Three-dimensional warehouse storage location recommendation decision-making method based on real-time big data prediction

Abstract

The invention discloses a three-dimensional warehouse storage location recommendation decision-making method based on real-time big data prediction, and relates to the technical field of warehouse management, and the three-dimensional warehouse storage location recommendation decision-making method based on real-time big data prediction mainly comprises the steps: obtaining the information of a to-be-stored material according to the stock of a three-dimensional warehouse; according to the information of the to-be-warehoused materials, it is determined that the to-be-warehoused materials exist in a three-dimensional warehouse; according to the storage location information of the same material in the three-dimensional warehouse, searching the storage location adjacent to the storage location of the same material as the warehousing recommendation storage location; if the proper storage location is not found or it is determined that the to-be-stored materials do not exist in the three-dimensional warehouse stock; searching the middle storage location of the empty storage location roadways as a recommended storage location; if the proper storage location cannot be found, searching a storage recommendation storage location by using a warehouse-out prediction method; and if the proper storage location cannot be found, generating a prompt that no proper storage location exists. By implementing the three-dimensional warehouse storage location recommendation decision-making method based on real-time big data prediction provided by the invention, the material warehouse-in and warehouse-out efficiency can be improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of warehouse management, more particularly, to a vertical warehouse storage location recommendation decision method based on real-time big data prediction. BACKGROUND

[0002] With the development and popularization of artificial intelligence technology, various industries have begun to integrate artificial intelligence technology to assist business development. In the warehouse logistics industry, by introducing big data computing, artificial intelligence learning and other architectures, the warehouse in and out and inventory data can be integrated based on massive data prediction to provide more accurate decision items for enterprises, thereby significantly improving the operation efficiency of the warehouse. However, in specific application scenarios, there are still obstacles. The shuttle car vertical warehouse is generally a dense warehouse, that is, there are three or more than three storage locations in the same storage location lane. In such a lane, the in and out operation will inevitably encounter the situation that one or more storage locations next to the storage location have obstructions when the material in and out of the storage location. At this time, it will be necessary to move the storage, and the increase of the moving process will inevitably increase the in and out time. With the increase of the operation amount, a large number of different materials will also be stored in the same lane, which will increase the moving process of the outer storage location when the material in the inner storage location is out, thereby reducing the out efficiency.

[0003] Therefore, how to recommend and decide the in warehouse storage location of the shuttle car vertical warehouse based on big data, and thereby improve the in and out efficiency of the shuttle car, has become a problem to be solved. SUMMARY

[0004] The purpose of the present application is to provide a vertical warehouse storage location recommendation decision method based on real-time big data prediction, which can provide the efficiency of the in and out of the material.

[0005] The present application provides a vertical warehouse storage location recommendation decision method based on real-time big data prediction, comprising the following steps: S1: obtaining the material information to be stored according to the vertical warehouse inventory; S2: determining that the material to be stored exists in the vertical warehouse inventory according to the material information to be stored; finding the adjacent storage location of the same material as the storage location of the same material in the vertical warehouse as the storage recommendation location according to the storage location information of the same material in the vertical warehouse; S3: According to the to-be-warehoused material information, if a warehousing recommended storage location cannot be found or it is determined that the to-be-warehoused material does not exist in the vertical warehouse inventory, a vertical warehouse layer is found according to the layer height and the cargo location weight, and the empty storage locations in the vertical warehouse layer are found in order from low to high, and the middle storage location of the aisle is selected as the warehousing recommended storage location; if the warehousing recommended storage location cannot be found, a suitable warehousing storage location is found by using the out-of-warehouse prediction method, and the warehousing recommended storage location is obtained; if the warehousing recommended storage location cannot be found, a prompt that there is no suitable warehousing storage location is generated.

[0006] The application further provides a computer readable storage medium, which stores a computer program, and the computer program is executed by a processor to implement the steps of the vertical warehouse warehousing storage location recommendation decision method based on real-time big data prediction.

[0007] The application further provides a computer device, which comprises a memory, a processor, and a computer program stored on the memory and executable on the processor, and the processor implements the steps of the vertical warehouse warehousing storage location recommendation decision method based on real-time big data prediction when executing the program.

[0008] The application further provides a computer program product, which comprises a computer program, and the computer program is executed by a processor to implement the steps of the vertical warehouse warehousing storage location recommendation decision method based on real-time big data prediction.

[0009] The vertical warehouse warehousing storage location recommendation decision method based on real-time big data prediction has the following beneficial effects: The application predicts the out-of-warehouse quantity of the material in a future period of time based on the sales quantity big data, takes the prediction value as one of the storage location recommendation conditions that can be referred to when the material is warehoused, preferentially places the to-be-warehoused material on the adjacent storage location of the same material when the to-be-warehoused material exists in the vertical warehouse, places the material on the suitable aisle where all the storage locations are empty if there is no suitable storage location, places the material next to the material with a similar out-of-warehouse prediction value as far as possible according to the out-of-warehouse prediction value if there is no suitable storage location, preferentially places the material on the suitable aisle where all the storage locations are empty when the to-be-warehoused material does not exist in the vertical warehouse, and places the material next to the material with a similar out-of-warehouse prediction value as far as possible according to the out-of-warehouse prediction value if there is no suitable storage location. In summary, the application predicts the out-of-warehouse quantity of the material in a future period of time based on the sales quantity big data, takes the prediction value as one of the storage location recommendation conditions that can be referred to when the material is warehoused, places the to-be-warehoused material next to the material with a similar out-of-warehouse prediction value when there is no available storage location adjacent to the same material and no aisle where all the storage locations are empty, and can ensure that the out-of-warehouse frequencies of the two materials are similar in a future period of time to a certain extent, thereby improving the efficiency of system warehousing and unwarehousing. BRIEF DESCRIPTION OF DRAWINGS

[0010] The application will be further described below in connection with the drawings and embodiments, wherein: Figure 1 is a flow chart of the vertical warehouse storage location recommendation decision method based on real-time big data prediction provided by the application; Figure 2 is a schematic diagram of the steps of the vertical warehouse storage location recommendation decision method based on real-time big data prediction provided by the application: Figure 3 is a schematic diagram of the vertical warehouse storage location recommendation decision method based on real-time big data prediction provided by the application; Figure 4 is a structural block diagram of the computer device provided by the application. DETAILED DESCRIPTION

[0011] In order to have a clearer understanding of the technical features, objectives and effects of the application, the specific embodiments of the application will be described in detail below with reference to the drawings.

[0012] Figure 1 shows a schematic diagram of the vertical warehouse storage location recommendation decision method based on real-time big data prediction of the embodiment. In this embodiment, the vertical warehouse storage location recommendation decision method based on real-time big data prediction includes the following steps: S1: obtaining the to-be-stored material information according to the vertical warehouse inventory; S2: determining that the to-be-stored material exists in the vertical warehouse inventory according to the to-be-stored material information; finding the adjacent storage location of the same material as the storage location of the same material in the vertical warehouse as the storage location recommendation for storage; In an exemplary embodiment, step S2 specifically includes: S21: determining the storage location of the material that already exists in the vertical warehouse according to the to-be-stored material information; taking the adjacent storage location of the storage location of the material that already exists as the storage location recommendation for storage; In an exemplary embodiment, step S21 specifically includes: S211: selecting a suitable storage location in the vertical warehouse according to the to-be-stored material layer height and the material weight; S212: finding the storage location recommendation for storage in the vertical warehouse layer in the order from low to high; S213: in a certain vertical warehouse layer, obtaining the storage location information of all materials that are the same as the to-be-stored material in the layer, and traversing the obtained same material storage locations in the order from near to far from the exit; S214: traversing the two sides of the storage location in the aisle for each same material storage location; S215: if there is a storage location occupied by a material in the two sides of the storage location in the aisle, ending the traversal search for the current storage location; S216: If there is a side storage location among the two side storage locations of the storage location and the aisle, and the side storage location is empty, then the empty storage location adjacent to the storage location and closer to the entrance is selected as the storage recommendation location; S22: If the storage recommendation location is not found in step S21, a storage layer with empty storage locations throughout the entire aisle is found, and empty storage locations are found in the order of the storage layer from low to high, and in each storage layer, the empty storage locations are found in the order of the entrance from near to far, and the middle storage location in the appropriate aisle is selected as the storage recommendation location; S23: If the storage recommendation location is not found in step S22, the out-of-stock prediction method is used to find the appropriate storage location, and the storage recommendation location is obtained; In an exemplary embodiment, step S23 specifically includes: S231: Obtain historical sales big data, including the daily sales quantity of the material in the out-of-stock history; S232: According to the actual sales quantity in the historical sales big data, a sales quantity prediction value formula is constructed using the simple exponential smoothing method; In an exemplary embodiment, the sales quantity prediction value formula is as follows: , wherein, and represent the sales quantity prediction value on the , th day, represents the actual sales quantity on the th day, is a weight constant, and the value range of the constant is ; S233: Obtain a weight constant set, and according to the weight constant set, the historical sales record of the material, and the sales quantity prediction value formula, a given sales quantity prediction value set is obtained; S234: According to the given sales quantity prediction value set, a given sales quantity prediction value average variance is obtained; In an exemplary embodiment, step S234 specifically includes: According to the given sales quantity prediction value set, a given sales quantity prediction value average variance is obtained, as shown in the formula: , wherein, is the given sales quantity prediction value average variance, represents the sales quantity prediction value on the th day, represents the actual sales quantity on the th day, is the statistical number of days of the material sales record; S235: According to the given sales quantity prediction value average variance, the minimum average variance value corresponding to the weight constant is selected as the optimal weight constant; S236: According to the optimal weight constant, the sales quantity prediction value formula is updated to obtain a new sales quantity prediction value formula; S237: The future period sales quantity and the outbound quantity are obtained by using the new sales quantity prediction value formula; In an exemplary embodiment, step S237 specifically comprises: , , wherein, is the outbound quantity, is the sales quantity prediction value of each day in the future period, i.e., the future period sales quantity; is the optimal weight constant; is the predicted number of days; S238: According to the obtained future period sales quantity and outbound quantity, the adjacent storage location of the material with a similar sales quantity prediction value is taken as the storage recommendation location of the material; S239: Obtain the outbound prediction value of the to-be-stored material and all in-stock materials in the vertical warehouse, calculate the absolute value of the difference between the outbound prediction value of all in-stock materials except the to-be-stored material and the outbound prediction value of the to-be-stored material, and sort the materials in order of absolute value from small to large to obtain a sorted material group; according to the sorted material group, the to-be-stored material is determined to exist in at least one side channel without obstruction in the vertical warehouse aisle, and the adjacent storage location satisfies the storage condition of the to-be-stored material, and the adjacent storage location is taken as the storage recommendation location; S24: If the storage recommendation location is not found in step S23, a prompt of no suitable storage location is generated; S3: According to the to-be-stored material information, if the storage recommendation location cannot be found or it is determined that the to-be-stored material does not exist in the vertical warehouse inventory; according to the storage location height and the storage location weight, a vertical warehouse layer with an empty storage location in the entire aisle is found, and an empty storage location aisle is found in order from low to high according to the vertical warehouse layer, and the middle storage location of the aisle is selected as the storage recommendation location; if the storage recommendation location cannot be found, a suitable storage location is found by using the outbound prediction method to obtain the storage recommendation location; if the storage recommendation location cannot be found, a prompt of no suitable storage location is generated.

[0013] In some embodiments, the vertical warehouse storage location recommendation decision method based on real-time big data prediction described above can also be implemented in the following way. As Figure 2 shown is a big data-based shuttle vehicle vertical warehouse storage location recommendation flowchart, as Figure 3The shuttle car vertical warehouse plan view is shown, wherein the material inlet and the material outlet of the vertical warehouse are respectively at the lower left corner, and the red box part is a storage location aisle.

[0014] In the present embodiment, the big data-based shuttle car vertical warehouse storage location recommendation decision system involves a historical sales record big data processing platform, calculation and prediction based on artificial intelligence and massive data, WMS system recommendation for storage locations, and a vertical warehouse storage location recommendation decision method based on real-time big data prediction, which contains: 1. Finding the material to be stored in the vertical warehouse inventory; 2. If the material to be stored exists in the vertical warehouse inventory, the following logic is used to recommend the storage location: 2.1. In order to minimize the relocation process required when picking up, ensure the efficiency of picking up, and give priority to storing the material to be stored in the vertical warehouse next to the storage location where the material already exists when storing; 2.1.1. Select the appropriate storage vertical layer according to the conditions such as the height of the material to be stored, the weight of the material, etc. 2.1.2. Find the recommended storage location in the vertical layer in order from low to high; 2.1.3. In a certain vertical layer, obtain the storage location information of all materials of the same material as the material to be stored in the layer, and traverse the obtained same-material storage locations in order from near to far from the entrance and exit; 2.1.4. For each same-material storage location, traverse the two side storage locations in the same aisle; 2.1.5. If there is a storage location occupied by a material in the two side storage locations of the same aisle, end the traversal search for the current storage location; 2.1.6. If there is an empty storage location on one side of the two side storage locations of the same aisle, return the empty storage location that is closer to the entrance and exit and adjacent to the storage location as the recommended storage location for storage; 2.2. If no suitable storage location is found in 2.1, find a vertical layer where the entire aisle is empty according to the conditions, and find the empty storage location in order from low to high in the vertical layer, and in each vertical layer, find the empty storage location in order from near to far from the entrance and exit, and select the middle storage location in the appropriate aisle as the recommended storage location for storage and return it; 2.3. If no suitable storage location is found in 2.2, use the picking prediction method to find a suitable storage location for storage; 2.3.1. Real-time processing of historical sales big data on the big data processing platform, preferably more than 5 years of massive data, using to represent, wherein represents the number of sales of the material per day in the picking history, i.e., the minimum description unit is day.

[0015] 2.3.2, using a simple exponential smoothing method, a formula is constructed , wherein represents the actual sales quantity of the first day, represents the sales quantity prediction value of the first day, represents the sales quantity prediction value of the first day, is a weight constant, the value range of the constant is , the predicted sales quantity value of the first day is consistent with the actual sales quantity value of the first day, that is ; 2.3.3, the value of the weight constant is calculated, a constant is obtained in ascending order according to a plurality of weight constants, the value set of the constant is , for each value in the set, based on the historical sales records of a material and the constructed formula, a prediction value can be obtained; 2.3.4, the average variance of the sales quantity prediction value can be calculated according to the sales quantity prediction value obtained in 2.3.3, and the calculation formula is: , wherein is the statistical number of material sales records; 2.3.5, for each constant , a corresponding average variance can be calculated, wherein the constant with the smallest average variance value is the optimal weight constant; 2.3.6, according to the optimal weight constant obtained in 2.3.5, a prediction formula can be obtained; 2.3.7, the sales quantity of a certain material in a future period of time under the current operation, that is, the outbound quantity, can be obtained from the above prediction formula , wherein are the sales quantity prediction values of each day in a future period of time, is the prediction number of days; 2.3.8, for materials with similar sales quantity prediction values, it can be considered that the outbound frequency in a future period of time will also be similar, and then the materials are placed in adjacent storage locations, which can improve the outbound efficiency to a certain extent; 2.3.9, obtain the material to be stored and the outbound forecast value of all in-stock materials in the vertical warehouse, calculate the absolute value of the difference between the outbound forecast value of all in-stock materials except the material to be stored and the outbound forecast value of the material to be stored, and sort the materials in order of absolute value from small to large to obtain a sorted material group , traverse the sorted materials in order, if there is no obstruction in a certain side passage of the vertical warehouse aisle where the traversed material is located, and the adjacent storage locations meet the storage conditions of the material to be stored, then return the adjacent storage locations as recommended storage locations; 2.3.10, if no suitable storage location is found after the above operation, prompt the operator that there is no suitable storage location; 3. If the material to be stored does not exist in the vertical warehouse inventory, recommend the storage location according to the following logic: 3.1, first, find the storage recommendation location according to the logic described in 2.2, if a suitable storage location is found, return, if not, proceed to the next step; 3.2, find the storage recommendation location according to the logic described in 2.3, if a suitable storage location is found, return, if not, prompt the operator that there is no suitable storage location; It should be noted that the shuttle car vertical warehouse is generally a dense warehouse, that is, there will be three or more storage locations in the same storage location aisle. When carrying out storage and retrieval operations in such an aisle, it is inevitable that when a material is stored or retrieved from a certain storage location, one or more adjacent storage locations will be obstructed. At this time, it will be necessary to move the storage, and the increase in the moving process will inevitably increase the time consumption of storage and retrieval. In view of this scenario, when storing, the material is preferentially allocated to the adjacent storage location of the same material or to the middle storage location of the empty aisle, which can to some extent reduce the moving process during retrieval. With the increase of operation quantity, different materials will inevitably be stored in the same aisle. In view of this scenario, a method based on massive historical sales records is used to predict the outbound quantity of the material to be stored and the in-stock material in the future period of time, so as to place the in-stock material with a predicted outbound quantity basically equivalent to the material to be stored in the adjacent storage location. In this way, the outbound frequency of adjacent storage locations in the future period of time will also be basically equivalent, thereby reducing the moving process during retrieval to some extent and improving the retrieval efficiency.

[0016] This embodiment provides a computer-readable storage medium storing a computer program thereon. When executed by a processor, the computer program implements the steps of the above-described method for recommending warehouse entry and exit locations based on real-time big data prediction. The storage medium can be a magnetic disk, optical disk, read-only memory (ROM), random access memory (RAM), flash memory, hard disk drive (HDD), or solid-state drive (SSD), etc.; the storage medium may also include combinations of the above types of memory.

[0017] This embodiment provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, it implements the steps of the above-described method for recommending warehouse entry locations based on real-time big data prediction.

[0018] like Figure 4 As shown, the computer device 120 may include: at least one processor 121, such as a central processing unit (CPU), at least one communication interface 123, memory 124, and at least one communication bus 122. The communication bus 122 is used to enable communication between these components. The communication interface 123 may include a display screen and a keyboard; optionally, the communication interface 123 may also include a standard wired interface or a wireless interface. The memory 124 may be high-speed random access memory (RAM) or non-volatile memory, such as at least one disk storage device. Optionally, the memory 124 may also be at least one storage device located remotely from the aforementioned processor 121. The memory 124 stores application programs, and the processor 121 calls the program code stored in the memory 124 to execute any of the aforementioned method steps. The communication bus 122 may be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. The communication bus 122 can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 4The bus 123 is only represented by one line, but does not represent only one bus or only one type of bus. The memory 124 can include volatile memory, such as random-access memory (RAM), and can also include non-volatile memory, such as flash memory, a hard disk drive (HDD), or a solid-state drive (SSD), or a combination of the above. The processor 121 can be a central processing unit (CPU), a network processor (NP), or a combination of the CPU and the NP. The processor 121 can further include a hardware chip. The hardware chip can be an application-specific integrated circuit (ASIC), a programmable logic device (PLD), or a combination thereof. The PLD can be a complex programmable logic device (CPLD), a field-programmable gate array (FPGA), a generic array logic (GAL), or any combination thereof. Optionally, the memory 124 is further configured to store program instructions. The processor 121 can invoke the program instructions to implement the method for recommending a storage location for a storage-in of a vertical warehouse based on real-time big data prediction.

[0019] The embodiment provides a computer program product, including a computer program, which, when executed by a processor, implements the steps of the method for recommending a storage location for a storage-in of a vertical warehouse based on real-time big data prediction.

[0020] The embodiments of the present application are described above with reference to the drawings; however, the present application is not limited to the specific embodiments described above, but the specific embodiments described above are only illustrative, rather than limiting, and a person of ordinary skill in the art can make many forms under the inspiration of the present application without departing from the purpose of the present application and the scope protected by the claims, which are all within the protection of the present application.

Claims

1. A method for recommending storage locations for vertical warehouses based on real-time big data prediction, characterized in that, Includes the following steps: S1: Obtain information on materials to be received based on the inventory in the automated warehouse; S2: Based on the information of the materials to be received, determine that the materials to be received exist in the automated warehouse inventory; Based on the location information of the same material in the automated warehouse, find the adjacent warehouse locations of the same material as the recommended warehouse locations for inbound storage; S3: Based on the information of the materials to be received, if no recommended storage location is found or it is determined that the materials to be received do not exist in the automated storage and retrieval system (AS / RS) inventory; search for AS / RS floors where the entire aisle is empty based on the floor height and weight of the goods; search for empty storage aisles in ascending order of AS / RS floors, and select the middle storage location in the aisle as the recommended storage location; if no recommended storage location can be found, use the outbound forecasting method to find a suitable storage location; if no recommended storage location can be found, generate a prompt that no suitable storage location is available.

2. The warehouse location recommendation decision method based on real-time big data prediction according to claim 1, characterized in that, Step S2 specifically includes: S21: Based on the information of the material to be put into storage, determine the storage location in the automated warehouse where the material already exists; and use the adjacent storage locations of the storage locations where the material already exists as recommended storage locations for inbound storage. S22: If step S21 fails to find a recommended storage location, search for vertical storage floors where the entire aisle is empty. Search for empty storage aisles in order of vertical storage floors from low to high. In each vertical storage floor, search for empty storage aisles in order of proximity to the entrance / exit. Select the middle storage location in the appropriate aisle as the recommended storage location. S23: If step S22 fails to find a recommended storage location for inbound goods, use the outbound goods forecasting method to find a suitable storage location for inbound goods and obtain a recommended storage location for inbound goods. S24: If step S23 fails to find a recommended storage location, a message indicating that no suitable storage location is found will be generated.

3. The warehouse location recommendation decision method based on real-time big data prediction according to claim 2, characterized in that, Step S21 specifically includes: S211: Select the appropriate storage level based on the matching layer height and weight of the materials to be stored; S212: The opposing storage layer searches for recommended storage locations in ascending order of storage level; S213: In a certain storage layer being traversed, obtain the storage location information of all materials in that layer that are the same as the material to be put into storage, and traverse the obtained storage locations of the same material in order from the nearest to the farthest from the entrance / exit. S214: For each storage location with the same material, iterate through the two storage locations on both sides of the same aisle. S215: If there are storage locations on both sides of the same aisle where the current storage location is occupied by materials, then the traversal search for the current storage location ends. S216: If one side of the storage location in the same aisle as the storage location is empty, the empty storage location that is closer to the entrance / exit and adjacent to the storage location will be the recommended storage location for entry.

4. The warehouse location recommendation decision method based on real-time big data prediction according to claim 2, characterized in that, Step S23 specifically includes: S231: Obtain historical sales big data, including the daily sales volume of materials in the outbound history; S232: Based on the actual sales volume in historical sales big data, construct a formula for predicting sales volume using a simple exponential smoothing method; S233: Obtain the set of weight constants, and based on the set of weight constants, the historical sales records of the materials, and the sales quantity prediction formula, obtain the set of given sales quantity prediction values; S234: Based on the given set of sales quantity forecasts, obtain the average variance of the given sales quantity forecasts; S235: Based on the average variance of the given sales quantity forecast, select the weight constant corresponding to the minimum average variance value as the optimal weight constant; S236: Update the sales quantity forecast formula according to the optimal weight constant to obtain a new sales quantity forecast formula; S237: Using the new sales quantity forecast formula, the sales quantity and outbound quantity for the future period are obtained; S238: Based on the sales volume and outbound volume obtained in the future time period, the nearest storage location of the material that is close to the sales volume forecast value is used as the recommended storage location for the material. S239: Obtain the outbound forecast values ​​of the materials to be received and all materials in the vertical warehouse. Calculate the absolute value of the difference between the outbound forecast value of all materials in the warehouse except the materials to be received and the outbound forecast value of the materials to be received. Sort the materials in ascending order of absolute value to obtain sorted material groups. Iterate through the sorted material groups in sequence. If it is determined that there is at least one unobstructed passage in the vertical warehouse aisle where the traversed material is located, and the adjacent storage location meets the warehousing conditions of the materials to be received, then the adjacent storage location is used as the recommended storage location for receiving materials.

5. The warehouse location recommendation decision method based on real-time big data prediction according to claim 4, characterized in that, The formula for the sales quantity forecast is as follows: ， in, and They represent the first , Daily sales volume forecast Indicates the first The actual sales volume of the day This is a weighting constant, and its value range is... .

6. The warehouse location recommendation decision method based on real-time big data prediction according to claim 4, characterized in that, Step S234 specifically includes: obtaining the average variance of the given sales quantity forecasts based on the given set of sales quantity forecasts, as shown in the formula: ， in, Given the average variance of the sales quantity forecast, Indicates the first Daily sales volume forecast Indicates the first The actual sales volume of the day This refers to the number of days for recording material sales.

7. The warehouse location recommendation decision method based on real-time big data prediction according to claim 4, characterized in that, Step S237 specifically includes: ， ， in, For the quantity shipped out, These are the daily sales volume forecasts for a future period of time, i.e., the sales volume for the future period. This is the optimal weight constant; This refers to the predicted number of days.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that, When executed by a processor, the computer program implements the steps of the warehouse location recommendation decision-making method based on real-time big data prediction as described in any one of claims 1-7.

9. A computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the warehouse location recommendation decision method based on real-time big data prediction as described in any one of claims 1-7.

10. A computer program product, comprising a computer program, characterized in that, When executed by a processor, the computer program implements the steps of the warehouse location recommendation decision-making method based on real-time big data prediction as described in any one of claims 1-7.

Images