A warehouse time-limited goods joint scheduling method and system

Abstract

Multiple embodiments of this specification relate to the field of information technology, and specifically to a warehouse time-limited goods joint scheduling method and system. The method includes the steps of: reading the on-shelf data of the time-limited products of the stores distributed by the warehouse, the on-shelf data including price, production date and quantity; obtaining the new arrival ratio, near-expiry ratio and expired ratio of the time-limited products of each store based on the on-shelf data; calculating the time-limited quality score based on the new arrival ratio, near-expiry ratio and expired ratio; establishing a sales forecast model for the store; generating the delivery volume for each store, and calculating the updated time-limited quality score for each store based on the on-shelf data and the delivery volume; obtaining the updated predicted sales based on the updated time-limited quality score, price and the sales forecast model; using the optimization algorithm to obtain the final delivery volume for each store with the goal of maximizing the updated predicted sales.

Description

Technical Field

[0001] Multiple embodiments of this specification relate to the field of information technology, and specifically to a warehouse time-limited cargo joint scheduling method and system. Background Art

[0002] Warehouse goods include some time-limited goods, such as time-limited products. Time-limited products are a type of goods distributed by warehouses that has grown significantly in recent years. Time-limited products usually have a high moisture content, are perishable, or have a certain period of popularity and value, so they have relatively stricter requirements for storage, transportation and distribution time. These products are characterized by a short shelf life or a short value period, and need to be delivered from the production site to the consumer in a short time to ensure their freshness, quality or freshness. Fresh or high-freshness time-limited products are more valuable, and time-limited products taste better and can meet the taste needs of consumers. The fresher the time-limited products, the less bacteria they breed and carry, and the healthier they are. These products can bring a better consumer experience. Fresh time-limited products have better market popularity. The loss rate of time-limited products is high. How to reduce losses while ensuring freshness and maximize sales is a topic that the industry needs to study. Summary of the invention

[0003] Multiple embodiments of this specification describe a warehouse time-limited cargo joint scheduling method and system.

[0004] In a first aspect, an embodiment of the present specification provides a method for joint scheduling of time-limited goods in a warehouse, comprising the steps of:

[0005] Read the on-shelf data of the time-limited products of the stores delivered by the warehouse, the on-shelf data including price, production date and quantity;

[0006] According to the on-shelf data, the new arrival ratio, the near-limit ratio and the over-limit ratio of the time-limited products of each store are obtained;

[0007] Calculate and obtain a time limit quality score based on the new entry ratio, critical limit ratio and over-limit ratio;

[0008] Establishing a sales forecasting model for the store, the sales forecasting model records the relationship between the time-limit quality score and price and the predicted sales;

[0009] Generate the delivery volume of each store, and calculate the update time limit quality score of each store based on the on-shelf data and the delivery volume;

[0010] Obtaining updated predicted sales volume according to the update time limit quality score, price and the sales volume prediction model;

[0011] With the goal of maximizing the updated predicted sales volume, an optimization algorithm is used to obtain the final delivery volume for each store.

[0012] In a second aspect, the embodiment of this specification provides a warehouse time-limited cargo joint scheduling system, including:

[0013] A reading module is used to read the on-shelf data of the time-limited products of the stores delivered by the warehouse, wherein the on-shelf data includes price, production date and quantity;

[0014] A calculation module, based on the on-shelf data, obtains the new arrival ratio, the near-limit ratio and the over-limit ratio of the time-limited products in each store;

[0015] A scoring module, which calculates a time limit quality score according to the new entry ratio, the critical limit ratio and the over-limit ratio;

[0016] A prediction module, which establishes a sales prediction model for a store, wherein the sales prediction model records the relationship between the time-limit quality score and the price and the predicted sales;

[0017] The initial module generates the delivery volume of each store, and calculates the update time limit quality score of each store based on the on-shelf data and the delivery volume;

[0018] An update module, which obtains updated predicted sales according to the update time limit quality score, price and the sales prediction model;

[0019] The optimization module uses an optimization algorithm to obtain the final delivery volume for each store with the goal of maximizing the updated predicted sales volume.

[0020] In a third aspect, an embodiment of this specification provides an electronic device, including a processor and a memory;

[0021] The processor is connected to the memory;

[0022] The memory is used to store executable program code;

[0023] The processor runs a program corresponding to the executable program code by reading the executable program code stored in the memory, so as to execute the method described in any one of the above aspects.

[0024] In a fourth aspect, an embodiment of the present specification provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the method described in any of the above aspects.

[0025] In a fifth aspect, an embodiment of this specification provides a computer program product, including a computer program, which implements the method described in any of the above aspects when executed by a processor.

[0026] The beneficial effects brought by the technical solutions provided by some embodiments of this specification include at least:

[0027] In multiple embodiments of the present specification, the provided warehouse time-limited goods joint dispatch method and system calculates the new arrival ratio, the limit ratio and the over-limit ratio of the store, and establishes a sales forecast model to provide decision support for determining the delivery volume of time-limited products, which can help ultimately increase the sales of time-limited products, thereby helping to reduce over-limit situations. With the help of the sales forecast model, the sales volume of time-limited products can be predicted, which helps to improve the scientific nature of delivery volume decisions and is better than manually determining the delivery volume based on experience. When generating the delivery volume of a store, weights are set according to the new arrival ratio, and the initial store delivery volume is generated according to the weights and the amount to be delivered, which helps to improve the execution efficiency of the optimization algorithm and helps to avoid falling into a local optimal solution.

[0028] Other features and advantages of the various embodiments of the present specification will be further disclosed in the following detailed description and drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] In order to more clearly illustrate the technical solutions in the embodiments of this specification, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this specification. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0030] Figure 1 This is a schematic diagram of the application scenario of the warehouse time-limited goods joint scheduling method provided in this manual.

[0031] Figure 2 A schematic diagram of the application architecture of the warehouse time-limited cargo joint scheduling method provided in this manual.

[0032] Figure 3 This is a schematic diagram of the interactive interface provided for this manual.

[0033] Figure 4 This is a flow chart of the warehouse time-limited cargo joint scheduling method provided in this manual.

[0034] Figure 5 This is a flow chart of the sales forecasting model establishment method provided in this manual.

[0035] Figure 6 This is a flow chart of the new entry ratio calculation method provided in this manual.

[0036] Figure 7 Schematic diagram of the warehouse cargo union system provided for this instruction manual.

[0037] Figure 8 Schematic diagram of the electronic device provided for this instruction manual. DETAILED DESCRIPTION

[0038] The following is an explanation and description of the technical solutions of the embodiments of this specification in conjunction with the drawings of the embodiments of this specification, but the following embodiments are only preferred embodiments of this specification, not all. Based on the embodiments in the implementation mode, other embodiments obtained by those skilled in the art without creative work are all within the scope of protection of this specification.

[0039] The terms "first", "second", "third", etc. in the description and claims of this specification and the above-mentioned drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally includes steps or units that are not listed, or optionally includes other steps or units inherent to these processes, methods, products or devices.

[0040] In the following description, terms such as "inside", "outside", "up", "down", "left", "right", etc. that indicate directions or positional relationships are only used to facilitate the description of the embodiments and simplify the description, and do not indicate or imply that the device or element referred to must have a specific direction, be constructed and operated in a specific direction, and therefore should not be understood as a limitation of this specification.

[0041] The data involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection of relevant data complies with the relevant laws, regulations and standards of relevant countries and regions.

[0042] Before describing the technical solution in this specification, the application scenarios and related technologies of the technical solution are introduced.

[0043] The freshness or freshness of time-limited products is an important factor that consumers consider when purchasing. However, the consideration of price is relatively small. For example, time-limited products include perishable goods such as vegetables and fruits, as well as popular blind boxes, figurines and other products with short-term popularity and popularity. As consumers pay more and more attention to dietary health, they are willing to pay higher prices for high-quality and safe time-limited products. In contrast, lower-priced time-limited products have relatively more risks during storage and transportation. Fresh time-limited products have higher nutritional value or can bring higher satisfaction. For example, they can provide more vitamins, minerals and other nutrients that are beneficial to the human body, or enable consumers to have new figurines that have just been put on the market. Fresh time-limited products have a more unique taste. The taste is more delicious and can provide a better experience. When consumers buy time-limited products, they often want to get the best taste and flavor, so they are willing to pay a higher price for it. Consumers generally believe that higher-priced time-limited products are usually of better quality and more trustworthy. This psychological expectation makes them pay more attention to freshness rather than price when buying time-limited products. Fresh time-limited products are more popular in the market, and merchants often attract consumers by improving freshness to increase sales. However, time-limited products that are not fresh or have low freshness or are not popular will lose more market opportunities.

[0044] The supply and distribution of time-limited products is a complex logistics management issue, involving multiple aspects and technologies. At present, the supply and distribution of time-limited products still adopt a relatively rough approach, based on the experience of managers, which leads to a poor grasp and matching of consumers' actual needs, affecting sales and causing relatively more over-limit and waste. Time-limited products need to complete the entire process from production to sales in a short period of time. The current management method lacks corresponding data support and reasonable decision-making plans. Managers mainly rely on experience and intuition to make decisions. This subjectivity and uncertainty greatly reduces the efficiency of the supply chain. In addition, the distribution lacks a flexible adjustment mechanism, making it difficult to respond to market changes quickly, resulting in an imbalance between supply and demand. On the one hand, overproduction or distribution will lead to product backlogs, increase storage costs and loss rates; on the other hand, insufficient production or delayed distribution will lead to out-of-stocks, missed sales opportunities, and affect customer satisfaction.

[0045] Another problem is that the inventory management of time-limited products is not sophisticated enough. The inventory management of time-limited products needs to be highly refined to ensure that the products reach consumers in the best condition. The current inventory management mainly relies on manual experience and simple inventory records. This extensive management method makes it difficult to accurately predict demand, resulting in frequent inventory backlogs or out-of-stocks. The inefficiency of the distribution link is also an important factor affecting the supply chain of time-limited products. The delivery of time-limited products needs to be completed in a short period of time, and there are strict requirements on time and temperature. The current distribution methods often lack scheduling and optimization tools, and mainly rely on manual scheduling and experience judgment, which can easily lead to delivery delays and unreasonable distribution of delivery volume.

[0046] To this end, it is necessary to study the technology of time-limited cargo scheduling. Figure 1 , which is a schematic diagram of the application scenario of this technical solution. The figure shows two delivery volume schemes. Before delivery, the new entry ratio of the first store is 0.724, the limit ratio is 0.185, and the over-limit ratio is 0.021. When the delivery volume of the first store is 30 pieces, the new entry ratio of the first store becomes 0.825, the limit ratio becomes 0.093, and the over-limit ratio becomes 0.018. When the delivery volume of the first store is 50 pieces, the new entry ratio of the first store becomes 0.873, the limit ratio becomes 0.052, and the over-limit ratio becomes 0.016. Exemplarily, after the sales forecast model of three stores, the updated forecast sales (the total updated forecast sales of the three stores) that can be obtained by the delivery volume ① (that is, the first store delivers 30 pieces, the second store delivers 50 pieces, and the third store delivers 40 pieces) is greater than the updated forecast sales that can be obtained by the delivery volume ② (that is, the first store delivers 50 pieces, the second store delivers 20 pieces, and the third store delivers 50 pieces). Therefore, the delivery volume ① is selected as the final delivery volume of each store. (Assume that only the delivery volume ① and the delivery volume ② are compared). This provides a basis for decision-making on allocating the delivery volume to each store. When the sales forecast model gradually improves in accuracy due to data iteration, more scientific decision-making results can be obtained, which helps to better sell time-limited products.

[0047] Please refer to the attached Figure 2 , which is a schematic diagram of the system architecture for the deployment of the technical solution recorded in this specification. The staff of each store and warehouse 11 uploads the relevant data to the server 20 through the terminal device 21. After the server 20 aggregates the data, it executes the technical solution recorded in this specification. Or after the server 20 aggregates the data, it sends it to the terminal device 21 of the staff of the warehouse 11, and the terminal device 21 executes the technical solution recorded in this specification to obtain the delivery volume of each store. Similarly, the technical solution recorded in this specification can also achieve the expected technical effect when executed by the terminal device 21 of the staff of a certain store.

[0048] Each terminal device 21 runs an interactive interface, which has areas for uploading shelf data, historical sales data, and quantities to be delivered, as well as an area for viewing the final delivery quantity of each store, as shown in the attached figure. Figure 3 As shown. The establishment of stores 10 and warehouses 11 is completed by the server 20, or by another interactive interface, and the technical solutions disclosed in the art can be used. The interactive interface can be run on the terminal device 21 in the form of a browser, or in the form of an independent application (application, APP), etc. The specific display form of the interactive interface is not limited here. The server 20 involved in this application can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (Content Delivery Network, CDN), and big data and artificial intelligence platforms. The terminal device 21 can be a smart phone, a tablet computer, a laptop, a PDA, a personal computer, a smart speaker, a smart TV, a smart watch, a car device, a wearable device, etc., but is not limited thereto. The terminal device 21 and the server 20 can be directly or indirectly connected by wired or wireless communication, and this application does not limit it here. There is no limit on the number of servers 20 and terminal devices 21. The solution provided in this application can be completed by the terminal device 21 independently, or by the server 20 independently, or by the terminal device 21 and the server 20 in cooperation, and this application does not make any specific limitation on this.

[0049] Since this application involves some professional terms, these professional terms will be introduced below.

[0050] New entry ratio

[0051] The new entry ratio refers to the time-limited products on the shelf whose production date is within the preset range. The specific judgment criteria will be described later.

[0052] Threshold ratio

[0053] The critical ratio indicates the time-limited products on the shelf whose time limit is within the preset range. The specific judgment criteria will be described later.

[0054] Over-limit ratio

[0055] The critical limit ratio refers to the number of time-limited products on the shelf that have exceeded their time limits before they are cleared out on the day. After counting the number of time-limited products that have exceeded their time limits, these time-limited products will be removed from the shelves. This is usually done before the business opens on the day.

[0056] Machine Learning Models

[0057] A machine learning model is a system that learns regularities and patterns from data through algorithms and statistical models. These models can automatically improve and optimize their performance by learning from large amounts of data without explicit programming. Common machine learning models include linear regression models, logistic regression models, decision tree models, random forest models, support vector machine models, and neural network models.

[0058] Optimization Algorithm

[0059] An optimization algorithm refers to an algorithm used to find the optimal solution or approximate optimal solution to a specific problem. The "optimal solution" here usually refers to a solution that can maximize or minimize a certain objective function under given conditions or constraints. Optimization problems exist in almost all fields of science and technology, including but not limited to engineering design, economics, physics, biology, computer science, etc. The objective function is the core of the optimization problem, which is one or more objective functions that describe the target to be optimized. For example, in the minimum cost production problem, the objective function may be the total cost; in the maximum profit sales problem, the objective function may be the total profit. Constraints are often accompanied by certain restrictions or constraints in optimization problems, which define the space of feasible solutions. For example, resources are limited, the number of products cannot be negative, etc. A feasible solution is a solution that satisfies all constraints. The optimal solution is the solution that makes the objective function reach the maximum or minimum value among all feasible solutions. In this specification, the objective function is the maximum sum of the updated predicted sales of all stores 10. The constraints include that the sum of the delivery volume of all stores 10 is equal to the volume to be delivered, and the delivery volume is a positive integer. Example 1

[0060] This manual first provides a warehouse time-limited cargo joint scheduling method. Figure 4 , including the steps of:

[0061] Step S101) Read the on-shelf data of the time-limited products of the store 10 distributed by the warehouse 11, and the on-shelf data includes price, production date and quantity. In this embodiment, the price adjustment is not considered. That is, this embodiment is applied to the joint scheduling scenario of time-limited products during price stability. Exemplarily, the on-shelf data of toast bread of store A includes a price of 5 yuan per package, a production date of the same day, a quantity of 20 packages, a production date of the previous day, a production date of 15 packages, a production date of the previous two days, a production date of 13 packages, a production date of the previous three days, a production date of 10 packages, a production date of the previous four days, a production date of 8 packages, a production date of the previous five days, a production date of 6 packages, a production date of the previous six days, a production date of 5 packages, a production date of the previous seven days, a production date of 2 packages, and a production date of the previous eight days. Assume that the shelf life of this toast bread is 7 days, that is, the time limit is 7 days. The 2 packages of toast bread that exceed the limit before the business on the same day will be removed from the shelves.

[0062] Step S102) According to the on-shelf data, the new arrival ratio, the near-limit ratio and the over-limit ratio of the time-limited products in each store are obtained.

[0063] For example, fresh toast bread is set to be less than 3 days from the date of production, and the toast bread with a limit date is set to be no more than 2 days from the expiration date. It can be calculated that the current new admission ratio of store A is (20+15+13) / (20+15+13+10+8+6+5+2+1)=60%, the limit rate is (6+5+2) / (20+15+13+10+8+6+5+2+1)=16.25%, and the over-limit ratio is 2 / (20+15+13+10+8+6+5+2+1)=2.5%.

[0064] Alternatively, the fresh ratio, the threshold ratio and the over-limit ratio can be calculated by using the technology disclosed in the art. For example, the freshness and threshold ranges can be manually set and then the calculation can be performed.

[0065] Step S103) Calculate and obtain a time limit quality score based on the new entry ratio, the threshold ratio and the over-limit ratio.

[0066] Exemplarily, the method for calculating the time limit quality score based on the new-entry ratio, the critical ratio and the over-limit ratio includes: setting the initial value of the time limit quality score to the product of the new-entry ratio and a preset constant; when the critical ratio is higher than the preset critical reference threshold, subtracting the product of a preset coefficient and the critical ratio from the time limit quality score; when the over-limit ratio is higher than the preset over-limit reference threshold, subtracting the product of another preset coefficient and the over-limit ratio from the time limit quality score.

[0067] When the new entry ratio is 60%, the critical ratio is 16.25%, the over-limit ratio is 2.5%, the critical reference threshold is 10%, the over-limit reference threshold is 3%, the preset constant is 100, and the preset coefficient is 50. The initial value of the time limit quality score is 60, and then 16.25%×50=8.125 needs to be subtracted, that is, the final time limit quality score is 51.875.

[0068] Step S104) Establish a sales forecast model for the store 10, the sales forecast model records the time limit quality score and the relationship between the price and the predicted sales. Since this embodiment is applicable to the application scenario of stable price, the sales forecast model actually records the relationship between the time limit quality score and the predicted sales. Sufficient sample data can be obtained through historical data, and the sales forecast model can be obtained by training the machine learning model using the sample data.

[0069] For details, please refer to the attached Figure 5 , the method of establishing the sales forecast model of store 10 includes:

[0070] Step S201) Obtain the store's historical sales data, historical shelf data, and historical prices. The store's historical sales data can be obtained from one or more of the sales system, inventory management system, and price management system. Preferably, it is pulled from the sales system, which generally records the sales date, time, quantity, unit price, etc. of each time-limited product.

[0071] Step S202) Calculate the daily time limit quality score based on the historical on-shelf data.

[0072] Step S203) Associate the daily time limit quality score and historical price with the corresponding sales quantity to obtain sample data. Link the time limit quality score, price and actual sales volume to form a data set that can be used to train the machine learning model. Collect the time limit quality score, price and actual sales volume of the day, and organize them into a table form, where each row represents one day's data, and the columns include date, time limit quality score, price and sales volume. This table constitutes the input data of the subsequent machine learning model and is read in by the machine learning model. The machine learning model can select a regression model, such as linear regression, decision tree regression, random forest regression, etc. This type of model is suitable for processing numerical outputs. Integrated learning models such as XGBoost, LightGBM, etc. can also be used to improve the accuracy and robustness of the model.

[0073] Step S204) Establish and use the sample data to train the machine learning model, and obtain the sales prediction model according to the trained machine learning model. After the sales prediction model is obtained by training the sample data, the time-limit quality score and price can be input into the sales prediction model to obtain the predicted sales of store 10. The sales prediction model does not include the flow of people as input because this embodiment is suitable for application scenarios where the flow of people is stable or the fluctuation of the flow of people has little impact on sales. For example, it is applied to the time-limited sales stalls in large-scale ultrasound. Since large supermarkets have sufficient flow of people, there is no need to consider the fluctuation of the flow of people. Or it is applied to the time-limited stores in the community business district. Since the community business district is mainly a place for residents in the community to consume, and the living habits of residents are relatively fixed, the change of the flow of people is not a key factor. Another exemplary example is an online store that sells by online push. The online store has a customer base and sells by pushing information related to time-limited products within the customer base.

[0074] Step S105) Generate the delivery volume of each store, and calculate the update time limit quality score of each store based on the on-shelf data and the delivery volume. As an example, the delivery volume of each store can be randomly generated. It is easy to know that the sum of the delivery volumes of all stores 10 is equal to the amount to be delivered. The time-limited products for delivery are generally produced on the same day, of course, they may also be produced on the previous day or a few days ago. According to the actual situation, recalculate the update time limit quality score of each store.

[0075] On the other hand, the methods for generating the delivery volume for each store include:

[0076] Generate a weight coefficient for each store based on the new entrant ratio of each store;

[0077] The delivery quantity for each store is generated according to the weight coefficient and the total quantity to be delivered of the time-limited products.

[0078] The weight coefficient of the store 10 with a higher new entry ratio is lower. A high new entry ratio means that the time-limited products with a small interval between dates in the store 10 are relatively sufficient, and the demand for replenishing more newly produced time-limited products is not high, so the weight setting is relatively lower. The method of generating the delivery volume of each store provided in this embodiment can make the delivery volume generated for the first time, that is, the final delivery volume, relatively closer. This provides a guarantee for the execution efficiency of the optimization algorithm and helps prevent the optimization algorithm from falling into a local optimal solution.

[0079] Step S106) Obtain updated predicted sales according to the update time limit quality score, price and the sales prediction model. After obtaining the update time limit quality score of each store, the updated predicted sales of each store can be obtained according to the update time limit quality score and the sales prediction model.

[0080] Step S107) With the goal of maximizing the updated predicted sales volume, an optimization algorithm is used to obtain the final delivery volume for each store. With the goal of maximizing the updated predicted sales volume, it is meant that the goal is to maximize the sum of the updated predicted sales volume of all stores 10. The final delivery volume for each store can be obtained by the optimization algorithm. The delivery volume that ultimately maximizes the total predicted sales volume is obtained, which helps to ultimately increase the sales volume of time-limited products. Due to the particularity of time-limited products, once the time-limited products have been produced, they must be put on the shelves for sale no matter what. Therefore, this embodiment does not make any adjustments or optimizations to the delivery volume. The amount to be delivered is related to the production volume. When the production is all supplied to one warehouse 11, the amount to be delivered is the production volume. The optimization adjustment of the production volume is not within the scope of the technical solution of this embodiment, and it can be determined using the technology that has been disclosed in the field.

[0081] The new technical effects that can be achieved by this embodiment include: by calculating the new entry ratio, the limit ratio and the over-limit ratio of the store 10, and establishing a sales forecast model, decision support is provided for determining the delivery volume of time-limited products, which can help ultimately increase the sales of time-limited products, thereby helping to reduce over-limit situations. With the help of the sales forecast model, the sales of time-limited products can be predicted, which helps to improve the scientific nature of delivery volume decisions and is better than manually determining the delivery volume based on experience. When generating the delivery volume of the store 10, the weight is set according to the new entry ratio, and the initial store 10 delivery volume is generated according to the weight and the amount to be delivered, which helps to improve the execution efficiency of the optimization algorithm and helps to avoid falling into a local optimal solution. Example 2

[0082] Compared with Example 1, this embodiment improves the method for determining the new-entry ratio, the critical ratio, and the time limit quality score, and the rest is the same as Example 1. Compared with Example 1, this embodiment can avoid the lack of data support and basis for determining the new-entry ratio, the critical ratio, and the time limit quality score, so that the new-entry ratio, the critical ratio, and the time limit quality score can be set relatively more reasonably.

[0083] For details, please refer to the attached Figure 6 , based on the on-shelf data, the method for obtaining the new entry ratio of the time-limited products in each store includes:

[0084] Step S301) Obtain the store's historical sales data and obtain the interval between the transaction date and the production date of each time-limited product sold.

[0085] Step S302) Count the sales quantity corresponding to each interval date to obtain the sales quantity ratio corresponding to the interval date.

[0086] Step S303) gradually increase the interval date and accumulate the corresponding sales quantity percentage until the accumulated sales quantity percentage reaches a preset first threshold, and the interval date at this time is used as the first main sales date.

[0087] Step S304) Continue to gradually increase the interval date and accumulate the corresponding sales quantity percentage until the accumulated sales quantity percentage reaches a preset second threshold, and the interval date at this time is used as the second main sales date.

[0088] Step S305) Obtain the interval date between the time-limited products on the shelf and their production date according to the on-shelf data.

[0089] Step S306) Calculate the weighted sum of the quantity of goods with an interval date less than a second threshold, record it as the fresh quantity, and use the ratio of the fresh quantity to the total quantity of time-limited products on the shelf as the new-in ratio; wherein the weight of the interval date less than the first main sales date is 1, and the weight of the quantity of goods with an interval date greater than or equal to the first threshold and less than the second threshold is the sales quantity ratio.

[0090] Please refer to Table 1, which shows the sales of toast bread for Store A last week and the historical sales data obtained. A total of 1,000 packages of toast bread were sold last week. Of the 1,000 packages sold, 300 packages were sold on the day of production. 160 packages were sold the day after production, and so on. And calculate the percentage of toast bread sold on alternate dates.

[0091] Table 1 Last week's historical sales data

[0092]

[0093] For example, the on-shelf data of toast bread in Store A includes the price of 5 yuan per pack, the quantity of 20 packs on the day of production, the quantity of 15 packs on the day before production, the quantity of 13 packs on the two days before production, the quantity of 10 packs on the three days before production, the quantity of 8 packs on the four days before production, the quantity of 6 packs on the five days before production, the quantity of 5 packs on the six days before production, the quantity of 2 packs on the seven days before production, the quantity of 2 packs on the eight days before production, the quantity of 1 pack on the nine days before production, and the quantity of 1 pack on the tenth day before production. Assume that the shelf life of this type of toast bread is 9 days, that is, the shelf life is 9 days, that is, the toast on the 10th day is an over-limit product. Configure the first threshold to 50% and the second threshold to 90%. The process of calculating the new entry ratio is as follows:

[0094] First, calculate the first major sales date and the second major sales date. Accumulate the sales volume percentage of the interval dates:

[0095] Day 0: 30%

[0096] 1 day: 30% + 16% = 46%

[0097] 2 days: 46% + 15% = 61%

[0098] 3 days: 61% + 10% = 71%

[0099] 4 days: 71% + 8% = 79%

[0100] 5 days: 79% + 6% = 85%

[0101] 6 days: 85% + 5% = 90%

[0102] Thus, the main sales date can be determined. When the cumulative sales volume ratio reaches or exceeds 50% for the first time, the corresponding interval date is 2 days, that is, the first main sales date is 2 days. When the cumulative sales volume ratio reaches or exceeds 90% for the first time, the corresponding interval date is 6 days, that is, the second main sales date is 6 days.

[0103] Secondly, calculate the fresh quantity:

[0104] The number of goods with an interval date of less than 2 days (whose weight is 1) includes: 20 (0 days) + 15 (1 day) = 35 packages. The number of goods with an interval date of greater than or equal to 2 days and less than 6 days (the weight is the corresponding sales volume ratio) includes:

[0105] The interval date is 2 days: 13 packs × 15% = 1.95 packs,

[0106] The interval date is 3 days: 10 packs × 10% = 1 pack,

[0107] The interval date is 4 days: 8 packs × 8% = 0.64 packs,

[0108] The interval date is 5 days: 6 packs × 6% = 0.36 packs,

[0109] Obtained, total fresh quantity: 35 + 1.95 + 1 + 0.64 + 0.36 = 38.95 packs.

[0110] The total number of time-limited products on the shelves is 83 packs. Therefore, the new entry ratio is (38.95 / 83)×100%=46.93%. That is, the new entry ratio of Store A is 46.93%.

[0111] On the other hand, according to the on-shelf data, a method for obtaining the near-limit ratio and over-limit ratio of time-limited products in each store includes:

[0112] Calculate the sum of the quantity of goods whose interval date is greater than or equal to the second threshold value, record it as the critical quantity, and use the ratio of the critical quantity to the total quantity of time-limited products on the shelf as the critical ratio;

[0113] The number of time-limited products that exceed the time limit on that day is counted and recorded as the over-limit quantity, and the ratio of the over-limit quantity to the total number of time-limited products on the shelf is referred to as the over-limit ratio.

[0114] The number of goods with an interval date greater than or equal to 6 days is: 5 (6 days) + 2 (7 days) + 2 (8 days) + 1 (9 days) = 10 packages. The threshold ratio is (10 / 83) × 100% = 12.05%.

[0115] There is 1 pack of toast that exceeds the limit, so the over-limit ratio is (1 / 83)×100%=1.21%.

[0116] That is, the new entry ratio is 46.93%, the threshold ratio is 12.05%, and the over-limit ratio is 1.21%. The threshold reference threshold is configured as 10%, the over-limit reference threshold is configured as 3%, the preset constant is 100, and the preset coefficient is 50. The initial value of the time limit quality score is 46.93, and then 12.05%×50=6.025 needs to be subtracted, that is, the final time limit quality score is 40.905.

[0117] Compared with Example 1, this embodiment provides data support for the method of determining the new entry ratio and the critical ratio, making the calculation of the time-limit quality score more reasonable, helping the store 10 to maintain a better time-limit product structure, and combined with the sales forecasting model, helping to increase the sales of time-limit products.

[0118] On the other hand, this specification provides a warehouse time-limited cargo joint dispatching system, please refer to the attached Figure 7 ,include:

[0119] The reading module 100 reads the on-shelf data of the time-limited products of the store 10 delivered by the warehouse 11, wherein the on-shelf data includes price, production date and quantity;

[0120] The calculation module 200 obtains the new arrival ratio, the near-limit ratio and the over-limit ratio of the time-limited products in each store according to the on-shelf data;

[0121] A scoring module 300, which calculates a time limit quality score according to the new entry ratio, the critical ratio and the over-limit ratio;

[0122] A prediction module 400 is used to establish a sales prediction model for the store 10, wherein the sales prediction model records the relationship between the time-limit quality score and the price and the predicted sales;

[0123] Initial module 500, generating the delivery volume of each store, and calculating the update time limit quality score of each store based on the on-shelf data and the delivery volume;

[0124] An updating module 600 obtains updated predicted sales according to the update time limit quality score, price and the sales prediction model;

[0125] The optimization module 700 uses an optimization algorithm to obtain the final delivery volume for each store with the goal of maximizing the updated predicted sales volume.

[0126] See also Figure 8 A schematic diagram of the structure of an electronic device provided in an embodiment of this specification is shown.

[0127] like Figure 8 As shown, the electronic device 1100 may include: at least one processor 1101, at least one network interface 1104, a user interface 1103, a memory 1105 and at least one communication bus 1102. Among them, the communication bus 1102 can be used to realize the connection and communication of the above-mentioned components. Among them, the user interface 1103 may include a button, and the optional user interface may also include a standard wired interface and a wireless interface. Among them, the network interface 1104 may include but is not limited to a Bluetooth module, an NFC module, a Wi-Fi module, etc. Among them, the processor 1101 may include one or more processing cores. The processor 1101 uses various interfaces and lines to connect various parts in the entire electronic device 1100, and executes various functions and processes data of the routing device 1100 by running or executing instructions, programs, code sets or instruction sets stored in the memory 1105, and calling data stored in the memory 1105. Optionally, the processor 1101 can be implemented in at least one hardware form of DSP, FPGA, and PLA. The processor 1101 may integrate one or a combination of CPU, GPU and modem, etc. Among them, the CPU mainly processes the operating system, user interface and application programs, etc.; the GPU is responsible for rendering and drawing the content to be displayed on the display screen; the modem is used to process wireless communication.

[0128] It is understandable that the above-mentioned modem may not be integrated into the processor 1101, but may be implemented by a separate chip.

[0129] Among them, the memory 1105 may include RAM or ROM. Optionally, the memory 1105 includes a non-transitory computer-readable medium. The memory 1105 can be used to store instructions, programs, codes, code sets or instruction sets. The memory 1105 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playback function, an image playback function, etc.), instructions for implementing the above-mentioned various method embodiments, etc.; the data storage area may store data involved in the above-mentioned various method embodiments, etc. The memory 1105 may also be at least one storage device located away from the aforementioned processor 1101. The memory 1105 as a computer storage medium may include an operating system, a network communication module, a user interface module and an application. The processor 1101 may be used to call the application stored in the memory 1105 and execute the methods in the above-mentioned multiple embodiments.

[0130] The embodiments of this specification also provide a computer-readable storage medium, which stores instructions, and when the instructions are executed on a computer or a processor, the computer or the processor executes the multiple steps in the above embodiments. If the components of the above electronic device are implemented in the form of software functional units and sold or used as independent products, they can be stored in the computer-readable storage medium.

[0131] The embodiments of this specification also provide a computer program product, including a computer program, which implements multiple steps in the above embodiments when executed by a processor.

[0132] In the absence of conflict, the technical features in this embodiment and implementation scheme can be combined arbitrarily.

[0133] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented by software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes a plurality of computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of this specification is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium or transmitted through the computer-readable storage medium. The computer instructions may be transmitted from a website site, a computer, a server or a data center to another website site, a computer, a server or a data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium may be any available medium that a computer can access or a data storage device such as a server or a data center that includes multiple available media integrated. The available medium may be a magnetic medium (eg, a floppy disk, a hard disk, a magnetic tape), an optical medium (eg, a digital versatile disc (DVD)), or a semiconductor medium (eg, a solid state drive (SSD)).

[0134] When implemented by hardware or firmware, the aforementioned method flow is programmed into the hardware circuit to obtain the corresponding hardware circuit structure and realize the corresponding function. For example, a programmable logic device (PLD) (such as a field programmable gate array (FPGA)) is such an integrated circuit, and its logic function is determined by the user programming the device. The designer programs by himself to "integrate" a digital system on a PLD, without asking a chip manufacturer to design and make a dedicated integrated circuit chip. Moreover, nowadays, instead of manually making integrated circuit chips, this programming is mostly implemented by "logic compiler" software, which is similar to the software compiler used when writing program development, and the original code before compilation must also be written in a specific programming language, which is called hardware description language (HDL), and HDL is not just one, but many. Those skilled in the art should also be aware that it is only necessary to program the method flow slightly in the above-mentioned hardware description languages ​​and program it into the integrated circuit to easily obtain the hardware circuit that implements the logic method flow.

[0135] The embodiments described above are merely preferred embodiments of this specification and are not intended to limit the scope of this specification. Without departing from the design spirit of this specification, various modifications and improvements made to the technical solutions of this specification by ordinary technicians in this field should fall within the scope of protection determined by the claims of this specification.

Claims

1. A warehouse time-limited goods joint scheduling method, characterized in that: Includes steps: Read the on-shelf data of the time-limited products of the stores delivered by the warehouse, the on-shelf data including price, production date and quantity; According to the on-shelf data, the new arrival ratio, near-expiry ratio and expired ratio of time-limited products in each store are obtained; According to the new admission ratio, near-expiry ratio and overdue ratio, a time limit quality score is calculated; Establishing a sales forecasting model for the store, the sales forecasting model records the relationship between the time-limit quality score and price and the predicted sales; Generate the delivery volume of each store, and calculate the update time limit quality score of each store based on the on-shelf data and the delivery volume; Obtaining updated predicted sales volume according to the update time limit quality score, price and the sales volume prediction model; With the goal of maximizing the updated predicted sales volume, an optimization algorithm is used to obtain the final delivery volume for each store; According to the on-shelf data, the method for obtaining the new entry ratio of the time-limited product in each store includes: Obtain the store's historical sales data and obtain the interval between the transaction date and the production date of each time-limited product sold; Count the sales quantity corresponding to each interval date and obtain the sales quantity proportion corresponding to the interval date; Gradually increase the interval date and accumulate the corresponding sales quantity ratio until the accumulated sales quantity ratio reaches a preset first threshold, and the interval date at this time is used as the first main sales date; Continue to gradually increase the interval date and accumulate the corresponding sales quantity ratio until the accumulated sales quantity ratio reaches the preset second threshold, and the interval date at this time is used as the second main sales date; Obtain the interval between the time-limited products on the shelves and their production dates according to the on-shelf data; Calculate the weighted sum of the quantity of goods whose interval date is less than the second threshold, record it as the fresh quantity, and use the ratio of the fresh quantity to the total quantity of time-limited products on the shelf as the new entry ratio; wherein, the weight of the quantity of goods whose interval date is less than the first main sales date is 1, and the weight of the quantity of goods whose interval date is greater than or equal to the first threshold and less than the second threshold is the sales quantity ratio; According to the on-shelf data, the method for obtaining the near-expiry ratio and the overdue ratio of the time-limited products in each store includes: Calculate the sum of the quantity of goods whose interval date is greater than or equal to the second threshold value, record it as the near-expiry quantity, and use the ratio of the near-expiry quantity to the total quantity of time-limited products on the shelf as the near-expiry ratio; The number of time-limited products that have exceeded their shelf life on that day is counted and recorded as the expired number, and the ratio of the expired number to the total number of time-limited products on the shelf is referred to as the expired ratio.

2. A warehouse time-limited goods joint dispatching method according to claim 1, characterized in that: According to the new entry ratio, near-expiry ratio and overdue ratio, the method for calculating the time limit quality score includes: Setting the initial value of the time limit quality score to the product of the new input ratio and a preset constant; When the near-term ratio is higher than the preset near-term reference threshold, the time limit quality score is subtracted from the product of the preset coefficient and the near-term ratio; When the expiration ratio is higher than a preset expiration reference threshold, the time limit quality score is reduced by a product of another preset coefficient and the expiration ratio.

3. A warehouse time-limited goods joint dispatching method according to claim 1, characterized in that: Methods for establishing a store sales forecasting model include: Obtain historical store sales data, historical shelf data and historical prices; Calculate the daily time-limit quality score based on the historical on-shelf data; Associating the daily time-limit quality score and historical price with the corresponding sales quantity to obtain sample data; Establish and use the sample data to train a machine learning model, and obtain the sales forecasting model based on the trained machine learning model.

4. A warehouse time-limited cargo joint dispatching method according to any one of claims 1 to 3, characterized in that: Methods for generating delivery volumes for each store include: Generate a weight coefficient for each store based on the new entrant ratio of each store; The delivery quantity for each store is generated according to the weight coefficient and the total quantity to be delivered of the time-limited products.

5. A warehouse time-limited cargo joint dispatching system, characterized in that: include: A reading module is used to read the on-shelf data of the time-limited products of the stores delivered by the warehouse, wherein the on-shelf data includes price, production date and quantity; A calculation module, based on the on-shelf data, obtains the new arrival ratio, near-expiry ratio and expired ratio of the time-limited products in each store; A scoring module, which calculates a time limit quality score based on the new admission ratio, the near-expiry ratio, and the overdue ratio; A prediction module, which establishes a sales prediction model for a store, wherein the sales prediction model records the relationship between the time-limit quality score and the price and the predicted sales; The initial module generates the delivery volume of each store, and calculates the update time limit quality score of each store based on the on-shelf data and the delivery volume; An update module, which obtains updated predicted sales according to the update time limit quality score, price and the sales prediction model; An optimization module, taking the updated predicted sales volume as the maximum as the goal, uses an optimization algorithm to obtain the final delivery volume for each store; According to the on-shelf data, the method for obtaining the new entry ratio of the time-limited product in each store includes: Obtain the store's historical sales data and obtain the interval between the transaction date and the production date of each time-limited product sold; Count the sales quantity corresponding to each interval date and obtain the sales quantity proportion corresponding to the interval date; Gradually increase the interval date and accumulate the corresponding sales quantity ratio until the accumulated sales quantity ratio reaches a preset first threshold, and the interval date at this time is used as the first main sales date; Continue to gradually increase the interval date and accumulate the corresponding sales quantity ratio until the accumulated sales quantity ratio reaches the preset second threshold, and the interval date at this time is used as the second main sales date; Obtain the interval between the time-limited products on the shelves and their production dates according to the on-shelf data; Calculate the weighted sum of the quantity of goods whose interval date is less than the second threshold, record it as the fresh quantity, and use the ratio of the fresh quantity to the total quantity of time-limited products on the shelf as the new entry ratio; wherein, the weight of the quantity of goods whose interval date is less than the first main sales date is 1, and the weight of the quantity of goods whose interval date is greater than or equal to the first threshold and less than the second threshold is the sales quantity ratio; According to the on-shelf data, the method for obtaining the near-expiry ratio and the overdue ratio of the time-limited products in each store includes: Calculate the sum of the quantity of goods whose interval date is greater than or equal to the second threshold value, record it as the near-expiry quantity, and use the ratio of the near-expiry quantity to the total quantity of time-limited products on the shelf as the near-expiry ratio; The number of time-limited products that have exceeded their shelf life on that day is counted and recorded as the expired number, and the ratio of the expired number to the total number of time-limited products on the shelf is referred to as the expired ratio.

6. Electronic equipment, including processor and memory; The processor is connected to the memory; The memory is used to store executable program code; The processor runs a program corresponding to the executable program code by reading the executable program code stored in the memory, so as to execute the method according to any one of claims 1 to 4.

7. A computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the method according to any one of claims 1 to 4.

8. A computer program product, comprising a computer program, which, when executed by a processor, implements the method according to any one of claims 1 to 4.

Images