Commodity intelligent management method, device, equipment and program product
By calculating the normalized ranking and classification of goods in the unmanned retail system and combining it with lifecycle prediction, the problem of inaccurate product evaluation in unmanned retail is solved, enabling precise product management and inventory optimization, and improving equipment efficiency and corporate profitability.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- SHENZHEN YOUBAOSI TECH CO LTD
- Filing Date
- 2026-01-20
- Publication Date
- 2026-06-09
AI Technical Summary
The unmanned retail industry struggles to accurately and effectively assess the quality of goods, resulting in underutilization of retail equipment, unbalanced inventory structures, and wasted resources.
By acquiring historical sales data from various retail devices, calculating the normalized ranking value of products, classifying them, and combining this with lifecycle forecasting and new product introduction forecasting, a product rotation strategy can be determined to achieve precise product management.
It enables accurate evaluation and quality assessment of goods, improves the efficiency of retail equipment, optimizes inventory structure, reduces losses of slow-moving goods, and enhances corporate profitability.
Smart Images
Figure CN122175662A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of new retail, and in particular to intelligent product management methods, devices, equipment and program products. Background Technology
[0002] In the retail industry, merchandise management is a core operational aspect, directly impacting a company's profitability and operational efficiency. Traditional merchandise management requires a comprehensive assessment of merchandise sales levels, performance in specific scenarios and regions, and the timing of disposing of slow-moving items. An objective and refined merchandise evaluation system can help companies accurately grasp the merchandise lifecycle, thereby increasing revenue and profit margins, reducing warehousing costs, and optimizing cash flow.
[0003] As an important branch of the retail industry, unmanned retail has a unique operating model. Each unmanned retail device is essentially a "mini-store," and the optimization of its SKU (Stock Keeping Unit) combination directly determines the profitability of a single location. Therefore, establishing a scientific and objective product sales evaluation system, realizing a data loop of "elimination" and "recommendation" of product SKUs, and continuously iterating the product combination within the device are the core driving forces for unmanned retail companies to achieve profit growth.
[0004] However, when evaluating products in the current unmanned retail industry, the different sales data from different devices make it difficult to accurately and effectively assess the quality of products, which is not conducive to better leveraging the efficiency of retail equipment. Summary of the Invention
[0005] In view of this, embodiments of this application provide a method, apparatus, equipment, and program product for intelligent commodity management, in order to solve the problem that the prior art is not convenient for accurately and effectively evaluating the quality of commodities, and is not conducive to better utilizing the efficiency of retail equipment.
[0006] A first aspect of this application provides a smart product management method, the method comprising: Obtain historical sales data for products in each retail device; Based on the historical sales data, determine the normalized value of the product's ranking across all retail devices; Obtain the category of the product, and determine the product's classification result in the category based on the ranking normalization value; Based on the product classification results, combined with the product lifecycle prediction results and / or new product introduction prediction results, the product rotation strategy is determined and implemented.
[0007] In conjunction with the first aspect, in a first possible implementation of the first aspect, the historical sales data includes the gross profit and revenue of the goods; Based on the historical sales data, the normalized ranking value of the product among all retail devices is determined, including: Determine the category of the goods in the retail equipment, and determine the gross profit ranking and revenue ranking of the goods in the category; Based on the gross profit ranking and the revenue ranking, determine the revenue normalized value of the product's revenue ranking and the gross profit normalized value of the product's gross profit ranking. The normalized value of the product is determined by weighted fusion of the normalized revenue value and the normalized gross profit value. The normalized composite value is subjected to attenuation processing and fluctuation correction to obtain the ranking normalized value.
[0008] In conjunction with the first aspect, in a second possible implementation of the first aspect, determining the normalized ranking value of a product across all retail devices based on the historical sales data includes: According to the formula Determine the normalized ranking value of the product, where x is the number of retail devices participating in the ranking calculation, and i is the ranking of the product within the retail device. k1 This represents the gross profit ranking of the k-th retail device, i. k2 For the revenue ranking of the kth retail device, j k Let S be the number of SKUs on the k-th retail device, S be the volatility factor, w_t be the decay factor, P1 be the gross profit weight, and P2 be the revenue weight.
[0009] In conjunction with the first aspect, in a third possible implementation of the first aspect, obtaining the category to which the product belongs and determining the product's grading result in the category based on the ranking normalization value includes: Obtain the category to which the product belongs, and determine the normalized ranking value of all products in the category; The normalized ranking values of all products in the category are compared to determine the product's classification result within the category.
[0010] In conjunction with the third possible implementation of the first aspect, in the fourth possible implementation of the first aspect, the ranking normalized values of all goods in the category are compared to determine the classification result of the goods in the category, including: The average normalized value is determined by calculating the mean of the normalized values of the rankings of all products in the category. Determine the difference between the normalized ranking value and the normalized average value of the product; The product's classification within the category is determined based on the difference.
[0011] In conjunction with the first aspect, in the fifth possible implementation of the first aspect, based on the product classification results and the product lifecycle prediction results, a product rotation strategy is determined and implemented, including: Based on the historical sales data of the product, a sales data prediction curve for the product is generated by fitting the data. Based on the sales data prediction curve and the product's grading result at the current time, the product's grading prediction result is predicted for a predetermined preset period after the current time. The product rotation strategy is determined and implemented based on the tiered prediction results.
[0012] In conjunction with the first aspect, in the sixth possible implementation of the first aspect, based on the product classification results and the new product introduction prediction results, the product rotation strategy is determined and implemented, including: Based on the product classification results, products with a first priority and products with a second priority are determined, with the first priority being higher than the second priority. Find the first product attribute of the product with the first priority, and find related new products based on the first product attribute; The product rotation strategy is determined and executed based on the relevant new products and the products with the first priority.
[0013] A second aspect of this application provides a smart commodity management device, the device comprising: The historical sales data acquisition unit is used to acquire historical sales data of goods in various retail devices; A normalization processing unit is used to determine the normalized ranking value of a product among all retail devices based on the historical sales data. A grading unit is used to obtain the category to which the product belongs and to determine the grading result of the product in the category based on the ranking normalization value. The rotation unit is used to determine and execute the rotation strategy of the product based on the product classification results, combined with the product life cycle prediction results and / or new product introduction prediction results.
[0014] A third aspect of this application provides a smart product management device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the smart product management device enables the smart product management device to implement the method described in any of the first aspects.
[0015] A fourth aspect of this application provides a computer program product that, when run on a computer, causes the computer to execute the methods described in the first aspect or its various implementations.
[0016] A fifth aspect of this application provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the method as described in any of the first aspects.
[0017] A sixth aspect of this application provides a chip for implementing the methods in the various implementations of the first aspect described above. Specifically, the chip includes a processor for calling and running a computer program from a memory, causing a device equipped with the chip to perform the methods as described in the first aspect or its various implementations.
[0018] The beneficial effects of this application embodiment compared with the prior art are as follows: This application embodiment calculates the normalized value of the product ranking across all retail devices based on the historical sales data of the products in each retail device, thereby effectively reflecting the ranking of the products in different retail devices. By determining the normalized value of the product ranking in the category, the products in the same category can be classified, and the classification results of the products in the same category can be accurately obtained. Furthermore, by combining the product life cycle prediction results and / or the new product introduction prediction results, the product rotation strategy can be determined. By determining the rotation strategy through the prediction results, the changes in future product data can be adapted more accurately. By predicting the classification results of the introduced new products, the rotation strategy of the new products can be determined more reliably, which is conducive to more reliable evaluation of the merits of the products and better utilization of the retail devices. Attached Figure Description
[0019] To more clearly illustrate the technical solutions in the embodiments of this application, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0020] Figure 1 This is a schematic diagram illustrating an implementation scenario of an intelligent commodity management method provided in an embodiment of this application; Figure 2 This is a schematic diagram illustrating the implementation process of a smart commodity management method provided in an embodiment of this application; Figure 3 This is a schematic diagram illustrating the implementation process for determining a ranking normalization value provided in an embodiment of this application; Figure 4 This is a schematic diagram illustrating the implementation process for determining a grading result provided in an embodiment of this application; Figure 5 This is a schematic diagram illustrating the implementation process of determining classification results based on the mean, as provided in an embodiment of this application. Figure 6This is a schematic diagram illustrating the implementation process of determining a rotation strategy according to an embodiment of this application; Figure 7 This is a schematic diagram of a smart commodity management device provided in an embodiment of this application; Figure 8 This is a schematic diagram of a smart commodity management device provided in an embodiment of this application. Detailed Implementation
[0021] In the following description, specific details such as particular system architectures and techniques are set forth for illustrative purposes and not for limitation, in order to provide a thorough understanding of the embodiments of this application. However, those skilled in the art will understand that this application may also be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, circuits, and methods have been omitted so as not to obscure the description of this application with unnecessary detail.
[0022] To illustrate the technical solution described in this application, specific embodiments are provided below.
[0023] Merchandise management is a core aspect of retail operations, directly impacting a company's profitability and operational efficiency. Traditional merchandise management requires a comprehensive assessment of product sales performance, regional adaptability, and the timing of eliminating slow-moving items. Establishing an objective and refined merchandise evaluation system helps companies accurately grasp the product lifecycle, increase revenue and profit margins, reduce warehousing costs, and optimize cash flow.
[0024] As an important branch of the retail industry, unmanned retail has a unique operating model. Each unmanned retail device is essentially a "mini-store," and the optimization of its SKU (stock keeping unit) combination directly determines the profitability of a single location. Therefore, establishing a scientific and objective product sales evaluation system, realizing a data closed loop of product SKU "elimination" and "recommendation," and continuously optimizing the device's product combination are the core driving forces for unmanned retail companies to achieve profit growth.
[0025] However, the current unmanned retail industry faces challenges in product evaluation: due to differences in sales data from different devices, it is difficult to accurately and effectively assess the quality of products, thus limiting the full utilization of retail equipment efficiency.
[0026] Furthermore, with the expansion of enterprise scale, the surge in the number of SKUs, and the diversification of sales channels and scenarios, the traditional product evaluation system suffers from difficulties in unifying data standards, lacking objective basis for evaluation criteria, and inefficient cross-departmental decision-making that is easily influenced by subjective interests. These problems often lead to the misjudgment and elimination of high-quality SKUs, while slow-moving products continue to be ordered, resulting in an imbalance in inventory structure and a double waste of capital and shelf resources.
[0027] Traditional product evaluation systems have the following specific problems: 1. Severe data lag: Traditional product evaluation systems rely on manual compilation of sales, gross profit and other report data, and then make decisions based on experience. The evaluation cycle is too long, and the best window of opportunity for product adjustment is missed.
[0028] 2. Data averaging distortion: Traditional product evaluation systems ignore revenue differences between different retail terminals, causing product sales indicators to be distorted after averaging, affecting the accuracy of evaluation conclusions.
[0029] 3. Limited evaluation dimensions: Traditional product evaluation systems rely excessively on traditional indicators such as historical sales volume, revenue, gross profit, and sales per square meter, lacking the integration of multi-dimensional parameters such as geographical region and terminal scenario, making it difficult to fully reflect the true performance of products.
[0030] 4. Lack of lifecycle management: Traditional product evaluation systems fail to systematically track the entire lifecycle of SKUs from introduction, growth, maturity to decline, resulting in inaccurate resource allocation. This makes it impossible to maximize profits during the maturity stage or to clear inventory in a timely manner during the decline stage.
[0031] 5. Lack of early warning mechanism: Traditional commodity evaluation systems lack intelligent early warning functions based on dynamic thresholds. They are often only discovered passively when sluggish sales problems become prominent and inventory backlog is serious, which has already caused substantial business losses.
[0032] 6. Lagging experience-based decision-making: Traditional product evaluation systems rely on human experience based on historical data, which is difficult to adapt to the reality of new product emergence, the replacement of best-selling products, and rapid changes in consumer preferences, causing experience to become an obstacle to decision-making.
[0033] 7. Difficulty in strategic coordination: Due to the lack of unified and transparent evaluation standards, traditional product evaluation systems are prone to a situation of "mutual distrust" between headquarters and regions in SKU selection - headquarters strongly promotes new products with high gross margins, while regions stick to local sales orientation, resulting in poor strategic execution and internal resource consumption.
[0034] 8. High compliance audit risk: The decision-making process of traditional product evaluation systems relies on personal experience and offline forms, lacking traceable approval processes and data support. It is difficult to prove the rationality and fairness of product replacement in internal audits or external inspections.
[0035] To address the aforementioned problems, this application proposes an intelligent commodity management method. Figure 1 This is a schematic diagram illustrating an implementation scenario for this method. For example... Figure 1As shown, this implementation scenario includes a server 1 and multiple retail devices 2. Retail devices 2 can be vending machines or smart vending machines. Retail devices 2 can transmit historical sales data to server 1. Server 1 can determine the normalized ranking value of a product among all retail devices based on the historical sales data, including the normalized values of ranking data such as product gross profit ranking and product revenue ranking. Based on the normalized ranking value, the server accurately obtains the product's classification result within its category. Based on the product classification result, combined with the product lifecycle prediction result and / or new product introduction prediction result, the server determines a product rotation strategy, increasing the number of high-level products and decreasing the number of low-level products, thereby effectively improving the efficiency of the retail devices.
[0036] Figure 2 A schematic diagram illustrating the implementation process of a smart commodity management method provided in this application embodiment is described in detail below: In S201, historical sales data of goods in each retail device are obtained.
[0037] The system can periodically extract historical sales data from the backend databases of retail devices (such as vending machines and smart lockers) distributed across various locations via API (Application Programming Interface) or data acquisition programs. This historical sales data includes, but is not limited to: product SKU code, sales time, sales quantity, sales amount, gross profit, device ID, device geographical location (e.g., province / city, business district), and device location type (e.g., school, office building, subway station). Data extraction can be performed daily, and the system retains complete data for the most recent 30 days for analysis.
[0038] Historical sales data can be sales data within a predetermined period prior to the current time, serving as the basis for subsequent analysis and calculations.
[0039] In S202, the normalized value of the product's ranking among all retail devices is determined based on the historical sales data.
[0040] The rank normalization value refers to the normalized value of a product's ranking among all retail devices. The formula for calculating the rank normalization value can be expressed as: Where x is the number of retail devices participating in the ranking calculation, and i is the ranking of the product within the retail device. k1 This represents the gross profit ranking of the k-th retail device, i. k2 For the revenue ranking of the kth retail device, j k Let S be the number of SKUs on the k-th retail device, S be the volatility factor, w_t be the decay factor, P1 be the gross profit weight, and P2 be the revenue weight.
[0041] The process of determining the normalized ranking value can be as follows: Figure 3 As shown, it includes: In S301, the category of the goods in the retail equipment is determined, and the gross profit ranking and revenue ranking of the goods in the category are determined.
[0042] To avoid unfairness in cross-category comparisons, product ranking refers to the ranking of a product within the same major, sub, or minor product category. For example, a major product category might include snacks and beverages. The major beverage category might include multiple subcategories such as bottled water, tea drinks, and functional beverages. Bottled water might include multiple minor categories, such as various brands of purified water and distilled water. The major, sub, and minor categories can be set according to the scope of the ranking as needed.
[0043] After determining the category of the goods in each device, the system will sort all goods in each category for each device based on their historical sales data (such as the last 30 days). The ranking of historical sales data includes the gross profit ranking and revenue ranking of each product in each device and each category (major category, medium category, or minor category).
[0044] The ranking system allows for two main methods: Gross Profit Ranking and Revenue Ranking. Gross Profit is ranked from highest to lowest for each product within the same category and for the same equipment, with the highest gross profit per unit time ranking first. Similarly, Revenue Ranking is ranked from highest to lowest for each product within the same category and for the same equipment, with the highest revenue per unit time ranking first. Using either Gross Profit or Revenue per Unit Time effectively accommodates scenarios where different products may be displayed for varying durations. Ranking based on Total Gross Profit or Total Revenue over a predetermined period is less accurate as the number of display days affects the calculated total gross profit and total revenue. Calculating Gross Profit and Revenue per Unit Time based on the product's display days, gross profit, and revenue effectively eliminates the influence of display days on the results, making the ranking more reliable and effective.
[0045] In S302, based on the gross profit ranking and the revenue ranking, the revenue normalized value of the revenue ranking of the product and the gross profit normalized value of the gross profit ranking of the product are determined.
[0046] In S303, the normalized revenue value and the normalized gross profit value are weighted and merged to determine the normalized composite value of the product.
[0047] For all products within the same retail device, their ranking within their corresponding category (major, intermediate, or minor category) can be determined by identifying the first interval between the product and the top-ranked product, as well as the maximum possible interval between the top and bottom-ranked products. The normalized value of the product within the major category is then determined based on the ratio of the first interval to the maximum interval. For example, a product's gross profit ranking determines its normalized gross profit value, while its revenue ranking determines its normalized revenue value.
[0048] Assuming the product's ranking in the category (major category) of retail equipment k is ik, and the number of SKUs in retail equipment k is jk, then the normalized value of the product can be expressed as: (ik-1) / (jk-1). The ranking ik can be either revenue ranking or gross profit ranking, and the determined normalized values are the revenue normalized value and the gross profit normalized value, respectively.
[0049] The normalized composite value can be obtained by combining the determined normalized gross profit value and normalized revenue value with their corresponding weights. The sum of the normalized gross profit values of all devices can be calculated, and then the average of these sums can be taken before weighting to obtain the weighted gross profit value. Similarly, the sum of the normalized revenue values of all devices can be calculated, and then the average of these sums can be taken before weighting to obtain the weighted revenue value. The sum of the weighted gross profit value and the weighted revenue value is the normalized composite value, which can be expressed as: Normalized Composite Value = P1*(1 / x)*Σ(Normalized Gross Profit Value) + P2*(1 / x)*Σ(Normalized Revenue Value). Where P1 is the gross profit weight, P2 is the revenue weight, and x is the number of retail devices participating in the ranking calculation.
[0050] In S304, the normalized composite value is subjected to attenuation processing and fluctuation correction to obtain the ranking normalized value.
[0051] To emphasize the importance of recent data, sales data from different dates can be assigned exponential decay weights, which can be expressed as w_t=exp(-λ*Δt). Applying decay weights to the normalized composite value makes the calculated normalized ranking value more accurate and reliable.
[0052] To eliminate the influence of factors such as time and climate, a volatility correction factor can be added. For example, a seasonal volatility factor S can be multiplied. When evaluating peak-season products during the off-season, S>1, amplifying the degree of poor performance and thus making the comparison more accurate.
[0053] In S203, the category to which the product belongs is obtained, and the grading result of the product in the category is determined based on the ranking normalization value.
[0054] The system first determines the precise category to which each product SKU belongs based on the product classification system (e.g., major category > intermediate category > minor category). For example, the major category "beverages" may include intermediate categories such as "water beverages," "functional beverages," and "tea beverages." These intermediate categories can be further subdivided; for instance, "water beverages" may include different brands of purified or distilled water beverages.
[0055] The process of determining the classification results can be as follows: Figure 4 As shown, it includes: In S401, the category to which the product belongs is obtained, and the normalized ranking value of all products in the category is determined.
[0056] When determining the product grading results, first determine the product category, which can be a major category, a medium category, or a minor category. Based on the product's ranking within that category, use... Figure 3 The method shown determines the normalized ranking value of each product in the category.
[0057] In S402, the normalized ranking values of all products in the category are compared to determine the classification result of the product in the category.
[0058] Based on the normalized ranking values of all products within the same category, products can be sorted from smallest to largest according to their normalized ranking values to obtain a ranking result. The grading result can then be used to determine the classification. For example, based on a pre-set proportional threshold, each product can be sequentially divided into different grading results.
[0059] For example, the grading results include four levels: A, B, C, and D. Level A products (star products) are the top 20% of products. They are the mainstays of sales and should receive the most distribution resources and promotional support. Level B products (potential products) are those ranking between 20% and 50%. They perform steadily or have growth potential and are an important source of revenue; their current distribution level should be maintained. Level C products (ordinary products) are those ranking between 50% and 80%. Their performance is average and they require optimization and evaluation; distribution should be reduced. Level D products (slow-moving products) are the bottom 20% of products. They perform poorly, tie up inventory and capital, and are the priority for elimination and replacement.
[0060] Among the possible implementations, the method for determining the grade order result can be as follows: Figure 5 As shown, it includes: In S501, the mean value is calculated based on the normalized ranking values of all products in the category to determine the average normalized value.
[0061] The system can first obtain the normalized ranking values of all valid products within a specified category. A lower normalized ranking value (Rank value) indicates better product performance. The arithmetic mean is then determined based on these normalized ranking values. The calculation formula is as follows: The average normalized value = (Rank value of product 1 + Rank value of product 2 + ... + Rank value of product n) / n. Where n is the total number of products in this category.
[0062] In S502, the difference between the normalized ranking value and the normalized average value of the product is determined.
[0063] To determine the quality level of a product, the difference between the product's normalized ranking value and its average normalized value can be calculated.
[0064] In S503, the grading result of the commodity in the category is determined based on the difference.
[0065] A negative difference indicates that the product's performance is above average, while a positive difference indicates that the product's performance is below average. Products can be categorized into different levels based on the extent to which they are above or below average; for example, products above average can be classified as A / B, and products below average as C / D.
[0066] In S204, based on the product classification results, combined with the product lifecycle prediction results and / or new product introduction prediction results, the product rotation strategy is determined and executed.
[0067] Based on the product classification results, the number of A-grade and B-grade products can be increased, while the number of C-grade and D-grade products can be decreased.
[0068] To manage goods more accurately and promptly, tiered forecasts can be generated based on historical data, such as... Figure 6 As shown, the process of determining the implementation of a product rotation strategy may include: In S601, the sales data of the historical products are fitted to generate a sales data prediction curve for the products.
[0069] The system can take historical sales data of a product (such as daily sales time series) as input and use algorithms such as regression analysis and time series models to fit the data, thereby finding the pattern of sales data changes over time (such as rise, fall, periodic fluctuations), and generating a sales data prediction curve that can extend into the future. This curve can identify which stage of the product's life cycle it is expected to be in (introduction, growth, maturity, or decline).
[0070] In S602, based on the sales data prediction curve and the product's grading result at the current time, the product's grading prediction result is predicted for a predetermined preset period after the current time.
[0071] The system transforms the sales data forecast curve obtained in the first step into predicted values for the product's core evaluation indicators (i.e., ranking normalized values) within a future preset period (such as the next quarter). Then, it compares these predicted values with the predicted indicators of other products in the same period to infer the product's future classification (e.g., A, B, C, D). For example, a product currently classified as B, if its sales are predicted to decline significantly, might be predicted to be classified as C or D in the future.
[0072] In S603, the rotation strategy for the goods is determined and executed based on the graded prediction results.
[0073] The system formulates rotation strategies not only based on the current classification results of the products, but also on their predicted future state, thereby enabling early intervention for products expected to deteriorate and reserving resources for products expected to perform well.
[0074] For example, for a product currently rated A but predicted to drop to C, the system might suggest gradually reducing its distribution, clearing inventory in advance, and making room for new products. For a product currently rated B but predicted to have the potential to become A, the system might suggest increasing its trial sales scope or stocking level. In this way, companies can prevent problems before they occur, significantly reduce losses caused by delayed responses to market changes, and seize growth opportunities.
[0075] In this embodiment, products can also be classified into first-priority and second-priority categories based on their classification results, with the first priority category having a higher priority than the second. First-priority products typically refer to the top-performing A-level products, and may also include potential B-level products. These are the engines and benchmarks for business growth, and require expanded distribution and focused maintenance. Second-priority products typically refer to poorly performing C-level and D-level products. These are products that need to be optimized, reduced, or phased out to free up resources for higher-priority products.
[0076] Based on the determined product priority, the first product attribute of the highest priority product can be searched, and related new products can be found based on the first product attribute. The first product attribute can include, for example, category / subcategory (e.g., "carbonated beverage", "tea beverage"), flavor (e.g., "white peach flavor", "sugar-free"), price range (e.g., "3-5 yuan range"), brand positioning (e.g., "health concept", "national trend brand"), packaging specifications (e.g., "500ml bottle", "250ml can"), etc.
[0077] The system can use these successful attributes in the first product attribute as filtering conditions to match in the supplier database or new product library to find related new products with similar or complementary attributes.
[0078] When determining a rotation strategy based on relevant new products and top-priority products, new products with high success potential can be introduced for trial sales, as these new products inherit successful genes (attributes) that have already been proven in the market. This forms a virtuous cycle of data loop where "high-performing products guide the introduction of new products, and new products replace poorly performing products."
[0079] This method employs data-driven, refined management of goods through an "assessment-grading-prediction-replacement" process. Based on a unified evaluation model, it achieves dynamic grading and rapid replacement, combined with intelligent forecasting to accurately guide supply chain decisions. All-chain indicators are objective and transparent, effectively improving collaborative efficiency and ultimately optimizing inventory—maximizing profits from best-selling products and minimizing losses from slow-moving items, thereby ensuring steady growth in enterprise revenue and profits.
[0080] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.
[0081] Figure 7 This is a schematic diagram of a smart commodity management device provided in an embodiment of this application. The device includes: Historical sales data acquisition unit 701 is used to acquire historical sales data of goods in various retail devices; Normalization processing unit 702 is used to determine the normalized ranking value of a product among all retail devices based on the historical sales data; The grading unit 703 is used to obtain the category of the product and determine the grading result of the product in the category based on the ranking normalization value. The rotation unit 704 is used to determine and execute the product rotation strategy based on the product classification results, combined with the product life cycle prediction results and / or new product introduction prediction results.
[0082] Figure 7 The intelligent product management device shown is, with Figure 2 The product intelligent management method shown corresponds to this.
[0083] Figure 8 This is a schematic diagram of a smart product management device provided in an embodiment of this application. Figure 8As shown, the intelligent product management device 8 of this embodiment includes: a processor 80, a memory 81, and a computer program 82 stored in the memory 81 and executable on the processor 80, such as an intelligent product management program. When the processor 80 executes the computer program 82, it implements the steps in the various intelligent product management method embodiments described above. Alternatively, when the processor 80 executes the computer program 82, it implements the functions of each module / unit in the various device embodiments described above.
[0084] For example, the computer program 82 can be divided into one or more modules / units, which are stored in the memory 81 and executed by the processor 80 to complete this application. The one or more modules / units can be a series of computer program instruction segments capable of performing specific functions, which describe the execution process of the computer program 82 in the intelligent commodity management device 8.
[0085] The intelligent product management device 8 can be a desktop computer, laptop, handheld computer, or cloud server, etc. The intelligent product management device may include, but is not limited to, a processor 80 and a memory 81. Those skilled in the art will understand that... Figure 8 This is merely an example of a smart product management device 8 and does not constitute a limitation on the smart product management device 8. It may include more or fewer components than shown, or combine certain components, or different components. For example, the smart product management device may also include input / output devices, network access devices, buses, etc.
[0086] The processor 80 may be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor.
[0087] The memory 81 can be an internal storage unit of the intelligent product management device 8, such as a hard drive or memory. The memory 81 can also be an external storage device of the intelligent product management device 8, such as a plug-in hard drive, Smart Media Card (SMC), Secure Digital (SD) card, or Flash Card. Furthermore, the memory 81 can include both internal and external storage units of the intelligent product management device 8. The memory 81 is used to store the computer program and other programs and data required by the intelligent product management device. The memory 81 can also be used to temporarily store data that has been output or will be output.
[0088] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is merely an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit. Furthermore, the specific names of the functional units and modules are only for easy differentiation and are not intended to limit the scope of protection of this application. The specific working process of the units and modules in the above system can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.
[0089] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail or recorded in a certain embodiment, please refer to the relevant descriptions of other embodiments.
[0090] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.
[0091] In the embodiments provided in this application, it should be understood that the disclosed devices / terminal equipment and methods can be implemented in other ways. For example, the device / terminal equipment embodiments described above are merely illustrative. For instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual coupling or direct coupling or communication connection may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.
[0092] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.
[0093] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.
[0094] If the integrated module / unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments can also be implemented by hardware related to computer program instructions. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording media, USB flash drives, portable hard drives, magnetic disks, optical disks, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media, etc.
[0095] In addition, this application also provides a computer program product that, when run on a computer, causes the computer to execute the methods in the above-described implementations.
[0096] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be included within the protection scope of this application.
Claims
1. A method for intelligent commodity management, characterized in that, The method includes: Obtain historical sales data for products in each retail device; Based on the historical sales data, determine the normalized value of the product's ranking across all retail devices; Obtain the category of the product, and determine the product's classification result in the category based on the ranking normalization value; Based on the product classification results, combined with the product lifecycle prediction results and / or new product introduction prediction results, the product rotation strategy is determined and implemented.
2. The method according to claim 1, characterized in that, The historical sales data includes the gross profit and revenue of the product; Based on the historical sales data, the normalized value of the product's ranking across all retail devices is determined, including: Determine the category of the goods in the retail equipment, and determine the gross profit ranking and revenue ranking of the goods in the category; Based on the gross profit ranking and the revenue ranking, determine the revenue normalized value of the product's revenue ranking and the gross profit normalized value of the product's gross profit ranking. The normalized value of the product is determined by weighted fusion of the normalized revenue value and the normalized gross profit value. The normalized composite value is subjected to attenuation processing and fluctuation correction to obtain the ranking normalized value.
3. The method according to claim 1, characterized in that, Based on the historical sales data, the normalized ranking value of the product among all retail devices is determined, including: According to the formula Determine the normalized ranking value of the product, where x is the number of retail devices participating in the ranking calculation, and i is the ranking of the product within the retail device. k1 This represents the gross profit ranking of the k-th retail device, i. k2 For the revenue ranking of the kth retail device, j k Let S be the number of SKUs on the k-th retail device, S be the volatility factor, w_t be the decay factor, P1 be the gross profit weight, and P2 be the revenue weight.
4. The method according to claim 1, characterized in that, Obtaining the category of the product and determining the product's grading result within that category based on the ranking normalization value includes: Obtain the category to which the product belongs, and determine the normalized ranking value of all products in the category; The normalized ranking values of all products in the category are compared to determine the product's classification result within the category.
5. The method according to claim 4, characterized in that, Comparing the normalized ranking values of all products in the category to determine the product's classification within the category includes: The average normalized value is determined by calculating the mean of the normalized values of the rankings of all products in the category. Determine the difference between the normalized ranking value and the normalized average value of the product; The product's classification within the category is determined based on the difference.
6. The method according to claim 1, characterized in that, Based on the product grading results and the product lifecycle prediction results, a product rotation strategy is determined and implemented, including: Based on the historical sales data of the product, a sales data prediction curve for the product is generated by fitting the data. Based on the sales data prediction curve and the product's grading result at the current time, the product's grading prediction result is predicted for a predetermined preset period after the current time. The product rotation strategy is determined and implemented based on the tiered prediction results.
7. The method according to claim 1, characterized in that, Based on the product classification results and the new product introduction prediction results, determine and implement the product rotation strategy, including: Based on the product classification results, products with a first priority and products with a second priority are determined, with the first priority being higher than the second priority. Find the first product attribute of the product with the first priority, and find related new products based on the first product attribute; The product rotation strategy is determined and executed based on the relevant new products and the products with the first priority.
8. A smart commodity management device, characterized in that, The device includes: The historical sales data acquisition unit is used to acquire historical sales data of goods in various retail devices; A normalization processing unit is used to determine the normalized ranking value of a product among all retail devices based on the historical sales data. A grading unit is used to obtain the category to which the product belongs and to determine the grading result of the product in the category based on the ranking normalization value. The rotation unit is used to determine and execute the rotation strategy of the product based on the product classification results, combined with the product life cycle prediction results and / or new product introduction prediction results.
9. A smart commodity management device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it causes the intelligent commodity management device to implement the method as described in any one of claims 1-7.
10. A computer program product comprising computer program instructions, characterized in that, When the computer program is run, the method as described in any one of claims 1-7 is performed.