Shelf warehouse returning method and device based on thermodynamic analysis, computing equipment and medium

Abstract

The invention discloses a goods shelf warehouse returning method and device based on thermal analysis, computing equipment and a medium, and relates to the technical field of warehousing. The method comprises the following steps: respectively determining the popularity of each cargo according to the turnover rate of the cargo, the warehouse-out time interval and the warehouse-out quantity of the cargo in a historical order; according to the goods number of the goods shelf and the heat degree of the goods stored in each goods allocation, the heat degree of each goods shelf is determined; according to the popularity of all the goods shelves, determining storage location popularity distribution; after the target shelf is delivered, determining the update popularity of the target shelf; according to the path cost of each storage position to the sorting work station and the cost of moving other goods shelves, the cost of each storage position is determined, and the cost is the cost of moving the target goods shelf from the sorting work station to the storage position; and according to the cost of each storage location, the update popularity of the target shelf and the storage location popularity distribution, carrying out storage location distribution on the target shelf. According to the invention, the storage position distribution of the goods shelf is dynamically realized, and the sorting and shelving efficiency of the sorting system is effectively improved.

Description

Technical Field

[0001] The present application relates to the field of warehousing technology, and in particular to a shelf return method, device, computing equipment and medium based on thermal analysis. Background Art

[0002] The rapid development of e-commerce has made the picking efficiency of warehouses more and more concerned by the industry. Goods-to-person picking systems have emerged in this context. With the promotion of goods-to-person picking systems, how to further improve their picking efficiency has become a new research direction. The allocation of shelf storage locations in the picking or shelving environment is one of the research focuses. In the goods-to-person picking system, the shelf storage location determines the distance and efficiency of AGV (Automated Guided Vehicle) transportation.

[0003] At present, most warehouses in the goods-to-person picking system use static storage location allocation technology. This method cannot reasonably allocate shelf storage locations, resulting in low efficiency in handling from shelves to workstations, increasing the waiting time of workers at workstations, and thus affecting the picking and shelving efficiency of the goods-to-person picking system. Summary of the invention

[0004] The purpose of the embodiments of the present application is to provide a shelf return method, device, computing equipment and medium based on thermal analysis, so as to solve the technical problem of low picking and shelving efficiency of the goods-to-person picking system in the prior art.

[0005] In order to achieve the above-mentioned purpose, the first aspect of the present application provides a shelf return method based on thermal analysis, comprising: Determine the popularity of each product based on its turnover rate, time interval between shipments, and the number of shipments in historical orders. Determine the temperature of each shelf according to the number of shelves and the temperature of the goods stored in each shelf; Determine the storage space heat distribution based on the heat of all shelves; After the target shelf is shipped out, determine the update heat of the target shelf; Determine the cost of each storage location based on the path cost from each storage location to the picking workstation and the cost of moving other shelves, where the cost is the cost of moving the target shelf from the picking workstation to the storage location; According to the cost of each storage location, the update heat of the target shelf and the storage location heat distribution, the storage locations are allocated to the target shelf.

[0006] In the embodiment of the present application, the popularity of each product is determined according to the turnover rate of the product, the time interval for shipment, and the quantity of shipments of the product in the historical orders, including: According to the frequency of the goods appearing in historical orders, the turnover rate of the goods is determined as the first popularity of the goods; Determine the time interval for goods to leave the warehouse based on the target deadline and the last time the goods left the warehouse; The second heat of the goods is obtained by multiplying the outbound time interval by the time decay coefficient and adding the preset value and finding the inverse thereof; Determine the picking quantity of the goods under the measure according to the quotient of the total outbound quantity of the goods in the historical orders and the measure, wherein the measure is the maximum outbound picking quantity of the goods; Determine the third heat of the goods based on the quotient of the goods and the sum of the picking quantities of all goods under the measurement; The first heat, the second heat, and the third heat are weightedly calculated to obtain the heat of the goods.

[0007] In the embodiment of the present application, the storage location heat distribution is determined according to the heat of all shelves, including: Sampling is performed based on the heat of each shelf to obtain multiple sampling distributions; The kernel density estimation is performed on multiple sampling distributions to obtain the reservoir heat distribution.

[0008] In the embodiment of the present application, sampling is performed according to the heat of each shelf to obtain multiple sampling distributions, including: Step S1, resample all shelves to obtain a sample set; Step S2, determining the heat of each shelf in the sample set; Repeat step S1 and step S2 to obtain multiple sampling distributions.

[0009] In the embodiment of the present application, kernel density estimation is performed on multiple sampling distributions to obtain reservoir heat distribution, including: Determining a bandwidth parameter based on distances between data points in the plurality of sampled distributions and a preset number of other closest data points; According to the bandwidth parameter, the kernel density estimation function of each sampling distribution is determined; According to the calculation results of the kernel density estimation function, the reservoir heat distribution is obtained.

[0010] In the embodiment of the present application, storage locations are allocated to the target shelf according to the cost of each storage location, the update heat of the target shelf, and the storage location heat distribution, including: Sort the cost of each storage position to obtain a storage position cost sequence; Divide the storage cost sequence according to the storage heat distribution to obtain the storage ID corresponding to each storage heat level; According to the update heat of the target shelf, determine the corresponding target storage location heat level; Select the storage location ID with the lowest cost and is free from all storage location IDs corresponding to the target storage location heat level to complete the storage location allocation to the target shelf.

[0011] In the embodiment of the present application, the Redis database is used to store and read the popularity of goods.

[0012] The second aspect of the present application provides a shelf return device based on thermal analysis, comprising: a memory configured to store instructions; The processor is configured to call instructions from the memory and implement the shelf return method based on thermal analysis according to the first aspect when executing the instructions.

[0013] A third aspect of the present application provides a computing device, including: A shelf return device based on thermal analysis according to the second aspect.

[0014] A fourth aspect of the present application provides a machine-readable storage medium having instructions stored thereon, the instructions being used to enable a machine to execute the shelf return method based on thermal analysis according to the first aspect.

[0015] Through the above-mentioned technical scheme, the shelf return method based on thermal analysis provided in the embodiment of the present application proposes a cargo heat calculation method based on historical orders. Since factors such as the outbound time interval and turnover rate are taken into consideration, the influence of time and turnover rate on cargo heat can be more intuitively reflected. After the shelf is outbound, the updated heat of the shelf is calculated in real time, and dynamic allocation is performed considering the current storage location status. Dynamic shelf storage location matching can be achieved, which can effectively improve the overall picking and shelving efficiency of the goods-to-person picking system, and improve the digitization and intelligence level of the goods-to-person picking system.

[0016] Other features and advantages of the embodiments of the present application will be described in detail in the subsequent specific implementation section. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The accompanying drawings are used to provide a further understanding of the embodiments of the present application and constitute a part of the specification. Together with the following specific implementations, they are used to explain the embodiments of the present application, but do not constitute a limitation on the embodiments of the present application. In the accompanying drawings: Figure 1 A schematic diagram of a process flow of a shelf return method based on thermal analysis according to an embodiment of the present application is shown; Figure 2 A schematic diagram schematically shows a kernel density estimation result according to an embodiment of the present application; Figure 3 The schematic diagram shows the structure of a shelf return device based on thermal analysis according to an embodiment of the present application. DETAILED DESCRIPTION

[0018] In order to make the purpose, technical scheme and advantages of the embodiments of the present application clearer, the technical scheme in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. It should be understood that the specific implementation methods described herein are only used to illustrate and explain the embodiments of the present application, and are not used to limit the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0019] In addition, if there are descriptions involving "first", "second", etc. in the embodiments of the present application, the descriptions of "first", "second", etc. are only used for descriptive purposes and cannot be understood as indicating or suggesting their relative importance or implicitly indicating the number of technical features indicated. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In addition, the technical solutions between the various embodiments can be combined with each other, but they must be based on the ability of ordinary technicians in the field to implement them. When the combination of technical solutions is contradictory or cannot be implemented, it should be deemed that such combination of technical solutions does not exist and is not within the scope of protection required by this application.

[0020] Figure 1 The flowchart of a shelf return method based on thermal analysis according to an embodiment of the present application is schematically shown. Figure 1 As shown, an embodiment of the present application provides a shelf return method based on thermal analysis, which may include the following steps.

[0021] Step 110: Determine the popularity of each product based on the turnover rate of the product, the time interval between shipments, and the shipment quantity of the product in historical orders.

[0022] The popularity of goods is affected by many factors such as season, policy, market demand, and supply chain efficiency. Accurate calculation of the popularity of goods directly affects the accuracy of dynamic allocation of warehouse storage space. This solution provides a method for calculating the popularity of goods based on historical orders. It also takes into account factors such as the turnover rate of goods and the time interval between shipments, and establishes a calculation model for the popularity of goods, thereby improving the accuracy of the calculation of the popularity of goods.

[0023] In an optional implementation, step 110 includes: According to the frequency of the goods appearing in historical orders, the turnover rate of the goods is determined as the first popularity of the goods; Determine the time interval for goods to leave the warehouse based on the target deadline and the last time the goods left the warehouse; The second heat of the goods is obtained by multiplying the outbound time interval by the time decay coefficient and adding the preset value and finding the inverse thereof; Determine the picking quantity of the goods under the measure according to the quotient of the total outbound quantity of the goods in the historical orders and the measure, wherein the measure is the maximum outbound picking quantity of the goods; Determine the third heat of the goods based on the quotient of the goods and the sum of the picking quantities of all goods under the measurement; The first heat, the second heat, and the third heat are weightedly calculated to obtain the heat of the goods.

[0024] Specifically, first of all, the turnover rate can be understood as the frequency of goods appearing in historical orders, which can be referred to in the following formula (1): (1) In the formula, p i Indicates the frequency of goods appearing in historical orders, n i represents the total number of occurrences of item i in the historical order range, and N represents the total number of item lines in the historical orders.

[0025] It can be understood that the first heat obtained from the turnover rate is between 0-1.

[0026] Secondly, time also affects the popularity of goods. The embodiment of the present application combines the time decay term of goods to reflect the change in popularity of goods over time. The target deadline can be understood as a deadline set based on actual needs, such as 5 o'clock. The difference between the target deadline and the last time the goods were shipped out of the warehouse is the time interval between shipments, that is, the time interval from the last shipment of the goods. The second heat can be obtained by multiplying the time interval between shipments by the time decay coefficient plus the sum of the preset values ​​and taking the inverse. Schematically, the preset value can be 1. The second heat can refer to the following formula (2): (2) In the formula, Indicates the second heat, α represents the time attenuation coefficient, α The larger the value of, the greater the impact of time on the heat decay of goods. T Indicates the target deadline, t i Indicates goods i The time of the most recent shipment.

[0027] It can be understood that in the embodiment of the present application, the maximum value of the second heat is 1.

[0028] Thirdly, the number of goods in historical orders also has a certain impact on the popularity of goods, but the popularity of goods in this dimension has a cumulative effect. In order to reduce the impact of the cumulative effect of heat on the popularity of goods, the embodiment of the present application uses the maximum number of goods picked out of the warehouse as the metric of the goods. The maximum number of goods picked out of the warehouse can be understood as the maximum value of the number of goods shipped out of the warehouse each time. Specifically, assuming that the goods i Total occurrences m times, and the quantity shipped out each time is s j , then the measurement of the goods is , which is the maximum number of goods to be picked out of the warehouse. i In measurement The picking quantity is: , which is the quotient of the total outbound quantity and measurement of goods in historical orders.

[0029] Therefore, the third heat of the goods is obtained according to the quotient of the goods and the sum of the picking quantities of all goods under measurement, which can be referred to formula (3): (3) In the formula, Indicates the third heat, represents the number of goods picked under measurement, and N represents the total number of goods in historical orders.

[0030] Finally, the heat of the goods can be calculated by weighting the first heat, the second heat, and the third heat, referring to formula (4): (4) In the formula, Indicates the temperature of the cargo. Indicates the first heat of the goods, Indicates the second heat of the goods, Indicates the third temperature of the goods. , , Respectively represent the weights corresponding to the first heat, the second heat, and the third heat, and satisfy .

[0031] In an optional implementation, the method further includes: Use the Redis database to store and read the popularity of goods.

[0032] Specifically, Redis database, whose full name is Remote Dictionary Server, is an open source, log-type, Key-Value database written in ANSI (American National Standards Institute) C language, supporting the network, memory-based and persistent, and providing API (Application Programming Interface) in multiple languages. The embodiment of the present application uses Redis database to store and read the heat of goods, which can effectively improve the calculation speed of the warehouse shelf return method based on thermal analysis.

[0033] Step 120: Determine the temperature of each shelf according to the number of shelves in the shelf and the temperature of the goods stored in each shelf.

[0034] Specifically, generally speaking, a shelf includes multiple cargo spaces, and the goods are stored on the shelf according to the principle of placing one type of goods in one cargo space, that is, different types of goods are not mixed. Based on the temperature of each product obtained in step 110, the temperature of each shelf can be obtained according to the number of cargo spaces on the shelf and the temperature of the goods stored in each cargo space. s The number of shelves is C, and each shelf has one type of goods. The temperature of the shelf can be determined by referring to formula (5): (5) In the formula, Indicates the temperature of the shelf, Indicates the cargo location o The heat of the goods stored in C Indicates the cargo location o The number of

[0035] Schematically, a shelf has 3*3 total 9 cargo positions, and the goods stored in each cargo position include: the first cargo position to the third cargo position are all stored goods i 1. The fourth to sixth cargo positions are used to store goods. i 2. Goods are stored in the seventh to ninth cargo positions i 3. Assuming the goods i 1. Goods i 2. Goods i The heat of 3 is , as well as , then the heat of the shelf is .

[0036] Step 130: Determine the storage location heat distribution based on the heat of all shelves.

[0037] Generally speaking, one shelf is in one storage location. In the embodiment of the present application, there are usually hundreds or thousands of shelves in a large warehouse. The heat distribution of the warehouse storage location layout can be more reasonably divided based on the overall distribution of shelf heat. It is understandable that the storage location heat distribution can be set according to actual needs, and the embodiment of the present application does not limit this. Schematically, the storage location heat distribution can include three levels: high, medium and low.

[0038] In an optional implementation, step 130 includes: Step 131: Sampling is performed according to the heat of each shelf to obtain multiple sampling distributions; Step 132: Perform kernel density estimation on multiple sampling distributions to obtain reservoir heat distribution.

[0039] Specifically, in the embodiment of the present application, sampling is first performed according to the heat of each shelf to obtain multiple sampling distributions, and then based on the results of the sampling distribution, the kernel density estimation method is used to evaluate the overall storage heat distribution. In order to improve the computational efficiency of the shelf return method based on thermal analysis, the embodiment of the present application adopts a self-service sampling method to estimate the overall distribution of shelves in the warehouse. The core idea is to simulate the distribution of overall storage heat through the existing sample data of shelf heat, thereby avoiding dependence on all data and improving the representativeness of the overall sampling data.

[0040] In an optional implementation, step 131 includes: Step 131a, resampling all shelves to obtain a sample set; Step 131b, determining the heat of each shelf in the sample set; Step 131a and step 131b are repeatedly executed to obtain multiple sampling distributions.

[0041] Illustratively, in the embodiment of the present application, a resampling method is used to obtain a sample set. Resampling is a method that can repeatedly extract samples from a data set, that is, a certain number of samples are randomly extracted from all shelves with replacement to obtain a sample set. In this process, the same sample is allowed to be extracted multiple times, so the extraction of each sample is independent, which improves the representativeness of the entire sample set. Then determine the popularity of each shelf in the sample set. It can be understood that in step 131b, a method similar to step 120 can be used to determine the popularity of the shelf. By repeating this process, a large number of sampling distributions can be constructed. It should be noted that the number of repetitions can be determined according to the number of sampled shelves.

[0042] In an optional implementation, step 132 includes: Determining a bandwidth parameter based on distances between data points in the plurality of sampled distributions and a preset number of other closest data points; According to the bandwidth parameter, the kernel density estimation function of each sampling distribution is determined; According to the calculation results of the kernel density estimation function, the reservoir heat distribution is obtained.

[0043] Specifically, in order to improve the accuracy of the kernel density estimation result, the embodiment of the present application adopts an adaptive bandwidth kernel density estimation method. Let the data points sampled from the multiple sampling distributions in the embodiment of the present application be , the data point represents the heat of the shelf, then the kernel density estimation function can be expressed as follows: (6) In the formula, n represents the number of data points, Represents data points i The heat, represents the kernel function, For data points The associated bandwidth parameter, x represents the input value.

[0044] In the embodiment of the present application, the kernel function adopts a Gaussian function, and its expression can refer to the following formula (7): (7) In the formula, x represents the input value, μ represents the mean, σ represents the variance, and e represents the natural constant.

[0045] Here, x is the temperature of the shelf in the embodiments of the present application.

[0046] In the embodiment of the present application, the bandwidth parameter in the kernel function Based on the nearest neighbor method. That is, each data point is calculated based on the distance to its nearest neighbor. Specifically, you can choose the data point The preset number of nearest neighbor data points is calculated, and the preset number of nearest neighbor data points and data points are calculated. The average distance between them is then multiplied by a constant factor Get bandwidth parameters , you can refer to the following formula (8): (8) In the formula, h i represents the bandwidth parameter, x i represents a data point, x j represents the nearest neighbor data point, represents the constant factor, k Represents the number of nearest neighbor data points, which is also the preset number.

[0047] It is understandable that the preset number can be set according to actual needs, and the embodiments of the present application do not limit this.

[0048] Furthermore, the kernel density estimation result is the distribution of all shelves in the warehouse. Figure 2 , Figure 2 A schematic diagram of a kernel density estimation result according to an embodiment of the present application is schematically shown. Figure 2 As shown, Figure 2 The red dashed lines in the figure are the kernel density estimation results for each sampling distribution, and the blue solid lines are the distribution of all shelves in the warehouse. It can be understood that the blue solid line can be obtained by superimposing multiple red dashed lines.

[0049] Based on the results of kernel density estimation, the storage locations in the warehouse can be divided into heat categories. Let the kernel density estimation result be , the range of kernel density estimation results is , the number of storage heat level divisions m It can be configured according to the actual needs of the user. After setting the number of divisions, the division point value will be generated , among which, m The calculation method for the proportion of the number of storage spaces corresponding to the heat level of each storage space to the total number of storage spaces can refer to the following formula (9): (9) In the formula, Indicates the proportion, represents the kernel density estimation result, Indicates m The dividing point value, , They represent the minimum and maximum values ​​of the kernel density estimation results respectively.

[0050] Step 140: After the target shelf is shipped out, determine the update heat of the target shelf.

[0051] In the embodiment of the present application, after the target shelf is shipped out, it will undergo picking or shelving, and the goods on the target shelf will change, decrease or increase. Therefore, it is necessary to determine the update heat of the target shelf after the goods change, so as to provide a basis for dynamically realizing the storage allocation of the shelf. It is understandable that a method similar to step 120 can also be used here.

[0052] Step 150: Determine the cost of each storage location based on the path cost from each storage location to the picking workstation and the cost of moving other shelves, wherein the cost is the cost of moving the target shelf from the picking workstation to the storage location.

[0053] In the embodiment of the present application, the cost of the storage location is the cost of moving the target shelf from the picking workstation to the storage location, including the path cost from the storage location to the picking workstation and the cost of moving other shelves. The path cost from the storage location to the picking workstation needs to select the path with the shortest length from all the paths obtained by path planning to improve the movement efficiency and reduce the cost of the storage location. The cost of moving other shelves can be understood as a shelf is in the center of the nine-square storage location, surrounded by eight shelves. If the shelf is to be moved out of the storage location, at least one other shelf needs to be moved to achieve it. Therefore, the cost can refer to the following formula (10): (10) In the formula, Indicates the cost of storage space, Indicates picking workstation to storage location r The lengths of multiple paths in the path set, Represents the cost of moving other shelves, represents the mapping factor of path length mapping to time, A factor that represents the mapping between shelf movement quantity and time.

[0054] Step 160: Allocate storage locations to the target shelf according to the cost of each storage location, the update heat of the target shelf, and the storage location heat distribution.

[0055] In an embodiment of the present application, after the target shelf is shipped out, the storage location of the target shelf back to the warehouse is determined based on the three information: the cost of each storage location obtained in step 150, the update heat of the target shelf obtained in step 140, and the storage location heat distribution obtained in step 130. Dynamic allocation of storage locations to the target shelf is achieved, which can effectively improve the efficiency of shelf returns to the warehouse, and further improve the overall picking and shelving efficiency of the goods-to-person picking system.

[0056] In an optional implementation, step 160 includes: Sort the cost of each storage position to obtain a storage position cost sequence; Divide the storage cost sequence according to the storage heat distribution to obtain the storage ID corresponding to each storage heat level; According to the update heat of the target shelf, determine the corresponding target storage location heat level; Select the storage location ID with the lowest cost and is free from all storage location IDs corresponding to the target storage location heat level to complete the storage location allocation to the target shelf.

[0057] In the embodiment of the present application, the cost of each storage location in the warehouse is first sorted to generate a storage location cost sequence, and the storage location ID (Identity) corresponding to each storage location heat level is obtained based on the storage location cost sequence, thereby realizing the division of storage locations. Furthermore, according to the updated heat of the target shelf after leaving the warehouse, it is matched with the storage location heat level, and the one with the lowest cost is selected from the corresponding target storage location heat level.

[0058] Schematically, there are 10 storage locations in the warehouse, and the storage location IDs are 1 to 10 respectively. The cost of each storage location is A1, A2, ..., A10 respectively. Arranged in descending order, the storage location cost sequence of A5, A8, A10, A3, A7, A2, A4, A1, A6, A9 is obtained. Assuming that the storage location heat distribution includes three categories of high, medium and low in a ratio of 1:3:1, the storage location IDs corresponding to the high heat level are 5 and 8, the storage location IDs corresponding to the medium heat level are 10, 3, 7, 2, 4 and 1, and the storage location IDs corresponding to the low heat level are 6 and 9. If the update heat of the target shelf corresponds to the medium heat level, then from the six storage location IDs of 10, 3, 7, 2, 4 and 1 corresponding to the medium heat level, the storage location ID with the smallest cost is selected based on the cost of each storage location to complete the storage location allocation for the target shelf. Assuming that the cost is the lowest and the free storage location ID is 3, the target shelf will be returned to the storage location with storage location ID 3.

[0059] The shelf return method based on thermal analysis provided in the embodiment of the present application proposes a cargo heat calculation method based on historical orders. Since factors such as the outbound time interval and turnover rate are taken into consideration, the impact of time and turnover rate on cargo heat can be more intuitively reflected. After the shelf is outbound, the updated heat of the shelf is calculated in real time, and dynamic allocation is performed considering the current storage location status. Dynamic shelf storage location matching can be achieved, which can effectively improve the overall picking and shelving efficiency of the goods-to-person picking system, and improve the digitization and intelligence level of the goods-to-person picking system.

[0060] Figure 3 The schematic diagram of the structure of a shelf return device based on thermal analysis according to an embodiment of the present application is shown. Figure 3 As shown, the embodiment of the present application provides a shelf return device based on thermal analysis, which may include: Memory 310, configured to store instructions; The processor 320 is configured to call instructions from the memory 310 and implement the above-mentioned method for controlling the boom when executing the instructions.

[0061] Specifically, in the embodiment of the present application, the processor 320 may be configured to: Determine the popularity of each product based on its turnover rate, time interval between shipments, and the number of shipments in historical orders. Determine the temperature of each shelf according to the number of shelves and the temperature of the goods stored in each shelf; Determine the storage space heat distribution based on the heat of all shelves; After the target shelf is shipped out, determine the update heat of the target shelf; Determine the cost of each storage location based on the path cost from each storage location to the picking workstation and the cost of moving other shelves, where the cost is the cost of moving the target shelf from the picking workstation to the storage location; According to the cost of each storage location, the update heat of the target shelf and the storage location heat distribution, the storage locations are allocated to the target shelf.

[0062] The shelf return device based on thermal analysis provided in the embodiment of the present application can realize each process of the shelf return method based on thermal analysis in the method embodiment, and can achieve the same technical effect. To avoid repetition, it will not be described here.

[0063] The present application also provides a computing device, which may include: The above-mentioned shelf return device based on thermal analysis.

[0064] An embodiment of the present application also provides a machine-readable storage medium, on which instructions are stored, and the instructions are used to enable a machine to execute the above-mentioned shelf return method based on thermal analysis.

[0065] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems or computer program products. Therefore, the present application may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present application may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0066] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of the processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0067] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0068] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0069] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0070] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0071] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0072] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0073] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included within the scope of the claims of the present application.

Claims

1. A shelf return method based on thermal analysis, characterized in that: include: Determine the popularity of each of the goods according to the turnover rate of the goods, the time interval between shipments, and the shipment quantity of the goods in the historical orders; Determine the temperature of each shelf according to the number of shelves and the temperature of the goods stored in each shelf; Determining storage space heat distribution according to the heat of all the shelves; After the target shelf is shipped out of the warehouse, determining the update heat of the target shelf; Determine the cost of each storage location according to the path cost from each storage location to the picking workstation and the cost of moving other shelves, wherein the cost is the cost of moving the target shelf from the picking workstation to the storage location; The target shelf is allocated storage locations according to the cost of each storage location, the update heat of the target shelf, and the storage location heat distribution.

2. The method according to claim 1, characterized in that Determining the popularity of each of the goods according to the turnover rate of the goods, the time interval for shipment, and the shipment quantity of the goods in the historical orders includes: According to the frequency of the goods appearing in the historical orders, the turnover rate of the goods is determined as the first popularity of the goods; Determine the time interval for the goods to be shipped out of the warehouse according to the target deadline and the most recent shipment time of the goods; The second temperature of the goods is obtained by multiplying the outbound time interval by the time decay coefficient and adding a preset value and calculating the inverse thereof; Determine the picking quantity of the goods under the measurement according to the quotient of the total outbound quantity of the goods in the historical orders and the measurement, wherein the measurement is the maximum outbound picking quantity of the goods; determining a third heat level of the goods according to a quotient of the goods and a sum of the picking quantities of all the goods under measurement; The first heat, the second heat, and the third heat are weightedly calculated to obtain the heat of the goods.

3. The method according to claim 1, characterized in that Determining the storage location heat distribution according to the heat of all the shelves includes: Sampling is performed according to the heat of each shelf to obtain multiple sampling distributions; Kernel density estimation is performed on the multiple sampling distributions to obtain reservoir heat distribution.

4. The method according to claim 3, characterized in that The sampling is performed according to the heat of each shelf to obtain multiple sampling distributions, including: Step S1, resampling all the shelves to obtain a sample set; Step S2, determining the heat of each shelf in the sample set; Repeat step S1 and step S2 to obtain multiple sampling distributions.

5. The method according to claim 3, characterized in that: The performing kernel density estimation on the multiple sampling distributions to obtain the reservoir heat distribution includes: Determining a bandwidth parameter based on distances between the data points in the plurality of sampled distributions and a preset number of other data points that are closest to each other; Determining a kernel density estimation function for each sampling distribution according to the bandwidth parameter; According to the calculation result of the kernel density estimation function, the reservoir heat distribution is obtained.

6. The method according to claim 1, characterized in that The allocating storage locations to the target shelf according to the cost of each storage location, the update heat of the target shelf, and the storage location heat distribution includes: Sort the cost of each storage position to obtain a storage position cost sequence; Dividing the storage cost sequence according to the storage heat distribution to obtain a storage ID corresponding to each storage heat level; Determine the corresponding target storage location heat level according to the updated heat of the target shelf; The storage location ID with the lowest cost and that is free is selected from all the storage location IDs corresponding to the target storage location heat level to complete the storage location allocation to the target shelf.

7. The method according to claim 1, characterized in that Also includes: The Redis database is used to store and read the popularity of the goods.

8. A shelf return device based on thermal analysis, characterized in that: include: a memory configured to store instructions; A processor is configured to call the instructions from the memory and implement the shelf return method based on thermal analysis according to any one of claims 1 to 7 when executing the instructions.

9. A computing device, characterized in that include: A shelf return device based on thermal analysis according to claim 8.

10. A machine-readable storage medium, characterized in that: The machine-readable storage medium stores instructions for causing a machine to execute the shelf return method based on thermal analysis according to any one of claims 1 to 7.

Images