Store inventory distribution management method and system, intelligent terminal and storage medium

Abstract

The invention relates to a store inventory distribution management method and system, an intelligent terminal and a storage medium, and relates to the technical field of inventory management, and the method comprises the steps: collecting goods requiring orders of a store; determining a distribution mode of purchased commodities according to the goods requiring order; under the condition that the distribution mode is a daily distribution mode, carrying out statistics on goods requiring orders to obtain a to-be-purchased quantity corresponding to the purchased goods; in response to purchase completion operation of the purchased commodities and the to-be-purchased quantity, distribution algorithms of the purchased commodities are obtained, and the distribution algorithms comprise an equal-proportion distribution algorithm and a one-key distribution algorithm; calculating the distribution number of purchased commodities according to a distribution algorithm; generating a first distribution scheme according to the purchased commodities and the distribution quantity; and under the condition that the distribution mode is the warehouse distribution mode, generating a second distribution scheme according to the goods requiring order and the warehouse storage mode. The method has the effect of improving the distribution management efficiency of the store inventory.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of inventory management, in particular to a store inventory allocation management method and system, an intelligent terminal and a storage medium. BACKGROUND

[0002] In the field of inventory allocation, efficient allocation of multi-store inventory directly affects enterprise operating costs and customer satisfaction.

[0003] The related art adopts a unified procurement and allocation mode, which requires each store to report its own demand to the supplier. The supplier then plans the transportation route, arranges the vehicle, and dispatches the distribution according to the demand of each store.

[0004] In view of the related art described above, the goods in the fresh food industry have a high loss rate, which leads to errors in inventory allocation and reduces the efficiency of allocation management. SUMMARY

[0005] In order to improve the allocation management efficiency of store inventory, the present application provides a store inventory allocation management method, system, intelligent terminal and storage medium.

[0006] In a first aspect, the present application provides a store inventory allocation management method, which adopts the following technical solution: A store inventory allocation management method, comprising: collecting a purchase order of a store; determining an allocation mode of a purchase commodity according to the purchase order; in the case of the allocation mode being a daily allocation mode, counting the purchase order to obtain a to-be-purchased quantity corresponding to the purchase commodity; in response to a purchase completion operation of the purchase commodity and the to-be-purchased quantity, obtaining an allocation algorithm of the purchase commodity, the allocation algorithm comprising an equal proportion allocation algorithm and a one-key allocation algorithm; calculating a delivery quantity of the purchase commodity according to the allocation algorithm; generating a first delivery plan according to the purchase commodity and the delivery quantity; in the case of the allocation mode being a warehouse allocation mode, generating a second delivery plan according to the purchase order and a warehouse storage mode.

[0007] By adopting the above technical solution, in the fresh food mode, the to-be-purchased quantity is counted based on the purchase order and the allocation algorithm is called to generate a delivery plan, ensuring accurate supply of high-frequency replenishment commodities; in the retail mode, a plan is directly generated in combination with the warehouse storage state, reducing calculation redundancy. This design significantly improves the adaptability of multi-mode scenarios, reduces the cost of manual intervention, and at the same time automatically generates a delivery plan through an algorithm, avoiding the risk of over-allocation or shortage, and overall improving the response efficiency of the supply chain.

[0008] Optionally, a difference between the to-be-purchased quantity and the already-allocated quantity is calculated to obtain a distribution quantity difference; A difference between the batch allocatable quantity and the batch already-allocated quantity is calculated to obtain a first distribution quantity difference; A difference between the batch inventory quantity and the batch already-allocated quantity is calculated to obtain a second distribution quantity difference; A quotient of the purchase quantity of the target store and the distribution quantity difference is calculated, and a product of the quotient and the first distribution quantity difference is calculated to obtain the batch distribution quantity of the target store, or a quotient of the purchase quantity of the target store and the distribution quantity difference is calculated, and a product of the quotient and the second distribution quantity difference is calculated to obtain the batch distribution quantity of the target store.

[0009] By adopting the above technical solution, the batch inventory is dynamically allocated according to the store purchase demand proportion through the linkage of multi-dimensional parameters such as the distribution quantity difference and the batch allocatable / stock difference. It is especially suitable for the batch arrival scene of popular goods, ensures that each store obtains a reasonable quota according to the actual demand, avoids the problem of large store monopoly of inventory or small store no inventory allocation, and significantly improves the fairness of the supply chain and the store satisfaction.

[0010] Optionally, a difference between the to-be-purchased quantity and the already-allocated quantity is calculated to obtain a distribution quantity difference; If the remaining inventory is greater than or equal to the distribution quantity difference, a sum of the distribution quantity difference and the batch already-allocated quantity is calculated to obtain the batch distribution quantity; If the remaining inventory is less than the distribution quantity difference, a sum of the remaining inventory and the batch already-allocated quantity is calculated to obtain the batch distribution quantity.

[0011] By adopting the above technical solution, the full allocation or maximum inventory allocation strategy is automatically selected through the direct comparison of the inventory and the distribution quantity difference. This design greatly simplifies the operation process, realizes second-level decision-making when the inventory is tight or there is a sudden replenishment demand, avoids the delay of manual calculation, and at the same time ensures the maximization of inventory resource utilization, especially suitable for time-sensitive goods such as fresh food and promotional products.

[0012] Optionally, according to the type of the purchase commodity, store information of the store is obtained; The store information is normalized to obtain a normalized score; The normalized score is weighted to obtain a priority score of the store; The priority score is sorted in descending order to obtain a score ranking; According to the score ranking, the distribution scheme of the purchase commodity is adjusted.

[0013] By adopting the technical scheme, the scientific priority evaluation system is constructed through the normalization processing, weighted scoring and sorting of the store information. The high-value store can obtain the shortage commodity quota preferentially, and the overall revenue potential is improved. The mechanism quantifies the business strategy into the distribution decision, and reduces the probability of resource mismatch.

[0014] Optionally, the geographic position of the store is acquired. The stores are clustered according to the geographic position, and a store cluster is obtained. The area where the store cluster is located is framed, and a framed area is obtained. The distance from the distribution point to the framed area is calculated, and a distribution distance is obtained. The distribution scheme of the store corresponding to the store cluster is adjusted according to the distribution distance.

[0015] By adopting the technical scheme, the store cluster is generated through the geographic position clustering, and the distribution scheme is dynamically adjusted in combination with the distribution distance from the distribution point to the cluster area. The cross-regional scattered distribution frequency is significantly reduced, the unit logistics cost is reduced, and the whole vehicle loading rate is improved. The design is especially suitable for regional warehouse networks, and the scale benefit is realized.

[0016] Optionally, the historical purchase records of the store are collected. The commodity purchase portrait of the store is established according to the historical purchase records. The similarity between the commodity purchase portrait and the order is calculated. If the similarity is less than a preset similarity threshold, the accuracy of the commodity purchase portrait and the order is judged, and the one with greater accuracy is taken as a correction parameter. If the correction parameter is the order, the commodity purchase portrait is updated using the correction parameter. If the correction parameter is the commodity purchase portrait, the commodity purchase portrait is maintained. If the similarity is greater than the preset similarity threshold, the distribution scheme is generated using the order.

[0017] By adopting the technical scheme, the similarity between the historical purchase portrait and the current order is analyzed, the data source is intelligently selected, the distribution scheme is ensured to respond to sudden demand changes, and abnormal orders are avoided to interfere with long-term rules. The design gives the system dynamic learning ability, and the system can flexibly adapt to market fluctuations while ensuring stability, and reduces the risk of coexistence of unsalable and short supply.

[0018] Optionally, the commodity category identifier and the purchase timestamp of the historical purchase record are extracted. The dynamic decay weight is assigned to the purchase records of different time periods based on the time difference between the current time and the purchase timestamp, wherein the greater the time difference, the lower the weight. According to the dynamic attenuation weight and the commodity category identifier, a historical purchase quantity of the same commodity is calculated by weighting to generate a time-sensitive commodity purchase portrait; The time-sensitive commodity purchase portrait is substituted for the commodity purchase portrait.

[0019] By adopting the above technical solution, a time attenuation weight mechanism is introduced for historical purchase records, which significantly improves the timeliness and decision accuracy of the commodity purchase portrait, can generate a more accurate commodity purchase portrait, and reduces the distortion probability of the commodity purchase portrait.

[0020] In a second aspect, the application provides a store inventory allocation management system, which adopts the following technical solution: A store inventory allocation management system comprises: An acquisition module is configured to acquire a requisition order, a purchase completion operation and a warehouse storage mode; A memory is configured to store a program of the store inventory allocation management method; A processor, the program in the memory can be loaded and executed by the processor and implement the store inventory allocation management method.

[0021] By adopting the above technical solution, in the fresh mode, the to-be-purchased quantity is counted based on the requisition order and the allocation algorithm is called to generate a delivery plan, ensuring accurate supply of high-frequency replenishment commodities; in the retail mode, the plan is directly generated in combination with the warehouse storage state, reducing calculation redundancy. The design significantly improves the adaptability of multi-mode scenarios, reduces the cost of manual intervention, and at the same time, automatically generates a delivery plan through the algorithm, avoiding over-delivery or out-of-stock risks, and overall improving the response efficiency of the supply chain.

[0022] In a third aspect, the application provides an intelligent terminal, which adopts the following technical solution: An intelligent terminal comprises a memory and a processor, and the memory stores a computer program capable of being loaded and executed by the processor to implement the store inventory allocation management method of any one of the above.

[0023] In a fourth aspect, the application provides a computer storage medium capable of storing a corresponding program, having the characteristics of facilitating the improvement of the allocation management efficiency of the store inventory, and adopting the following technical solution: A computer readable storage medium stores a computer program capable of being loaded and executed by a processor to implement any one of the above store inventory allocation management methods.

[0024] In summary, the application has at least one of the following beneficial technical effects: 1. In the fresh mode, the to-be-purchased quantity is calculated based on the order statistics, and the distribution algorithm is called to generate the distribution scheme, ensuring accurate supply of high-frequency replenishment goods; in the retail mode, the scheme is directly generated combined with the warehouse storage state, reducing calculation redundancy. This design significantly improves the adaptability of multi-mode scenarios, reduces the cost of manual intervention, and at the same time, automatically generates the distribution scheme through the algorithm to avoid over-distribution or out-of-stock risks, and overall improves the response efficiency of the supply chain; 2. Through the linkage of multi-dimensional parameters such as distribution quantity difference, batch distribution / stock difference, etc., the batch inventory is dynamically allocated according to the store procurement demand ratio. Especially suitable for batch arrival scenarios of popular goods, ensuring that each store obtains a reasonable quota according to actual demand, avoiding the problem of large stores monopolizing inventory or small stores having no inventory to distribute, significantly improving the fairness of the supply chain and store satisfaction; 3. Through direct comparison of inventory and distribution quantity difference, automatically select full allocation or maximum inventory allocation strategy. This design greatly simplifies the operation process, realizes second-level decision-making when inventory is tight or sudden replenishment demand occurs, avoids manual calculation delay, and at the same time ensures maximum utilization of inventory resources, especially suitable for time-sensitive goods such as fresh food and promotional products. BRIEF DESCRIPTION OF DRAWINGS

[0025] Figure 1 is a flowchart of a store inventory allocation management method provided by an embodiment of the present application.

[0026] Figure 2 is a flowchart of an adjustment method one of a distribution scheme provided by an embodiment of the present application.

[0027] Figure 3 is a flowchart of an adjustment method two of a distribution scheme provided by an embodiment of the present application.

[0028] Figure 4 is a flowchart of an adjustment method three of a distribution scheme provided by an embodiment of the present application.

[0029] Figure 5 is a flowchart of an adjustment method four of a distribution scheme provided by an embodiment of the present application.

[0030] Figure 6 is a structural diagram of a store inventory allocation management system provided by an embodiment of the present application. DETAILED DESCRIPTION

[0031] In order to make the purpose, technical scheme and advantages of the present application more clear, the following will combine the drawings provided in the present application with embodiments to make a further detailed description of the present application. It should be understood that the specific embodiments described herein are only used to explain the present application, and are not used to limit the present application. Figure 1 to Figure 6 and embodiments, the present application will be further described in detail. It should be understood that the specific embodiments described herein are only used to explain the present application, and are not used to limit the present application.

[0032] The embodiment of the application discloses a store inventory allocation management method. Referring to Figure 1 The method comprises the following steps: Step S101: collecting a purchase order of a store.

[0033] The purchase order is a request for goods sent by the store to the goods supplier. The purchase order includes, but is not limited to, at least one of the following: purchase order time, product category, product quantity, and product weight.

[0034] The purchase order can be sent by the store to the goods supplier in real time, or can be sent by the store to the goods supplier at a fixed time.

[0035] Step S102: determining an allocation mode of the purchased goods according to the purchase order.

[0036] The allocation mode includes a daily allocation mode and a warehouse allocation mode. The daily allocation mode refers to that the goods supplier distributes goods to the store every day. The daily allocation mode is usually applied to fresh food, cooked food and the like. For example, the goods supplier counts and purchases the product categories and goods required by each store every day, and distributes the corresponding goods to each store according to the product categories and goods.

[0037] The warehouse allocation mode refers to a mode in which the goods are stored, transferred, distributed and the like in the warehouse. The warehouse allocation mode needs to sort and distribute the goods according to the allocation amount. The warehouse allocation mode is usually applied to retail products, snacks and the like.

[0038] Step S103: in the case where the allocation mode is the daily allocation mode, counting the purchase order to obtain a to-be-purchased amount corresponding to the purchased goods.

[0039] The to-be-purchased amount refers to the daily purchase amount of the purchased goods. The to-be-purchased amount corresponds to the purchased goods one by one, and different purchased goods are provided with corresponding to-be-purchased amounts.

[0040] For example, for a target purchased good in the purchased goods, the sub-quantity in each purchase order of the target purchased good is counted. The to-be-purchased amount is obtained by counting the sub-quantity.

[0041] Step S104: in response to a purchase completion operation of the purchased goods and the to-be-purchased amount, obtaining an allocation algorithm of the purchased goods, the allocation algorithm including a proportional allocation algorithm and a one-key allocation algorithm.

[0042] The purchase completion operation indicates that the purchase of the purchased goods is completed. The purchase completion operation includes a product category purchase completion operation and a product quantity purchase completion operation. The product category purchase completion operation indicates that the goods supplier completes the purchase of the product category corresponding to the purchased goods. The product quantity purchase completion operation indicates that the goods supplier completes the purchase of the product quantity corresponding to the purchased goods.

[0043] In some embodiments, the equal proportion allocation algorithm is as follows: calculate the difference between the to-be-purchased quantity and the already-allocated quantity to obtain a delivery quantity difference. Calculate the difference between the batch deliverable quantity and the batch already-allocated quantity to obtain a first delivery quantity difference. Calculate the difference between the batch inventory quantity and the batch already-allocated quantity to obtain a second delivery quantity difference. Calculate the quotient of the target store's to-be-purchased quantity and the delivery quantity difference, and calculate the product of the quotient and the first delivery quantity difference to obtain the batch delivery quantity of the target store, or calculate the quotient of the target store's to-be-purchased quantity and the delivery quantity difference, and calculate the product of the quotient and the second delivery quantity difference to obtain the batch delivery quantity of the target store.

[0044] For example, batch delivery quantity = to-be-purchased quantity / (to-be-purchased quantity - already-allocated quantity) * (batch deliverable quantity - batch already-allocated quantity).

[0045] In some embodiments, the one-key allocation algorithm is as follows: calculate the difference between the to-be-purchased quantity and the already-allocated quantity to obtain a delivery quantity difference. If the remaining inventory is greater than or equal to the delivery quantity difference, calculate the sum of the delivery quantity difference and the batch already-allocated quantity to obtain the batch delivery quantity. If the remaining inventory is less than the delivery quantity difference, calculate the sum of the remaining inventory and the batch already-allocated quantity to obtain the batch delivery quantity.

[0046] For example, when the remaining inventory is greater than the difference between the to-be-purchased quantity and the already-allocated quantity, the batch delivery quantity = to-be-purchased quantity - already-allocated quantity + batch already-allocated quantity. When the remaining inventory is less than the difference between the to-be-purchased quantity and the already-allocated quantity, the batch delivery quantity = remaining inventory + batch already-allocated quantity.

[0047] Step S105: Calculate the delivery quantity of the purchased commodity according to the allocation algorithm.

[0048] The delivery quantity refers to the quantity of the purchased commodity allocated to the store.

[0049] Step S106: Generate a first delivery plan according to the purchased commodity and the delivery quantity.

[0050] The first delivery plan refers to the delivery plan of the store in the daily delivery mode. For example, the first delivery plan is that store 1 needs to deliver 20 pieces of commodity A and 5 pieces of commodity B; store 2 needs to deliver 10 pieces of commodity A and 3 pieces of commodity C.

[0051] Step S107: In the case of the allocation mode being the warehouse delivery mode, generate a second delivery plan according to the order and the warehouse inventory mode.

[0052] In one embodiment, in the case of the allocation mode being the warehouse delivery mode, the process includes commodity purchase and storage, commodity inventory visualization, store ordering, sorting and delivery in the order of execution.

[0053] In an implementation, when the distribution mode is a warehouse distribution mode, the process includes store ordering, aggregating store data into a purchase order, receiving goods at the warehouse, and collecting and distributing goods in the order of execution.

[0054] By adopting the above technical solution, in the fresh mode, the to-be-purchased quantity is counted based on the ordering order, and the distribution algorithm is called to generate a distribution plan, ensuring accurate supply of high-frequency replenishment goods. In the retail mode, the plan is directly generated in combination with the warehouse inventory status, reducing calculation redundancy. This design significantly improves the adaptability of multi-mode scenarios, reduces the cost of manual intervention, and automatically generates a distribution plan through the algorithm to avoid overstocking or out-of-stock risks, thereby improving the overall supply chain response efficiency.

[0055] In the following embodiments, when distributing goods for stores, different degrees of distribution priority can be provided according to the value of different stores to adapt to the needs of the stores. Therefore, the present application discloses a method for adjusting a distribution plan I. Referring to Figure 2 , the method comprises: Step S201: obtaining store information of a store according to a type of a purchased good.

[0056] The store information includes at least one of main products of the store, daily traffic, a difference between the purchased good and the main product, daily net income, and daily sales volume.

[0057] The difference between the purchased good and the main product refers to a difference in the type of the good. For example, if the purchased good is vegetables and the main product is aquatic products, a first number vector corresponding to the vegetables and a second number vector corresponding to the aquatic products are obtained. The difference between the first number vector and the second number vector is taken as the difference between the purchased good and the main product.

[0058] Step S202: normalizing the store information to obtain a normalized score.

[0059] The normalization processing is used to scale different types of store information so that different store information falls into the same specific interval. For example, the normalization processing can use any one of linear normalization, standard deviation normalization, and logarithmic normalization.

[0060] Step S203: weighted calculation of the normalized score to obtain a priority score of the store.

[0061] When the normalized score is weighted calculated, the weight value can be pre-set. For example, the weight value corresponding to the difference between the purchased good and the main product is 60%, the weight value corresponding to the daily traffic is 20%, and the weight value corresponding to the daily net income is 20%.

[0062] Step S204: descending sorting of the priority score to obtain a score ranking.

[0063] The priority score is sorted in descending order, which can quickly determine the stores with higher priority scores, thereby providing limited priority for the stores to provide distribution services.

[0064] Step S205: According to the score ranking, adjust the distribution scheme of the purchased goods.

[0065] Different purchased goods provide different distribution schemes for the same store, because the same store has different selling effects on different goods when selling different goods.

[0066] For example, according to the score ranking, the top n stores are taken to obtain the target store. The distribution scheme corresponding to the target store is determined. The number of purchased goods of the target store in the distribution scheme is increased. Further, for the target store, the increased number of purchased goods can be determined according to the sequence number of the target store in the score ranking, for example, if the target store ranks first in the score ranking, the increased number of purchased goods takes 5% of the daily sales volume of the target store for the purchased goods.

[0067] By adopting the above technical solution, a scientific priority evaluation system is constructed through normalization processing, weighted scoring and sorting of store information. High-value stores can obtain the distribution quota of scarce goods in priority, thereby improving the overall revenue potential. The mechanism quantifies the business strategy into the distribution decision, thereby reducing the probability of resource mismatch.

[0068] In the following embodiments, when distributing stores, the distribution scheme can be appropriately adjusted according to the geographical position of the store to improve the distribution efficiency of the purchased goods. Therefore, the present application discloses a second method for adjusting the distribution scheme. Referring to Figure 3 The method comprises: Step S301: Obtain the geographical position of the store.

[0069] For example, the geographical position is pre-stored in the database, so the geographical position of the store can be directly called from the database. For example, the database stores the correspondence between the store number and the geographical position, and the geographical position can be determined by the correspondence and the store number.

[0070] Step S302: Cluster the stores according to the geographical position to obtain a store cluster.

[0071] The clustering processing is a processing method of grouping the stores close in geographical position together. The clustering processing method includes but is not limited to at least one of DBSCAN algorithm, K-Means algorithm, and hierarchical clustering algorithm.

[0072] Step S303: Frame the area where the store cluster is located to obtain a framed area.

[0073] The bounding box is the minimum circumscribed rectangle of the store cluster.

[0074] Step S304: Calculate the distance from the delivery point to the bounding box to obtain the delivery distance.

[0075] The delivery point refers to the harvesting location or procurement location of the purchased goods.

[0076] Optionally, the shortest path from the delivery point to the bounding box is calculated to obtain the delivery distance.

[0077] Optionally, the geometric center of the bounding box is obtained. The path from the delivery point to the bounding box is calculated to obtain the delivery distance.

[0078] Step S305: Adjust the goods allocation scheme of the store corresponding to the store cluster according to the delivery distance.

[0079] Optionally, when the delivery distance is greater than a preset first delivery distance threshold, the number of purchased goods in the goods allocation scheme of the store corresponding to the store cluster is reduced. When the delivery distance is less than a preset second delivery distance threshold, the number of purchased goods in the goods allocation scheme of the store corresponding to the store cluster is increased.

[0080] By adopting the above technical solution, the store cluster is generated by geographical position clustering, and the goods allocation scheme is dynamically adjusted in combination with the delivery distance from the delivery point to the cluster area. The cross-regional scattered delivery frequency is significantly reduced, the unit logistics cost is reduced, and the whole vehicle loading rate is improved. It is especially suitable for regional warehouse networks to achieve large-scale benefits.

[0081] Embodiments of the present application disclose a third method for adjusting a goods allocation scheme. Referring to Figure 4 The method comprises: Step S401: Collect historical purchase records of stores.

[0082] The historical purchase record refers to the purchase record of the store in the historical period. The historical purchase record is used to store at least one of the purchased goods type, the purchased goods quantity, and the purchase time of the store.

[0083] Step S402: Establish a goods purchase portrait of the store according to the historical purchase record.

[0084] The goods purchase portrait is used to describe the purchase tendency of the store.

[0085] Exemplarily, the commodity purchase features are generated according to historical purchase records, and the commodity purchase features include commodity structure features, purchase behavior features, and purchase price features. The commodity structure features are used to describe the composition of the types of purchased commodities, the purchase behavior features include purchase frequency, purchase cycle, order size, and seasonality index, and the purchase price features are used to describe the price tendency of the commodities purchased by the store. The commodity purchase portrait is formed according to the commodity purchase features.

[0086] Step S403: Calculate the similarity between the commodity purchase portrait and the order.

[0087] Exemplarily, the order is converted into a feature vector. The cosine similarity between the commodity purchase portrait and the feature vector is calculated to obtain the similarity of the present step.

[0088] Step S404: If the similarity is less than a preset similarity threshold, the accuracy of the commodity purchase portrait and the order is judged, and the one with higher accuracy is taken as the correction parameter.

[0089] The similarity threshold is a preset empirical value, and the specific value of the similarity threshold can be adjusted by the technician according to the actual demand.

[0090] If the similarity is less than the preset similarity threshold, it means that there is a large deviation between the commodity purchase portrait and the order, and the accuracy of one of them is higher, so the one with higher accuracy is determined as the correction parameter.

[0091] The accuracy judgment is used to quantify the accuracy of the commodity purchase portrait and the order.

[0092] Optionally, the accuracy judgment includes data integrity judgment and data consistency judgment. Exemplarily, the data integrity judgment includes purchase portrait judgment and order judgment, for example, the purchase portrait judgment includes checking the time period covered by the commodity purchase portrait, and the order judgment includes verifying the integrity of the items of the order.

[0093] Exemplarily, the data consistency judgment includes comparing the consistency of the commodity purchase portrait with a preset database, and checking the consistency of the order with the commodity purchase portrait.

[0094] Step S405: If the correction parameter is the order, the commodity purchase portrait is updated using the correction parameter.

[0095] If the correction parameter is the order, it means that the accuracy of the commodity purchase portrait is lower, and the commodity purchase portrait needs to be updated using the correction parameter.

[0096] Step S406: If the correction parameter is the commodity purchase portrait, the commodity purchase portrait is kept.

[0097] If the modified parameter is the commodity procurement portrait, it indicates that the accuracy of the commodity procurement portrait is high, and the commodity procurement portrait does not need to be modified.

[0098] Step S407: If the similarity is greater than the preset similarity threshold, a delivery plan is generated according to the to-be-ordered order.

[0099] If the similarity is greater than the preset similarity threshold, it indicates that the commodity procurement portrait is close to the to-be-ordered order, and both the commodity procurement portrait and the to-be-ordered order are accurate, and do not need to be modified.

[0100] By using the above technical solutions, the similarity between the historical procurement portrait and the current to-be-ordered order is analyzed, the data source is intelligently selected, and it is ensured that the delivery plan responds to sudden demand changes and avoids abnormal order interference with long-term regularity. The design gives the system dynamic learning ability, which flexibly adapts to market fluctuations while ensuring stability, reduces the risk of coexistence of unsalable and out-of-stock products.

[0101] Embodiments of the present application disclose a fourth method for adjusting a delivery plan. Referring to Figure 5 , the method comprises: Step S501: Extracting the commodity category identifier and the purchase timestamp of the historical purchase record.

[0102] The commodity category identifier is used to uniquely identify the purchased commodity. Optionally, the commodity category identifier is a commodity classification code, for example, the commodity category identifier of fresh food is F001, and the commodity category identifier of daily necessities is D002.

[0103] The purchase timestamp records the accurate time of purchase.

[0104] Illustratively, the database is scanned, and the commodity category identifier and the purchase timestamp field of each record are parsed.

[0105] Step S502: Based on the time difference between the current time and the purchase timestamp, a dynamic decay weight is assigned to the purchase record of different time period, wherein the greater the time difference, the lower the weight.

[0106] Optionally, the calculation formula of the dynamic decay weight is 1 / (1+0.01x time difference). Further, if the time difference is greater than a preset time threshold, the dynamic decay weight is set to a preset weight. For example, when the time difference is greater than 30 days, the corresponding dynamic decay weight is set to 0.05.

[0107] Step S503: According to the dynamic decay weight and the commodity category identifier, the historical purchase quantity of the same type of commodity is weighted and calculated to generate a time-sensitive commodity procurement portrait.

[0108] Optionally, the same type of goods is merged according to the commodity category identification. The same type of goods is subjected to a weighted operation according to a dynamic attenuation weight, to obtain a weighted total purchase quantity. The time-sensitive commodity purchase portrait is generated based on the weighted total purchase quantity.

[0109] Step S504: replacing the commodity purchase portrait with the time-sensitive commodity purchase portrait.

[0110] The time-sensitive commodity purchase portrait is used to replace the commodity purchase portrait, so that the time-sensitive commodity purchase portrait performs subsequent processes.

[0111] By adopting the above technical solutions, the time attenuation weight mechanism is introduced for the historical purchase record, the timeliness and decision accuracy of the commodity purchase portrait are significantly improved, a more accurate commodity purchase portrait can be generated, and the distortion probability of the commodity purchase portrait is reduced.

[0112] Based on the same inventive concept, an embodiment of the present application provides a store inventory allocation management system, comprising: The acquisition module 601 is configured to acquire a goods ordering order, a purchase completion operation, and a warehouse storage mode. The memory 602 is configured to store a program of the store inventory allocation management method. The processor 603 is configured to load and execute the program in the memory, and implement the store inventory allocation management method.

[0113] By adopting the above technical solutions, in the fresh mode, the to-be-purchased quantity is counted based on the goods ordering order, and the allocation algorithm is called to generate a goods allocation scheme, to ensure accurate supply of high-frequency replenishment goods; in the retail mode, the scheme is directly generated in combination with the warehouse storage state, to reduce calculation redundancy. The design significantly improves the adaptability of the multi-mode scene, reduces the cost of manual intervention, automatically generates the goods allocation scheme through the algorithm, avoids the risk of over-allocation or shortage, and overall improves the response efficiency of the supply chain.

[0114] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the division of the above functional modules is taken as an example for illustration, and in actual application, the above functions can be completed by different functional modules according to needs, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. The specific working process of the system, device and unit described above can refer to the corresponding process in the foregoing method embodiments, which will not be described here.

[0115] An embodiment of the present application provides a computer readable storage medium, which stores a computer program capable of being loaded and executed by a processor to perform a store inventory allocation management method.

[0116] The computer storage medium includes, for example, a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and various media capable of storing program codes.

[0117] Based on the same inventive concept, the embodiment of the present application provides a kind of intelligent terminal, including memory and processor, memory is stored with the computer program of store inventory allocation management method capable of being loaded and being executed by processor.

[0118] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the above-mentioned division of each functional module is exemplified, and in actual application, the above-mentioned functions can be completed by different functional modules according to needs, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above.The specific working process of the above-described system, device and unit can refer to the corresponding process in the foregoing method embodiments, which will not be described here.

[0119] The above are preferred embodiments of the present application, and are not intended to limit the protection scope of the present application, any feature disclosed in the specification (including the abstract and drawings) can be replaced by other equivalent or similar purpose alternative features, unless specifically described. That is, unless specifically described, each feature is only an example of a series of equivalent or similar features.

Claims

1. A store inventory allocation management method, characterized in that: The method comprises: Collect orders from stores; Determine a distribution mode for purchased goods based on the purchase order; In the case where the distribution mode is a daily distribution mode, the order quantity is counted to obtain the quantity to be purchased corresponding to the purchased goods; In response to the purchase completion operation of the purchased commodity and the quantity to be purchased, obtaining an allocation algorithm for the purchased commodity, the allocation algorithm including an equal proportion allocation algorithm and a one-key allocation algorithm; Calculating the distribution quantity of the purchased goods according to the allocation algorithm; generating a first distribution plan according to the purchased goods and the distribution quantity; In the case where the distribution mode is the warehouse distribution mode, a second distribution plan is generated according to the purchase order and the warehouse storage mode.

2. The store inventory allocation management method according to claim 1, characterized in that: The equal proportion allocation algorithm includes: Calculate the difference between the quantity to be purchased and the quantity already allocated to obtain the allocated quantity difference; Calculate the difference between the batch available quantity and the batch allocated quantity to obtain the first allocation quantity difference; Calculate the difference between the batch inventory quantity and the allocated quantity of the batch to obtain a second allocation quantity difference; Calculate the quotient of the target store's purchase quantity and the difference in the allocation quantity, and calculate the product of the quotient and the first allocation quantity difference to obtain the batch allocation quantity of the target store, or calculate the quotient of the target store's purchase quantity and the difference in the allocation quantity, and calculate the product of the quotient and the second allocation quantity difference to obtain the batch allocation quantity of the target store.

3. The store inventory allocation management method according to claim 1, characterized in that: The one-key allocation algorithm includes: Calculate the difference between the quantity to be purchased and the quantity already allocated to obtain the allocated quantity difference; If the remaining inventory is greater than or equal to the allocation quantity difference, the sum of the allocation quantity difference and the batch allocated quantity is calculated to obtain the batch allocation quantity; If the remaining inventory is less than the allocation quantity difference, the sum of the remaining inventory and the batch allocated quantity is calculated to obtain the batch allocation quantity.

4. The store inventory allocation management method according to claim 1, characterized in that: The method further comprises: Obtaining store information of the store according to the type of the purchased goods; Normalizing the store information to obtain a normalized score; Weighted calculation of the normalized scores to obtain the priority score of the store; Sorting the priority scores in descending order to obtain a score ranking; According to the score ranking, the distribution plan of the purchased goods is adjusted.

5. The store inventory allocation management method according to claim 4, characterized in that: The method further comprises: Obtaining the geographic location of the store; Clustering the stores according to the geographical locations to obtain store clusters; Select the area where the store cluster is located to obtain the selected area; Calculate the distance from the shipping point to the selected area to obtain the delivery distance; The distribution plan of the stores corresponding to the store cluster is adjusted according to the delivery distance.

6. The store inventory allocation management method according to claim 4, characterized in that: The method further comprises: Collect historical purchase records of the stores; Establishing a merchandise purchasing profile of the store based on the historical purchasing records; Calculating the similarity between the product purchase profile and the purchase order; If the similarity is less than a preset similarity threshold, the accuracy of the product purchase profile and the purchase order is evaluated, and the one with greater accuracy between the product purchase profile and the purchase order is used as the correction parameter; if the correction parameter is the purchase order, the product purchase profile is updated using the correction parameter; if the correction parameter is the product purchase profile, the product purchase profile is maintained; If the similarity is greater than a preset similarity threshold, the distribution plan is generated according to the purchase order.

7. The store inventory allocation management method according to claim 6, characterized in that: The method further comprises: Extracting the commodity category identifier and purchase timestamp of the historical purchase record; Based on the time difference between the current time and the purchase timestamp, dynamically decaying weights are assigned to purchase records in different time periods, wherein the greater the time difference, the lower the weight; Performing weighted calculation on the historical purchase quantity of similar products based on the dynamic attenuation weight and the product category identifier to generate a time-sensitive product purchase profile; The time-sensitive commodity procurement profile is used to replace the commodity procurement profile.

8. A store inventory distribution management system, characterized in that: The system is used to execute the store inventory allocation management method according to any one of claims 1 to 7, and the system includes: The acquisition module is used to obtain the order, purchase completion operation and warehouse inventory mode; A memory for storing a program of the store inventory allocation management method; The program in the memory can be loaded and executed by the processor to implement the store inventory allocation management method.

9. An intelligent terminal, characterized in that: The method comprises a memory and a processor, wherein the memory stores a computer program that can be loaded by the processor and execute the store inventory allocation management method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that The computer program is stored which can be loaded by a processor and execute the store inventory allocation management method according to any one of claims 1 to 7.

Images