weighted summed according to the preset weights to obtain the market feedback evaluation score; The retailer's business capability evaluation score and the market feedback evaluation score are summed according to preset weights to obtain the evaluation score; Sort by rating.

4. The method according to claim 1, characterized in that: The method of screening out the corresponding number and proportion of retailers in the retailer ranking table from high to low based on the adjusted number of retailers and the proportion of the regions where they are located, so as to update the initial delivery plan, is carried out according to a preset adjustment cycle.

5. The method according to claim 1, characterized in that The methods for adjusting the number of retailers include abrupt method, linear method and exponential method; The leaping method is to first maintain the number of retailers in the initial delivery plan until the preset conditions are met, and then expand the number of retailers in the initial delivery plan to the target number of retailers; The linear method is to increase the number of the retailers in a linear manner within a preset time range; The exponential method is to increase the number of the retailers exponentially within a preset time range.

6. The method according to any one of claims 1 to 5, characterized in that: Adjustments are made to the ratio of where retailers are located, including: Calculate the recent sales power index of each retailer based on the initial launch data; Obtaining the sales force index of the region where each retailer is located according to the recent sales force index of each retailer; Sort by sales force index of each region from high to low; The regional proportions corresponding to the preset sorting range are adjusted upward or downward to obtain the adjusted regional proportions of the retailers.

7. A new product delivery device based on big data, characterized in that: The device comprises: An acquisition module, used to acquire the product type of a target cigarette product and the historical launch data of cigarette products of the product type; A calculation module, used to calculate the evaluation score of each retailer based on the evaluation index and the historical delivery data; A ranking module, used to obtain a ranking table of retailers according to the evaluation scores of the retailers; A forming module, used to select initial retailers from the retailers to form an initial placement plan; A delivery module, used for performing initial delivery according to the initial delivery plan to obtain initial delivery data; An adjustment module, for adjusting the number of retailers and the ratio of the regions where the retailers are located in the initial delivery plan according to the initial delivery data, to obtain the adjusted number of retailers and the ratio of the regions where the retailers are located; The updating module is used to screen out the corresponding number and proportion of retailers in the retailer ranking table from high to low according to the adjusted number of retailers and the proportion of the regions where they are located, so as to update the initial delivery plan.

8. A computer device, characterized in that: include: A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the method according to any one of claims 1 to 6 by executing the computer instructions.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a computer to execute the method according to any one of claims 1 to 6.

10. A computer program product, characterized in that The method comprises computer instructions for causing a computer to execute the method according to any one of claims 1 to 6.