Cloud warehouse material storage location dynamic management system and method based on time control

Abstract

The present invention discloses a cloud warehouse material storage location dynamic management system and method based on time control, and relates to the field of material location management. The present invention provides a classification model for subsequent classification of material quantity and material data ratio of a cloud warehouse to be managed by constructing a first final support vector machine classification model and a second final support vector machine classification model, thereby no longer needing to measure and calculate space utilization data and operation efficiency data of the cloud warehouse to be managed, thereby improving analysis efficiency; since order quantity data directly determines the efficiency of material outbound delivery, the order quantity data of multiple statistical time points in the cloud warehouse to be managed are predicted and data merged in this scheme, providing a basis for subsequent targeted setting of optimization strategies based on order quantity data, making the set optimization strategies more accurate, and thus making the final updated material location more conducive to adapting to changes in order quantity data.

Description

Technical Field

[0001] The present invention belongs to the field of material location management, and in particular, relates to a cloud warehouse material storage location dynamic management system and method based on time control. Background Art

[0002] Chinese patent CN112258125B discloses a multi-material dynamic collaborative management system and method based on Euro warehouse, which obtains material demand information and synchronously obtains material storage information in the Euro warehouse, obtains material replenishment information based on the material storage information and material demand information, and then obtains material outbound information based on the material demand information and material storage information; controls the Euro warehouse to carry out material outbound according to the material outbound information, and controls the Euro warehouse to carry out material replenishment according to the material replenishment information.

[0003] Due to the complexity and variability of market demand, such as sudden order surges or slow increases in order volume to a larger amount, current cloud warehousing is unable to make targeted material storage location update strategies for these different changes in order quantity, thereby limiting the efficiency of cloud warehousing in dispatching material orders. Summary of the invention

[0004] In view of the problems in the related art, the present invention proposes a cloud warehouse material storage location dynamic management system and method based on time control to overcome the above-mentioned technical problems existing in the existing related art.

[0005] In order to solve the above technical problems, the present invention is achieved through the following technical solutions:

[0006] The present invention is a method for dynamic management of cloud storage material storage locations based on time control, comprising the following steps:

[0007] S1. Set multiple material placement principles to obtain a material placement principle set; collect material quantity ratio data, space utilization data, and operation efficiency data of multiple cloud warehouses according to the collected material placement principle set to obtain a material quantity ratio set, an average space utilization data set, and an average operation efficiency data set;

[0008] S2. Collect the quantity grades of materials in multiple cloud warehouses to obtain a material quantity grade data set; use the material quantity grade data set, the material quantity ratio set, the space utilization average data set and the operation efficiency average data set to construct a first final support vector machine classification model and a second final support vector machine classification model;

[0009] S3, predicting and merging the order quantity data at multiple statistical time points in the cloud warehouse to be managed to obtain a merged order quantity data set; setting an optimization strategy for the material quantity and material data ratio of the cloud warehouse to be managed according to the merged order quantity data set to obtain a setting result; performing a first adjustment or a second adjustment on the material quantity and material data ratio of the cloud warehouse to be managed according to the setting result and in conjunction with the first final support vector machine classification model and the second final support vector machine classification model to obtain an adjustment result;

[0010] S4. Update the location of the materials in the cloud warehouse to be managed according to the adjustment results;

[0011] As the material placement principles are different, the material locations in the cloud warehouse are also different; therefore, in this solution, by setting multiple material placement principles, the material location change strategy is considered from the two perspectives of material placement principles and material quantity, so that the final location change strategy is more comprehensive and accurate; by collecting material quantity level data and material quantity ratio data as well as space utilization data and operation efficiency data from multiple cloud warehouses, training and test data and corresponding classification label data are provided for the subsequent construction of the first final support vector machine classification model and the second final support vector machine classification model; by constructing the first final support vector machine classification model and the second final support The vector machine classification model provides a classification model for the subsequent classification of the material quantity and material data ratio of the cloud warehouse to be managed, so there is no need to measure and calculate the space utilization data and operation efficiency data of the cloud warehouse to be managed, which improves the analysis efficiency; because the order quantity data directly determines the efficiency of material outbound delivery, the order quantity data of multiple statistical time points in the cloud warehouse to be managed are predicted and merged in this scheme, which provides a basis for the subsequent targeted setting of optimization strategies based on the order quantity data, making the set optimization strategies more accurate, and thus making the final updated material location more conducive to adapting to changes in order quantity data.

[0012] Preferably, the S1 comprises the following steps:

[0013] S11. Set cloud storage library set a = {a1, a2, ..., a i ,...,a a′} and material placement principles a i represents the i-th cloud storage library, and a′ represents the total number of cloud storage libraries; They represent the material outgoing frequency and material volume respectively;

[0014] Then set the cloud storage library set a={a1,a2,...,a i ,...,a a′}In each cloud warehouse, material samples are stored, and the material sample matrix a~ is obtained; as follows,

[0015]

[0016] in, Represents the cloud storage library set a={a1,a2,...,a i ,...,a a′}, the jth material sample in the i-th cloud warehouse, b i Represents the cloud storage library set a={a1,a2,...,a i ,...,a a′ The total number of material samples in the i-th cloud warehouse in};

[0017] S12. Set the material quantity level and the corresponding material quantity range to obtain the material quantity level set. And the material quantity interval set b1′ i Indicates the set i-th material quantity level, Indicates the total number of set material quantity levels; b2′ i1 , b2′ i2 They respectively represent the lower and upper limits of the material quantity corresponding to the i-th material quantity level;

[0018] Set the cloud storage library set a = {a1, a2, ..., a i ,...,a a′ Each cloud warehouse in the The material quantity ratio of the two material placement principles is obtained, and the material quantity ratio set is obtained. Represents the cloud storage library set a={a1,a2,...,a i ,...,a a′ The material placement principle set used in the i-th cloud warehouse in} The ratio of material quantities between the two material placement principles;

[0019] S13. Set multiple historical time points to obtain a set of historical time points c i ′ represents the set i-th historical time point, Indicates the total number of set historical time points; according to the set of historical time points Collection cloud storage library set a = {a1, a2, ..., a i ,...,a a′}, and obtain the space utilization data matrix and operational efficiency data matrix They are as follows:

[0020]

[0021] in, Respectively represent the cloud storage library set a={a1,a2,...,a i ,...,a a′} space utilization data and operation efficiency data of the i-th cloud warehouse at the j-th historical time point;

[0022] Calculate the space utilization data matrix and operational efficiency data matrix The average value of each row of data in the space utilization average data set is obtained and the average data set of work efficiency Respectively represent the cloud storage library set

[0023] a={a1,a2,...,a i ,...,a a′ The average space utilization rate and operation efficiency data of the i-th cloud warehouse in};

[0024] From the perspectives of the two material placement principles based on material outbound frequency and material volume, placing materials based on material outbound frequency is more conducive to improving the operating efficiency of the entire cloud warehouse, and placing materials based on material volume is more conducive to improving the space utilization of the entire cloud warehouse; improving the set material quantity level set and material quantity range set, classifying and simplifying the numerous material quantity data, thereby reducing the amount of data in the subsequent training and testing process of the first final support vector machine classification model and the second final support vector machine classification model.

[0025] Preferably, S2 comprises the following steps:

[0026] S21, according to the material quantity level set Material quantity interval set And the material sample matrix Set the cloud repository set a = {a1, a2, ..., a i ,...,a a′}, and obtain the material quantity grade data set d = {d1, d2, ..., d i ,...,d a′}, d i Represents the cloud repository set

[0027] a={a1,a2,...,a i ,...,a a′}The material quantity and grade data of the i-th cloud warehouse;

[0028] S22, constructing a first initial support vector machine classification model and a second initial support vector machine classification model;

[0029] Using the material quantity level data set d = {d1, d2, ..., d i ,...,d a′}、Material quantity ratio set And the space utilization average data set Training and testing the first initial support vector machine classification model; after the training and testing are completed, obtaining the first final support vector machine classification model;

[0030] Using the material quantity level data set d = {d1, d2, ..., d i ,...,d a′}、Material quantity ratio set and the average data set of work efficiency Training and testing the second initial support vector machine classification model; after the training and testing are completed, obtaining the second final support vector machine classification model;

[0031] By using the material quantity grade data set, the material quantity ratio set and the average space utilization data set to train and test the first initial support vector machine classification model, the first final support vector machine classification model obtained has a good mapping ability between the material quantity grade data set, the material quantity ratio set and the average space utilization data set; and then by using the material quantity grade data set, the material quantity ratio set and the average operation efficiency data set to train and test the second initial support vector machine classification model, the second final support vector machine classification model obtained has a good mapping ability between the material quantity grade data set, the material quantity ratio set and the average operation efficiency data set.

[0032] Preferably, the material quantity level data set d={d1, d2, ..., d i ,...,d a′}、Material quantity ratio set And the space utilization average data set Training and testing the first initial support vector machine classification model includes the following steps:

[0033] S2211, setting a first training data ratio; and performing a material quantity level data set d={d1, d2, ..., d i ,...,d a′}、Material quantity ratio set And the space utilization average data set Perform data division to obtain a first material quantity level training data set, a first material quantity level test data set, a first material quantity ratio training set, a first material quantity ratio test set, a space utilization average training data set, and a space utilization average test data set;

[0034] S2212, setting a first training error threshold; inputting the first material quantity level training data set, the first material quantity ratio training set, and the space utilization average training data set into the first initial support vector machine classification model for training; during the training process, when the training error is less than the first training error threshold, stopping the training to obtain a first trained support vector machine classification model; otherwise, continuing the training until the training error is less than the first training error threshold;

[0035] S2213, setting a first accuracy threshold; inputting the first material quantity level test data set, the first material quantity ratio test set and the space utilization average test data set into the first trained support vector machine classification model for testing to obtain a first test accuracy; when the first test accuracy is greater than or equal to the first accuracy threshold, using the first trained support vector machine classification model as the first final support vector machine classification model; otherwise, returning to S2212 to continue training until the first test accuracy is greater than or equal to the first accuracy threshold;

[0036] In S22, the material quantity level data set d={d1, d2, ..., d i ,...,d a′}、Material quantity ratio set and the average data set of work efficiency Training and testing the second initial support vector machine classification model includes the following steps:

[0037] S2221, setting a second training data ratio; and performing a material quantity level data set d={d1, d2, ..., d i ,...,d a′}、Material quantity ratio set and the average data set of work efficiency Perform data division to obtain a second material quantity grade training data set, a second material quantity grade test data set, a second material quantity ratio training set, a second material quantity ratio test set, an operation efficiency average training data set, and an operation efficiency average test data set;

[0038] S2222, setting a second training error threshold; inputting the second material quantity level training data set, the second material quantity ratio training set, and the operation efficiency average training data set into the second initial support vector machine classification model for training; during the training process, when the training error is less than the second training error threshold, stopping the training to obtain a second trained support vector machine classification model; otherwise, continuing the training until the training error is less than the second training error threshold;

[0039] S2223, set a second accuracy threshold; input the second material quantity level test data set, the second material quantity ratio test set and the operation efficiency average test data set into the second trained support vector machine classification model for testing to obtain a second test accuracy; when the second test accuracy is greater than or equal to the second accuracy threshold, use the second trained support vector machine classification model as the second final support vector machine classification model; otherwise, return to S2212 to continue training until the second test accuracy is greater than or equal to the second accuracy threshold;

[0040] Preferably, S3 comprises the following steps:

[0041] S31, set a cloud warehouse to be managed, the average number of materials in the cloud warehouse to be managed is e1, and adopt the material placement principle set The material quantity ratio of the two material placement principles is e2, the space utilization rate is e3, and the operation efficiency is e4, which are recorded as the initial material quantity, the initial material data ratio, the initial space utilization rate data, and the initial operation efficiency data respectively;

[0042] Set multiple statistical time points to get a set of statistical time points d1′ i Indicates the set i-th statistical time point, Indicates the total number of set statistical time points; according to the statistical time point set Collect the order volume of the cloud warehouse to be managed at each statistical time point to obtain the order volume data set Represents the order volume data of the cloud warehouse to be managed at the i-th statistical time point;

[0043] S32, set multiple prediction time points to obtain a prediction time point set d2′ i represents the set i-th prediction time point, Indicates the total number of set prediction time points; according to the order volume data set And the statistical time point set Predict the order volume data of the managed cloud warehouse at each prediction time point to obtain the order volume prediction data set represents the predicted order volume data of the cloud warehouse to be managed at the i-th prediction time point; the order volume prediction data set And the order volume dataset Merge to get the order volume merged data set Indicates that the order quantity prediction dataset And the order volume dataset The i-th order quantity data obtained after merging, is the total number of order quantity data in the order quantity merged data set,

[0044] S33, setting an order quantity data threshold e1′ and an order quantity change amplitude threshold e′2; adjusting the initial material quantity e1, the initial material data ratio e2, the initial space utilization rate data e3 and the initial operation efficiency data e4 according to the order quantity data threshold e1′ and the order quantity change amplitude threshold e′2;

[0045] By setting multiple statistical time points and collecting corresponding order quantity data, data support is provided for the subsequent prediction of order quantity data at future time points; by merging the predicted data with the data used for prediction, the richness of the order quantity data is improved, providing richer data support for the subsequent setting of material location update strategies.

[0046] Preferably, the S33 includes the following process:

[0047] When the order quantity data in the order quantity merged data set is greater than or equal to the order quantity data threshold value e1′, and the difference between the order quantity data and the order quantity data at the adjacent time points on the left and right sides of the order quantity merged data set is less than e′2, the initial material quantity e1 and the initial material data ratio e2 are first adjusted; after the first adjustment is completed, the first final material quantity e5, the first final material data ratio e6, and the corresponding first final space utilization data e7 and the first final operation efficiency data e8 are obtained;

[0048] When the order quantity data in the order quantity merged data set is greater than or equal to the order quantity data threshold value e1′, and the difference between the order quantity data and the order quantity data at the adjacent time point on the left or right side of the order quantity merged data set is greater than or equal to e′2, the initial material quantity e1 and the initial material data ratio e2 are adjusted for the second time; after the second adjustment is completed, the second final material quantity e9 and the second final material data ratio e1 are obtained. 10 And the corresponding second final operation efficiency data e 11 ;

[0049] When there is order volume data in the order volume merged data set that is greater than or equal to the order volume data threshold, and the difference between the order volume data and the order volume data at adjacent time points on the left and right sides of the order volume merged data set is less than the order volume change amplitude threshold, it indicates that the order volume data at this time point has exceeded the predetermined range, but the change rate of the order volume data is not large, so there is sufficient time to comprehensively consider the space utilization and operation efficiency of the cloud warehouse to be managed; when there is order volume data in the order volume merged data set that is greater than or equal to the order volume data threshold, and the difference between the order volume data and the order volume data at adjacent time points on the left or right sides of the order volume merged data set is greater than or equal to the order volume change amplitude threshold, it indicates that the order volume data at this time point has exceeded the predetermined range and the change rate of the order volume data is large, so only the operation efficiency of the cloud warehouse to be managed is considered to adapt to the sudden change in order volume data.

[0050] Preferably, the first adjustment of the initial material quantity e1 and the initial material data ratio e2 in S33 includes the following steps:

[0051] S3311. Establishing the first population of sooty terns represents the i-th sooty tern in the first sooty tern population, represents the size of the first sooty tern population; sets the maximum number of iterations of the first sooty tern population to f1 and the current number of iterations to f2, which are recorded as the first maximum number of iterations and the first current number of iterations respectively; the search space dimension of the first sooty tern population is 2;

[0052] S3312, setting the initial position of each sooty tern in the first sooty tern population according to the initial material quantity e1 and the initial material data ratio e2, and obtaining a first initial position matrix f1′; as follows,

[0053]

[0054] Among them, f1′ i1 、f1′ i2 They respectively represent the components of the initial position of the i-th sooty tern in the first sooty tern population in the first and second search space dimensions; the calculation formulas are as follows:

[0055]

[0056] In the formula, Respectively represent the minimum quantity and maximum quantity of materials that can be stored in the cloud warehouse to be managed; respectively represent the minimum and maximum values ​​of the material data ratio in the cloud warehouse to be managed; rand 1i1 、rand 1i2Respectively represent the i1 and f1′ i2 A random number generated between 0 and 1; ceil represents the rounding function;

[0057] S3313: constructing a fitness function of the first sooty tern population according to the initial space utilization rate data e3 and the initial operation efficiency data e4 as follows,

[0058]

[0059] In the formula, β represents the preference coefficient for space utilization;

[0060] S3314, start iteration, set the first current iteration number f2 to 1 before iteration; use the fitness function of the first sooty tern population in the first round of iteration Calculate the fitness value of each position in the first initial position matrix f1′ to obtain a first fitness value set; select the maximum fitness value in the first fitness value set and the position corresponding to the sooty tern and update the first initial position matrix f1′;

[0061] In each other iteration, the fitness function of the first sooty tern population is used Calculate the fitness value of each position in the position matrix updated in the previous round of iteration to obtain a second fitness value set; select the maximum fitness value and the position of the corresponding sooty tern in the second fitness value set and update the position of each sooty tern in the first sooty tern population; after the update is completed, add 1 to the first current iteration number f2 and enter the next round of iteration;

[0062] S3315. When f2≥f1, stop iteration and output the first final global optimal position; use the first final global optimal position to replace the initial material quantity e1 and the initial material data ratio e2 to obtain the first adjusted material quantity and the first adjusted material data ratio;

[0063] According to the order quantity data in the combined order quantity data set that is greater than or equal to the order quantity data threshold e1′, a first space rate threshold and a first operating efficiency threshold are set; the first final support vector machine classification model and the second final support vector machine classification model are respectively used to calculate the space utilization data and the operating efficiency data corresponding to the ratio of the first adjusted material quantity to the first adjusted material data, to obtain the first adjusted space utilization data and the first adjusted operating efficiency data;

[0064] When the first adjusted space utilization data is greater than or equal to the first space rate threshold and the first adjusted operation efficiency data is greater than or equal to the first operation efficiency threshold, the first adjusted material quantity, the first adjusted material data ratio, the first adjusted space utilization data and the first adjusted operation efficiency data are respectively used as the first final material quantity e5, the first final material data ratio e6 and the corresponding first final space utilization data e7 and the first final operation efficiency data e8; otherwise, return to S3314 to continue iterating until the first adjusted space utilization data is greater than or equal to the first space rate threshold and the first adjusted operation efficiency data is greater than or equal to the first operation efficiency threshold;

[0065] The Sooty Tern optimization algorithm conducts extensive exploration in the search space and can find the global optimal solution quickly. At the same time, it conducts detailed searches in local areas and has a high optimization accuracy. Therefore, in this scheme, the Sooty Tern optimization algorithm is used to perform multiple iterations of optimization on the initial material quantity and the initial material data ratio, and the combined calculation of the initial space utilization data and the initial operation efficiency data is used as the criterion for measuring the pros and cons of the optimization. As the iteration proceeds, the space utilization data and operation efficiency data of the cloud warehouse to be managed are continuously improved, and finally the requirements of the order volume data are met.

[0066] Preferably, the second adjustment of the initial material quantity e1 and the initial material data ratio e2 in S33 includes the following steps:

[0067] S3321. Establishing the second population of sooty terns represents the i-th sooty tern in the second sooty tern population, represents the size of the second sooty tern population; setting the maximum number of iterations of the second sooty tern population to f3 and the current number of iterations to f4, which are recorded as the second maximum number of iterations and the second current number of iterations respectively; the search space dimension of the second sooty tern population is 2;

[0068] S3322, setting the initial position of each sooty tern in the second sooty tern population according to the initial material quantity e1 and the initial material data ratio e2, and obtaining a second initial position matrix f2′; as follows,

[0069]

[0070] Among them, f2′ i1 、f2′ i2 They respectively represent the components of the initial position of the i-th sooty tern in the second sooty tern population in the first and second search space dimensions; the calculation formulas are as follows:

[0071]

[0072] In the formula, rand 2i1 、rand 2i2 Respectively represent the f2′ i1 and f2′ i2 Generate a random number between 0 and 1;

[0073] S3323, constructing a fitness function of the second sooty tern population according to the initial operation efficiency data e4 as follows,

[0074]

[0075] S3324, start iteration, and set the second current iteration number f4 to 1 before iteration; in the first round of iteration, the fitness function of the second sooty tern population is used Calculate the fitness value of each position in the second initial position matrix f2′ to obtain a third fitness value set; select the maximum fitness value in the third fitness value set and the position corresponding to the sooty tern and update the second initial position matrix f2′;

[0076] The fitness function of the second sooty tern population is used in each other iteration process Calculate the fitness value of each position in the position matrix updated in the previous round of iteration to obtain a fourth fitness value set; select the maximum fitness value in the fourth fitness value set and the position of the corresponding sooty tern and update the position of each sooty tern in the second sooty tern population; after the update is completed, add 1 to the second current iteration number f4 and enter the next round of iteration;

[0077] S3325. When f4≥f2, stop iteration and output the second final global optimal position; use the second final global optimal position to replace the initial material quantity e1 and the initial material data ratio e2 to obtain the second adjusted material quantity and the second adjusted material data ratio;

[0078] A second operating efficiency threshold is set according to the order quantity data in the combined order quantity data set that is greater than or equal to the order quantity data threshold e1′ and the difference between the order quantity data and the order quantity data at adjacent time points on the left or right side of the combined order quantity data set; the operating efficiency data corresponding to the second adjusted material quantity and the second adjusted material data ratio is calculated using the second final support vector machine classification model to obtain the second adjusted operating efficiency data;

[0079] When the second adjusted operating efficiency data is greater than or equal to the second operating efficiency threshold, the second adjusted material quantity, the second adjusted material data ratio and the second adjusted operating efficiency data are respectively used as the second final material quantity e9 and the second final material data ratio e 10 And the corresponding second final operation efficiency data e 11 ; Otherwise, return to S3324 and continue to iterate until the second adjusted operating efficiency data is greater than or equal to the second operating efficiency threshold;

[0080] By using the Sooty Tern optimization algorithm to perform multiple iterative optimizations on the initial material quantity and the initial material data ratio, and using the initial operating efficiency data as the criterion for measuring the pros and cons of the optimization, the operating efficiency data of the cloud warehouse to be managed will continue to improve with the progress of iterations, and ultimately meet the requirements of the order volume data.

[0081] Preferably, S4 comprises the following steps:

[0082] S41, setting the initial position of the material in the cloud warehouse to be managed and encoding it, to obtain a data set of position codes of the material to be managed Represents the location code of the i-th material in the cloud warehouse to be managed;

[0083] S42: when the order quantity data in the combined order quantity data set is greater than or equal to the order quantity data threshold value e1′, and the difference between the order quantity data and the order quantity data at the adjacent time points on the left and right sides of the combined order quantity data set is less than e′2, the material position code data set is managed according to the first final material quantity e5 and the first final material data ratio e6. Update to obtain the first updated material location code data set g i The position coding data representing the i-th material in the first updated material position coding data set;

[0084] When the order quantity data in the combined order quantity data set is greater than or equal to the order quantity data threshold value e1′, and the difference between the order quantity data and the order quantity data at the adjacent time point on the left or right side of the combined order quantity data set is greater than or equal to e′2, the second final material quantity e9, the second final material data ratio e 10 Manage material location code data sets Update to obtain the second updated material location code data set g i ′ is the position code data representing the i-th material in the second updated material position code data set;

[0085] According to the optimal material quantity and material data ratio obtained by searching in the above steps, the position of each material in the cloud warehouse to be managed is changed, so that the changed cloud warehouse to be managed can truly adapt to the changes in order quantity data and ensure the normal operation of the cloud warehouse to be managed.

[0086] A cloud warehouse material storage location dynamic management system based on time control, including a placement principle setting module, a cloud warehouse data collection module, a cloud warehouse material quantity data collection module, a classification model building module, a prediction module, an optimization strategy setting module, a cloud warehouse material data optimization module to be managed, and a material location update management module;

[0087] The placement principle setting module is used to set multiple material placement principles to obtain a material placement principle set;

[0088] The cloud warehouse data collection module is used to collect material quantity ratio data, space utilization data and operation efficiency data of each cloud warehouse in multiple cloud warehouses according to the material placement principle set, and obtain a material quantity ratio set, an average space utilization data set and an average operation efficiency data set;

[0089] The cloud storage material quantity data collection module is used to collect the quantity levels of materials in multiple cloud storage warehouses to obtain a material quantity level data set;

[0090] The classification model construction module is used to construct a first final support vector machine classification model and a second final support vector machine classification model using a material quantity grade data set, a material quantity ratio set, a space utilization average data set, and an operation efficiency average data set;

[0091] The prediction module is used to predict and merge the order volume data at multiple statistical time points in the managed cloud warehouse to obtain an order volume merged data set;

[0092] The optimization strategy setting module is used to set the optimization strategy for the material quantity and material data ratio of the cloud warehouse to be managed according to the order quantity merged data set, and obtain the setting result;

[0093] The material data optimization module of the cloud warehouse to be managed is used to perform a first adjustment or a second adjustment on the material quantity and the material data ratio of the cloud warehouse to be managed according to the setting result and in cooperation with the first final support vector machine classification model and the second final support vector machine classification model to obtain an adjustment result;

[0094] The material location update management module is used to update the location of the materials in the cloud warehouse to be managed according to the adjustment results.

[0095] The present invention has the following beneficial effects:

[0096] 1. The present invention provides a classification model for the subsequent classification of the material quantity and material data ratio of the cloud warehouse to be managed by constructing the first final support vector machine classification model and the second final support vector machine classification model, thereby eliminating the need to measure and calculate the space utilization data and operation efficiency data of the cloud warehouse to be managed, thereby improving the analysis efficiency; the order quantity data of multiple statistical time points in the cloud warehouse to be managed are predicted and the data are merged, providing a basis for the subsequent targeted setting of optimization strategies based on the order quantity data, making the set optimization strategies more accurate, and thus making the final updated material positions more conducive to adapting to changes in order quantity data.

[0097] 2. In the present invention, by comparing each order volume data in the order volume merged data set with the order volume data threshold and the order volume data at adjacent time points on the left and right, it is determined whether the order volume data at that time point exceeds a predetermined range and whether the change rate of the order volume data exceeds the set threshold, thereby selecting different tuning strategies to make the tuning more accurate.

[0098] 3. In the present invention, the initial material quantity and the initial material data ratio are iteratively optimized multiple times by using the Sooty Tern optimization algorithm, so that as the iteration proceeds, the space utilization data and the operation efficiency data of the cloud warehouse to be managed are continuously improved at the same time, and finally the requirements of the order quantity data are met.

[0099] Of course, any product implementing the present invention does not necessarily need to achieve all of the advantages described above at the same time. BRIEF DESCRIPTION OF THE DRAWINGS

[0100] In order to more clearly illustrate the technical solutions of the embodiments of the invention, the drawings required for describing the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the invention. For ordinary technicians in this field, they can also obtain drawings based on these drawings without paying creative work.

[0101] Figure 1 The present invention is a schematic diagram of a process for dynamically managing cloud warehouse material storage locations by using a cloud warehouse material storage location dynamic management system based on time control. DETAILED DESCRIPTION

[0102] The following will be combined with the drawings in the embodiments of the invention to clearly and completely describe the technical solutions in the embodiments of the invention. Obviously, the described embodiments are only part of the embodiments of the invention, not all of the embodiments. Based on the embodiments in the invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the invention.

[0103] In the description of the present invention, it is necessary to understand that the terms "opening", "upper", "lower", "top", "middle", "inside" and the like indicating orientation or positional relationship are only for the convenience of describing the invention and simplifying the description, and do not indicate or imply that the components or elements referred to must have a specific orientation, be constructed and operate in a specific orientation, and therefore cannot be understood as limiting the invention.

[0104] Embodiment 1

[0105] This embodiment is a method for dynamically managing the storage location of cloud warehouse materials based on time control, comprising the following steps:

[0106] S1. Set multiple material placement principles to obtain a material placement principle set; collect material quantity ratio data, space utilization data, and operation efficiency data of multiple cloud warehouses according to the collected material placement principle set to obtain a material quantity ratio set, an average space utilization data set, and an average operation efficiency data set;

[0107] The S1 comprises the following steps:

[0108] S11. Set cloud storage library set a = {a1, a2, ..., a i ,...,a a′} and material placement principles a i represents the i-th cloud storage library, and a′ represents the total number of cloud storage libraries; They represent the material outgoing frequency and material volume respectively;

[0109] Then set the cloud storage library set a={a1,a2,...,a i ,...,a a′}In each cloud warehouse, material samples are stored to obtain a material sample matrix as follows,

[0110]

[0111] in, Represents the cloud storage library set a={a1,a2,...,a i ,...,a a′}, the jth material sample in the i-th cloud warehouse, b i Represents the cloud storage library set a={a1,a2,...,a i ,...,a a′ The total number of material samples in the i-th cloud warehouse in};

[0112] S12. Set the material quantity level and the corresponding material quantity range to obtain the material quantity level set. And the material quantity interval set b1′ i Indicates the set i-th material quantity level, Indicates the total number of set material quantity levels; b2′ i1 , b2′ i2 They respectively represent the lower and upper limits of the material quantity corresponding to the i-th material quantity level;

[0113] Set the cloud storage library set a = {a1, a2, ..., a i ,...,a a′ Each cloud warehouse in the The material quantity ratio of the two material placement principles is obtained, and the material quantity ratio set is obtained. Represents the cloud storage library set a={a1,a2,...,a i ,...,a a′ The material placement principle set used in the i-th cloud warehouse in} The ratio of material quantities between the two material placement principles;

[0114] S13. Set multiple historical time points to obtain a set of historical time points c i ′ represents the set i-th historical time point, Indicates the total number of set historical time points; according to the set of historical time points Collection cloud storage library set a = {a1, a2, ..., a i ,...,a a′}, and obtain the space utilization data matrix and operational efficiency data matrix They are as follows:

[0115]

[0116] in, Respectively represent the cloud storage library set a={a1,a2,...,a i ,...,a a′} space utilization data and operation efficiency data of the i-th cloud warehouse at the j-th historical time point;

[0117] Calculate the space utilization data matrix and operational efficiency data matrix The average value of each row of data in the space utilization average data set is obtained and the average data set of work efficiency Respectively represent the cloud storage library set

[0118] a={a1,a2,...,a i ,...,a a′ The average space utilization rate and operation efficiency data of the i-th cloud warehouse in};

[0119] S2. Collect the quantity grades of materials in multiple cloud warehouses to obtain a material quantity grade data set; use the material quantity grade data set, the material quantity ratio set, the space utilization average data set and the operation efficiency average data set to construct a first final support vector machine classification model and a second final support vector machine classification model;

[0120] The S2 comprises the following steps:

[0121] S21, according to the material quantity level set Material quantity interval set And the material sample matrix Set the cloud repository set a = {a1, a2, ..., a i ,...,a a′}, and obtain the material quantity grade data set d = {d1, d2, ..., d i ,...,d a′}, d i Represents the cloud repository set

[0122] a={a1,a2,...,a i ,...,a a′}The material quantity and grade data of the i-th cloud warehouse;

[0123] S22, constructing a first initial support vector machine classification model and a second initial support vector machine classification model;

[0124] Using the material quantity level data set d = {d1, d2, ..., d i ,...,d a′}、Material quantity ratio set And the space utilization average data set Training and testing the first initial support vector machine classification model; after the training and testing are completed, obtaining the first final support vector machine classification model;

[0125] Using the material quantity level data set d = {d1, d2, ..., d i ,...,d a′}、Material quantity ratio set and the average data set of work efficiency Training and testing the second initial support vector machine classification model; after the training and testing are completed, obtaining the second final support vector machine classification model;

[0126] S3, predicting and merging the order quantity data at multiple statistical time points in the cloud warehouse to be managed to obtain a merged order quantity data set; setting an optimization strategy for the material quantity and material data ratio of the cloud warehouse to be managed according to the merged order quantity data set to obtain a setting result; performing a first adjustment or a second adjustment on the material quantity and material data ratio of the cloud warehouse to be managed according to the setting result and in conjunction with the first final support vector machine classification model and the second final support vector machine classification model to obtain an adjustment result;

[0127] The S3 comprises the following steps:

[0128] S31, set a cloud warehouse to be managed, the average number of materials in the cloud warehouse to be managed is e1, and adopt the material placement principle set The material quantity ratio of the two material placement principles is e2, the space utilization rate is e3, and the operation efficiency is e4, which are recorded as the initial material quantity, the initial material data ratio, the initial space utilization rate data, and the initial operation efficiency data respectively;

[0129] Set multiple statistical time points to get a set of statistical time points d1′ i Indicates the set i-th statistical time point, Indicates the total number of set statistical time points; according to the statistical time point set Collect the order volume of the cloud warehouse to be managed at each statistical time point to obtain the order volume data set Represents the order volume data of the cloud warehouse to be managed at the i-th statistical time point;

[0130] S32, set multiple prediction time points to obtain a prediction time point set d2′ i represents the set i-th prediction time point, Indicates the total number of set prediction time points; according to the order volume data set And the statistical time point set Predict the order volume data of the managed cloud warehouse at each prediction time point to obtain the order volume prediction data set represents the predicted order volume data of the cloud warehouse to be managed at the i-th prediction time point; the order volume prediction data set And the order volume dataset Merge to get the order volume merged data set Indicates that the order quantity prediction dataset And the order volume dataset The i-th order quantity data obtained after merging, is the total number of order quantity data in the order quantity merged data set,

[0131] S33, setting an order quantity data threshold e1′ and an order quantity change amplitude threshold e′2; adjusting the initial material quantity e1, the initial material data ratio e2, the initial space utilization rate data e3 and the initial operation efficiency data e4 according to the order quantity data threshold e1′ and the order quantity change amplitude threshold e′2;

[0132] The S33 includes the following process:

[0133] When the order quantity data in the order quantity merged data set is greater than or equal to the order quantity data threshold value e1′, and the difference between the order quantity data and the order quantity data at the adjacent time points on the left and right sides of the order quantity merged data set is less than e′2, the initial material quantity e1 and the initial material data ratio e2 are first adjusted; after the first adjustment is completed, the first final material quantity e5, the first final material data ratio e6, and the corresponding first final space utilization data e7 and the first final operation efficiency data e8 are obtained;

[0134] When the order quantity data in the order quantity merged data set is greater than or equal to the order quantity data threshold value e1′, and the difference between the order quantity data and the order quantity data at the adjacent time point on the left or right side of the order quantity merged data set is greater than or equal to e′2, the initial material quantity e1 and the initial material data ratio e2 are adjusted for the second time; after the second adjustment is completed, the second final material quantity e9 and the second final material data ratio e1 are obtained. 10 And the corresponding second final operation efficiency data e 11 ;

[0135] The first adjustment of the initial material quantity e1 and the initial material data ratio e2 in S33 includes the following steps:

[0136] S3311. Establishing the first population of sooty terns represents the i-th sooty tern in the first sooty tern population, represents the size of the first sooty tern population; sets the maximum number of iterations of the first sooty tern population to f1 and the current number of iterations to f2, which are recorded as the first maximum number of iterations and the first current number of iterations respectively; the search space dimension of the first sooty tern population is 2;

[0137] S3312, setting the initial position of each sooty tern in the first sooty tern population according to the initial material quantity e1 and the initial material data ratio e2, and obtaining a first initial position matrix f1′; as follows,

[0138]

[0139] Among them, f1′ i1 、f1′ i2 They respectively represent the components of the initial position of the i-th sooty tern in the first sooty tern population in the first and second search space dimensions; the calculation formulas are as follows:

[0140]

[0141] In the formula, Respectively represent the minimum quantity and maximum quantity of materials that can be stored in the cloud warehouse to be managed; respectively represent the minimum and maximum values ​​of the material data ratio in the cloud warehouse to be managed; rand 1i1 、rand 1i2 Respectively represent the i1 and f1′ i2 A random number generated between 0 and 1; ceil represents the rounding function;

[0142] S3313: constructing a fitness function of the first sooty tern population according to the initial space utilization rate data e3 and the initial operation efficiency data e4 as follows,

[0143]

[0144] In the formula, β represents the preference coefficient for space utilization;

[0145] S3314, start iteration, set the first current iteration number f2 to 1 before iteration; use the fitness function of the first sooty tern population in the first round of iteration Calculate the fitness value of each position in the first initial position matrix f1′ to obtain a first fitness value set; select the maximum fitness value in the first fitness value set and the position corresponding to the sooty tern and update the first initial position matrix f1′;

[0146] In each other iteration, the fitness function of the first sooty tern population is used Calculate the fitness value of each position in the position matrix updated in the previous round of iteration to obtain a second fitness value set; select the maximum fitness value and the position of the corresponding sooty tern in the second fitness value set and update the position of each sooty tern in the first sooty tern population; after the update is completed, add 1 to the first current iteration number f2 and enter the next round of iteration;

[0147] S3315. When f2≥f1, stop iteration and output the first final global optimal position; use the first final global optimal position to replace the initial material quantity e1 and the initial material data ratio e2 to obtain the first adjusted material quantity and the first adjusted material data ratio;

[0148] According to the order quantity data in the combined order quantity data set that is greater than or equal to the order quantity data threshold e1′, a first space rate threshold and a first operating efficiency threshold are set; the first final support vector machine classification model and the second final support vector machine classification model are respectively used to calculate the space utilization data and the operating efficiency data corresponding to the ratio of the first adjusted material quantity to the first adjusted material data, to obtain the first adjusted space utilization data and the first adjusted operating efficiency data;

[0149] When the first adjusted space utilization data is greater than or equal to the first space rate threshold and the first adjusted operation efficiency data is greater than or equal to the first operation efficiency threshold, the first adjusted material quantity, the first adjusted material data ratio, the first adjusted space utilization data and the first adjusted operation efficiency data are respectively used as the first final material quantity e5, the first final material data ratio e6 and the corresponding first final space utilization data e7 and the first final operation efficiency data e8; otherwise, return to S3314 to continue iterating until the first adjusted space utilization data is greater than or equal to the first space rate threshold and the first adjusted operation efficiency data is greater than or equal to the first operation efficiency threshold;

[0150] The second adjustment of the initial material quantity e1 and the initial material data ratio e2 in S33 includes the following steps:

[0151] S3321. Establishing the second population of sooty terns represents the i-th sooty tern in the second sooty tern population, represents the size of the second sooty tern population; setting the maximum number of iterations of the second sooty tern population to f3 and the current number of iterations to f4, which are recorded as the second maximum number of iterations and the second current number of iterations respectively; the search space dimension of the second sooty tern population is 2;

[0152] S3322, setting the initial position of each sooty tern in the second sooty tern population according to the initial material quantity e1 and the initial material data ratio e2, and obtaining a second initial position matrix f2′; as follows,

[0153]

[0154] Among them, f2′ i1 、f2′ i2They respectively represent the components of the initial position of the i-th sooty tern in the second sooty tern population in the first and second search space dimensions; the calculation formulas are as follows:

[0155]

[0156] In the formula, rand 2i1 、rand 2i2 Respectively represent the f2′ i1 and f2′ i2 Generate a random number between 0 and 1;

[0157] S3323, constructing a fitness function of the second sooty tern population according to the initial operation efficiency data e4 as follows,

[0158]

[0159] S3324, start iteration, and set the second current iteration number f4 to 1 before iteration; in the first round of iteration, the fitness function of the second sooty tern population is used Calculate the fitness value of each position in the second initial position matrix f2′ to obtain a third fitness value set; select the maximum fitness value in the third fitness value set and the position corresponding to the sooty tern and update the second initial position matrix f2′;

[0160] The fitness function of the second sooty tern population is used in each other iteration process Calculate the fitness value of each position in the position matrix updated in the previous round of iteration to obtain a fourth fitness value set; select the maximum fitness value in the fourth fitness value set and the position of the corresponding sooty tern and update the position of each sooty tern in the second sooty tern population; after the update is completed, add 1 to the second current iteration number f4 and enter the next round of iteration;

[0161] S3325. When f4≥f2, stop iteration and output the second final global optimal position; use the second final global optimal position to replace the initial material quantity e1 and the initial material data ratio e2 to obtain the second adjusted material quantity and the second adjusted material data ratio;

[0162] A second operating efficiency threshold is set according to the order quantity data in the combined order quantity data set that is greater than or equal to the order quantity data threshold e1′ and the difference between the order quantity data and the order quantity data at adjacent time points on the left or right side of the combined order quantity data set; the operating efficiency data corresponding to the second adjusted material quantity and the second adjusted material data ratio is calculated using the second final support vector machine classification model to obtain the second adjusted operating efficiency data;

[0163] When the second adjusted operating efficiency data is greater than or equal to the second operating efficiency threshold, the second adjusted material quantity, the second adjusted material data ratio and the second adjusted operating efficiency data are respectively used as the second final material quantity e9 and the second final material data ratio e 10 And the corresponding second final operation efficiency data e 11 ; Otherwise, return to S3324 and continue to iterate until the second adjusted operating efficiency data is greater than or equal to the second operating efficiency threshold;

[0164] S4. Update the location of the materials in the cloud warehouse to be managed according to the adjustment results;

[0165] The S4 comprises the following steps:

[0166] S41, setting the initial position of the material in the cloud warehouse to be managed and encoding it, to obtain a data set of position codes of the material to be managed Represents the location code of the i-th material in the cloud warehouse to be managed;

[0167] S42: when the order quantity data in the combined order quantity data set is greater than or equal to the order quantity data threshold value e1′, and the difference between the order quantity data and the order quantity data at the adjacent time points on the left and right sides of the combined order quantity data set is less than e′2, the material position code data set is managed according to the first final material quantity e5 and the first final material data ratio e6. Update to obtain the first updated material location code data set g i The position coding data representing the i-th material in the first updated material position coding data set;

[0168] When the order quantity data in the combined order quantity data set is greater than or equal to the order quantity data threshold value e1′, and the difference between the order quantity data and the order quantity data at the adjacent time point on the left or right side of the combined order quantity data set is greater than or equal to e′2, the second final material quantity e9, the second final material data ratio e 10 Manage material location code data sets Update to obtain the second updated material location code data set g i ′ is the position coding data representing the i-th material in the second updated material position coding data set.

[0169] Embodiment 2

[0170] This embodiment discloses a cloud warehouse material storage location dynamic management system based on time control, which can implement the method of the above embodiment, including a placement principle setting module, a cloud warehouse data collection module, a cloud warehouse material quantity data collection module, a classification model building module, a prediction module, an optimization strategy setting module, a cloud warehouse material data optimization module to be managed, and a material location update management module;

[0171] The placement principle setting module is used to set multiple material placement principles to obtain a material placement principle set;

[0172] The cloud warehouse data collection module is used to collect material quantity ratio data, space utilization data and operation efficiency data of each cloud warehouse in multiple cloud warehouses according to the material placement principle set, and obtain a material quantity ratio set, an average space utilization data set and an average operation efficiency data set;

[0173] The cloud storage material quantity data collection module is used to collect the quantity levels of materials in multiple cloud storage warehouses to obtain a material quantity level data set;

[0174] The classification model construction module is used to construct a first final support vector machine classification model and a second final support vector machine classification model using a material quantity grade data set, a material quantity ratio set, a space utilization average data set, and an operation efficiency average data set;

[0175] The prediction module is used to predict and merge the order volume data at multiple statistical time points in the managed cloud warehouse to obtain an order volume merged data set;

[0176] The optimization strategy setting module is used to set the optimization strategy for the material quantity and material data ratio of the cloud warehouse to be managed according to the order quantity merged data set, and obtain the setting result;

[0177] The material data optimization module of the cloud warehouse to be managed is used to perform a first adjustment or a second adjustment on the material quantity and the material data ratio of the cloud warehouse to be managed according to the setting result and in cooperation with the first final support vector machine classification model and the second final support vector machine classification model to obtain an adjustment result;

[0178] The material location update management module is used to update the location of the materials in the cloud warehouse to be managed according to the adjustment results.

[0179] In the description of this specification, the description with reference to the terms "one embodiment", "example", "specific example", etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0180] The preferred embodiments of the invention disclosed above are only used to help explain the invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to the specific implementation methods described. Obviously, many modifications and changes can be made according to the content of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the invention, so that those skilled in the art can understand and use the invention well.

Claims

1. A method for dynamic management of cloud warehouse material storage locations based on time control, characterized in that: The following steps are involved: S1. Set multiple material placement principles to obtain a material placement principle set; collect material quantity ratio data, space utilization data, and operation efficiency data of multiple cloud warehouses according to the collected material placement principle set to obtain a material quantity ratio set, an average space utilization data set, and an average operation efficiency data set; S2. Collect the quantity levels of materials in multiple cloud warehouses to obtain a material quantity level data set; A first final support vector machine classification model and a second final support vector machine classification model are constructed using a material quantity grade data set, a material quantity ratio value set, a space utilization average data set, and an operation efficiency average data set; S3, predicting and merging the order quantity data at multiple statistical time points in the cloud warehouse to be managed to obtain a merged order quantity data set; setting an optimization strategy for the material quantity and material data ratio of the cloud warehouse to be managed according to the merged order quantity data set to obtain a setting result; performing a first adjustment or a second adjustment on the material quantity and material data ratio of the cloud warehouse to be managed according to the setting result and in conjunction with the first final support vector machine classification model and the second final support vector machine classification model to obtain an adjustment result; S4. Update the location of the materials in the cloud warehouse to be managed according to the adjustment results; The S1 comprises the following steps: S11, setting a cloud storage library set and a material placement principle set; and then setting material samples to be stored in each cloud storage library in the cloud storage library set to obtain a material sample matrix; S12. Set the material quantity level and the corresponding material quantity interval range to obtain a material quantity level set and a material quantity interval set; set the material quantity ratio of the two material placement principles in the material placement principle set adopted by each cloud warehouse in the cloud warehouse set to obtain a material quantity ratio set; S13, setting multiple historical time points to obtain a historical time point set; collecting space utilization data and operation efficiency data of each cloud warehouse in the cloud warehouse set according to the historical time point set and calculating the average value to obtain an average space utilization data set and an average operation efficiency data set; The S2 comprises the following steps: S21, setting the material quantity grade data of each cloud warehouse in the cloud warehouse set according to the material quantity grade set, the material quantity interval set and the material sample matrix, to obtain a material quantity grade data set; S22, constructing a first initial support vector machine classification model and a second initial support vector machine classification model; respectively using the material quantity grade data set, material quantity ratio set, space utilization average data set and material quantity grade data set, material quantity ratio set and operation efficiency average data set to train and test the first initial support vector machine classification model and the second initial support vector machine classification model; after the training and testing are completed, a first final support vector machine classification model and a second final support vector machine classification model are obtained; The S3 comprises the following steps: S31, setting a cloud warehouse to be managed, the average quantity of materials in the cloud warehouse to be managed, the ratio of the quantity of materials using the two material placement principles of the material placement principle set, the space utilization rate and the operating efficiency, which are recorded as the initial material quantity, the initial material data ratio, the initial space utilization rate data and the initial operating efficiency data respectively; setting multiple statistical time points to obtain a statistical time point set; collecting the order quantity of the cloud warehouse to be managed at each statistical time point according to the statistical time point set to obtain an order quantity data set; S32, setting multiple prediction time points to obtain a prediction time point set; predicting the order volume data of the cloud warehouse to be managed at each prediction time point according to the order volume data set and the statistical time point set to obtain an order volume prediction data set; merging the order volume prediction data set and the order volume data set to obtain an order volume merged data set; S33. Set order volume data threshold And the order volume change threshold ;according to as well as Adjusting initial material quantity, initial material data ratio, initial space utilization data, and initial operation efficiency data; The S33 includes the following process: When the order volume merged data set contains order volume data greater than or equal to , and the difference between the order volume data and the order volume data at adjacent time points on the left and right sides of the combined order volume data set is less than When the initial material quantity and the initial material data ratio are adjusted in a first manner, a first final material quantity, a first final material data ratio, and corresponding first final space utilization rate data and first final operation efficiency data are obtained; When the order volume merged data set contains order volume data greater than or equal to , and the difference between the order volume data and the order volume data at the adjacent time point on the left or right side of the combined order volume data set is greater than or equal to When the initial material quantity and the initial material data ratio are adjusted for the second time, a second final material quantity, a second final material data ratio and corresponding second final operating efficiency data are obtained.

2. The method for dynamic management of cloud warehouse material storage locations based on time control according to claim 1 is characterized in that: The first adjustment of the initial material quantity and the initial material data ratio in S33 includes the following steps: S3311, constructing a first population of sooty terns; setting the maximum number of iterations of the first population of sooty terns to , the current number of iterations is , respectively recorded as the first maximum number of iterations and the first current number of iterations; S3312, setting the initial position of each sooty tern in the first sooty tern population according to the initial material quantity and the initial material data ratio, to obtain a first initial position matrix; S3313, constructing a fitness function of the first sooty tern population according to the initial space utilization rate data and the initial operation efficiency data; S3314, start iteration; in each round of iteration, use the fitness function of the first sooty tern population to calculate the fitness value of each position in the position matrix updated in the previous round of iteration, and update the position of each sooty tern in the first sooty tern population; S3315, when When , the iteration is stopped and the first final global optimal position is output; the first final global optimal position is used to replace the initial material quantity and the initial material data ratio to obtain the first adjusted material quantity and the first adjusted material data ratio; According to the order volume, the data is merged into a set that is greater than or equal to The first space rate threshold and the first operating efficiency threshold are set based on the order quantity data; the first final support vector machine classification model and the second final support vector machine classification model are respectively used to calculate the space utilization data and the operating efficiency data corresponding to the ratio of the first adjusted material quantity and the first adjusted material data, to obtain the first adjusted space utilization data and the first adjusted operating efficiency data; When the first adjusted space utilization data is greater than or equal to the first space rate threshold and the first adjusted operating efficiency data is greater than or equal to the first operating efficiency threshold, the first adjusted material quantity, the first adjusted material data ratio, the first adjusted space utilization data and the first adjusted operating efficiency data are used as the first final material quantity, the first final material data ratio and the corresponding first final space utilization data and first final operating efficiency data respectively; otherwise, return to S3314 to continue iterating until the first adjusted space utilization data is greater than or equal to the first space rate threshold and the first adjusted operating efficiency data is greater than or equal to the first operating efficiency threshold.

3. The method for dynamic management of cloud warehouse material storage location based on time control according to claim 2 is characterized in that: In S33, the second adjustment of the initial material quantity and the initial material data ratio is performed using the Sooty Tern optimization algorithm.

4. The method for dynamic management of cloud warehouse material storage location based on time control according to claim 3 is characterized in that: The S4 comprises the following steps: S41, setting the initial position of the material in the cloud warehouse to be managed and encoding it to obtain a data set of position codes of the material to be managed; S42: When the order volume merged data set contains order volume data greater than or equal to , and the difference between the order volume data and the order volume data at adjacent time points on the left and right sides of the combined order volume data set is less than , updating the material position code data set to be managed according to the first final material quantity and the first final material data ratio to obtain a first updated material position code data set; When the order volume merged data set contains order volume data greater than or equal to , and the difference between the order volume data and the order volume data at the adjacent time point on the left or right side of the combined order volume data set is greater than or equal to When the second material position code data set is updated according to the second final material quantity and the second final material data ratio, the second updated material position code data set is obtained.

5. A system for implementing the time-controlled cloud warehouse material storage location dynamic management method as described in any one of claims 1-4.

Images