A method, device, electronic device and storage medium for determining a product elimination strategy

Abstract

The present invention discloses a method, device, electronic device and storage medium for determining a product elimination strategy. First, the time series corresponding to the historical sales data of the target product is obtained, and the target product includes the product to be evaluated and the eliminated product; the sales features of each time series in multiple dimensions are extracted; the target product is clustered based on the sales features to obtain multiple clusters; the number of eliminated products in each cluster is determined to obtain the elimination number; the life cycle corresponding to the product to be evaluated in each cluster is determined based on the elimination number; and the elimination strategy of the product to be evaluated is output in combination with the life cycle. The sales features of different dimensions represent the performance of the product in different aspects in the market. Clustering is based on sales features. The product to be evaluated and the eliminated product are clustered and evaluated together. Products with similar features and performances to the eliminated products can be screened out in the product to be evaluated. The product elimination strategy can be automatically output in combination with historical data to reduce the interference of human subjective factors.

Description

Technical Field

[0001] The present invention relates to the technical field of product data analysis, and in particular to a method, device, electronic device and storage medium for determining a product elimination strategy. Background Art

[0002] Product life cycle strategy can help enterprises formulate product management, production strategy and marketing strategies that adapt to market demand and guide corporate decision-making according to the different stages of the product life cycle in the market, so as to help enterprises maximize product value. In industries such as the beauty industry where products are diversified and frequently replaced, in order to ensure the market competitiveness of enterprises, it is usually necessary to manage the product life cycle and then implement product elimination strategies based on the product life cycle.

[0003] In the existing technology, the product life cycle is mainly judged by statistical methods or the experience of the product development department to decide whether to eliminate a product. However, due to the wide variety of products and the long analysis cycle involved, this method is prone to misjudgment of the product life cycle stage, which in turn affects the company's production plan and market competitiveness. Summary of the invention

[0004] The present invention provides a product elimination strategy determination method to solve the problem of product elimination strategy determination.

[0005] In a first aspect, the present invention provides a method for determining a product elimination strategy, comprising:

[0006] Obtaining a time series corresponding to historical sales data of a target product, wherein the target product includes a product to be evaluated and an eliminated product;

[0007] Extracting sales features of each of the time series in multiple dimensions;

[0008] Clustering the target products based on the sales characteristics to obtain multiple clusters;

[0009] Determine the number of the obsolete products in each cluster to obtain the obsolete number;

[0010] Determine the life cycle corresponding to the product to be evaluated in each cluster based on the elimination number;

[0011] Output an elimination strategy for the product to be evaluated in combination with the life cycle.

[0012] In a second aspect, the present invention provides a device for determining a product elimination strategy, comprising:

[0013] A data acquisition module, used to acquire a time series corresponding to historical sales data of a target product, wherein the target product includes a product to be evaluated and an eliminated product;

[0014] A feature extraction module, used to extract sales features of each of the time series in multiple dimensions;

[0015] A clustering module, used for clustering the target products based on the sales characteristics to obtain multiple clusters;

[0016] The elimination quantity determination module is used to determine the quantity of the eliminated products in each cluster to obtain the elimination quantity;

[0017] A life cycle determination module, used to determine the life cycle corresponding to the product to be evaluated in each cluster based on the elimination quantity;

[0018] A strategy output module is used to output an elimination strategy for the product to be evaluated in combination with the life cycle.

[0019] In a third aspect, the present invention provides an electronic device, the electronic device comprising:

[0020] at least one processor; and

[0021] a memory communicatively connected to the at least one processor; wherein,

[0022] The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the product elimination strategy determination method described in the first aspect of the present invention.

[0023] In a fourth aspect, the present invention provides a computer-readable storage medium storing computer instructions, wherein the computer instructions are used to enable a processor to implement the product elimination strategy determination method described in the first aspect of the present invention when executed.

[0024] The embodiment of the present invention provides a method for determining a product elimination strategy. The method comprises the following steps: firstly obtaining a time series corresponding to the historical sales data of a target product, wherein the target product includes a product to be evaluated and an eliminated product; extracting the sales features of each time series in multiple dimensions; clustering the target product based on the sales features to obtain multiple clusters; determining the number of eliminated products in each cluster to obtain the elimination number; determining the life cycle corresponding to the product to be evaluated in each cluster based on the elimination number; and outputting an elimination strategy for the product to be evaluated in combination with the life cycle. On the one hand, the sales features of different dimensions represent the performance of the product in different aspects in the market. Clustering is based on the sales features. The product to be evaluated and the eliminated product are clustered and evaluated together. The products to be evaluated that have similar features and performances to the eliminated products can be screened out. Then, the life cycle of the part of the product to be evaluated can be set to be consistent with the life cycle of the eliminated product. The product elimination strategy can be automatically output in combination with a large amount of historical data, thereby reducing the interference of human subjective factors and making the product elimination strategy more accurate. On the other hand, the life cycle of obsolete products is known, and the life cycle of the product to be evaluated is to be predicted. The life cycles of products in the same cluster are similar. Therefore, the life cycle of the product to be evaluated can be predicted based on the life cycle of obsolete products in the cluster. This can also reduce the interference of human subjective factors, making product life cycle prediction more accurate, and thus improving the rationality of product elimination strategies.

[0025] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0027] Figure 1 is a flow chart of a method for determining a product elimination strategy provided by Embodiment 1 of the present invention;

[0028] Figure 2 is a flow chart of a method for determining a product elimination strategy provided by Embodiment 2 of the present invention;

[0029] Figure 3 It is a structural schematic diagram of a device for determining a product elimination strategy provided by Embodiment 3 of the present invention;

[0030] Figure 4It is a schematic diagram of the structure of an electronic device provided in Embodiment 4 of the present invention. DETAILED DESCRIPTION

[0031] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme 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 only 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 ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0032] Embodiment 1

[0033] Figure 1 This is a flowchart of a product elimination strategy determination method provided in Embodiment 1 of the present invention. This embodiment is applicable to the situation of product elimination strategy determination. The method can be executed by a product elimination strategy determination device. The product elimination strategy determination device can be implemented in the form of hardware and / or software. The product elimination strategy determination device can be configured in an electronic device. Figure 1 As shown, the product elimination strategy determination method includes:

[0034] S101. Obtain a time series corresponding to historical sales data of a target product, where the target product includes products to be evaluated and eliminated products.

[0035] Historical sales data is usually stored in a database, and the sales data is usually stored in days or months as the smallest unit.

[0036] In the database, each product is set with a different product code. The time series is the sales data indexed by time. Therefore, the time series can be sales data in units of days or months. To obtain the time series of the target product, the time period to be analyzed can be selected for different product codes of the target product, and the sales data within the time period can be exported from the database in turn to obtain the time series.

[0037] In addition, sales data also has an annual sales cycle, so it is usually analyzed on an annual basis. For example, the time period to be analyzed is 2020-2023, and sales data is usually in months as the smallest unit. The data corresponding to the time series may include: sales data from January to December 2020, sales data from January to December 2021, sales data from January to December 2022, and sales data from January to December 2023.

[0038] Time series can be obtained using time series forecasting algorithm models. Time series forecasting algorithm models are a type of method that uses a sequence of historical data points arranged in chronological order to predict future trends. These methods usually involve statistical analysis of time series data to reveal its patterns and periodicity. They are more effective when processing data with clear trends, seasonal or cyclical changes, so that they can predict the future. Time series forecasting algorithm models can be based on machine learning algorithms and exponential smoothing methods, etc.

[0039] The purpose of setting the target products to include products to be evaluated and obsolete products is to compare the characteristics of the products to be evaluated and the obsolete products together, so as to determine the products to be evaluated that have the same characteristics as the obsolete products. Each target product can be distinguished by setting attribute tags, which include attributes to be evaluated and obsolete attributes. The attribute tags are associated with the product number of the target product.

[0040] S102: Extract sales features of each time series in multiple dimensions.

[0041] Sales characteristics may include at least one of the average monthly sales volume of the product, the retail price of the product, the time of product launch, the latest transaction date, the number of completed orders, and the number of returned orders. In addition, sales characteristics may also include recent sales characteristics, historical sales characteristics, and annual sales volume of the product. The type of sales characteristics may be set according to actual needs.

[0042] The information in the time series can be regarded as text information, and the time series can be converted into sales features through processing methods such as text vectorization, keyword extraction, and feature matching.

[0043] S103: Cluster the target products based on sales characteristics to obtain multiple clusters.

[0044] This embodiment adopts the K-means clustering method. For K-means clustering, K represents the number of clusters, that is, the number of clusters.

[0045] Specifically, firstly, K-means clustering is performed on the target products based on sales characteristics to obtain groups with different numbers of clusters, where the number of clusters is the number of clusters in the group; the intra-cluster sum of squares corresponding to each group is calculated; the target number of clusters is determined based on the number of clusters of the group and the intra-cluster sum of squares; the groups corresponding to the target number of clusters are obtained to obtain multiple clusters.

[0046] In unsupervised machine learning, different K values ​​(number of clusters) can be tried. Usually, K values ​​within a certain range are pre-set based on empirical values ​​as a reference, for example, the K value range is 4-8. Under each K value, the within-cluster sum of squares (WCSS) is calculated. The within-cluster sum of squares is used to measure the compactness of the clustering results or the discreteness of the samples within the group. Each cluster has a centroid, which is the average value of the coordinates of all samples in the cluster. WCSS is an indicator with the centroid as the reference point.

[0047] The formula for calculating WCSS is as follows:

[0048]

[0049] Assume there are K clusters, each cluster i contains n i samples (sales features), each sample is represented by X ij , i represents the index of the cluster, j represents the index of the sample in the cluster. The centroid of cluster i is C i .

[0050] After calculating WCSS, a curve graph of the number of clusters K and WCSS is drawn. In the curve graph, the horizontal axis is the number of clusters K, and the vertical axis is WCSS. For example, K takes values ​​of 4-8, corresponding to WCSS values ​​of S4-S8, respectively. Points (4, S4), (5, S5), (6, S6), (7, S7) and (8, S8) can be marked in the curve graph, and then these points are connected with lines to obtain a curve graph. Then, the point where the curve begins to flatten can be determined from the curve graph, and the K value corresponding to the point is regarded as the optimal number of clusters. The curve begins to flatten specifically when the rate of change of the curve is less than the preset rate of change.

[0051] It should be noted that the sales features are the sales features of the target products. Clustering the sales features means clustering the target products.

[0052] S104: Determine the number of obsolete products in each cluster to obtain an obsolete number.

[0053] The sales data of the target product is historical data, and the number of obsolete products in each cluster can be obtained by statistics. Specifically, the target product is provided with an attribute tag, which includes attributes to be evaluated and obsolete attributes. By screening products with obsolete attributes in the attribute tag, the number of obsolete products can be obtained.

[0054] S105: Determine the life cycle corresponding to the product to be evaluated in each cluster based on the number of eliminations.

[0055] Commercial products have a life cycle. Generally speaking, the life cycle can include the introduction period, growth period, maturity period, decline period and the end of sales period. The present invention is to evaluate the elimination of products, and mainly focuses on products at the end of sales period. When the product is at the end of sales period, the enterprise formulates different goals and strategies from multiple aspects such as marketing to maximize the interests of the enterprise. Therefore, except for the end of sales period, the life cycle of other stages is uniformly regarded as the observation period.

[0056] The life cycle of obsolete products is known, that is, the end of their sales, and the life cycle of the products to be evaluated is to be predicted. The life cycles of products in the same cluster are similar, so the life cycle of the products to be evaluated can be predicted based on the life cycle of obsolete products in the cluster. This can also reduce the interference of human subjective factors, making product life cycle predictions more accurate, thereby improving the rationality of product elimination strategies.

[0057] In an optional embodiment A, the life cycle corresponding to the product to be evaluated in each cluster is determined based on the elimination number, including: arranging the clusters from large to small according to the elimination number; taking the first cluster as the counting starting point, and taking the clusters with a cumulative number in the arrangement order as the target group, and the initial value of the cumulative number is 1; calculating the sum of the elimination numbers of the target group to obtain the total elimination number; calculating the ratio of the total elimination number to the number of all eliminated products to obtain the elimination ratio; judging whether the elimination ratio is greater than a preset first ratio; if so, marking the life cycle of the product to be evaluated in the target group as the end of sales, and marking the life cycle of other products to be evaluated as the observation period; if not, increasing the cumulative value by 1, and returning to execute the step of taking the first cluster as the counting starting point, and taking the clusters with a cumulative number in the arrangement order as the target group.

[0058] Exemplarily, assume that n is the number of clusters after clustering is completed, and S is the number of all eliminated products.

[0059] Get the clustering result at this time, count the number of eliminations corresponding to each cluster in turn, and arrange the clusters in order from large to small according to the number of eliminations, recorded as C1(N1), C2(N2)...Ci(Ni)...Cn(Nn), where Ni is the number of eliminations corresponding to cluster Ci. The initial value of the cumulative value is 1, so the first target group only includes cluster C1, calculate N1 / S to get the elimination ratio L1, and judge whether L1 is greater than the preset first ratio M1; if so, mark the life cycle of the product to be evaluated in cluster C1 as the end of sales, and mark the life cycle of other products to be evaluated in C1-Cn as the observation period. If not, the cumulative value is updated to 2, then the second target group includes clusters C1 and C2, calculate (N1+N2) / S to get the elimination ratio L2, and judge whether L2 is greater than the preset first ratio M1; if so, mark the life cycle of the product to be evaluated in clusters C1 and C2 as the end of sales, and mark the life cycle of other products to be evaluated in C3-Cn as the observation period. This cycle is repeated until the products to be evaluated whose life cycle is marked as the end of sales are screened out. Among them, M1 can be 0.8.

[0060] In this embodiment A, the life cycle of each product is evaluated in combination with the life cycle of all target products. The life cycle of obsolete products is the end of sales. Considering that many products are involved in the evaluation, it is necessary to screen out some of the products to be eliminated. Therefore, clusters with a large proportion of obsolete products are screened out from all clusters, that is, clusters with a large proportion of obsolete products. These clusters contain more obsolete products. These clusters are regarded as clusters with a life cycle of the end of sales. Based on the feature similarity of clustering clusters, the life cycle of the products to be evaluated in these clusters can be defined as the end of sales, and the life cycle of the products to be evaluated in other clusters can be defined as the observation period.

[0061] In another optional embodiment B, the life cycle corresponding to the product to be evaluated in each cluster is determined based on the number of eliminations, including: for each cluster, determining the number of all products in the cluster to obtain the number within the cluster; judging whether the ratio of the number of eliminations to the number within the cluster is greater than a preset second ratio; if so, marking the life cycle of the product to be evaluated in the cluster as the end of sales, if not, marking the life cycle of the product to be evaluated in the cluster as the observation period.

[0062] For example, for each cluster Ci, it is determined whether the ratio of the number of obsolete products k to the total number of all products Ki in the cluster is greater than a preset second ratio M2. If so, it is considered that the products in cluster Ci have obvious characteristics of obsolete products, and therefore the life cycle of the products to be evaluated in cluster Ci is determined to be the end of sales. M2 can be 0.3-0.6.

[0063] In this embodiment B, the life cycle of the products to be evaluated in the cluster is evaluated based on the life cycle of the products in each cluster. The proportion of the number of obsolete products in a cluster is used as the basis for evaluating the overall characteristics of the cluster. After determining the overall characteristics of the cluster, the life cycle of the products to be evaluated in the entire cluster can be defined.

[0064] It should be noted that the above two methods for determining the life cycle of the product to be evaluated are only examples. In the actual production process, the above two methods for determining the life cycle can be adopted in combination with actual needs, or the two methods can be improved based on actual needs to obtain other methods for determining the life cycle.

[0065] S106. Output the elimination strategy of the product to be evaluated based on the life cycle.

[0066] Specifically, for products whose life cycle is at the end of the sales period, elimination suggestions (which can be embodied as labels) are given, and for products whose life cycle is in the observation period, retention suggestions are given. Of course, it is also possible to only give elimination suggestions and not comment on products for which no suggestions are given.

[0067] In the elimination strategy, a binary label will be given to the product to be evaluated. The binary label is a label indicating whether the product to be evaluated is eliminated. For example, if it is eliminated, the label is 0, and if it is not eliminated, the label is 1.

[0068] After the elimination strategy of the product to be evaluated is outputted in combination with the life cycle, it is usually also included: removing the product to be evaluated from the shelves based on the elimination strategy. For example, when the product to be evaluated is given a binary label in the elimination strategy, the product to be evaluated with a label of 0 can be eliminated and removed from the shelves, specifically, the product is removed from the sales channel or sales are stopped.

[0069] The embodiment of the present invention provides a method for determining a product elimination strategy. The method comprises the following steps: firstly obtaining a time series corresponding to the historical sales data of a target product, wherein the target product includes a product to be evaluated and an eliminated product; extracting the sales features of each time series in multiple dimensions; clustering the target product based on the sales features to obtain multiple clusters; determining the number of eliminated products in each cluster to obtain the elimination number; determining the life cycle corresponding to the product to be evaluated in each cluster based on the elimination number; and outputting an elimination strategy for the product to be evaluated in combination with the life cycle. On the one hand, the sales features of different dimensions represent the performance of the product in different aspects in the market. Clustering is based on the sales features. The product to be evaluated and the eliminated product are clustered and evaluated together. The products to be evaluated that have similar features and performances to the eliminated products can be screened out. Then, the life cycle of the part of the product to be evaluated can be set to be consistent with the life cycle of the eliminated product. The product elimination strategy can be automatically output in combination with a large amount of historical data, thereby reducing the interference of human subjective factors and making the product elimination strategy more accurate. On the other hand, the life cycle of obsolete products is known, and the life cycle of the product to be evaluated is to be predicted. The life cycles of products in the same cluster are similar. Therefore, the life cycle of the product to be evaluated can be predicted based on the life cycle of obsolete products in the cluster. This can also reduce the interference of human subjective factors, making product life cycle prediction more accurate, and thus improving the rationality of product elimination strategies.

[0070] Embodiment 2

[0071] Figure 2 Flow chart of a method for determining a product elimination strategy provided in Embodiment 2 of the present invention. Embodiment 2 of the present invention is optimized based on Embodiment 1 above. Figure 2 As shown, the product elimination strategy determination method includes:

[0072] S201. Obtain a time series corresponding to historical sales data of a target product, where the target product includes products to be evaluated and eliminated products.

[0073] S202: Extract sales features of each time series in multiple dimensions.

[0074] The sales characteristics may include at least one of the average monthly sales volume of the product, the retail price of the product, the time the product was launched on the market, the latest transaction date, the number of completed orders, and the number of return orders.

[0075] S201-S202 are similar to S101-S102 in the first embodiment, and the details can be referred to the relevant description.

[0076] S203: For each time series, fit the sales data in the time series to obtain a historical trend curve.

[0077] S204. Perform linear regression fitting on the historical trend curve to obtain a first slope.

[0078] S205 , selecting a recent trend curve from the historical trend curves, where the recent sequence is a trend curve within a recent preset time period.

[0079] S206. Perform linear regression fitting on the recent trend curve to obtain a second slope.

[0080] S207: Add the first slope and the second slope to the sales features of the time series.

[0081] S203-S207 This embodiment further extracts sales volume features as newly added sales features based on the partial sales features extracted in S202. The linear regression fitting slopes corresponding to the trend of sales volume data in the time series in the recent period and the trend in the entire historical period are provided respectively, that is, sales volume features of different time periods are added. For the first slope obtained by fitting the historical trend curve, it represents the sales volume features of the total sales volume in the entire historical period, and for the second slope obtained by fitting the recent trend curve, it represents the sales volume features of the total sales volume in the recent period. Because the product is phased, the first slope can only determine the sales volume features of the product from a longer period of time, and for products with an iterative nature, sales volume in the recent period is also equally important. Therefore, the second slope is added to determine the sales volume features of the product from the recent period.

[0082] For example, the total sales volume of a product in the entire historical period is good, with a total sales volume of 100,000 pieces. The first slope k1 is obtained by using its corresponding time series. However, the total sales volume in recent times is poor, with a total sales volume of 30 pieces. The second slope k2 is obtained by using its corresponding time series. This indicates that the sales volume of the product was good at a certain stage before the recent period, but the current sales volume of the product has dropped sharply. If only the first slope k1 is used as the sales volume feature, it will obviously bring errors to the product evaluation. It can be seen that the historical total sales volume cannot fully express the sales volume trend of the product. Therefore, providing sales volume characteristics of products in different periods will help to make a more accurate evaluation of the product life cycle.

[0083] S208. Cluster the target products based on the sales characteristics to obtain multiple clusters.

[0084] S209: Determine the number of obsolete products in each cluster to obtain an obsolete number.

[0085] S210: Determine the life cycle corresponding to the product to be evaluated in each cluster based on the number of eliminations.

[0086] S211. Output the elimination strategy for the product to be evaluated based on the life cycle.

[0087] S208-S211 are similar to S103-S106 in the first embodiment, and the details can be referred to the relevant description.

[0088] In this embodiment, after extracting the sales features of each time series in multiple dimensions, for each time series, the sales data in the time series is fitted to obtain a historical trend curve; a linear regression fitting is performed on the historical trend curve to obtain a first slope; a recent trend curve is selected from the historical trend curve, and the recent series is a trend curve in the most recent preset time period; a linear regression fitting is performed on the recent trend curve to obtain a second slope; and the first slope and the second slope are added to the sales features of the time series. Adding sales features in different time periods helps to more accurately evaluate the product life cycle.

[0089] In an optional embodiment, an elimination strategy for the product to be evaluated is output in combination with the life cycle, including: obtaining the code update status, sample status and packaging material minimum order quantity determination result of each product to be evaluated; using the code update status, sample status, packaging material minimum order quantity determination result and life cycle as evaluation items; when the evaluation item presents negative feedback, determining the score of the evaluation item to be 1; obtaining the total score of the product to be evaluated based on the score and the preset weight of the evaluation item; setting an elimination label for the product to be evaluated whose total score is greater than the preset score threshold; after the evaluation is completed, outputting the product to be evaluated, the evaluation item and the score as the elimination strategy.

[0090] Among them, positive feedback and negative feedback are evaluated based on the perspective of product sales. Positive feedback refers to feedback that is conducive to product sales, and negative feedback refers to feedback that is not conducive to product sales.

[0091] Specifically, after obtaining the life cycle of each product, all products can be traversed to perform multi-dimensional scoring on whether to recommend elimination (removal from the shelves), where multiple dimensions are multiple evaluation items. Suppose the score is Score, and its initial value is 0.

[0092] Evaluation item 1: Determination of new and old codes.

[0093] Since some products will be upgraded and given new product codes after the upgrade, the old version of the product should not be produced any more. Therefore, if the current product code has a new code, Score1 = 1, and if the current product code does not have a new code, Score1 = 0.

[0094] Evaluation item 2: Sample status.

[0095] Some products are divided into full-size and sample products. Sample products include trial products (white boxes) and small and medium-sized samples. It should be noted that when a product is a sample, the sample status is included in the elimination evaluation. When a product is a full-size product, the sample status is not included in the elimination evaluation.

[0096] When a product is a sample and the regular version of the sample has been removed from the shelves, the sample should not be produced any more. Therefore, if the current product sample status is that the regular version (corresponding to the sample) has been removed from the shelves, Score2 = 1, and if the current product sample status is that the regular version has not been removed from the shelves, Score2 = 0.

[0097] Evaluation Item 3: Results of Minimum Order Quantity for Packaging Materials

[0098] There is a minimum order quantity requirement for product packaging materials. If the product sales are not good, the number of consumables used in the production process may not reach the minimum order quantity for packaging materials. If the material procurement and production are carried out based on the minimum order quantity for packaging materials, it will cause redundant material waste, and then cause losses. At this time, the packaging material will usually not be purchased, and the product should not continue to be produced. Therefore, the result of the minimum order quantity determination of packaging materials can be used as an evaluation item. Specifically: if the material quantity corresponding to the sales volume of the current product in the past 6 months is less than the minimum order quantity for packaging materials, Score3 = 1; if the material quantity corresponding to the sales volume of the current product in the past 6 months is greater than or equal to the minimum order quantity for packaging materials, Score3 = 0.

[0099] Evaluation item 4: life cycle.

[0100] When the product life cycle is at the end of internal sales, the sales volume of the product is usually low. In order to avoid unsalable products, production should be reduced or stopped. Therefore, if the current product life cycle is at the end of sales, Score4 = 1, and if the current product life cycle is in the observation period, Score4 = 0.

[0101] After obtaining the scores of all evaluation items, the scores are weighted to calculate the total score.

[0102] Total score = a1*Score1+a2*Score2+a3*Score3+a4*Score4.

[0103] a1, a2, a3, and a4 are the corresponding weights respectively.

[0104] Exemplarily, a1=a2=a3=0.25, a4=0.2, the preset score threshold is 0.6, and when the total score is greater than 0.6, an elimination label is set.

[0105] The products to be evaluated, evaluation items and scores are output as elimination strategies. The evaluation basis and evaluation results are summarized in the elimination strategies, so that manufacturers can adjust product production based on the elimination policies and remove products that are not conducive to sales in a timely manner to avoid waste of consumables and economic losses.

[0106] In summary, the product elimination strategy determination method of this embodiment has the following beneficial effects:

[0107] Scientific decision-making basis: Through machine learning, modeling and analysis of product sales data, combined with weighted judgment of conditions in production, procurement and other links, it can provide scientific decision-making basis for enterprises. Compared with traditional statistical methods or judgment based on experience, the evaluation process is more objective and accurate, reducing the interference of subjective factors and making decisions more rational.

[0108] Optimize life cycle management: The present invention can more accurately determine the life cycle distribution of products, including the growth, maturity and decline stages of products. By timely eliminating low-selling or obsolete products, the company's product portfolio can be optimized and the overall sales efficiency and profit margin of products can be improved.

[0109] Improve production efficiency: A reasonable product elimination strategy can avoid overproduction and inventory backlog, reduce production and storage costs, and improve production efficiency. Enterprises can make production plans and resource allocation more accurately, reduce resource waste, and improve resource utilization.

[0110] Enhance market competitiveness: Through scientific decision-making and life cycle management optimization, enterprises can better meet market demand and provide more competitive products. Timely elimination of low-selling or obsolete products can release more resources for developing new products or strengthening market promotion, thus enhancing the market competitiveness of enterprises.

[0111] In summary, the product elimination strategy determination method of the present invention can help enterprises formulate more scientific and reasonable product elimination strategies, improve production efficiency, reduce costs, and enhance market competitiveness, thereby achieving sustainable and stable business development.

[0112] Embodiment 3

[0113] Figure 3 This is a schematic diagram of the structure of a device for determining a product elimination strategy provided by Embodiment 3 of the present invention. Figure 3 As shown, the product elimination strategy determination device includes:

[0114] The data acquisition module 301 is used to acquire the time series corresponding to the historical sales data of the target product, wherein the target product includes the product to be evaluated and the eliminated product;

[0115] A feature extraction module 302 is used to extract sales features of each of the time series in multiple dimensions;

[0116] A clustering module 303, configured to cluster the target products based on the sales characteristics to obtain multiple clusters;

[0117] The elimination quantity determination module 304 is used to determine the quantity of the eliminated products in each cluster to obtain the elimination quantity;

[0118] A life cycle determination module 305, configured to determine the life cycle corresponding to the product to be evaluated in each cluster based on the number of obsolete products;

[0119] The strategy output module 306 is used to output the elimination strategy of the product to be evaluated in combination with the life cycle.

[0120] Optionally, the product elimination strategy determination device further includes:

[0121] A historical trend curve fitting module, used for fitting the sales data in each time series to obtain a historical trend curve;

[0122] A first slope acquisition module, used for performing linear regression fitting on the historical trend curve to obtain a first slope;

[0123] A recent trend curve fitting module is used to select a recent trend curve from the historical trend curve, wherein the recent sequence is a trend curve within a recent preset time period;

[0124] A second slope acquisition module, used for performing linear regression fitting on the recent trend curve to obtain a second slope;

[0125] A sales feature adding module is used to add the first slope and the second slope to the sales feature of the time series.

[0126] Optionally, the clustering module 303 includes:

[0127] A clustering submodule, used for performing K-means clustering on the target product based on the sales characteristics to obtain groups with different cluster numbers, where the cluster number is the number of clusters in the group;

[0128] A parameter calculation submodule, used for calculating the intra-cluster sum of squares corresponding to each of the groups;

[0129] A target cluster number determination submodule, configured to determine a target cluster number based on the cluster number of the group and the intra-cluster sum of squares;

[0130] The cluster determination submodule is used to obtain the group corresponding to the target cluster quantity to obtain multiple clusters.

[0131] Optionally, the life cycle determination module 305 includes:

[0132] An arrangement submodule, used for arranging each cluster from large to small according to the elimination number;

[0133] The target group determination submodule is used to take the first cluster as the counting starting point, and select the clusters whose number is a cumulative value in the arrangement order as the target group, wherein the initial value of the cumulative value is 1;

[0134] The total number of eliminations calculation submodule is used to calculate the sum of the elimination numbers of the target group to obtain the total number of eliminations;

[0135] The elimination ratio calculation submodule is used to calculate the ratio of the total elimination amount to the number of all the eliminated products to obtain the elimination ratio;

[0136] A first ratio calculation submodule is used to determine whether the elimination ratio is greater than a preset first ratio; if so, the content of the first life cycle determination submodule is executed; if not, the content of the cumulative value update submodule is executed;

[0137] A life cycle determination submodule, used to mark the life cycle of the product to be evaluated in the target group as the end of sales, and mark the life cycle of other products to be evaluated as the observation period;

[0138] The accumulated value updating submodule is used to increase the accumulated value by 1 and return the content of the target group determination submodule.

[0139] Optionally, the life cycle determination module 305 further includes:

[0140] The submodule for determining the number of products in a cluster is used to determine the number of all products in each cluster to obtain the number of products in the cluster.

[0141] The second ratio calculation submodule is used to determine whether the ratio of the eliminated number to the in-cluster number is greater than a preset second ratio; if so, the content of the end-of-sales marking submodule is executed; if not, the content of the observation period marking submodule is executed;

[0142] The end-of-sale marking submodule is used to mark the life cycle of the product to be evaluated in the cluster as the end of its sales period;

[0143] The observation period marking submodule is used to mark the life cycle of the product to be evaluated in the cluster as the observation period.

[0144] Optionally, the policy output module 306 includes:

[0145] An evaluation item information acquisition submodule is used to obtain the code update status, sample status and packaging material minimum order quantity determination result of each product to be evaluated;

[0146] An evaluation item determination submodule, used to use the code update status, the sample status, the packaging material minimum order quantity determination result and the life cycle as evaluation items;

[0147] An evaluation item score determination submodule, used for determining the score of the evaluation item to be 1 when the evaluation item presents negative feedback;

[0148] A total score determination submodule, used to obtain the total score of the product to be evaluated based on the score and the preset weights of the evaluation items;

[0149] An elimination label setting submodule, used for setting an elimination label for the product to be evaluated whose total score is greater than a preset score threshold;

[0150] The elimination strategy output submodule is used to output the product to be evaluated, the evaluation items and the scores as an elimination strategy after the evaluation is completed.

[0151] Optionally, the sales characteristics include at least one of the average monthly sales volume of the product, the retail price of the product, the time of product launch, the most recent transaction date, the number of completed orders and the number of return orders.

[0152] The product elimination strategy determination device provided in the embodiment of the present invention can execute the product elimination strategy determination method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0153] Embodiment 4

[0154] Figure 4 A schematic diagram of an electronic device 40 that can be used to implement an embodiment of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0155] like Figure 4 As shown, the electronic device 40 includes at least one processor 41, and a memory connected to the at least one processor 41, such as a read-only memory (ROM) 42, a random access memory (RAM) 43, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 41 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 42 or the computer program loaded from the storage unit 48 to the random access memory (RAM) 43. In the RAM 43, various programs and data required for the operation of the electronic device 40 can also be stored. The processor 41, the ROM 42, and the RAM 43 are connected to each other through a bus 44. An input / output (I / O) interface 45 is also connected to the bus 44.

[0156] A number of components in the electronic device 40 are connected to the I / O interface 45, including: an input unit 46, such as a keyboard, a mouse, etc.; an output unit 47, such as various types of displays, speakers, etc.; a storage unit 48, such as a disk, an optical disk, etc.; and a communication unit 49, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 49 allows the electronic device 40 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0157] The processor 41 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 41 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The processor 41 executes the various methods and processes described above, such as a product elimination strategy determination method.

[0158] In some embodiments, the product elimination strategy determination method may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 48. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 40 via the ROM 42 and / or the communication unit 49. When the computer program is loaded into the RAM 43 and executed by the processor 41, one or more steps of the product elimination strategy determination method described above may be performed. Alternatively, in other embodiments, the processor 41 may be configured to execute the product elimination strategy determination method in any other appropriate manner (e.g., by means of firmware).

[0159] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0160] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0161] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0162] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0163] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0164] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0165] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0166] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for determining a product elimination strategy, characterized in that: include: Obtaining a time series corresponding to historical sales data of a target product, wherein the target product includes a product to be evaluated and an eliminated product; Extracting sales features of each of the time series in multiple dimensions; Clustering the target products based on the sales characteristics to obtain multiple clusters; Determine the number of the obsolete products in each cluster to obtain the obsolete number; Determine the life cycle corresponding to the product to be evaluated in each cluster based on the elimination quantity; obtain the code update status, sample status and packaging material minimum order quantity determination result of each product to be evaluated; The coding update status, the sample status, the packaging material minimum order quantity determination result and the life cycle are used as evaluation items; When the evaluation item presents negative feedback, determining the score of the evaluation item to be 1; Obtaining a total score of the product to be evaluated based on the score and the preset weights of the evaluation items; Setting an elimination label for the product to be evaluated whose total score is greater than a preset score threshold; After the evaluation is completed, the product to be evaluated, the evaluation items and the scores are output as an elimination strategy; The determining of the life cycle corresponding to the product to be evaluated in each cluster based on the number of eliminations includes: Arrange the clusters from largest to smallest according to the number of eliminations; Taking the first cluster as the counting starting point, the clusters with a cumulative number in the order of arrangement are taken as the target group, and the initial value of the cumulative number is 1; Calculating the sum of the elimination numbers of the target group to obtain a total elimination number; Calculate the ratio of the total number of eliminated products to the number of all eliminated products to obtain the elimination ratio; Determining whether the elimination ratio is greater than a preset first ratio; If yes, the life cycle of the product to be evaluated in the target group is marked as the end of sales, and the life cycle of other products to be evaluated is marked as the observation period; If not, the cumulative value is increased by 1, and the process returns to the step of taking the first cluster as the counting starting point and taking the clusters whose number is equal to the cumulative value as the target group in the order of arrangement; Alternatively, the determining the life cycle corresponding to the product to be evaluated in each cluster based on the number of obsolete products includes: For each cluster, determine the number of all products in the cluster to obtain the number within the cluster; Determine whether the ratio of the number of eliminated and the number of in-cluster numbers is greater than a preset second ratio; If yes, the life cycle of the product to be evaluated in the cluster is marked as the end of sales period; if no, the life cycle of the product to be evaluated in the cluster is marked as the observation period.

2. The method for determining a product elimination strategy according to claim 1, characterized in that: After extracting the sales features of each of the time series in multiple dimensions, the method further includes: For each of the time series, fitting the sales data in the time series to obtain a historical trend curve; Performing linear regression fitting on the historical trend curve to obtain a first slope; Selecting a recent trend curve from the historical trend curve, the time series being a trend curve within a recent preset time period; Performing linear regression fitting on the recent trend curve to obtain a second slope; The first slope and the second slope are added to the sales feature of the time series.

3. The method for determining a product elimination strategy according to claim 1, wherein: The target products are clustered based on the sales characteristics to obtain multiple clusters, including: Performing K-means clustering on the target product based on the sales characteristics to obtain groups with different cluster numbers, where the cluster number is the number of clusters in the group; Calculate the intra-cluster sum of squares corresponding to each of the groups; Determining a target number of clusters based on the number of clusters of the group and the intra-cluster sum of squares; The groups corresponding to the target clustering quantity are obtained to obtain a plurality of clusters.

4. The method for determining a product elimination strategy according to any one of claims 1 to 3, characterized in that: The sales characteristics include at least one of the average monthly sales volume of the product, the retail price of the product, the time the product was launched on the market, the latest transaction date, the number of completed orders and the number of return orders.

5. A device for determining a product elimination strategy, characterized in that: include: A data acquisition module, used to acquire a time series corresponding to historical sales data of a target product, wherein the target product includes a product to be evaluated and an eliminated product; A feature extraction module, used to extract sales features of each of the time series in multiple dimensions; A clustering module, used for clustering the target products based on the sales characteristics to obtain multiple clusters; The elimination quantity determination module is used to determine the quantity of the eliminated products in each cluster to obtain the elimination quantity; A life cycle determination module, used to determine the life cycle corresponding to the product to be evaluated in each cluster based on the elimination quantity; An evaluation item information acquisition submodule is used to obtain the code update status, sample status and packaging material minimum order quantity determination result of each product to be evaluated; An evaluation item determination submodule, used to use the code update status, the sample status, the packaging material minimum order quantity determination result and the life cycle as evaluation items; An evaluation item score determination submodule, used for determining the score of the evaluation item to be 1 when the evaluation item presents negative feedback; A total score determination submodule, used to obtain the total score of the product to be evaluated based on the score and the preset weights of the evaluation items; An elimination label setting submodule, used for setting an elimination label for the product to be evaluated whose total score is greater than a preset score threshold; An elimination strategy output submodule, used to output the product to be evaluated, the evaluation items and the scores as an elimination strategy after the evaluation is completed; The life cycle determination module includes: an arrangement submodule, a target group determination submodule, an elimination total calculation submodule, an elimination ratio calculation submodule, a first ratio calculation submodule, a life cycle determination submodule, and a cumulative value update submodule; The arrangement submodule is used to arrange the clusters from large to small according to the elimination number; The target group determination submodule is used to take the first cluster as the counting starting point, and select the clusters whose number is a cumulative value in the arrangement order as the target group, and the initial value of the cumulative value is 1; The total number of eliminations calculation submodule is used to calculate the sum of the elimination numbers of the target group to obtain the total number of eliminations; The elimination ratio calculation submodule is used to calculate the ratio of the total elimination number to the number of all the eliminated products to obtain the elimination ratio; The first ratio calculation submodule is used to determine whether the elimination ratio is greater than a preset first ratio; if so, the content of the life cycle determination first submodule is executed; if not, the content of the cumulative value update submodule is executed; The life cycle determination submodule is used to mark the life cycle of the product to be evaluated in the target group as the end of sales, and mark the life cycle of other products to be evaluated as the observation period; The accumulated value updating submodule is used to increase the accumulated value by 1 and return the content of the target group determination submodule; Alternatively, the life cycle determination module includes: a cluster quantity determination submodule, a second ratio calculation submodule, a sales end marking submodule, and an observation period marking submodule; The cluster quantity determination submodule is used to determine the quantity of all products in each cluster to obtain the cluster quantity; The second ratio calculation submodule is used to determine whether the ratio of the number of eliminated products to the number of products in the cluster is greater than a preset second ratio; if so, the content of the end-of-sales marking submodule is executed; if not, the content of the observation period marking submodule is executed; The end-of-sale marking submodule is used to mark the life cycle of the to-be-evaluated product in the cluster as the end-of-sale period; the observation period marking submodule is used to mark the life cycle of the to-be-evaluated product in the cluster as the observation period.

6. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the product elimination strategy determination method according to any one of claims 1 to 4.

7. 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 processor to implement the product elimination strategy determination method according to any one of claims 1 to 4 when executed.

Images