Determination method and determination device for inventory apron efficiency parameters and electronic equipment

Abstract

The embodiment of the invention discloses a determination method and a determination device for inventory apron efficiency parameters and electronic equipment. A specific implementation mode of the determination method comprises the steps that according to storage information of all warehouses, in-warehouse article territory effects of different articles in all the warehouses are determined, a reference data set is obtained, and the in-warehouse article territory effects represent the occupancy conditions of the articles on the storage areas of the warehouses; analyzing the data in the reference data set, and checking whether the data accords with preset data distribution or not; and in response to the conformity with the preset data distribution, sampling determination is carried out on related parameters influencing the inventory territory efficiency according to the reference data set, and the inventory territory efficiency represents the utilization condition of the warehouse storage area. The implementation mode is related to a warehouse management technology, and the existing data can be used for testing the hypothetical data distribution, so that sampling estimation of the related parameters of the inventory floor effect is carried out. Therefore, while the accuracy of the sampled data is ensured, the data volume of related parameters can be greatly increased.

Description

Technical Field

[0001] Embodiments of the present disclosure relate to the technical field of warehouse management, and more particularly to a method, apparatus, and electronic device for determining inventory floor efficiency parameters. Background Art

[0002] In recent years, with the advancement of the digitalization process of the supply chain, inventory, as a core scenario in supply chain planning, is particularly important for estimating various inventory parameter indicators. For example, floor efficiency generally refers to the value generated per square meter of a warehouse, that is, it is used to measure the efficiency of the warehouse area. In the supply chain business scenario, if the floor efficiency of items can be compared horizontally, the overall floor efficiency can be further analyzed and improved.

[0003] The above information disclosed in this background art section is only used to enhance the understanding of the background of the inventive concept, and thus, it may include information that does not form the prior art known to those of ordinary skill in the art in this country. Summary of the Invention

[0004] This section of the present disclosure is used to briefly introduce concepts that will be described in detail in the subsequent Detailed Description section. This section of the present disclosure is not intended to identify the key features or essential features of the claimed technical solution, nor is it intended to limit the scope of the claimed technical solution.

[0005] Some embodiments of the present disclosure provide a method, apparatus, electronic device, computer-readable medium, and computer program product for determining inventory floor efficiency parameters to solve one or more of the technical problems mentioned in the above Background Art section.

[0006] In a first aspect, some embodiments of the present disclosure provide a method for determining inventory floor efficiency parameters, including: determining the in-warehouse item floor efficiency of different items in each warehouse based on the storage information of each warehouse to obtain a reference data set, where the in-warehouse item floor efficiency represents the occupancy of the warehouse storage area by the item; analyzing the data in the reference data set to check whether it conforms to a preset data distribution; in response to conforming to the preset data distribution, sampling and determining relevant parameters affecting inventory floor efficiency based on the reference data set, where the inventory floor efficiency represents the utilization of the warehouse storage area.

[0007] In some embodiments, analyzing the data in the reference data set to check whether it conforms to a preset data distribution includes: for each in-warehouse item floor efficiency data in the reference data set, taking the logarithm of the data and performing normalization processing on the logarithmized data; using a normality test method to perform a normal distribution test on the normalized data.

[0008] In some embodiments, according to a reference data set, relevant parameters affecting inventory floor efficiency are sampled and determined, including: setting an initial state and a prior distribution of relevant parameters affecting inventory floor efficiency; and for each inventory floor efficiency parameter, taking the data average value of the reference data set as the first sampling value of the inventory floor efficiency parameter, and using the Monte Carlo Markov Chain algorithm to determine the next sampling value of the inventory floor efficiency parameter for state transition.

[0009] In some embodiments, sampling and determining relevant parameters affecting inventory floor efficiency further includes: determining the probability difference between the previous sampling value and the next sampling value of the inventory floor efficiency parameter; determining whether to retain the next sampling value according to the comparison result between the probability difference and a random number threshold; in response to determining to retain the next sampling value, determining that the inventory floor efficiency parameter has completed a state transition, and performing state transition on other inventory floor efficiency parameters among each inventory floor efficiency parameter.

[0010] In some embodiments, the method further includes: in response to determining that each inventory floor efficiency parameter has completed a state transition, counting that the Monte Carlo Markov Chain algorithm has completed one sampling; in response to determining that the Monte Carlo Markov Chain algorithm has completed a preset number of samplings, ending the parameter sampling, and taking the target sampling result as the target sampling value of each inventory floor efficiency parameter.

[0011] In some embodiments, according to the storage information of each warehouse, the in-warehouse item floor efficiency of different items in each warehouse is determined, including: for each item stored in the same warehouse, counting the total volume of the item, and determining the in-warehouse item floor efficiency of the item according to the total volume of the item and the total storage area of the warehouse.

[0012] In some embodiments, the method further includes: statistically analyzing each inventory floor efficiency parameter determined by sampling to determine the data distribution of each inventory floor efficiency parameter; based on the comparison result between each inventory floor efficiency parameter, determining an optimization method for warehouse storage management to improve the utilization rate of the warehouse storage area.

[0013] In a second aspect, some embodiments of the present disclosure provide an apparatus for determining inventory floor efficiency parameters, including: a reference data generation unit configured to determine the in-warehouse item floor efficiency of different items in each warehouse according to the storage information of each warehouse to obtain a reference data set, where the in-warehouse item floor efficiency represents the occupancy of the warehouse storage area by the item; a distribution inspection unit configured to analyze the data in the reference data set to check whether it conforms to a preset data distribution; a parameter sampling unit configured to, in response to conforming to the preset data distribution, sample and determine relevant parameters affecting inventory floor efficiency according to the reference data set, where the inventory floor efficiency represents the utilization of the warehouse storage area.

[0014] In some embodiments, the distribution inspection unit is further configured to take the logarithm of the in-warehouse item floor efficiency data in the reference dataset for each item, and perform normalization processing on the logarithmized data; and use a normality test method to perform a normal distribution test on the normalized data.

[0015] In some embodiments, the parameter sampling unit is further configured to set the initial state and prior distribution of the relevant parameters affecting the inventory floor efficiency; and for each inventory floor efficiency parameter, use the data average value of the reference dataset as the first sampling value of the inventory floor efficiency parameter, and use the Monte Carlo Markov chain algorithm to determine the next sampling value of the inventory floor efficiency parameter for state transition.

[0016] In some embodiments, the parameter sampling unit is further configured to determine the probability difference between the previous sampling value and the next sampling value of the inventory floor efficiency parameter; determine whether to retain the next sampling value according to the comparison result between the probability difference and the random number threshold; in response to determining to retain the next sampling value, determine that the inventory floor efficiency parameter has completed a state transition, and perform state transition on other inventory floor efficiency parameters among the inventory floor efficiency parameters.

[0017] In some embodiments, the determination device further includes a sampling end unit, configured to count that the Monte Carlo Markov chain algorithm has completed one sampling in response to determining that each inventory floor efficiency parameter has completed a state transition; end parameter sampling in response to determining that the Monte Carlo Markov chain algorithm has completed a preset number of samplings, and use the target sampling result of the target number of samplings as the target sampling value of each inventory floor efficiency parameter.

[0018] In some embodiments, the reference data generation unit is further configured to count the total volume of each item stored in the same warehouse, and determine the in-warehouse item floor efficiency of the item according to the total volume of the item and the total storage area of the warehouse.

[0019] In some embodiments, the determination device further includes a management optimization unit, configured to perform statistical analysis on each inventory floor efficiency parameter determined by sampling to determine the data distribution of each inventory floor efficiency parameter; and determine an optimization method for warehouse storage management based on the comparison result between each inventory floor efficiency parameter to improve the utilization rate of the warehouse storage area.

[0020] In a third aspect, some embodiments of the present disclosure provide an electronic device, including: one or more processors; a storage device having one or more programs stored thereon, and when the one or more programs are executed by the one or more processors, the one or more processors implement the determination method described in any implementation manner of the first aspect above.

[0021] Fourthly, some embodiments of the present disclosure provide a computer-readable medium, on which a computer program is stored. When the computer program is executed by a processor, the determination method described in any implementation manner of the first aspect above is implemented.

[0022] Fifthly, some embodiments of the present disclosure provide a computer program product, including a computer program. When the computer program is executed by a processor, the determination method described in any implementation manner of the first aspect above is implemented.

[0023] The above embodiments of the present disclosure have the following beneficial effects: The determination method of the inventory floor efficiency parameter in some embodiments of the present disclosure can effectively increase the data volume of the inventory floor efficiency parameter and reduce the data acquisition cost. Specifically, first, the original storage information of the warehouse can be used to obtain a reference data set. These reference data are usually obtained through real statistics and can represent the real storage situation of each warehouse. Then, these reference data can be used to perform a test of the preset data distribution, that is, to test and obtain a probability distribution model that conforms to business cognition. That is to say, the distribution of the data is determined through real statistical data. This is beneficial to ensuring the accuracy of the determined data distribution model. Further, according to the reference data set and the determined data distribution model, random sampling of the inventory floor efficiency-related parameters can be performed. In this way, while effectively increasing the data volume of the inventory floor efficiency parameter and reducing the data acquisition cost, the accuracy of the sampled data can also be ensured, that is, it is relatively close to the real data distribution. Furthermore, the application scope of the method can be expanded. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Combined with the drawings and referring to the following specific embodiments, the above and other features, advantages and aspects of the embodiments of the present disclosure will become more obvious. Throughout the drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and the elements and elements are not necessarily drawn to scale.

[0025] Figure 1 is a flowchart of some embodiments of the determination method of the inventory floor efficiency parameter of the present disclosure;

[0026] Figure 2 is a flowchart of some other embodiments of the determination method of the inventory floor efficiency parameter of the present disclosure;

[0027] Figure 3A and Figure 3B is a statistical analysis schematic diagram of some embodiments of the inventory floor efficiency parameter;

[0028] Figure 4 is a schematic structural diagram of some embodiments of the determination device of the inventory floor efficiency parameter of the present disclosure;

[0029] Figure 5It is a schematic structural diagram of an electronic device suitable for implementing some embodiments of the present disclosure. Detailed implementation manners

[0030] Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although some embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. On the contrary, these embodiments are provided to more thoroughly and completely understand the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes and are not used to limit the protection scope of the present disclosure.

[0031] In addition, it should be noted that for the sake of convenience of description, only the parts related to the relevant invention are shown in the drawings. Without conflict, the embodiments in the present disclosure and the features in the embodiments can be combined with each other.

[0032] It should be noted that the concepts such as "first" and "second" mentioned in the present disclosure are only used to distinguish different devices, modules or units, and are not used to limit the order of functions performed by these devices, modules or units or their interdependent relationships.

[0033] It should be noted that the modifications of "one" and "multiple" mentioned in the present disclosure are illustrative rather than restrictive. Those skilled in the art should understand that unless otherwise clearly indicated in the context, it should be understood as "one or more".

[0034] The present disclosure will be described in detail below with reference to the drawings and in combination with embodiments.

[0035] Figure 1 Flow 100 of some embodiments of a method for determining the inventory floor efficiency parameter according to the present disclosure is shown. The determination method includes the following steps:

[0036] Step 101, determine the in-warehouse item floor efficiency of different items in each warehouse according to the storage information of each warehouse, and obtain a reference data set.

[0037] In some embodiments, the execution entity (such as a server) of the method for determining the inventory floor efficiency parameter can obtain the storage information of each warehouse through a wired connection method or a wireless connection method. For example, the execution entity can obtain the storage information of the warehouse specified by the user from the warehouse management system. For another example, the execution entity can obtain the storage information of each warehouse according to the path specified by the user. Among them, the storage information is usually used to represent the information of the items stored in the warehouse. For example, the storage information may include at least one of the following: warehouse identifier (such as ID, Identity Document), total storage area of the warehouse, item (commodity) identifier (such as SKU, Stock Keeping Unit, minimum inventory unit), item volume, storage location, and so on.

[0038] In some embodiments, the execution entity can determine the in-warehouse item floor efficiency of different items in each warehouse according to the storage information of each warehouse. And these in-warehouse item floor efficiencies can be used as reference data to obtain a reference data set. As an example, first, the required data can be screened out from the storage information. Then, the screened-out data can be used to calculate the in-warehouse item floor efficiency of each item in different warehouses. Among them, the in-warehouse item floor efficiency can be used to characterize the occupancy of the storage area of the warehouse by the item. For example, for the items in the same warehouse, the total volume of the same item in the warehouse and the storage area occupied by the item can be calculated. Then, the quotient of the two can be used as the in-warehouse item floor efficiency of the item. The same item here can be an item with the same item ID or the same type (such as the classification method is not limited).

[0039] It should be noted that in actual business, the problem of incomplete data is often faced. Business personnel usually only count the volume of the commodity, but do not count the actual floor area of the commodity. So usually, the above method cannot be used to directly calculate the specific floor efficiency of the commodity. In addition, the statistical accuracy or precision of these data is often limited.

[0040] Therefore, in some embodiments, for each item stored in the same warehouse, the execution entity can count the total volume of the item. And obtain the total storage area of the warehouse where it is located. In this way, the in-warehouse item floor efficiency of the item can be determined according to the total volume of the item and the total storage area of the warehouse. For example, the quotient of the total volume and the total storage area can be used as the in-warehouse item floor efficiency of the item. For another example, when the items are stored, they are usually stacked. That is to say, the actual floor area of the item is generally smaller than the total volume. At this time, the total volume can be multiplied by a coefficient, and then the quotient with the total storage area is calculated. The coefficient here can be set according to requirements, such as being determined according to the volume level.

[0041] In some embodiments, according to the in-warehouse item floor efficiency of different items in different warehouses, the following reference dataset can be obtained. Among them, the rows are item identifiers, the columns are warehouse identifiers, and NaN indicates null.

[0042]

[0043] Step 102: Analyze the data in the reference dataset to check whether it conforms to a preset data distribution.

[0044] In some embodiments, the execution entity can analyze the data in the reference dataset obtained in step 101 to check whether it conforms to a preset data distribution. Among them, the preset data distribution can be set according to the actual situation, such as normal distribution, exponential distribution, etc.

[0045] For example, in the data example shown in the above table, there are a total of i = N warehouses and j = M items, and their values are the in-warehouse item floor efficiency P ij . Existing research and business experience show that the in-warehouse item floor efficiency P ij is a random variable, usually conforming to a lognormal distribution, and its probability density expression is as follows:

[0046]

[0047] where x represents the value of the in-warehouse item floor efficiency; a i represents the warehouse floor efficiency management ability (which can also be understood as the floor efficiency control ability of the warehouse administrator); b j represents the item floor efficiency attribute (determined by the physical properties of the item itself); σ j represents the mean of the distribution of the in-warehouse item floor efficiency random variable of an item, which is jointly determined by a j and b j ; σ is the floor efficiency variance parameter, representing the floor efficiency difference value of the item under different warehouses, which is determined by the physical properties of the item itself; π represents pi.

[0048] Here, a hypothesis test can be performed on the distribution of the in-warehouse item floor efficiency of all warehouses. For example, for the in-warehouse item floor efficiency data in the reference dataset, first, the logarithm of these data can be taken, such as lnP ij . Then, the logarithmized data can be standardized. For example, the data can be subtracted from the overall mean and then divided by the overall variance. The overall mean and overall variance here are obtained by taking the mean and variance of the logarithmized data as a whole. After that, a normality test method can be used to perform a normal distribution test on the standardized data. The normality test method here is also not limited, such as including but not limited to the normal probability paper method, skewness-kurtosis test method, etc.

[0049] It can be understood that if the original hypothesis is that the data distribution conforms to the normal distribution. After testing, if the original hypothesis is not rejected, it means that the data distribution is relatively close to the normal distribution. At this time, step 103 can be continued. On the contrary, it can be shown that the data distribution does not conform to the normal distribution.

[0050] Step 103, in response to conforming to the preset data distribution, sample and determine the relevant parameters affecting the inventory floor efficiency according to the reference data set.

[0051] In some embodiments, if it is determined through the test in step 102 that the data in the reference data set conforms to the preset data distribution, the execution entity can perform sampling estimation of the inventory floor efficiency parameters. That is, sample and determine the relevant parameters affecting the inventory floor efficiency according to the reference data set. Among them, the inventory floor efficiency can be used to characterize the utilization of the warehouse storage area. For example, the inventory floor efficiency can be the value generated per square meter of the warehouse, that is, to measure the efficiency of the warehouse area. And the inventory floor efficiency parameters are usually the factor parameters that mainly affect the inventory floor efficiency. For example, it can include at least one of the following: the warehouse floor efficiency management ability, the item floor efficiency attribute, and the floor efficiency variance of the item. For example, according to the preset inventory floor efficiency parameter table, data related to the parameters in the table can be selected from the reference data set. Or, the Markov Chain Monte Carlo method can be used to sample and determine the relevant parameter data from the reference data set.

[0052] It should be noted that the Markov Chain Monte Carlo method (MCMC) emerged in the early 1950s. Generally, it is a Monte Carlo method (Monte Carlo) simulated by a computer under the Bayesian theory framework. This method introduces the Markov process into the Monte Carlo simulation to achieve a dynamic simulation where the sampling distribution changes as the simulation progresses, making up for the defect that the traditional Monte Carlo integration can only perform static simulation. The MCMC method usually uses the Monte Carlo integration of the Markov chain. Its basic idea is: construct a Markov chain whose stationary distribution is the posterior distribution of the parameter to be estimated, generate samples of the posterior distribution through this Markov chain, and perform Monte Carlo integration based on the samples (effective samples) when the Markov chain reaches the stationary distribution.

[0053] As an example, first, the execution entity can set the initial state and prior distribution of the relevant parameters affecting the inventory floor efficiency. For example, the initial value of the warehouse floor efficiency management ability can be 0, and the prior distribution is the standard normal distribution. The initial value of the item floor efficiency attribute can be 0, and the prior distribution is the standard normal distribution. And the initial value of the floor efficiency variance parameter can be 1, and the prior distribution is the lognormal distribution.

[0054] Next, for each inventory turnover efficiency parameter, the data average value of the reference data set can be used as the first sampling value of the inventory turnover efficiency parameter. Also, the Monte Carlo Markov Chain algorithm can be used to determine the next sampling value of the inventory turnover efficiency parameter for state transition. Specifically, for each inventory turnover efficiency parameter, the probability difference between the previous sampling value and the next sampling value of the inventory turnover efficiency parameter can be determined. Then, based on the comparison result between the probability difference and the random number threshold, it can be determined whether to retain the next sampling value. If the probability difference is less than the random number threshold, it will be retained. If the next sampling value is retained, it can be determined that the inventory turnover efficiency parameter has completed a state transition.

[0055] It should be noted that when using the MCMC method, the construction of the Markov chain transition kernel is crucial. Different methods for constructing the transition kernel will result in different MCMC methods. There are mainly two commonly used MCMC methods: the Metropolis-Hastings (M-H) algorithm and Gibbs sampling. The M-H algorithm usually uses a symmetric proposal distribution to generate a potential transition point, and then decides whether to transfer to this potential point according to a specific acceptance-rejection method. The Gibbs algorithm is often a special M-H algorithm. For a multi-dimensional random variable, when generating the i-th component of the variable, the Gibbs algorithm selects the proposal distribution as the conditional distribution of the i-th component based on all other components.

[0056] In some embodiments, for each of the above inventory turnover efficiency parameters, the execution entity can construct a Markov chain respectively (i.e., three). And these Markov chains can be sampled and estimated simultaneously.

[0057] Optionally, the execution entity can also use the Gibbs algorithm to sample and estimate the Markov chains corresponding to each inventory turnover efficiency parameter in sequence. As an example, the state transition can be first performed in the dimension of warehouse turnover efficiency management ability, using the sampling value of the warehouse turnover efficiency management ability of this state as the mean. And using the normal distribution with a variance of 1 as the transition sampling probability function, and taking the randomly generated value as the next transition state (i.e., the next sampling value). Then, the logarithmic probability difference before and after the transition can be calculated. After obtaining the probability difference, it can be decided whether to retain the sampling result and complete the state transition through the M-H method (i.e., the random number threshold). Then, the state transition can be performed in the commodity dimension, using the sampling values of the item turnover efficiency attribute and the turnover efficiency variance parameter of this state as the means respectively. Also using the normal distribution with a variance of 1 as the transition sampling probability function. Consistent with the process in the dimension of warehouse turnover efficiency management ability, the logarithmic probability difference of the transition is also calculated, and the random number threshold is used to decide whether to accept the sampling value.

[0058] That is to say, the execution entity can adopt the Gibbs algorithm to sample and estimate each inventory floor efficiency parameter in a certain order. That is, when a certain inventory floor efficiency parameter completes a state transition, the execution entity can continue the state transition for other inventory floor efficiency parameters among the inventory floor efficiency parameters according to the set order. Here, the other inventory floor efficiency parameters usually refer to the remaining inventory floor efficiency parameters except for the inventory floor efficiency parameter that has just (the previous one) completed the state transition. This sampling method can reduce the amount of data to be processed, thus helping to improve the sampling efficiency.

[0059] In some embodiments, the execution entity can adopt a variety of convergence diagnosis methods to determine whether to stop sampling, such as the ratio diagnosis method, Geweke Test (usually composed of a series of Z-tests), etc. Optionally, in order to further improve the sampling efficiency, the sampling times can also be used to judge the stop of sampling. It can be understood that a Markov chain often needs to go through multiple state transition processes to reach a stable state. Only at this time is the sampling relatively close to the true distribution. This process is called burn in. Here, the length of the sampled Markov chain can be set to 15,000. That is, repeat the above state transition process 15,000 times.

[0060] In some application scenarios, for the above Gibbs sampling algorithm, the execution entity can complete one sampling of the Monte Carlo Markov chain algorithm when it is determined that each inventory floor efficiency parameter has completed a state transition. And when it is determined that the Monte Carlo Markov chain algorithm has completed sampling a preset number of times (such as 15,000 times), the parameter sampling can be ended. In addition, in order to make the sampling result closer to the true distribution, the target sub-sampling result here can be used as the target sampling value of each inventory floor efficiency parameter. For example, generally, burn in can be achieved by discarding a certain number of sampling results in the early stage. Here, it can be considered to discard the first 3,000 sampling results and retain the last 12,000 sampling results as the sampling results of the final three parameters.

[0061] It should be noted that in the existing business scenarios, the expression "floor efficiency parameter statistic = volume of the product / area occupied by the product" is usually used. However, the inventor found that the actual business often faces the problem of incomplete data. Business personnel usually only count the volume of the product and do not count the actual floor area occupied by the product. Therefore, the specific floor efficiency of the product cannot be directly calculated. At the same time, because the products in different warehouses are different, the directly calculated total floor efficiency does not necessarily represent the actual floor efficiency management ability of the warehouse. Therefore, the prior art can also adopt the relevant gradient descent method to solve the floor efficiency parameter of each product through the total warehouse area and the specific volume of the product.

[0062] However, for this method, the inventors also found that due to the limitations of the statistical accuracy of the original data itself and the limited number of warehouse and commodity data in the actual scenario, there is a high cost of data acquisition. This also leads to difficulties in optimizing the solution algorithm, large errors in the solution results, and limited application value.

[0063] Based on this, the method for determining the inventory floor efficiency parameter in some embodiments of the present disclosure can effectively increase the amount of data of the inventory floor efficiency parameter and reduce the data acquisition cost. Specifically, first, the original storage information of the warehouse can be used to obtain a reference data set. These reference data are usually obtained through real statistics and can represent the real storage situation of each warehouse. Then, these reference data can be used to perform a test of the preset data distribution, that is, to test and obtain a probability distribution model that conforms to business cognition. That is to say, the distribution of the data is determined through real statistical data. This is conducive to ensuring the accuracy of the determined data distribution model. Further, according to the reference data set and the determined data distribution model, random sampling of the parameters related to the inventory floor efficiency can be performed. In this way, while effectively increasing the amount of data of the inventory floor efficiency parameter and reducing the data acquisition cost, the accuracy of the sampled data can also be ensured, that is, it is relatively close to the real data distribution. Furthermore, the application scope of the method can be expanded.

[0064] Continue to refer to Figure 2 , which shows the process 200 of another embodiment of the method for determining the inventory floor efficiency parameter according to the present disclosure. The determination method may further include the following steps:

[0065] Step 201, perform statistical analysis on each inventory floor efficiency parameter determined by sampling to determine the data distribution of each inventory floor efficiency parameter.

[0066] In some embodiments, the execution subject of the method for determining the inventory floor efficiency parameter may also perform statistical analysis on each inventory floor efficiency parameter determined by sampling in the Figure 1 embodiment to determine the data distribution of each inventory floor efficiency parameter. The statistical analysis method here can be set according to the actual situation. For example, the mean, variance, etc. of the sampled values of each inventory floor efficiency parameter can be determined. In addition, various statistical charts, such as histograms, curve charts, etc., can also be used to analyze and display the data distribution of the inventory floor efficiency parameter.

[0067] Step 202, based on the comparison results between the inventory floor efficiency parameters, determine the optimization method for warehouse storage management to improve the utilization rate of the warehouse storage area.

[0068] In some embodiments, the execution subject may also perform comparative analysis on each inventory floor efficiency parameter. Furthermore, based on the comparison results between the inventory floor efficiency parameters, the optimization method for warehouse storage management can be determined to improve the utilization rate of the warehouse storage area, that is, to improve the inventory floor efficiency.

[0069] As an example, such as Figure 3A The comparative analysis chart of the warehouse floor efficiency management ability shown. By calculating the mean variance and frequency statistics of the Markov chain (i.e., the sampled values) of the warehouse floor efficiency management ability, the results after Monte Carlo simulation of the floor efficiency management ability of each warehouse can be obtained. This parameter usually eliminates the influence of different inventory items on the specific floor efficiency. The mean of the sampling results can be used as an estimate of the warehouse floor efficiency management ability for horizontal comparison of the management abilities of different warehouses. For warehouses with a relatively small mean of the sampling results of this parameter, the inventory floor efficiency management can be further analyzed and optimized. Figure 3A The sampling results of two certain warehouses are extracted, the frequencies are counted and plotted as a histogram. It can be seen from the histogram that the floor efficiency management ability of Warehouse 2 is better than that of Warehouse 1.

[0070] In addition, for the item floor efficiency attribute. This parameter usually eliminates the influence of different inventory management abilities on the specific floor efficiency. The mean of the sampling results can be used as an estimate of the item floor efficiency attribute for horizontal comparison of the floor efficiency attributes of different items. The specific comparison method is the same as that of the inventory floor efficiency management ability and will not be elaborated here.

[0071] Another example is Figure 3B The comparative analysis chart of the item floor efficiency variance shown. This parameter compares the degree of difference in the floor efficiency of items in different warehouses. The larger the mean of the distribution of this parameter, it usually indicates that the item is more likely to be an item with an irregular shape. The floor efficiency difference in different warehouses is generally large, and the improvement of the floor efficiency of such items can be focused on. From Figure 3B it can be seen that the mean of the floor efficiency variance of Product b is larger than that of Product a.

[0072] It should be noted that Figure 3A and Figure 3B are both frequency statistical charts of the sampling results. Among them, the abscissa represents the value of the target parameter sampling. The ordinate represents the frequency of the sampling values in the corresponding interval after n samplings.

[0073] The method for determining the inventory floor efficiency parameter of the embodiments of the present disclosure further enriches and improves the statistical analysis of the sampling results of the inventory floor efficiency parameter. Through corresponding processing, analysis, display, etc. of the sampling results in this embodiment, the distribution of the simulated sampling of the inventory floor efficiency related parameters can be obtained. By comparing the parameter statistical values of different warehouses and items, we can obtain corresponding business optimization conclusions. Even a statistical conclusion on whether there is a significant difference between the two in a certain parameter can be obtained. Thereby, it helps to improve and enhance the utilization rate of the warehouse storage area. While the commonly used gradient solving algorithm usually can only solve the parameters under optimized conditions and cannot estimate the distribution of the parameters, and cannot fully explore the information behind the data.

[0074] Further reference is made to Figure 4 , in implementation of the determination method as described above Figure 1 、 2 , some embodiments of an apparatus for determining inventory floor efficiency parameters are provided by the present disclosure. These embodiments of the determination apparatus correspond to those embodiments of the determination methods as shown in Figure 1 、 2 . The apparatus for determining inventory floor efficiency parameters can be specifically applied to various electronic devices.

[0075] As shown in Figure 4 , an apparatus 400 for determining inventory floor efficiency parameters in some embodiments may include: a reference data generation unit 401 configured to determine the in-warehouse item floor efficiency of different items in each warehouse according to the storage information of each warehouse, so as to obtain a reference data set, where the in-warehouse item floor efficiency characterizes the occupancy of the warehouse storage area by the items; a distribution inspection unit 402 configured to analyze the data in the reference data set to check whether it conforms to a preset data distribution; and a parameter sampling unit 403 configured to, in response to conforming to the preset data distribution, sample and determine the relevant parameters affecting the inventory floor efficiency according to the reference data set, where the inventory floor efficiency characterizes the utilization of the warehouse storage area.

[0076] In some embodiments, the distribution inspection unit 402 may be further configured to, for each in-warehouse item floor efficiency data in the reference data set, take the logarithm of the data and perform normalization processing on the logarithmized data; and use a normality test method to perform a normal distribution test on the normalized data.

[0077] In some embodiments, the parameter sampling unit 403 may be further configured to set the initial state and prior distribution of the relevant parameters affecting the inventory floor efficiency; and for each inventory floor efficiency parameter, use the data average value of the reference data set as the first sampling value of the inventory floor efficiency parameter, and use the Monte Carlo Markov chain algorithm to determine the next sampling value of the inventory floor efficiency parameter for state transition.

[0078] In some embodiments, the parameter sampling unit 403 may also be further configured to determine the probability difference between the previous sampling value and the next sampling value of the inventory floor efficiency parameter; determine whether to retain the next sampling value according to the comparison result between the probability difference and a random number threshold; in response to determining to retain the next sampling value, determine that the inventory floor efficiency parameter has completed a state transition, and perform state transition on other inventory floor efficiency parameters among the inventory floor efficiency parameters.

[0079] In some embodiments, the determining device 400 may further include a sampling end unit (not shown in the figure), configured to, in response to determining that each inventory floor efficiency parameter has completed a state transition, count that the Monte Carlo Markov chain algorithm has completed one sampling; in response to determining that the Monte Carlo Markov chain algorithm has completed a preset number of samplings, end parameter sampling, and use the target sub-sampling result as the target sampling value of each inventory floor efficiency parameter.

[0080] In some embodiments, the reference data generation unit 401 may be further configured to, for each item stored in the same warehouse, count the total volume of the item, and determine the in-warehouse item floor efficiency of the item according to the total volume of the item and the total storage area of the warehouse.

[0081] In some embodiments, the determining device 400 may further include a management optimization unit (not shown in the figure), configured to perform statistical analysis on each inventory floor efficiency parameter determined by sampling, determine the data distribution of each inventory floor efficiency parameter; based on the comparison result between each inventory floor efficiency parameter, determine an optimization method for warehouse storage management to improve the utilization rate of the warehouse storage area.

[0082] It can be understood that the various units described in the determining device 400 of the inventory floor efficiency parameter correspond to the respective steps in the method described in the reference Figure 1 、 2 Therefore, the operations, features, and beneficial effects described above for the method also apply to the determining device 400 and the units included therein, and will not be elaborated here.

[0083] Next, refer to Figure 5 , which shows a schematic structural diagram of an electronic device 500 suitable for implementing some embodiments of the present disclosure. Figure 5 The electronic device shown is only an example and should not impose any limitations on the functions and usage scope of the embodiments of the present disclosure.

[0084] As Figure 5 shown, the electronic device 500 may include a processing device 501 (such as a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM) 502 or the program loaded from the storage device 508 into the random access memory (RAM) 503. In the RAM 503, various programs and data required for the operation of the electronic device 500 are also stored. The processing device 501, the ROM 502, and the RAM 503 are connected to each other through a bus 504. The input / output (I / O) interface 505 is also connected to the bus 504.

[0085] Typically, the following devices can be connected to the I / O interface 505: an input device 506 including, for example, a touch screen, a touchpad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 507 including, for example, a speaker, a vibrator, etc.; a storage device 508 including, for example, a disk, a hard disk, etc.; and a communication device 509. The communication device 509 can allow the electronic device 500 to communicate with other devices wirelessly or wiredly to exchange data. Although Figure 5 the electronic device 500 with various devices is shown, it should be understood that it is not required to implement or have all the shown devices. Instead, more or fewer devices can be implemented or had. Figure 5 Each block shown in

[0086] can represent one device or, as needed, multiple devices.

[0087] It should be noted that the computer-readable media described in some embodiments of the present disclosure may be a computer-readable signal medium, a computer-readable storage medium, or any combination of the two. A computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above. More specific examples of the computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In some embodiments of the present disclosure, the computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In some embodiments of the present disclosure, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries computer-readable program code. Such a propagated data signal may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. The computer-readable signal medium may also be any computer-readable medium other than the computer-readable storage medium, and the computer-readable signal medium may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0088] In some embodiments, the client and the server may communicate using any currently known or future-developed network protocol such as HTTP (Hyper Text Transfer Protocol), and may be interconnected with digital data communication in any form or medium (e.g., a communication network). Examples of communication networks include local area networks ("LANs"), wide area networks ("WANs"), the Internet (e.g., the Internet), and end-to-end networks (e.g., ad hoc end-to-end networks), as well as any currently known or future-developed networks.

[0089] The above computer-readable medium may be included in the above electronic device; or it may exist independently without being assembled into the electronic device. The above computer-readable medium carries one or more programs, and when the one or more programs are executed by the electronic device, the electronic device is caused to: determine the in-warehouse item floor efficiency of different items in each warehouse according to the storage information of each warehouse, so as to obtain a reference data set, where the in-warehouse item floor efficiency represents the occupancy of the warehouse storage area by the items; analyze the data in the reference data set to check whether it conforms to a preset data distribution; in response to conforming to the preset data distribution, sample and determine the relevant parameters affecting the inventory floor efficiency according to the reference data set, where the inventory floor efficiency represents the utilization of the warehouse storage area.

[0090] In addition, computer program code for performing the operations of some embodiments of the present disclosure may be written in one or more programming languages or combinations thereof. The programming languages include object-oriented programming languages such as Java, Smalltalk, C++, and also include conventional procedural programming languages such as the "C" language or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, executed as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (for example, by using an Internet service provider to connect through the Internet).

[0091] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions, and operations of systems, methods, and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagram may represent a module, a program segment, or a part of code that contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than marked in the accompanying drawings. For example, two consecutive blocks shown may actually be executed substantially in parallel, and they may sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram and / or flowchart, and the combination of blocks in the block diagram and / or flowchart, may be implemented by a dedicated hardware-based system for performing the specified functions or operations, or may be implemented by a combination of dedicated hardware and computer instructions.

[0092] The units described in some embodiments of the present disclosure can be implemented in software or in hardware. The described units can also be provided in a processor. For example, it can be described as: A processor includes a reference data generation unit, a distribution inspection unit, and a parameter sampling unit. Among them, the names of these units do not constitute a limitation to the unit itself in some cases. For example, the reference data generation unit can also be described as "the unit for obtaining a reference data set".

[0093] The functions described above in this document can be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that can be used include: Field Programmable Gate Array (FPGA), Application Specific Integrated Circuit (ASIC), Application Specific Standard Product (ASSP), System on Chip (SOC), Complex Programmable Logic Device (CPLD), and so on.

[0094] Some embodiments of the present disclosure also provide a computer program product, including a computer program, which when executed by a processor, implements any one of the above methods for determining the inventory floor efficiency parameter.

[0095] The above description is only some preferred embodiments of the present disclosure and an explanation of the applied technical principles. Those skilled in the art should understand that the scope of the invention involved in the embodiments of the present disclosure is not limited to the technical solutions formed by the specific combination of the above technical features, and should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above inventive concept. For example, the technical solutions formed by mutually replacing the above features with the (but not limited to) technical features having similar functions disclosed in the embodiments of the present disclosure.

Claims

1. A method for determining inventory floor efficiency parameters, comprising: Based on the storage information of each warehouse, determine the in-warehouse item floor efficiency of different items in each warehouse to obtain a reference data set, where the in-warehouse item floor efficiency characterizes the occupancy of the warehouse storage area by the items; Analyze the data in the reference data set to check whether it conforms to a preset data distribution; In response to conforming to the preset data distribution, determine by sampling the relevant parameters affecting the inventory floor efficiency according to the reference data set, where the inventory floor efficiency characterizes the utilization of the warehouse storage area.

2. The determination method according to claim 1, wherein, The analyzing the data in the reference data set to check whether it conforms to a preset data distribution includes: For each in-warehouse item floor efficiency data in the reference data set, take the logarithm of the data and perform standardization processing on the logarithmized data; Use a normality test method to perform a normal distribution test on the standardized data.

3. The determination method according to claim 1, wherein, The determining by sampling the relevant parameters affecting the inventory floor efficiency according to the reference data set includes: Set the initial state and prior distribution of the relevant parameters affecting the inventory floor efficiency; and For each inventory floor efficiency parameter, take the average value of the data in the reference data set as the first sampling value of the inventory floor efficiency parameter, and use the Monte Carlo Markov chain algorithm to determine the next sampling value of the inventory floor efficiency parameter for state transition.

4. The determination method according to claim 3, wherein, The determining by sampling the relevant parameters affecting the inventory floor efficiency further includes: Determine the probability difference between the previous sampling value and the next sampling value of the inventory floor efficiency parameter; According to the comparison result between the probability difference and the random number threshold, determine whether to retain the next sampling value; In response to determining to retain the next sampling value, determine that the inventory floor efficiency parameter has completed a state transition, and perform state transitions on other inventory floor efficiency parameters among the various inventory floor efficiency parameters.

5. The determination method according to claim 3, wherein, The method further includes: In response to determining that all the inventory floor efficiency parameters have completed a state transition, count that the Monte Carlo Markov chain algorithm has completed one sampling; In response to determining that the Monte Carlo Markov chain algorithm has completed sampling a preset number of times, end the parameter sampling, and use the target sampling result of the target sampling times as the target sampling values of the various inventory floor efficiency parameters.

6. The determination method according to claim 1, wherein, The determining the in-warehouse item floor efficiency of different items in each warehouse based on the storage information of each warehouse includes: For each item stored in the same warehouse, count the total volume of the item, and determine the in-warehouse item floor efficiency of the item according to the total volume of the item and the total storage area of the warehouse.

7. The determination method according to any one of claims 1-6, wherein, The method further includes: Perform statistical analysis on the various inventory floor efficiency parameters determined by sampling to determine the data distribution of the various inventory floor efficiency parameters; Based on the comparison results among the various inventory floor efficiency parameters, determine an optimization method for warehouse storage management to improve the utilization rate of the warehouse storage area.

8. An apparatus for determining inventory floor efficiency parameters, comprising: A reference data generation unit, configured to determine the in-warehouse item floor efficiency of different items in each warehouse based on the storage information of each warehouse to obtain a reference data set, where the in-warehouse item floor efficiency characterizes the occupancy of the warehouse storage area by the items; A distribution test unit, configured to analyze the data in the reference data set to check whether it conforms to a preset data distribution; A parameter sampling unit, configured to sample and determine relevant parameters affecting inventory floor efficiency according to the reference data set in response to meeting a preset data distribution, wherein the inventory floor efficiency characterizes the utilization of the warehouse storage area.

9. An electronic device, comprising: One or more processors; A storage device on which one or more programs are stored, When the one or more programs are executed by the one or more processors, the one or more processors implement the determination method according to any one of claims 1-7.

10. A computer-readable medium having a computer program stored thereon, wherein, When the computer program is executed by a processor, the determination method according to any one of claims 1-7 is implemented.

11. A computer program product comprising a computer program which, when executed by a processor, implements the determination method according to any one of claims 1-7.

Images