Storage goods location management method and system

Abstract

The invention relates to the technical field of warehouse management, in particular to a warehouse goods allocation management method and system, and the method comprises the steps: training a prediction model through a training set; the training set comprises sales volume data and environment data of dairy products in multiple continuous years and quarters; inputting the sales volume data of the dairy product in the current time period and the future environment data of the future time period into the trained prediction model to output a sales volume prediction result of the future time period; according to the sales volume prediction result of the dairy products, carrying out pre-adjustment on storage goods locations; the scheme of the invention can reasonably arrange the storage location according to the sales prediction result of the dairy products.

Description

Technical Field

[0001] The present invention relates to the field of warehouse management technology, and more specifically, to a warehouse storage location management method and system. Background Art

[0002] The warehouse storage space management method is to manage the storage space of materials in the warehouse to improve space utilization, facilitate goods management, and improve inventory accuracy.

[0003] Warehouse storage management is closely related to product sales; that is, in the product sales process, sellers need to complete operations such as warehouse purchase, stocking, and replenishment before actual sales. The data for sellers to perform the above operations comes from future forecasts rather than actual values, so it is very important to predict product sales in the future.

[0004] Taking dairy products as an example, it is very important to predict the sales volume of dairy products. It can not only allocate dairy products with high predicted sales volume to storage locations that are easy to access, thereby improving operational efficiency, but also reasonably adjust inventory to avoid out-of-stock or backlogs. Using the predicted sales volume of dairy products can make warehouse storage location management more scientific and efficient, reduce costs, and improve benefits.

[0005] In the related technology, such as the patent document with authorization announcement number CN110555578B and name "A sales forecasting method and device", it discloses determining the number of lead time periods based on the sales time series and time series model corresponding to the product identification; inputting the sales time series and the environmental data of the corresponding time period into a machine learning algorithm to train the sales forecasting model; inputting the sales data, environmental data of the number of lead time periods and the environmental data of the next time period into the sales forecasting model to output the sales forecasting data of the next time period.

[0006] Although the above scheme takes environmental data into consideration, the loss function generally used in prediction is the mean square error loss function, which will fit all data evenly. However, since dairy product sales are easily affected by seasonal factors, the machine learning algorithm does not take seasonal changes into account, resulting in inaccurate model prediction results and the inability to reasonably manage storage space. Summary of the invention

[0007] The purpose of the present invention is to propose a warehouse storage location management method and system to solve the problem that product sales forecasting and, thus, reasonable warehouse storage location management cannot be performed in the prior art; to this end, the present invention provides solutions in the following two aspects.

[0008] In a first aspect, the present invention provides a storage space management method, comprising: The prediction model is trained using a training set; the training set includes sales data and environmental data of dairy products in each quarter of multiple consecutive years; Input the current time period sales data of dairy products and the future environmental data of the future time period into the trained prediction model to output the sales forecast results of the future time period; Make advance adjustments to warehouse storage space based on sales forecasts for dairy products; The loss function of the prediction model is obtained by weighting the square of the difference between the actual sales volume and the predicted value in the sales volume data using each loss weight; the loss weight is the product of the seasonal matching degree of each sales volume data and the trend degree of each actual sales volume in the corresponding sales volume data; The trend degree represents the actual sales volume difference change in the same quarter of any two years; The seasonal matching degree is the product of the change indexes of multiple regions; the change index for: ; , are the ath region in the i-th year and the The value of the kth parameter in the environmental data for the jth quarter of the year, is the linear normalization function, is the normalized value of the distribution volume of the ath region in the jth quarter of the ith year, is the number of parameter categories in the environmental data; The year is the last year in a series of consecutive years.

[0009] In the above scheme, by analyzing the changes in environmental data and sales data, the trend degree and seasonal matching degree can be obtained, and then the loss function of the prediction model can be improved to obtain a more accurate prediction model, realize the sales forecast of dairy products in the future, and then based on the sales forecast results, make more reasonable advance adjustments to the storage space.

[0010] Optionally, the distribution volume is the sales volume of a corresponding region in any quarter, and the sum of the distribution volumes of all regions in any quarter is the total sales volume of the corresponding quarter.

[0011] Optionally, the loss function for: ; In the formula, , are the loss weight and predicted value of the nth actual sales volume in the sales volume data of the jth quarter of the i-th year, respectively; is the nth actual sales volume in the sales volume data of the jth quarter of the i-th year; is the total number of sales data in the jth quarter; The total number of years for multiple consecutive years.

[0012] In the above scheme, by introducing the loss weight of each actual sales volume in each quarter, the learning of the subsequent trained prediction model for data points with high reference value can be improved, and the learning of data points with low reference value can be reduced.

[0013] Optionally, the trend for: ; is the nth actual sales volume in the sales volume data of the jth quarter of the i-th year; is the sales volume of the jth quarter in the i-th year. Actual sales volume, For the The nth actual sales volume in the jth quarter sales data of the year; For the The sales volume data for the jth quarter of the year Actual sales volume; is the total sales volume in the jth quarter of the i-th year; For the Total sales volume in the jth quarter of year; is a linear normalization function.

[0014] The above solution can reflect the real seasonal change trend by analyzing the sales volume difference in the same quarter of any two years.

[0015] Optionally, the specific process of making advance adjustments to storage locations based on the sales forecast results of dairy products is as follows: when a predicted value in the sales forecast results is greater than the target number of locations, and the number of shared goods in the storage locations at the time corresponding to the predicted value is available, the shared location information is allocated to dairy products; when all predicted values ​​in the sales forecast results are less than or equal to the target number of locations, there is no need to allocate storage locations; wherein, the storage locations include the target number of locations for dairy products and the number of shared locations.

[0016] The above scheme can reasonably adjust the storage space according to the sales forecast results.

[0017] Optionally, the prediction model is a random forest model.

[0018] Optionally, the specific process of training the prediction model is: The sales data of the first m quarters of dairy products in the training set and the environmental data of the m+1 quarter in multiple consecutive years are input into the prediction model, the sales data of the m+1 quarter is used as the label, and the loss between the output prediction value and the label is calculated to train the prediction model; Use gradient descent to adjust model parameters to minimize prediction error; Iteratively adjust the parameters of the prediction model until the loss is less than the set value or the set number of training times is reached, and finally a trained prediction model is obtained.

[0019] The above scheme improves the loss function so that the prediction model can focus more on learning data with high reference value during training, thereby improving the accuracy of subsequent predictions of the prediction model.

[0020] Optionally, the environmental data includes meteorological data, wherein the meteorological data is daily temperature, precipitation, wind speed, humidity, air pressure and air quality index of each year.

[0021] In a second aspect, a warehouse storage location management system includes: processor; The memory stores computer instructions for warehouse storage location management. When the computer instructions are executed by the processor, the system executes the above-mentioned warehouse storage location management method.

[0022] The beneficial effects of the present invention are: The solution of the present invention is mainly aimed at predicting the sales volume of dairy products that are highly affected by seasons, that is, by obtaining the seasonal matching degree of each sales volume data and the trend degree of each actual sales volume in each sales volume data, the loss weight of each actual sales volume is determined, and the loss function of the prediction model is obtained according to the loss weight to obtain a dairy product sales volume prediction result that is more in line with the season; compared with the existing model that uses the mean square error loss function, it can avoid fitting all data in a balanced manner and fit data with high reference value more effectively to improve the accuracy of the model prediction results, and provide more reasonable data support for the subsequent management of warehouse storage locations. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] By reading the following detailed description with reference to the accompanying drawings, the above and other objects, features and advantages of the exemplary embodiments of the present invention will become readily understood. In the accompanying drawings, several embodiments of the present invention are shown in an exemplary and non-limiting manner, and the same or corresponding reference numerals represent the same or corresponding parts, wherein: Figure 1 The following is a schematic diagram showing the steps of the storage location management method in this embodiment; Figure 2 The structural block diagram of the warehouse storage location management system in this embodiment is schematically shown. DETAILED DESCRIPTION

[0024] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0025] The scenario targeted by the present invention is the storage location management of products, wherein the products may be any product among food, daily necessities, household appliances, etc. Specifically, the present invention takes dairy products among foods as an example to introduce the storage location management method and system of the present invention.

[0026] Specifically, taking a certain type of dairy products as an example, the storage location management method in this embodiment is as follows: Figure 1 As shown, the following steps are included: Step S1, obtaining a training set. The training data set in this embodiment includes sales data and environmental data of dairy products in each quarter of multiple consecutive years.

[0027] The sales data is the sales history data of a certain type of dairy product in recent years. One set of sales data corresponds to one quarter. The sales data in each quarter includes multiple actual sales, which are the total sales in a set time period. The set time period can be one day or several consecutive days.

[0028] The environmental data includes meteorological data; specifically, meteorological data includes temperature, precipitation, wind speed, humidity, air pressure, air quality index, etc. The above meteorological data can be obtained from the Meteorological Bureau. Specifically, the meteorological data website obtains the six parameters of the daily average temperature, precipitation, wind speed, humidity, air pressure, and air quality index of the provincial capital cities in each dairy region in each quarter in the past three years to construct meteorological data and obtain meteorological data for each region in recent years.

[0029] The multiple consecutive years in this embodiment may be 3, 5, 10, etc. In this embodiment, the sales data of dairy products in each quarter for 3 consecutive years in the historical data are obtained.

[0030] The multiple consecutive years in this embodiment are selected from several years before the current year of sales to be predicted. For example, when the sales data of the past three years are collected as the training set, since the sales data of the third year are close to the date to be predicted in the current year, the sales data are generally similar to the sales data of the date to be predicted in terms of weather impact, and are more referenceable.

[0031] It should be noted that the above environmental data is collected because environmental data has an impact on the sales of dairy products, and the weather conditions in the same quarter of different years may also be different, so the sales data in different quarters may also be different.

[0032] Of course, as another implementation method, the environmental data may also include sales environmental data.

[0033] Among them, sales environment data include price, whether there is a promotion, the intensity of the promotion, whether there are gifts, user views, user praise rate, user negative review rate, number of user comments, sales in adjacent areas, etc.

[0034] It should be noted that since dairy products are highly affected by seasons (for example, yogurt may be popular in spring, summer and autumn, ice cream in summer, milk powder in winter, etc.), the environmental data in this embodiment only considers meteorological data.

[0035] Step S2: training the constructed prediction model using the training set.

[0036] The prediction model constructed above can be a random forest model or a support vector machine model.

[0037] In this embodiment, taking the random forest model as an example, the total number of decision trees in the random forest model can be 200. The purpose of using the random forest model is that since the dairy product sales data is affected by various factors and has a complex nonlinear relationship with time, the random forest model can capture the nonlinear relationship in the data and is suitable for complex data patterns, so the random forest model is selected for prediction.

[0038] In this embodiment, the process of obtaining the loss function of the prediction model is: First, obtain the seasonal matching degree of each sales data.

[0039] Due to the obvious seasonal changes in the sales data of dairy products, that is, when the weather conditions in the same quarter of different years are slightly different, the possibility of the quarterly sales change pattern being the same is higher, and the sales data with consistent change trends are more worthy of reference; when the difference is large, the possibility of the quarterly sales change pattern being the same is not high; at the same time, the historical year closest to the current year may have the highest reference value, while the years farther away may have a lower reference value, so it is necessary to obtain the seasonal matching degree of each sales data.

[0040] Specifically, the seasonal matching degree of sales data in the jth quarter of the i-th year is The calculation formula is as follows: ; Among them, ∏ is the multiplication symbol, is the change indicator of sales data of region a in the jth quarter of year i, and A is the total number of regions.

[0041] The change indicators are: ; , are the ath region in the i-th year and the The value of the kth parameter in the environmental data for the jth quarter of the year, is the linear normalization function, is the normalized value of the distribution volume of the ath region in the jth quarter of the ith year, is the number of parameter categories in the environmental data.

[0042] Among them, 2021 is the last year of a number of consecutive years; for example, when there are three consecutive years, it is the last year, such as the three consecutive years are 2021, 2022, and 2023, then the first year is the last year. The year is 2023.

[0043] The linear normalization function can normalize the maximum and minimum values.

[0044] in, Indicates that the ath region is in The value of the kth parameter in the environmental data of the jth quarter of the year is the same as the value of the parameter in the ath region in the The similarity of the kth parameter value of the environmental data in the jth quarter of the year, the higher the similarity, the closer the weather conditions of the ath region in the jth quarter of the ith year are to the local weather conditions of the corresponding quarter of the most recent year; the closer the weather conditions of the ath region in the jth quarter of the ith year are to the local weather conditions of the corresponding quarter of the most recent year, and the higher the sales volume of the ath region in the jth quarter of the ith year, the higher the possibility that the impact of the weather on sales in the jth quarter of the ith year and the corresponding quarter of the most recent year are similar, and the higher the seasonal matching degree.

[0045] The above distribution volume is the total sales volume of each region in each quarter in different years; the total sales volume of each region is then normalized to obtain the normalized value; the sum of the distribution volume of all regions in the same year and the same quarter is the total sales volume of the corresponding quarter.

[0046] The above normalization method adopts the maximum value normalization method. Specifically, the distribution volume of each region and each quarter is summarized and linearly normalized to obtain the normalized value of each region and each quarter.

[0047] Secondly, obtain the trend degree corresponding to each actual sales volume in each sales volume data.

[0048] Furthermore, in this embodiment, it is taken into consideration that when the sales volume change trend in the same quarter that is far away from the sales volume year to be predicted is very different from the sales volume change trend in the same quarter that is close to the sales volume year to be predicted, the sales volume fluctuation is higher than that in other quarters, resulting in a high possibility that the seasonal change trend is not obvious, which cannot reflect the real seasonal change trend and has a low reference value. Therefore, it is also necessary to obtain the seasonal trend degree of each sales series every day.

[0049] Specifically, the trend of the nth actual sales volume in the sales volume data of the jth quarter of the ith year is The calculation formula is as follows: ; is the nth actual sales volume in the sales volume data of the jth quarter of the i-th year; is the sales volume of the jth quarter in the i-th year. Actual sales volume, For the The nth actual sales volume in the jth quarter sales data of the year; For the The sales volume data for the jth quarter of the year Actual sales volume; is the total sales volume in the jth quarter of the i-th year; For the Total sales volume in the jth quarter of year; is a linear normalization function.

[0050] in, It represents the relative change trend of the actual sales volume of the nth item in the sales volume data of the jth quarter of the ith year; Indicates The relative change trend of the actual sales volume of the nth quarter in the sales volume data of the jth quarter of the year is The smaller the value of , the more likely it is that the nth actual sales volume in the sales data of the jth quarter of the ith year will be similar to the seasonal changes of the corresponding date in the most recent year, the higher the trend degree, and the greater the reference value of the corresponding actual sales volume in predicting future sales.

[0051] The total sales volume in each quarter of the above-mentioned years is the sum of all actual sales volume in the sales data; using the total sales volume in the same quarter of different years can conveniently measure the sales volume change trend in the same quarter of different years.

[0052] Then, the loss weight of each actual sales volume in each sales volume data is obtained according to the seasonal matching degree and trend degree; the square of the difference between the predicted value and the actual sales volume is weighted using the loss weight to obtain the loss function.

[0053] Among them, Year The calculation formula for the loss weight of each actual sales volume in the quarterly sales volume data is as follows: ; In the formula, is the loss weight of the nth actual sales volume in the jth quarter sales volume data of the i-th year; is the seasonal matching degree of sales data in the jth quarter of the i-th year; It is the trend degree of the nth actual sales volume in the jth quarter sales volume data of the i-th year.

[0054] In this embodiment, loss weights are obtained to improve the fitting of the random forest model to data points with high reference value and reduce the fitting of data points with low reference value.

[0055] Among the above or When the value of is 0, the corresponding weight is 0. At this time, the corresponding data has low reference value and can be removed.

[0056] The loss function is: ; In the formula, is the loss function value; is the loss weight of the nth actual sales volume in the jth quarter sales volume data of the i-th year; is the predicted value corresponding to the nth actual sales volume in the jth quarter sales volume data of the i-th year; is the nth actual sales volume in the jth quarter sales data of the i-th year; is the total number of days in the jth quarter; The total number of years for which sales data was collected.

[0057] The total number of years of sales data in this embodiment can be 3, 5, 10, etc. .

[0058] It should be noted that, taking meteorological data as an example, if the actual sales volume in the sales volume data in the same quarter of different years is affected by seasonal factors to a similar extent, a higher loss weight can be set to improve the model's fit to the actual sales volume in this part of the sales volume data; and if the actual sales volume in the sales volume data in the same quarter of different years is not affected by seasonal factors to a similar extent, a lower loss weight can be set to reduce the model's fit to the actual sales volume in this part of the sales volume data.

[0059] In this embodiment, the sales data of each quarter in the past three years is used as a training set to train the random forest model. The training process is as follows: The sales data of the first m quarters of dairy products in the training set and the environmental data of the m+1 quarter in multiple consecutive years are input into the prediction model, the sales data of the m+1 quarter is used as the label, and the loss between the output prediction value and the label is calculated to train the prediction model; Use gradient descent to adjust model parameters to minimize prediction error; Iteratively adjust the parameters of the prediction model until the loss is less than the set value or the set number of training times is reached, and finally a trained prediction model is obtained.

[0060] The set value can be set according to the actual situation.

[0061] Step S3, inputting the sales data of the dairy product in the current time period and the future environmental data in the future time period into the trained prediction model to output the sales prediction result in the future time period.

[0062] In this embodiment, the trained random forest model is used to predict the sales volume of dairy products and obtain the sales volume forecast result for the next time period.

[0063] In order to make the prediction more accurate, the current sales data in this embodiment can be the sales data of the five consecutive days before the current day, and the future time period is the five consecutive days in the future; of course, it can also be the sales data of the current quarter or the sales data of the current month, and the corresponding future time period is the future quarter or the future month, etc. The specific method can be determined according to the actual situation.

[0064] In one embodiment, the future environmental data (weather data) of the future time period may be directly obtained from the Meteorological Bureau.

[0065] In another embodiment, the acquisition of the future environmental data in the above-mentioned future time period can also be predicted by an ARIMA (Autoregressive Integrated Moving Average Model) model or a moving average prediction method. Since the ARIMA model or the moving average prediction method is a prior art, it will not be described in detail here.

[0066] Step S4, adjusting the storage space in advance according to the sales forecast result of dairy products to achieve storage space management.

[0067] The storage locations in this embodiment include target location information and shared location information of different products, wherein the target location information corresponds to different products, and the shared location information is used to allocate according to the sales forecast results of different products.

[0068] When the predicted value in the sales forecast result is greater than the target storage location quantity, and the number of shared goods in the storage location at the time corresponding to the predicted value is available, the shared storage location information will be allocated to dairy products; when all predicted values ​​in the sales forecast result are less than or equal to the target storage location quantity, there is no need to allocate storage locations.

[0069] It should be noted that the dairy product sales forecast results in this embodiment represent possible future sales situations. The sales forecast results can also be revised based on the sales environment data. Based on the revised sales forecast results of dairy products, the inventory level can be adjusted in advance and the storage locations can be optimized, thereby improving warehouse operating efficiency and saving storage costs.

[0070] The solution of the present invention collects sales data and meteorological data of dairy products, obtains the seasonal matching degree of each sales data, and the trend degree of each actual sales volume in each sales data, and obtains the loss weight of each actual sales volume in each sales data according to the seasonal matching degree and the trend degree, so as to train the prediction model, so as to obtain more accurate dairy product sales prediction results that are more in line with seasonal changes, and then reasonably adjust the storage cargo space.

[0071] The present invention also provides a storage location management system. Figure 2 As shown, the system includes a processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, the above-mentioned warehouse storage location management method according to the present invention is implemented.

[0072] The management system also includes other components well known to those skilled in the art, such as a communication bus and a communication interface, and the configuration and functions of these components are known in the art, so they will not be described in detail here.

[0073] In the present invention, the aforementioned memory may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, apparatus or device. For example, a computer-readable storage medium may be any appropriate magnetic storage medium or magneto-optical storage medium, such as a resistive random access memory RRAM (Resistive Random Access Memory), a dynamic random access memory DRAM (Dynamic Random Access Memory), a static random access memory SRAM (Static Random-Access Memory), an enhanced dynamic random access memory EDRAM (Enhanced Dynamic Random Access Memory), a high-bandwidth memory HBM (High-Bandwidth Memory), a hybrid memory cube HMC (Hybrid Memory Cube), etc., or any other medium that can be used to store the required information and can be accessed by an application, a module, or both. Any such computer storage medium may be part of a device or accessible or connectable to a device. Any application or module described in the present invention may be implemented using computer-readable / executable instructions that may be stored or otherwise maintained by such a computer-readable medium.

[0074] In the description of this specification, “plurality” means at least two, such as two, three or more, etc., unless otherwise clearly and specifically defined.

[0075] Although this specification has shown and described a number of embodiments of the present invention, it will be apparent to those skilled in the art that such embodiments are provided by way of example only. Those skilled in the art will conceive of many modifications, changes and alternatives without departing from the ideas and spirit of the present invention. It should be understood that in the practice of the present invention, various alternatives to the embodiments of the present invention described herein may be employed.

Claims

1. A warehouse storage location management method, characterized in that: include: The prediction model is trained using a training set; the training set includes sales data and environmental data of dairy products in each quarter of multiple consecutive years; Input the current time period sales data of dairy products and the future environmental data of the future time period into the trained prediction model to output the sales forecast results of the future time period; Make advance adjustments to warehouse storage space based on sales forecasts for dairy products; The loss function of the prediction model is obtained by weighting the square of the difference between the actual sales volume and the predicted value in the sales volume data using each loss weight; the loss weight is the product of the seasonal matching degree of each sales volume data and the trend degree of each actual sales volume in the corresponding sales volume data; The trend degree represents the difference in actual sales volume in the same quarter of any two years; The seasonal matching degree is the product of the change indexes of multiple regions; the change index for: ; , are the ath region in the i-th year and the The value of the kth parameter in the environmental data for the jth quarter of the year, is the linear normalization function, is the normalized value of the distribution volume of the ath region in the jth quarter of the ith year, is the number of parameter categories in the environmental data; The year is the last year in a series of consecutive years.

2. The storage space management method according to claim 1, characterized in that: The distribution volume is the sales volume of the corresponding region in any quarter, and the sum of the distribution volumes of all regions in any quarter is the total sales volume of the corresponding quarter.

3. The storage space management method according to claim 1, characterized in that: The loss function for: ； In the formula, , are the loss weight and predicted value of the nth actual sales volume in the sales volume data of the jth quarter of the i-th year, respectively; is the nth actual sales volume in the sales volume data of the jth quarter of the i-th year; is the total number of sales data in the jth quarter; The total number of years for multiple consecutive years.

4. The storage space management method according to claim 1, characterized in that: The trend for: ; is the nth actual sales volume in the sales volume data of the jth quarter of the i-th year; is the sales volume of the jth quarter in the i-th year. Actual sales volume, For the The nth actual sales volume in the jth quarter sales data of the year; For the The sales volume data for the jth quarter of the year Actual sales volume; is the total sales volume in the jth quarter of the i-th year; For the Total sales volume in the jth quarter of year; is a linear normalization function.

5. The storage space management method according to claim 1, characterized in that: The specific process of making advance adjustments to storage locations based on the sales forecast results of dairy products is as follows: when a predicted value in the sales forecast results is greater than the target number of locations, and there is vacancies in the number of shared goods in the storage locations at the time corresponding to the predicted value, the shared location information is allocated to dairy products; when all predicted values ​​in the sales forecast results are less than or equal to the target number of locations, there is no need to allocate storage locations; wherein, the storage locations include the target number of locations for dairy products and the number of shared locations.

6. The storage space management method according to claim 3 is characterized in that: The prediction model is a random forest model.

7. The storage space management method according to claim 6, characterized in that: The specific process of training the prediction model is as follows: The sales data of the first m quarters of dairy products in the training set and the environmental data of the m+1 quarter in multiple consecutive years are input into the prediction model, the sales data of the m+1 quarter is used as the label, and the loss between the output prediction value and the label is calculated to train the prediction model; Use gradient descent to adjust model parameters to minimize prediction error; Iteratively adjust the parameters of the prediction model until the loss is less than the set value or the set number of training times is reached, and finally a trained prediction model is obtained.

8. The method for managing storage space according to claim 1, characterized in that: The environmental data includes meteorological data, wherein the meteorological data is the daily temperature, precipitation, wind speed, humidity, air pressure and air quality index of each year.

9. Warehouse storage location management system, characterized in that: include: processor; A memory storing computer instructions for warehouse storage location management, wherein when the computer instructions are executed by the processor, the system executes the warehouse storage location management method according to any one of claims 1 to 8.

Images